A stable neural network-based controller for class of nonlinear systems

A novel method to solve the stabilization problem for a class of nonlinear affine single-input systems using neural networks is proposed in this paper. The controller is based on feedback linearization where the control signal is directly estimated by a nonlinear in parameter neural network (NLPNN). A modified Back Propagation (BP) algorithm with e-modification is used to update the weights of the network. The stability of overall closed-loop system is shown using Lyapunov method. To evaluate the performance of the proposed controller, a set of simulations is performed on a Rossler chaotic system.