PID Control Parameter Tuning Method of Permanent Magnet Synchronous Motor Based on Improved AHP-BP Neural Network Algorithm

For the proportional-integral and derivative (PID) control parameter tuning problem of Permanent Magnet Synchronous Motors (PMSM), a parameter tuning method is proposed, which combines the Analytic Hierarchy Process (AHP) and Back-Propagation (BP) neural network. First, this paper establishes a PID control model of permanent magnet synchronous motors, including input and output parameters such as current, voltage, speed, and torque. The AHP algorithm is used to initially select the proportional, integral, and derivative coefficients of the PID controller. Second, the initially selected parameters are inputted into the BP neural network. The network can train the parameters of the PID controller to approximate the stable control performance. Finally, through Simulink simulation and algorithm comparison, the effectiveness and superiority of the proposed method are verified. The results show that the proposed method can effectively select PID control parameters, thereby the PID control performance of PMSM is enhanced. The needs of modern industrial high-performance servo control are satisfied by the proposed method.