2022 37th Youth Academic Annual Conference of Chinese Association of Automation (YAC)最新文献

{"title":"Billet Number Recognition Based on ESRGAN and Improved YOLOv5","authors":"Zijia Wang, Yichao Dong, D. Niu, Minghao Liu, Qi Li, Xisong Chen","doi":"10.1109/YAC57282.2022.10023659","DOIUrl":"https://doi.org/10.1109/YAC57282.2022.10023659","url":null,"abstract":"Aiming at solving the problem of billet number recognition and further improve the rate of recognition, this paper proposes a billet number recognition algorithm based on ESRGAN and improved YOLOv5, which is referred to as YOLOv5-Billet in this paper. According to the actual situation, we propose a target recognition algorithm that uses the lightweight network MobileNetv3 to replace the backbone feature extraction network of YOLOv5. We also introduce ESRGAN to improve the quality of the input image and further improve the recognition effect. A series of rigorous experiments show that YOLOv5-Billet has a certain improvement in billet recognition speed and precision. Specifically, the average precision of YOLOv5-Billet is improved by 10.8%, and the detection speed is also improved by 5.12fps, reaching 40.35fps. Through the experimental verification of real-time collection of data sets, compared with a variety of classical target detection methods, the recognition precision and detection speed are improved to varying degrees. This model maintains the lightweight characteristics of YOLOv5 and meets the requirements of real-time monitoring of the number of blanks.","PeriodicalId":272227,"journal":{"name":"2022 37th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115432531","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fault Detection of Valve Based on 2D Localization and 3D Pose Solution","authors":"Yuanfu Du, Linzi Xie, N. Qin, Zhonghe Zhou, De-Young Huang","doi":"10.1109/YAC57282.2022.10023676","DOIUrl":"https://doi.org/10.1109/YAC57282.2022.10023676","url":null,"abstract":"We present a detection method based on 2D image localization and 3D pose calculation to solve the fault detection of high-speed train valves. In this paper, the lightweight PP-PicoDet detector is selected to identify and locate valve components, and the 3D pose calculation with spatial position alignment is used to solve the valve state. The novelty of this method adopts the preprocessing method of image object detection and the mapping relationship between image and point cloud. Through experiments, the algorithm has an accuracy of 97% in detecting objects within 0.1s, and solves the valve state within 0. 3s with a deviation of less than 1.5°. The experimental results show that the valve fault detection method combined with PP-PicoDet network and 3D state solution has practical engineering significance.","PeriodicalId":272227,"journal":{"name":"2022 37th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121834990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prescribed-Time Synchronization for Complex Networks With Additive Coupling","authors":"Linlong Xu, Xiwei Liu","doi":"10.1109/YAC57282.2022.10023624","DOIUrl":"https://doi.org/10.1109/YAC57282.2022.10023624","url":null,"abstract":"We discuss the prescribed-time synchronization for directed complex networks with additive coupling, where the settling time is independent of initial values and any other parameters. Considering the case that inner coupling matrices may be not available, we make full use of the irreducible and asymmetric outer coupling matrices and their normalized left eigenvectors (NLEVecs) corresponding to the zero eigenvalue to design a new vector by combining all these NLEVecs. We prove that if the Chebyshev distances between this vector and any NLEVec is in the region of allowable deviation for each matrix, then we can establish a new Lyapunov function with it to analyze the prescribed-time synchronization. Numerical simulations are provided to verify our theoretical results.","PeriodicalId":272227,"journal":{"name":"2022 37th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116767300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Multi-scale Contextual Attention Mechanism For Convolutional Neural Networks","authors":"Yun Xie, Chanting Cao, MingChao Liao, Yao Yu","doi":"10.1109/yac57282.2022.10023920","DOIUrl":"https://doi.org/10.1109/yac57282.2022.10023920","url":null,"abstract":"In recent years, attention mechanism has been widely studied in the field of computer vision, which can effectively improve the performance of visual tasks. In the past, many classical attention models have studied the modeling of nonlinear relationships in the spatial or channel dimensions of feature maps, ignoring the use of contextual relationships to capture the information interaction of the three dimensions to obtain a global attention feature map. In this paper, we investigate an effective multi-scale contextual attention mechanism, which can obtain feature information of different receptive fields through the combination of multi-branch conventional convolution and dilated convolution, which can increase