Identification and control of nonlinear systems using dynamic neural networks

Abstract

In this paper, the adaptive identification and control for continuous-time nonlinear systems are addressed using dynamic neural networks. The control scheme includes two parts: a dynamic neural network is employed to perform system identification, and then a controller based on a dynamic neural network model is developed to track a reference trajectory. Stability analysis for the identification and tracking errors is performed. Finally, the paper illustrates the effectiveness of these methods by simulations of the Duffing chaotic system and the one-link rigid robot manipulator.