Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You and Your Team.

Learn More →

Digital twin-based sustainable intelligent manufacturing: a review

Digital twin-based sustainable intelligent manufacturing: a review Adv. Manuf. (2021) 9:1–21 https://doi.org/10.1007/s40436-020-00302-5 1 1 Bin He Kai-Jian Bai Received: 29 June 2019 / Revised: 4 September 2019 / Accepted: 26 March 2020 / Published online: 4 May 2020 The Author(s) 2020 Abstract As the next-generation manufacturing system, 1 Introduction intelligent manufacturing enables better quality, higher productivity, lower cost, and increased manufacturing As an upgrade to manufacturing industries, Industry 4.0 flexibility. The concept of sustainability is receiving proposed next-generation intelligent manufacturing to increasing attention, and sustainable manufacturing is achieve high adaptability, rapid design changes, digital evolving. The digital twin is an emerging technology used information technology, and more flexible technical in intelligent manufacturing that can grasp the state of workforce training. Manufacturing technologies include intelligent manufacturing systems in real-time and predict cyber-physical systems [1, 2], Internet of Things (IoT) [3], system failures. Sustainable intelligent manufacturing and cloud computing [4, 5]. In the Industry 4.0 era, intel- based on a digital twin has advantages in practical appli- ligent manufacturing has received increasing attention cations. To fully understand the intelligent manufacturing owing to the need for sustainability. Intelligent manufac- that provides the digital twin, this study reviews both turing should consider sustainability aspects [6], and technologies and discusses the sustainability of intelligent intelligent manufacturing equipment, such as computerized manufacturing. Firstly, the relevant content of intelligent numerical control (CNC) machine tools and industrial manufacturing, including intelligent manufacturing equip- robots [7–10], should have more intelligence, which aid ment, systems, and services, is analyzed. In addition, the their better integration into the intelligent manufacturing sustainability of intelligent manufacturing is discussed. closed loop to complete manufacturing tasks. Intelligent Subsequently, a digital twin and its application are intro- manufacturing systems are showing a diversified trend, and duced along with the development of intelligent manu- an increasing number of them are being developed for facturing based on the digital twin technology. Finally, specific tasks and applied to actual production, thereby combined with the current status, the future development greatly improving the level of intelligence [11–16]. New direction of intelligent manufacturing is presented. services for intelligent manufacturing are explored and improved, and the sustainable collaborative manufacturing Keywords Intelligent manufacturing  Digital twin  system platform integrates customers, experts, and enter- Advanced manufacturing  Industry 4.0  Sustainable prises and provides them with personalized services manufacturing [17–24]. A complete real-time presentation of the state of the intelligent manufacturing system is a challenge; however, the emergence of a digital twin has made it possible to solve this problem [25–27]. Manufacturing systems can & Bin He mehebin@gmail.com monitor physical processes, create a digital twin in the physical world [28], receive real-time information from the Shanghai Key Laboratory of Intelligent Manufacturing and physical world for simulation analysis, and make informed Robotics, School of Mechatronic Engineering and decisions through real-time communication and collabo- Automation, Shanghai University, Shanghai 200444, ration with humans. The combination of digital twin and People’s Republic of China 123 2 B. He, K.-J. Bai intelligent manufacturing makes manufacturing smarter, 2 Digital twin more efficient, and more convenient. This paper is devoted to reviewing digital twin-driven 2.1 Concept of digital twin sustainable intelligent manufacturing, which summarizes the intelligent manufacturing that uses a digital twin from a The idea of a digital twin was described as an information sustainable perspective. Firstly, the concept and application mirror model by Grieves [29]. A digital twin is a digital of a digital twin are introduced along with the application replica of a living or non-living physical entity. It enables a of the digital twin from three aspects: product design, seamless transfer of data by connecting physical and virtual manufacturing, and product service. Secondly, digital twin- worlds [30], thereby allowing virtual entities to exist driven sustainable intelligent manufacturing is introduced simultaneously with physical entities. The definition of the from three aspects: intelligent manufacturing equipment, digital twin technology emphasizes two important features. system, and service (see Fig. 1). Firstly, each definition emphasizes the connection between Sustainable intelligent manufacturing contains sustain- the physical model and the corresponding virtual model or able intelligent manufacturing equipment, system, and virtual counterpart. Secondly, the connection is established service, which support each other. Intelligent manufactur- by using sensors to generate real-time data [31, 32]. ing equipment is introduced from two dimensions: intelli- Table 1 lists some definitions of a digital twin in Refs. gent manufacturing unit and line. From the perspective of a [30, 31–37]. life cycle, the intelligent manufacturing system is divided Based on the definitions provided in the abovemen- into four parts: design, production, logistics and sales. tioned literature, a digital twin is a real-time digital Intelligent manufacturing services are introduced from reproduction of physical entities. It faithfully maps physi- three aspects: product development, manufacturing, and cal objects and can not only describe physical objects, but after-sales services. Finally, the development trend of also optimize physical objects based on models. intelligent manufacturing is summarized from three aspects: framework, enabling technology and application 2.2 Applications of digital twin of sustainable intelligent manufacturing. The framework of sustainable intelligent manufacturing includes sustainable The digital twin technology has recently received wide- intelligent design, comprehensive sustainability, human- spread attention. The world’s most authoritative IT machine collaboration, sustainable intelligent manufactur- research and advisory firm, Gartner, chose digital twin as ing for product life cycle, across enterprise value chain, for one of the top ten strategic technology trends since 2016. product environmental footprint, and sustainable intelligent Lockheed Martin, the world’s largest weapon manufac- manufacturing equipment, system, and service. The turer, listed digital twin as the first of six top technologies enabling technology of sustainable intelligent manufac- in the defense and aerospace industry in 2017. The China turing includes digital twin-based big data-driven, artificial Association for Science and Intelligent Manufacturing intelligence-driven, and Internet of Things (IoTs)-driven academic consortium also selected digital twin intelligent sustainable intelligent manufacturing. manufacturing assembly as one of the top 10 scientific and technological progresses in intelligent manufacturing in 2017. A digital twin chooses products as the main research object. Digital twin technology exists in different stages of Sustainable intelligent the product life cycle, and different elements are intro- manufacturing equipment duced at each stage. Therefore, digital twin has different performance forms. This section introduces the digital twin application from three aspects: product design, manufac- Contain turing and product service. Support Support Sustainable intelligent 2.2.1 Digital twin in product design manufacturing The digital twin application in product design is mainly Contain Contain based on digital twin research product design methods to make it more efficient. This includes digital design and Support Sustainable intelligent Sustainable intelligent digital simulation. manufacturing system manufacturing service Fig. 1 Three aspects of intelligent manufacturing 123 Digital twin-based sustainable intelligent manufacturing: a review 3 Table 1 Definition of digital twin in the literature Definition Refs. Digital twin is an integrated multi-physics, multi-scale, probabilistic simulation of completed vehicles Glaessgen and or systems that use the best physical models, sensor updates, fleet history, etc. to reflect the life of Stargel [33] their corresponding flying twin Digital twin is digital copies of biological or non-biological physical entities. By bridging the physical Abdulmotaleb [30] and virtual worlds, data is seamlessly transferred, allowing virtual entities to exist simultaneously with physical entities A coupled model of real machines running on a cloud platform that uses a combination of data-driven Lee et al. [34] analysis algorithms and other available physics knowledge to simulate health conditions Real-time optimization using digital copies of physical systems Soderberg et al. [35] The dynamic virtual representation of a physical object or system throughout its lifecycle, using real- Bolton et al. [36] time data to achieve understanding, learning, and reasoning Digital twin uses physical data, virtual data and interactive data between them to map all components Tao et al. [37] in the product lifecycle 2.2.1.1 Digital design Modeling tools are used to build build a solid model, which is applied to the product pro- virtual models of the products to visually express their cessing and assembly to achieve precise production con- physical parameters. A product design method based on a trol. This part includes the production process simulation, digital twin was proposed, and the framework of the digital digital production line, and equipment status monitoring. twin product design was analyzed [37]. A new cloud-based digital twin approach was developed for network physics 2.2.2.1 Production process simulation Before product cloud manufacturing platforms to reduce computing production, the production process can be simulated by resources and enable an efficient interaction between users means of virtual production, and productivity and effi- and physical machines [38]. Product design, manufactur- ciency can be comprehensively analyzed. A new method ing, and service approach were proposed, driven by a was proposed for resource supply and demand matching digital twin to make the product design, manufacturing, manufacturing based on complex networks and IoTs to and service more efficient [39]. Schleich et al. [40] pro- realize the intellectual perception and access to manufac- posed a comprehensive reference model based on the turing resources [44]. Bilberg and Malik [45] applied a concept of skin model shape, which corresponded to digital twin to the assembly unit to create a digital twin physical products in design and manufacturing. The digital model that extended the use of virtual simulation models twin-driven product design method enables researchers to developed during the production system design phase to quickly find design flaws and improve design efficiency implementation control, human and machine task assign- when designing products. ment, and task sequencing. Um et al. [46] proposed a universal data model based on a digital twin to support 2.2.1.2 Digital simulation The adaptability could be plug-and-play in modular, multi-vendor assembly lines. A verified at the design stage through a series of simulation digital twin with intelligent manufacturing services was experiments to verify the product performance. Haag and combined to produce more sensible manufacturing plan- Anderl [41] developed a network physical bending beam ning and precise production control [47]. A digital net- test rig to demonstrate the digital twin concept. A modular work-based manufacturing network physics system was approach was studied to build a digital twin and make the proposed to control intelligent workshops in parallel under corresponding changes [42]. Using the built-in flexible a large-scale personalization paradigm [48]. A factory digital twin helps designers quickly evaluate different network physical integration framework was proposed for designs and find design flaws. A method was proposed for digital-based systems to address the problems faced by modeling and operating a digital twin in a manufacturing digital factories and shift the current state of digital fac- environment [43]. At the design stage, researchers use tories to intelligent manufacturing [49]. simulation experiments to verify the product, which greatly improves the product adaptability. 2.2.2.2 Digital production line All the elements of the production stage are integrated into a closely coordinated 2.2.2 Digital twin in manufacturing production process through digital methods to achieve an automated production process. The digital twin model was The digital twin application in manufacturing is mainly studied using the digital twin technology to control robots based on the virtual simulation model of a digital twin to to automatically assemble large spacecraft components 123 4 B. He, K.-J. Bai [50]. Digital twin modeling and data fusion issues at each generation. The operation mode of the device can be steel product life cycle stage were explored to achieve optimized according to the state data of the virtual model to complex tasks [51]. A digital twin-based approach was reduce failure rate and improve stability. studied for the rapid personalization of insulated glass The application of product services aims to combine a production lines [52]. Moreover, a framework was pro- digital twin with other technologies, such as virtual reality, posed for intelligent production management and control to form a new model of digital twin-based services. In the methods using the digital twin technology and applied to manufacturing sector, Pairet et al. [57] introduced the assembly shops for complex products [53]. A digital twin Offshore Robotics for the Certification of Assets or ORCA method was proposed for the rapid personalization of Hub simulator for training and testing human-machine automated flow shop manufacturing systems, combining collaboration solutions that unify three types of home- physical system modeling and semi-physical simulation to made systems on the marine digital twin platform. Voinov generate authoritative digital designs of the system during et al. [58] studied a method for providing reliable man- the pre-production phase [54]. Liau et al. [55] applied a agement of complex IoT systems. Uhlemann et al. [59] digital twin to the injection molding industry, modeling all studied the concept of a learning factory based on the stages of injection molding as virtual models to achieve a advantages of real-time data acquisition and subsequent two-way control of physical processes. simulation data processing. Meanwhile, Coronado et al. [60] developed and implemented a low-cost manufacturing 2.2.2.3 Equipment status monitoring The production execution system (MES) and an android operating system process can be monitored visually by collecting the real- (OS) application to generate a shop floor digital twin model by collecting machine data enabled by MES and MTCon- time operation data of production equipment. The abnor- mal equipment must be dealt with and adjusted in time to nect. Schluse et al. [61] introduced an experimental digital optimize the production process. Botkina et al. [56] intro- twin to create interactions in different application scenarios duced digital twin data formats and structures for cutting and provided a new foundation for simulation-based inte- tools, information flow, and data management and applied grated systems engineering. Macchi et al. [62] explored the that digital twin to improve machining solutions optimized role of a digital twin in asset lifecycle management. Kunath for process planning. When the digital twin application is and Winkler [63] discussed the conceptual framework and applied in the production workshop, the state of the potential applications of digital twin decision support sys- machines and products in the workshop is reflected in the tems that were eager to manufacture systems in the order virtual model in real-time, thereby making the manufacture management process. Biesinger et al. [64] introduced the of the product more intelligent. digital twin of the body-in-white production system to achieve a rapid integration of new cars. Vacha´lek et al. [65] 2.2.3 Digital twin in product service introduced a digital twin and supported existing production structures and the most efficient use of resources in the The digital twin application in fault prediction is based on automotive industry through digital production and the virtual simulation model of a digital model based on a enhanced production and planning strategies. Uhlemann digital twin. The virtual simulation model faithfully reflects et al. [66] also introduced multimodal data acquisition the state of the solid model. The virtual simulation model methods to ensure the most accurate synchronization of will generate faults when the solid model fails. This is the digitally generated network physical processes with real fault detection. The virtual simulation model judges whe- physical models. Tao and Zhang [67] studied the digital ther the physical model will generate a fault based on the twin workshop based on a digital twin and its operation real-time state data and can effectively reduce the failure mechanism and implementation method. In the manufac- rate. This part includes product fault warning and mainte- turing process, the carbon emission problem in the manu- nance and production index optimization. facturing process should also be considered in addition to ensuring the manufacturing stability [68]. 2.2.3.1 Product fault warning and maintenance By The progress made by the digital twin technology in the reading the real-time parameters of the sensors or control research of medical, sports, manufacturing, etc., has led to systems of intelligent industrial products, a visual remote the continuous development of these industries. In the monitoring model is built to analyze the state of products medical field, Martinez et al. [69] studied the impact of with artificial intelligence and make early warning in time. digital twin on service business model innovation by fully Meanwhile, maintenance strategies are given to reduce understanding how to set up, implement, and use digital losses. Fault detection and health management can be health and understanding the impact of digital health in the implemented for different devices based on digital enterprise services business. A cloud healthcare system 123 Resource element Interconnection Fusion sharing System integration Emerging business Digital twin-based sustainable intelligent manufacturing: a review 5 System level framework was proposed for digital twin healthcare aimed at achieving the goal of personal health management by Collaboration integrating medical physics and virtual space [70]. In the field of sports, Balachandar and Chinnaiyan [71] used a Enterprise digital twin in the field of sports to make virtual connec- Workshop tions and monitor athletes in the lab. Unit 2.2.3.2 Production index optimization By reading and Device Life cycle analyzing the status data of products, the configuration Design Production Logistics Sales Service parameters of products are modified to improve their per- formance and optimize the production indexes. Guivarch et al. [72] proposed a new method for developing a digital twin for helicopter power systems to better predict the service life of mechanical components. A general digital twin model was established for complex devices. A method was also proposed for using the digital twin to drive pre- Intelligent feature diction and health management to improve the accuracy and efficiency of forecasting and health management [73]. Fig. 2 System architecture of intelligent manufacturing [86] Lynn et al. [74] proposed a network-, physical system- equipment, features, and others involved in intelligent based manufacturing system for implementing process manufacturing from three dimensions, namely life cycle, control and optimization. A multi-domain unified modeling system level, and intelligent features [86]. method was established for the digital twin to study its The intelligent manufacturing technology is the deep computer numerical control (CNC) machine tools and integration and integration of the information technology, make these tools more intelligent while optimizing the intelligent technology, and equipment manufacturing tech- operating mode, reducing the sudden failure rate, and nology. The intelligent manufacturing technology is based improving the CNC machine tool stability [75]. Dynamic on advanced technologies, such as the modern sensing Bayesian networks were used to build multi-function technology, network technology, automation technology, diagnostic and predictive probabilistic models to achieve a and anthropomorphic intelligence technology. The intelli- digital twin [76]. gent manufacturing technology can realize intelligent design process, intelligent manufacturing process, and intelligent manufacturing equipment through intelligent sensing, 3 Digital twin-driven sustainable intelligent human-computer interaction, decision making, and execu- manufacturing tion technology. In addition, the concept of sustainable [87, 88] manufacturing is receiving increasing attention, and Research on digital twin-driven intelligent manufacturing is intelligent manufacturing should be sustainable [89]. a hot trend and has achieved good results in life cycle man- Intelligent manufacturing plays a pivotal role in next- agement, data fusion, rapid production, intelligent forecast- generation manufacturing, especially in high-end manu- ing, and sustainable manufacturing [77–85]. Intelligent facturing; hence, the world’s traditional manufacturing manufacturing is a deep integration between the artificial powers and new manufacturing powers have come up with intelligence technology and the advanced manufacturing plans to develop intelligent manufacturing. Table 2 pre- technology. The new generation artificial intelligence tech- sents the intelligent manufacturing development plans of nology mainly includes cloud computing, IoTs and big data, some countries and organizations [90–95]. This section among others. Intelligent manufacturing brings great chan- describes intelligent manufacturing in terms of intelligent ges to all aspects of the manufacturing industry, making it manufacturing equipment, intelligent manufacturing sys- capable of learning, generating, and using knowledge. The tems, and intelligent manufacturing services. digitalization, networking, and intelligence of intelligent manufacturing have been balanced. 3.1 Sustainable intelligent manufacturing Intelligent manufacturing is a broad manufacturing equipment category that uses computer integrated manufacturing, high levels of adaptability and rapid design changes, digital Intelligent manufacturing equipment refers to manufac- information technology, and more flexible technical turing equipment with sensing, analysis, reasoning, deci- workforce training. Figure 2 shows the system architecture sion-making, and control functions. It is a deep integration of intelligent manufacturing, which describes the activities, 123 6 B. He, K.