Advanced Detection of Inter-Turn Short-Circuit Faults in PMSMs Using FFT and AI Methods

This study introduces a novel method for detecting inter-turn short-circuit (ISF) faults in Permanent Magnet Synchronous Machines (PMSMs). The approach leverages zerosequence voltage signals, identified as highly sensitive indicators of ISF faults, and applies Fast Fourier Transform (FFT) analysis to extract critical features. To automate the fault detection process, Artificial Intelligence (AI) algorithms including Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and decision trees-are employed. Among these, Support Vector Machines (SVM) and K-Nearest Neighbors (KNN) demonstrated exceptional performance, achieving perfect precision and recall rates. The integration of signal processing and AI techniques significantly enhances the accuracy and reliability of ISF fault detection. This research represents a meaningful advancement in the development of intelligent monitoring systems for electric machines, supporting early detection and predictive maintenance strategies.