{"title":"多尺度卷积条件域对抗网络与通道关注用于无监督轴承故障诊断","authors":"Haomiao Wang, Yibin Li, Mingshun Jiang, Faye Zhang","doi":"10.1177/09596518241226461","DOIUrl":null,"url":null,"abstract":"Unsupervised cross-domain fault diagnosis is an effective technical way to realize the engineering application of bearing fault diagnosis methods. However, there are still two problems that need to be resolved. First, the importance of fault features at different scales is generally not consistent. There is redundant information in the fault features. Second, most methods mainly study how to lessen the marginal distribution difference in source and target domains while ignoring their class information. When the data distribution contains complex multimodal structure, this may lead to failure to capture the multimodal structure. To address the above problems, a multiscale channel attention conditional domain adversarial network is proposed. First, a new channel attention module is designed to assign different weights to different channels, which can highlight valuable features and stamp out superfluous features. Then, conditional domain adversarial is used to fully capture the multimodal structure through cross-covariance dependencies between features and classes. Our method’s capability is validated by diagnose results on public data sets and self-built data sets.","PeriodicalId":20638,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2024-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Multiscale convolutional conditional domain adversarial network with channel attention for unsupervised bearing fault diagnosis\",\"authors\":\"Haomiao Wang, Yibin Li, Mingshun Jiang, Faye Zhang\",\"doi\":\"10.1177/09596518241226461\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Unsupervised cross-domain fault diagnosis is an effective technical way to realize the engineering application of bearing fault diagnosis methods. However, there are still two problems that need to be resolved. First, the importance of fault features at different scales is generally not consistent. There is redundant information in the fault features. Second, most methods mainly study how to lessen the marginal distribution difference in source and target domains while ignoring their class information. When the data distribution contains complex multimodal structure, this may lead to failure to capture the multimodal structure. To address the above problems, a multiscale channel attention conditional domain adversarial network is proposed. First, a new channel attention module is designed to assign different weights to different channels, which can highlight valuable features and stamp out superfluous features. Then, conditional domain adversarial is used to fully capture the multimodal structure through cross-covariance dependencies between features and classes. Our method’s capability is validated by diagnose results on public data sets and self-built data sets.\",\"PeriodicalId\":20638,\"journal\":{\"name\":\"Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2024-01-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1177/09596518241226461\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"AUTOMATION & CONTROL SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1177/09596518241226461","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}
Multiscale convolutional conditional domain adversarial network with channel attention for unsupervised bearing fault diagnosis
Unsupervised cross-domain fault diagnosis is an effective technical way to realize the engineering application of bearing fault diagnosis methods. However, there are still two problems that need to be resolved. First, the importance of fault features at different scales is generally not consistent. There is redundant information in the fault features. Second, most methods mainly study how to lessen the marginal distribution difference in source and target domains while ignoring their class information. When the data distribution contains complex multimodal structure, this may lead to failure to capture the multimodal structure. To address the above problems, a multiscale channel attention conditional domain adversarial network is proposed. First, a new channel attention module is designed to assign different weights to different channels, which can highlight valuable features and stamp out superfluous features. Then, conditional domain adversarial is used to fully capture the multimodal structure through cross-covariance dependencies between features and classes. Our method’s capability is validated by diagnose results on public data sets and self-built data sets.
期刊介绍:
Systems and control studies provide a unifying framework for a wide range of engineering disciplines and industrial applications. The Journal of Systems and Control Engineering refleSystems and control studies provide a unifying framework for a wide range of engineering disciplines and industrial applications. The Journal of Systems and Control Engineering reflects this diversity by giving prominence to experimental application and industrial studies.
"It is clear from the feedback we receive that the Journal is now recognised as one of the leaders in its field. We are particularly interested in highlighting experimental applications and industrial studies, but also new theoretical developments which are likely to provide the foundation for future applications. In 2009, we launched a new Series of "Forward Look" papers written by leading researchers and practitioners. These short articles are intended to be provocative and help to set the agenda for future developments. We continue to strive for fast decision times and minimum delays in the production processes." Professor Cliff Burrows - University of Bath, UK
This journal is a member of the Committee on Publication Ethics (COPE).cts this diversity by giving prominence to experimental application and industrial studies.