EUVIMEDEUVIMED entdecken
Crossref

Cross-domain self-supervised contrastive learning with multi-scale feature fusion for bearing fault diagnosis under limited labels

Cainian Li, Teng Ran, Chao Liu, Hong Jiang, Liang Yuan, Jun Xie

Measurement Science and Technology · 31.10.2025 · 36 (10) · 106125

DOI: 10.1088/1361-6501/ae0e8d ↗

Kurz gefasst

Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 16.10.2025. Verfasst von Cainian Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: The key research and development projects of Xinjiang Uygur Autonomous Region under Grants, Tianshan Talent Training Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning is extensively used in fault diagnosis. Actual implementations frequently encounter the issue of limited labeled data. This paper proposes a cross-domain self-supervised contrastive learning method with multi-scale feature fusion (CD-MSSCL) for bearing fault diagnosis under limited samples. The method first employs a specialized time-domain data augmentation strategy to capture the complexity of industrial vibration signals and enhance model generalization. A designed encoder backbone network combines multi-scale features with a SENet attention mechanism using pyramid fusion. The network performs self-supervised pre-training on unlabeled samples to effectively capture multi-frequency fault features critical for bearing fault diagnosis. Limited labeled samples then fine-tune the model to transfer pre-trained features to specific tasks. Experimental results show CD-MSSCL outperforms traditional deep learning and current contrastive learning methods in accuracy and domain adaptation under limited labels. The approach significantly reduces data collection and labeling costs through effective unsupervised knowledge extraction and transfer.

Förderung

  • The key research and development projects of Xinjiang Uygur Autonomous Region under Grants
  • Tianshan Talent Training Program

Zitieren

APA

Li, C., Ran, T., Liu, C., Jiang, H., Yuan, L., & Xie, J. (2025). Cross-domain self-supervised contrastive learning with multi-scale feature fusion for bearing fault diagnosis under limited labels. Measurement Science and Technology, 36(10), 106125. https://doi.org/10.1088/1361-6501/ae0e8d

Vancouver

Li C, Ran T, Liu C, Jiang H, Yuan L, Xie J. Cross-domain self-supervised contrastive learning with multi-scale feature fusion for bearing fault diagnosis under limited labels. Measurement Science and Technology. 2025;36(10):106125. doi:10.1088/1361-6501/ae0e8d

BibTeX
@article{Li2025,
  author = {Li, Cainian and Ran, Teng and Liu, Chao and Jiang, Hong and Yuan, Liang and Xie, Jun},
  title = {Cross-domain self-supervised contrastive learning with multi-scale feature fusion for bearing fault diagnosis under limited labels},
  journal = {Measurement Science and Technology},
  year = {2025},
  volume = {36},
  number = {10},
  pages = {106125},
  doi = {10.1088/1361-6501/ae0e8d}
}
Kostenlos starten →