MLP/RBF neural-networks-based online global model identification of synchronous generator

Jung Wook Park, Ganesh Kumar Venayagamoorthy, Ronald G. Harley

Research output: Contribution to journalArticle

56 Citations (Scopus)

Abstract

This paper compares the performances of a multilayer perceptron neural network (MLPN) and a radial basis function neural network (RBFN) for online identification of the nonlinear dynamics of a synchronous generator in a power system. The computational requirement to process the data during the online training, local convergence, and online global convergence properties are investigated by time-domain simulations. The performances of the identifiers as a global model, which are trained at different stable operating conditions, are compared using the actual signals as well as the deviation signals for the inputs of the identifiers. Such an online-trained identifier with fixed optimal weights after the global convergence test is needed to provide information about the plant to a neurocontroller. The use of the fixed weights is to provide against a sensor failure in which case the training of the identifiers would be automatically stopped, and their weights frozen, but the control action, which uses the identifier, would be able to continue.

Original languageEnglish
Pages (from-to)1685-1695
Number of pages11
JournalIEEE Transactions on Industrial Electronics
Volume52
Issue number6
DOIs
Publication statusPublished - 2005 Dec 1

Fingerprint

Synchronous generators
Identification (control systems)
generators
Neural networks
education
Multilayer neural networks
self organizing systems
Sensors
deviation
requirements
sensors
simulation

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Park, Jung Wook ; Venayagamoorthy, Ganesh Kumar ; Harley, Ronald G. / MLP/RBF neural-networks-based online global model identification of synchronous generator. In: IEEE Transactions on Industrial Electronics. 2005 ; Vol. 52, No. 6. pp. 1685-1695.
@article{69e0937cf40f4e9abcac7b7d8232cdab,
title = "MLP/RBF neural-networks-based online global model identification of synchronous generator",
abstract = "This paper compares the performances of a multilayer perceptron neural network (MLPN) and a radial basis function neural network (RBFN) for online identification of the nonlinear dynamics of a synchronous generator in a power system. The computational requirement to process the data during the online training, local convergence, and online global convergence properties are investigated by time-domain simulations. The performances of the identifiers as a global model, which are trained at different stable operating conditions, are compared using the actual signals as well as the deviation signals for the inputs of the identifiers. Such an online-trained identifier with fixed optimal weights after the global convergence test is needed to provide information about the plant to a neurocontroller. The use of the fixed weights is to provide against a sensor failure in which case the training of the identifiers would be automatically stopped, and their weights frozen, but the control action, which uses the identifier, would be able to continue.",
author = "Park, {Jung Wook} and Venayagamoorthy, {Ganesh Kumar} and Harley, {Ronald G.}",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/TIE.2005.858703",
language = "English",
volume = "52",
pages = "1685--1695",
journal = "IEEE Transactions on Industrial Electronics",
issn = "0278-0046",
publisher = "IEEE Industrial Electronics Society",
number = "6",

}

MLP/RBF neural-networks-based online global model identification of synchronous generator. / Park, Jung Wook; Venayagamoorthy, Ganesh Kumar; Harley, Ronald G.

In: IEEE Transactions on Industrial Electronics, Vol. 52, No. 6, 01.12.2005, p. 1685-1695.

Research output: Contribution to journalArticle

TY - JOUR

T1 - MLP/RBF neural-networks-based online global model identification of synchronous generator

AU - Park, Jung Wook

AU - Venayagamoorthy, Ganesh Kumar

AU - Harley, Ronald G.

PY - 2005/12/1

Y1 - 2005/12/1

N2 - This paper compares the performances of a multilayer perceptron neural network (MLPN) and a radial basis function neural network (RBFN) for online identification of the nonlinear dynamics of a synchronous generator in a power system. The computational requirement to process the data during the online training, local convergence, and online global convergence properties are investigated by time-domain simulations. The performances of the identifiers as a global model, which are trained at different stable operating conditions, are compared using the actual signals as well as the deviation signals for the inputs of the identifiers. Such an online-trained identifier with fixed optimal weights after the global convergence test is needed to provide information about the plant to a neurocontroller. The use of the fixed weights is to provide against a sensor failure in which case the training of the identifiers would be automatically stopped, and their weights frozen, but the control action, which uses the identifier, would be able to continue.

AB - This paper compares the performances of a multilayer perceptron neural network (MLPN) and a radial basis function neural network (RBFN) for online identification of the nonlinear dynamics of a synchronous generator in a power system. The computational requirement to process the data during the online training, local convergence, and online global convergence properties are investigated by time-domain simulations. The performances of the identifiers as a global model, which are trained at different stable operating conditions, are compared using the actual signals as well as the deviation signals for the inputs of the identifiers. Such an online-trained identifier with fixed optimal weights after the global convergence test is needed to provide information about the plant to a neurocontroller. The use of the fixed weights is to provide against a sensor failure in which case the training of the identifiers would be automatically stopped, and their weights frozen, but the control action, which uses the identifier, would be able to continue.

UR - http://www.scopus.com/inward/record.url?scp=29244437885&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=29244437885&partnerID=8YFLogxK

U2 - 10.1109/TIE.2005.858703

DO - 10.1109/TIE.2005.858703

M3 - Article

AN - SCOPUS:29244437885

VL - 52

SP - 1685

EP - 1695

JO - IEEE Transactions on Industrial Electronics

JF - IEEE Transactions on Industrial Electronics

SN - 0278-0046

IS - 6

ER -