Adaptive control of nonlinear non-minimum phase systems using neural networks

A novel technique, using neural networks, is proposed for the adaptive control of a class of nonlinear nonminimum phase systems. Using Taylor expansion, the nonlinear system can be regarded as a linear nonminimum phase system with a measurable disturbance. Pole-placement is used to stabilize the system, and a neural network is used to approximate the nonlinear term. Feedforward compensation is used to eliminate steady tracking errors which are caused by the nonlinear term.