Multi-scale residual network-based image restorationYang, Liu; You, Fucheng
doi: 10.1088/1742-6596/2189/1/012009pmid: N/A
All Image restoration technology has undergone extensive research. For image degradation, inverse filtering was proposed in the last century. Then Helstrom proposed a Wiener filtering algorithm. In recent years, the convolutional neural network has promoted the further development of image restoration technology. The coarse-to-fine multi-scale residual network Multiscale Deblur Net (MDN) used in this paper is stable in operation, simple in structure, and easy to train. It has a good deblurring ability for motion-blurred images by testing in the GO_PRO dataset.
Monthly-scale runoff forecast model based on PSO-SVRQiao, Guangchao; Yang, Mingxiang; Zeng, Xiaoling
doi: 10.1088/1742-6596/2189/1/012016pmid: N/A
The current methods used in the Lubbog reservoir runoff forecast generally have shortcomings such as low forecast accuracy and low stability. Aiming at these problems, this paper constructs a PSO-SVR mid-and-long term forecast model, and it uses the particle swarm optimization algorithm (PSO) to find the penalty coefficient C, the insensitivity coefficient ε and the gamma parameter of the Gaussian radial basis kernel function of the support vector regression machine (SVR). The results demonstrates that the average relative errors of the PSO-SVR forecast model is relatively small, which are all within a reasonable range; the qualification rates for most monthly forecasts are above 80%. Experimental results indicate that compared with multiple regression analysis, the PSO-SVR model has a higher forecast accuracy, a stronger stability, and a higher credibility. It has a certain practical value and provides a reference for related research.
A new algorithm for precise location of power cable fault based on zero phase filterZhang, Xiaojun; Zhang, Bo; Wu, Suzhou; Li, Chao; Lei, Zeyang
doi: 10.1088/1742-6596/2189/1/012020pmid: N/A
In order to improve the fault location accuracy of power cables, the two-side method is used for fault location. The main factors affecting the cable fault accuracy of the double-ended fault location method are the wave speed of traveling waves transmitted in the cable and the time difference between the traveling waves arriving at the monitoring equipment. In fact, traveling wave signals with different frequencies propagate at different wave speeds, and the use of fixed wave speeds for positioning calculations will inevitably cause positioning errors. First, the center frequency spectrum method is used to calculate the wave speed, and different wave speeds are used for different types of cables, so as to reduce the positioning error caused by the wave speed. Then, the devices on both sides use high-precision GPS to synchronize the time to reduce the natural error. For the time difference between the detected traveling waves reaching the devices on both sides, the triangle algorithm can be used to find the starting point for time difference calculation, thereby constructing a new cable fault location algorithm. Finally, a large number of PSCAD simulations and field discharge tests of cable grounding were carried out. The simulation results and test results verified the feasibility and superiority of this algorithm.
A miniaturized seven-electrode conductivity and temperature integrated sensorSun, Wei; Guo, Fengxiang; Chai, Xu; Hu, Ding; Zhang, Xueyu; Xu, Mingxia; Wang, Yibao; Wang, Shaoyan; Wu, Xiaofan; Qu, Chuang; Gai, Zhigang
doi: 10.1088/1742-6596/2189/1/012008pmid: N/A
Marine environmental monitoring technology is the support of marine development, and its development level and innovation capability have become important criteria for measuring a country’s marine science and technology indicators. In order to meet the application demand of large-scale and high-density deployment of marine observation network, a planar open seven-electrode conductivity and platinum resistance temperature integrated sensor is developed by using Micro Electro Mechanical System(MEMS) technology, combined with semiconductor micro and nano precision processing technologies such as mask lithography and physical sputtering. The measurement principle, probe design preparation, packaging and calibration method of this conductivity temperature sensor are presented. By calibrating and fitting the measurement data of this sensor, good measurement accuracy results were obtained. The miniaturized conductivity temperature sensor has the advantages of small size, low power consumption, low cost and high accuracy of probe processing, high batch consistency, and fully meets the application requirements of marine observation network.
