Adaptive control of a class of nonlinear discrete-time systems using hybrid neural networks

Teh-Lu Liao, J. H. Horng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, an indirect adaptive controller based on hybrid neural networks, which are composed of two-layered neural networks and radial basis function (RBF) neural networks, is derived for controlling a class of unknown nonlinear discrete-time systems. A hybrid-neural-network-based estimator is used to characterize the input-output behavior of the unknown systems. An adaptation law which adjusts the connection weights of the neural network is used to minimize the error signal which is difference between the actual response and that of the neural network. The indirect adaptive control law is generated on-line using another hybrid neural network related to the estimator, so that the plant results in a bounded tracking error with respect to a desired reference signal. It is proved that the control objective is achieved by the closed-loop system and that the system remains closed-loop stability. The effectiveness of the proposed control scheme is also demonstrated by a simulation example.

Original languageEnglish
Title of host publicationECC 1997 - European Control Conference
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages506-511
Number of pages6
ISBN (Electronic)9783952426906
Publication statusPublished - 1997 Apr 8
Event4th European Control Conference, ECC 1997 - Brussels, Belgium
Duration: 1997 Jul 11997 Jul 4

Publication series

NameECC 1997 - European Control Conference

Other

Other4th European Control Conference, ECC 1997
CountryBelgium
CityBrussels
Period97-07-0197-07-04

Fingerprint

Hybrid systems
Neural networks
Closed loop systems
Controllers

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering

Cite this

Liao, T-L., & Horng, J. H. (1997). Adaptive control of a class of nonlinear discrete-time systems using hybrid neural networks. In ECC 1997 - European Control Conference (pp. 506-511). [7082145] (ECC 1997 - European Control Conference). Institute of Electrical and Electronics Engineers Inc..
Liao, Teh-Lu ; Horng, J. H. / Adaptive control of a class of nonlinear discrete-time systems using hybrid neural networks. ECC 1997 - European Control Conference. Institute of Electrical and Electronics Engineers Inc., 1997. pp. 506-511 (ECC 1997 - European Control Conference).
@inproceedings{628f456f4aff49deb1780ba10ec73c18,
title = "Adaptive control of a class of nonlinear discrete-time systems using hybrid neural networks",
abstract = "In this paper, an indirect adaptive controller based on hybrid neural networks, which are composed of two-layered neural networks and radial basis function (RBF) neural networks, is derived for controlling a class of unknown nonlinear discrete-time systems. A hybrid-neural-network-based estimator is used to characterize the input-output behavior of the unknown systems. An adaptation law which adjusts the connection weights of the neural network is used to minimize the error signal which is difference between the actual response and that of the neural network. The indirect adaptive control law is generated on-line using another hybrid neural network related to the estimator, so that the plant results in a bounded tracking error with respect to a desired reference signal. It is proved that the control objective is achieved by the closed-loop system and that the system remains closed-loop stability. The effectiveness of the proposed control scheme is also demonstrated by a simulation example.",
author = "Teh-Lu Liao and Horng, {J. H.}",
year = "1997",
month = "4",
day = "8",
language = "English",
series = "ECC 1997 - European Control Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "506--511",
booktitle = "ECC 1997 - European Control Conference",
address = "United States",

}

Liao, T-L & Horng, JH 1997, Adaptive control of a class of nonlinear discrete-time systems using hybrid neural networks. in ECC 1997 - European Control Conference., 7082145, ECC 1997 - European Control Conference, Institute of Electrical and Electronics Engineers Inc., pp. 506-511, 4th European Control Conference, ECC 1997, Brussels, Belgium, 97-07-01.

Adaptive control of a class of nonlinear discrete-time systems using hybrid neural networks. / Liao, Teh-Lu; Horng, J. H.

ECC 1997 - European Control Conference. Institute of Electrical and Electronics Engineers Inc., 1997. p. 506-511 7082145 (ECC 1997 - European Control Conference).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Adaptive control of a class of nonlinear discrete-time systems using hybrid neural networks

AU - Liao, Teh-Lu

AU - Horng, J. H.

PY - 1997/4/8

Y1 - 1997/4/8

N2 - In this paper, an indirect adaptive controller based on hybrid neural networks, which are composed of two-layered neural networks and radial basis function (RBF) neural networks, is derived for controlling a class of unknown nonlinear discrete-time systems. A hybrid-neural-network-based estimator is used to characterize the input-output behavior of the unknown systems. An adaptation law which adjusts the connection weights of the neural network is used to minimize the error signal which is difference between the actual response and that of the neural network. The indirect adaptive control law is generated on-line using another hybrid neural network related to the estimator, so that the plant results in a bounded tracking error with respect to a desired reference signal. It is proved that the control objective is achieved by the closed-loop system and that the system remains closed-loop stability. The effectiveness of the proposed control scheme is also demonstrated by a simulation example.

AB - In this paper, an indirect adaptive controller based on hybrid neural networks, which are composed of two-layered neural networks and radial basis function (RBF) neural networks, is derived for controlling a class of unknown nonlinear discrete-time systems. A hybrid-neural-network-based estimator is used to characterize the input-output behavior of the unknown systems. An adaptation law which adjusts the connection weights of the neural network is used to minimize the error signal which is difference between the actual response and that of the neural network. The indirect adaptive control law is generated on-line using another hybrid neural network related to the estimator, so that the plant results in a bounded tracking error with respect to a desired reference signal. It is proved that the control objective is achieved by the closed-loop system and that the system remains closed-loop stability. The effectiveness of the proposed control scheme is also demonstrated by a simulation example.

UR - http://www.scopus.com/inward/record.url?scp=84949111203&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949111203&partnerID=8YFLogxK

M3 - Conference contribution

T3 - ECC 1997 - European Control Conference

SP - 506

EP - 511

BT - ECC 1997 - European Control Conference

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Liao T-L, Horng JH. Adaptive control of a class of nonlinear discrete-time systems using hybrid neural networks. In ECC 1997 - European Control Conference. Institute of Electrical and Electronics Engineers Inc. 1997. p. 506-511. 7082145. (ECC 1997 - European Control Conference).