Application of Fuzzy Neural PID Controller Based on PSO for High Precision Servo System

Friction is a key factor that influences the low velocity performance of high precision servo systems. It usually causes the steady-state error of servo systems and results in the creeping phenomenon in low velocity motions. Friction is complicated nonlinear process with time-varying uncertainties. The traditional PID controller of servo systems with fricition was not satisfactory in control precision and response time. In this paper, the fuzzy neural PID controller based on fuzzy neural network(FNN), which combines the advantages of robustness and nonlinear characteristic of fuzzy control and adaptive self-learning capability of neural network, was used to eliminate nonlinear disturbance caused by friction. To solve the problems of stagnation, poor convergence and local optima in traditional NN Learning Algorithms, the modified PSO algorithm is adopted to train FNN on line. The experiment result demonstrates that FNN PID controller can remove friction disturbance efficiently and reduce steady-state error to only one fifth of the one using the PID algorithm.