Generative Dual-Modal Data Augmentation for Motor Fault Diagnosis Under Sample Imbalance
Machines · 01.06.2026 · 14 (6) · 633
DOI: 10.3390/machines14060633 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machines, online erschienen am 01.06.2026. Verfasst von Ganxin Jie und 4 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: State Key Laboratory of Environmental Adaptability for Industrial Products, China National Electric Apparatus Research Institute Co., Ltd.
Abstract (Originalsprache)
This study investigates class imbalance in motor fault diagnosis. Fault samples, especially those at different severity levels, are often much fewer than healthy samples. To address this issue, a self-attention guided Wasserstein conditional GAN with gradient normalization (SWGAN) is proposed. The method is based on synchronized three-phase current and vibration measurements. It separately generates label-conditioned current spectra and vibration spectra to supplement minority fault classes. Self-attention is used to capture long-range spectral dependencies. Gradient normalization is introduced to improve adversarial training stability. The generated current and vibration spectra are then fused at the feature level and fed into a stacked autoencoder (SAE)-based multi-modal classifier. Experiments were conducted on a PMSM stator fault dataset and a variable-speed three-phase asynchronous motor dataset. On the PMSM dataset, SWGAN achieved highest accuracies of 98.90% and 97.81% under two fault-category imbalance settings. On the variable-speed motor dataset, the proposed method achieved accuracies of 98.10% and 97.65%, respectively. These results show that SWGAN can provide effective supplementary samples for minority fault classes. They also indicate that the proposed method improves diagnostic performance under both fixed-speed and variable-speed conditions.
Förderung
- State Key Laboratory of Environmental Adaptability for Industrial Products, China National Electric Apparatus Research Institute Co., Ltd
Zitieren
APA
Jie, G., Zhang, C., Ma, J., Yang, Y., & Chen, C. (2026). Generative Dual-Modal Data Augmentation for Motor Fault Diagnosis Under Sample Imbalance. Machines, 14(6), 633. https://doi.org/10.3390/machines14060633
Vancouver
Jie G, Zhang C, Ma J, Yang Y, Chen C. Generative Dual-Modal Data Augmentation for Motor Fault Diagnosis Under Sample Imbalance. Machines. 2026;14(6):633. doi:10.3390/machines14060633
BibTeX
@article{Jie2026,
author = {Jie, Ganxin and Zhang, Cailiang and Ma, Junqing and Yang, Yang and Chen, Chuan},
title = {Generative Dual-Modal Data Augmentation for Motor Fault Diagnosis Under Sample Imbalance},
journal = {Machines},
year = {2026},
volume = {14},
number = {6},
pages = {633},
doi = {10.3390/machines14060633}
}
EUVIMED