Neural network-based control design: An LMI approach

Suttipan Limanond, Jennie Si

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

1 Citation (Scopus)

Abstract

In this paper we address a neural network-based control design for a discrete-time nonlinear system. Our design approach is to approximate the nonlinear system with a multilayer perception of which the activation functions are of the sigmoid type symmetric to the origin. A linear difference inclusion representation is then established for this class of approximating neural networks and is used to design a state-feedback control law for the nonlinear system based on the Certainty Equivalence Principle. The control design equations are shown to be a set of linear matrix inequalities where a convex optimization algorithm can be applied to determine the control signal. Further, the stability of the closed-loop is guaranteed in the sense that there exists a unique global attraction region in the neighborhood of the origin to which every trajectory of the closed-loop system converges. Finally, a simple example is presented so as to illustrate our control design procedure.

Original languageEnglish (US)
Title of host publicationProceedings of the American Control Conference
Pages970-974
Number of pages5
Volume2
DOIs
StatePublished - 1998
Event1998 American Control Conference, ACC 1998 - Philadelphia, PA, United States
Duration: Jun 24 1998Jun 26 1998

Other

Other1998 American Control Conference, ACC 1998
CountryUnited States
CityPhiladelphia, PA
Period6/24/986/26/98

Fingerprint

Neural networks
Nonlinear systems
Convex optimization
Linear matrix inequalities
State feedback
Closed loop systems
Feedback control
Multilayers
Chemical activation
Trajectories

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Limanond, S., & Si, J. (1998). Neural network-based control design: An LMI approach. In Proceedings of the American Control Conference (Vol. 2, pp. 970-974). [703553] https://doi.org/10.1109/ACC.1998.703553

Neural network-based control design : An LMI approach. / Limanond, Suttipan; Si, Jennie.

Proceedings of the American Control Conference. Vol. 2 1998. p. 970-974 703553.

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

Limanond, S & Si, J 1998, Neural network-based control design: An LMI approach. in Proceedings of the American Control Conference. vol. 2, 703553, pp. 970-974, 1998 American Control Conference, ACC 1998, Philadelphia, PA, United States, 6/24/98. https://doi.org/10.1109/ACC.1998.703553
Limanond S, Si J. Neural network-based control design: An LMI approach. In Proceedings of the American Control Conference. Vol. 2. 1998. p. 970-974. 703553 https://doi.org/10.1109/ACC.1998.703553
Limanond, Suttipan ; Si, Jennie. / Neural network-based control design : An LMI approach. Proceedings of the American Control Conference. Vol. 2 1998. pp. 970-974
@inproceedings{9668a17a2f8d43bb9a060c06e04b1070,
title = "Neural network-based control design: An LMI approach",
abstract = "In this paper we address a neural network-based control design for a discrete-time nonlinear system. Our design approach is to approximate the nonlinear system with a multilayer perception of which the activation functions are of the sigmoid type symmetric to the origin. A linear difference inclusion representation is then established for this class of approximating neural networks and is used to design a state-feedback control law for the nonlinear system based on the Certainty Equivalence Principle. The control design equations are shown to be a set of linear matrix inequalities where a convex optimization algorithm can be applied to determine the control signal. Further, the stability of the closed-loop is guaranteed in the sense that there exists a unique global attraction region in the neighborhood of the origin to which every trajectory of the closed-loop system converges. Finally, a simple example is presented so as to illustrate our control design procedure.",
author = "Suttipan Limanond and Jennie Si",
year = "1998",
doi = "10.1109/ACC.1998.703553",
language = "English (US)",
isbn = "0780345304",
volume = "2",
pages = "970--974",
booktitle = "Proceedings of the American Control Conference",

}

TY - GEN

T1 - Neural network-based control design

T2 - An LMI approach

AU - Limanond, Suttipan

AU - Si, Jennie

PY - 1998

Y1 - 1998

N2 - In this paper we address a neural network-based control design for a discrete-time nonlinear system. Our design approach is to approximate the nonlinear system with a multilayer perception of which the activation functions are of the sigmoid type symmetric to the origin. A linear difference inclusion representation is then established for this class of approximating neural networks and is used to design a state-feedback control law for the nonlinear system based on the Certainty Equivalence Principle. The control design equations are shown to be a set of linear matrix inequalities where a convex optimization algorithm can be applied to determine the control signal. Further, the stability of the closed-loop is guaranteed in the sense that there exists a unique global attraction region in the neighborhood of the origin to which every trajectory of the closed-loop system converges. Finally, a simple example is presented so as to illustrate our control design procedure.

AB - In this paper we address a neural network-based control design for a discrete-time nonlinear system. Our design approach is to approximate the nonlinear system with a multilayer perception of which the activation functions are of the sigmoid type symmetric to the origin. A linear difference inclusion representation is then established for this class of approximating neural networks and is used to design a state-feedback control law for the nonlinear system based on the Certainty Equivalence Principle. The control design equations are shown to be a set of linear matrix inequalities where a convex optimization algorithm can be applied to determine the control signal. Further, the stability of the closed-loop is guaranteed in the sense that there exists a unique global attraction region in the neighborhood of the origin to which every trajectory of the closed-loop system converges. Finally, a simple example is presented so as to illustrate our control design procedure.

UR - http://www.scopus.com/inward/record.url?scp=33746342535&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33746342535&partnerID=8YFLogxK

U2 - 10.1109/ACC.1998.703553

DO - 10.1109/ACC.1998.703553

M3 - Conference contribution

AN - SCOPUS:33746342535

SN - 0780345304

SN - 9780780345300

VL - 2

SP - 970

EP - 974

BT - Proceedings of the American Control Conference

ER -