Intelligent Diagnostic Methods Based on Machine Learning for Enhanced Fault Identification in Permanent Magnet Synchronous Motors Used in Electric Vehicles

Main Article Content

Rachid Hamidania, Ali Reziga, DjerdirAbdesslemb

Abstract

The Permanent Magnet Synchronous Motor (PMSM) has emerged as the predominant engine in electric vehicles due to its numerous advantages. However, the occurrence of faults in PMSMs can compromise the vehicle’s power, stability, and safety, posing potential risks to both the vehicle and its occupants. Therefore, the accurate detection and diagnosis of these faults play a crucial role. In recent years, intelligent diagnostic methods leveraging machine learning techniques have garnered significant attention as they offer enhanced precision and differentiation in fault identification, enabling effective monitoring of PMSM health. This work presents a comprehensive review of intelligent diagnostic methods based on machine learning, including wide margin separators, expert systems, neural networks, fuzzy logic, and deep learning approaches. These methods have shown promising results in accurately identifying and classifying faults in PMSMs, contributing to the maintenance and optimal performance of electric vehicles.

Article Details

Section
Articles