Transactions of the Institute of Measurement and Control

Sun, Shixiang; Ren, Tao; Xu, Yanjie

doi: 10.1177/01423312231182468pmid: N/A

Identifying influential nodes has drawn great attention in recent years. In this paper, a novel method for identifying influential spreaders based on potential edge weights (WDK for simplicity) for both undirected and unweighted networks is proposed. Degree and k-shell of a node and its neighbors are considered simultaneously, which are regarded as the weight of the edge directly connected to the node. The algorithm considers not only the local information of nodes but also their location information. The proposed method not only improves the accuracy of node mining but also has approximately linear time complexity, which indicates that the proposed method is suitable for large-scale networks. In order to validate the effectiveness of the proposed method, different evaluation indexes are introduced in nine real networks. Compared with five classical key nodes identification methods, the experimental results show that the proposed method performs optimally in all networks.

Li, Yong; Cheng, Gang; Ma, Sencai; Li, Xin

doi: 10.1177/01423312231185425pmid: N/A

To solve the problem of bearing fault diagnosis at different speeds, a fault diagnosis method based on single-component variational modal decomposition (SCVMD) and coarse-grained lattice feature (CGLF) is proposed by analyzing the influence mode of speed transformation on frequency spectrum. First, the central frequency of the main resonance band of the signal is extracted based on SCVMD to eliminate the problem of spectrum shift caused by speed change. Then, the signal fragments are intercepted from the original signal spectrum to construct CGLF. Finally, a deep convolutional neural network (DCNN) is established to solve the sideband shrinkage problem caused by speed change and used to construct the mapping relationship between CGLF and category labels. In the experiment, bearing fault experimental platform dataset is used for the algorithm verification, and the final recognition rate is 98.3%. It proves that the method can effectively achieve bearing fault diagnosis at different speeds.

Zhao, Yinghao; Yang, Xu; Huang, Jian; Wu, Xia; Cui, Jiarui

doi: 10.1177/01423312231184292pmid: N/A

Driven by the increasing needs for production safety in mass varieties production process, an adaptive weighting strategy is proposed for fault detection and diagnosis to weaken the influence brought by the change of operational conditions. To this end, considering the correlation between features and operational conditions, representative features extracted from multi-domain are selected using max-relevance and min-redundancy (mRMR) to establish the connection between features and operational condition. On this basis, a health index (HI) is fused for fault detection based on adaptive weight coefficients calculated according to the difference of features. Moreover, the input weight matrix of extreme learning machine (ELM) is redesigned based on the adaptive weight coefficients and the historical information to curb the impact of random factors. The effectiveness of the proposed method is demonstrated by rolling bearing test rig and industrial reciprocating pump. The results show that the rate of detection using the HI designed in this paper can reach 100% and the average diagnosis accuracy can reach 94.3% and 98.8%.

Zhu, Keheng; Zhou, Shunming; Chen, Liang; Gu, Bangping; Hu, Xiong

doi: 10.1177/01423312231184932pmid: N/A

This paper addresses the application of a deep convolutional fuzzy system (DCFS) for the fault diagnosis of rolling element bearings. The limitations of the conventional deep convolutional neural network (CNN) are the huge computational load of training the tones of parameters and the lack of interpretability for the corresponding parameters. In this paper, a DCFS-based bearing fault diagnosis method under variable working conditions is proposed. The DCFS on a high dimensional input space is a multilayer connection of many low dimensional fuzzy systems, which can overcome the computational and interpretability problems of the traditional CNN. Moreover, to improve the identification efficiency and diagnosis accuracy, the infinite feature selection (Inf-FS) algorithm is employed to select the most informative fault features. The proposed approach is experimentally demonstrated to be able to identify the different fault types and fault severities of rolling bearings under variable running states.

Ling, Yunhan; Fu, Dianyu; Jiang, Peng; Sun, Yong; Yuan, Chao; Huang, Dali; Lu, Jingfeng; Lu, Siliang

doi: 10.1177/01423312231185702pmid: N/A

Rotating machine fault diagnosis plays a vital role in reducing maintenance costs and preventing accidents. Machine learning (ML) methods and Internet of things (IoT) technologies have been recently introduced into machine fault diagnosis and have generated inspiring results. An ML model with more trainable parameters can typically generate a higher fault diagnostic accuracy. However, the IoT nodes have limited computation and storage resources. How to design an ML model with high accuracy and computational efficiency is still a difficulty and challenge. This work develops an enhanced sparse filtering (ESF) method for mining and fusing the features of the machine signals for fault diagnosis. First, a dimension reduction algorithm is utilized for obtaining the principal components of the vibration signals that are hindered by noises. The distinct features of the principal components are then exploited by using sparse filtering (SF). To reduce the overfitting of the SF model, the L1/2 norm is applied to regularize the objective function. Finally, the obtained features are combined as the inputs of a softmax classifier for machine fault pattern recognition. The effectiveness, superiority, and robustness of the proposed ESF method are validated by the simulated signals and the practical bearing and motor fault signals compared with the other conventional methods. The lightweight and intelligent ESF algorithm is also deployed onto an edge computing node to realize online motor fault diagnosis. The designed model and the proposed method show great potential in highly accurate and efficient rotation machine fault diagnosis.