-J. Bai Table 2 Main intelligent manufacturing development plans in the world Country/organization Intelligent manufacturing development plan Refs. Germany Industry 4.0 [90] European Union Horizon 2020 [91] Japan Industrial Value Chain Initiative [13] United States Advanced Manufacturing Partnership [92] South Korea Manufacturing Industry Innovation 3.0 strategy [90] United Kingdom Modern industrial strategy [93] France New France Industrial [94] China Made in China 2025 [95] of the advanced manufacturing technology, information [99]. Yang et al. [100] proposed a method to accurately technology, and intelligent technology. The development determine the critical point of thermal coupling deforma- of intelligent manufacturing equipment reflects the level of tion of machine tools. A two-dimensional thermal error the manufacturing industry. Intelligent manufacturing compensation method was proposed for the thermal error equipment can be classified into two types: intelligent compensation of CNC machine tools, which greatly manufacturing unit and intelligent manufacturing produc- improved the compensation effect of the workbench [101]. tion line. An improved energy consumption model that effectively reflected the relationship between processing parameters 3.1.1 Intelligent manufacturing unit and energy consumption in machining processes was pro- posed based on empirical models and contributed to sus- The intelligent manufacturing unit is an independent pro- tainable manufacturing [102]. Krimpenis and Fountas cessing equipment in intelligent manufacturing, which is [103] studied the multi-objective machining optimization the smallest processing unit for intelligent manufacturing. problem based on a genetic algorithm and examined the A knowledge-driven digital twin manufacturing unit that influence of the key machining parameters of CNC supports self-manufacturing for the overall framework of machining operations. The different stages of the machine intelligent manufacturing was proposed [96]. Lohtander tools were introduced [104], including Machine 1.0, et al. [97] studied the digital twin technology based on Machine 2.0, Machine 3.0, and detailed key features of micro-manufacturing units. The intelligent manufacturing Machine 4.0, such as network physics machines and ver- unit contains various processing equipment, such as tical and horizontal integrated machine tools. Jeon and Ha machine tools, robots, and special equipment. [105] proposed a general method for generating the velocity distributions for acceleration and deceleration 3.1.1.1 Machine tools and equipment The machine tool techniques for CNC machine tools. A proportion integra- is mainly used to perform machining tasks. From the first tion differentiation iterative learning controller for the machine tool to the present, the machine tool has achieved CNC machine tools to perform repetitive tasks was pro- great development. The style, type, and technology also posed in Ref. [106]. Keller et al. [107] conducted a study experienced revolutionary innovation. on the reliability and maintainability of CNC machine tools CNC machine tools are automatic machine tools with a after analyzing the field fault data of 35 CNC machine tools. Yamato et al. [108] built an automatic flutter sup- program control system, which could solve the processing problems of complex and precision products and represent pression system for parallel turning, integrating on-line the development trend of modern machine tools. Compared flutter monitoring based on the cutting force estimation. with traditional machine tools, CNC machine tools have At present, the research on CNC machine tools mainly the following advantages: high processing precision, focuses on fault diagnosis, error compensation, parameter stable processing quality, high productivity and flexibility. optimization, etc., which greatly improve the fault diag- Many researchers conducted intelligent manufacturing-re- nosis efficiency and the machining accuracy of CNC lated research on CNC machine tools. machine tools. The research on CNC machine tools would A fault diagnosis strategy based on cascade faults was also be extended to online real-time monitoring of prod- proposed to ensure the safe operation of CNC machine ucts, smart machine tools, and green manufacturing. tools [98]. The state-based monitoring architecture was The cold heading machine is a type of machine tool that used for the alarm management of CNC machine tools uses a mold and a punch to make a part from a wire. The 123 Digital twin-based sustainable intelligent manufacturing: a review 7 force driven by the punch pushes the material from the the exchange of programming information for different mold into a new shape [109]. Li et al. [110] revealed the processing projects, and integration is difficult [117]. mechanical behavior and the dynamic response of the cold Slavkovic et al. [118] introduced an indirect method for heading machine and designed a new type of cold head industrial robot programming for machining tasks, saving force polyvinylidene fluoride piezoelectric film force sen- machining project information in a standard for exchange sor. The sensor has excellent dynamic performance and of product model data-numerical control format for an easy high precision measurement deformation ability. The exchange between different users for machining. A tool multi-station cold heading machine is an automated, high- path generation method based on a network model was precision forming equipment widely used in manufacturing studied and integrated into the offline robot programming for the mass production of bolts and nuts. The reliability of system to provide a comprehensive solution for robot the cold heading machine would affect the quality of the modeling, simulation, and tool path generation [119]. Some processed product and the processing efficiency [111]. researchers used modeling software to simulate the struc- Cold heading machines should meet the needs of a low- ture of industrial robots using the finite element method. carbon economy [112]. The research team of Shanghai Berg et al. [120] studied an interaction concept that uses University developed the first servo cold heading machine tracking of gestures and eyes to achieve a path to the tool in China, which opened a new direction for the cold robotic system and through projection to achieve a channel heading machine tool development. from the robotic system. Norrlof [121] studied an adaptive iterative learning control algorithm based on the estimation 3.1.1.2 Industrial robotics The automation and intelli- process and quadratic criterion optimization using the Kalman filter and successfully applied in industrial robots. gence of manufacturing are inseparable from the applica- tion of industrial robots, which are widely used in all In addition, research on underactuated robots has made aspects of manufacturing. With the development of the great progress [122–124]. manufacturing industry, the types and functions of indus- The research on industrial robots makes industrial robots trial robots are becoming more diverse. In the process of more competitive in an application. With higher precision, traditional manufacturing to intelligent manufacturing, smaller error, more reasonable structure, more convenient industrial robots would also usher in a new and greater programming, and more friendly human-computer inter- development. action, industrial robots are becoming increasingly impor- In recent years, an increasing number of researchers tant in industrial applications. have been working on industrial robots. Some industrial robots must be taught before application to ensure effi- 3.1.1.3 Special equipment Special equipment includes mining machinery, oil drilling equipment, special metal- ciency. A scheme was proposed to minimize external force estimation errors and reduce guidance task interference by lurgical equipment, and other special equipment. using virtual mass and virtual friction models for the Researchers studied the use of hydrogen as a fuel in mining manual teaching of industrial robots without force sensors machinery to meet sustainability requirements [125]. Islam [113]. The accuracy of industrial robots is affected by the et al. [126] studied the vibration problem of holding oil and uncertain parameters of link size and joint clearance gas through simulation experiments. Andreev et al. [127] deviation. Pe´rez et al. [114] studied the synergy between studied the technical parameters of the complex non-fur- virtual reality and robots to create a fully immersive nace treatment of blast furnace cast iron by the pulsating environment based on virtual reality, thereby improving the inert gas injection method, which significantly increased efficiency of the training and simulation process and pro- the operation resistance of metallurgical equipment. viding a cost-effective solution. Industrial robots can sub- mit efficiency and precision through teaching and training. 3.1.2 Intelligent manufacturing production line In addition, they may also experience problems, such as loss of posture during exercise. An interval method was The intelligent manufacturing line consists of a series of used to analyze the motion response of industrial robots precisely arranged intelligent manufacturing units that with uncertain, but bounded parameters [115]. A path could be processed more flexibly and intelligently. Indri planning method was proposed to ensure that the floating et al. [128] researched on a new paradigm of production base reached the predetermined attitude when the end-ef- lines based on three different sensor development methods fector of the space-based n-joint manipulator moved to the characterized by a high degree of flexibility. The thin-film predetermined position [116]. An improved omnidirec- solar cell production line production capacity is low. The tional mobile industrial robot tracking and localization low-pressure chemical vapor deposition (LPCVD) is the algorithm could be proposed to solve the problem of atti- main process leading to low productivity. To solve this tude loss in motion. Industrial robots are inconvenient in problem, a method of prioritizing the LPCVD process work 123 8 B. He, K.-J. Bai list was proposed, which greatly increased the production palm-based biomass [134]. A mesoscale simulation method capacity and prolonged the service life of the device [129]. was proposed for heavy oil petroleum structural units and A task scheduling strategy was proposed based on a hybrid dissipative ion dynamics and used to simulate various heuristic algorithm after studying the task scheduling heavy oil petroleum systems [135]. strategy of fog computing, which solved the problem of Research on process manufacturing systems focused on limited computing resources and high energy consumption the petrochemical industry. Future research will focus on in intelligent production lines [130]. A large number of intelligence, safety, and efficiency. simulation experiments are required to reduce cost and save time before a production line is put into use. The 3.2.2 Discrete manufacturing system intelligent production line fully verifies the availability of the production line by communicating with the external Discrete manufacturing systems refer to products that are real programmable logic controller. The genetic algorithm- made up of many independently machined parts ultimately based approach is applied to the overhead shuttle (OHS) assembled into a system of products. This section intro- system design of flat panel display production lines [131]. duces discrete manufacturing systems from the perspective To solve the problem of low efficiency and poor model of the product life cycle, from design, production, logistics, quality of the production line modeling method, the con- and sales. cept of the digital twin production line was proposed, and the real-time modeling and simulation method of the digital 3.2.2.1 Design The design could be divided into con- twin production line were studied [132]. Its effectiveness ventional and innovative designs. was verified on the product assembly line. Research on (i) Conventional design intelligent manufacturing production lines still mainly Given that existing computer-aided design systems do not focused on improving productivity. However, a few studies effectively provide the proper use of geometric tolerances, also combined virtual platforms, such as production lines Lemu [136] proposed an algorithm development solution and digital twin, which will be a research direction in the to achieve appropriate tolerances and conditions for use future. during the design specification phase. The facial prosthesis system based on computer-aided design/computer-aided 3.2 Sustainable intelligent manufacturing system manufacturing (CAD/CAM) was developed for the manu- facture of facial prosthesis [137]. Lv and Lin [138] The intelligent manufacturing system is a human-machine developed a real-time operational planning system in a integrated intelligent system composed of intelligent distributed manufacturing network that significantly machines and experts. According to different processing reduced planned workload. Gu et al. [139] studied the methods, intelligent manufacturing systems could be divi- design of a multi-stage reconfigurable manufacturing sys- ded into process manufacturing systems and discrete tem and measured the production loss, throughput stabi- manufacturing systems. According to the product life cycle lization time, and total production shortage time. Maturana process, discrete intelligent systems could be introduced et al. [140] proposed MetaMorph, an adaptive multi-agent from four aspects: design (e.g., low carbon design [133]), manufacturing system architecture for dynamically creat- production, logistics, and sales. This section introduces ing and managing agent communities. intelligent manufacturing systems. (ii) Innovative design 3.2.1 Process manufacturing system He et al. [141–147] used intelligent feature- and model- based methods, spatial matrix, parametric, and other Process manufacturing refers to the process in which the methods for intelligent design. The intelligent design sys- processed object continuously passes through the produc- tem was used in the design process of the product, making tion equipment, and the raw materials are physically or the design process more efficient with a higher precision chemically changed to finally obtain the product. The [148], a smaller error, and more sustainability [149] and process manufacturing system refers to the production generally requiring a computer-aided design system. A system applied to the process manufacturing process and is low-carbon design method based on carbon footprint was widely used in the petroleum and chemical industries. also proposed for product design [150–154]. Gregor et al. Three generations of systems can produce three products at [155] created the Zilina Intelligent Manufacturing System the same time, but their processing units are susceptible to expected to create an integrated collaborative environment failure. Accordingly, an integration framework was pro- that connected real, digital, and virtual. A low-carbon posed to solve the research on the three generations of 123 Digital twin-based sustainable intelligent manufacturing: a review 9 design method based on carbon footprint is also proposed [167] and in rationalizing the processing steps to make the for product design. process meet sustainability requirements. Research on intelligent design systems has made the Helo et al. [168] developed a cloud-based distributed design process more standardized, thereby greatly reducing manufacturing execution system to address the needs and challenges of managing distributed manufacturing in a workload and improving efficiency [156]. However, the current intelligent design system still has some shortcom- multi-company supply chain. The architecture of intelli- gent manufacturing systems was proposed based on dis- ings. The current intelligent design system is not intuitive in the design process. Therefore, integration with the vir- tributed artificial intelligence to shorten the product development cycle [169]. The structure of the intelligent tual reality technology and the collaborative design [157] would be the key research direction of the next stage. chemical industry network physical system was proposed and applied to the intelligent distillation tower [170]. The operation results showed that stability and robustness met 3.2.2.2 Production Intelligent production systems are the requirements. used in the processing of products, optimizing the pro- Resource-intelligence and access systems were devel- cessing steps of products, and improving the resource uti- oped based on the IoTs to realize the manufacturing model lization, adaptability, and robustness of manufacturing of cloud manufacturing [171]. Jain et al. [172] developed a systems. Manufacturing could be divided into two pro- digital twin model that implemented an estimate of the cesses: machining and assembly. measurable characteristic output of a photovoltaic energy (i) Machining conversion unit. Based on this model, 10 different faults, power converters, and electronic sensor faults were Simeone et al. [158] proposed an intelligent cloud manu- facturing platform for sheet metal cutting services that detected and identified in the photovoltaic energy conver- increased the utilization of supplier resources to 92.3%. sion unit. The detection and identification times were less The intelligent immune system for energy-saving manu- than 290 ls and 4 ms, respectively. Moreover, the fault facturing can achieve an energy savings of approximately detection and recognition time in the distributed photo- voltaic panels were less than 80 ms and 1.2 s, respectively. 30% in the factory and increase the production efficiency by more than 50% [159]. Stadnicka et al. [160] analyzed (ii) Assembly the role of humans in intelligent manufacturing systems An IoT intelligent assembly system framework was pro- and proposed innovative ways to learn how to simulate a posed based on the information and communication tech- virtual reality to transfer knowledge of intelligent manu- nology, sensor networks, and radio frequency identification facturing systems. In addition, considering the low carbon and applied to the assembly process of mechanical prod- requirements in the production process will save more ucts [173]. Research on the intelligent production system energy [161]. Tao et al. [162] proposed a cloud manufac- based on the agent technology can effectively improve the turing service system and a framework based on the IoTs system adaptability. An agent-based manufacturing system and cloud computing. They also analyzed the relationship architecture was proposed for application to hybrid multi- between the two. An advanced manufacturing IoT intelli- product production to improve the adaptability and gent manufacturing platform was designed based on IoTs, robustness of the manufacturing system [174]. Chaplin cloud computing, big data analysis, network physics sys- et al. [175] designed evolvable assembly systems using the tem, and prediction technology. This platform was then intelligent agent technology and data distribution services. applied to the bumping process of semiconductor compa- Intelligent production systems can be developed based on nies. The application results showed that the platform could distributed technologies to shorten the development cycle. perform comprehensive inspections in production [163]. Intelligent production systems for specific product research He et al. [164] put forward a new method of constraint meet specific production needs. Wang [176] introduced the mechanism function synthesis based on system dynamic general framework of a zero-defect manufacturing system programming, which was applied to the offshore platform and introduced the application of zero-defect manufactur- jacking system. A network physics system based on multi- ing methods to create zero-defect products. The network agent technology was developed and applied to the man- physical system architecture of the intelligent manufac- ufacturing workshop to improve the reconfigurability and turing workshop was proposed, and it verified the feasi- responsiveness of the workshop [165]. Lee et al. [166] bility of the architecture on a small flexible automated proposed the industrial IoT suite to run high value-added production line [177]. A custom-oriented intelligent man- manufacturing processes, implement intelligent production, ufacturing system was proposed, and a customizable candy and achieve re-industrialization in Hong Kong. These production system was established [178]. A labeling and studies effectively improved resource utilization and pro- management framework was proposed for steel label duction efficiency. Other studies focused on sustainability 123 10 B. He, K.-J. Bai characters, while a method for the online monitoring and sales services (see Fig. 3). Sustainable intelligent manu- tracking of marker characters based on machine vision was facturing service contains product development, manufac- proposed to realize information management and intelli- turing, and after sales services, which support each other. gent manufacturing for steel manufacturing [179]. A knowledge-based intelligent system for diagnosing web- 3.3.1 Product development services based management was studied, and its defects increased the wafer manufacturing throughput [180]. Specific intel- The product development service in the intelligent manu- ligent production systems enable agile manufacturing and facturing service mainly serves the whole process of pro- reduce the probability of defects. duct development, making the development process simple and efficient. This part includes collaborative design ser- 3.2.2.3 Logistics The intelligent logistics system is vice, product customization service, and so on. applied to the traceability of product processing and the management of product logistics information. Strandhagen 3.3.1.1 Collaborative design service Collaborative et al. [181] studied Industry 4.0 for manufacturing logistics. design service mainly provides a platform to integrate The study of four Norwegian manufacturing companies people with design requirements and capabilities. When showed that the practicality of Industry 4.0 in manufac- someone has design requirements, they can publish the turing logistics depended on the production environment. A requirements to the platform. People with design capabil- food traceability network physical system method based on ities can undertake the requirements and participate in the intelligent value stream was proposed to improve the effi- design together. Zhang et al. [190] proposed an intelligent ciency of the food traceability system [182]. Maoudj et al. manufacturing integration system that was applied to the [183] developed a distributed multi-agent system for projects they participated in and achieved good results. He scheduling and controlling robotic flexible assembly units. et al. [191] proposed sustainable supply chain design The production data are collected in real time for product model. Sun et al. [192] studied the security of networked traceability based on the intelligent logistics system control systems. McFarlane et al. [193] explored the impact developed by the radio frequency identification technology of automatic identification systems on the intelligent con- [184–188], realizing the production management and trol of manufacturing plants. To solve the layout opti- dynamic scheduling of the workshop. The intelligent mization problem of the multi-module satellite equipment, logistics system realizes the logistics function in intelligent a two-system co-evolution algorithm based on the bode manufacturing and can track the status and logistics coevolution framework was proposed [194]. Malik and information of the product in real time to realize dynamic Bilberg [195] proposed a digital and physical medical scheduling. workspace that combined the digital and physical worlds for collaborative design. To solve the problems in dis- 3.2.2.4 Sales The intelligent sales system is used to sell tributed collaborative design system of complex products, a manufactured products and manage sales information for group global search and negotiation algorithm based on intelligent sales. A vehicle sales integrated management fuzzy matter-element particle swarm optimization was system was studied. It can manage vehicle sales in a unified proposed [196]. manner and input real-time information into mobile devi- ces with high security [189]. Take the marketing module of a company’s collabora- Product development service tive manufacturing system as an example. The module has the functions of entering order information, querying order information, and managing customer information for Contain entering and managing order information. After the sales- person obtains the order, the order information is entered Support Support into the system, and the order information could then be Sustainable intelligent manufacturing service queried and managed. 3.3 Sustainable intelligent manufacturing services Contain Contain Support Intelligent manufacturing services for intelligent manu- Manufacturing service After sales service facturing have a wide range of applications. This section introduces intelligent manufacturing services from three aspects: product development, manufacturing, and after Fig. 3 Three aspects of intelligent manufacturing service 123 Digital twin-based sustainable intelligent manufacturing: a review 11 3.3.1.2 Product customization service A large-scale manufacturing service mainly serves the whole process of personalized production framework based on the concept product processing and manufacturing and provides ser- of Industry 4.0 was proposed and realized large-scale vices, such as monitoring, scheduling, online monitoring, personalized production in industrial practice [197]. Rød- sustainable manufacturing, and real-time warning for pro- seth et al. [198] developed a new model of deep digital duct processing. Kim and Hwangbo [216] developed an maintenance based on network physics systems and intelligent real-time early warning system for plastic film maintenance theory to achieve integrated planning. To production with a prediction accuracy close to 100%. achieve a new approach to personalization and cus- tomization, researchers are rapidly deploying resources 3.3.2.2 Intelligent control An intelligent decision sup- based on manufacturing services [199–204]. port system architecture based on radio frequency identi- fication was proposed for processing production 3.3.1.3 Other services The performance estimation monitoring and scheduling in a distributed manufacturing model-based optimization algorithm was studied [205] and environment [217]. Tan et al. [218] proposed an embedded applied to large-scale complex manufacturing system adaptive network service framework [219] and applied this simulations [206], reducing the run time by more than 7%. to networked manufacturing systems. A browser-server- A product lifecycle management application framework terminal model is proposed to realize remote control of based on the digital twin was proposed [207]. A view- embedded terminal devices, and a new method of remote based 3D CAD model reuse framework was proposed to control of embedded terminal devices is proposed [220]. enable the effective reuse of 3D CAD models in the pro- Theorin et al. [221] proposed a line information system duct life cycle [208]. He et al. [209] used the low-carbon architecture for flexible plant integration and data appli- concept to optimize the structure of the product to meet the cations. A mapping-based computational experimental low carbon requirements. Bodrow [210] proposed an approach was proposed and used to solve the complexity of application scenario for knowledge visualization to test the the construction and development of the manufacturing expertise and demonstrated its usefulness in intelligent service ecosystem and analyze the evolution of the manu- software applications for process control. Giret et al. [211] facturing service ecosystem [222]. proposed a specific software engineering approach to help developers develop a sustainable intelligent manufacturing 3.3.2.3 Collaborative manufacturing In addition, for the system, called Go-green ANEMONA. A graph-based problem of close contact between users and manufacturers, knowledge reuse method was proposed to support knowl- a synergistic-based service combination approach can be edge-driven decision making in product development, used to connect users to manufacturers and make full use of reuse the knowledge already in the manufacturing industry, resources to create a collaborative manufacturing platform and improve the product innovation quality [212]. [223–228]. Through research on intelligent development services, Take an equipment collaborative manufacturing system the running time of the complex manufacturing system as an example to illustrate the intelligent manufacturing simulation is shortened, and the accuracy and the real-time service [229]. The equipment collaborative manufacturing performance of online monitoring systems are improved, system is a collaborative manufacturing platform that making product development easier. integrates customers, experts, and manufacturing compa- nies. The customers are provided with collaborative design 3.3.2 Manufacturing service and collaborative manufacturing services. When customers have design or manufacturing requirements, but do not Manufacturing services mainly include intelligent moni- have the conditions for completion, they can post demand toring, intelligent control, and collaborative manufacturing. orders on the platform, describe the requirements in detail, provide the necessary documentation, and wait for experts 3.3.2.1 Intelligent monitoring A 3D visual monitoring or a manufacturing company to accept the order. system for production lines based on OpenGL modeling on For a company, when a customer issues a demand order, the VC??6.0 platform was established to meet effective the company first reviews and evaluates whether it can production [213]. A grey online modeling surface rough- complete the order. If yes, it directly accepts the order, ness monitoring system was developed to accurately pre- directly connects with the customer, and no longer pub- dict the surface roughness in end milling [214]. Machine lishes it on the platform; otherwise, the order will be sorted center fault diagnosis and prediction based on data mining out. The order is then released to the platform for experts or were studied to develop a systematic approach and obtain manufacturing companies that cooperate with the platform. predictive maintenance knowledge in the Industry 4.0 era A platform for experts or manufacturing companies to [215]. The manufacturing service in the intelligent undertake design or manufacturing orders is provided. 123 12 B. He, K.