EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CWMS-GAN: A small-sample bearing fault diagnosis method based on continuous wavelet transform and multi-size kernel attention mechanism

Shun Yu, Zi Li, Jialin Gu, Runpu Wang, Xiaoyu Liu, Lin Li, Fusen Guo iD, Yuheng Ren iD

PLOS ONE · 11.04.2025 · 20 (4) · e0319202

DOI: 10.1371/journal.pone.0319202 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 11.04.2025. Verfasst von Shun Yu und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Systems and Computing, University of New South Wales, Canberra, Australia. Hauptthemen laut MEDLINE: Wavelet Analysis, Neural Networks, Computer. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In industrial production, obtaining sufficient bearing fault signals is often extremely difficult, leading to a significant degradation in the performance of traditional deep learning-based fault diagnosis models. Many recent studies have shown that data augmentation using generative adversarial networks (GAN) can effectively alleviate this problem. However, the quality of generated samples is closely related to the performance of fault diagnosis models. For this reason, this paper proposes a new GAN-based small-sample bearing fault diagnosis method. Specifically, this study proposes a continuous wavelet convolution strategy (CWCL) instead of the traditional convolution operation in GAN, which can additionally capture the signal’s frequency domain features. Meanwhile, this study designed a new multi-size kernel attention mechanism (MSKAM), which can extract the features of bearing vibration signals from different scales and adaptively select the features that are more important for the generation task to improve the accuracy and authenticity of the generated signals. In addition, the structural similarity index (SSIM) is adopted to quantitatively evaluate the quality of the generated signal by calculating the similarity between the generated signal and the real signal in both the time and frequency domains. Finally, we conducted extensive experiments on the CWRU and MFPT datasets and made a comprehensive comparison with existing small-sample bearing fault diagnosis methods, which verified the effectiveness of the proposed approach.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Wavelet AnalysisNeural Networks, ComputerAlgorithmsDeep Learning

Autor:innen und Institutionen

  • School of Systems and Computing, University of New South Wales, Canberra, Australia.
  • Guanghua School of Management, Peking university, Beijing, China.
  • Faculty of Science and Engineering, Southern Cross University, Gold Coast, Australia.
  • School of Business Economics, European Union University, Montreux, Switzerland.

ORCID-Profile: Fusen Guo, Yuheng Ren

Zitieren

APA

Yu, S., Li, Z., Gu, J., Wang, R., Liu, X., Li, L., Guo, F., & Ren, Y. (2025). CWMS-GAN: A small-sample bearing fault diagnosis method based on continuous wavelet transform and multi-size kernel attention mechanism. PLOS ONE, 20(4), e0319202. https://doi.org/10.1371/journal.pone.0319202

Vancouver

Yu S, Li Z, Gu J, Wang R, Liu X, Li L, et al. CWMS-GAN: A small-sample bearing fault diagnosis method based on continuous wavelet transform and multi-size kernel attention mechanism. PLOS ONE. 2025;20(4):e0319202. doi:10.1371/journal.pone.0319202

BibTeX
@article{Yu2025,
  author = {Yu, Shun and Li, Zi and Gu, Jialin and Wang, Runpu and Liu, Xiaoyu and Li, Lin and Guo, Fusen and Ren, Yuheng},
  title = {CWMS-GAN: A small-sample bearing fault diagnosis method based on continuous wavelet transform and multi-size kernel attention mechanism},
  journal = {PLOS ONE},
  year = {2025},
  volume = {20},
  number = {4},
  pages = {e0319202},
  doi = {10.1371/journal.pone.0319202}
}
Kostenlos starten →