A Novel Adaptive Self-turned PID controller based on Recurrent-Wavelet-Neural-Network for PMSM Speed Servo Drive System

The conventional PID controller can not have a satisfactory performance when it has been applied in the permanent-magnet synchronous motor (PMSM) speed regulation system which has the characteristics of nonlinearity, strong coupling and multi-variable. With the purpose to solve this problem, a new hybrid control algorithm utilizing recurrent wavelet neural network (RWNN) is proposed, which can adjust parameters on line to be adaptive to the parameter variety and load disturbance. The effectiveness of the proposed controller is demonstrated by numerical simulations and experiments. It is proved that this scheme not only has good dynamics and steady-state performance but also enhances the robustness of system.