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

doi:10.1016/j.isatra.2021.12.037

CORC > 兰州理工大学 > 兰州理工大学 > 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, Tianjing 1; Wei, Kongyuan 1; Yang, Qidong 2
刊名	ISA Transactions
	2022
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
ISSN号	0019-0578
DOI	10.1016/j.isatra.2021.12.037
英文摘要	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
语种	英语
出版者	ISA - Instrumentation, Systems, and Automation Society
内容类型	期刊论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/159100]
专题	机电工程学院
作者单位	1.School of Mechanical and Electrical Engineering, Lanzhou University of Technology, Lanzhou; 730050, China; 2.Gansu Agricultural Mechanization Technology Extension Station, Lanzhou; 730046, China
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.
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.
MLA	Chen, Pengfei,et al."Unsupervised domain adaptation of bearing fault diagnosis based on Join Sliced Wasserstein Distance".ISA Transactions (2022).