Mechanical equipment fault diagnosis technology is a new research field with the development of modern science and technology In recent years, the deep learning has been applied into the field of mechanical equipment fault diagnosis by more and more researchers. Deep learning has been widely applied in various in dustries and fields with its unique advantages in feature extraction and pattern recognition. The development history of deep learning is first briefly reviewed. Then, four fault diagnosis methods based on deep learning model are emphatically analyzed com bined with the characteristics and requirements of fault diagnosis technology for large rotating machinery equipment, and the problems and challenges they face are discussed. Finally, the research direction worth to be carried out in the future is prospected.
{"title":"REVIEW OF FAULT DIAGNOSIS METHODS FOR ROTATING MACHINERY BASED ON DEEP LEARNING","authors":"Y. L. Guo, G. Wu, X. L. Liu, X. L. Xu","doi":"10.1049/icp.2021.1316","DOIUrl":"https://doi.org/10.1049/icp.2021.1316","url":null,"abstract":"Mechanical equipment fault diagnosis technology is a new research field with the development of modern science and technology In recent years, the deep learning has been applied into the field of mechanical equipment fault diagnosis by more and more researchers. Deep learning has been widely applied in various in dustries and fields with its unique advantages in feature extraction and pattern recognition. The development history of deep learning is first briefly reviewed. Then, four fault diagnosis methods based on deep learning model are emphatically analyzed com bined with the characteristics and requirements of fault diagnosis technology for large rotating machinery equipment, and the problems and challenges they face are discussed. Finally, the research direction worth to be carried out in the future is prospected.","PeriodicalId":337028,"journal":{"name":"The 8th International Symposium on Test Automation & Instrumentation (ISTAI 2020)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124787810","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}
The integrated navigation system that combines the global positioning system (GPS) and the inertial navigation system (INS) has attracted widespread attention. In order to improve its positioning and navigation accuracy, Kalman filtering algorithms are usually used to process navigation data. This paper combines fuzzy control theory with Kalman filter, and proposes an integrated navigation algorithm based on fuzzy control theory, specifically observing each component of the residual error, using multiple fuzzy inference systems to modify the measurement noise variance matrix to approximate the real noise characteristic. Through multiple simulation experiments, the results show that the algorithm can effectively suppress the filtering divergence.
{"title":"INTEGRATED NAVIGATION ALGORITHM BASED ON FUZZY CONTROL","authors":"Z. Jiangmiao, X. Dong, H. Yan, Y. Sha","doi":"10.1049/icp.2021.1330","DOIUrl":"https://doi.org/10.1049/icp.2021.1330","url":null,"abstract":"The integrated navigation system that combines the global positioning system (GPS) and the inertial navigation system (INS) has attracted widespread attention. In order to improve its positioning and navigation accuracy, Kalman filtering algorithms are usually used to process navigation data. This paper combines fuzzy control theory with Kalman filter, and proposes an integrated navigation algorithm based on fuzzy control theory, specifically observing each component of the residual error, using multiple fuzzy inference systems to modify the measurement noise variance matrix to approximate the real noise characteristic. Through multiple simulation experiments, the results show that the algorithm can effectively suppress the filtering divergence.","PeriodicalId":337028,"journal":{"name":"The 8th International Symposium on Test Automation & Instrumentation (ISTAI 2020)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126110508","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}
In view of the problem that the combination of gyroscope and accelerometer is used to obtain the carrier attitude information in the traditional attitude solving method, an attitude solving method of inertial measurement unit based on gradient descentalgorithm is proposed.This method uses a quaternion-based gradient descent algorithm to fuse sensor data, and obtains the attitude angle information of the carrier movement. The three-dimensional flight simulation system is used to collect experimental data and verify the stability and effectiveness of the algorithm. Compared with the traditional attitude calculation method, it is verified that this method has the characteristics of fast convergence.
