This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Residual Adversarial Subdomain Adaptation Network Based on Wasserstein Metrics for Intelligent Fault Diagnosis of Bearings
by
Haichao Cai
Haichao Cai 1,2,3,*,†,
Bo Yang
Bo Yang 1,2,3,†,
Yujun Xue
Yujun Xue 1,3 and
Yanwei Xu
Yanwei Xu 1
1
School of Mechanical and Electrical Engineering, Henan University of Science and Technology, Luoyang 471003, China
2
LongMen Laboratory, Luoyang 471003, China
3
Collaborative Innovation Center of High-End Bearing, Luoyang 471000, China
*
Author to whom correspondence should be addressed.
†
These authors contributed equally to this work.
Appl. Sci. 2024, 14(19), 9057; https://doi.org/10.3390/app14199057 (registering DOI)
Submission received: 19 August 2024
/
Revised: 27 September 2024
/
Accepted: 4 October 2024
/
Published: 7 October 2024
Abstract
Subdomain adaptation plays a significant role in the field of bearing fault diagnosis. It effectively aligns the pertinent distributions across subdomains and addresses the frequent issue of lacking local category information in domain adaptation. Nonetheless, this approach overlooks the quantitative discrepancies in distribution between samples from the source and target domains, leading to the vanishing gradient issue during the training of models. To tackle this challenge, this paper proposes a bearing fault diagnosis method based on Wasserstein metric residual adversarial subdomain adaptation. The Wasserstein metric is introduced as the optimized objective function of the domain discriminator in RASAN-W. The distribution discrepancy between the source domain and target domain samples is quantitatively measured, achieving the alignment of the relevant subdomain distributions between the source domain and the target domain. Ultimately, extensive experiments conducted on two real-world datasets reveal that the diagnostic accuracy of this method is significantly enhanced when compared to various leading bearing fault diagnosis techniques.
Share and Cite
MDPI and ACS Style
Cai, H.; Yang, B.; Xue, Y.; Xu, Y.
Residual Adversarial Subdomain Adaptation Network Based on Wasserstein Metrics for Intelligent Fault Diagnosis of Bearings. Appl. Sci. 2024, 14, 9057.
https://doi.org/10.3390/app14199057
AMA Style
Cai H, Yang B, Xue Y, Xu Y.
Residual Adversarial Subdomain Adaptation Network Based on Wasserstein Metrics for Intelligent Fault Diagnosis of Bearings. Applied Sciences. 2024; 14(19):9057.
https://doi.org/10.3390/app14199057
Chicago/Turabian Style
Cai, Haichao, Bo Yang, Yujun Xue, and Yanwei Xu.
2024. "Residual Adversarial Subdomain Adaptation Network Based on Wasserstein Metrics for Intelligent Fault Diagnosis of Bearings" Applied Sciences 14, no. 19: 9057.
https://doi.org/10.3390/app14199057
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.