Neuro-fuzzy modeling of superheating system of a steam power plant

A. R. Mehrabian, A. Yousefi-Koma, M. Mohammad-Zaheri, A. Ghaffari, D. Mehrabi

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

1 Citation (Scopus)

Abstract

In this paper superheating system of a 325MW steam power plant is modeled based on the recurrent neuro-fuzzy networks and subtractive clustering. The experimental data are obtained from a complete set of field experiments under various operating conditions. Nine neuro-fuzzy models are constructed and trained for seven subsystems of the superheating unit. Then, these nine fuzzy models are put together merging series and parallel units according to the real power plant subsystems, to obtain the global model of the superheating process. Comparing the time response of the nonlinear neuro-fuzzy model of a subsystem with the time response of its linear model based on the Least Square Error (LSE) method, indicates that the nonlinear neurofuzzy model is more accurate and reliable than the linear model in the sense that its response is closer to the response of the actual superheating system.

Original languageEnglish
Title of host publicationProceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2006
Pages347-352
Number of pages6
Publication statusPublished - 2006
EventIASTED International Conference on Artificial Intelligence and Applications, AIA 2006 - Innsbruck, Austria
Duration: Feb 13 2006Feb 16 2006

Other

OtherIASTED International Conference on Artificial Intelligence and Applications, AIA 2006
CountryAustria
CityInnsbruck
Period2/13/062/16/06

Fingerprint

Steam power plants
Merging
Power plants

Keywords

  • Fuzzy sets
  • Neuro-fuzzy systems
  • Nonlinear modeling
  • Nonlinear systems
  • PID controller
  • Steam power plant

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Software

Cite this

Mehrabian, A. R., Yousefi-Koma, A., Mohammad-Zaheri, M., Ghaffari, A., & Mehrabi, D. (2006). Neuro-fuzzy modeling of superheating system of a steam power plant. In Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2006 (pp. 347-352)

Neuro-fuzzy modeling of superheating system of a steam power plant. / Mehrabian, A. R.; Yousefi-Koma, A.; Mohammad-Zaheri, M.; Ghaffari, A.; Mehrabi, D.

Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2006. 2006. p. 347-352.

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

Mehrabian, AR, Yousefi-Koma, A, Mohammad-Zaheri, M, Ghaffari, A & Mehrabi, D 2006, Neuro-fuzzy modeling of superheating system of a steam power plant. in Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2006. pp. 347-352, IASTED International Conference on Artificial Intelligence and Applications, AIA 2006, Innsbruck, Austria, 2/13/06.
Mehrabian AR, Yousefi-Koma A, Mohammad-Zaheri M, Ghaffari A, Mehrabi D. Neuro-fuzzy modeling of superheating system of a steam power plant. In Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2006. 2006. p. 347-352
Mehrabian, A. R. ; Yousefi-Koma, A. ; Mohammad-Zaheri, M. ; Ghaffari, A. ; Mehrabi, D. / Neuro-fuzzy modeling of superheating system of a steam power plant. Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2006. 2006. pp. 347-352
@inproceedings{a74d953be8b64b85970773c6ad18e8f5,
title = "Neuro-fuzzy modeling of superheating system of a steam power plant",
abstract = "In this paper superheating system of a 325MW steam power plant is modeled based on the recurrent neuro-fuzzy networks and subtractive clustering. The experimental data are obtained from a complete set of field experiments under various operating conditions. Nine neuro-fuzzy models are constructed and trained for seven subsystems of the superheating unit. Then, these nine fuzzy models are put together merging series and parallel units according to the real power plant subsystems, to obtain the global model of the superheating process. Comparing the time response of the nonlinear neuro-fuzzy model of a subsystem with the time response of its linear model based on the Least Square Error (LSE) method, indicates that the nonlinear neurofuzzy model is more accurate and reliable than the linear model in the sense that its response is closer to the response of the actual superheating system.",
keywords = "Fuzzy sets, Neuro-fuzzy systems, Nonlinear modeling, Nonlinear systems, PID controller, Steam power plant",
author = "Mehrabian, {A. R.} and A. Yousefi-Koma and M. Mohammad-Zaheri and A. Ghaffari and D. Mehrabi",
year = "2006",
language = "English",
pages = "347--352",
booktitle = "Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2006",

}

TY - GEN

T1 - Neuro-fuzzy modeling of superheating system of a steam power plant

AU - Mehrabian, A. R.

AU - Yousefi-Koma, A.

AU - Mohammad-Zaheri, M.

AU - Ghaffari, A.

AU - Mehrabi, D.

PY - 2006

Y1 - 2006

N2 - In this paper superheating system of a 325MW steam power plant is modeled based on the recurrent neuro-fuzzy networks and subtractive clustering. The experimental data are obtained from a complete set of field experiments under various operating conditions. Nine neuro-fuzzy models are constructed and trained for seven subsystems of the superheating unit. Then, these nine fuzzy models are put together merging series and parallel units according to the real power plant subsystems, to obtain the global model of the superheating process. Comparing the time response of the nonlinear neuro-fuzzy model of a subsystem with the time response of its linear model based on the Least Square Error (LSE) method, indicates that the nonlinear neurofuzzy model is more accurate and reliable than the linear model in the sense that its response is closer to the response of the actual superheating system.

AB - In this paper superheating system of a 325MW steam power plant is modeled based on the recurrent neuro-fuzzy networks and subtractive clustering. The experimental data are obtained from a complete set of field experiments under various operating conditions. Nine neuro-fuzzy models are constructed and trained for seven subsystems of the superheating unit. Then, these nine fuzzy models are put together merging series and parallel units according to the real power plant subsystems, to obtain the global model of the superheating process. Comparing the time response of the nonlinear neuro-fuzzy model of a subsystem with the time response of its linear model based on the Least Square Error (LSE) method, indicates that the nonlinear neurofuzzy model is more accurate and reliable than the linear model in the sense that its response is closer to the response of the actual superheating system.

KW - Fuzzy sets

KW - Neuro-fuzzy systems

KW - Nonlinear modeling

KW - Nonlinear systems

KW - PID controller

KW - Steam power plant

UR - http://www.scopus.com/inward/record.url?scp=38049105863&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38049105863&partnerID=8YFLogxK

M3 - Conference contribution

SP - 347

EP - 352

BT - Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2006

ER -