Control Of Nonlinear Dynamical Systems Using Neural Networks Controllability And Stabilization英文电子书.pdf

192 IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 4, NO. 2, MARCH 1993 Control of Nonlinear Dynamical Systems Using Neural Networks: Controllability and Stabilization Asriel U. Levin and Kumpati S. Narendra, Fellow, IEEE Abstract- The main objective of this paper is to indicate tation of the system is not completely known. In such cases, how practically viable controllers can be designed using neural stringent assumptions have to be made if neural networks are networks, based on results in nonlinear control theory. The paper to be used for their identification and control. Further, while considers the problem of stabilization of a dynamical system around an equilibrium point, when the state of the system is several theoretically elegant results have been reported in the accessible. Simulation results are included to complement the control literature, many of them are not directly applicable to theoretical discussions. the practical identification and control of nonlinear systems. Hence our objective in this paper is threefold: The first is to I. INTRODUCTION provide the reader with some background concerning concepts in control theory on which many of the re