Solving discrete-time nonlinear servomechanism problem with feedforward neural networks

The solution of discrete-time nonlinear servomechanism problem relies on the solvability of a set of nonlinear functional equations known as the discrete regulator equations. Due to the nonlinear nature, it is difficult to obtain the exact solution of the discrete regulator equations. This paper presents a feedforward neural network based approach to solving the discrete regulator equations. This approach leads to an effective way to practically solve the discrete nonlinear servomechanism problem. The approach has been illustrated using the well known inverted pendulum on a cart system. The simulation shows that the control law designed by the proposed approach performs much better than the linear control law does