Robust Adaptive Neural Network Control for Nonlinear MIMO Time-delay Systems

Authors:	Tee Keng-Peng, National University of Singapore, Singapore Ge Shuzhi Sam, National University of Singapore, Singapore
Topic:	2.3 Non-Linear Control Systems
Session:	Adaptive Nonlinear Control
Keywords:	Adaptive control, neural networks, time-delay systems, MIMO nonlinear systems

Abstract

This paper proposes an adaptive neural network (NN) controller for a class of multi-input multi-output (MIMO) nonlinear systems with unknown delays, but with known bounds on the delay functionals. The use of a separation technique removes the need to make any assumptions with regard to the structure of the delay functionals, thus making our results applicable to a larger class of systems. Given that the bounds on the delay functionals are known, we can construct Lyapunov-Krasovskii functionals and adaptive NNs to obtain a controller that guarantees all signals to be semi-globally uniformly ultimately bounded (SGUUB) while the outputs track specified desired trajectories.