A dead-zone approach in nonlinear adaptive control using neural networks

Fu-Chuang Chen

doi:10.1109/CDC.1991.261277

A dead-zone approach in nonlinear adaptive control using neural networks

Fu-Chuang Chen^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

Layered neural networks are used in a nonlinear self-tuning adaptive control problem. The plant is an unknown feedback-linearizable discrete-time system, represented by an input-output model, with a relative degree possibly higher than one. To arrive at a convergence result, a dead zone is used in the neural network updating rule. The result indicates that for any initial conditions of the plant, if the neural network model contains a sufficient number of nonlinear hidden neurons and if the initial guess of the network weights is sufficiently close to the correct weights, then the tracking error between the plant output and the reference command will converge to a bounded ball. Computer simulations verified the theoretical result.

Original language	English
Title of host publication	Proceedings of the IEEE Conference on Decision and Control
Publisher	Publ by IEEE
Pages	156-161
Number of pages	6
ISBN (Print)	0780304500
DOIs	https://doi.org/10.1109/CDC.1991.261277
State	Published - 1 Jan 1992
Event	Proceedings of the 30th IEEE Conference on Decision and Control Part 1 (of 3) - Brighton, Engl Duration: 11 Dec 1991 → 13 Dec 1991

Publication series

Name	Proceedings of the IEEE Conference on Decision and Control
ISSN (Print)	0191-2216

Conference

Conference	Proceedings of the 30th IEEE Conference on Decision and Control Part 1 (of 3)
City	Brighton, Engl
Period	11/12/91 → 13/12/91

Access to Document

10.1109/CDC.1991.261277

Cite this

@inproceedings{d03928d8e67345ea87491f5890c08808,

title = "A dead-zone approach in nonlinear adaptive control using neural networks",

abstract = "Layered neural networks are used in a nonlinear self-tuning adaptive control problem. The plant is an unknown feedback-linearizable discrete-time system, represented by an input-output model, with a relative degree possibly higher than one. To arrive at a convergence result, a dead zone is used in the neural network updating rule. The result indicates that for any initial conditions of the plant, if the neural network model contains a sufficient number of nonlinear hidden neurons and if the initial guess of the network weights is sufficiently close to the correct weights, then the tracking error between the plant output and the reference command will converge to a bounded ball. Computer simulations verified the theoretical result.",

author = "Fu-Chuang Chen",

year = "1992",

month = jan,

day = "1",

doi = "10.1109/CDC.1991.261277",

language = "English",

isbn = "0780304500",

series = "Proceedings of the IEEE Conference on Decision and Control",

publisher = "Publ by IEEE",

pages = "156--161",

booktitle = "Proceedings of the IEEE Conference on Decision and Control",

note = "Proceedings of the 30th IEEE Conference on Decision and Control Part 1 (of 3) ; Conference date: 11-12-1991 Through 13-12-1991",

}

Chen, F-C 1992, A dead-zone approach in nonlinear adaptive control using neural networks. in Proceedings of the IEEE Conference on Decision and Control. Proceedings of the IEEE Conference on Decision and Control, Publ by IEEE, pp. 156-161, Proceedings of the 30th IEEE Conference on Decision and Control Part 1 (of 3), Brighton, Engl, 11/12/91. https://doi.org/10.1109/CDC.1991.261277

TY - GEN

T1 - A dead-zone approach in nonlinear adaptive control using neural networks

AU - Chen, Fu-Chuang

PY - 1992/1/1

Y1 - 1992/1/1

N2 - Layered neural networks are used in a nonlinear self-tuning adaptive control problem. The plant is an unknown feedback-linearizable discrete-time system, represented by an input-output model, with a relative degree possibly higher than one. To arrive at a convergence result, a dead zone is used in the neural network updating rule. The result indicates that for any initial conditions of the plant, if the neural network model contains a sufficient number of nonlinear hidden neurons and if the initial guess of the network weights is sufficiently close to the correct weights, then the tracking error between the plant output and the reference command will converge to a bounded ball. Computer simulations verified the theoretical result.

AB - Layered neural networks are used in a nonlinear self-tuning adaptive control problem. The plant is an unknown feedback-linearizable discrete-time system, represented by an input-output model, with a relative degree possibly higher than one. To arrive at a convergence result, a dead zone is used in the neural network updating rule. The result indicates that for any initial conditions of the plant, if the neural network model contains a sufficient number of nonlinear hidden neurons and if the initial guess of the network weights is sufficiently close to the correct weights, then the tracking error between the plant output and the reference command will converge to a bounded ball. Computer simulations verified the theoretical result.

UR - http://www.scopus.com/inward/record.url?scp=0026676735&partnerID=8YFLogxK

U2 - 10.1109/CDC.1991.261277

DO - 10.1109/CDC.1991.261277

M3 - Conference contribution

AN - SCOPUS:0026676735

SN - 0780304500

T3 - Proceedings of the IEEE Conference on Decision and Control

SP - 156

EP - 161

BT - Proceedings of the IEEE Conference on Decision and Control

PB - Publ by IEEE

T2 - Proceedings of the 30th IEEE Conference on Decision and Control Part 1 (of 3)

Y2 - 11 December 1991 through 13 December 1991

ER -

A dead-zone approach in nonlinear adaptive control using neural networks

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this