-J. Bai When an expert or a manufacturing company finds an value of the cloud manufacturing service platform [238]. appropriate order on the platform, it can apply for the Lartigau et al. [239] proposed a service quality assessment- order. They can then establish contact on the platform after based approach for transport impact analysis. the platform administrator approves the application. Such an equipment collaborative manufacturing system inte- 3.3.3.2 Fault maintenance The interstitial error data grates customers, experts, and manufacturing companies interpretation and the compensation of machine center into a closed loop of manufacturing, thereby providing intelligent predictive maintenance were studied based on intelligent services to customers, experts, and manufac- an artificial neural network [240]. The research results turing companies and enabling them to benefit from them. showed that the gap error in the front and back directions of With the increasing use of cloud applications, tech- the machining center could be predicted and compensated. nologies, such as cloud manufacturing and cloud services, Liu and Ming [241] proposed a framework for the revision can be applied to the after-sales service of intelligent of the rough Decision Making Trial and Evaluation Lab- manufacturing services. A dynamic ant colony genetic oratory method for capturing and evaluating intelligent hybrid algorithm was proposed for solving large-scale industrial product service systems. cloud service composition and optimization problems The after-sales service research includes fault warning, [230]. A multi-objective hybrid artificial bee colony algo- fault diagnosis, quality maintenance, and cloud-based rithm was proposed for service composition and opti- after-sales service. Fault warning and diagnosis enable the mization selection in cloud manufacturing [231]. An offline user to grasp the status of the product in real time and take 3D automated printer approach to enhance the competi- corresponding measures according to the feedback in time, tiveness of 3D printing was developed based on the cloud which greatly increases the service life of the product. manufacturing service model and the 3D printing cloud service platform [232]. The optimal choice of a cloud service portfolio in cloud manufacturing was studied, and a 4 Framework of digital twin-driven sustainable cloud service category and a service quality index were intelligent manufacturing established [233]. The agent-based manufacturing service discovery framework was studied. This framework consists This study proposed the framework of digital twin-driven of an object- and model-based manufacturing task agent, a sustainable intelligent manufacturing (see Fig. 4). manufacturing service agent, and task and service matching Digital twin-driven sustainable intelligent manufactur- process knowledge base to realize the manufacturing ser- ing consists of a basic platform, sustainable intelligent vice discovery in a cloud manufacturing environment manufacturing equipment, sustainable intelligent manu- [234]. The development of the cloud manufacturing service facturing system, and sustainable intelligent manufacturing platform provides technical support. A cloud manufactur- service. Among them, the basic platform is mapped with ing service platform for small- and medium-sized enter- sustainable intelligent manufacturing equipment, sustain- prises, which implements semantic intelligence search, able intelligent manufacturing system, and sustainable order tracking, event task guidance, and collaborative intelligent manufacturing service. The sustainable intelli- management, was developed [235]. gent manufacturing equipment, sustainable intelligent manufacturing system, and sustainable intelligent manu- 3.3.3 After-sales service facturing service support each other. Sustainable intelligent manufacturing platforms could be interconnected to inte- After-sales service mainly includes fault diagnosis and grate the value chain among enterprises and form a new maintenance. industrial form. The data of the basic platform comes from the equip- 3.3.3.1 Fault diagnosis DeSmit et al. [236] studied a ment layer of the platform, which includes equipment, unit, method for systematically identifying network physical production line, and production workshop. After the plat- vulnerabilities in intelligent manufacturing systems. This form obtains data from the device layer, it combines cloud method can analyze the potential impact of vulnerabilities in computing, artificial intelligence, IoTs, and other tech- intelligent manufacturing systems. Fault diagnosis and pre- nologies. It then comprehensively considers environmental, diction of wind turbines based on supervisory control and economic, and social factors and combines human, equip- data acquisition (SCADA) data were studied, and an artificial ment, and technology to provide data for virtual and intelligence-based framework was proposed for wind turbine physical prototyping. Virtual and physical prototyping map fault diagnosis and prediction using the SCADA data [237]. with sustainable intelligent manufacturing equipment, A neighborhood enhancement matrix decomposition sustainable intelligent manufacturing systems, and sus- method was proposed to predict the loss of the service quality tainable intelligent manufacturing services. 123 Digital twin-based sustainable intelligent manufacturing: a review 13 Fig. 4 Framework of digital twin-driven sustainable intelligent manufacturing 123 14 B. He, K.-J. Bai Sustainable intelligent manufacturing equipment intelligent manufacturing to achieve sustainable intelligent includes an intelligent manufacturing unit and an intelli- manufacturing is an important future research direction. As gent manufacturing production line. The intelligent man- a sustainable technology, it could reduce emissions in the ufacturing unit includes machine tools, robots, special life cycle of products, thereby achieving the requirements of both intelligent manufacturing and comprehensive sus- equipment, measurement and control equipment, and other equipment. Sustainable intelligent manufacturing equip- tainability from the perspective of environmental, eco- nomic, and social aspects. ment maps to virtual and physical prototyping. The sustainable intelligent manufacturing system (iii) Sustainable intelligent manufacturing for the product includes a discrete manufacturing system and a process life cycle manufacturing system. In the horizontal direction, the Sustainable intelligent manufacturing for the product life sustainable intelligent manufacturing system could be cycle, including design, production, logistics, sale, and divided into sustainable design, sustainable production, service, must be achieved. The virtual and augmented sustainable logistics, sustainable sales, and sustainable realities could be also used in the product life cycle. services and form a sustainable closed loop. In the vertical direction, it could be divided into automatic production (iv) Sustainable intelligent manufacturing across enter- prise value chain system, manufacturing execution system, and enterprise resource management. Discrete and process manufacturing The interconnection among enterprises could be more universal; thus, the intelligent manufacturing could pay systems overlap and differ in all directions. Sustainable intelligent manufacturing service includes more attention on the enterprise value chain. product development, manufacturing, and after-sales ser- (v) Sustainable intelligent manufacturing for product vices. Product development services include collaborative environmental footprint design, product customization, and others. Manufacturing The massive emissions of greenhouse gases, especially services include intelligent monitoring, intelligent control, carbon dioxide, have led to increasing global warming. and collaborative manufacturing. After-sales service Therefore, cleaner production is receiving global attention includes fault diagnosis and maintenance. in the manufacturing industry. The industry is responsible for producing products in an environmentally friendly manner. The European Union (EU) proposes the use of the 5 Future works product environmental footprint [245, 246], including 14 types of environmental factors (e.g., product carbon foot- It is gradually phasing out the industry with a heavy print, product water footprint, etc.) to simulate the envi- environmental burden. Developing intelligent manufactur- ronmental impact of the emissions generated during the ing with increasing attention on sustainability is vigorous. product life cycle. The environmental impact of manufac- Sustainability is paid increasing attention, thereby clearly turing is becoming increasingly serious. Hence, the chal- positioning the sustainable development of the manufac- lenges of improving production efficiency and reducing turing industry as the foundation. Sustainable intelligent carbon footprint during the product life cycle are receiving manufacturing plays an irreplaceable role. Several future increasing attention [247]. In studying the intelligent works are needed in this topic. manufacturing of the carbon footprint of products, one must consider the carbon emissions of products from raw 5.1 Framework of sustainable intelligent materials, processing, transportation, use, recycling, etc., to manufacturing guide the development of intelligent manufacturing. To achieve clean manufacturing, low-carbon manufacturing is (i) Sustainable intelligent design a future research direction. The design is the foundation of intelligent manufacturing; (vi) Human-machine collaboration therefore, the traditional design must urgently be upgraded Human and machine could interact with each other more to a sustainable intelligent design to achieve sustainable collaboratively in sustainable intelligent manufacturing, intelligent manufacturing. Virtual and physical prototyping which enables a human to have efficient and effective could be interconnected in real time at the design stage. decision-making with machines. Achieving a sustainable design for the sustainable supply (vii) Sustainable intelligent manufacturing equipment, chain is also important. sustainable intelligent manufacturing system, and (ii) Comprehensive sustainability sustainable intelligent manufacturing service The concept of sustainability has become an important topic [242–244], and combining sustainable concepts with 123 Digital twin-based sustainable intelligent manufacturing: a review 15 5.2 Enabling technology of sustainable intelligent 6 Conclusions manufacturing With the transformation and upgrade of manufacturing, (i) Digital twin-based big data-driven sustainable intel- sustainable intelligent manufacturing has become increas- ligent manufacturing ingly important. Intelligent manufacturing combined with a digital twin has the functions of intelligent sensing and With the implementation of intelligent manufacturing, simulation, which makes the production of products more manufacturing precision, product quality, and processing efficient and intelligent. At the same time, it could monitor efficiency would continuously improve. With the help of the status of products and production equipment in real the digital twin and big data technologies, a virtual simu- time and predict possible failures in time. After the intro- lation model of the solid model would be established, and duction of a digital twin and its application, three aspects of the entity status could be fed back in real time. The digital digital twin-driven sustainable intelligent manufacturing, twin could be applied to online real-time product inspec- namely sustainable intelligent manufacturing equipment, tion and equipment fault diagnosis and repair. sustainable intelligent manufacturing systems, and sus- (ii) Artificial intelligence-driven sustainable intelligent tainable intelligent manufacturing services, were intro- manufacturing duced. The framework of the digital twin-driven Information technology has achieved rapid development sustainable intelligent manufacturing was proposed in since the beginning of the 21st century. In recent years, detail. The future direction of digital twin-driven sustain- artificial intelligence has rapidly developed in the aspects able intelligent manufacturing was also discussed. of medical, monitoring, and interaction, thereby greatly changing people’s lifestyles. In the future, the intelligent Acknowledgements The work was supported by the National Nat- ural Science Foundation of China (Grant No. 51675319), and manufacturing process would inevitably reduce the human Shanghai Science and Technology Committee Project (Grant No. factor. Therefore, applying artificial intelligence to intelli- 19511104702). gent manufacturing, gradually replacing the role of human beings, and realizing unmanned intelligent manufacturing Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, will be the future research direction. adaptation, distribution and reproduction in any medium or format, as (iii) IoTs-driven sustainable intelligent manufacturing long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate The Internet of Things enables all objects that could per- if changes were made. The images or other third party material in this form independent functions to be connected to the network, article are included in the article’s Creative Commons licence, unless thereby enabling interconnection and interoperability to indicated otherwise in a credit line to the material. If material is not achieve the effect of the Internet of everything. Combining included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted IoTs with intelligent manufacturing enables the production use, you will need to obtain permission directly from the copyright equipment and production products to be interconnected. holder. To view a copy of this licence, visit http://creativecommons. The equipment can independently sense the processing org/licenses/by/4.0/. quality of the products and make timely adjustments to achieve independent production. References 5.3 Application of sustainable intelligent 1. Waschull S, Bokhorst JAC, Molleman E et al (2020) Work manufacturing design in future industrial production: transforming towards cyber-physical systems. Comput Ind Eng. 139:105679 Sustainable intelligent manufacturing must be put into 2. Javed Y, Felemban M, Shawly T et al (2019) A partition-driven integrated security architecture for cyber-physical systems. applications. For process intelligent manufacturing sys- arXiv:190103018[csSY] tems, such as those used in the steel, pharmaceutical, and 3. Van Der Zeeuw A, Van Deursen AJ, Jansen G (2019) petrochemical industries, and for the discrete intelligent Inequalities in the social use of the internet of things: a capital manufacturing system, such as that used in the mechanical and skills perspective. New Media Soc 21(6):1344–1361 4. Habibi M, Fazli M, Movaghar A (2019) Efficient distribution of manufacturing industry, the MES could play an important requests in federated cloud computing environments utilizing role in the manufacturing system. statistical multiplexing. Future Gener Comput Syst 90:451–460 5. Yan H, Yu P, Long D (2019) Study on deep unsupervised learning optimization algorithm based on cloud computing. In: 2019 international conference on intelligent transportation, Big data & smart city (ICITBS), pp 679–681 6. He B, Pan QJ, Deng ZQ (2018) Product carbon footprint for product life cycle under uncertainty. J Clean Prod 187:459–472 123 16 B. He, K.-J. Bai 7. Radhi H (2019) Multi-objective optimization of turning process with big data based feedback and coordination. Comput Netw during machining of AISI 1025 on CNC machine using multi- 101:158–168 objective particle swarm optimization. Univ Thi-Qar J Eng Sci 29. Grieves M (2014) Digital twin: manufacturing excellence 10(1):65–70 through virtual factory replication. White paper, pp 1–7 8. He B, Cao XY, Gu ZC (2020) Kinematics of underactuated 30. Abdulmotaleb ES (2018) Digital twins: the convergence of robotics for product carbon footprint. J Clean Prod 257:120491 multimedia technologies. IEEE Multimed 25(2):87–92 9. Chiaverini S, Siciliano B, Egeland O (1994) Review of the 31. Negri E, Fumagalli L, Macchi M (2017) A review of the roles of damped least-squares inverse kinematics with experiments on an digital twin in CPS-based production systems. Procedia Manuf industrial robot manipulator. IEEE Trans Control Syst Technol 11:939–948 2(2):123–134 32. Chhetri MB, Krishnaswamy S, Loke SW (2004) Smart virtual 10. Altintas Y, Yang J, Kilic ZM (2019) Virtual prediction and counterparts for learning communities. In: Bussler C et al (eds) constraint of contour errors induced by cutting force distur- Web information systems—WISE 2004 workshops, WISE 2004. bances on multi-axis CNC machine tools. CIRP Ann Springer, Berlin, pp 125–134 68(1):377–380 33. Glaessgen E, Stargel D (2012) The digital twin paradigm for 11. Zheng P, Wang HH, Sang ZQ et al (2018) Smart manufacturing future NASA and U.S. Air force vehicles. In: 2012 53rd AIAA/ systems for Industry 4.0: conceptual framework, scenarios, and ASME/ASCE/AHS/ASC Structures, structural dynamics and future perspectives. Front Mech Eng 13(2):137–150 materials conference, pp 1–14 12. Tao F, Qi QL, Liu A et al (2018) Data-driven smart manufac- 34. Lee J, Bagheri B, Kao HA (2015) A cyber-physical systems turing. J Manuf Syst 48:157–169 architecture for Industry 4.0-based manufacturing systems. 13. Zhong RY, Xu X, Klotz E et al (2017) Intelligent manufacturing Manuf Lett 3:18–23 in the context of Industry 4.0: a review. Engineering 35. So¨derberg R, Wa¨rmefjord K, Carlson JS et al (2017) Toward a 3(5):616–630 digital twin for real-time geometry assurance in individualized 14. Yadav A, Jayswal SC (2017) Modelling of flexible manufac- production. CIRP Ann 66(1):137–140 turing system: a review. Int J Prod Res 56(7):2464–2487 36. Bolton RN, McColl-Kennedy JR, Cheung L et al (2018) Cus- 15. Li BH, Hou BC, Yu WT et al (2017) Applications of artificial tomer experience challenges: bringing together digital, physical intelligence in intelligent manufacturing: a review. Front Inf and social realms. J Serv Manag 29(5):776–808 Technol Electron Eng 18(1):86–96 37. Tao F, Sui FY, Liu A et al (2019) Digital twin-driven product 16. Kusiak A (2017) Smart manufacturing. Int J Prod Res 56(1/ design framework. Int J Prod Res. 57(12):3935–3953 2):508–517 38. Hu LW, Nguyen NT, Tao WJ et al (2018) Modeling of cloud- 17. He B, Hua YC (2017) Feature-based integrated product model based digital twins for smart manufacturing with mt connect. for low-carbon conceptual design. J Eng Des 28(6):408–432 Procedia Manuf 26:1193–1203 18. Bouzary H, Frank Chen F (2018) Service optimal selection and 39. Tao F, Cheng JF, Qi QL et al (2017) Digital twin-driven product composition in cloud manufacturing: a comprehensive survey. design, manufacturing and service with big data. Int J Adv Int J Adv Manuf Technol 97(1/4):795–808 Manuf Technol 94(9/12):3563–3576 19. Bouzary H, Chen FF, Krishnaiyer K (2018) Service matching 40. Schleich B, Anwer N, Mathieu L et al (2017) Shaping the digital and selection in cloud manufacturing: a state-of-the-art review. twin for design and production engineering. CIRP Ann Procedia Manuf 26:1128–1136 66(1):141–144 20. Bauer D, Stock D, Bauernhansl T (2017) Movement towards 41. Haag S, Anderl R (2018) Digital twin—proof of concept. Manuf service-orientation and app-orientation in manufacturing it. Lett 15:64–66 Procedia CIRP 62:199–204 42. Guo JP, Zhao N, Sun L et al (2018) Modular based flexible 21. Giret A, Garcia E, Botti V (2016) An engineering framework for digital twin for factory design. J Ambient Intell Hum Comput service-oriented intelligent manufacturing systems. Comput Ind 10(3):1189–1200 81:116–127 43. Bao JS, Guo DS, Li J et al (2018) The modelling and operations 22. Cao Y, Wang SL, Kang L et al (2015) Study on machining for the digital twin in the context of manufacturing. Enterp Inf service modes and resource selection strategies in cloud manu- Syst 13(4):534–556 facturing. Int J Adv Manuf Technol 81(1/4):597–613 44. Cheng Y, Tao F, Xu LD et al (2016) Advanced manufacturing 23. He B, Zhang D, Gu ZC et al (2020) Skeleton model-based systems: supply-demand matching of manufacturing resource product low carbon design optimization. J Clean Prod. https:// based on complex networks and internet of things. Enterp Inf doi.org/10.1016/j.jclepro.2020.121687 Syst 12(7):780–797 24. Grossmann IE (2019) Optimization and management in manu- 45. Bilberg A, Malik AA (2019) Digital twin driven human–robot facturing engineering: resource collaborative optimization and collaborative assembly. CIRP Ann 68(1):499–502 management through the internet of things. Optim Methods 46. Um J, Weyer S, Quint F (2017) Plug-and-simulate within Softw 34(1):220–223 modular assembly line enabled by digital twins and the use of 25. Soni R, Bhatia M, Singh T (2019) Digital twin: intersection of automation ML. IFAC-PapersOnLine 50(1):15904–15909 mind and machine. Int J Comput Intell IoT 2(3):667–670 47. Qi QL, Tao F, Zuo Y et al (2018) Digital twin service towards 26. Zheng P, Lin Y, Chen CH et al (2018) Smart, connected open smart manufacturing. Procedia CIRP 72:237–242 architecture product: an IT-driven co-creation paradigm with 48. Leng JW, Zhang H, Yan DX et al (2018) Digital twin-driven manufacturing cyber-physical system for parallel controlling of lifecycle personalization concerns. Int J Prod Res 57(8):2571–2584 smart workshop. J Ambient Intell Hum Comput 27. Nikolakis N, Alexopoulos K, Xanthakis E et al (2019) The 10(3):1155–1166 digital twin implementation for linking the virtual representation 49. Cheng Y, Zhang YP, Ji P et al (2018) Cyber-physical integration of human-based production tasks to their physical counterpart in for moving digital factories forward towards smart manufac- the factory-floor. Int J Comput Integr Manuf 32(1):1–12 turing: a survey. Int J Adv Manuf Technol 97(1/4):1209–1221 28. Wang SY, Wan JF, Zhang DQ et al (2016) Towards smart 50. Meng SH, Tang SL, Zhu YH et al (2019) Digital twin-driven factory for Industry 4.0: a self-organized multi-agent system control method for robotic automatic assembly system. IOP Conf Ser Mater Sci Eng 493:012128 123 Digital twin-based sustainable intelligent manufacturing: a review 17 51. Xiang F, Zhi Z, Jiang GZ (2018) Digital twins technology and 70. Liu Y, Zhang L, Yang Y et al (2019) A novel cloud-based its data fusion in iron and steel product life cycle. In: 2018 IEEE framework for the elderly healthcare services using digital twin. 15th international conference on networking, sensing and con- IEEE Access 7:49088–49101 trol (ICNSC), pp 1–5 71. Balachandar S, Chinnaiyan R (2019) Reliable digital twin for 52. Zhang H, Liu Q, Chen X et al (2017) A digital twin-based connected footballer. In: International conference on computer approach for designing and multi-objective optimization of networks and communication technologies. pp 185–191 hollow glass production line. IEEE Access 5:26901–26911 72. Guivarch D, Mermoz E, Marino Y et al (2019) Creation of 53. Zhuang CB, Liu JH, Xiong H (2018) Digital twin-based smart helicopter dynamic systems digital twin using multibody simu- production management and control framework for the complex lations. CIRP Ann 68(1):133–136 product assembly shop-floor. Int J Adv Manuf Technol 96(1/ 73. Tao F, Zhang M, Liu YS et al (2018) Digital twin driven 4):1149–1163 prognostics and health management for complex equipment. 54. Liu Q, Zhang H, Leng JW et al (2018) Digital twin-driven rapid CIRP Ann 67(1):169–172 individualised designing of automated flow-shop manufacturing 74. Lynn R, Chen A, Locks S et al (2015) Intelligent and accessible system. Int J Prod Res 57:3903–3919 data flow architectures for manufacturing system optimization. 55. Liau Y, Lee H, Ryu K (2018) Digital twin concept for smart In: Umeda S, Nakano M, Mizuyama H et al (eds) Advances in injection molding. IOP Conf Ser Mater Sci Eng 324:012077 production management systems: innovative production man- 56. Botkina D, Hedlind M, Olsson B et al (2018) Digital twin of a agement towards sustainable growth. Springer, Berlin, pp 27–35 cutting tool. Procedia CIRP 72:215–218 75. Luo W, Hu T, Zhang C et al (2018) Digital twin for CNC 57. Pairet E, Ardo´n P, Liu X et al (2019) A digital twin for human– machine tool: modeling and using strategy. J Ambient Intell robot interaction. In: 2019 14th ACM/IEEE international con- Hum Comput 10(3):1129–1140 ference on human-robot interaction (HRI), pp 372-372 76. Li CZ, Mahadevan S, Ling Y et al (2017) Dynamic bayesian 58. Voinov N, Chernorutsky I, Drobintsev P et al (2017) An network for aircraft wing health monitoring digital twin. AIAA J approach to net-centric control automation of technological 55(3):930–941 processes within industrial IoT systems. Adv Manuf 77. Kaebernick H, Kara S, Sun M (2003) Sustainable product 5(4):388–393 development and manufacturing by considering environmental 59. Uhlemann THJ, Schock C, Lehmann C et al (2017) The digital requirements. Robot Comput Integr Manuf 19(6):461–468 twin: demonstrating the potential of real time data acquisition in 78. Rusinko C (2007) Green manufacturing: an evaluation of production systems. Procedia Manuf 9:113–120 environmentally sustainable manufacturing practices and their 60. Coronado PDU, Lynn R, Louhichi W et al (2018) Part data impact on competitive outcomes. IEEE Trans Eng Manag integration in the shop floor digital twin: mobile and cloud 54(3):445–454 technologies to enable a manufacturing execution system. 79. Miller G, Pawloski J, Standridge CR (2010) A case study of J Manuf Syst 48:25–33 lean, sustainable manufacturing. J Ind Eng Manag 3(1):11–32 61. Schluse M, Priggemeyer M, Atorf L et al (2018) Experi- 80. Akbar M, Irohara T (2018) Scheduling for sustainable manu- mentable digital twins—streamlining simulation-based systems facturing: a review. J Clean Prod 205:866–883 engineering for Industry 4.0. IEEE Trans Ind Inf 81. Carvalho N, Chaim O, Cazarini E et al (2018) Manufacturing in 14(4):1722–1731 the fourth industrial revolution: a positive prospect in sustain- 62. Macchi M, Roda I, Negri E et al (2018) Exploring the role of able manufacturing. Procedia Manuf 21:671–678 digital twin for asset lifecycle management. IFAC-PapersOn- 82. Gbededo MA, Liyanage K, Garza-Reyes JA (2018) Towards a Line 51(11):790–795 life cycle sustainability analysis: a systematic review of 63. Kunath M, Winkler H (2018) Integrating the digital twin of the approaches to sustainable manufacturing. J Clean Prod manufacturing system into a decision support system for 184:1002–1015 improving the order management process. Procedia CIRP 83. Koren Y, Gu X, Badurdeen F et al (2018) Sustainable living 72:225–231 factories for next generation manufacturing. Procedia Manuf 64. Biesinger F, Meike D, Kraß B et al (2018) A case study for a 21:26–36 digital twin of body-in-white production systems general con- 84. Stoycheva S, Marchese D, Paul C et al (2018) Multi-criteria cept for automated updating of planning projects in the digital decision analysis framework for sustainable manufacturing in factory. In: 2018 IEEE 23rd international conference on automotive industry. J Clean Prod 187:257–272 emerging technologies and factory automation (ETFA), 85. Moldavska A, Welo T (2019) A holistic approach to corporate pp 19–26 sustainability assessment: incorporating sustainable develop- 65. Vachalek J, Bartalsky´ L, Rovny´ O et al (2017) The digital twin ment goals into sustainable manufacturing performance evalu- of an industrial production line within the Industry 4.0 concept. ation. J Manuf Syst 50:53–68 In: 2017 21st international conference on process control (PC), 86. Physicsweb. http://www.Miit.Gov.Cn/n1146295/n1652858/ pp 258–262 n1652930/n3757016/c6429243/content.Html. Accessed 14 Aug 66. Uhlemann THJ, Lehmann C, Steinhilper R (2017) The digital 2018 twin: realizing the cyber-physical production system for Indus- 87. Stock T, Seliger G (2016) Opportunities of sustainable manu- try 4.0. Procedia CIRP 61:335–340 facturing in Industry 4.0. Procedia CIRP 40:536–541 67. Tao F, Zhang M (2017) Digital twin shop-floor: a new shop- 88. Garetti M, Taisch M (2012) Sustainable manufacturing: trends and research challenges. Prod Plan Control 23(2/3):83–104 floor paradigm towards smart manufacturing. IEEE Access 5:20418–20427 89. He B, Zhou GF, Hou SC et al (2016) An approach to compu- 68. He B, Deng ZQ, Huang S et al (2014) Application of unascer- tational co-evolutionary product design. Int J Adv Manuf tained number for the integration of carbon footprint in con- Technol 90(1/4):249–265 ceptual design. Proc Inst Mech Eng J Eng Manuf 90. Kang HS, Lee JY, Choi S et al (2016) Smart manufacturing: past 229(11):2088–2092 research, present findings, and future directions. Int J Precis Eng 69. Martinez HV, Neely AD, Ouyang A et al (2019) Service busi- Manuf Green Technol 3(1):111–128 ness model innovation: the digital twin technology. EurOMA. https://doi.org/10.17863/CAM.35482 123 18 B. He, K.