Wang, Rui; Song, Chunyue; Chen, Sikai; Zhao, Jun

doi: 10.1177/01423312231184728pmid: N/A

Uncertainties in a battery would result in unreliable state of health (SOH) estimation. Considering the greater risk after reaching the end of life (EOL), designing a suitable ensemble learning to provide early warning before reaching EOL with uncertainty measurement is desirable for confidence estimation. In this paper, a novel probabilistic ensemble learning method-Gaussian process-based neural networks is proposed for the SOH confidence estimation by describing the uncertainties in probabilistic form. First, different neural networks are built based on health features. Second, battery data are classified under the recovery of capacity and normal operation conditions to characterize the uncertainties of the data under different operation conditions. Besides, the Gaussian process-based neural networks method is constructed based on the data from different conditions for neural networks weighted ensemble with the probabilistic form of Gaussian distribution. Therefore, the uncertainties are measured in the probabilistic form considering different operation conditions which is different from other methods. With the probabilistic form, the confidence interval could be determined to ensure the real SOH within the confidence interval, which improves the estimation performance of the proposed method because of the early warning near the EOL. Finally, the effectiveness is validated by NASA data sets and our experiment with the commercial 18650 lithium-ion battery. From the results, the mean error is less than 1% and real SOH is within the confidence interval.

Taleshian, Tahereh; Ranjbar Noei, Abolfazl; Sadati, Jalil; Malekzadeh, Milad

doi: 10.1177/01423312231184561pmid: N/A

In this paper, an optimal extended state observer (ESO) is designed for nonlinear integral chain system. For the first time, in this paper, proportional–integral (PI) extremum seeking control (ESC; PIESC) approach is applied to design a perturbation observer by minimizing the estimation error. The PI type structure of the ESC provides fast transient response for the closed-loop system to attain optimum equilibrium point. A mathematical proof is presented to show that the average error dynamic asymptotically converges to zero while the estimation error is minimized. The simulation results verify that the estimation error achieved by the proposed PIESC-based ESO (PIESC-ESO) is found significantly less than that achieved by the classic ESO and PSO-based ESO. Moreover, if slow changes occur within the system or external to it, the PIESC-ESO is still able to modify the observer gains such that the estimation error is minimized again. Therefore, this may help PIESC-ESO to be used in practical applications.

Li, Sifan; Xu, Yanhe; Jiang, Wei; Zhao, Kunjie; Liu, Wei

doi: 10.1177/01423312231188777pmid: N/A

Data-driven methods have been applied in fault diagnosis. However, in practical engineering, workers are more concerned with the real-time health status of bearings. And it is difficult to complete the effective training of diagnostic models with insufficient labeled fault data. Therefore, this paper proposes a modular method based on a mask kernel and multi-head self-attention mechanism for rolling bearing fault diagnosis. First, the proposed method divides the diagnosis into two modules of status detection and fault recognition. The approach of sharing one backbone for both modules simplifies the optimization process. The method combines the translation invariance of the convolution kernel and the mask attention mechanism of the transformer by computing the local self-attention and superimposing the partial local attention by the mask to ensure the integrity of the information. Finally, a zero-shot training method is proposed to embed the query into the model to achieve cross-distribution fault diagnosis of bearings. The experiments on the data sets of Case Western Reserve University and machinery fault simulator are implemented to diagnose the bearings. The results show that the proposed method can obtain higher diagnostic accuracy and computational efficiency than the existing methods and can be valid for scenarios with cross-condition diagnosis or imbalanced samples.

Tan, Xiaoying; Guo, Wei; Liu, Ranran; Pan, Tianhong

doi: 10.1177/01423312231181379pmid: N/A

Functional principal component analysis (FPCA) and functional partial least squares (FPLS) are two mainstream functional data analysis (FDA) methods, which have been commonly used to extract deep information hidden in the original data space. However, the process data always contain random noise, which affects the performance of FDA models. To overcome this issue, two functional probabilistic latent variable models (FPLVMs), including functional probabilistic principal component analysis (FPPCA) and functional probabilistic partial least squares (FPPLS) are proposed in this work. First, the process data are converted into functional data using the FDA. Subsequently, a log-likelihood function considering the noise factor and functional latent variables is designed. Finally, the regression model parameters are estimated using an expectation–maximisation algorithm. In contrast to FPPCA, FPPLS decomposes the process data and the key variable with constrained latent variables, which is similar to the partial least squares (PLS) and the principal component analysis (PCA). Moreover, the degeneration mechanism from FPLVMs into probabilistic latent variable models and latent variable models is discussed. An adaptive strategy with functional covariance is used to satisfy the online predictive capabilities of the model. Finally, the proposed approach is validated using a numerical case, the Tennessee Eastman process and an industrial o-xylene distillation column for evaluation.

Han, Baokun; Li, Bo; Du, Huadong; Wang, Jinrui; Xing, Shuo; Song, Lijin; Ma, Junqing; Ma, Hao

doi: 10.1177/01423312231190435pmid: N/A

In recent years, transfer learning has been widely used in mechanical fault diagnosis with some achievements. However, most transfer learning methods do not perform well in diagnosis when the speed and load change simultaneously. Inspired by the adversarial learning mechanism, a transfer learning method named attention mechanism-guided domain adversarial network (AMDAN) is proposed in this paper. AMDAN regards the convolutional neural networks (CNNs) as the generator of the domain adversarial network to learn mutually invariant features and the domain classifier as the discriminator of the domain adversarial network. Attention mechanism is introduced to take into account the interchannel and intraspace feature fusion to improve the training efficiency. Then, multi-kernel maximum mean discrepancy (MK-MMD) is used to measure the distance of different feature spaces to achieve domain alignment. Finally, the superiority of AMDAN is verified by two sets of gear fault diagnosis experiments. The experimental results show that AMDAN has the highest classification accuracy and the strongest generalization ability compared with other methods.