Adaptive output feedback control for general nonlinear systems using multilayer neural networks

Abstract

In this paper, the adaptive output feedback control problem is investigated using multilayer neural networks (MNNs) for a class of general nonlinear systems. The adaptive output feedback controller is developed based on a high-gain observer which is used to estimate the time derivatives of the system output. The Lyapunov stability of the resulting closed-loop system is guaranteed and the tracking error converges to a small neighborhood of the origin. The effectiveness of the proposed controller is illustrated through an example of composition control for a continuously stirred tank reactor (CSTR) system. © 1998 AACC.