Multidimensional Minimization Training Algorithms for Steam Boiler Drum Level Trip Using Artificial Intelligence Monitoring System
This paper deals with the Fault Detection and Diagnosis of steam boiler drum low level by artificial Neural Networks using two different interpretation algorithms. The BFGS quasi-Newton (TRAINBFG) and Levenberg-Marquart (TRAINLV) have been adopted as training algorithms of the neural network model....
Saved in:
Main Authors: | , |
---|---|
Format: | Article |
Published: |
IEEE Catalog Number CFP1066c-CDR
2010
|
Subjects: | |
Online Access: | http://eprints.utp.edu.my/4215/1/cookiedetectresponse.jsp http://ieeexplore.ieee.org/xpls http://eprints.utp.edu.my/4215/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utp.eprints.4215 |
---|---|
record_format |
eprints |
spelling |
my.utp.eprints.42152017-01-19T08:23:57Z Multidimensional Minimization Training Algorithms for Steam Boiler Drum Level Trip Using Artificial Intelligence Monitoring System Ismail, F. B. Al-Kayiem, Hussain H. TJ Mechanical engineering and machinery This paper deals with the Fault Detection and Diagnosis of steam boiler drum low level by artificial Neural Networks using two different interpretation algorithms. The BFGS quasi-Newton (TRAINBFG) and Levenberg-Marquart (TRAINLV) have been adopted as training algorithms of the neural network model. Real site data was captured from a 3x700MWatt 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 for the neural networks is based on merging between theoretical analysis base and the plant operator experience. The merging procedure is described in the paper. Results are obtained from one hidden layer neural network and two hidden layers neural network structures, for both adopted algorithms. Comparisons have been made between the results from the two algorithms based on the Root Mean Square Error. The one hidden layer with one neuron using BFG training algorithm provides the best optimum neural network structure. Keywords Steam Boiler, Drum Level Trip, Fault Detection and Diagnosis(FDD), Artificial Neural Networks (ANN). IEEE Catalog Number CFP1066c-CDR 2010-06-17 Article PeerReviewed application/pdf http://eprints.utp.edu.my/4215/1/cookiedetectresponse.jsp http://ieeexplore.ieee.org/xpls Ismail, F. B. and Al-Kayiem, Hussain H. (2010) Multidimensional Minimization Training Algorithms for Steam Boiler Drum Level Trip Using Artificial Intelligence Monitoring System. Proceedings of the 3rd International Conference on Intelligent and Advanced Systems (ICIAS2010) . ISSN ISBN:978-1-4244-6624-5 http://eprints.utp.edu.my/4215/ |
institution |
Universiti Teknologi Petronas |
building |
UTP Resource Centre |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Petronas |
content_source |
UTP Institutional Repository |
url_provider |
http://eprints.utp.edu.my/ |
topic |
TJ Mechanical engineering and machinery |
spellingShingle |
TJ Mechanical engineering and machinery Ismail, F. B. Al-Kayiem, Hussain H. Multidimensional Minimization Training Algorithms for Steam Boiler Drum Level Trip Using Artificial Intelligence Monitoring System |
description |
This paper deals with the Fault Detection and Diagnosis of steam boiler drum low level by artificial Neural Networks using two different interpretation algorithms. The BFGS quasi-Newton (TRAINBFG) and Levenberg-Marquart (TRAINLV) have been adopted as training algorithms of the neural network model. Real site data was captured from a 3x700MWatt 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 for the neural networks is based on merging between theoretical analysis base and the plant operator experience. The merging procedure is described in the paper. Results are obtained from one hidden layer neural network and two hidden layers neural network structures, for both adopted algorithms. Comparisons have been made between the results from the two algorithms based on the Root Mean Square Error. The one hidden layer with one neuron using BFG training algorithm provides the best optimum neural network structure.
Keywords Steam Boiler, Drum Level Trip, Fault Detection and Diagnosis(FDD), Artificial Neural Networks (ANN).
|
format |
Article |
author |
Ismail, F. B. Al-Kayiem, Hussain H. |
author_facet |
Ismail, F. B. Al-Kayiem, Hussain H. |
author_sort |
Ismail, F. B. |
title |
Multidimensional Minimization Training Algorithms for Steam Boiler Drum Level Trip Using Artificial Intelligence Monitoring System |
title_short |
Multidimensional Minimization Training Algorithms for Steam Boiler Drum Level Trip Using Artificial Intelligence Monitoring System |
title_full |
Multidimensional Minimization Training Algorithms for Steam Boiler Drum Level Trip Using Artificial Intelligence Monitoring System |
title_fullStr |
Multidimensional Minimization Training Algorithms for Steam Boiler Drum Level Trip Using Artificial Intelligence Monitoring System |
title_full_unstemmed |
Multidimensional Minimization Training Algorithms for Steam Boiler Drum Level Trip Using Artificial Intelligence Monitoring System |
title_sort |
multidimensional minimization training algorithms for steam boiler drum level trip using artificial intelligence monitoring system |
publisher |
IEEE Catalog Number CFP1066c-CDR |
publishDate |
2010 |
url |
http://eprints.utp.edu.my/4215/1/cookiedetectresponse.jsp http://ieeexplore.ieee.org/xpls http://eprints.utp.edu.my/4215/ |
_version_ |
1738655326812504064 |
score |
13.19449 |