-J. Bai 91. Walshe K, McKee M, McCarthy M et al (2013) Health systems and criticality analysis. Int J Adv Manuf Technol 100(5/ and policy research in Europe: Horizon 2020. Lancet 8):1695–1717 382(9893):668–669 112. Li ZM (2016) The knowledge expression for the low carbon 92. Hemphill TA (2014) Policy debate: the US advanced manu- economy of cold heading machine. J Low Carbon Econ facturing initiative: will it be implemented as an innovation—or 05(02):20–25 industrial—policy? Innovation 16(1):67–70 113. Zhang SL, Wang S, Jing FS et al (2019) A sensorless hand 93. Lewis P, Bell K (2019) Understanding the UK’s productivity guiding scheme based on model identification and control for problems: new technological solutions or a case for the renewal industrial robot. IEEE Trans Ind Inf 15:5204–5213 of old institutions? Employ Relat Int J 41(2):296–312 114. Pe´rez L, Diez E, Usamentiaga R et al (2019) Industrial robot 94. Radanliev P, De Roure D, Nurse JR et al (2019) New devel- control and operator training using virtual reality interfaces. opments in cyber physical systems, the internet of things and the Comput Ind 109:114–120 digital economy—discussion on future developments in the 115. Wu JH, Han X, Tao YR (2019) Kinematic response of industrial industrial internet of things and Industry 4.0. Preprints 2019, robot with uncertain-but-bounded parameters using interval 2019030094 analysis method. J Mech Sci Technol 33(1):333–340 95. Yeung G (2019) ‘Made in China 2025’: the development of a 116. Chen Z, Zhou W (2017) Path planning for a space-based new energy vehicle industry in China. Area Dev Policy manipulator system based on quantum genetic algorithm. 4(1):39–59 J Robot. 3207950 96. Zhou GH, Zhang C, Li Z et al (2019) Knowledge-driven digital 117. Guo S, Fang TT, Song T et al (2018) Tracking and localization twin manufacturing cell towards intelligent manufacturing. Int J for omni-directional mobile industrial robot using reflectors. Prod Res 58:1034–1051 Adv Manuf 6(1):118–125 97. Lohtander M, Ahonen N, Lanz M et al (2018) Micro manu- 118. Slavkovic N, Zivanovic S, Milutinovic D (2019) An indirect facturing unit and the corresponding 3D-model for the digital method of industrial robot programming for machining tasks twin. Procedia Manuf 25:55–61 based on STEP-NC. Int J Comput Integr Manuf 32(1):43–57 98. Zhang YZ, Mu LM, Shen GX et al (2019) Fault diagnosis 119. Lyu H, Liu Y, Guo JY et al (2019) Tool-path generation for strategy of CNC machine tools based on cascading failure. industrial robotic surface-based application. Adv Manuf J Intell Manuf 30(5):2193–2202 7(1):64–72 99. Villalonga A, Beruvides G, Castan˜o F et al (2018) Condition- 120. Berg J, Lottermoser A, Richter C et al (2019) Human-robot- based monitoring architecture for CNC machine tools based on interaction for mobile industrial robot teams. Procedia CIRP global knowledge. IFAC-PapersOnLine 51(11):200–204 79:614–619 100. Yang HT, Li L, Zhang SD et al (2019) Critical point determi- 121. Norrlof M (2002) An adaptive iterative learning control algo- nation method of thermal-force coupling deformation of CNC rithm with experiments on an industrial robot. IEEE Trans Rob machine tool bed. In: Tenth international symposium on preci- Autom 18(2):245–251 sion engineering measurements and instrumentation, 122. Gao Z, Zeng L, He B et al (2018) Type synthesis of non-holo- pp 1105325 nomic spherical constraint underactuated parallel robotics. Acta 101. Wei XY, Miao EM, Liu H et al (2019) Two-dimensional ther- Astronaut 152:509–520 mal error compensation modeling for worktable of CNC 123. He B, Wang S, Liu Y (2019) Underactuated robotics: a review. machine tools. Int J Adv Manuf Technol 101(1/4):501–509 Int J Adv Robot Syst 16(4):1–29 102. Jiang ZP, Gao D, Lu Y et al (2019) Electrical energy con- 124. He B, Zhang P, Liu W et al (2017) Dynamics analysis and sumption of CNC machine tools based on empirical modeling. numerical simulation of a novel underactuated robot wrist. Proc Int J Adv Manuf Technol 100(9/12):2255–2267 Inst Mech Eng J Eng Manuf 231(12):2145–2158 103. Krimpenis AA, Fountas NA (2016) Balancing multiple criteria 125. Fu´nez Guerra C, Reyes-Bozo L, Vyhmeister E et al (2019) in formulation of weighted, single-objective genetic algorithm Viability analysis of underground mining machinery using green optimization for CNC machining problems. Adv Manuf hydrogen as a fuel. Int J Hydrogen Energy 45:5112–5121 4(2):178–188 126. Islam MS, Peter N, Wiens T (2019) Simulation and experiment 104. Xu X (2017) Machine tool 4.0 for the new era of manufacturing. of vibrational or acoustic communication in mining and oil-gas Int J Adv Manuf Technol 92(5/8):1893–1900 drill strings. Trans Can Soc Mech Eng 43:454–462 105. Jeon JW, Ha YY (2000) A generalized approach for the accel- 127. Andreev V, Voronkova L, Lybianoi D (2019) Innovative tech- eration and deceleration of industrial robots and CNC machine nology of manufacturing of reusable metallurgical equipment tools. IEEE Trans Ind Electron 47(1):133–139 with increased operational resistance from the blast furnace cast 106. Kim DI, Kim S (1996) An iterative learning control method with iron of the first melting. J Mater Sci Res Rev 2:1–8 application for CNC machine tools. IEEE Trans Ind Appl 128. Indri M, Lachello L, Lazzero I et al (2019) Smart sensors 32(1):66–72 applications for a new paradigm of a production line. Sensors 107. Keller A, Kamath A, Perera U (1982) Reliability analysis of 19(3):650. https://doi.org/10.3390/s19030650 CNC machine tools. Reliab Eng 3(6):449–473 129. Dong X, Ma R (2019) Optimization of the LPCVD equipment 108. Yamato S, Yamada Y, Nakanishi K et al (2018) Integrated in- intergraded production system of the solar cell production line. process chatter monitoring and automatic suppression with AIP Conf Proc 2122(1):1–5 adaptive pitch control in parallel turning. Adv Manuf 130. Wang J, Li D (2019) Task scheduling based on a hybrid heuristic algorithm for smart production line with fog comput- 6(3):291–300 109. He B, Wang J, Huang S et al (2015) Low-carbon product design ing. Sensors 19(5):1–18 for product life cycle. J Eng Des 26(10–12):321–339 131. Hwang I, Jang YJ, Choi H (2018) Overhead shuttle design for a 110. Li YJ, Wang GC, Cui HY et al (2019) Dynamic characteristics flat panel display production line considering the contactless and optimization research on PVDF piezoelectric film force power supply capacity. Comput Ind Eng 126:232–242 sensor for steel ball cold heading machine. ISA Trans 132. Gao Y, Lyu H, Hou Y et al (2019) Real-time modeling and 94:265–275 simulation method of digital twin production line. In: 2019 IEEE 111. He B, Xue HJ, Liu LL et al (2019) Rigid-flexible coupling 8th joint international information technology and artificial virtual prototyping-based approach to the failure mode, effects, intelligence conference (ITAIC), pp 1639–1642 123 Digital twin-based sustainable intelligent manufacturing: a review 19 133. He B, Wang J, Deng ZQ (2015) Cost-constrained low-carbon 155. Gregor M, Hercko J, Fusko M et al (2019) Zilina intelligent product design. Int J Adv Manuf Technol 79(9/12):1821–1828 manufacturing system: best practice of cooperation between 134. Andiappan V, Benjamin MFD, Tan RR et al (2019) An inte- university and research center. In: Caganova D, Balog M, grated framework to address criticality in biomass tri-generation Knapcikova L et al (eds) Smart technology trends in industrial systems via redundancy allocation. Process Integr Optim Sustain and business management. Springer, Berlin, pp 183–198 3(1):65–73 156. He B, Li FF, Cao XY et al (2020) Product sustainable design: a 135. Guan D, Feng S, Zhang L et al (2019) Mesoscale simulation for review from the environmental, economic, and social aspects. heavy petroleum system using structural unit and dissipative ASME J Comput Inf Sci Eng 20:040801 particle dynamics (SU–DPD) frameworks. Energy Fuel 157. He B, Wang YG, Song W et al (2014) Design resource man- 33(2):1049–1060 agement for virtual prototyping in product collaborative design. 136. Lemu HG (2014) Current status and challenges of using geo- Proc Inst Mech Eng J Eng Manuf 229(12):2284–2300 metric tolerance information in intelligent manufacturing sys- 158. Simeone A, Caggiano A, Boun L et al (2019) Intelligent cloud tems. Adv Manuf 2(1):13–21 manufacturing platform for efficient resource sharing in smart 137. Sun J, Xi J, Chen X et al (2011) A CAD/CAM system for manufacturing networks. Procedia CIRP 79:233–238 fabrication of facial prostheses. Rapid Prototyp J 17(4):253–261 159. Wang S, Liang YC, Li WD et al (2018) Big data enabled 138. Lv YQ, Lin DP (2017) Design an intelligent real-time operation intelligent immune system for energy efficient manufacturing planning system in distributed manufacturing network. Ind management. J Clean Prod 195:507–520 Manag Data Syst 117(4):742–753 160. Stadnicka D, Litwin P, Antonelli D (2019) Human factor in 139. Gu X, Jin XN, Ni J et al (2015) Manufacturing system design for intelligent manufacturing systems—knowledge acquisition and resilience. Procedia CIRP 36:135–140 motivation. Procedia CIRP 79:718–723 140. Maturana F, Shen W, Norrie DH (1999) Metamorph: an adap- 161. He B, Tang W, Wang J et al (2015) Low-carbon conceptual tive agent-based architecture for intelligent manufacturing. Int J design based on product life cycle assessment. Int J Adv Manuf Prod Res 37(10):2159–2173 Technol 81(5/8):863–874 141. He B, Hou S, Song W (2015) Integrating engineering design and 162. Tao F, Cheng Y, Xu LD et al (2014) CCIOT-CMFG: cloud analysis using a parameter constraint graph approach. Simula- computing and internet of things-based cloud manufacturing tion 91(7):625–647 service system. IEEE Trans Ind Inf 10(2):1435–1442 142. He B, Hua Y (2016) Synthesis of mechanisms integrated with 163. Lin YC, Hung MH, Huang HC et al (2017) Development of motion and force transformation. Int J Precis Eng Manuf advanced manufacturing cloud of things (AMCOT)—a smart 17(12):1643–1649 manufacturing platform. IEEE Rob Autom Lett 2(3):1809–1816 143. He B, Huang S (2016) Functional synthesis of mechanisms 164. He B, Zhang P, Liu L (2014) Simultaneous functional synthesis under cost consideration. Proc Inst Mech Eng J Eng Manuf of mechanisms with mechanical efficiency and cost. Int J Adv 230(1):91–99 Manuf Technol 75(5/8):659–665 144. He B, Song W, Wang Y (2015) Computational conceptual 165. Zhang YF, Qian C, Lyu JX et al (2017) Agent and cyber- design using space matrix. J Comput Inf Sci Eng 15(1):1–7 physical system based self-organizing and self-adaptive intelli- 145. He B, Song W, Wang YG (2013) A feature-based approach gent shopfloor. IEEE Trans Ind Inf 13(2):737–747 towards an integrated product model in intelligent design. Int J 166. Lee CKM, Zhang SZ, Ng KKH (2017) Development of an Adv Manuf Technol 69(1/4):15–30 industrial internet of things suite for smart factory towards re- 146. He B, Zhang P, Wang J (2014) Automated synthesis of mech- industrialization. Adv Manuf 5(4):335–343 anisms with consideration of mechanical efficiency. J Eng Des 167. He B, Niu YC, Hou SC et al (2018) Sustainable design from 25(4/6):213–237 functional domain to physical domain. J Clean Prod 147. He B, Zhang P, Zhu N et al (2016) Skeleton model-based 197:1296–1306 approach to integrated engineering design and analysis. Int J 168. Helo P, Suorsa M, Hao Y et al (2014) Toward a cloud-based Adv Manuf Technol 85(5):1105–1115 manufacturing execution system for distributed manufacturing. 148. He B, Ostrosi E, Pfaender F et al (2014) Intelligent engineering Comput Ind 65(4):646–656 design of complex city: a co-evolution model. In: Cha J, Chou 169. Guo QL, Zhang M (2009) A novel approach for multi-agent- SY, Stjepandic J et al (eds) Moving integrated product devel- based intelligent manufacturing system. Inf Sci opment to service clouds in the global economy. IOS Press, 179(18):3079–3090 Amsterdam, pp 434–443 170. Ji X, He G, Xu JJ et al (2016) Study on the mode of intelligent 149. He B, Luo T, Huang S (2019) Product sustainability assessment chemical industry based on cyber-physical system and its for product life cycle. J Clean Prod 206:238–250 implementation. Adv Eng Software 99:18–26 150. He B, Deng ZQ, Huang S et al (2015) Application of unascer- 171. Tao F, Zuo Y, Xu LD et al (2014) IoT-based intelligent per- tained number for the integration of carbon footprint in con- ception and access of manufacturing resource toward cloud ceptual design. Proc Inst Mech Eng J Eng Manuf manufacturing. IEEE Trans Ind Inf 10(2):1547–1557 229(11):2088–2092 172. Jain P, Poon J, Singh JP et al (2019) A digital twin approach for 151. Yu QY, He B (2020) Automated sustainable low-carbon design fault diagnosis in distributed photovoltaic system. IEEE Trans of offshore platform for product life cycle. In: Tan J (ed) Power Electron 35:940–956 Advances in mechanical design. Springer, Berlin, pp 1–17 173. Liu MZ, Ma J, Lin L et al (2014) Intelligent assembly system for mechanical products and key technology based on internet of 152. He B, Huang S, Wang J (2015) Product low-carbon design using dynamic programming algorithm. Int J Precis Eng Manuf Green things. J Intell Manuf 28(2):271–299 Technol 2(1):37–42 174. Tang H, Li D, Wang SY et al (2018) Casoa: an architecture for 153. He B, Tang W, Wang J (2015) Product model integrated with agent-based manufacturing system in the context of Industry 4.0. carbon footprint for low-carbon design. Int J Precis Eng Manuf IEEE Access 6:12746–12754 16(11):2383–2388 175. Chaplin J, Bakker O, de Silva L et al (2015) Evolvable assembly 154. He B, Feng P (2012) Guiding conceptual design through func- systems: a distributed architecture for intelligent manufacturing. tional space exploration. Int J Adv Manuf Technol 66(9/ IFAC-PapersOnLine 48(3):2065–2070 12):1999–2011 123 20 B. He, K.-J. Bai 176. Wang KS (2013) Towards zero-defect manufacturing (ZDM)— 198. Rødseth H, Schjølberg P, Marhaug A (2017) Deep digital a data mining approach. Adv Manuf 1(1):62–74 maintenance. Adv Manuf 5(4):299–310 177. Liu C, Jiang PY (2016) A cyber-physical system architecture in 199. Gamboa Quintanilla F, Cardin O, L’Anton A et al (2016) A shop floor for intelligent manufacturing. Procedia CIRP modeling framework for manufacturing services in service-ori- 56:372–377 ented holonic manufacturing systems. Eng Appl Artif Intell 178. Wan JF, Yi ML, Li D et al (2016) Mobile services for cus- 55:26–36 tomization manufacturing systems: an example of Industry 4.0. 200. He B, Zhu XR, Zhang D (2020) Boundary encryption-based IEEE Access 4:8977–8986 Monte Carlo learning method for workspace modeling. ASME J 179. Zhao QJ, Cao P, Tu DW (2014) Toward intelligent manufac- Comp Inf Sci Eng. 20:034502. https://doi.org/10.1115/1. turing: label characters marking and recognition method for 4046816 steel products with machine vision. Adv Manuf 2(1):3–12 201. Li F, Zhang L, Liu YK et al (2017) A clustering network-based 180. Liu CW, Chien CF (2013) An intelligent system for wafer bin approach to service composition in cloud manufacturing. Int J map defect diagnosis: an empirical study for semiconductor Comput Integr Manuf 30(12):1331–1342 manufacturing. Eng Appl Artif Intell 26(5/6):1479–1486 202. Lu YQ, Xu X (2017) A semantic web-based framework for 181. Strandhagen JW, Alfnes E, Strandhagen JO et al (2017) The fit service composition in a cloud manufacturing environment. of Industry 4.0 applications in manufacturing logistics: a mul- J Manuf Syst 42:69–81 tiple case study. Adv Manuf 5(4):344–358 203. Zhang S, Xu YB, Zhang WY et al (2017) A new fuzzy QOS- 182. Chen RY (2017) An intelligent value stream-based approach to aware manufacture service composition method using extended collaboration of food traceability cyber physical system by fog flower pollination algorithm. J Intell Manuf 30(5):2069–2083 computing. Food Control 71:124–136 204. Zhou JJ, Yao XF (2016) A hybrid artificial bee colony algorithm 183. Maoudj A, Bouzouia B, Hentout A et al (2017) Distributed for optimal selection of QOS-based cloud manufacturing service multi-agent scheduling and control system for robotic flexible composition. Int J Adv Manuf Technol 88(9/12):3371–3387 assembly cells. J Intell Manuf 30(4):1629–1644 205. Yao F, Yao YP, Xing LN et al (2019) An intelligent scheduling 184. Barenji AV, Barenji RV, Hashemipour M (2016) Flexible test- algorithm for complex manufacturing system simulation with ing platform for employment of RFID-enabled multi-agent frequent synchronizations in a cloud environment. Memet system on flexible assembly line. Adv Eng Softw 91:1–11 Comput 11:357–370 185. Wang KS (2014) Intelligent and integrated RFID (II-RFID) 206. Ruiz N, Giret A, Botti V et al (2014) An intelligent simulation system for improving traceability in manufacturing. Adv Manuf environment for manufacturing systems. Comput Ind Eng 2(2):106–120 76:148–168 186. Zhong RY, Dai QY, Qu T et al (2013) RFID-enabled real-time 207. Zheng Y, Yang S, Cheng HC (2018) An application framework manufacturing execution system for mass-customization pro- of digital twin and its case study. J Ambient Intell Hum Comput duction. Robot Comput Integr Manuf 29(2):283–292 10(3):1141–1153 187. Leng JW, Jiang PY (2017) Dynamic scheduling in RFID-driven 208. Zhang C, Zhou G (2019) A view-based 3D CAD model reuse discrete manufacturing system by using multi-layer network framework enabling product lifecycle reuse. Adv Eng Softw metrics as heuristic information. J Intell Manuf 30(3):979–994 127:82–89 188. Guo ZX, Wong WK, Guo CX (2013) A cloud-based intelligent 209. He B, Tang W, Huang S et al (2015) Towards low-carbon decision-making system for order tracking and allocation in product architecture using structural optimization for light- apparel manufacturing. Int J Prod Res 52(4):1100–1115 weight. Int J Adv Manuf Technol 83(5/8):1419–1429 189. Qiu C (2018) Implementation of vehicle mobile sales cloud 210. Bodrow W (2014) The dynamic of professional knowledge management system based on intelligent community. In: 2018 utilized in software applications for process controlling. Adv 14th international conference on computational intelligence and Manuf 2(2):173–178 security (CIS), pp 341–344 211. Giret A, Trentesaux D, Salido MA et al (2017) A holonic multi- 190. Zhang XY, Ming XG, Liu ZW et al (2019) An overall frame- agent methodology to design sustainable intelligent manufac- work and subsystems for smart manufacturing integrated system turing control systems. J Clean Prod 167:1370–1386 (SMIS) from multi-layers based on multi-perspectives. Int J Adv 212. Zhang C, Zhou G, Lu Q et al (2017) Graph-based knowledge Manuf Technol 103:703–722 reuse for supporting knowledge-driven decision-making in new 191. He B, Liu YJ, Zeng LB et al (2020) Product carbon footprint product development. Int J Prod Res 55(23):7187–7203 across sustainable supply chain. J Clean Prod 241:118320 213. Chai JF, Hu XM, Qu HW et al (2018) Production line 3D 192. Sun HT, Peng C, Zhou P et al (2017) A brief overview on secure visualization monitoring system design based on OpenGL. Adv control of networked systems. Adv Manuf 5(3):243–250 Manuf 6(1):126–135 193. McFarlane D, Sarma S, Chirn JL et al (2003) Auto ID systems 214. Huang PB, Zhang HJ, Lin YC (2017) Development of a grey and intelligent manufacturing control. Eng Appl Artif Intell online modeling surface roughness monitoring system in end 16(4):365–376 milling operations. J Intell Manuf 30(4):1923–1936 194. Cui FZ, Xu ZZ, Wang XK et al (2018) A dual-system cooper- 215. Li Z, Wang Y, Wang KS (2017) Intelligent predictive mainte- ative co-evolutionary algorithm for satellite equipment layout nance for fault diagnosis and prognosis in machine centers: optimization. Proc Inst Mech Eng G J Aerosp Eng Industry 4.0 scenario. Adv Manuf 5(4):377–387 232(13):2432–2457 216. Kim J, Hwangbo H (2019) Real-time early warning system for sustainable and intelligent plastic film manufacturing. Sustain- 195. Malik AA, Bilberg A (2018) Phygital workspace as a digital twin for design & planning of smart factories, pp 1–2 ability 11(5):1490–1503 196. Yin Y, Sun L, Guo C (2008) A policy of conflict negotiation 217. Guo ZX, Ngai EWT, Yang C et al (2015) An RFID-based based on fuzzy matter element particle swarm optimization in intelligent decision support system architecture for production distributed collaborative creative design. Comput Aided Des monitoring and scheduling in a distributed manufacturing 40(10/11):1009–1014 environment. Int J Prod Econ 159:16–28 197. Wang Y, Ma HS, Yang JH et al (2017) Industry 4.0: a way from 218. Tan DP, Zhang LB, Ai QL (2016) An embedded self-adapting mass customization to mass personalization production. Adv network service framework for networked manufacturing sys- Manuf 5(4):311–320 tem. J Intell Manuf 30(2):539–556 123 Digital twin-based sustainable intelligent manufacturing: a review 21 219. Arica E, Powell DJ (2014) A framework for ICT-enabled real- transportation using an improved artificial bee colony optimi- time production planning and control. Adv Manuf 2(2):158–164 sation algorithm. Int J Prod Res 53(14):4380–4404 220. Su Y, Ding X, Zheng H et al (2009) A new method of remote 240. Wang KS, Li Z, Braaten J et al (2015) Interpretation and control for embedded terminal based on browser/server/terminal compensation of backlash error data in machine centers for model. In: 2009 Pacific-Asia conference on circuits, communi- intelligent predictive maintenance using ANNs. Adv Manuf cations and systems, pp 151–154 3(2):97–104 221. Theorin A, Bengtsson K, Provost J et al (2016) An event-driven 241. Liu ZW, Ming XG (2019) A framework with revised rough- manufacturing information system architecture for Industry 4.0. DEMATEL to capture and evaluate requirements for smart Int J Prod Res 55(5):1297–1311 industrial product-service system of systems. Int J Prod Res 222. Xiao X, Wang SF, Zhang LJ et al (2018) Complexity analysis of 57:7104–7122 manufacturing service ecosystem: a mapping-based computa- 242. Liu Q, Liu ZH, Xu WJ et al (2019) Human-robot collaboration tional experiment approach. Int J Prod Res 57(2):357–378 in disassembly for sustainable manufacturing. Int J Prod Res 223. Baxter D, Roy R, Doultsinou A et al (2009) A knowledge 57:4027–4044 management framework to support product-service systems 243. Dyllick T, Rost Z (2017) Towards true product sustainability. design. Int J Comput Integr Manuf 22(12):1073–1088 J Clean Prod 162:346–360 224. Matsas M, Pintzos G, Kapnia A et al (2017) An integrated 244. He B, Gu ZC (2016) Sustainable design synthesis for product collaborative platform for managing product-service across their environmental footprints. Des Stud 45:159–186 life cycle. Procedia CIRP 59:220–226 245. He B, Xiao JL, Deng ZQ (2018) Product design evaluation for 225. Balta EC, Lin Y, Barton K et al (2018) Production as a service: a product environmental footprint. J Clean Prod 172:3066–3080 digital manufacturing framework for optimizing utilization. 246. Manfredi S, Allacker K, Pelletier N et al (2012) Product envi- IEEE Trans Autom Sci Eng 15(4):1483–1493 ronmental footprint (PEF) guide. European Commission 226. Cheng Y, Bi LN, Tao F et al (2018) Hypernetwork-based 247. He B, Shao Y, Wang S et al (2019) Product environmental manufacturing service scheduling for distributed and collabo- footprints assessment for product life cycle. J Clean Prod rative manufacturing operations towards smart manufacturing. 233:446–460 J Intell Manuf. https://doi.org/10.1007/s10845-018-1417-8 227. Ren M, Ren L, Jain H (2018) Manufacturing service composi- tion model based on synergy effect: a social network analysis Bin He received his degrees approach. Appl Soft Comput 70:288–300 (from Bachelor to Ph.D Degree) 228. Siderska J, Jadaan KS (2018) Cloud manufacturing: a service- from Zhejiang University. Dr. oriented manufacturing paradigm. A review paper. Eng Manag He is a Full Professor and Prod Serv 10(1):22–31 Deputy Director of Shanghai 229. He B, Feng PE (2012) Research on collaborative conceptual Key Laboratory of Intelligent design based on distributed knowledge resource. Int J Adv Manufacturing and Robotics, Manuf Technol 66(5/8):645–662 Director of Robotics and Intel- 230. Yang YF, Yang B, Wang SL et al (2019) A dynamic ant-colony ligent Design Institute, School genetic algorithm for cloud service composition optimization. of Mechatronic Engineering and Int J Adv Manuf Technol 102(1/4):355–368 Automation, Shanghai Univer- 231. Zhou JJ, Yao XF (2017) A hybrid approach combining modified sity. Dr. He is Associate Editor artificial bee colony and cuckoo search algorithms for multi- of ASME Journal of Computing objective cloud manufacturing service composition. Int J Prod and Information Science in Res 55(16):4765–4784 Engineering, Editor-in-Chief of 232. Zhang CL, Sheng BY, Yin XY et al (2017) Research and International Journal of Advanced Robotic Systems. Dr. He has development of off-line services for the 3D automatic printing interests in sustainable intelligent design and intelligent manufactur- machine based on cloud manufacturing. J Ambient Intell Hum ing, and robotics. Comput 10(3):1109–1128 233. Huang BQ, Li CH, Tao F (2013) A chaos control optimal Kai-Jian Bai received a BS algorithm for QOS-based service composition selection in cloud degree in Mechanical Engi- manufacturing system. Enterp Inf Syst 8(4):445–463 neering from Shanghai Univer- 234. Guo L, Wang SL, Kang L et al (2015) Agent-based manufac- sity, P.R.C., in 2018. He is now turing service discovery method for cloud manufacturing. Int J studying for a master’s degree Adv Manuf Technol 81(9/12):2167–2181 in the School of Mechatronic 235. Song TX, Liu HM, Wei CM et al (2014) Common engines of Engineering and Automation, cloud manufacturing service platform for SMES. Int J Adv Shanghai University. He has Manuf Technol 73(1/4):557–569 interests in intelligent manufac- 236. DeSmit Z, Elhabashy AE, Wells LJ et al (2017) An approach to turing systems. cyber-physical vulnerability assessment for intelligent manu- facturing systems. J Manuf Syst 43:339–351 237. Wang KS, Sharma VS, Zhang ZY (2014) SCADA data based condition monitoring of wind turbines. Adv Manuf 2(1):61–69 238. Feng Y, Huang BQ (2018) Cloud manufacturing service QOS prediction based on neighbourhood enhanced matrix factoriza- tion. J Intell Manuf. https://doi.org/10.1007/s10845-018-1409-8 239. Lartigau J, Xu XF, Nie LS et al (2015) Cloud manufacturing service composition based on QOS with geo-perspective http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Advances in Manufacturing Springer Journals

Digital twin-based sustainable intelligent manufacturing: a review

Advances in Manufacturing , Volume 9 (1) – May 4, 2020

Loading next page...
