EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Bearing Fault Diagnosis Method Based on Dual-Stream Hybrid-Domain Adaptation

Xinze Jiao, Jianjie Zhang, Jianhui Cao

Sensors · 12.06.2025 · 25 (12) · 3686

DOI: 10.3390/s25123686 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 12.06.2025. Verfasst von Xinze Jiao und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Mechanical Engineering, Xinjiang University, Urumqi 830017, China. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Research and Development Program of Xinjiang Uygur Autonomous Region.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bearing fault diagnosis under varying operating conditions faces challenges of domain shift and labeled data scarcity. This paper proposes a dual-stream hybrid-domain adaptation network (DS-HDA Net) that fuses CNN-extracted time-domain features with MLP-processed frequency-domain features for comprehensive fault representation. The method employs hierarchical domain adaptation: marginal distribution adaptation (MDA) for global alignment and conditional domain adaptation (CDA) for class-conditional alignment. A novel soft pseudo-label generation mechanism combining Gaussian mixture models (GMMs) with the Mahalanobis distance provides reliable supervisory signals for unlabeled target domain data. Extensive experiments on the Paderborn University and Jiangnan University datasets demonstrate that DS-HDA Net achieves average accuracy values of 99.43% and 99.56%, respectively, significantly outperforming state-of-the-art methods. The approach effectively addresses bearing fault diagnosis under complex operating conditions with minimal labeled data requirements.

Schlagwörter

Stichwörter der Autor:innen

bearingsdomain adaptationdual-stream networkfault diagnosispseudo-labelingtransfer learning

Autor:innen und Institutionen

  • College of Mechanical Engineering, Xinjiang University, Urumqi 830017, China.

Förderung

  • Key Research and Development Program of Xinjiang Uygur Autonomous Region

Zitieren

APA

Jiao, X., Zhang, J., & Cao, J. (2025). A Bearing Fault Diagnosis Method Based on Dual-Stream Hybrid-Domain Adaptation. Sensors, 25(12), 3686. https://doi.org/10.3390/s25123686

Vancouver

Jiao X, Zhang J, Cao J. A Bearing Fault Diagnosis Method Based on Dual-Stream Hybrid-Domain Adaptation. Sensors. 2025;25(12):3686. doi:10.3390/s25123686

BibTeX
@article{Jiao2025,
  author = {Jiao, Xinze and Zhang, Jianjie and Cao, Jianhui},
  title = {A Bearing Fault Diagnosis Method Based on Dual-Stream Hybrid-Domain Adaptation},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {12},
  pages = {3686},
  doi = {10.3390/s25123686}
}
Kostenlos starten →