Unsupervised domain adaptation of bearing fault diagnosis based on Join Sliced Wasserstein Distance

doi:10.1016/j.isatra.2021.12.037

IR > 机电工程学院

	Unsupervised domain adaptation of bearing fault diagnosis based on Join Sliced Wasserstein Distance
	Chen, Pengfei 1,2; Zhao, Rongzhen 1; He, Tianjing1 ; Wei, Kongyuan1 ; Yang, Qidong 2
	2022-10
发表期刊	ISA Transactions
ISSN	0019-0578
卷号	129 页码:504-519
摘要	Deep neural networks have been successfully utilized in the mechanical fault diagnosis, however, a large number of them have been based on the same assumption that training and test datasets followed the same distributions. Unfortunately, the mechanical systems are easily affected by environment noise interference, speed or load change. Consequently, the trained networks have poor generalization under various working conditions. Recently, unsupervised domain adaptation has been concentrated on more and more attention since it can handle different but related data. Sliced Wasserstein Distance has been successfully utilized in unsupervised domain adaptation and obtained excellent performances. However, most of the approaches have ignored the class conditional distribution. In this paper, a novel approach named Join Sliced Wasserstein Distance (JSWD) has been proposed to address the above issue. Four bearing datasets have been selected to validate the practicability and effectiveness of the JSWD framework. The experimental results have demonstrated that about 5% accuracy is improved by JSWD with consideration of the conditional probability than no the conditional probability, in addition, the other experimental results have indicated that JSWD could effectively capture the distinguishable and domain-invariant representations and have a has superior data distribution matching than the previous methods under various application scenarios. © 2022 ISA
关键词	Bearings (machine parts) Deep neural networks Fault detection Large dataset Probability distributions Bearing fault diagnosis Conditional probabilities Domain adaptation Faults diagnosis Mechanical faults diagnosis Mechanical systems Noise interference Pseudo label Sliced wasserstein distances Unsupervised domain adaptation
DOI	10.1016/j.isatra.2021.12.037
收录类别	EI ; SCIE
语种	英语
WOS研究方向	Automation & Control Systems ; Engineering ; Instruments & Instrumentation
WOS类目	Automation & Control Systems ; Engineering, Multidisciplinary ; Instruments & Instrumentation
WOS记录号	WOS:000875903100005
出版者	ISA - Instrumentation, Systems, and Automation Society
EI入藏号	20220411491377
EI主题词	Failure analysis
EI分类号	461.4 Ergonomics and Human Factors Engineering ; 601.2 Machine Components ; 723.2 Data Processing and Image Processing ; 922.1 Probability Theory
来源库	WOS
引用统计	被引频次：23[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/159100
专题	机电工程学院
通讯作者	Chen, Pengfei
作者单位	1.Lanzhou Univ Technol, Sch Mech & Elect Engn, Lanzhou 730050, Peoples R China; 2.Gansu Agr Mechanizat Technol Extens Stn, Lanzhou 730046, Peoples R China
第一作者单位	兰州理工大学
通讯作者单位	兰州理工大学
第一作者的第一单位	兰州理工大学
推荐引用方式 GB/T 7714	Chen, Pengfei,Zhao, Rongzhen,He, Tianjing,et al. Unsupervised domain adaptation of bearing fault diagnosis based on Join Sliced Wasserstein Distance[J]. ISA Transactions,2022,129:504-519.
APA	Chen, Pengfei,Zhao, Rongzhen,He, Tianjing,Wei, Kongyuan,&Yang, Qidong.(2022).Unsupervised domain adaptation of bearing fault diagnosis based on Join Sliced Wasserstein Distance.ISA Transactions,129,504-519.
MLA	Chen, Pengfei,et al."Unsupervised domain adaptation of bearing fault diagnosis based on Join Sliced Wasserstein Distance".ISA Transactions 129(2022):504-519.