Multidimensional minimization training algorithms for steam boiler drum level trip using artificial intelligent monitoring system

Firas Basim Ismail, Hussain H. Al-Kayiem

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

2 Citations (Scopus)

Abstract

This paper deals with the Fault Detection and Diagnosis of steam boiler using developed artificial Neural networks model. Water low level trip of steam boiler is artificially monitored and analyzed in this study, using two different interpretation algorithms. The Broyden-Fletcher-Goldfarb-Shanno quasi-Newton and Levenberg-Marquart are adopted as training algorithms of the developed neural network model. Real site data is captured from a coal-fired thermal power plant in Perak state - Malaysia. Among three power units in the plant, the boiler drum data of unit3 was considered. The selection of the relevant variables to train and validate the neural networks is based on the merging between the theoretical base and the operators experience and the procedure is described in the paper. Results are obtained from one hidden layer and two hidden layers neural network structures for both adopted algorithms. Detailed comparisons have been made based on the Root Mean Square Error. The results are demonstrating that the one hidden layer with one neuron using BFGS training algorithm provides the best optimum NN structure.

Original languageEnglish
Title of host publication2010 International Conference on Intelligent and Advanced Systems, ICIAS 2010
DOIs
Publication statusPublished - 2010
Event2010 International Conference on Intelligent and Advanced Systems, ICIAS 2010 - Kuala Lumpur, Malaysia
Duration: 15 Jun 201017 Jun 2010

Other

Other2010 International Conference on Intelligent and Advanced Systems, ICIAS 2010
CountryMalaysia
CityKuala Lumpur
Period15/06/1017/06/10

Fingerprint

Boilers
Steam
Neural networks
Monitoring
Fault detection
Merging
Mean square error
Neurons
Failure analysis
Power plants
Coal
Water

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Ismail, Firas Basim ; Al-Kayiem, Hussain H. / Multidimensional minimization training algorithms for steam boiler drum level trip using artificial intelligent monitoring system. 2010 International Conference on Intelligent and Advanced Systems, ICIAS 2010. 2010.
@inproceedings{b2a4c98903b04bbf870dd80d1db0d60c,
title = "Multidimensional minimization training algorithms for steam boiler drum level trip using artificial intelligent monitoring system",
abstract = "This paper deals with the Fault Detection and Diagnosis of steam boiler using developed artificial Neural networks model. Water low level trip of steam boiler is artificially monitored and analyzed in this study, using two different interpretation algorithms. The Broyden-Fletcher-Goldfarb-Shanno quasi-Newton and Levenberg-Marquart are adopted as training algorithms of the developed neural network model. Real site data is captured from a coal-fired thermal power plant in Perak state - Malaysia. Among three power units in the plant, the boiler drum data of unit3 was considered. The selection of the relevant variables to train and validate the neural networks is based on the merging between the theoretical base and the operators experience and the procedure is described in the paper. Results are obtained from one hidden layer and two hidden layers neural network structures for both adopted algorithms. Detailed comparisons have been made based on the Root Mean Square Error. The results are demonstrating that the one hidden layer with one neuron using BFGS training algorithm provides the best optimum NN structure.",
author = "Ismail, {Firas Basim} and Al-Kayiem, {Hussain H.}",
year = "2010",
doi = "10.1109/ICIAS.2010.5716197",
language = "English",
isbn = "9781424466238",
booktitle = "2010 International Conference on Intelligent and Advanced Systems, ICIAS 2010",

}

Ismail, FB & Al-Kayiem, HH 2010, Multidimensional minimization training algorithms for steam boiler drum level trip using artificial intelligent monitoring system. in 2010 International Conference on Intelligent and Advanced Systems, ICIAS 2010., 5716197, 2010 International Conference on Intelligent and Advanced Systems, ICIAS 2010, Kuala Lumpur, Malaysia, 15/06/10. https://doi.org/10.1109/ICIAS.2010.5716197

Multidimensional minimization training algorithms for steam boiler drum level trip using artificial intelligent monitoring system. / Ismail, Firas Basim; Al-Kayiem, Hussain H.

2010 International Conference on Intelligent and Advanced Systems, ICIAS 2010. 2010. 5716197.

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

TY - GEN

T1 - Multidimensional minimization training algorithms for steam boiler drum level trip using artificial intelligent monitoring system

AU - Ismail, Firas Basim

AU - Al-Kayiem, Hussain H.

PY - 2010

Y1 - 2010

N2 - This paper deals with the Fault Detection and Diagnosis of steam boiler using developed artificial Neural networks model. Water low level trip of steam boiler is artificially monitored and analyzed in this study, using two different interpretation algorithms. The Broyden-Fletcher-Goldfarb-Shanno quasi-Newton and Levenberg-Marquart are adopted as training algorithms of the developed neural network model. Real site data is captured from a coal-fired thermal power plant in Perak state - Malaysia. Among three power units in the plant, the boiler drum data of unit3 was considered. The selection of the relevant variables to train and validate the neural networks is based on the merging between the theoretical base and the operators experience and the procedure is described in the paper. Results are obtained from one hidden layer and two hidden layers neural network structures for both adopted algorithms. Detailed comparisons have been made based on the Root Mean Square Error. The results are demonstrating that the one hidden layer with one neuron using BFGS training algorithm provides the best optimum NN structure.

AB - This paper deals with the Fault Detection and Diagnosis of steam boiler using developed artificial Neural networks model. Water low level trip of steam boiler is artificially monitored and analyzed in this study, using two different interpretation algorithms. The Broyden-Fletcher-Goldfarb-Shanno quasi-Newton and Levenberg-Marquart are adopted as training algorithms of the developed neural network model. Real site data is captured from a coal-fired thermal power plant in Perak state - Malaysia. Among three power units in the plant, the boiler drum data of unit3 was considered. The selection of the relevant variables to train and validate the neural networks is based on the merging between the theoretical base and the operators experience and the procedure is described in the paper. Results are obtained from one hidden layer and two hidden layers neural network structures for both adopted algorithms. Detailed comparisons have been made based on the Root Mean Square Error. The results are demonstrating that the one hidden layer with one neuron using BFGS training algorithm provides the best optimum NN structure.

UR - http://www.scopus.com/inward/record.url?scp=79952768751&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952768751&partnerID=8YFLogxK

U2 - 10.1109/ICIAS.2010.5716197

DO - 10.1109/ICIAS.2010.5716197

M3 - Conference contribution

SN - 9781424466238

BT - 2010 International Conference on Intelligent and Advanced Systems, ICIAS 2010

ER -