A Machine-Learning-Based Fault Diagnosis Method With Adaptive Secondary Sampling for Multiphase Drive Systems

Abstract

Dueto various kinds of stator phase arrangements, existing fault diagnosis (FD) methods cannot be applied to different types of multiphase machines. Spurred by the era of big data and artificial intelligence, an improved machine-learning-based FD method with adaptive secondary sampling filtering is proposed for the multiphase drive systems. Experimental results of the proposed method on both five-phase and six-phase motor drive platforms validate its satisfying generalization capability as well as high accuracy and strong robustness.