EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Episodic Training and Feature Orthogonality-Driven Domain Generalization for Rotating Machinery Fault Diagnosis Under Unseen Working Conditions

Yixiao Liao, Songbin Zhou, Yisen Liu, Kunkun Pang, Jing Li, Chang Li, Lulu Zhao

Machines · 28.06.2025 · 13 (7) · 563

DOI: 10.3390/machines13070563 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 28.06.2025. Verfasst von Yixiao Liao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: GDAS’ Project of Science and Technology Development.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, domain generalization-based fault diagnosis (DGFD) methods have shown significant potential in rotating machinery fault diagnosis in unseen target domains. However, these methods focus on learning domain-invariant representations via feature distribution adaptation. The generalization of classifiers and the orthogonality between fault-related and domain-related features have not been thoroughly explored, which hinders further improvements in DGFD performance. To address these limitations, an episodic training and feature orthogonality-driven domain generalization (EODG) method is proposed. In this method, episodic training is introduced to jointly improve the generalization capabilities of both the feature extractor and fault classifier, while a novel feature transfer loss is proposed for learning domain-invariant representations. Furthermore, the orthogonality between fault-related and domain-related features is enhanced by minimizing their cosine similarity, thereby improving the generalization capability of the DGFD model. The experimental results validated the effectiveness and superiority of the proposed method on domain generalization-based fault diagnosis tasks.

Förderung

  • GDAS’ Project of Science and Technology Development

Zitieren

APA

Liao, Y., Zhou, S., Liu, Y., Pang, K., Li, J., Li, C., & Zhao, L. (2025). Episodic Training and Feature Orthogonality-Driven Domain Generalization for Rotating Machinery Fault Diagnosis Under Unseen Working Conditions. Machines, 13(7), 563. https://doi.org/10.3390/machines13070563

Vancouver

Liao Y, Zhou S, Liu Y, Pang K, Li J, Li C, et al. Episodic Training and Feature Orthogonality-Driven Domain Generalization for Rotating Machinery Fault Diagnosis Under Unseen Working Conditions. Machines. 2025;13(7):563. doi:10.3390/machines13070563

BibTeX
@article{Liao2025,
  author = {Liao, Yixiao and Zhou, Songbin and Liu, Yisen and Pang, Kunkun and Li, Jing and Li, Chang and Zhao, Lulu},
  title = {Episodic Training and Feature Orthogonality-Driven Domain Generalization for Rotating Machinery Fault Diagnosis Under Unseen Working Conditions},
  journal = {Machines},
  year = {2025},
  volume = {13},
  number = {7},
  pages = {563},
  doi = {10.3390/machines13070563}
}
Kostenlos starten →