EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Supervision-Guided Contrastive Learning for Rolling Bearing Fault Diagnosis Under Label Scarcity

Xinwei Zhao, Xu Zhang, Lei Su, Ke Li

IEEE Access · 2026 · 14 · 86458-86473

DOI: 10.1109/access.2026.3698190 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Xinwei Zhao und 3 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, State Key Laboratory of Mechanical System and Vibration, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

While deep learning has advanced industrial fault diagnosis, its reliance on massive labeled datasets remains a major obstacle to real-world application. In response to the scarcity of labeled fault samples and ineffective utilization of abundant unlabeled data, this paper proposes a novel semi-supervised fault diagnosis method based on supervision-guided contrastive learning (SGCL). First, a supervision-guided mechanism is introduced to leverage a small number of labeled samples to construct semantic class centers. This explicitly guides unlabeled data toward their respective categories, thereby alleviating the mismatch between different optimization objectives and enhancing intra-class compactness and inter-class separability. Second, a consistency regularization strategy is introduced to improve the model’s representation capability via pseudo-label constraints, enabling unlabeled representations to directly participate in updating the classifier parameters. By jointly optimizing these mechanisms, the proposed framework seamlessly translates raw unlabeled data into highly discriminative diagnostic features. Comprehensive experiments on a self-built dataset and the Paderborn dataset demonstrate that SGCL achieves diagnostic accuracies of 91.74% and 91.42%, respectively, under a 5% label ratio. This represents an average improvement of approximately 8%-10% over compared generative and contrastive semi-supervised methods, verifying the effectiveness of the proposed approach in addressing fault diagnosis tasks under severely limited label conditions.

Förderung

  • National Natural Science Foundation of China
  • State Key Laboratory of Mechanical System and Vibration
  • National Key Research and Development Program of China

Zitieren

APA

Zhao, X., Zhang, X., Su, L., & Li, K. (2026). Supervision-Guided Contrastive Learning for Rolling Bearing Fault Diagnosis Under Label Scarcity. IEEE Access, 14, 86458-86473. https://doi.org/10.1109/access.2026.3698190

Vancouver

Zhao X, Zhang X, Su L, Li K. Supervision-Guided Contrastive Learning for Rolling Bearing Fault Diagnosis Under Label Scarcity. IEEE Access. 2026;14:86458-86473. doi:10.1109/access.2026.3698190

BibTeX
@article{Zhao2026,
  author = {Zhao, Xinwei and Zhang, Xu and Su, Lei and Li, Ke},
  title = {Supervision-Guided Contrastive Learning for Rolling Bearing Fault Diagnosis Under Label Scarcity},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {86458--86473},
  doi = {10.1109/access.2026.3698190}
}
Kostenlos starten →