 
/lp/springer-journals/digital-twin-based-sustainable-intelligent-manufacturing-a-review-ae9Ry0UWp5
Publisher
Springer Journals
Copyright
Copyright © The Author(s) 2020
ISSN
2095-3127
eISSN
2195-3597
DOI
10.1007/s40436-020-00302-5
Publisher site
See Article on Publisher Site

Abstract

Adv. Manuf. (2021) 9:1–21 https://doi.org/10.1007/s40436-020-00302-5 1 1 Bin He Kai-Jian Bai Received: 29 June 2019 / Revised: 4 September 2019 / Accepted: 26 March 2020 / Published online: 4 May 2020 The Author(s) 2020 Abstract As the next-generation manufacturing system, 1 Introduction intelligent manufacturing enables better quality, higher productivity, lower cost, and increased manufacturing As an upgrade to manufacturing industries, Industry 4.0 flexibility. The concept of sustainability is receiving proposed next-generation intelligent manufacturing to increasing attention, and sustainable manufacturing is achieve high adaptability, rapid design changes, digital evolving. The digital twin is an emerging technology used information technology, and more flexible technical in intelligent manufacturing that can grasp the state of workforce training. Manufacturing technologies include intelligent manufacturing systems in real-time and predict cyber-physical systems [1, 2], Internet of Things (IoT) [3], system failures. Sustainable intelligent manufacturing and cloud computing [4, 5]. In the Industry 4.0 era, intel- based on a digital twin has advantages in practical appli- ligent manufacturing has received increasing attention cations. To fully understand the intelligent manufacturing owing to the need for sustainability. Intelligent manufac- that provides the digital twin, this study reviews both turing should consider sustainability aspects [6], and technologies and discusses the sustainability of intelligent intelligent manufacturing equipment, such as computerized manufacturing. Firstly, the relevant content of intelligent numerical control (CNC) machine tools and industrial manufacturing, including intelligent manufacturing equip- robots [7–10], should have more intelligence, which aid ment, systems, and services, is analyzed. In addition, the their better integration into the intelligent manufacturing sustainability of intelligent manufacturing is discussed. closed loop to complete manufacturing tasks. Intelligent Subsequently, a digital twin and its application are intro- manufacturing systems are showing a diversified trend, and duced along with the development of intelligent manu- an increasing number of them are being developed for facturing based on the digital twin technology. Finally, specific tasks and applied to actual production, thereby combined with the current status, the future development greatly improving the level of intelligence [11–16]. New direction of intelligent manufacturing is presented. services for intelligent manufacturing are explored and improved, and the sustainable collaborative manufacturing Keywords Intelligent manufacturing  Digital twin  system platform integrates customers, experts, and enter- Advanced manufacturing  Industry 4.0  Sustainable prises and provides them with personalized services manufacturing [17–24]. A complete real-time presentation of the state of the intelligent manufacturing system is a challenge; however, the emergence of a digital twin has made it possible to solve this problem [25–27]. Manufacturing systems can & Bin He mehebin@gmail.com monitor physical processes, create a digital twin in the physical world [28], receive real-time information from the Shanghai Key Laboratory of Intelligent Manufacturing and physical world for simulation analysis, and make informed Robotics, School of Mechatronic Engineering and decisions through real-time communication and collabo- Automation, Shanghai University, Shanghai 200444, ration with humans. The combination of digital twin and People’s Republic of China 123 2 B. He, K.-J. Bai intelligent manufacturing makes manufacturing smarter, 2 Digital twin more efficient, and more convenient. This paper is devoted to reviewing digital twin-driven 2.1 Concept of digital twin sustainable intelligent manufacturing, which summarizes the intelligent manufacturing that uses a digital twin from a The idea of a digital twin was described as an information sustainable perspective. Firstly, the concept and application mirror model by Grieves [29]. A digital twin is a digital of a digital twin are introduced along with the application replica of a living or non-living physical entity. It enables a of the digital twin from three aspects: product design, seamless transfer of data by connecting physical and virtual manufacturing, and product service. Secondly, digital twin- worlds [30], thereby allowing virtual entities to exist driven sustainable intelligent manufacturing is introduced simultaneously with physical entities. The definition of the from three aspects: intelligent manufacturing equipment, digital twin technology emphasizes two important features. system, and service (see Fig. 1). Firstly, each definition emphasizes the connection between Sustainable intelligent manufacturing contains sustain- the physical model and the corresponding virtual model or able intelligent manufacturing equipment, system, and virtual counterpart. Secondly, the connection is established service, which support each other. Intelligent manufactur- by using sensors to generate real-time data [31, 32]. ing equipment is introduced from two dimensions: intelli- Table 1 lists some definitions of a digital twin in Refs. gent manufacturing unit and line. From the perspective of a [30, 31–37]. life cycle, the intelligent manufacturing system is divided Based on the definitions provided in the abovemen- into four parts: design, production, logistics and sales. tioned literature, a digital twin is a real-time digital Intelligent manufacturing services are introduced from reproduction of physical entities. It faithfully maps physi- three aspects: product development, manufacturing, and cal objects and can not only describe physical objects, but after-sales services. Finally, the development trend of also optimize physical objects based on models. intelligent manufacturing is summarized from three aspects: framework, enabling technology and application 2.2 Applications of digital twin of sustainable intelligent manufacturing. The framework of sustainable intelligent manufacturing includes sustainable The digital twin technology has recently received wide- intelligent design, comprehensive sustainability, human- spread attention. The world’s most authoritative IT machine collaboration, sustainable intelligent manufactur- research and advisory firm, Gartner, chose digital twin as ing for product life cycle, across enterprise value chain, for one of the top ten strategic technology trends since 2016. product environmental footprint, and sustainable intelligent Lockheed Martin, the world’s largest weapon manufac- manufacturing equipment, system, and service. The turer, listed digital twin as the first of six top technologies enabling technology of sustainable intelligent manufac- in the defense and aerospace industry in 2017. The China turing includes digital twin-based big data-driven, artificial Association for Science and Intelligent Manufacturing intelligence-driven, and Internet of Things (IoTs)-driven academic consortium also selected digital twin intelligent sustainable intelligent manufacturing. manufacturing assembly as one of the top 10 scientific and technological progresses in intelligent manufacturing in 2017. A digital twin chooses products as the main research object. Digital twin technology exists in different stages of Sustainable intelligent the product life cycle, and different elements are intro- manufacturing equipment duced at each stage. Therefore, digital twin has different performance forms. This section introduces the digital twin application from three aspects: product design, manufac- Contain turing and product service. Support Support Sustainable intelligent 2.2.1 Digital twin in product design manufacturing The digital twin application in product design is mainly Contain Contain based on digital twin research product design methods to make it more efficient. This includes digital design and Support Sustainable intelligent Sustainable intelligent digital simulation. manufacturing system manufacturing service Fig. 1 Three aspects of intelligent manufacturing 123 Digital twin-based sustainable intelligent manufacturing: a review 3 Table 1 Definition of digital twin in the literature Definition Refs. Digital twin is an integrated multi-physics, multi-scale, probabilistic simulation of completed vehicles Glaessgen and or systems that use the best physical models, sensor updates, fleet history, etc. to reflect the life of Stargel [33] their corresponding flying twin Digital twin is digital copies of biological or non-biological physical entities. By bridging the physical Abdulmotaleb [30] and virtual worlds, data is seamlessly transferred, allowing virtual entities to exist simultaneously with physical entities A coupled model of real machines running on a cloud platform that uses a combination of data-driven Lee et al. [34] analysis algorithms and other available physics knowledge to simulate health conditions Real-time optimization using digital copies of physical systems Soderberg et al. [35] The dynamic virtual representation of a physical object or system throughout its lifecycle, using real- Bolton et al. [36] time data to achieve understanding, learning, and reasoning Digital twin uses physical data, virtual data and interactive data between them to map all components Tao et al. [37] in the product lifecycle 2.2.1.1 Digital design Modeling tools are used to build build a solid model, which is applied to the product pro- virtual models of the products to visually express their cessing and assembly to achieve precise production con- physical parameters. A product design method based on a trol. This part includes the production process simulation, digital twin was proposed, and the framework of the digital digital production line, and equipment status monitoring. twin product design was analyzed [37]. A new cloud-based digital twin approach was developed for network physics 2.2.2.1 Production process simulation Before product cloud manufacturing platforms to reduce computing production, the production process can be simulated by resources and enable an efficient interaction between users means of virtual production, and productivity and effi- and physical machines [38]. Product design, manufactur- ciency can be comprehensively analyzed. A new method ing, and service approach were proposed, driven by a was proposed for resource supply and demand matching digital twin to make the product design, manufacturing, manufacturing based on complex networks and IoTs to and service more efficient [39]. Schleich et al. [40] pro- realize the intellectual perception and access to manufac- posed a comprehensive reference model based on the turing resources [44]. Bilberg and Malik [45] applied a concept of skin model shape, which corresponded to digital twin to the assembly unit to create a digital twin physical products in design and manufacturing. The digital model that extended the use of virtual simulation models twin-driven product design method enables researchers to developed during the production system design phase to quickly find design flaws and improve design efficiency implementation control, human and machine task assign- when designing products. ment, and task sequencing. Um et al. [46] proposed a universal data model based on a digital twin to support 2.2.1.2 Digital simulation The adaptability could be plug-and-play in modular, multi-vendor assembly lines. A verified at the design stage through a series of simulation digital twin with intelligent manufacturing services was experiments to verify the product performance. Haag and combined to produce more sensible manufacturing plan- Anderl [41] developed a network physical bending beam ning and precise production control [47]. A digital net- test rig to demonstrate the digital twin concept. A modular work-based manufacturing network physics system was approach was studied to build a digital twin and make the proposed to control intelligent workshops in parallel under corresponding changes [42]. Using the built-in flexible a large-scale personalization paradigm [48]. A factory digital twin helps designers quickly evaluate different network physical integration framework was proposed for designs and find design flaws. A method was proposed for digital-based systems to address the problems faced by modeling and operating a digital twin in a manufacturing digital factories and shift the current state of digital fac- environment [43]. At the design stage, researchers use tories to intelligent manufacturing [49]. simulation experiments to verify the product, which greatly improves the product adaptability. 2.2.2.2 Digital production line All the elements of the production stage are integrated into a closely coordinated 2.2.2 Digital twin in manufacturing production process through digital methods to achieve an automated production process. The digital twin model was The digital twin application in manufacturing is mainly studied using the digital twin technology to control robots based on the virtual simulation model of a digital twin to to automatically assemble large spacecraft components 123 4 B. He, K.-J. Bai [50]. Digital twin modeling and data fusion issues at each generation. The operation mode of the device can be steel product life cycle stage were explored to achieve optimized according to the state data of the virtual model to complex tasks [51]. A digital twin-based approach was reduce failure rate and improve stability. studied for the rapid personalization of insulated glass The application of product services aims to combine a production lines [52]. Moreover, a framework was pro- digital twin with other technologies, such as virtual reality, posed for intelligent production management and control to form a new model of digital twin-based services. In the methods using the digital twin technology and applied to manufacturing sector, Pairet et al. [57] introduced the assembly shops for complex products [53]. A digital twin Offshore Robotics for the Certification of Assets or ORCA method was proposed for the rapid personalization of Hub simulator for training and testing human-machine automated flow shop manufacturing systems, combining collaboration solutions that unify three types of home- physical system modeling and semi-physical simulation to made systems on the marine digital twin platform. Voinov generate authoritative digital designs of the system during et al. [58] studied a method for providing reliable man- the pre-production phase [54]. Liau et al. [55] applied a agement of complex IoT systems. Uhlemann et al. [59] digital twin to the injection molding industry, modeling all studied the concept of a learning factory based on the stages of injection molding as virtual models to achieve a advantages of real-time data acquisition and subsequent two-way control of physical processes. simulation data processing. Meanwhile, Coronado et al. [60] developed and implemented a low-cost manufacturing 2.2.2.3 Equipment status monitoring The production execution system (MES) and an android operating system process can be monitored visually by collecting the real- (OS) application to generate a shop floor digital twin model by collecting machine data enabled by MES and MTCon- time operation data of production equipment. The abnor- mal equipment must be dealt with and adjusted in time to nect. Schluse et al. [61] introduced an experimental digital optimize the production process. Botkina et al. [56] intro- twin to create interactions in different application scenarios duced digital twin data formats and structures for cutting and provided a new foundation for simulation-based inte- tools, information flow, and data management and applied grated systems engineering. Macchi et al. [62] explored the that digital twin to improve machining solutions optimized role of a digital twin in asset lifecycle management. Kunath for process planning. When the digital twin application is and Winkler [63] discussed the conceptual framework and applied in the production workshop, the state of the potential applications of digital twin decision support sys- machines and products in the workshop is reflected in the tems that were eager to manufacture systems in the order virtual model in real-time, thereby making the manufacture management process. Biesinger et al. [64] introduced the of the product more intelligent. digital twin of the body-in-white production system to achieve a rapid integration of new cars. Vacha´lek et al. [65] 2.2.3 Digital twin in product service introduced a digital twin and supported existing production structures and the most efficient use of resources in the The digital twin application in fault prediction is based on automotive industry through digital production and the virtual simulation model of a digital model based on a enhanced production and planning strategies. Uhlemann digital twin. The virtual simulation model faithfully reflects et al. [66] also introduced multimodal data acquisition the state of the solid model. The virtual simulation model methods to ensure the most accurate synchronization of will generate faults when the solid model fails. This is the digitally generated network physical processes with real fault detection. The virtual simulation model judges whe- physical models. Tao and Zhang [67] studied the digital ther the physical model will generate a fault based on the twin workshop based on a digital twin and its operation real-time state data and can effectively reduce the failure mechanism and implementation method. In the manufac- rate. This part includes product fault warning and mainte- turing process, the carbon emission problem in the manu- nance and production index optimization. facturing process should also be considered in addition to ensuring the manufacturing stability [68]. 2.2.3.1 Product fault warning and maintenance By The progress made by the digital twin technology in the reading the real-time parameters of the sensors or control research of medical, sports, manufacturing, etc., has led to systems of intelligent industrial products, a visual remote the continuous development of these industries. In the monitoring model is built to analyze the state of products medical field, Martinez et al. [69] studied the impact of with artificial intelligence and make early warning in time. digital twin on service business model innovation by fully Meanwhile, maintenance strategies are given to reduce understanding how to set up, implement, and use digital losses. Fault detection and health management can be health and understanding the impact of digital health in the implemented for different devices based on digital enterprise services business. A cloud healthcare system 123 Resource element Interconnection Fusion sharing System integration Emerging business Digital twin-based sustainable intelligent manufacturing: a review 5 System level framework was proposed for digital twin healthcare aimed at achieving the goal of personal health management by Collaboration integrating medical physics and virtual space [70]. In the field of sports, Balachandar and Chinnaiyan [71] used a Enterprise digital twin in the field of sports to make virtual connec- Workshop tions and monitor athletes in the lab. Unit 2.2.3.2 Production index optimization By reading and Device Life cycle analyzing the status data of products, the configuration Design Production Logistics Sales Service parameters of products are modified to improve their per- formance and optimize the production indexes. Guivarch et al. [72] proposed a new method for developing a digital twin for helicopter power systems to better predict the service life of mechanical components. A general digital twin model was established for complex devices. A method was also proposed for using the digital twin to drive pre- Intelligent feature diction and health management to improve the accuracy and efficiency of forecasting and health management [73]. Fig. 2 System architecture of intelligent manufacturing [86] Lynn et al. [74] proposed a network-, physical system- equipment, features, and others involved in intelligent based manufacturing system for implementing process manufacturing from three dimensions, namely life cycle, control and optimization. A multi-domain unified modeling system level, and intelligent features [86]. method was established for the digital twin to study its The intelligent manufacturing technology is the deep computer numerical control (CNC) machine tools and integration and integration of the information technology, make these tools more intelligent while optimizing the intelligent technology, and equipment manufacturing tech- operating mode, reducing the sudden failure rate, and nology. The intelligent manufacturing technology is based improving the CNC machine tool stability [75]. Dynamic on advanced technologies, such as the modern sensing Bayesian networks were used to build multi-function technology, network technology, automation technology, diagnostic and predictive probabilistic models to achieve a and anthropomorphic intelligence technology. The intelli- digital twin [76]. gent manufacturing technology can realize intelligent design process, intelligent manufacturing process, and intelligent manufacturing equipment through intelligent sensing, 3 Digital twin-driven sustainable intelligent human-computer interaction, decision making, and execu- manufacturing tion technology. In addition, the concept of sustainable [87, 88] manufacturing is receiving increasing attention, and Research on digital twin-driven intelligent manufacturing is intelligent manufacturing should be sustainable [89]. a hot trend and has achieved good results in life cycle man- Intelligent manufacturing plays a pivotal role in next- agement, data fusion, rapid production, intelligent forecast- generation manufacturing, especially in high-end manu- ing, and sustainable manufacturing [77–85]. Intelligent facturing; hence, the world’s traditional manufacturing manufacturing is a deep integration between the artificial powers and new manufacturing powers have come up with intelligence technology and the advanced manufacturing plans to develop intelligent manufacturing. Table 2 pre- technology. The new generation artificial intelligence tech- sents the intelligent manufacturing development plans of nology mainly includes cloud computing, IoTs and big data, some countries and organizations [90–95]. This section among others. Intelligent manufacturing brings great chan- describes intelligent manufacturing in terms of intelligent ges to all aspects of the manufacturing industry, making it manufacturing equipment, intelligent manufacturing sys- capable of learning, generating, and using knowledge. The tems, and intelligent manufacturing services. digitalization, networking, and intelligence of intelligent manufacturing have been balanced. 3.1 Sustainable intelligent manufacturing Intelligent manufacturing is a broad manufacturing equipment category that uses computer integrated manufacturing, high levels of adaptability and rapid design changes, digital Intelligent manufacturing equipment refers to manufac- information technology, and more flexible technical turing equipment with sensing, analysis, reasoning, deci- workforce training. Figure 2 shows the system architecture sion-making, and control functions. It is a deep integration of intelligent manufacturing, which describes the activities, 123 6 B. He, K.