Resumen
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.