Deep learning fault diagnosis method based on global optimization GAN for unbalanced data

• Published in: Knowledge-based systems 2020-01, Vol.187, p.104837, Article 104837
• Main Authors: Zhou, Funa, Yang, Shuai, Fujita, Hamido, Chen, Danmin, Wen, Chenglin
• Format: Article
• Language: English
• Subjects: Algorithms; Coders; Deep learning; Fault diagnosis; Feature extraction; GAN; Generative adversarial networks; Global optimization; Machine learning; Roller bearings; Statistical methods; Unbalance data
• ISSN: 0950-7051; 1872-7409
• DOI: 10.1016/j.knosys.2019.07.008

Deep learning can be applied to the field of fault diagnosis for its powerful feature representation capabilities. When a certain class fault samples available are very limited, it is inevitably to be unbalanced. The fault feature extracted from unbalanced data via deep learning is inaccurate, which can lead to high misclassification rate. To solve this problem, new generator and discriminator of Generative Adversarial Network (GAN) are designed in this paper to generate more discriminant fault samples using a scheme of global optimization. The generator is designed to generate those fault feature extracted from a few fault samples via Auto Encoder (AE) instead of fault data sample. The training of the generator is guided by fault feature and fault diagnosis error instead of the statistical coincidence of traditional GAN. The discriminator is designed to filter the unqualified generated samples in the sense that qualified samples are helpful for more accurate fault diagnosis. The experimental results of rolling bearings verify the effectiveness of the proposed algorithm. •Design a new generator to generate fault feature rather than the fault data itself.•Design a two-hierarchical discriminator which can filter unqualified fault samples.•Generator, discriminator and DNN fault diagnosis model are alternatively optimized.