Control of a class of nonlinear discrete-time systems using multilayer neural networks

A multilayer neural-network (NN) controller is designed to deliver a desire d tracking performance for the control of a class of unknown nonlinear syst ems in discrete time where the system nonlinearities do not satisfy a match ing condition. Using the Lyapunov approach, the uniform ultimate boundednes s (UUB) of the tracking error and the NN weight estimates are shown by usin g a novel weight updates. Further, a rigorous procedure is provided from th is analysis to select the NN controller parameters. The resulting structure consists of several NN function approximation inner loops and an outer pro portional derivative (PD) tracking loop. Simulation results are then carrie d out to justify the theoretical conclusions. The net result is the design and development of an NN controller for strict-feedback class of nonlinear discrete-time systems.