{"title":"IMU ATTITUDE CALCULATION METHOD BASED ON GRADIENT DESCENT ALGORITHM","authors":"W. Qi, N. Liu","doi":"10.1049/icp.2021.1315","DOIUrl":"https://doi.org/10.1049/icp.2021.1315","url":null,"abstract":"In view of the problem that the combination of gyroscope and accelerometer is used to obtain the carrier attitude information in the traditional attitude solving method, an attitude solving method of inertial measurement unit based on gradient descentalgorithm is proposed.This method uses a quaternion-based gradient descent algorithm to fuse sensor data, and obtains the attitude angle information of the carrier movement. The three-dimensional flight simulation system is used to collect experimental data and verify the stability and effectiveness of the algorithm. Compared with the traditional attitude calculation method, it is verified that this method has the characteristics of fast convergence.","PeriodicalId":337028,"journal":{"name":"The 8th International Symposium on Test Automation & Instrumentation (ISTAI 2020)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124546702","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}
Jitter is a very important parameter in wired digital communication. It is usually measured by SDH transmission analyzer. When the jitter of SDH transmission analyzer is calibrated, the Bessel function ratio method is used. However, the method is not suitable for large jitter amplitude output from SDH transmission analyzer such as 50UIpp above. This paper introduces the wide-band frequency modulation method to calibrate the jitter amplitude of SDH analyzer, and the uncertainty evaluation results are given at the end of this paper
{"title":"LARGE JITTER AMPLITUDE CALIBRATION OF SDH TRANSMISSION ANALYZER BY WIDE BAND FM METHOD","authors":"Z. Zhan, L. Yu, Y. Wang","doi":"10.1049/ICP.2021.1300","DOIUrl":"https://doi.org/10.1049/ICP.2021.1300","url":null,"abstract":"Jitter is a very important parameter in wired digital communication. It is usually measured by SDH transmission analyzer. When the jitter of SDH transmission analyzer is calibrated, the Bessel function ratio method is used. However, the method is not suitable for large jitter amplitude output from SDH transmission analyzer such as 50UIpp above. This paper introduces the wide-band frequency modulation method to calibrate the jitter amplitude of SDH analyzer, and the uncertainty evaluation results are given at the end of this paper","PeriodicalId":337028,"journal":{"name":"The 8th International Symposium on Test Automation & Instrumentation (ISTAI 2020)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121824811","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}
In order to increase comprehension on abstract theory and decrease the fear of writing intelligent algorithms, engineering training based on poetry automatic generation system of natural speech recognition technology is proposed. Firstly, the background of artificial intelligence(AI) is introduced, then the comprehensive experimental teaching was separated into the simple operation training model designing and exploring teaching model, due to the characteristics and problems of complex artificial intelli-gence engineering simulation education for undergraduates. Finally, Combining the advantages of some algorithms, Displaying the automatically generated poetry to collect samples, which can enable students to learn the application of intelligent algorithm intuitively. The test on the training platform shows that the automatic generation of five characters or seven characters poems has a high probability of poetic features, and the strong correlation is between the poems generated by LSTM model and keywords.
{"title":"POETRY AUTOMATIC GENERATION SYSTEM BASED ON NATURAL LANGUAGE PROCESSING","authors":"X. Xu, J. Miao, Y. Chen, S. Yang","doi":"10.1049/icp.2021.1308","DOIUrl":"https://doi.org/10.1049/icp.2021.1308","url":null,"abstract":"In order to increase comprehension on abstract theory and decrease the fear of writing intelligent algorithms, engineering training based on poetry automatic generation system of natural speech recognition technology is proposed. Firstly, the background of artificial intelligence(AI) is introduced, then the comprehensive experimental teaching was separated into the simple operation training model designing and exploring teaching model, due to the characteristics and problems of complex artificial intelli-gence engineering simulation education for undergraduates. Finally, Combining the advantages of some algorithms, Displaying the automatically generated poetry to collect samples, which can enable students to learn the application of intelligent algorithm intuitively. The test on the training platform shows that the automatic generation of five characters or seven characters poems has a high probability of poetic features, and the strong correlation is between the poems generated by LSTM model and keywords.","PeriodicalId":337028,"journal":{"name":"The 8th International Symposium on Test Automation & Instrumentation (ISTAI 2020)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134091750","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}
Building a cloud service platform for CNC machine can save a lot of training costs and time, effectively solve the problems such as large investment in the renovation of CNC equipment and fast replacement speed, simulate the production and processing process of enterprises, and seamlessly connect real machine tools. The training cloud platform can provide MOOC-style teaching simultaneously and the information interaction of each simulation terminal is realized. Enterprise cloud platform is equipped with the online publishing function of enterprise requirements, remote expert system and early fault simulation and prediction function to realize the efficient utilization of intelligent manufacturing resources.
