Vector Control of PMSM Using TD3 Reinforcement Learning Algorithm

Permanent magnet synchronous motor (PMSM) drive systems are commonly utilized in mobile electric drive systems due to their high efficiency, high power density, and low maintenance cost. To reduce the tracking error of the permanent magnet synchronous motor, a reinforcement learning (RL) control algorithm based on double delay deterministic gradient algorithm (TD3) is proposed. The physical modeling of PMSM is carried out in Simulink, and the current controller controlling id-axis and iq-axis in the current loop is replaced by a reinforcement learning controller. The optimal control network parameters were obtained through simulation learning, and DDPG, BP, and LQG algorithms were simulated and compared under the same conditions. In the experiment part, the trained RL network was compiled into C code according to the workflow with the help of rapid prototyping control, and then downloaded to the controller for testing. The measured output signal is consistent with the simulation results, which shows that the algorithm can significantly reduce the tracking error under the variable speed of the motor, making the system have a fast response.