Few-Shot Cross-Domain Fault Diagnosis of Transportation Motor Bearings Using MAML-GA
IEEE Transactions on Transportation Electrification · 2026-02 · 12 (1) · 1165-1174
DOI: 10.1109/tte.2025.3625779 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Transportation Electrification, 2026-02. Verfasst von Huimin Zhao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 32 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, State Key Laboratory of Rail Transit Vehicle System, Southwest Jiaotong University.
Abstract (Originalsprache)
The dynamic working conditions and scarcity of fault samples in train motors pose significant challenges to the generalization capability of diagnostic models. To address this issue, this article proposes a cross-domain fault diagnosis method with strong generalization capability under few-shot conditions, termed MAML-GA. In the meta-task construction phase, a dynamic meta-task augmentation (TaskAug) mechanism is introduced within the meta-learning framework to alleviate the problem of limited data by expanding the sample space and generating virtual meta-tasks. During the training phase, a parameter update operator (PUO) is designed to regulate the inner-loop gradient descent process, thereby optimizing the training strategy and preventing the model from overfitting to noisy or irrelevant features. These two mechanisms significantly enhance the cross-domain generalization ability of the diagnostic model and reduce the risk of overfitting under few-shot scenarios. Furthermore, a lightweight key feature extraction network is developed as the backbone of the proposed method. This network integrates a multidimensional spatial-channel attention module, which improves the extraction of discriminative fault features under both limited data and dynamic working conditions. Experimental validations conducted on both a metro transmission system dataset and a laboratory dataset demonstrate that the proposed method achieves diagnostic accuracies of 99.46% and 97.42%, respectively. Compared with mainstream methods such as ProtoNet and RelationNet, the proposed method shows improvements of 2%–6% and 6%–15%, respectively, thereby confirming its effectiveness in handling variable rail transit conditions and data scarcity.
Förderung
- National Natural Science Foundation of China
- National Key Research and Development Program of China
- State Key Laboratory of Rail Transit Vehicle System, Southwest Jiaotong University
Zitieren
APA
Zhao, H., Liu, C., Dang, X., Xu, J., & Deng, W. (2026). Few-Shot Cross-Domain Fault Diagnosis of Transportation Motor Bearings Using MAML-GA. IEEE Transactions on Transportation Electrification, 12(1), 1165-1174. https://doi.org/10.1109/tte.2025.3625779
Vancouver
Zhao H, Liu C, Dang X, Xu J, Deng W. Few-Shot Cross-Domain Fault Diagnosis of Transportation Motor Bearings Using MAML-GA. IEEE Transactions on Transportation Electrification. 2026;12(1):1165-1174. doi:10.1109/tte.2025.3625779
BibTeX
@article{Zhao2026,
author = {Zhao, Huimin and Liu, Chao and Dang, Xiangjun and Xu, Junjie and Deng, Wu},
title = {Few-Shot Cross-Domain Fault Diagnosis of Transportation Motor Bearings Using MAML-GA},
journal = {IEEE Transactions on Transportation Electrification},
year = {2026},
volume = {12},
number = {1},
pages = {1165--1174},
doi = {10.1109/tte.2025.3625779}
}
EUVIMED