Direct Torque Controlled Drive for Permanent Magnet Synchronous Motor Based on Neural Networks and Multi Fuzzy Controllers

摘要

For permanent magnet synchronous motor (PMSM) direct torque controlled (DTC) drive, stator resistance variation and conventional hystersis controller will bring high flux linkage and torque ripples inevitably. In order to solve this problem, the implementation of direct torque controlled drive for permanent magnet synchronous based on neural networks and multi fuzzy controllers is presented, which replaces the conventional hystersis controller with fuzzy controller and estimates the stator resistance online using the learning capability of neural networks. To tune the weights and biases of the neural networks online, another fuzzy controller is adopted. Results of simulation are provided to demonstrate that the proposed drive has low flux linkage and torque ripples, and has the quick response performance even under the occurrence of parameter variations and external disturbance.