Interior Permanent Magnet Synchronous Motor Drive System with Machine Learning-Based Maximum Torque per Ampere and Flux-Weakening Control

An interior permanent magnet synchronous motor (IPMSM) drive system with machine learning-based maximum torque per ampere (MTPA) as well flux-weakening (FW) control was developed and is presented in this study. Since the performance of IPMSM varies significantly due to temperature variation magnetic saturation, a MTPA using Petri probabilistic fuzzy neural network an asymmetric membership function (PPFNN-AMF) developed. First, d-axis current command, which can achieve IPMSM, derived. Then, difference value dq-axis inductance obtained by PPFNN-AMF substituted into command alleviate saturation effect constant region. Moreover, voltage loop, limit inverter output at high-speed, designed for FW power In addition, adaptive complementary sliding mode (ACSM) speed controller improve transient response control. Finally, some experimental results are given demonstrate validity proposed high-performance strategies.