A PERCEPTION NETWORK FOR FUNCTIONAL IDENTIFICATION AND CONTROL OF NONLINEAR-SYSTEMS

被引：193

作者：

SADEGH, N

机构：

[1] George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1993年 / 4卷 / 06期

基金：

美国国家科学基金会;

关键词：

D O I：

10.1109/72.286893

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Tracking control of a general class of nonlinear systems using a perceptron neural network (PNN) is presented. The basic structure of the PNN and its training law are first derived. A novel discrete-time control strategy is introduced that employs the PNN for direct on-line estimation of the required feedforward control input. The developed controller can be applied to both discrete and continuous-times plants. Unlike most of the existing direct adaptive or learning schemes, the nonlinear plant is not assumed to be feedback linearizable. The stability of the neural controller under ideal conditions, and its robust stability to inexact modeling information is rigorously analyzed.

引用

页码：982 / 988

页数：7

共 14 条

[1]

ANTSAKLIS PJ, 1990, IEEE T NEURAL NETWOR, V1

[2]

Goodwin GC., 1984, ADAPTIVE FILTERING P

[3] (ADF,G), (ADF,G) AND LOCALLY (ADF,G) INVARIANT AND CONTROLLABILITY DISTRIBUTIONS [J].

KRENER, AJ .

SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 1985, 23 (04) :523-549

[4]

KWATO M, 1987, BIOL CYBERN, V57, P169

[5]

LEONARD JE, 1991, IEEE CONTR SYST MAG, V11

[6] STABLE DISCRETE ADAPTIVE-CONTROL [J].

NARENDRA, KS ;

LIN, YH .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1980, 25 (03) :456-461

[7]

Pao Y.-H., 1989, ADAPTIVE PATTERN REC

[8]

Parthasarathy K., 1990, IEEE T NEURAL NETWOR, VI

[9]

PSALTIS D, 1988, IEEE CONTR SYST MAG

[10]

Royden H, 1968, REAL ANAL

← 1 2 →