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.