Design of Neural Network PID Controller Based on Brushless DC Motor

For the performance and accuracy requirements of brushless DC motor speed control system, this paper integrates organically neural network and the traditional PID to constitute brushless DC motor speed control system based on BP neural network self-tuning parameters PID control. The traditional PID controller is used in the beginning several seconds, and then another parameter self-tuning PID controller based on BP neural network is converted to after training for seconds. Simulation model was established in Matlab/Simulink. The simulation results indicate that the neutral network PID controller can improve the robustness of the system and has better adaptabilities to the model and environments compared with the traditional PID controller.

I. Introduction

PID control has the advantages of simple structure, high reliability and easy to engineering achieves, so it is still widely used. Traditional speed control system for brushless DC motor is usually used PID control. Despite it is simple, easy to regulate the parameters and has a certain control precision, the PID control algorithm do has limitations. Today controlled objects are increasingly complicated; the traditional PID can no longer meet the requirements of rapid, stability and robustness for speed control system of brushless DC motor. Three PID control parameters of proportion, integral and differential, while coordinating with each other, are nonetheless checking on, which is not a simple linear combination. The desired control effect will be obtained as long as the best relationship is found between the changing non-linear relationships.