Contro of nonlinear dynamical systems using neural networks .2. Observability, identification, and control

被引:300
作者
Levin, AU [1 ]
Narendra, KS [1 ]
机构
[1] YALE UNIV,CTR SYST SCI,DEPT ELECT ENGN,NEW HAVEN,CT 06520
来源
IEEE TRANSACTIONS ON NEURAL NETWORKS | 1996年 / 7卷 / 01期
基金
美国国家科学基金会;
关键词
D O I
10.1109/72.478390
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper considers the problems of regulation and tracking of a dynamical system when the state variables of the dynamical system are not accessible, The existence of the nonlinear maps describing the identifier and controller are first established and the implications for neural network realizations are described, Simulation results are included to complement the theoretical discussions.
引用
收藏
页码:30 / 42
页数:13
相关论文
共 20 条
[1]  
[Anonymous], 1983, REAL ANAL
[2]   REPRODUCIBILITY OF MULTIVARIABLE SYSTEMS [J].
BROCKETT, RW ;
MESAROVI.MD .
JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 1965, 11 (1-3) :548-&
[3]  
Cybenko G., 1989, Mathematics of Control, Signals, and Systems, V2, P303, DOI 10.1007/BF02551274
[4]   MULTILAYER FEEDFORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS [J].
HORNIK, K ;
STINCHCOMBE, M ;
WHITE, H .
NEURAL NETWORKS, 1989, 2 (05) :359-366
[5]  
JORDAN MI, 1990, 6TH P YAL WKSHP AD L, P145
[6]   RIGHT INVERSE OF A DISCRETE-TIME NONLINEAR-SYSTEM [J].
KOTTA, U .
INTERNATIONAL JOURNAL OF CONTROL, 1990, 51 (01) :1-9
[7]   INPUT OUTPUT PARAMETRIC MODELS FOR NON-LINEAR SYSTEMS .1. DETERMINISTIC NON-LINEAR SYSTEMS [J].
LEONTARITIS, IJ ;
BILLINGS, SA .
INTERNATIONAL JOURNAL OF CONTROL, 1985, 41 (02) :303-328
[8]   RECURSIVE-IDENTIFICATION USING FEEDFORWARD NEURAL NETWORKS [J].
LEVIN, AU ;
NARENDRA, KS .
INTERNATIONAL JOURNAL OF CONTROL, 1995, 61 (03) :533-547
[9]  
LEVIN AU, 1992, THESIS YALE U NEW HA
[10]  
LEVIN AU, 1993, IEEE T NEURAL NETWOR, V4