Adversarial domain adaptation network with MixMatch for incipient fault diagnosis of PMSM under multiple working conditions

Abstract

The incipient faults diagnosis under multiple working conditions has been a challenging problem due to the small difference of incipient fault features, and different feature divergences and distributions under different working conditions. In this paper, an Adversarial Domain Adaptation Network with MixMatch (ADANM) is proposed for the incipient faults diagnosis of permanent magnet synchronous motor (PMSM) under multiple working conditions. In ADANM, through selecting multi-scale convolutional kernels, an Adaptive Multi-scale Convolutional Neural Network (AM-CNN) is designed to improve the adaptability of extracted features for the incipient faults of PMSM under different working conditions. Meanwhile, the MixMatch and confidence-thresholding embedded in the adversarial network are employed to reduce the conditional distribution discrepancy by reducing the number of false pseudo-labels. The proposed ADANM is evaluated by diagnosing 4 types of incipient faults in PMSM under multiple working conditions. Extensive experiments are conducted on the hardware-in-the-loop (HIL) real-time platform, and our method outperforms existing methods by an average accuracy increase of approximately 8.12% across three different datasets. This significant improvement validates the effectiveness and superiority of the proposed method.