Adaptive Control of Nonlinear Continuous-Time Systems Using Neural Networks - General Relative Degree and MIMO Cases

Abstract

Multilayer neural networks are used in a nonlinear adaptive control problem. The plant is an unknown feedback linearizable continuous-time system with relative degree ≥ 1. The single-input/single-output system is studied first and then the methodology is extended to control square multi-input/multi-output systems. The control objective is for the plant to track a reference trajectory, nd the control law is defined in terms of the outputs of the neural networks. he parameters of the networks are updated on-line according to an augmented tracking error and the network derivatives. local convergence theorem is given on he convergence of the tracking error and its derivatives, nd the norm of the parameter error vectors. his control algorithm is applied to control a two-input/two-output relative-degree-two system.