Online Automatic Parameter Optimization of Marine Permanent Magnet Synchronous Motor Speed Controller Based on Reinforcement Learning

For the ship electric propulsion system, it is very important to maintain the stability of the speed. In this paper, the vector control system of permanent magnet synchronous motor (PMSM) is introduced. At the same time, aiming at the shortcomings of traditional proportional integral (PI) control, such as sensitivity to motor parameters and insufficient control performance when the load torque fluctuation is relatively large, a speed control strategy based on Q-learning reinforcement learning theory is proposed, which replaces the manual debugging process with intelligent algorithm online debugging.