-J. Bai Table 2 Main intelligent manufacturing development plans in the world Country/organization Intelligent manufacturing development plan Refs. Germany Industry 4.0 [90] European Union Horizon 2020 [91] Japan Industrial Value Chain Initiative [13] United States Advanced Manufacturing Partnership [92] South Korea Manufacturing Industry Innovation 3.0 strategy [90] United Kingdom Modern industrial strategy [93] France New France Industrial [94] China Made in China 2025 [95] of the advanced manufacturing technology, information [99]. Yang et al. [100] proposed a method to accurately technology, and intelligent technology. The development determine the critical point of thermal coupling deforma- of intelligent manufacturing equipment reflects the level of tion of machine tools. A two-dimensional thermal error the manufacturing industry. Intelligent manufacturing compensation method was proposed for the thermal error equipment can be classified into two types: intelligent compensation of CNC machine tools, which greatly manufacturing unit and intelligent manufacturing produc- improved the compensation effect of the workbench [101]. tion line. An improved energy consumption model that effectively reflected the relationship between processing parameters 3.1.1 Intelligent manufacturing unit and energy consumption in machining processes was pro- posed based on empirical models and contributed to sus- The intelligent manufacturing unit is an independent pro- tainable manufacturing [102]. Krimpenis and Fountas cessing equipment in intelligent manufacturing, which is [103] studied the multi-objective machining optimization the smallest processing unit for intelligent manufacturing. problem based on a genetic algorithm and examined the A knowledge-driven digital twin manufacturing unit that influence of the key machining parameters of CNC supports self-manufacturing for the overall framework of machining operations. The different stages of the machine intelligent manufacturing was proposed [96]. Lohtander tools were introduced [104], including Machine 1.0, et al. [97] studied the digital twin technology based on Machine 2.0, Machine 3.0, and detailed key features of micro-manufacturing units. The intelligent manufacturing Machine 4.0, such as network physics machines and ver- unit contains various processing equipment, such as tical and horizontal integrated machine tools. Jeon and Ha machine tools, robots, and special equipment. [105] proposed a general method for generating the velocity distributions for acceleration and deceleration 3.1.1.1 Machine tools and equipment The machine tool techniques for CNC machine tools. A proportion integra- is mainly used to perform machining tasks. From the first tion differentiation iterative learning controller for the machine tool to the present, the machine tool has achieved CNC machine tools to perform repetitive tasks was pro- great development. The style, type, and technology also posed in Ref. [106]. Keller et al. [107] conducted a study experienced revolutionary innovation. on the reliability and maintainability of CNC machine tools CNC machine tools are automatic machine tools with a after analyzing the field fault data of 35 CNC machine tools. Yamato et al. [108] built an automatic flutter sup- program control system, which could solve the processing problems of complex and precision products and represent pression system for parallel turning, integrating on-line the development trend of modern machine tools. Compared flutter monitoring based on the cutting force estimation. with traditional machine tools, CNC machine tools have At present, the research on CNC machine tools mainly the following advantages: high processing precision, focuses on fault diagnosis, error compensation, parameter stable processing quality, high productivity and flexibility. optimization, etc., which greatly improve the fault diag- Many researchers conducted intelligent manufacturing-re- nosis efficiency and the machining accuracy of CNC lated research on CNC machine tools. machine tools. The research on CNC machine tools would A fault diagnosis strategy based on cascade faults was also be extended to online real-time monitoring of prod- proposed to ensure the safe operation of CNC machine ucts, smart machine tools, and green manufacturing. tools [98]. The state-based monitoring architecture was The cold heading machine is a type of machine tool that used for the alarm management of CNC machine tools uses a mold and a punch to make a part from a wire. The 123 Digital twin-based sustainable intelligent manufacturing: a review 7 force driven by the punch pushes the material from the the exchange of programming information for different mold into a new shape [109]. Li et al. [110] revealed the processing projects, and integration is difficult [117]. mechanical behavior and the dynamic response of the cold Slavkovic et al. [118] introduced an indirect method for heading machine and designed a new type of cold head industrial robot programming for machining tasks, saving force polyvinylidene fluoride piezoelectric film force sen- machining project information in a standard for exchange sor. The sensor has excellent dynamic performance and of product model data-numerical control format for an easy high precision measurement deformation ability. The exchange between different users for machining. A tool multi-station cold heading machine is an automated, high- path generation method based on a network model was precision forming equipment widely used in manufacturing studied and integrated into the offline robot programming for the mass production of bolts and nuts. The reliability of system to provide a comprehensive solution for robot the cold heading machine would affect the quality of the modeling, simulation, and tool path generation [119]. Some processed product and the processing efficiency [111]. researchers used modeling software to simulate the struc- Cold heading machines should meet the needs of a low- ture of industrial robots using the finite element method. carbon economy [112]. The research team of Shanghai Berg et al. [120] studied an interaction concept that uses University developed the first servo cold heading machine tracking of gestures and eyes to achieve a path to the tool in China, which opened a new direction for the cold robotic system and through projection to achieve a channel heading machine tool development. from the robotic system. Norrlof [121] studied an adaptive iterative learning control algorithm based on the estimation 3.1.1.2 Industrial robotics The automation and intelli- process and quadratic criterion optimization using the Kalman filter and successfully applied in industrial robots. gence of manufacturing are inseparable from the applica- tion of industrial robots, which are widely used in all In addition, research on underactuated robots has made aspects of manufacturing. With the development of the great progress [122–124]. manufacturing industry, the types and functions of indus- The research on industrial robots makes industrial robots trial robots are becoming more diverse. In the process of more competitive in an application. With higher precision, traditional manufacturing to intelligent manufacturing, smaller error, more reasonable structure, more convenient industrial robots would also usher in a new and greater programming, and more friendly human-computer inter- development. action, industrial robots are becoming increasingly impor- In recent years, an increasing number of researchers tant in industrial applications. have been working on industrial robots. Some industrial robots must be taught before application to ensure effi- 3.1.1.3 Special equipment Special equipment includes mining machinery, oil drilling equipment, special metal- ciency. A scheme was proposed to minimize external force estimation errors and reduce guidance task interference by lurgical equipment, and other special equipment. using virtual mass and virtual friction models for the Researchers studied the use of hydrogen as a fuel in mining manual teaching of industrial robots without force sensors machinery to meet sustainability requirements [125]. Islam [113]. The accuracy of industrial robots is affected by the et al. [126] studied the vibration problem of holding oil and uncertain parameters of link size and joint clearance gas through simulation experiments. Andreev et al. [127] deviation. Pe´rez et al. [114] studied the synergy between studied the technical parameters of the complex non-fur- virtual reality and robots to create a fully immersive nace treatment of blast furnace cast iron by the pulsating environment based on virtual reality, thereby improving the inert gas injection method, which significantly increased efficiency of the training and simulation process and pro- the operation resistance of metallurgical equipment. viding a cost-effective solution. Industrial robots can sub- mit efficiency and precision through teaching and training. 3.1.2 Intelligent manufacturing production line In addition, they may also experience problems, such as loss of posture during exercise. An interval method was The intelligent manufacturing line consists of a series of used to analyze the motion response of industrial robots precisely arranged intelligent manufacturing units that with uncertain, but bounded parameters [115]. A path could be processed more flexibly and intelligently. Indri planning method was proposed to ensure that the floating et al. [128] researched on a new paradigm of production base reached the predetermined attitude when the end-ef- lines based on three different sensor development methods fector of the space-based n-joint manipulator moved to the characterized by a high degree of flexibility. The thin-film predetermined position [116]. An improved omnidirec- solar cell production line production capacity is low. The tional mobile industrial robot tracking and localization low-pressure chemical vapor deposition (LPCVD) is the algorithm could be proposed to solve the problem of atti- main process leading to low productivity. To solve this tude loss in motion. Industrial robots are inconvenient in problem, a method of prioritizing the LPCVD process work 123 8 B. He, K.-J. Bai list was proposed, which greatly increased the production palm-based biomass [134]. A mesoscale simulation method capacity and prolonged the service life of the device [129]. was proposed for heavy oil petroleum structural units and A task scheduling strategy was proposed based on a hybrid dissipative ion dynamics and used to simulate various heuristic algorithm after studying the task scheduling heavy oil petroleum systems [135]. strategy of fog computing, which solved the problem of Research on process manufacturing systems focused on limited computing resources and high energy consumption the petrochemical industry. Future research will focus on in intelligent production lines [130]. A large number of intelligence, safety, and efficiency. simulation experiments are required to reduce cost and save time before a production line is put into use. The 3.2.2 Discrete manufacturing system intelligent production line fully verifies the availability of the production line by communicating with the external Discrete manufacturing systems refer to products that are real programmable logic controller. The genetic algorithm- made up of many independently machined parts ultimately based approach is applied to the overhead shuttle (OHS) assembled into a system of products. This section intro- system design of flat panel display production lines [131]. duces discrete manufacturing systems from the perspective To solve the problem of low efficiency and poor model of the product life cycle, from design, production, logistics, quality of the production line modeling method, the con- and sales. cept of the digital twin production line was proposed, and the real-time modeling and simulation method of the digital 3.2.2.1 Design The design could be divided into con- twin production line were studied [132]. Its effectiveness ventional and innovative designs. was verified on the product assembly line. Research on (i) Conventional design intelligent manufacturing production lines still mainly Given that existing computer-aided design systems do not focused on improving productivity. However, a few studies effectively provide the proper use of geometric tolerances, also combined virtual platforms, such as production lines Lemu [136] proposed an algorithm development solution and digital twin, which will be a research direction in the to achieve appropriate tolerances and conditions for use future. during the design specification phase. The facial prosthesis system based on computer-aided design/computer-aided 3.2 Sustainable intelligent manufacturing system manufacturing (CAD/CAM) was developed for the manu- facture of facial prosthesis [137]. Lv and Lin [138] The intelligent manufacturing system is a human-machine developed a real-time operational planning system in a integrated intelligent system composed of intelligent distributed manufacturing network that significantly machines and experts. According to different processing reduced planned workload. Gu et al. [139] studied the methods, intelligent manufacturing systems could be divi- design of a multi-stage reconfigurable manufacturing sys- ded into process manufacturing systems and discrete tem and measured the production loss, throughput stabi- manufacturing systems. According to the product life cycle lization time, and total production shortage time. Maturana process, discrete intelligent systems could be introduced et al. [140] proposed MetaMorph, an adaptive multi-agent from four aspects: design (e.g., low carbon design [133]), manufacturing system architecture for dynamically creat- production, logistics, and sales. This section introduces ing and managing agent communities. intelligent manufacturing systems. (ii) Innovative design 3.2.1 Process manufacturing system He et al. [141–147] used intelligent feature- and model- based methods, spatial matrix, parametric, and other Process manufacturing refers to the process in which the methods for intelligent design. The intelligent design sys- processed object continuously passes through the produc- tem was used in the design process of the product, making tion equipment, and the raw materials are physically or the design process more efficient with a higher precision chemically changed to finally obtain the product. The [148], a smaller error, and more sustainability [149] and process manufacturing system refers to the production generally requiring a computer-aided design system. A system applied to the process manufacturing process and is low-carbon design method based on carbon footprint was widely used in the petroleum and chemical industries. also proposed for product design [150–154]. Gregor et al. Three generations of systems can produce three products at [155] created the Zilina Intelligent Manufacturing System the same time, but their processing units are susceptible to expected to create an integrated collaborative environment failure. Accordingly, an integration framework was pro- that connected real, digital, and virtual. A low-carbon posed to solve the research on the three generations of 123 Digital twin-based sustainable intelligent manufacturing: a review 9 design method based on carbon footprint is also proposed [167] and in rationalizing the processing steps to make the for product design. process meet sustainability requirements. Research on intelligent design systems has made the Helo et al. [168] developed a cloud-based distributed design process more standardized, thereby greatly reducing manufacturing execution system to address the needs and challenges of managing distributed manufacturing in a workload and improving efficiency [156]. However, the current intelligent design system still has some shortcom- multi-company supply chain. The architecture of intelli- gent manufacturing systems was proposed based on dis- ings. The current intelligent design system is not intuitive in the design process. Therefore, integration with the vir- tributed artificial intelligence to shorten the product development cycle [169]. The structure of the intelligent tual reality technology and the collaborative design [157] would be the key research direction of the next stage. chemical industry network physical system was proposed and applied to the intelligent distillation tower [170]. The operation results showed that stability and robustness met 3.2.2.2 Production Intelligent production systems are the requirements. used in the processing of products, optimizing the pro- Resource-intelligence and access systems were devel- cessing steps of products, and improving the resource uti- oped based on the IoTs to realize the manufacturing model lization, adaptability, and robustness of manufacturing of cloud manufacturing [171]. Jain et al. [172] developed a systems. Manufacturing could be divided into two pro- digital twin model that implemented an estimate of the cesses: machining and assembly. measurable characteristic output of a photovoltaic energy (i) Machining conversion unit. Based on this model, 10 different faults, power converters, and electronic sensor faults were Simeone et al. [158] proposed an intelligent cloud manu- facturing platform for sheet metal cutting services that detected and identified in the photovoltaic energy conver- increased the utilization of supplier resources to 92.3%. sion unit. The detection and identification times were less The intelligent immune system for energy-saving manu- than 290 ls and 4 ms, respectively. Moreover, the fault facturing can achieve an energy savings of approximately detection and recognition time in the distributed photo- voltaic panels were less than 80 ms and 1.2 s, respectively. 30% in the factory and increase the production efficiency by more than 50% [159]. Stadnicka et al. [160] analyzed (ii) Assembly the role of humans in intelligent manufacturing systems An IoT intelligent assembly system framework was pro- and proposed innovative ways to learn how to simulate a posed based on the information and communication tech- virtual reality to transfer knowledge of intelligent manu- nology, sensor networks, and radio frequency identification facturing systems. In addition, considering the low carbon and applied to the assembly process of mechanical prod- requirements in the production process will save more ucts [173]. Research on the intelligent production system energy [161]. Tao et al. [162] proposed a cloud manufac- based on the agent technology can effectively improve the turing service system and a framework based on the IoTs system adaptability. An agent-based manufacturing system and cloud computing. They also analyzed the relationship architecture was proposed for application to hybrid multi- between the two. An advanced manufacturing IoT intelli- product production to improve the adaptability and gent manufacturing platform was designed based on IoTs, robustness of the manufacturing system [174]. Chaplin cloud computing, big data analysis, network physics sys- et al. [175] designed evolvable assembly systems using the tem, and prediction technology. This platform was then intelligent agent technology and data distribution services. applied to the bumping process of semiconductor compa- Intelligent production systems can be developed based on nies. The application results showed that the platform could distributed technologies to shorten the development cycle. perform comprehensive inspections in production [163]. Intelligent production systems for specific product research He et al. [164] put forward a new method of constraint meet specific production needs. Wang [176] introduced the mechanism function synthesis based on system dynamic general framework of a zero-defect manufacturing system programming, which was applied to the offshore platform and introduced the application of zero-defect manufactur- jacking system. A network physics system based on multi- ing methods to create zero-defect products. The network agent technology was developed and applied to the man- physical system architecture of the intelligent manufac- ufacturing workshop to improve the reconfigurability and turing workshop was proposed, and it verified the feasi- responsiveness of the workshop [165]. Lee et al. [166] bility of the architecture on a small flexible automated proposed the industrial IoT suite to run high value-added production line [177]. A custom-oriented intelligent man- manufacturing processes, implement intelligent production, ufacturing system was proposed, and a customizable candy and achieve re-industrialization in Hong Kong. These production system was established [178]. A labeling and studies effectively improved resource utilization and pro- management framework was proposed for steel label duction efficiency. Other studies focused on sustainability 123 10 B. He, K.-J. Bai characters, while a method for the online monitoring and sales services (see Fig. 3). Sustainable intelligent manu- tracking of marker characters based on machine vision was facturing service contains product development, manufac- proposed to realize information management and intelli- turing, and after sales services, which support each other. gent manufacturing for steel manufacturing [179]. A knowledge-based intelligent system for diagnosing web- 3.3.1 Product development services based management was studied, and its defects increased the wafer manufacturing throughput [180]. Specific intel- The product development service in the intelligent manu- ligent production systems enable agile manufacturing and facturing service mainly serves the whole process of pro- reduce the probability of defects. duct development, making the development process simple and efficient. This part includes collaborative design ser- 3.2.2.3 Logistics The intelligent logistics system is vice, product customization service, and so on. applied to the traceability of product processing and the management of product logistics information. Strandhagen 3.3.1.1 Collaborative design service Collaborative et al. [181] studied Industry 4.0 for manufacturing logistics. design service mainly provides a platform to integrate The study of four Norwegian manufacturing companies people with design requirements and capabilities. When showed that the practicality of Industry 4.0 in manufac- someone has design requirements, they can publish the turing logistics depended on the production environment. A requirements to the platform. People with design capabil- food traceability network physical system method based on ities can undertake the requirements and participate in the intelligent value stream was proposed to improve the effi- design together. Zhang et al. [190] proposed an intelligent ciency of the food traceability system [182]. Maoudj et al. manufacturing integration system that was applied to the [183] developed a distributed multi-agent system for projects they participated in and achieved good results. He scheduling and controlling robotic flexible assembly units. et al. [191] proposed sustainable supply chain design The production data are collected in real time for product model. Sun et al. [192] studied the security of networked traceability based on the intelligent logistics system control systems. McFarlane et al. [193] explored the impact developed by the radio frequency identification technology of automatic identification systems on the intelligent con- [184–188], realizing the production management and trol of manufacturing plants. To solve the layout opti- dynamic scheduling of the workshop. The intelligent mization problem of the multi-module satellite equipment, logistics system realizes the logistics function in intelligent a two-system co-evolution algorithm based on the bode manufacturing and can track the status and logistics coevolution framework was proposed [194]. Malik and information of the product in real time to realize dynamic Bilberg [195] proposed a digital and physical medical scheduling. workspace that combined the digital and physical worlds for collaborative design. To solve the problems in dis- 3.2.2.4 Sales The intelligent sales system is used to sell tributed collaborative design system of complex products, a manufactured products and manage sales information for group global search and negotiation algorithm based on intelligent sales. A vehicle sales integrated management fuzzy matter-element particle swarm optimization was system was studied. It can manage vehicle sales in a unified proposed [196]. manner and input real-time information into mobile devi- ces with high security [189]. Take the marketing module of a company’s collabora- Product development service tive manufacturing system as an example. The module has the functions of entering order information, querying order information, and managing customer information for Contain entering and managing order information. After the sales- person obtains the order, the order information is entered Support Support into the system, and the order information could then be Sustainable intelligent manufacturing service queried and managed. 3.3 Sustainable intelligent manufacturing services Contain Contain Support Intelligent manufacturing services for intelligent manu- Manufacturing service After sales service facturing have a wide range of applications. This section introduces intelligent manufacturing services from three aspects: product development, manufacturing, and after Fig. 3 Three aspects of intelligent manufacturing service 123 Digital twin-based sustainable intelligent manufacturing: a review 11 3.3.1.2 Product customization service A large-scale manufacturing service mainly serves the whole process of personalized production framework based on the concept product processing and manufacturing and provides ser- of Industry 4.0 was proposed and realized large-scale vices, such as monitoring, scheduling, online monitoring, personalized production in industrial practice [197]. Rød- sustainable manufacturing, and real-time warning for pro- seth et al. [198] developed a new model of deep digital duct processing. Kim and Hwangbo [216] developed an maintenance based on network physics systems and intelligent real-time early warning system for plastic film maintenance theory to achieve integrated planning. To production with a prediction accuracy close to 100%. achieve a new approach to personalization and cus- tomization, researchers are rapidly deploying resources 3.3.2.2 Intelligent control An intelligent decision sup- based on manufacturing services [199–204]. port system architecture based on radio frequency identi- fication was proposed for processing production 3.3.1.3 Other services The performance estimation monitoring and scheduling in a distributed manufacturing model-based optimization algorithm was studied [205] and environment [217]. Tan et al. [218] proposed an embedded applied to large-scale complex manufacturing system adaptive network service framework [219] and applied this simulations [206], reducing the run time by more than 7%. to networked manufacturing systems. A browser-server- A product lifecycle management application framework terminal model is proposed to realize remote control of based on the digital twin was proposed [207]. A view- embedded terminal devices, and a new method of remote based 3D CAD model reuse framework was proposed to control of embedded terminal devices is proposed [220]. enable the effective reuse of 3D CAD models in the pro- Theorin et al. [221] proposed a line information system duct life cycle [208]. He et al. [209] used the low-carbon architecture for flexible plant integration and data appli- concept to optimize the structure of the product to meet the cations. A mapping-based computational experimental low carbon requirements. Bodrow [210] proposed an approach was proposed and used to solve the complexity of application scenario for knowledge visualization to test the the construction and development of the manufacturing expertise and demonstrated its usefulness in intelligent service ecosystem and analyze the evolution of the manu- software applications for process control. Giret et al. [211] facturing service ecosystem [222]. proposed a specific software engineering approach to help developers develop a sustainable intelligent manufacturing 3.3.2.3 Collaborative manufacturing In addition, for the system, called Go-green ANEMONA. A graph-based problem of close contact between users and manufacturers, knowledge reuse method was proposed to support knowl- a synergistic-based service combination approach can be edge-driven decision making in product development, used to connect users to manufacturers and make full use of reuse the knowledge already in the manufacturing industry, resources to create a collaborative manufacturing platform and improve the product innovation quality [212]. [223–228]. Through research on intelligent development services, Take an equipment collaborative manufacturing system the running time of the complex manufacturing system as an example to illustrate the intelligent manufacturing simulation is shortened, and the accuracy and the real-time service [229]. The equipment collaborative manufacturing performance of online monitoring systems are improved, system is a collaborative manufacturing platform that making product development easier. integrates customers, experts, and manufacturing compa- nies. The customers are provided with collaborative design 3.3.2 Manufacturing service and collaborative manufacturing services. When customers have design or manufacturing requirements, but do not Manufacturing services mainly include intelligent moni- have the conditions for completion, they can post demand toring, intelligent control, and collaborative manufacturing. orders on the platform, describe the requirements in detail, provide the necessary documentation, and wait for experts 3.3.2.1 Intelligent monitoring A 3D visual monitoring or a manufacturing company to accept the order. system for production lines based on OpenGL modeling on For a company, when a customer issues a demand order, the VC??6.0 platform was established to meet effective the company first reviews and evaluates whether it can production [213]. A grey online modeling surface rough- complete the order. If yes, it directly accepts the order, ness monitoring system was developed to accurately pre- directly connects with the customer, and no longer pub- dict the surface roughness in end milling [214]. Machine lishes it on the platform; otherwise, the order will be sorted center fault diagnosis and prediction based on data mining out. The order is then released to the platform for experts or were studied to develop a systematic approach and obtain manufacturing companies that cooperate with the platform. predictive maintenance knowledge in the Industry 4.0 era A platform for experts or manufacturing companies to [215]. The manufacturing service in the intelligent undertake design or manufacturing orders is provided. 123 12 B. He, K.