Reinforcement Learning and Optimal Control of PMSM Speed Servo System

This article proposes a novel model-free optimal speed tracking control scheme for permanent magnet synchronous motors (PMSMs) through reinforcement learning (RL). To achieve the speed servo control, we formulate the linear quadratic regulator associated with the reduced-order model in the outer loop controller design. Such a model is obtained in terms of singular perturbation theory, which enables the separation of slow and fast time-scale dynamics. Moreover, we develop an off-policy RL algorithm to iteratively approximate the ideal value of solution to the linear quadratic regulator without requiring any knowledge of model parameters of the PMSM and the measurement of the load torque. Both simulation and experimental tests are carried out to justify that the proposed control scheme realizes precision speed tracking performance and shape transient response in the presence of unknown model parameters.