Unsupervised domain adaptation of bearing fault diagnosis based on Join Sliced Wasserstein Distance | |
Chen, Pengfei1,2; Zhao, Rongzhen1; He, Tianjing1; Wei, Kongyuan1; Yang, Qidong2 | |
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 | |
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. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论