Performance analysis of intelligent controllers for permanent magnet synchronous motor drive systems

Abstract

Permanent magnet synchronous motors (PMSMs) are utilized in robotics and automation applications due to their exceptional performance, compact dimensions, and minimal maintenance needs. To ensure dynamic operation and achieve outstanding performance, accurate rotor position detection and real-time control methods are required, independent of the motor's mathematical model. Several intelligent controllers based on soft-computing tools were designed and tested to evaluate the performance of the PMSM drive system. The performance of these intelligent controllers was compared to that of a conventional proportional-integral-derivative (PID) controller, which adjusts its parameters according to the mathematical model of the PMSM. The results indicate that the proposed intelligent controllers outperform the conventional PID controller in controlling the speed of the PMSM. The deep learning-based controller achieved the best results among all evaluated controllers, demonstrating rapid response, minimal overshoot (less than 0.35%), and improved capabilities for handling disturbances or changes in motor parameters.