Analysis of Brushless DC Motor Control Strategy Based on Q-Learning Algorithm

The traditional PID makes it challenging to achieve high-precision control of motor speed, and the fuzzy PID regulator is limited by expert experience, parameter adjustment difficulties and other issues. In order to solve the problems of low control precision, high noise and weak adaptability of traditional motors in the drive system of new energy vehicles, this paper proposes to establish a Q-learning PID brushless DC motor vector control system. The Q-learning algorithm is different from other control methods. It does not need the specific knowledge of the system, but learns and adjusts the control strategy through the system state. The control model is built by MATLAB/SIMULINK simulation platform, and the speed response and adjustment speed of fuzzy PID control are compared and analyzed. The experimental results show that the adaptive control effect of low overshoot and fast adjustment of the Q-learning PID controller has good anti-interference ability and strong robustness.