Vector Controlled Permanent Magnet Synchronous Motor Drive Based on Neural Network and Multi Fuzzy Controllers

Abstract

A novel implementation of speed controller based on adaptive fuzzy neural network controller (FNNC) for permanent magnet synchronous motor (PMSM) is presented in this paper. FNNC includes one neural network controller (NC) and two fuzzy controllers (FC). It combines the capability of fuzzy reasoning in handling uncertain information and the capability of neural network in learning from processes. The initial weights and biases of the artificial neural network (ANN) are obtained by offline training method. Using the output of one fuzzy controller (FC), online training is carried out to update the weights and biases of the ANN. To improve the dynamic performances of the PMSM drive, another fuzzy controller is adopted. Results of simulation are provided to demonstrate the effectiveness of the proposed FNNC under the occurrence of parameter variations and external disturbance.