Identification and control of continuous-time nonlinear systems via dynamic neural networks.pdfVIP

478 IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, VOL. 50, NO. 3, JUNE 2003 Identification and Control of Continuous-Time Nonlinear Systems via Dynamic Neural Networks X. M. Ren, A. B. Rad, P. T. Chan, and Wai Lun Lo Abstract—In this paper, we present an algorithm for the online Moreover, for unknown nonlinear systems, there is no identification and adaptive control of a class of continuous-time effective method to design adaptive controllers to ensure nonlinear systems via dynamic neural networks. The plant con- good tracking performance. Recently, neural networks have sidered is an unknown multi-input/multi-output continuous-time higher order nonlinear system. The control scheme includes two been employed in the identification and control of unknown parts: a dynamic neural network is employed to perform system nonlinear systems owing to their massive parallelism, fast identification and a controller based on the proposed dynamic adaptation and learning capability [6]–[13]. Until now, the most neural network is developed to track a reference trajectory. widely used neural networks have been feedforward neural Stability analysis for the identification and the tracking errors networks and dynamic neural networks. Many researchers use is performed by means of Lyapunov stability criterion. Finally, we illustrate the effectiveness of these methods by computer the feedforward neural networks as the representation of a simulations of the Duffing chaotic system and one-link rigid nonlinear operator in the right-hand side of the dynamic model robot manipulator. The simulation r