Neural network based modeling of a large steam turbine-generator rotor body parameters from on-line disturbance data

H. Bora Karayaka, Ali Keyhani, Gerald Thomas Heydt, Baj L. Agrawal, Douglas A. Selin

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

A novel technique to estimate and model rotor-body parameters of a large steam turbine-generator from real time disturbance data is presented. For each set of disturbance data collected at different operating conditions, the rotor body parameters of the generator are estimated using an Output Error Method (OEM). Artificial neural network (ANN) based estimators are later used to model the nonlinearities in the estimated parameters based on the generator operating conditions. The developed ANN models are then validated with measurements not used in the training procedure. The performance of estimated parameters is also validated with extensive simulations and compared against the manufacturer values.

Original languageEnglish (US)
Pages (from-to)305-311
Number of pages7
JournalIEEE Transactions on Energy Conversion
Volume16
Issue number4
DOIs
StatePublished - Dec 2001

Fingerprint

Turbogenerators
Steam turbines
Rotors
Neural networks

Keywords

  • Artificial neural networks
  • Large utility generators
  • Parameter identification
  • Rotor body parameters

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Fuel Technology
  • Electrical and Electronic Engineering

Cite this

Neural network based modeling of a large steam turbine-generator rotor body parameters from on-line disturbance data. / Karayaka, H. Bora; Keyhani, Ali; Heydt, Gerald Thomas; Agrawal, Baj L.; Selin, Douglas A.

In: IEEE Transactions on Energy Conversion, Vol. 16, No. 4, 12.2001, p. 305-311.

Research output: Contribution to journalArticle

@article{fa9f0ea75931450380b12ef506a39051,
title = "Neural network based modeling of a large steam turbine-generator rotor body parameters from on-line disturbance data",
abstract = "A novel technique to estimate and model rotor-body parameters of a large steam turbine-generator from real time disturbance data is presented. For each set of disturbance data collected at different operating conditions, the rotor body parameters of the generator are estimated using an Output Error Method (OEM). Artificial neural network (ANN) based estimators are later used to model the nonlinearities in the estimated parameters based on the generator operating conditions. The developed ANN models are then validated with measurements not used in the training procedure. The performance of estimated parameters is also validated with extensive simulations and compared against the manufacturer values.",
keywords = "Artificial neural networks, Large utility generators, Parameter identification, Rotor body parameters",
author = "Karayaka, {H. Bora} and Ali Keyhani and Heydt, {Gerald Thomas} and Agrawal, {Baj L.} and Selin, {Douglas A.}",
year = "2001",
month = "12",
doi = "10.1109/60.969468",
language = "English (US)",
volume = "16",
pages = "305--311",
journal = "IEEE Transactions on Energy Conversion",
issn = "0885-8969",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Neural network based modeling of a large steam turbine-generator rotor body parameters from on-line disturbance data

AU - Karayaka, H. Bora

AU - Keyhani, Ali

AU - Heydt, Gerald Thomas

AU - Agrawal, Baj L.

AU - Selin, Douglas A.

PY - 2001/12

Y1 - 2001/12

N2 - A novel technique to estimate and model rotor-body parameters of a large steam turbine-generator from real time disturbance data is presented. For each set of disturbance data collected at different operating conditions, the rotor body parameters of the generator are estimated using an Output Error Method (OEM). Artificial neural network (ANN) based estimators are later used to model the nonlinearities in the estimated parameters based on the generator operating conditions. The developed ANN models are then validated with measurements not used in the training procedure. The performance of estimated parameters is also validated with extensive simulations and compared against the manufacturer values.

AB - A novel technique to estimate and model rotor-body parameters of a large steam turbine-generator from real time disturbance data is presented. For each set of disturbance data collected at different operating conditions, the rotor body parameters of the generator are estimated using an Output Error Method (OEM). Artificial neural network (ANN) based estimators are later used to model the nonlinearities in the estimated parameters based on the generator operating conditions. The developed ANN models are then validated with measurements not used in the training procedure. The performance of estimated parameters is also validated with extensive simulations and compared against the manufacturer values.

KW - Artificial neural networks

KW - Large utility generators

KW - Parameter identification

KW - Rotor body parameters

UR - http://www.scopus.com/inward/record.url?scp=0035673289&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035673289&partnerID=8YFLogxK

U2 - 10.1109/60.969468

DO - 10.1109/60.969468

M3 - Article

AN - SCOPUS:0035673289

VL - 16

SP - 305

EP - 311

JO - IEEE Transactions on Energy Conversion

JF - IEEE Transactions on Energy Conversion

SN - 0885-8969

IS - 4

ER -