Improved Performance for the PMSM Control Based on PCH Controller and Computational Intelligence

Based on the classic Field Oriented Control (FOC) structure of the Permanent Magnet Synchronous Motor (PMSM), the paper presents a control structure based on the Port Controlled Hamiltonian (PCH) type controller for the inner current control loop, in which the parameters of the control laws are optimized using computational intelligence algorithms: Particle Swarm Optimization (PSO) algorithm, Simulated Annealing (SA) algorithm, Genetic Algorithm (GA), Gray Wolf Optimization (GWO) algorithm, and Reinforcement Learning - Twin Delayed Deep Deterministic Policy Gradient (RL-TD3) agent algorithm. The paper also presents the control structures and the main stages regarding the synthesis of the control laws, the training, and the performance evaluation. The numerical simulations performed in the Matlab/Simulink programming environment attest to the superior performance of the PMSM control system in the case of optimizing the PCH-type controller parameters using computational intelligence algorithms.