Journal
IEEE SENSORS JOURNAL
Volume 22, Issue 9, Pages 8749-8759Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSEN.2022.3160762
Keywords
Generators; Feature extraction; Fault diagnosis; Training; Rolling bearings; Generative adversarial networks; Data models; Fault diagnosis; auxiliary classifier generative adversarial network; self-attention; residual network; semi-supervised learning
Funding
- Open Fund of Hubei Key Laboratory of Hydroelectric Machinery Design and Maintenance [2020KJX03]
- National Natural Science Foundation of China (NSFC) [51975324]
Ask authors/readers for more resources
This paper proposes a bearing fault diagnosis method based on feature-enhanced generative adversarial networks with an auxiliary classifier (AC-FEGAN). It can automatically extract representative faulty features and achieve more accurate and effective fault diagnosis through refined feature extraction and improved quality of generated samples.
Most current rolling bearing fault diagnostic approaches presume that sufficient labeled data are available for training. However, labeled fault data collection in realistic engineering is time-consuming and expensive, whereas the majority of data available are unlabeled, restricting diagnostic performance. To alleviate the dependence of feature self-extraction model on rolling bearing fault data and improve the feature capture ability, a bearing fault diagnosis method based on feature-enhanced generative adversarial networks with an auxiliary classifier (AC-FEGAN) is proposed in this paper. Firstly, the non-saturating loss with gradient penalty term is introduced to circumvent the gradient vanishing and improve learning stability. Then, employing identity mapping of residual networks introduced into AC-FEGAN, representative faulty features can be automatically extracted, overcoming the restrictions of shallow convolutional neural networks in feature extraction. Simultaneously, to improve feature learning ability, the self-attention module embedded in the residual network accomplishes refined feature extraction by incorporating appropriate weight matrices into the faulty feature maps. Finally, the auxiliary classifier is employed as a pre-training model for the fault diagnosis model, with generated and unlabeled samples employed to fine-tune the auxiliary classifier to identify faulty bearings. The experimental results show that the proposed method can significantly improve the quality of generated samples while eliminating the reliance of existing diagnosis methods on data volume to achieve more accurate and effective fault diagnosis.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available