A hybrid dynamic adversarial domain adaptation network with multi-channel attention mechanism for rotating machinery unsupervised fault diagnosis under varying operating conditions

IF 1.8 4区 工程技术 Q3 ENGINEERING, MECHANICAL
Hangbo Duan, Zongyan Cai, Yuanbo Xu
{"title":"A hybrid dynamic adversarial domain adaptation network with multi-channel attention mechanism for rotating machinery unsupervised fault diagnosis under varying operating conditions","authors":"Hangbo Duan, Zongyan Cai, Yuanbo Xu","doi":"10.1177/09544062241266349","DOIUrl":null,"url":null,"abstract":"Data-driven intelligent fault diagnosis methods have been extensively researched and applied in rotating machinery. In practical application scenarios, factors such as variable operating conditions and scarcity of labeled samples in rotating machinery hinder the engineering application and promotion of diagnostic models. To address these challenges, this paper proposes an unsupervised domain adaptation network called the Multi-scale Hybrid Domain Adaptation with Attention (MHDAA). Firstly, a multi-scale convolutional module was developed to extract fault features at different scales. Secondly, a multi-channel attention mechanism was proposed to enable the convolution layers of different convolution kernels fully extract feature information. Finally, a hybrid domain adaptation was constructed to dynamically extract invariant features from both the source and target domains. The method was evaluated in multiple transfer scenarios of planetary gearboxes and bearings. Experimental results demonstrate that the proposed method can effectively utilize fault features with high correlation from multiple source domains to complete fault diagnosis with unknown data labels in the target domain. Moreover, the proposed method exhibits superior diagnostic performance.","PeriodicalId":20558,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science","volume":null,"pages":null},"PeriodicalIF":1.8000,"publicationDate":"2024-07-26","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 C: Journal of Mechanical Engineering Science","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1177/09544062241266349","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}
引用次数: 0

Abstract

Data-driven intelligent fault diagnosis methods have been extensively researched and applied in rotating machinery. In practical application scenarios, factors such as variable operating conditions and scarcity of labeled samples in rotating machinery hinder the engineering application and promotion of diagnostic models. To address these challenges, this paper proposes an unsupervised domain adaptation network called the Multi-scale Hybrid Domain Adaptation with Attention (MHDAA). Firstly, a multi-scale convolutional module was developed to extract fault features at different scales. Secondly, a multi-channel attention mechanism was proposed to enable the convolution layers of different convolution kernels fully extract feature information. Finally, a hybrid domain adaptation was constructed to dynamically extract invariant features from both the source and target domains. The method was evaluated in multiple transfer scenarios of planetary gearboxes and bearings. Experimental results demonstrate that the proposed method can effectively utilize fault features with high correlation from multiple source domains to complete fault diagnosis with unknown data labels in the target domain. Moreover, the proposed method exhibits superior diagnostic performance.
具有多通道关注机制的混合动态对抗域适应网络,用于不同运行条件下旋转机械的无监督故障诊断
数据驱动的智能故障诊断方法在旋转机械领域得到了广泛的研究和应用。在实际应用场景中,旋转机械的运行条件多变、标注样本稀缺等因素阻碍了诊断模型的工程应用和推广。为应对这些挑战,本文提出了一种无监督域自适应网络,称为多尺度混合注意域自适应(MHDAA)。首先,开发了一个多尺度卷积模块来提取不同尺度的故障特征。其次,提出了一种多通道关注机制,使不同卷积核的卷积层能够充分提取特征信息。最后,构建了一种混合域自适应方法,以动态提取源域和目标域的不变特征。该方法在行星齿轮箱和轴承的多个传输场景中进行了评估。实验结果表明,所提出的方法能有效利用来自多个源域的高相关性故障特征,在目标域数据标签未知的情况下完成故障诊断。此外,所提出的方法还具有卓越的诊断性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
3.80
自引率
10.00%
发文量
625
审稿时长
4.3 months
期刊介绍: The Journal of Mechanical Engineering Science advances the understanding of both the fundamentals of engineering science and its application to the solution of challenges and problems in engineering.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信