EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Intelligent Bearing Fault Transfer Diagnosis Method Based on Improved Domain Adaption

Jinli Che iD, Liqing Fang, Qiao Ma, Guibo Yu, Xiaoting Sun, Xiujie Zhu

Entropy · 20.11.2025 · 27 (11) · 1178

DOI: 10.3390/e27111178 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 20.11.2025. Verfasst von Jinli Che und 5 weiteren Autor:innen. Beteiligte Einrichtung: Shijiazhuang Campus, Army Engineering University of PLA, Shijiazhuang 050003, China. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aiming to tackle the challenge of feature transfer in cross-domain fault diagnosis for rolling bearings, an enhanced domain adaptation-based intelligent fault diagnosis method is proposed. This method systematically combines multi-layer multi-core MMD with adversarial domain classification. Specifically, we will extend alignment to multiple network layers, while previous work typically applied MMD to fewer layers or used single core variants. Initially, a one-dimensional convolutional neural network (1D-CNN) is utilized to extract features from both the source and target domains, thereby enhancing the diagnostic model’s cross-domain adaptability through shared feature learning. Subsequently, to address the distribution differences in feature extraction, the multi-layer multi-kernel maximum mean discrepancy (ML-MK MMD) method is employed to quantify the distribution disparity between the source and target domain features, with the objective of extracting domain-invariant features. Moreover, to further mitigate domain shift, a novel loss function is developed by integrating ML-MK MMD with a domain classifier loss, which optimizes the alignment of feature distributions between the two domains. Ultimately, testing on target domain samples demonstrates that the proposed method effectively extracts domain-invariant features, significantly reduces the distribution gap between the source and target domains, and thereby enhances cross-domain diagnostic performance.

Schlagwörter

Stichwörter der Autor:innen

bearing fault diagnosisdomain adaptationmaximum mean discrepancytransfer learning

Autor:innen und Institutionen

  • Shijiazhuang Campus, Army Engineering University of PLA, Shijiazhuang 050003, China.

ORCID-Profile: Jinli Che

Zitieren

APA

Che, J., Fang, L., Ma, Q., Yu, G., Sun, X., & Zhu, X. (2025). An Intelligent Bearing Fault Transfer Diagnosis Method Based on Improved Domain Adaption. Entropy, 27(11), 1178. https://doi.org/10.3390/e27111178

Vancouver

Che J, Fang L, Ma Q, Yu G, Sun X, Zhu X. An Intelligent Bearing Fault Transfer Diagnosis Method Based on Improved Domain Adaption. Entropy. 2025;27(11):1178. doi:10.3390/e27111178

BibTeX
@article{Che2025,
  author = {Che, Jinli and Fang, Liqing and Ma, Qiao and Yu, Guibo and Sun, Xiaoting and Zhu, Xiujie},
  title = {An Intelligent Bearing Fault Transfer Diagnosis Method Based on Improved Domain Adaption},
  journal = {Entropy},
  year = {2025},
  volume = {27},
  number = {11},
  pages = {1178},
  doi = {10.3390/e27111178}
}
Kostenlos starten →