IBN-MixStyle Network With Dynamic Weighted Invariant Risk Minimization for Domain-Generalized Bearing Fault Diagnosis
IEEE Transactions on Consumer Electronics · 2025-11 · 71 (4) · 9929-9939
DOI: 10.1109/tce.2025.3607134 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2025-11. Verfasst von Jian Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: National Natural Science Foundation of China, State Key Laboratory of Rail Transit Vehicle System of Southwest Jiaotong University.
Abstract (Originalsprache)
In recent years, substantial progress has been made in cross-working condition fault diagnosis through transfer learning. However, a significant trade-off between diagnostic accuracy and generalization capability remains unresolved, especially in practical industrial scenarios where data from unseen domains is unavailable. To address this challenge, this paper proposes a novel domain generalization (DG) method that effectively integrates both discriminative and generalizable features for rolling bearing fault diagnosis under varying working conditions. Firstly, Fast Fourier Transform (FFT) is employed to extract phase-frequency representations, which are fused with time-domain signals to form a comprehensive input to the diagnostic network. Then a dual-branch architecture based on Instance-Batch Normalization (IBN) and MixStyle is constructed, the IBN captures discriminative features to enhance classification accuracy, and the MixStyle learns generalizable features to improve cross-domain adaptability. Furthermore, a Dynamic Weighting Invariant Risk Minimization (DWA-IRM) strategy is designed to assign higher importance to source domains with poor performance, thereby enforcing robust invariance constraints. The extensive experiments show that the proposed method achieves an average accuracy improvement of approximately 5.3% to 15.47% over state-of-the-art DG approaches, which demonstrate its effectiveness. This work offers a practical and scalable solution for intelligent fault diagnosis in highly variable industrial environments.
Förderung
- National Natural Science Foundation of China
- State Key Laboratory of Rail Transit Vehicle System of Southwest Jiaotong University
Zitieren
APA
Li, J., Deng, W., Ding, J., & Zhao, H. (2025). IBN-MixStyle Network With Dynamic Weighted Invariant Risk Minimization for Domain-Generalized Bearing Fault Diagnosis. IEEE Transactions on Consumer Electronics, 71(4), 9929-9939. https://doi.org/10.1109/tce.2025.3607134
Vancouver
Li J, Deng W, Ding J, Zhao H. IBN-MixStyle Network With Dynamic Weighted Invariant Risk Minimization for Domain-Generalized Bearing Fault Diagnosis. IEEE Transactions on Consumer Electronics. 2025;71(4):9929-9939. doi:10.1109/tce.2025.3607134
BibTeX
@article{Li2025,
author = {Li, Jian and Deng, Wu and Ding, Jianming and Zhao, Huimin},
title = {IBN-MixStyle Network With Dynamic Weighted Invariant Risk Minimization for Domain-Generalized Bearing Fault Diagnosis},
journal = {IEEE Transactions on Consumer Electronics},
year = {2025},
volume = {71},
number = {4},
pages = {9929--9939},
doi = {10.1109/tce.2025.3607134}
}
EUVIMED