Adaptive neural output regulation control of a solar power plant

Paulo José Carrilho de Sousa Gil; DEE Group Author

doi:10.1016/j.conengprac.2010.06.001

Adaptive neural output regulation control of a solar power plant

Paulo José Carrilho de Sousa Gil, DEE Group Author

Research output: Contribution to journal › Article › peer-review

14 Citations (Scopus)

Abstract

This work proposes an indirect adaptive nonlinear control scheme based on a recurrent neural network and the output regulation theory. The neural model is first trained off-line, being further improved by means of an on-line learning strategy using the Lyapunov and nonlinear observation theories. The regulation problem is solved by an iterative strategy, formulated as an eigenvalue assignment problem, ensuring the convergence of the regulation equations. The strategy was tested on a distributed collector field of a solar power plant (Plataforma Solar de Almeria, Spain). Experimental results, collected on the solar power plant, show the effectiveness of the proposed approach. (c) 2010 Elsevier Ltd. All rights reserved.

Original language	Unknown
Pages (from-to)	1183-1196
Journal	Control Engineering Practice
Volume	18
Issue number	10
DOIs	https://doi.org/10.1016/j.conengprac.2010.06.001
Publication status	Published - 1 Jan 2010

Access to Document

10.1016/j.conengprac.2010.06.001

Cite this

@article{e4b6f7c188b146e1a23da5172e12e4e5,

title = "Adaptive neural output regulation control of a solar power plant",

abstract = "This work proposes an indirect adaptive nonlinear control scheme based on a recurrent neural network and the output regulation theory. The neural model is first trained off-line, being further improved by means of an on-line learning strategy using the Lyapunov and nonlinear observation theories. The regulation problem is solved by an iterative strategy, formulated as an eigenvalue assignment problem, ensuring the convergence of the regulation equations. The strategy was tested on a distributed collector field of a solar power plant (Plataforma Solar de Almeria, Spain). Experimental results, collected on the solar power plant, show the effectiveness of the proposed approach. (c) 2010 Elsevier Ltd. All rights reserved.",

keywords = "neural, Solar, control, learning, Recurrent, schemes, networks, nonlinear, On-line, collector, adaptive, regulation, plants, Output, Discrete-time, power, time, fields, nonlinear-systems",

author = "Gil, {Paulo Jos{\'e} Carrilho de Sousa} and {DEE Group Author}",

year = "2010",

month = jan,

day = "1",

doi = "10.1016/j.conengprac.2010.06.001",

language = "Unknown",

volume = "18",

pages = "1183--1196",

journal = "Control Engineering Practice",

issn = "0967-0661",

publisher = "Elsevier Science B.V., Amsterdam.",

number = "10",

}

TY - JOUR

T1 - Adaptive neural output regulation control of a solar power plant

AU - Gil, Paulo José Carrilho de Sousa

AU - DEE Group Author

PY - 2010/1/1

Y1 - 2010/1/1

N2 - This work proposes an indirect adaptive nonlinear control scheme based on a recurrent neural network and the output regulation theory. The neural model is first trained off-line, being further improved by means of an on-line learning strategy using the Lyapunov and nonlinear observation theories. The regulation problem is solved by an iterative strategy, formulated as an eigenvalue assignment problem, ensuring the convergence of the regulation equations. The strategy was tested on a distributed collector field of a solar power plant (Plataforma Solar de Almeria, Spain). Experimental results, collected on the solar power plant, show the effectiveness of the proposed approach. (c) 2010 Elsevier Ltd. All rights reserved.

AB - This work proposes an indirect adaptive nonlinear control scheme based on a recurrent neural network and the output regulation theory. The neural model is first trained off-line, being further improved by means of an on-line learning strategy using the Lyapunov and nonlinear observation theories. The regulation problem is solved by an iterative strategy, formulated as an eigenvalue assignment problem, ensuring the convergence of the regulation equations. The strategy was tested on a distributed collector field of a solar power plant (Plataforma Solar de Almeria, Spain). Experimental results, collected on the solar power plant, show the effectiveness of the proposed approach. (c) 2010 Elsevier Ltd. All rights reserved.

KW - neural

KW - Solar

KW - control

KW - learning

KW - Recurrent

KW - schemes

KW - networks

KW - nonlinear

KW - On-line

KW - collector

KW - adaptive

KW - regulation

KW - plants

KW - Output

KW - Discrete-time

KW - power

KW - time

KW - fields

KW - nonlinear-systems

U2 - 10.1016/j.conengprac.2010.06.001

DO - 10.1016/j.conengprac.2010.06.001

M3 - Article

SN - 0967-0661

VL - 18

SP - 1183

EP - 1196

JO - Control Engineering Practice

JF - Control Engineering Practice

IS - 10

ER -