{"title":"RESEARCH ON SEMI-PHYSICAL SIMULATION SYSTEM OF HIGH-END CNC MACHINE BASED ON CLOUD PLATFORM","authors":"G. Wu, J. Zhanglei, X. Liu, S. Deng, X. Xu","doi":"10.1049/icp.2021.1317","DOIUrl":"https://doi.org/10.1049/icp.2021.1317","url":null,"abstract":"Building a cloud service platform for CNC machine can save a lot of training costs and time, effectively solve the problems such as large investment in the renovation of CNC equipment and fast replacement speed, simulate the production and processing process of enterprises, and seamlessly connect real machine tools. The training cloud platform can provide MOOC-style teaching simultaneously and the information interaction of each simulation terminal is realized. Enterprise cloud platform is equipped with the online publishing function of enterprise requirements, remote expert system and early fault simulation and prediction function to realize the efficient utilization of intelligent manufacturing resources.","PeriodicalId":337028,"journal":{"name":"The 8th International Symposium on Test Automation & Instrumentation (ISTAI 2020)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122055983","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}
In the context of the increasing speed of high-speed trains, the safe and comfortable operation depends on the wheel-rail condition monitoring. First, this paper introduces the analysis of wheel-rail adhesion behavior from the aspects of rolling contact model and adhesion and wear. Second, this paper summarizes the research results related to the perception of wheel-rail condition information in recent years from the perspectives of wheel-rail force measurement and wheel-rail damage detection. Third, it focuses on the current situation of wheel-rail dynamic damage diagnosis and discusses the microdamage diagnosis around deep learning. Finally, the development trend of wheel-rail condition monitoring is stated from the perspectives of multicoupling wheel-rail dynamic contact system modeling, highly precise wheel-rail condition information perception, and wheel-rail dynamic microdamage diagnosis based on small sample.
{"title":"REVIEW OF RESEARCH ON KEY TECHNOLOGIES FOR HIGH-SPEED TRAIN WHEEL-RAIL CONDITION MONITORING","authors":"C. Zhang, Q. Zhang, J. He, J. Liu","doi":"10.1049/ICP.2021.1332","DOIUrl":"https://doi.org/10.1049/ICP.2021.1332","url":null,"abstract":"In the context of the increasing speed of high-speed trains, the safe and comfortable operation depends on the wheel-rail condition monitoring. First, this paper introduces the analysis of wheel-rail adhesion behavior from the aspects of rolling contact model and adhesion and wear. Second, this paper summarizes the research results related to the perception of wheel-rail condition information in recent years from the perspectives of wheel-rail force measurement and wheel-rail damage detection. Third, it focuses on the current situation of wheel-rail dynamic damage diagnosis and discusses the microdamage diagnosis around deep learning. Finally, the development trend of wheel-rail condition monitoring is stated from the perspectives of multicoupling wheel-rail dynamic contact system modeling, highly precise wheel-rail condition information perception, and wheel-rail dynamic microdamage diagnosis based on small sample.","PeriodicalId":337028,"journal":{"name":"The 8th International Symposium on Test Automation & Instrumentation (ISTAI 2020)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127331361","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}
DC current ratio error is an essential measurement performance of DC current ratio instrument, for example, DC current comparator, DC current transformer and DC current sensor. Error determination contributes to the instrument rational use. Based on the principle of secondary differential current measurement, self-calibration method, equal-ratio calibration method and stage-connection equal-ratio calibration method were put forward according to the characteristics of different calibrated instruments. Then, the actual value and error of DC current ratio were available. Meanwhile, circuit diagrams, calibration process and examples were provided; measurement uncertainty was evaluated. The result shows that the proposed methods meet the calibration requirements of DC current ratio instruments; the expanded uncertainty for the 1 A: 1 A～ 1000 A: 0.5 A ratio is 1.7×10-8～8.4×10-6. The automatic measurement program can effectively improve the work efficiency.
