Model-following control of nonlinear servo systems using neural networks

The most useful property of neural networks for system identification and c ontrol is their ability to approximate arbitrary nonlinear mappings. In thi s paper, a new neural network model-following control method is proposed fo r nonlinear servo systems. First, three-layer artificial neural networks ar e trained to describe the forward and inverse dynamic characteristics of on e type of specified nonlinear servo systems by using the backpropagation al gorithm, Then the neural network inverse model is used as a feedforward con troller for model-following control of the nonlinear servo systems. Compute r simulation results obtained from MATLAB verify the applicability of neura l network identification and control for nonlinear servo systems.