-J. Bai When an expert or a manufacturing company finds an value of the cloud manufacturing service platform [238]. appropriate order on the platform, it can apply for the Lartigau et al. [239] proposed a service quality assessment- order. They can then establish contact on the platform after based approach for transport impact analysis. the platform administrator approves the application. Such an equipment collaborative manufacturing system inte- 3.3.3.2 Fault maintenance The interstitial error data grates customers, experts, and manufacturing companies interpretation and the compensation of machine center into a closed loop of manufacturing, thereby providing intelligent predictive maintenance were studied based on intelligent services to customers, experts, and manufac- an artificial neural network [240]. The research results turing companies and enabling them to benefit from them. showed that the gap error in the front and back directions of With the increasing use of cloud applications, tech- the machining center could be predicted and compensated. nologies, such as cloud manufacturing and cloud services, Liu and Ming [241] proposed a framework for the revision can be applied to the after-sales service of intelligent of the rough Decision Making Trial and Evaluation Lab- manufacturing services. A dynamic ant colony genetic oratory method for capturing and evaluating intelligent hybrid algorithm was proposed for solving large-scale industrial product service systems. cloud service composition and optimization problems The after-sales service research includes fault warning, [230]. A multi-objective hybrid artificial bee colony algo- fault diagnosis, quality maintenance, and cloud-based rithm was proposed for service composition and opti- after-sales service. Fault warning and diagnosis enable the mization selection in cloud manufacturing [231]. An offline user to grasp the status of the product in real time and take 3D automated printer approach to enhance the competi- corresponding measures according to the feedback in time, tiveness of 3D printing was developed based on the cloud which greatly increases the service life of the product. manufacturing service model and the 3D printing cloud service platform [232]. The optimal choice of a cloud service portfolio in cloud manufacturing was studied, and a 4 Framework of digital twin-driven sustainable cloud service category and a service quality index were intelligent manufacturing established [233]. The agent-based manufacturing service discovery framework was studied. This framework consists This study proposed the framework of digital twin-driven of an object- and model-based manufacturing task agent, a sustainable intelligent manufacturing (see Fig. 4). manufacturing service agent, and task and service matching Digital twin-driven sustainable intelligent manufactur- process knowledge base to realize the manufacturing ser- ing consists of a basic platform, sustainable intelligent vice discovery in a cloud manufacturing environment manufacturing equipment, sustainable intelligent manu- [234]. The development of the cloud manufacturing service facturing system, and sustainable intelligent manufacturing platform provides technical support. A cloud manufactur- service. Among them, the basic platform is mapped with ing service platform for small- and medium-sized enter- sustainable intelligent manufacturing equipment, sustain- prises, which implements semantic intelligence search, able intelligent manufacturing system, and sustainable order tracking, event task guidance, and collaborative intelligent manufacturing service. The sustainable intelli- management, was developed [235]. gent manufacturing equipment, sustainable intelligent manufacturing system, and sustainable intelligent manu- 3.3.3 After-sales service facturing service support each other. Sustainable intelligent manufacturing platforms could be interconnected to inte- After-sales service mainly includes fault diagnosis and grate the value chain among enterprises and form a new maintenance. industrial form. The data of the basic platform comes from the equip- 3.3.3.1 Fault diagnosis DeSmit et al. [236] studied a ment layer of the platform, which includes equipment, unit, method for systematically identifying network physical production line, and production workshop. After the plat- vulnerabilities in intelligent manufacturing systems. This form obtains data from the device layer, it combines cloud method can analyze the potential impact of vulnerabilities in computing, artificial intelligence, IoTs, and other tech- intelligent manufacturing systems. Fault diagnosis and pre- nologies. It then comprehensively considers environmental, diction of wind turbines based on supervisory control and economic, and social factors and combines human, equip- data acquisition (SCADA) data were studied, and an artificial ment, and technology to provide data for virtual and intelligence-based framework was proposed for wind turbine physical prototyping. Virtual and physical prototyping map fault diagnosis and prediction using the SCADA data [237]. with sustainable intelligent manufacturing equipment, A neighborhood enhancement matrix decomposition sustainable intelligent manufacturing systems, and sus- method was proposed to predict the loss of the service quality tainable intelligent manufacturing services. 123 Digital twin-based sustainable intelligent manufacturing: a review 13 Fig. 4 Framework of digital twin-driven sustainable intelligent manufacturing 123 14 B. He, K.-J. Bai Sustainable intelligent manufacturing equipment intelligent manufacturing to achieve sustainable intelligent includes an intelligent manufacturing unit and an intelli- manufacturing is an important future research direction. As gent manufacturing production line. The intelligent man- a sustainable technology, it could reduce emissions in the ufacturing unit includes machine tools, robots, special life cycle of products, thereby achieving the requirements of both intelligent manufacturing and comprehensive sus- equipment, measurement and control equipment, and other equipment. Sustainable intelligent manufacturing equip- tainability from the perspective of environmental, eco- nomic, and social aspects. ment maps to virtual and physical prototyping. The sustainable intelligent manufacturing system (iii) Sustainable intelligent manufacturing for the product includes a discrete manufacturing system and a process life cycle manufacturing system. In the horizontal direction, the Sustainable intelligent manufacturing for the product life sustainable intelligent manufacturing system could be cycle, including design, production, logistics, sale, and divided into sustainable design, sustainable production, service, must be achieved. The virtual and augmented sustainable logistics, sustainable sales, and sustainable realities could be also used in the product life cycle. services and form a sustainable closed loop. In the vertical direction, it could be divided into automatic production (iv) Sustainable intelligent manufacturing across enter- prise value chain system, manufacturing execution system, and enterprise resource management. Discrete and process manufacturing The interconnection among enterprises could be more universal; thus, the intelligent manufacturing could pay systems overlap and differ in all directions. Sustainable intelligent manufacturing service includes more attention on the enterprise value chain. product development, manufacturing, and after-sales ser- (v) Sustainable intelligent manufacturing for product vices. Product development services include collaborative environmental footprint design, product customization, and others. Manufacturing The massive emissions of greenhouse gases, especially services include intelligent monitoring, intelligent control, carbon dioxide, have led to increasing global warming. and collaborative manufacturing. After-sales service Therefore, cleaner production is receiving global attention includes fault diagnosis and maintenance. in the manufacturing industry. The industry is responsible for producing products in an environmentally friendly manner. The European Union (EU) proposes the use of the 5 Future works product environmental footprint [245, 246], including 14 types of environmental factors (e.g., product carbon foot- It is gradually phasing out the industry with a heavy print, product water footprint, etc.) to simulate the envi- environmental burden. Developing intelligent manufactur- ronmental impact of the emissions generated during the ing with increasing attention on sustainability is vigorous. product life cycle. The environmental impact of manufac- Sustainability is paid increasing attention, thereby clearly turing is becoming increasingly serious. Hence, the chal- positioning the sustainable development of the manufac- lenges of improving production efficiency and reducing turing industry as the foundation. Sustainable intelligent carbon footprint during the product life cycle are receiving manufacturing plays an irreplaceable role. Several future increasing attention [247]. In studying the intelligent works are needed in this topic. manufacturing of the carbon footprint of products, one must consider the carbon emissions of products from raw 5.1 Framework of sustainable intelligent materials, processing, transportation, use, recycling, etc., to manufacturing guide the development of intelligent manufacturing. To achieve clean manufacturing, low-carbon manufacturing is (i) Sustainable intelligent design a future research direction. The design is the foundation of intelligent manufacturing; (vi) Human-machine collaboration therefore, the traditional design must urgently be upgraded Human and machine could interact with each other more to a sustainable intelligent design to achieve sustainable collaboratively in sustainable intelligent manufacturing, intelligent manufacturing. Virtual and physical prototyping which enables a human to have efficient and effective could be interconnected in real time at the design stage. decision-making with machines. Achieving a sustainable design for the sustainable supply (vii) Sustainable intelligent manufacturing equipment, chain is also important. sustainable intelligent manufacturing system, and (ii) Comprehensive sustainability sustainable intelligent manufacturing service The concept of sustainability has become an important topic [242–244], and combining sustainable concepts with 123 Digital twin-based sustainable intelligent manufacturing: a review 15 5.2 Enabling technology of sustainable intelligent 6 Conclusions manufacturing With the transformation and upgrade of manufacturing, (i) Digital twin-based big data-driven sustainable intel- sustainable intelligent manufacturing has become increas- ligent manufacturing ingly important. Intelligent manufacturing combined with a digital twin has the functions of intelligent sensing and With the implementation of intelligent manufacturing, simulation, which makes the production of products more manufacturing precision, product quality, and processing efficient and intelligent. At the same time, it could monitor efficiency would continuously improve. With the help of the status of products and production equipment in real the digital twin and big data technologies, a virtual simu- time and predict possible failures in time. After the intro- lation model of the solid model would be established, and duction of a digital twin and its application, three aspects of the entity status could be fed back in real time. The digital digital twin-driven sustainable intelligent manufacturing, twin could be applied to online real-time product inspec- namely sustainable intelligent manufacturing equipment, tion and equipment fault diagnosis and repair. sustainable intelligent manufacturing systems, and sus- (ii) Artificial intelligence-driven sustainable intelligent tainable intelligent manufacturing services, were intro- manufacturing duced. The framework of the digital twin-driven Information technology has achieved rapid development sustainable intelligent manufacturing was proposed in since the beginning of the 21st century. In recent years, detail. The future direction of digital twin-driven sustain- artificial intelligence has rapidly developed in the aspects able intelligent manufacturing was also discussed. of medical, monitoring, and interaction, thereby greatly changing people’s lifestyles. In the future, the intelligent Acknowledgements The work was supported by the National Nat- ural Science Foundation of China (Grant No. 51675319), and manufacturing process would inevitably reduce the human Shanghai Science and Technology Committee Project (Grant No. factor. Therefore, applying artificial intelligence to intelli- 19511104702). gent manufacturing, gradually replacing the role of human beings, and realizing unmanned intelligent manufacturing Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, will be the future research direction. adaptation, distribution and reproduction in any medium or format, as (iii) IoTs-driven sustainable intelligent manufacturing long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate The Internet of Things enables all objects that could per- if changes were made. The images or other third party material in this form independent functions to be connected to the network, article are included in the article’s Creative Commons licence, unless thereby enabling interconnection and interoperability to indicated otherwise in a credit line to the material. If material is not achieve the effect of the Internet of everything. Combining included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted IoTs with intelligent manufacturing enables the production use, you will need to obtain permission directly from the copyright equipment and production products to be interconnected. holder. To view a copy of this licence, visit http://creativecommons. The equipment can independently sense the processing org/licenses/by/4.0/. quality of the products and make timely adjustments to achieve independent production. References 5.3 Application of sustainable intelligent 1. Waschull S, Bokhorst JAC, Molleman E et al (2020) Work manufacturing design in future industrial production: transforming towards cyber-physical systems. Comput Ind Eng. 139:105679 Sustainable intelligent manufacturing must be put into 2. Javed Y, Felemban M, Shawly T et al (2019) A partition-driven integrated security architecture for cyber-physical systems. applications. For process intelligent manufacturing sys- arXiv:190103018[csSY] tems, such as those used in the steel, pharmaceutical, and 3. Van Der Zeeuw A, Van Deursen AJ, Jansen G (2019) petrochemical industries, and for the discrete intelligent Inequalities in the social use of the internet of things: a capital manufacturing system, such as that used in the mechanical and skills perspective. New Media Soc 21(6):1344–1361 4. Habibi M, Fazli M, Movaghar A (2019) Efficient distribution of manufacturing industry, the MES could play an important requests in federated cloud computing environments utilizing role in the manufacturing system. statistical multiplexing. Future Gener Comput Syst 90:451–460 5. Yan H, Yu P, Long D (2019) Study on deep unsupervised learning optimization algorithm based on cloud computing. In: 2019 international conference on intelligent transportation, Big data & smart city (ICITBS), pp 679–681 6. He B, Pan QJ, Deng ZQ (2018) Product carbon footprint for product life cycle under uncertainty. J Clean Prod 187:459–472 123 16 B. He, K.-J. Bai 7. Radhi H (2019) Multi-objective optimization of turning process with big data based feedback and coordination. Comput Netw during machining of AISI 1025 on CNC machine using multi- 101:158–168 objective particle swarm optimization. Univ Thi-Qar J Eng Sci 29. Grieves M (2014) Digital twin: manufacturing excellence 10(1):65–70 through virtual factory replication. White paper, pp 1–7 8. He B, Cao XY, Gu ZC (2020) Kinematics of underactuated 30. Abdulmotaleb ES (2018) Digital twins: the convergence of robotics for product carbon footprint. J Clean Prod 257:120491 multimedia technologies. IEEE Multimed 25(2):87–92 9. Chiaverini S, Siciliano B, Egeland O (1994) Review of the 31. Negri E, Fumagalli L, Macchi M (2017) A review of the roles of damped least-squares inverse kinematics with experiments on an digital twin in CPS-based production systems. Procedia Manuf industrial robot manipulator. IEEE Trans Control Syst Technol 11:939–948 2(2):123–134 32. Chhetri MB, Krishnaswamy S, Loke SW (2004) Smart virtual 10. Altintas Y, Yang J, Kilic ZM (2019) Virtual prediction and counterparts for learning communities. In: Bussler C et al (eds) constraint of contour errors induced by cutting force distur- Web information systems—WISE 2004 workshops, WISE 2004. bances on multi-axis CNC machine tools. CIRP Ann Springer, Berlin, pp 125–134 68(1):377–380 33. Glaessgen E, Stargel D (2012) The digital twin paradigm for 11. Zheng P, Wang HH, Sang ZQ et al (2018) Smart manufacturing future NASA and U.S. Air force vehicles. In: 2012 53rd AIAA/ systems for Industry 4.0: conceptual framework, scenarios, and ASME/ASCE/AHS/ASC Structures, structural dynamics and future perspectives. Front Mech Eng 13(2):137–150 materials conference, pp 1–14 12. Tao F, Qi QL, Liu A et al (2018) Data-driven smart manufac- 34. Lee J, Bagheri B, Kao HA (2015) A cyber-physical systems turing. J Manuf Syst 48:157–169 architecture for Industry 4.0-based manufacturing systems. 13. Zhong RY, Xu X, Klotz E et al (2017) Intelligent manufacturing Manuf Lett 3:18–23 in the context of Industry 4.0: a review. Engineering 35. So¨derberg R, Wa¨rmefjord K, Carlson JS et al (2017) Toward a 3(5):616–630 digital twin for real-time geometry assurance in individualized 14. Yadav A, Jayswal SC (2017) Modelling of flexible manufac- production. CIRP Ann 66(1):137–140 turing system: a review. Int J Prod Res 56(7):2464–2487 36. Bolton RN, McColl-Kennedy JR, Cheung L et al (2018) Cus- 15. Li BH, Hou BC, Yu WT et al (2017) Applications of artificial tomer experience challenges: bringing together digital, physical intelligence in intelligent manufacturing: a review. Front Inf and social realms. J Serv Manag 29(5):776–808 Technol Electron Eng 18(1):86–96 37. Tao F, Sui FY, Liu A et al (2019) Digital twin-driven product 16. Kusiak A (2017) Smart manufacturing. Int J Prod Res 56(1/ design framework. Int J Prod Res. 57(12):3935–3953 2):508–517 38. Hu LW, Nguyen NT, Tao WJ et al (2018) Modeling of cloud- 17. He B, Hua YC (2017) Feature-based integrated product model based digital twins for smart manufacturing with mt connect. for low-carbon conceptual design. J Eng Des 28(6):408–432 Procedia Manuf 26:1193–1203 18. Bouzary H, Frank Chen F (2018) Service optimal selection and 39. Tao F, Cheng JF, Qi QL et al (2017) Digital twin-driven product composition in cloud manufacturing: a comprehensive survey. design, manufacturing and service with big data. Int J Adv Int J Adv Manuf Technol 97(1/4):795–808 Manuf Technol 94(9/12):3563–3576 19. Bouzary H, Chen FF, Krishnaiyer K (2018) Service matching 40. Schleich B, Anwer N, Mathieu L et al (2017) Shaping the digital and selection in cloud manufacturing: a state-of-the-art review. twin for design and production engineering. CIRP Ann Procedia Manuf 26:1128–1136 66(1):141–144 20. Bauer D, Stock D, Bauernhansl T (2017) Movement towards 41. Haag S, Anderl R (2018) Digital twin—proof of concept. Manuf service-orientation and app-orientation in manufacturing it. Lett 15:64–66 Procedia CIRP 62:199–204 42. Guo JP, Zhao N, Sun L et al (2018) Modular based flexible 21. Giret A, Garcia E, Botti V (2016) An engineering framework for digital twin for factory design. J Ambient Intell Hum Comput service-oriented intelligent manufacturing systems. Comput Ind 10(3):1189–1200 81:116–127 43. Bao JS, Guo DS, Li J et al (2018) The modelling and operations 22. Cao Y, Wang SL, Kang L et al (2015) Study on machining for the digital twin in the context of manufacturing. Enterp Inf service modes and resource selection strategies in cloud manu- Syst 13(4):534–556 facturing. Int J Adv Manuf Technol 81(1/4):597–613 44. Cheng Y, Tao F, Xu LD et al (2016) Advanced manufacturing 23. He B, Zhang D, Gu ZC et al (2020) Skeleton model-based systems: supply-demand matching of manufacturing resource product low carbon design optimization. J Clean Prod. https:// based on complex networks and internet of things. Enterp Inf doi.org/10.1016/j.jclepro.2020.121687 Syst 12(7):780–797 24. Grossmann IE (2019) Optimization and management in manu- 45. Bilberg A, Malik AA (2019) Digital twin driven human–robot facturing engineering: resource collaborative optimization and collaborative assembly. CIRP Ann 68(1):499–502 management through the internet of things. Optim Methods 46. Um J, Weyer S, Quint F (2017) Plug-and-simulate within Softw 34(1):220–223 modular assembly line enabled by digital twins and the use of 25. Soni R, Bhatia M, Singh T (2019) Digital twin: intersection of automation ML. IFAC-PapersOnLine 50(1):15904–15909 mind and machine. Int J Comput Intell IoT 2(3):667–670 47. Qi QL, Tao F, Zuo Y et al (2018) Digital twin service towards 26. Zheng P, Lin Y, Chen CH et al (2018) Smart, connected open smart manufacturing. Procedia CIRP 72:237–242 architecture product: an IT-driven co-creation paradigm with 48. Leng JW, Zhang H, Yan DX et al (2018) Digital twin-driven manufacturing cyber-physical system for parallel controlling of lifecycle personalization concerns. Int J Prod Res 57(8):2571–2584 smart workshop. J Ambient Intell Hum Comput 27. Nikolakis N, Alexopoulos K, Xanthakis E et al (2019) The 10(3):1155–1166 digital twin implementation for linking the virtual representation 49. Cheng Y, Zhang YP, Ji P et al (2018) Cyber-physical integration of human-based production tasks to their physical counterpart in for moving digital factories forward towards smart manufac- the factory-floor. Int J Comput Integr Manuf 32(1):1–12 turing: a survey. Int J Adv Manuf Technol 97(1/4):1209–1221 28. Wang SY, Wan JF, Zhang DQ et al (2016) Towards smart 50. Meng SH, Tang SL, Zhu YH et al (2019) Digital twin-driven factory for Industry 4.0: a self-organized multi-agent system control method for robotic automatic assembly system. IOP Conf Ser Mater Sci Eng 493:012128 123 Digital twin-based sustainable intelligent manufacturing: a review 17 51. Xiang F, Zhi Z, Jiang GZ (2018) Digital twins technology and 70. Liu Y, Zhang L, Yang Y et al (2019) A novel cloud-based its data fusion in iron and steel product life cycle. In: 2018 IEEE framework for the elderly healthcare services using digital twin. 15th international conference on networking, sensing and con- IEEE Access 7:49088–49101 trol (ICNSC), pp 1–5 71. Balachandar S, Chinnaiyan R (2019) Reliable digital twin for 52. Zhang H, Liu Q, Chen X et al (2017) A digital twin-based connected footballer. In: International conference on computer approach for designing and multi-objective optimization of networks and communication technologies. pp 185–191 hollow glass production line. IEEE Access 5:26901–26911 72. Guivarch D, Mermoz E, Marino Y et al (2019) Creation of 53. Zhuang CB, Liu JH, Xiong H (2018) Digital twin-based smart helicopter dynamic systems digital twin using multibody simu- production management and control framework for the complex lations. CIRP Ann 68(1):133–136 product assembly shop-floor. Int J Adv Manuf Technol 96(1/ 73. Tao F, Zhang M, Liu YS et al (2018) Digital twin driven 4):1149–1163 prognostics and health management for complex equipment. 54. Liu Q, Zhang H, Leng JW et al (2018) Digital twin-driven rapid CIRP Ann 67(1):169–172 individualised designing of automated flow-shop manufacturing 74. Lynn R, Chen A, Locks S et al (2015) Intelligent and accessible system. Int J Prod Res 57:3903–3919 data flow architectures for manufacturing system optimization. 55. Liau Y, Lee H, Ryu K (2018) Digital twin concept for smart In: Umeda S, Nakano M, Mizuyama H et al (eds) Advances in injection molding. IOP Conf Ser Mater Sci Eng 324:012077 production management systems: innovative production man- 56. Botkina D, Hedlind M, Olsson B et al (2018) Digital twin of a agement towards sustainable growth. Springer, Berlin, pp 27–35 cutting tool. Procedia CIRP 72:215–218 75. Luo W, Hu T, Zhang C et al (2018) Digital twin for CNC 57. Pairet E, Ardo´n P, Liu X et al (2019) A digital twin for human– machine tool: modeling and using strategy. J Ambient Intell robot interaction. In: 2019 14th ACM/IEEE international con- Hum Comput 10(3):1129–1140 ference on human-robot interaction (HRI), pp 372-372 76. Li CZ, Mahadevan S, Ling Y et al (2017) Dynamic bayesian 58. Voinov N, Chernorutsky I, Drobintsev P et al (2017) An network for aircraft wing health monitoring digital twin. AIAA J approach to net-centric control automation of technological 55(3):930–941 processes within industrial IoT systems. Adv Manuf 77. Kaebernick H, Kara S, Sun M (2003) Sustainable product 5(4):388–393 development and manufacturing by considering environmental 59. Uhlemann THJ, Schock C, Lehmann C et al (2017) The digital requirements. Robot Comput Integr Manuf 19(6):461–468 twin: demonstrating the potential of real time data acquisition in 78. Rusinko C (2007) Green manufacturing: an evaluation of production systems. Procedia Manuf 9:113–120 environmentally sustainable manufacturing practices and their 60. Coronado PDU, Lynn R, Louhichi W et al (2018) Part data impact on competitive outcomes. IEEE Trans Eng Manag integration in the shop floor digital twin: mobile and cloud 54(3):445–454 technologies to enable a manufacturing execution system. 79. Miller G, Pawloski J, Standridge CR (2010) A case study of J Manuf Syst 48:25–33 lean, sustainable manufacturing. J Ind Eng Manag 3(1):11–32 61. Schluse M, Priggemeyer M, Atorf L et al (2018) Experi- 80. Akbar M, Irohara T (2018) Scheduling for sustainable manu- mentable digital twins—streamlining simulation-based systems facturing: a review. J Clean Prod 205:866–883 engineering for Industry 4.0. IEEE Trans Ind Inf 81. Carvalho N, Chaim O, Cazarini E et al (2018) Manufacturing in 14(4):1722–1731 the fourth industrial revolution: a positive prospect in sustain- 62. Macchi M, Roda I, Negri E et al (2018) Exploring the role of able manufacturing. Procedia Manuf 21:671–678 digital twin for asset lifecycle management. IFAC-PapersOn- 82. Gbededo MA, Liyanage K, Garza-Reyes JA (2018) Towards a Line 51(11):790–795 life cycle sustainability analysis: a systematic review of 63. Kunath M, Winkler H (2018) Integrating the digital twin of the approaches to sustainable manufacturing. J Clean Prod manufacturing system into a decision support system for 184:1002–1015 improving the order management process. Procedia CIRP 83. Koren Y, Gu X, Badurdeen F et al (2018) Sustainable living 72:225–231 factories for next generation manufacturing. Procedia Manuf 64. Biesinger F, Meike D, Kraß B et al (2018) A case study for a 21:26–36 digital twin of body-in-white production systems general con- 84. Stoycheva S, Marchese D, Paul C et al (2018) Multi-criteria cept for automated updating of planning projects in the digital decision analysis framework for sustainable manufacturing in factory. In: 2018 IEEE 23rd international conference on automotive industry. J Clean Prod 187:257–272 emerging technologies and factory automation (ETFA), 85. Moldavska A, Welo T (2019) A holistic approach to corporate pp 19–26 sustainability assessment: incorporating sustainable develop- 65. Vachalek J, Bartalsky´ L, Rovny´ O et al (2017) The digital twin ment goals into sustainable manufacturing performance evalu- of an industrial production line within the Industry 4.0 concept. ation. J Manuf Syst 50:53–68 In: 2017 21st international conference on process control (PC), 86. Physicsweb. http://www.Miit.Gov.Cn/n1146295/n1652858/ pp 258–262 n1652930/n3757016/c6429243/content.Html. Accessed 14 Aug 66. Uhlemann THJ, Lehmann C, Steinhilper R (2017) The digital 2018 twin: realizing the cyber-physical production system for Indus- 87. Stock T, Seliger G (2016) Opportunities of sustainable manu- try 4.0. Procedia CIRP 61:335–340 facturing in Industry 4.0. Procedia CIRP 40:536–541 67. Tao F, Zhang M (2017) Digital twin shop-floor: a new shop- 88. Garetti M, Taisch M (2012) Sustainable manufacturing: trends and research challenges. Prod Plan Control 23(2/3):83–104 floor paradigm towards smart manufacturing. IEEE Access 5:20418–20427 89. He B, Zhou GF, Hou SC et al (2016) An approach to compu- 68. He B, Deng ZQ, Huang S et al (2014) Application of unascer- tational co-evolutionary product design. Int J Adv Manuf tained number for the integration of carbon footprint in con- Technol 90(1/4):249–265 ceptual design. Proc Inst Mech Eng J Eng Manuf 90. Kang HS, Lee JY, Choi S et al (2016) Smart manufacturing: past 229(11):2088–2092 research, present findings, and future directions. Int J Precis Eng 69. Martinez HV, Neely AD, Ouyang A et al (2019) Service busi- Manuf Green Technol 3(1):111–128 ness model innovation: the digital twin technology. EurOMA. https://doi.org/10.17863/CAM.35482 123 18 B. He, K.