EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Self-Supervised CNN–Transformer Anomaly Detection for Bearing Health Monitoring

Syed Haseeb Haider Zaidi, Alex Shenfield, Hongwei Zhang, Augustine Ikpehai

Processes · 30.07.2026 · 14 (15) · 2452

DOI: 10.3390/pr14152452 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Processes, online erschienen am 30.07.2026. Verfasst von Syed Haseeb Haider Zaidi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable bearing fault detection is essential for predictive maintenance in industrial systems; however, obtaining labelled fault data is often expensive, time-consuming, and impractical in real-world deployments. To address this challenge, this study proposes a healthy-only self-supervised anomaly detection framework for bearing health monitoring using vibration measurements. The proposed approach combines convolutional neural networks and Transformer-based temporal modelling to learn informative representations from healthy vibration signals without requiring fault labels during representation learning. Three self-supervised learning strategies—reconstruction-based, contrastive, and a unified contrastive–reconstruction objective—are investigated to evaluate the effectiveness of different representation learning approaches. The learned latent representations are subsequently analysed using Isolation Forest and Mahalanobis-distance anomaly scoring methods. To provide a realistic assessment of generalisation, a strict grouped cross-validation protocol is employed, where data are partitioned at the sample level to prevent information leakage between training and testing sets. Furthermore, prevalence-aware experiments are conducted under 5% and 10% fault prevalence scenarios to assess deployment robustness. Experimental results on the Paderborn bearing dataset demonstrate that the proposed CNN + Transformer model trained with combined contrastive and reconstruction objectives and evaluated using Isolation Forest achieves the best overall performance, obtaining a ROC-AUC of 0.878±0.015, a PR-AUC of 0.958±0.005, and an F1-score of 0.590±0.040. The results consistently outperform classical feature-based approaches, One-Class SVM, and autoencoder baselines. Ablation analysis further shows that combining contrastive and reconstruction objectives produces more informative representations than either objective alone. The findings demonstrate that the proposed healthy-only self-supervised framework provides an effective and label-efficient approach for rolling bearing anomaly detection and shows promise for predictive maintenance applications where labelled fault data are limited or unavailable.

Zitieren

APA

Zaidi, S. H. H., Shenfield, A., Zhang, H., & Ikpehai, A. (2026). Self-Supervised CNN–Transformer Anomaly Detection for Bearing Health Monitoring. Processes, 14(15), 2452. https://doi.org/10.3390/pr14152452

Vancouver

Zaidi SHH, Shenfield A, Zhang H, Ikpehai A. Self-Supervised CNN–Transformer Anomaly Detection for Bearing Health Monitoring. Processes. 2026;14(15):2452. doi:10.3390/pr14152452

BibTeX
@article{Zaidi2026,
  author = {Zaidi, Syed Haseeb Haider and Shenfield, Alex and Zhang, Hongwei and Ikpehai, Augustine},
  title = {Self-Supervised CNN–Transformer Anomaly Detection for Bearing Health Monitoring},
  journal = {Processes},
  year = {2026},
  volume = {14},
  number = {15},
  pages = {2452},
  doi = {10.3390/pr14152452}
}
Kostenlos starten →