Decentralized control of large-scale systems using single Hidden layer neural networks

F. Nardi; N. Hovakimyan; A. J. Calise

doi:10.1109/acc.2001.946400

Decentralized control of large-scale systems using single Hidden layer neural networks

F. Nardi, N. Hovakimyan, A. J. Calise

Research output: Contribution to journal › Conference article › peer-review

Abstract

A decentralized adaptive control design procedure for large-scale uncertain systems is developed using Single Hidden Layer neural networks. The subsystems are assumed to be feedback linearizable and non-affine in the control, and their interconnections bounded linearly by the tracking error norms. Single Hidden Layer neural networks are introduced to approximate the feedback linearization error signal online from available measurements. A robust adaptive signal is required in the analysis to shield the feedback linearizing control law from the interconnection effects. The tracking errors are shown to be uniformly ultimately bounded, and all other signals uniformly bounded. The proposed adaptive algorithm is implemented in simulation to stabilize an interconnected double inverted pendulum.

Original language	English (US)
Pages (from-to)	3122-3127
Number of pages	6
Journal	Proceedings of the American Control Conference
Volume	4
DOIs	https://doi.org/10.1109/acc.2001.946400
State	Published - 2001
Externally published	Yes
Event	2001 American Control Conference - Arlington, VA, United States Duration: Jun 25 2001 → Jun 27 2001

ASJC Scopus subject areas

Electrical and Electronic Engineering

Online availability

10.1109/acc.2001.946400

Library availability

Discover UIUC Full Text

Cite this

@article{491d95961c944b728690c2b2fe77eed6,

title = "Decentralized control of large-scale systems using single Hidden layer neural networks",

abstract = "A decentralized adaptive control design procedure for large-scale uncertain systems is developed using Single Hidden Layer neural networks. The subsystems are assumed to be feedback linearizable and non-affine in the control, and their interconnections bounded linearly by the tracking error norms. Single Hidden Layer neural networks are introduced to approximate the feedback linearization error signal online from available measurements. A robust adaptive signal is required in the analysis to shield the feedback linearizing control law from the interconnection effects. The tracking errors are shown to be uniformly ultimately bounded, and all other signals uniformly bounded. The proposed adaptive algorithm is implemented in simulation to stabilize an interconnected double inverted pendulum.",

author = "F. Nardi and N. Hovakimyan and Calise, {A. J.}",

year = "2001",

doi = "10.1109/acc.2001.946400",

language = "English (US)",

volume = "4",

pages = "3122--3127",

journal = "Proceedings of the American Control Conference",

issn = "0743-1619",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "2001 American Control Conference ; Conference date: 25-06-2001 Through 27-06-2001",

}

TY - JOUR

T1 - Decentralized control of large-scale systems using single Hidden layer neural networks

AU - Nardi, F.

AU - Hovakimyan, N.

AU - Calise, A. J.

PY - 2001

Y1 - 2001

N2 - A decentralized adaptive control design procedure for large-scale uncertain systems is developed using Single Hidden Layer neural networks. The subsystems are assumed to be feedback linearizable and non-affine in the control, and their interconnections bounded linearly by the tracking error norms. Single Hidden Layer neural networks are introduced to approximate the feedback linearization error signal online from available measurements. A robust adaptive signal is required in the analysis to shield the feedback linearizing control law from the interconnection effects. The tracking errors are shown to be uniformly ultimately bounded, and all other signals uniformly bounded. The proposed adaptive algorithm is implemented in simulation to stabilize an interconnected double inverted pendulum.

AB - A decentralized adaptive control design procedure for large-scale uncertain systems is developed using Single Hidden Layer neural networks. The subsystems are assumed to be feedback linearizable and non-affine in the control, and their interconnections bounded linearly by the tracking error norms. Single Hidden Layer neural networks are introduced to approximate the feedback linearization error signal online from available measurements. A robust adaptive signal is required in the analysis to shield the feedback linearizing control law from the interconnection effects. The tracking errors are shown to be uniformly ultimately bounded, and all other signals uniformly bounded. The proposed adaptive algorithm is implemented in simulation to stabilize an interconnected double inverted pendulum.

UR - http://www.scopus.com/inward/record.url?scp=0034848856&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034848856&partnerID=8YFLogxK

U2 - 10.1109/acc.2001.946400

DO - 10.1109/acc.2001.946400

M3 - Conference article

AN - SCOPUS:0034848856

SN - 0743-1619

VL - 4

SP - 3122

EP - 3127

JO - Proceedings of the American Control Conference

JF - Proceedings of the American Control Conference

T2 - 2001 American Control Conference

Y2 - 25 June 2001 through 27 June 2001

ER -

Decentralized control of large-scale systems using single Hidden layer neural networks

Abstract

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this