A Machine-Learning-Based Interturn Short-Circuit Diagnosis for Multi-Three-Phase Brushless Motors

Abstract

Over the past few years, Artificial Intelligence (AI) techniques have become one of the most exciting technologies of our age. This fascinating field paves the way for new possibilities and extends to almost all areas of industry and research. This paper illustrates a Short-Circuit (SC) diagnosis strategy for a multi-three-phase brushless AC motor drive based on Machine Learning (ML). A thorough model of the electrical machine is obtained through specific finite-element simulations and used to replicate various fault scenarios. This model quickly yields a large amount of data, which is then employed for training the ML algorithms. Once trained, the ML models are tested, with experimental data directly obtained from a prototype of multiphase drive, to verify the effectiveness of the diagnostic algorithms. The ML algorithms allow monitoring the health condition of the machine, distinguishing and localizing two types of faults, i.e., inter-turn SCs and Extra Turns (ETs), placed in different coils of the machine.