-J. Bai 91. Walshe K, McKee M, McCarthy M et al (2013) Health systems and criticality analysis. Int J Adv Manuf Technol 100(5/ and policy research in Europe: Horizon 2020. Lancet 8):1695–1717 382(9893):668–669 112. Li ZM (2016) The knowledge expression for the low carbon 92. Hemphill TA (2014) Policy debate: the US advanced manu- economy of cold heading machine. J Low Carbon Econ facturing initiative: will it be implemented as an innovation—or 05(02):20–25 industrial—policy? Innovation 16(1):67–70 113. Zhang SL, Wang S, Jing FS et al (2019) A sensorless hand 93. Lewis P, Bell K (2019) Understanding the UK’s productivity guiding scheme based on model identification and control for problems: new technological solutions or a case for the renewal industrial robot. IEEE Trans Ind Inf 15:5204–5213 of old institutions? Employ Relat Int J 41(2):296–312 114. Pe´rez L, Diez E, Usamentiaga R et al (2019) Industrial robot 94. Radanliev P, De Roure D, Nurse JR et al (2019) New devel- control and operator training using virtual reality interfaces. opments in cyber physical systems, the internet of things and the Comput Ind 109:114–120 digital economy—discussion on future developments in the 115. Wu JH, Han X, Tao YR (2019) Kinematic response of industrial industrial internet of things and Industry 4.0. Preprints 2019, robot with uncertain-but-bounded parameters using interval 2019030094 analysis method. J Mech Sci Technol 33(1):333–340 95. Yeung G (2019) ‘Made in China 2025’: the development of a 116. Chen Z, Zhou W (2017) Path planning for a space-based new energy vehicle industry in China. Area Dev Policy manipulator system based on quantum genetic algorithm. 4(1):39–59 J Robot. 3207950 96. Zhou GH, Zhang C, Li Z et al (2019) Knowledge-driven digital 117. Guo S, Fang TT, Song T et al (2018) Tracking and localization twin manufacturing cell towards intelligent manufacturing. Int J for omni-directional mobile industrial robot using reflectors. Prod Res 58:1034–1051 Adv Manuf 6(1):118–125 97. Lohtander M, Ahonen N, Lanz M et al (2018) Micro manu- 118. Slavkovic N, Zivanovic S, Milutinovic D (2019) An indirect facturing unit and the corresponding 3D-model for the digital method of industrial robot programming for machining tasks twin. Procedia Manuf 25:55–61 based on STEP-NC. Int J Comput Integr Manuf 32(1):43–57 98. Zhang YZ, Mu LM, Shen GX et al (2019) Fault diagnosis 119. Lyu H, Liu Y, Guo JY et al (2019) Tool-path generation for strategy of CNC machine tools based on cascading failure. industrial robotic surface-based application. Adv Manuf J Intell Manuf 30(5):2193–2202 7(1):64–72 99. Villalonga A, Beruvides G, Castan˜o F et al (2018) Condition- 120. Berg J, Lottermoser A, Richter C et al (2019) Human-robot- based monitoring architecture for CNC machine tools based on interaction for mobile industrial robot teams. Procedia CIRP global knowledge. IFAC-PapersOnLine 51(11):200–204 79:614–619 100. Yang HT, Li L, Zhang SD et al (2019) Critical point determi- 121. Norrlof M (2002) An adaptive iterative learning control algo- nation method of thermal-force coupling deformation of CNC rithm with experiments on an industrial robot. IEEE Trans Rob machine tool bed. In: Tenth international symposium on preci- Autom 18(2):245–251 sion engineering measurements and instrumentation, 122. Gao Z, Zeng L, He B et al (2018) Type synthesis of non-holo- pp 1105325 nomic spherical constraint underactuated parallel robotics. Acta 101. Wei XY, Miao EM, Liu H et al (2019) Two-dimensional ther- Astronaut 152:509–520 mal error compensation modeling for worktable of CNC 123. He B, Wang S, Liu Y (2019) Underactuated robotics: a review. machine tools. Int J Adv Manuf Technol 101(1/4):501–509 Int J Adv Robot Syst 16(4):1–29 102. Jiang ZP, Gao D, Lu Y et al (2019) Electrical energy con- 124. He B, Zhang P, Liu W et al (2017) Dynamics analysis and sumption of CNC machine tools based on empirical modeling. numerical simulation of a novel underactuated robot wrist. Proc Int J Adv Manuf Technol 100(9/12):2255–2267 Inst Mech Eng J Eng Manuf 231(12):2145–2158 103. Krimpenis AA, Fountas NA (2016) Balancing multiple criteria 125. Fu´nez Guerra C, Reyes-Bozo L, Vyhmeister E et al (2019) in formulation of weighted, single-objective genetic algorithm Viability analysis of underground mining machinery using green optimization for CNC machining problems. Adv Manuf hydrogen as a fuel. Int J Hydrogen Energy 45:5112–5121 4(2):178–188 126. Islam MS, Peter N, Wiens T (2019) Simulation and experiment 104. Xu X (2017) Machine tool 4.0 for the new era of manufacturing. of vibrational or acoustic communication in mining and oil-gas Int J Adv Manuf Technol 92(5/8):1893–1900 drill strings. Trans Can Soc Mech Eng 43:454–462 105. Jeon JW, Ha YY (2000) A generalized approach for the accel- 127. Andreev V, Voronkova L, Lybianoi D (2019) Innovative tech- eration and deceleration of industrial robots and CNC machine nology of manufacturing of reusable metallurgical equipment tools. IEEE Trans Ind Electron 47(1):133–139 with increased operational resistance from the blast furnace cast 106. Kim DI, Kim S (1996) An iterative learning control method with iron of the first melting. J Mater Sci Res Rev 2:1–8 application for CNC machine tools. IEEE Trans Ind Appl 128. Indri M, Lachello L, Lazzero I et al (2019) Smart sensors 32(1):66–72 applications for a new paradigm of a production line. Sensors 107. Keller A, Kamath A, Perera U (1982) Reliability analysis of 19(3):650. https://doi.org/10.3390/s19030650 CNC machine tools. Reliab Eng 3(6):449–473 129. Dong X, Ma R (2019) Optimization of the LPCVD equipment 108. Yamato S, Yamada Y, Nakanishi K et al (2018) Integrated in- intergraded production system of the solar cell production line. process chatter monitoring and automatic suppression with AIP Conf Proc 2122(1):1–5 adaptive pitch control in parallel turning. Adv Manuf 130. Wang J, Li D (2019) Task scheduling based on a hybrid heuristic algorithm for smart production line with fog comput- 6(3):291–300 109. He B, Wang J, Huang S et al (2015) Low-carbon product design ing. Sensors 19(5):1–18 for product life cycle. J Eng Des 26(10–12):321–339 131. Hwang I, Jang YJ, Choi H (2018) Overhead shuttle design for a 110. Li YJ, Wang GC, Cui HY et al (2019) Dynamic characteristics flat panel display production line considering the contactless and optimization research on PVDF piezoelectric film force power supply capacity. Comput Ind Eng 126:232–242 sensor for steel ball cold heading machine. ISA Trans 132. Gao Y, Lyu H, Hou Y et al (2019) Real-time modeling and 94:265–275 simulation method of digital twin production line. In: 2019 IEEE 111. He B, Xue HJ, Liu LL et al (2019) Rigid-flexible coupling 8th joint international information technology and artificial virtual prototyping-based approach to the failure mode, effects, intelligence conference (ITAIC), pp 1639–1642 123 Digital twin-based sustainable intelligent manufacturing: a review 19 133. He B, Wang J, Deng ZQ (2015) Cost-constrained low-carbon 155. Gregor M, Hercko J, Fusko M et al (2019) Zilina intelligent product design. Int J Adv Manuf Technol 79(9/12):1821–1828 manufacturing system: best practice of cooperation between 134. Andiappan V, Benjamin MFD, Tan RR et al (2019) An inte- university and research center. In: Caganova D, Balog M, grated framework to address criticality in biomass tri-generation Knapcikova L et al (eds) Smart technology trends in industrial systems via redundancy allocation. Process Integr Optim Sustain and business management. Springer, Berlin, pp 183–198 3(1):65–73 156. He B, Li FF, Cao XY et al (2020) Product sustainable design: a 135. Guan D, Feng S, Zhang L et al (2019) Mesoscale simulation for review from the environmental, economic, and social aspects. heavy petroleum system using structural unit and dissipative ASME J Comput Inf Sci Eng 20:040801 particle dynamics (SU–DPD) frameworks. Energy Fuel 157. He B, Wang YG, Song W et al (2014) Design resource man- 33(2):1049–1060 agement for virtual prototyping in product collaborative design. 136. Lemu HG (2014) Current status and challenges of using geo- Proc Inst Mech Eng J Eng Manuf 229(12):2284–2300 metric tolerance information in intelligent manufacturing sys- 158. Simeone A, Caggiano A, Boun L et al (2019) Intelligent cloud tems. Adv Manuf 2(1):13–21 manufacturing platform for efficient resource sharing in smart 137. Sun J, Xi J, Chen X et al (2011) A CAD/CAM system for manufacturing networks. Procedia CIRP 79:233–238 fabrication of facial prostheses. Rapid Prototyp J 17(4):253–261 159. Wang S, Liang YC, Li WD et al (2018) Big data enabled 138. Lv YQ, Lin DP (2017) Design an intelligent real-time operation intelligent immune system for energy efficient manufacturing planning system in distributed manufacturing network. Ind management. J Clean Prod 195:507–520 Manag Data Syst 117(4):742–753 160. Stadnicka D, Litwin P, Antonelli D (2019) Human factor in 139. Gu X, Jin XN, Ni J et al (2015) Manufacturing system design for intelligent manufacturing systems—knowledge acquisition and resilience. Procedia CIRP 36:135–140 motivation. Procedia CIRP 79:718–723 140. Maturana F, Shen W, Norrie DH (1999) Metamorph: an adap- 161. He B, Tang W, Wang J et al (2015) Low-carbon conceptual tive agent-based architecture for intelligent manufacturing. Int J design based on product life cycle assessment. Int J Adv Manuf Prod Res 37(10):2159–2173 Technol 81(5/8):863–874 141. He B, Hou S, Song W (2015) Integrating engineering design and 162. Tao F, Cheng Y, Xu LD et al (2014) CCIOT-CMFG: cloud analysis using a parameter constraint graph approach. Simula- computing and internet of things-based cloud manufacturing tion 91(7):625–647 service system. IEEE Trans Ind Inf 10(2):1435–1442 142. He B, Hua Y (2016) Synthesis of mechanisms integrated with 163. Lin YC, Hung MH, Huang HC et al (2017) Development of motion and force transformation. Int J Precis Eng Manuf advanced manufacturing cloud of things (AMCOT)—a smart 17(12):1643–1649 manufacturing platform. IEEE Rob Autom Lett 2(3):1809–1816 143. He B, Huang S (2016) Functional synthesis of mechanisms 164. He B, Zhang P, Liu L (2014) Simultaneous functional synthesis under cost consideration. Proc Inst Mech Eng J Eng Manuf of mechanisms with mechanical efficiency and cost. Int J Adv 230(1):91–99 Manuf Technol 75(5/8):659–665 144. He B, Song W, Wang Y (2015) Computational conceptual 165. Zhang YF, Qian C, Lyu JX et al (2017) Agent and cyber- design using space matrix. J Comput Inf Sci Eng 15(1):1–7 physical system based self-organizing and self-adaptive intelli- 145. He B, Song W, Wang YG (2013) A feature-based approach gent shopfloor. IEEE Trans Ind Inf 13(2):737–747 towards an integrated product model in intelligent design. Int J 166. Lee CKM, Zhang SZ, Ng KKH (2017) Development of an Adv Manuf Technol 69(1/4):15–30 industrial internet of things suite for smart factory towards re- 146. He B, Zhang P, Wang J (2014) Automated synthesis of mech- industrialization. Adv Manuf 5(4):335–343 anisms with consideration of mechanical efficiency. J Eng Des 167. He B, Niu YC, Hou SC et al (2018) Sustainable design from 25(4/6):213–237 functional domain to physical domain. J Clean Prod 147. He B, Zhang P, Zhu N et al (2016) Skeleton model-based 197:1296–1306 approach to integrated engineering design and analysis. Int J 168. Helo P, Suorsa M, Hao Y et al (2014) Toward a cloud-based Adv Manuf Technol 85(5):1105–1115 manufacturing execution system for distributed manufacturing. 148. He B, Ostrosi E, Pfaender F et al (2014) Intelligent engineering Comput Ind 65(4):646–656 design of complex city: a co-evolution model. In: Cha J, Chou 169. Guo QL, Zhang M (2009) A novel approach for multi-agent- SY, Stjepandic J et al (eds) Moving integrated product devel- based intelligent manufacturing system. Inf Sci opment to service clouds in the global economy. IOS Press, 179(18):3079–3090 Amsterdam, pp 434–443 170. Ji X, He G, Xu JJ et al (2016) Study on the mode of intelligent 149. He B, Luo T, Huang S (2019) Product sustainability assessment chemical industry based on cyber-physical system and its for product life cycle. J Clean Prod 206:238–250 implementation. Adv Eng Software 99:18–26 150. He B, Deng ZQ, Huang S et al (2015) Application of unascer- 171. Tao F, Zuo Y, Xu LD et al (2014) IoT-based intelligent per- tained number for the integration of carbon footprint in con- ception and access of manufacturing resource toward cloud ceptual design. Proc Inst Mech Eng J Eng Manuf manufacturing. IEEE Trans Ind Inf 10(2):1547–1557 229(11):2088–2092 172. Jain P, Poon J, Singh JP et al (2019) A digital twin approach for 151. Yu QY, He B (2020) Automated sustainable low-carbon design fault diagnosis in distributed photovoltaic system. IEEE Trans of offshore platform for product life cycle. In: Tan J (ed) Power Electron 35:940–956 Advances in mechanical design. Springer, Berlin, pp 1–17 173. Liu MZ, Ma J, Lin L et al (2014) Intelligent assembly system for mechanical products and key technology based on internet of 152. He B, Huang S, Wang J (2015) Product low-carbon design using dynamic programming algorithm. Int J Precis Eng Manuf Green things. J Intell Manuf 28(2):271–299 Technol 2(1):37–42 174. Tang H, Li D, Wang SY et al (2018) Casoa: an architecture for 153. He B, Tang W, Wang J (2015) Product model integrated with agent-based manufacturing system in the context of Industry 4.0. carbon footprint for low-carbon design. Int J Precis Eng Manuf IEEE Access 6:12746–12754 16(11):2383–2388 175. Chaplin J, Bakker O, de Silva L et al (2015) Evolvable assembly 154. He B, Feng P (2012) Guiding conceptual design through func- systems: a distributed architecture for intelligent manufacturing. tional space exploration. Int J Adv Manuf Technol 66(9/ IFAC-PapersOnLine 48(3):2065–2070 12):1999–2011 123 20 B. He, K.-J. Bai 176. Wang KS (2013) Towards zero-defect manufacturing (ZDM)— 198. Rødseth H, Schjølberg P, Marhaug A (2017) Deep digital a data mining approach. Adv Manuf 1(1):62–74 maintenance. Adv Manuf 5(4):299–310 177. Liu C, Jiang PY (2016) A cyber-physical system architecture in 199. Gamboa Quintanilla F, Cardin O, L’Anton A et al (2016) A shop floor for intelligent manufacturing. Procedia CIRP modeling framework for manufacturing services in service-ori- 56:372–377 ented holonic manufacturing systems. Eng Appl Artif Intell 178. Wan JF, Yi ML, Li D et al (2016) Mobile services for cus- 55:26–36 tomization manufacturing systems: an example of Industry 4.0. 200. He B, Zhu XR, Zhang D (2020) Boundary encryption-based IEEE Access 4:8977–8986 Monte Carlo learning method for workspace modeling. ASME J 179. Zhao QJ, Cao P, Tu DW (2014) Toward intelligent manufac- Comp Inf Sci Eng. 20:034502. https://doi.org/10.1115/1. turing: label characters marking and recognition method for 4046816 steel products with machine vision. Adv Manuf 2(1):3–12 201. Li F, Zhang L, Liu YK et al (2017) A clustering network-based 180. Liu CW, Chien CF (2013) An intelligent system for wafer bin approach to service composition in cloud manufacturing. Int J map defect diagnosis: an empirical study for semiconductor Comput Integr Manuf 30(12):1331–1342 manufacturing. Eng Appl Artif Intell 26(5/6):1479–1486 202. Lu YQ, Xu X (2017) A semantic web-based framework for 181. Strandhagen JW, Alfnes E, Strandhagen JO et al (2017) The fit service composition in a cloud manufacturing environment. of Industry 4.0 applications in manufacturing logistics: a mul- J Manuf Syst 42:69–81 tiple case study. Adv Manuf 5(4):344–358 203. Zhang S, Xu YB, Zhang WY et al (2017) A new fuzzy QOS- 182. Chen RY (2017) An intelligent value stream-based approach to aware manufacture service composition method using extended collaboration of food traceability cyber physical system by fog flower pollination algorithm. J Intell Manuf 30(5):2069–2083 computing. Food Control 71:124–136 204. Zhou JJ, Yao XF (2016) A hybrid artificial bee colony algorithm 183. Maoudj A, Bouzouia B, Hentout A et al (2017) Distributed for optimal selection of QOS-based cloud manufacturing service multi-agent scheduling and control system for robotic flexible composition. Int J Adv Manuf Technol 88(9/12):3371–3387 assembly cells. J Intell Manuf 30(4):1629–1644 205. Yao F, Yao YP, Xing LN et al (2019) An intelligent scheduling 184. Barenji AV, Barenji RV, Hashemipour M (2016) Flexible test- algorithm for complex manufacturing system simulation with ing platform for employment of RFID-enabled multi-agent frequent synchronizations in a cloud environment. Memet system on flexible assembly line. Adv Eng Softw 91:1–11 Comput 11:357–370 185. Wang KS (2014) Intelligent and integrated RFID (II-RFID) 206. Ruiz N, Giret A, Botti V et al (2014) An intelligent simulation system for improving traceability in manufacturing. Adv Manuf environment for manufacturing systems. Comput Ind Eng 2(2):106–120 76:148–168 186. Zhong RY, Dai QY, Qu T et al (2013) RFID-enabled real-time 207. Zheng Y, Yang S, Cheng HC (2018) An application framework manufacturing execution system for mass-customization pro- of digital twin and its case study. J Ambient Intell Hum Comput duction. Robot Comput Integr Manuf 29(2):283–292 10(3):1141–1153 187. Leng JW, Jiang PY (2017) Dynamic scheduling in RFID-driven 208. Zhang C, Zhou G (2019) A view-based 3D CAD model reuse discrete manufacturing system by using multi-layer network framework enabling product lifecycle reuse. Adv Eng Softw metrics as heuristic information. J Intell Manuf 30(3):979–994 127:82–89 188. Guo ZX, Wong WK, Guo CX (2013) A cloud-based intelligent 209. He B, Tang W, Huang S et al (2015) Towards low-carbon decision-making system for order tracking and allocation in product architecture using structural optimization for light- apparel manufacturing. Int J Prod Res 52(4):1100–1115 weight. Int J Adv Manuf Technol 83(5/8):1419–1429 189. Qiu C (2018) Implementation of vehicle mobile sales cloud 210. Bodrow W (2014) The dynamic of professional knowledge management system based on intelligent community. In: 2018 utilized in software applications for process controlling. Adv 14th international conference on computational intelligence and Manuf 2(2):173–178 security (CIS), pp 341–344 211. Giret A, Trentesaux D, Salido MA et al (2017) A holonic multi- 190. Zhang XY, Ming XG, Liu ZW et al (2019) An overall frame- agent methodology to design sustainable intelligent manufac- work and subsystems for smart manufacturing integrated system turing control systems. J Clean Prod 167:1370–1386 (SMIS) from multi-layers based on multi-perspectives. Int J Adv 212. Zhang C, Zhou G, Lu Q et al (2017) Graph-based knowledge Manuf Technol 103:703–722 reuse for supporting knowledge-driven decision-making in new 191. He B, Liu YJ, Zeng LB et al (2020) Product carbon footprint product development. Int J Prod Res 55(23):7187–7203 across sustainable supply chain. J Clean Prod 241:118320 213. Chai JF, Hu XM, Qu HW et al (2018) Production line 3D 192. Sun HT, Peng C, Zhou P et al (2017) A brief overview on secure visualization monitoring system design based on OpenGL. Adv control of networked systems. Adv Manuf 5(3):243–250 Manuf 6(1):126–135 193. McFarlane D, Sarma S, Chirn JL et al (2003) Auto ID systems 214. Huang PB, Zhang HJ, Lin YC (2017) Development of a grey and intelligent manufacturing control. Eng Appl Artif Intell online modeling surface roughness monitoring system in end 16(4):365–376 milling operations. J Intell Manuf 30(4):1923–1936 194. Cui FZ, Xu ZZ, Wang XK et al (2018) A dual-system cooper- 215. Li Z, Wang Y, Wang KS (2017) Intelligent predictive mainte- ative co-evolutionary algorithm for satellite equipment layout nance for fault diagnosis and prognosis in machine centers: optimization. Proc Inst Mech Eng G J Aerosp Eng Industry 4.0 scenario. Adv Manuf 5(4):377–387 232(13):2432–2457 216. Kim J, Hwangbo H (2019) Real-time early warning system for sustainable and intelligent plastic film manufacturing. Sustain- 195. Malik AA, Bilberg A (2018) Phygital workspace as a digital twin for design & planning of smart factories, pp 1–2 ability 11(5):1490–1503 196. Yin Y, Sun L, Guo C (2008) A policy of conflict negotiation 217. Guo ZX, Ngai EWT, Yang C et al (2015) An RFID-based based on fuzzy matter element particle swarm optimization in intelligent decision support system architecture for production distributed collaborative creative design. Comput Aided Des monitoring and scheduling in a distributed manufacturing 40(10/11):1009–1014 environment. Int J Prod Econ 159:16–28 197. Wang Y, Ma HS, Yang JH et al (2017) Industry 4.0: a way from 218. Tan DP, Zhang LB, Ai QL (2016) An embedded self-adapting mass customization to mass personalization production. Adv network service framework for networked manufacturing sys- Manuf 5(4):311–320 tem. J Intell Manuf 30(2):539–556 123 Digital twin-based sustainable intelligent manufacturing: a review 21 219. Arica E, Powell DJ (2014) A framework for ICT-enabled real- transportation using an improved artificial bee colony optimi- time production planning and control. Adv Manuf 2(2):158–164 sation algorithm. Int J Prod Res 53(14):4380–4404 220. Su Y, Ding X, Zheng H et al (2009) A new method of remote 240. Wang KS, Li Z, Braaten J et al (2015) Interpretation and control for embedded terminal based on browser/server/terminal compensation of backlash error data in machine centers for model. In: 2009 Pacific-Asia conference on circuits, communi- intelligent predictive maintenance using ANNs. Adv Manuf cations and systems, pp 151–154 3(2):97–104 221. Theorin A, Bengtsson K, Provost J et al (2016) An event-driven 241. Liu ZW, Ming XG (2019) A framework with revised rough- manufacturing information system architecture for Industry 4.0. DEMATEL to capture and evaluate requirements for smart Int J Prod Res 55(5):1297–1311 industrial product-service system of systems. Int J Prod Res 222. Xiao X, Wang SF, Zhang LJ et al (2018) Complexity analysis of 57:7104–7122 manufacturing service ecosystem: a mapping-based computa- 242. Liu Q, Liu ZH, Xu WJ et al (2019) Human-robot collaboration tional experiment approach. Int J Prod Res 57(2):357–378 in disassembly for sustainable manufacturing. Int J Prod Res 223. Baxter D, Roy R, Doultsinou A et al (2009) A knowledge 57:4027–4044 management framework to support product-service systems 243. Dyllick T, Rost Z (2017) Towards true product sustainability. design. Int J Comput Integr Manuf 22(12):1073–1088 J Clean Prod 162:346–360 224. Matsas M, Pintzos G, Kapnia A et al (2017) An integrated 244. He B, Gu ZC (2016) Sustainable design synthesis for product collaborative platform for managing product-service across their environmental footprints. Des Stud 45:159–186 life cycle. Procedia CIRP 59:220–226 245. He B, Xiao JL, Deng ZQ (2018) Product design evaluation for 225. Balta EC, Lin Y, Barton K et al (2018) Production as a service: a product environmental footprint. J Clean Prod 172:3066–3080 digital manufacturing framework for optimizing utilization. 246. Manfredi S, Allacker K, Pelletier N et al (2012) Product envi- IEEE Trans Autom Sci Eng 15(4):1483–1493 ronmental footprint (PEF) guide. European Commission 226. Cheng Y, Bi LN, Tao F et al (2018) Hypernetwork-based 247. He B, Shao Y, Wang S et al (2019) Product environmental manufacturing service scheduling for distributed and collabo- footprints assessment for product life cycle. J Clean Prod rative manufacturing operations towards smart manufacturing. 233:446–460 J Intell Manuf. https://doi.org/10.1007/s10845-018-1417-8 227. Ren M, Ren L, Jain H (2018) Manufacturing service composi- tion model based on synergy effect: a social network analysis Bin He received his degrees approach. Appl Soft Comput 70:288–300 (from Bachelor to Ph.D Degree) 228. Siderska J, Jadaan KS (2018) Cloud manufacturing: a service- from Zhejiang University. Dr. oriented manufacturing paradigm. A review paper. Eng Manag He is a Full Professor and Prod Serv 10(1):22–31 Deputy Director of Shanghai 229. He B, Feng PE (2012) Research on collaborative conceptual Key Laboratory of Intelligent design based on distributed knowledge resource. Int J Adv Manufacturing and Robotics, Manuf Technol 66(5/8):645–662 Director of Robotics and Intel- 230. Yang YF, Yang B, Wang SL et al (2019) A dynamic ant-colony ligent Design Institute, School genetic algorithm for cloud service composition optimization. of Mechatronic Engineering and Int J Adv Manuf Technol 102(1/4):355–368 Automation, Shanghai Univer- 231. Zhou JJ, Yao XF (2017) A hybrid approach combining modified sity. Dr. He is Associate Editor artificial bee colony and cuckoo search algorithms for multi- of ASME Journal of Computing objective cloud manufacturing service composition. Int J Prod and Information Science in Res 55(16):4765–4784 Engineering, Editor-in-Chief of 232. Zhang CL, Sheng BY, Yin XY et al (2017) Research and International Journal of Advanced Robotic Systems. Dr. He has development of off-line services for the 3D automatic printing interests in sustainable intelligent design and intelligent manufactur- machine based on cloud manufacturing. J Ambient Intell Hum ing, and robotics. Comput 10(3):1109–1128 233. Huang BQ, Li CH, Tao F (2013) A chaos control optimal Kai-Jian Bai received a BS algorithm for QOS-based service composition selection in cloud degree in Mechanical Engi- manufacturing system. Enterp Inf Syst 8(4):445–463 neering from Shanghai Univer- 234. Guo L, Wang SL, Kang L et al (2015) Agent-based manufac- sity, P.R.C., in 2018. He is now turing service discovery method for cloud manufacturing. Int J studying for a master’s degree Adv Manuf Technol 81(9/12):2167–2181 in the School of Mechatronic 235. Song TX, Liu HM, Wei CM et al (2014) Common engines of Engineering and Automation, cloud manufacturing service platform for SMES. Int J Adv Shanghai University. He has Manuf Technol 73(1/4):557–569 interests in intelligent manufac- 236. DeSmit Z, Elhabashy AE, Wells LJ et al (2017) An approach to turing systems. cyber-physical vulnerability assessment for intelligent manu- facturing systems. J Manuf Syst 43:339–351 237. Wang KS, Sharma VS, Zhang ZY (2014) SCADA data based condition monitoring of wind turbines. Adv Manuf 2(1):61–69 238. Feng Y, Huang BQ (2018) Cloud manufacturing service QOS prediction based on neighbourhood enhanced matrix factoriza- tion. J Intell Manuf. https://doi.org/10.1007/s10845-018-1409-8 239. Lartigau J, Xu XF, Nie LS et al (2015) Cloud manufacturing service composition based on QOS with geo-perspective

Journal

Advances in ManufacturingSpringer Journals

Published: May 4, 2020

There are no references for this article.