Research on classification method based on multi-scale segmentation and hierarchical classificationZhang, Xiaohua; Wang, Hui; Xue, Wenxiang; Qin, Chaoyun; Wu, Yuping; Wang, Shuyuan; Qiu, Peng
doi: 10.1088/1742-6596/2189/1/012029pmid: N/A
This paper transmission line corridors covering area in Hebei north area as the research object to explore multi-scale segmentation threshold suitable for Hebei north image, found applicable to Hebei north region segmentation threshold rules. Main methods are the object-oriented multi-scale segmentation and hierarchical classification, using image segmentation principle, make full use of high resolution image rich features such as shape, texture, object relationships. It is used for the follow-up investigation of hidden danger of external damage of power transmission channel in northern Hebei region. The main conclusions of the experiment are as follows: 1. By comparing and analyzing the results of five groups of different thresholds (40, 50, 60, 70 and 80), it is concluded that the single threshold of the multi-scale segmentation method suitable for most mountainous images in the study area is 60, and this method can achieve high-precision ground object classification for images in northern Hebei region. 2. The ground feature cover classification method that is more suitable for the parallel processing of a large number of study areas is the object-oriented hierarchical classification method, and preliminary exploration results of detailed parameters have been achieved.
Research on the Methods to Improve RFSS AccuracyYuan, Qingze
doi: 10.1088/1742-6596/2189/1/012028pmid: N/A
RFSS is a common test method in the research and development of radar guidance systems, which overcomes the problem of the large cost of the field test to a certain extent. With the development of radar technology, the evaluation of hardware in the loop RF simulation error needs to be more accurate. This paper summarizes the current research, mainly focusing on simulation error analysis, near-field error and near-field correction, expansion of simulation object and suppression of simulation error. At present, most studies focus on azimuth error and pitch error respectively, but do not take into account the correlation of the errors in these two different angle domains. Or only the root mean square of the amplitude of the two-dimensional angle error is considered, without considering the directional distribution of the angle error.
An Optimization method for the Internet of vehicles oriented to moving relayLiang, Cai
doi: 10.1088/1742-6596/2189/1/012026pmid: N/A
Moving relay (MR) is a relay node deployed on public transportation such as cars and trains, which can effectively combat the vehicle penetration loss (VPL) problem in vehicle communication. outage probability (OP) is an expression of link capacity. When the link capacity cannot meet the required user rate, an outage will occur. For the downlink multi-user network, we compared the performance of direct transmission and MR-assisted transmission with the probability of interruption as a performance indicator. Subsequently, we design a joint optimization scheme for transmission mode selection and user scheduling, select the transmission mode suitable for the user, schedule the user with the largest information rate, and derive the closed-form expression of the scheduling scheme. And compared with random selection scheduling. The experiment compares random scheduling with the scheduling scheme we proposed. Experimental results show that compared with random selection and scheduling scheme, the proposed scheduling scheme can reduce OP, thereby improving system performance.
Research on intelligent peak-cutting and valley-filling charging and swapping mode based on potential game theoryHu, Lanxin; Yue, Feiyang
doi: 10.1088/1742-6596/2189/1/012013pmid: N/A
With the continuous increase in the proportion of renewable energy represented by wind and light in the power grid in recent years, on the one hand, the energy structure of the existing power grid has been directly optimized, and on the other hand, the full utilization of renewable clean energy can also reduce traditional power generation. The pollution caused by the industry to the environment. As an indispensable infrastructure for electric vehicles, charging and swapping stations, after being connected to a distributed micro-grid, can play a role in reducing peaks and valleys, promoting the consumption of new energy, and saving costs through reasonable configuration. The analysis of calculation examples shows that the intelligent charging and swapping system model based on the potential game theory proposed in this paper can effectively reduce the operating cost and user cost of the swap station, and effectively improve the level of wind and solar consumption, and achieve the level of smoothing the grid curve and peak-shaving and valley-filling. Purpose has important practical significance and engineering value.
Model Extraction Attack and Defense on Deep Generative ModelsLiu, Shengyi
doi: 10.1088/1742-6596/2189/1/012024pmid: N/A
The security issues of machine learning have aroused much attention and model extraction attack is one of them. The definition of model extraction attack is that an adversary can collect data through query access to a victim model and train a substitute model with it in order to steal the functionality of the target model. At present, most of the related work has focused on the research of model extraction attack against discriminative models while this paper pays attention to deep generative models. First, considering the difference of an adversary` goals, the attacks are taxonomized into two different types: accuracy extraction attack and fidelity extraction attack and the effect is evaluated by 1-NN accuracy. Attacks among three main types of deep generative models and the influence of the number of queries are also researched. Finally, this paper studies different defensive techniques to safeguard the models according to their architectures.