{"title":"AUTOMATIC MEASUREMENT AND CALIBRATION OF DC CURRENT RATIO ERROR","authors":"L. Zhou, Y. Pan, L. Lai, J. Feng, G. Zhan","doi":"10.1049/ICP.2021.1295","DOIUrl":"https://doi.org/10.1049/ICP.2021.1295","url":null,"abstract":"DC current ratio error is an essential measurement performance of DC current ratio instrument, for example, DC current comparator, DC current transformer and DC current sensor. Error determination contributes to the instrument rational use. Based on the principle of secondary differential current measurement, self-calibration method, equal-ratio calibration method and stage-connection equal-ratio calibration method were put forward according to the characteristics of different calibrated instruments. Then, the actual value and error of DC current ratio were available. Meanwhile, circuit diagrams, calibration process and examples were provided; measurement uncertainty was evaluated. The result shows that the proposed methods meet the calibration requirements of DC current ratio instruments; the expanded uncertainty for the 1 A: 1 A～ 1000 A: 0.5 A ratio is 1.7×10-8～8.4×10-6. The automatic measurement program can effectively improve the work efficiency.","PeriodicalId":337028,"journal":{"name":"The 8th International Symposium on Test Automation & Instrumentation (ISTAI 2020)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131593812","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}
The rapid development of digital information technology and its application in packaging have brought many innovative functions to packaging, as a result, digital intelligent packaging has emerged. According to the differences of application technology, digital intelligent packaging can be divided into ontology intelligent packaging, controlled packaging based on the Internet of Things, platform packaging based on mobile Internet, and interactive packaging based on ARVR technology. The features of digital intelligent packaging include enhanced packaging information transmission, enhanced promotional effects, enhanced packaging control, and enhanced anti-counterfeiting functions.
{"title":"RESEARCH ON DIGITAL INTELLIGENT PACKAGING","authors":"S. Ke, P. Guo, Y. Ma, Z. Yang","doi":"10.1049/icp.2021.1334","DOIUrl":"https://doi.org/10.1049/icp.2021.1334","url":null,"abstract":"The rapid development of digital information technology and its application in packaging have brought many innovative functions to packaging, as a result, digital intelligent packaging has emerged. According to the differences of application technology, digital intelligent packaging can be divided into ontology intelligent packaging, controlled packaging based on the Internet of Things, platform packaging based on mobile Internet, and interactive packaging based on ARVR technology. The features of digital intelligent packaging include enhanced packaging information transmission, enhanced promotional effects, enhanced packaging control, and enhanced anti-counterfeiting functions.","PeriodicalId":337028,"journal":{"name":"The 8th International Symposium on Test Automation & Instrumentation (ISTAI 2020)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133084420","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}
Galloping is a disaster of transmission lines. It is a large-amplitude, low-frequency mechanical vibration that occurs on transmission lines under a combination of wind, ice-covered lift, and wire tension under specific weather conditions. At present, an online monitoring system with a single sensing method is widely used in the power grid. There is still relatively little research on the prediction of galloping disasters. This article designs an online monitoring and prediction system that combines video monitoring and inertial navigation modules. In the system, the data fusion method is repeatedly used to achieve more accurate on-line monitoring and short-term prediction of transmission line galloping.
{"title":"DESIGN OF MONITORAND PREDICTION SYSTEM FOR HIGH VOLTAGE TRANSMISSION LINE GALLOPING","authors":"R. Li, T. Wang","doi":"10.1049/icp.2021.1313","DOIUrl":"https://doi.org/10.1049/icp.2021.1313","url":null,"abstract":"Galloping is a disaster of transmission lines. It is a large-amplitude, low-frequency mechanical vibration that occurs on transmission lines under a combination of wind, ice-covered lift, and wire tension under specific weather conditions. At present, an online monitoring system with a single sensing method is widely used in the power grid. There is still relatively little research on the prediction of galloping disasters. This article designs an online monitoring and prediction system that combines video monitoring and inertial navigation modules. In the system, the data fusion method is repeatedly used to achieve more accurate on-line monitoring and short-term prediction of transmission line galloping.","PeriodicalId":337028,"journal":{"name":"The 8th International Symposium on Test Automation & Instrumentation (ISTAI 2020)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132646061","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：