A RECURRENT NEURAL-NET APPROACH TO ONE-STEP AHEAD CONTROL-PROBLEMS

被引：15

作者：

YIP, PPC

PAO, YH

机构：

[1] Department of Electrical Engineering and Applied Physics, Case Western Reserve University, Cleveland, OH

来源：

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS | 1994年 / 24卷 / 04期

关键词：

Neural networks;

D O I：

10.1109/21.286388

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, we present a recurrent neural net technique to provide control actions for nonlinear dynamic systems. In most current neural net control approaches, two nets are usually required. One acts as a system emulator, and the other one is a controller network. Rather than using two nets, our system requires only one net which is the system emulator. In our proposed system, a neural net is used to learn the forward dynamics of the system, and the control signal is evolved from the output of the same net with use of an equation of motion. There is no need to learn the control law from another neural net, such as a system inverse net. The use of the proposed algorithm is illustrated with an example.

引用

页码：678 / 683

页数：6

共 16 条

[1]

Astrom K.J., 1995, ADAPTIVE CONTROL

[2] SELF TUNING REGULATORS [J].

ASTROM, KJ ;

WITTENMARK, B .

AUTOMATICA, 1973, 9 (02) :185-199

[3]

CHEN CF, 1989, THESIS CASE W RESERV

[4]

Chen F.-C., 1990, IEEE Control Systems Magazine, V10, P44, DOI 10.1109/37.55123

[5] SELF-TUNING CONTROL [J].

CLARKE, DW ;

GAWTHROP, PJ .

PROCEEDINGS OF THE INSTITUTION OF ELECTRICAL ENGINEERS-LONDON, 1979, 126 (06) :633-640

[6] MULTILAYER FEEDFORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS [J].

HORNIK, K ;

STINCHCOMBE, M ;

WHITE, H .

NEURAL NETWORKS, 1989, 2 (05) :359-366

[7]

Landau ID, 1979, ADAPTIVE CONTROL

[8]

Narendra K S, 1990, IEEE Trans Neural Netw, V1, P4, DOI 10.1109/72.80202

[9]

Nguyen D. H., 1990, IEEE Control Systems Magazine, V10, P18, DOI 10.1109/37.55119

[10]

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

← 1 2 →