Fuzzy RBF neural network in the application of magnetic levitation system

Abstract

To solve the problems that magnetic levitation system has the characteristics of open-loop instability and nonlinearity and the traditional PID controller is difficult to achieve good control effect because of the fixed parameters, a kind of intelligent PID control system based on fuzzy RBF neural network is proposed in this paper. This method combines the reasoning ability of fuzzy control with study ability of neural network. Fuzzy control and RBF neural network are applied in order to adjust the parameters of PID kp, ki and kd online which is to satisfy the static and dynamic performance requirements in magnetic levitation system. By comparing with the conventional PID control, the results showed that, the improved control has better adaptability and robustness which can control magnetic levitation system more effectively.