Application of self tuning PID controller based on RBF network

A self tuning PID control strategy based on RBF network is proposed, to the nonlinear and time-varition industrial process with uncertainties. RBF network is built to construct processing model through on-line identification and the Jacobian information of the system controller is obtained. By using a new learning algorithm which is generated by RLS algorithm and gradient method and combining this control method together with PID controller. It can be used to solve the problem of bad robustness and big overshoot and low tracking speed. The simulation result indicate that the system robustness and tracking performance are superior to those of the traditional PID control method and prove the improved algorithm is valid and feasible.