Fault Diagnosis of Inter-Turn Fault in Permanent Magnet-Synchronous Motors Based on Cycle-Generative Adversarial Networks and Deep Autoencoder

Featured Application The main research focus of this paper is to explore the use of the cycle-generative adversarial network (GAN) method to address the inter-turn fault issue in permanent magnet-synchronous motors (PMSMs). Specifically, this study aims to overcome the challenges of scarce and imbalanced fault samples by expanding the sample set. By applying the Cycle GAN method, it is possible to generate more authentic and diversified fault samples, thereby improving the accuracy of fault diagnosis. Moreover, this method exhibits scalability and can be applied to other fault diagnosis problems that share similar difficulties.Abstract This paper addresses the issue of the difficulty in obtaining inter-turn fault (ITF) samples in electric motors, specifically in permanent magnet-synchronous motors (PMSMs), where the number of ITF samples in the stator windings is severely lacking compared to healthy samples. To effectively identify these faults, an improved fault diagnosis method based on the combination of a cycle-generative adversarial network (GAN) and a deep autoencoder (DAE) is proposed. In this method, the Cycle GAN is used to expand the collection of fault samples for PMSMs, while the DAE enhances the capability to extract and analyze these fault samples, thus improving the accuracy of fault diagnosis. The experimental results demonstrate that Cycle GAN exhibits an excellent capability to generate ITF fault samples. The proposed method achieves a diagnostic accuracy rate of up to 98.73% for ITF problems.