A Wasserstein gradient-penalty generative adversarial network with deep auto-encoder for bearing intelligent fault diagnosis. (9th January 2020)

• Record Type: Journal Article
• Authors: Xiong, Xiong; Hongkai, Jiang; Li, Xingqiu; Niu, Maogui
• Is Part Of: Measurement science & technology. Volume 31:Number 4(2020)
• Publication Date: 2020-01-09
• Subjects: rolling bearing -- intelligent fault diagnosis -- Wasserstein gradient-penalty generative adversarial network -- deep auto-encoder -- unsupervised learning; Physical measurements -- Periodicals; Scientific apparatus and instruments -- Periodicals; Equipment and Supplies -- Periodicals; Science -- instrumentation -- Periodicals; Technology -- instrumentation -- Periodicals; Mesures physiques -- Périodiques; Physical measurements; Scientific apparatus and instruments; Periodicals; 502.87
• DOI: 10.1088/1361-6501/ab47df
• Languages: English
• ISSNs: 0957-0233

Abstract

Abstract: It is a great challenge to manipulate unbalanced fault data in the field of rolling bearings intelligent fault diagnosis. In this paper, a novel intelligent fault diagnosis method called the Wasserstein gradient-penalty generative adversarial network with deep auto-encoder is proposed for intelligent fault diagnosis of rolling bearings. Firstly, the gradient penalty term is added to the Wasserstein generative adversarial network to enhance the stability and convergence of the network. Secondly, a deep auto-encoder network comprised of multiple auto-encoders is regarded as the discriminator. Finally, the sparse auto-encoder is placed at the end of the proposed method as the classifier to classify synthetic bearing faults. The results show that the proposed method has a better performance than traditional methods and the Wasserstein generative adversarial network.