Direct Adaptive Neural Control Scheme for Discrete Time Affine Nonlinear Systems

A feedback linearization based direct adaptive neural control scheme is proposed for a class of affine nonlinear discrete time systems. Two radial basis function networks are used to approximate the unknown system dynamics. The weight update laws for the networks are derived to make the closed loop error dynamics Lyapunov stable. The proposed control scheme removes the need for any projection algorithm or additional control action presented in the literature. Simulation results are presented to demonstrate the theoretical formulations.