混沌系统的神经网络控制

王忠勇　蔡远利　贾冬　刘文江

摘　要　提出一种利用神经网络控制系统混沌运动的新方法，并用该方法实现了Lorenz和Rossler系统混沌运动控制，从而使系统由混沌运动状态转变为规则运动状态。仿真结果表明，该方法控制混沌系统响应速度快，控制精度高。
关键词　混沌控制，神经网络，数值仿真
分类号　TP 273

Neural Network Control of Chaotic Systems

Wang Zhongyong
(Zhengzhou University)
Cai Yuanli, Jia Dong, Liu Wenjiang
(Xi′an Jiaotong University)

Abstract　A new method of chaotic control with multilayer feed-forward neural network is presented. The chaotic behaviors of the Lorenz and Rossler equations are controlled by this method. The chaotic motions of the systems are successfully converted to regular motions. The simulation results have shown that rapid response and higher accuracy of the chaotic system can be obtained based on the proposed control method.
Key words　chaotic control, neural network, numerical simulation

国家自然科学基金项目(19402011)

王忠勇(郑州大学电子工程系　450052)　
蔡远利(西安交通大学自动控制系)
贾冬(西安交通大学自动控制系)
刘文江(西安交通大学自动控制系)

参考文献

［1］Fowler T B. Application of stochastic control techniques to chaotic nonlinear system. IEEE Trans on Autom Contr, 1989, 34(2):201-205
［2］Hartely T T, Mossayebi F. A classical approach to controlling the Lorenz equation. Int J Bifurcation and Chaos, 1992,2(4):881-887
［3］Gallegos J A. Nonlinear regulation of a Lorenz system by feedback linearization techniques. Dynamics and Control, 1994, 4:277-289
［4］Gonzale G A. Controlling chaos of an uncertain Lozi system via adaptive techniques. Int J Bifurcation and Chaos, 1995,5(2):559-562
［5］Chen G, Dong X. On feedback control of chaotic dynamic system. Int J Bifurcation and Chaos, 1992, 2(2):407-411
［6］Chen G, Dong X. On feedback control of chaotic continuous-time systems. IEEE Trans on Circuits and System, 1993, 40(9):591-600
［7］Yeap T H, Ahmed N U. Feedback control of chaotic systems. Dynamics and Control, 1994, 4:97-114
［8］Robert H N. Theory of the back-propagation neural network. In: Proc IJCNN. Washington, 1989, 1: 593-605

　 收稿日期：1998-05-25

修稿日期：1998-08-25