Spectrum-Aware Generative Model for Small-Sample Motor Fault Diagnosis
Actuators · 28.05.2026 · 15 (6) · 299
DOI: 10.3390/act15060299 ↗Kurz gefasst
Fachartikel in der Zeitschrift Actuators, online erschienen am 28.05.2026. Verfasst von Lijing Wang und 4 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, Heilongjiang Provincial University Basic Research Foundation of China.
Abstract (Originalsprache)
This paper proposes a spectrum-aware generative learning framework for intelligent motor fault diagnosis under small-sample conditions. To address the challenges of insufficient labeled fault data and imbalanced distributions in motor systems, a hybrid model integrating a generative adversarial network (GAN) with an attention-enhanced deep neural network is developed. First, vibration signals of the motor are transformed into time–frequency representations to capture discriminative spectral features. Then, the GAN is employed to augment minority classes and improve data diversity, while the SE (squeeze-and-excitation) mechanism enhances feature extraction by emphasizing critical fault-related components. Finally, a deep classifier is trained on the augmented dataset for fault identification. Experimental results on benchmark datasets demonstrate that the proposed method achieves superior diagnostic accuracy and robustness compared with several state-of-the-art approaches, especially under severe data scarcity and imbalance scenarios. The results indicate that the proposed framework effectively improves generalization performance and provides a reliable solution for intelligent motor fault diagnosis in practical industrial applications.
Förderung
- National Key R&D Program of China
- Heilongjiang Provincial University Basic Research Foundation of China
Zitieren
APA
Wang, L., Xie, Y., Yang, Y., Han, C., & Zhao, Q. (2026). Spectrum-Aware Generative Model for Small-Sample Motor Fault Diagnosis. Actuators, 15(6), 299. https://doi.org/10.3390/act15060299
Vancouver
Wang L, Xie Y, Yang Y, Han C, Zhao Q. Spectrum-Aware Generative Model for Small-Sample Motor Fault Diagnosis. Actuators. 2026;15(6):299. doi:10.3390/act15060299
BibTeX
@article{Wang2026,
author = {Wang, Lijing and Xie, Ying and Yang, Yuchen and Han, Chunsong and Zhao, Qi},
title = {Spectrum-Aware Generative Model for Small-Sample Motor Fault Diagnosis},
journal = {Actuators},
year = {2026},
volume = {15},
number = {6},
pages = {299},
doi = {10.3390/act15060299}
}
EUVIMED