Nonlinear neural controller with neural Smith predictor

摘要

This paper proposes a new nonlinear neural controller with a neural Smith predictor for time-delay compensation of nonlinear processes. Similar to the conventional linear PID controller, the nonlinear neural network based controller uses the system error, the integral of the system error, and the derivative of the system error as its inputs but the mapping from the inputs to the output of the controller is nonlinear. Finally simulation results are presented.