The Design of Adaptive PI Speed Controller for Permanent Magnet Synchronous Motor Servo System

This chapter proposes a novel adaptive PI speed controller for permanent magnet synchronous motor (PMSM) servo system. A radial basis function neural network (RBFNN) is used for the controller to identify the PMSM servo system and an improved particle swarm optimization (IPSO) algorithm is adopted to optimize the parameters of the RBFNN for fast training. The Jacobian information of PMSM obtained by RBFNN identification is used to adjust the adaptive PI parameters for speed controller online. Simulation result shows good dynamic response, strong robustness and satisfactory control performance in PMSM servo system.