the image receptive field, and combine global features and detailed features to effectively use contextual information. In addition, since the input tensors interact with each other on the three dimensions of the feature map and was adjusted by an adaptive parameter, this also makes the three-dimensional attention weights we obtain more differentiated. Our MCA model is simple and can be flexibly embedded in a variety of classical backbone networks, and experimental evaluation of the proposed attention mechanism on common datasets for image classification and object detection also proves the effectiveness of our attention meachine.","PeriodicalId":272227,"journal":{"name":"2022 37th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127276483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prescribed Performance Integral Sliding Control of Robot System with Event-Triggered Unknown System Dynamic Estimator","authors":"Chao Zhang, X. Ren, Dong-dong Zheng, J. Na","doi":"10.1109/YAC57282.2022.10023784","DOIUrl":"https://doi.org/10.1109/YAC57282.2022.10023784","url":null,"abstract":"In this paper, a prescribed performance integral sliding control approach based on the event-triggered unknown system dynamics estimator (ET-USDE) is proposed for robot system to obtain a satisfactory position tracking control error. The lumped dynamics including unknown system dynamics and external disturbances are estimated and compensated by ETUSDE. An event-triggered mechanism is employed into the ETUSDE, the communication burden of the robot system is reduced based on an event-based sampler. A tuning function is used in the prescribed performance integral sliding control design, enabling significant improvements in the control performance of the robot system. Through the Lyapunov analysis it can be ensured that the estimation error is uniformly ultimately bounded and that all signals are bounded as well. Finally, the satisfactory motion control performance with reduced sampling cost of the proposed method is validated through numerical simulations.","PeriodicalId":272227,"journal":{"name":"2022 37th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127471214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design of Self-Shielded Uniform Magnetic Field Coil based on Improved TFM","authors":"Haoying Pang, Wenfeng Fan, Jing Wang, Feng Liu, Zhihong Wu, Qi Yuan","doi":"10.1109/YAC57282.2022.10023873","DOIUrl":"https://doi.org/10.1109/YAC57282.2022.10023873","url":null,"abstract":"Aiming at the influence of the magnetic shielding cylinder on the coil performance in the atomic sensor, a transverse self-shield uniform field coil is obtained by using improved target field method (TFM). The coil consists of two coaxial coils that produce the uniform field in the coil center, and the field decays rapidly to zero outside the coil. Based on the improved TFM, the current densities are expanded into triangular series and their Fourier coefficients are obtained from the target field point expected value. Compared with the traditional design method, this method can determine the winding form according to the desired target, and can obtain better uniformity. Through numerical simulation, the designed self-shielded coil has a uniformity of $6.1times 10^{-4}$ in the target area, and has outstanding self-shielded effect. This paper not only improves the uniformity, but also further solves the coupling problem between the coil and shield. This is beneficial to the performance improvement of the magnetic compensation system in atomic sensors.","PeriodicalId":272227,"journal":{"name":"2022 37th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127507606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research on equivalent modeling of VSC-HVDC grid-connected system for large-scale offshore wind power energy","authors":"Gen Li, Y. Xing, Xiaoxue Li, Yan Li, Fangqi Dong, Guanning Jiang","doi":"10.1109/YAC57282.2022.10023724","DOIUrl":"https://doi.org/10.1109/YAC57282.2022.10023724","url":null,"abstract":"Offshore wind generation energy is developed rapidly, especially the urgent need to build a 10 million kilowatt Offshore wind generation base. The transmission and grid connection of large offshore wind generation has become an urgent problem to be studied and solved. When offshore wind generations are far offshore, the cost of long-distance AC transmission is higher than that of DC transmission. At the same time, the charging power of inductance and capacitor is too large, reactive power compensation is required, and the quality of incoming power is reduced. VSC-HVDC transmission technology not only has the characteristics of traditional DC transmission technology (including long-distance transmission), but also has many advantages, such as no commutation failure, reactive and active power decoupling control, power supply to passive network and so on. Therefore, VSC-HVDC transmission technology will become one of the development trends of large number of offshore wind generation transmission. It is urgent to carry out the research on