PID controller design using dynamical neural networks

In this paper, a new PID control scheme using neural networks is presented. The scheme is to parameterize a Ziegler-Nichols-like formula with a single parameter and use the dynamical neural networks to tune the parameter. A Lyapunov type stability criterion is derived to ensure the convergence of the neural procedure and guarantee the stability of the closed-loop system. The simulation examples with small and large time delay are given to illustrate the performance of the proposed method. Simulation results demonstrate that better control performance can be achieved when compared with that of the Ziegler-Nichols PID controllers and that of the fuzzy selftuning of PID control scheme.