Self-tuning PID Control of Induction Motor Speed Control System Based on Diagonal Recurrent Neural Network

Abstract

The performance optimization of induction motor speed control system is studied and self-tuning PID controller based on diagonal recurrent neural network (DRNN) is presented in this paper. Neural network control does not require the precise mathematical model of the system, and it only needs to train neural network online or offline, then use the training results to design the control system. It is applicable of the nonlinear, strong coupling and multi variable system, which is composed of inverter and induction motor. The speed regulation control performances are tested on the experimental platform constructed by SIMATIC S7-300 power PLC. The results of experiment indicate that, compared with conventional PID controller, induction motor speed control system, which is controlled by self-tuning PID controller based on DRNN, has better static-dynamic and following performances, stronger anti-interference ability and robustness.