control and protection technology of large number of offshore VSC-HVDC grid connected transmission. Provide technical support for the development and operation of large offshore wind generation in eastern coastal areas such as Shandong and Jiangsu, promote the development of multi VSC-HVDC parallel transmission technology, improve the manufacturing technology level of offshore wind generation equipment, and promote the healthy development of offshore wind generation. Aiming at the technical requirements of VSCHVDC grid connected transmission in large offshore wind generation ten million kW base, this paper studies how to establish an accurate electromagnetic transient model of wind turbine based on a large number of practical tests and offshore wind turbine data. By selecting appropriate aggregation variables and aggregation algorithms, the necessity of proposing electromagnetic transient equivalent modeling method of wind generation is analyzed. It provides a research basis for analyzing the technical requirements of modeling and simulation development of tens of thousands of kW offshore wind generation cluster and revealing the interaction of fault characteristics between large offshore wind energy power base and power system grid under different faults.","PeriodicalId":272227,"journal":{"name":"2022 37th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123470111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Simulation Research On Photovoltaic-storage Distributed Power System In Island Operation","authors":"Tingbao Yu, Yulin Ye, Chen Liu, Hui Sun","doi":"10.1109/YAC57282.2022.10023782","DOIUrl":"https://doi.org/10.1109/YAC57282.2022.10023782","url":null,"abstract":"The stability of island operation of high power distributed power system is the focus and difficulty of distributed power supply research. We use the simulation software PSCAD/EMTDC to establish the model of the power supply system in this paper. The master-slave control method was adopted to simulate the island operating condition of the distributed power supply system. Through the simulation of ground fault condition of each circuit, the influence of ground fault condition on the island operation condition was verified. The simulation results show that the distributed power system with master-slave control can operate normally and stably under steady and ground fault conditions.","PeriodicalId":272227,"journal":{"name":"2022 37th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125593032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predictive Control of Networked High-Order Fully Actuated Systems with Packets Dropouts","authors":"Da‐Wei Zhang, Guo‐Ping Liu, Baolin Tan","doi":"10.1109/YAC57282.2022.10023658","DOIUrl":"https://doi.org/10.1109/YAC57282.2022.10023658","url":null,"abstract":"This research investigates an output tracking problem for networked control systems (NCSs) with packets dropouts. A high-order fully actuated (HOFA) model is applied to describe the dynamical model of NCSs. Correspondingly, a HOFA predictive control method is presented to solve this problem, where a HOFA prediction model can be established by using a Diophantine equation (DE) to substitute a reduced-order prediction model, then the multi-step output predictions are developed to derive an optimal control protocol which can implement the output tracking and compensate for the packets dropouts. A simple criterion is given to maintain the stability and output tracking for closed-loop NHOFA systems. Numerical simulation and comparison are provided to verify the feasibility of the proposed method.","PeriodicalId":272227,"journal":{"name":"2022 37th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115533287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Study of the Multivariate Image Analysis Method Combining Texture with Colour Features","authors":"Cheng Wang, Jinyu Wang, Ming Lu, Zezhong Liu","doi":"10.1109/yac57282.2022.10023552","DOIUrl":"https://doi.org/10.1109/yac57282.2022.10023552","url":null,"abstract":"Multivariate image analysis is a method of analysing multiple images by using principal component analysis, which analyses the information between multiple spectra of multiple images, and also means the colour information in RGB terms. While multivariate image analysis can get the colour features of an image, analysis of the texture features of an image is missing. This paper proposes a dual-feature multivariate image analysis method based on the grey-level co-occurrence matrix and the sliding window method to extract texture feature information in images and fuse it with colour feature information. This approach makes up for the shortcomings of the multivariate image analysis method for the analysis of texture feature information in images. The experiment on images with both texture features and colour features shows that the method proposed in this paper is effective.","PeriodicalId":272227,"journal":{"name":"2022 37th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114289305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}