Early tube leak detection system for steam boiler at KEV power plant

Firas Basim Ismail, Deshvin Singh, N. Maisurah, Abu Bakar Haji Musa

Research output: Contribution to journalConference article

1 Citation (Scopus)

Abstract

Tube leakage in boilers has been a major contribution to trips which eventually leads to power plant shut downs. Training of network and developing artificial neural network (ANN) models are essential in fault detection in critically large systems. This research focusses on the ANN modelling through training and validation of real data acquired from a sub-critical boiler unit. The artificial neural network (ANN) was used to develop a compatible model and to evaluate the working properties and behaviour of boiler. The training and validation of real data has been applied using the feed-forward with back-propagation (BP). The right combination of number of neurons, number of hidden layers, training algorithms and training functions was run to achieve the best ANN model with lowest error. The ANN was trained and validated using real site data acquired from a coal fired power plant in Malaysia. The results showed that the Neural Network (NN) with one hidden layers performed better than two hidden layer using feed-forward back-propagation network. The outcome from this study give us the best ANN model which eventually allows for early detection of boiler tube leakages, and forecast of a trip before the real shutdown. This will eventually reduce shutdowns in power plants.

Original languageEnglish
Article number00006
JournalMATEC Web of Conferences
Volume74
DOIs
Publication statusPublished - 29 Aug 2016
Event3rd International Conference on Mechanical Engineering Research, ICMER 2015 - Kuantan, Pahang, Malaysia
Duration: 18 Aug 201519 Aug 2015

Fingerprint

Leak detection
Steam
Boilers
Power plants
Neural networks
Plant shutdowns
Backpropagation
Coal
Fault detection
Neurons

All Science Journal Classification (ASJC) codes

  • Chemistry(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

@article{f4b08fe2466243969219b114a2c45227,
title = "Early tube leak detection system for steam boiler at KEV power plant",
abstract = "Tube leakage in boilers has been a major contribution to trips which eventually leads to power plant shut downs. Training of network and developing artificial neural network (ANN) models are essential in fault detection in critically large systems. This research focusses on the ANN modelling through training and validation of real data acquired from a sub-critical boiler unit. The artificial neural network (ANN) was used to develop a compatible model and to evaluate the working properties and behaviour of boiler. The training and validation of real data has been applied using the feed-forward with back-propagation (BP). The right combination of number of neurons, number of hidden layers, training algorithms and training functions was run to achieve the best ANN model with lowest error. The ANN was trained and validated using real site data acquired from a coal fired power plant in Malaysia. The results showed that the Neural Network (NN) with one hidden layers performed better than two hidden layer using feed-forward back-propagation network. The outcome from this study give us the best ANN model which eventually allows for early detection of boiler tube leakages, and forecast of a trip before the real shutdown. This will eventually reduce shutdowns in power plants.",
author = "Ismail, {Firas Basim} and Deshvin Singh and N. Maisurah and {Haji Musa}, {Abu Bakar}",
year = "2016",
month = "8",
day = "29",
doi = "10.1051/matecconf/20167400006",
language = "English",
volume = "74",
journal = "MATEC Web of Conferences",
issn = "2261-236X",
publisher = "EDP Sciences",

}

Early tube leak detection system for steam boiler at KEV power plant. / Ismail, Firas Basim; Singh, Deshvin; Maisurah, N.; Haji Musa, Abu Bakar.

In: MATEC Web of Conferences, Vol. 74, 00006, 29.08.2016.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Early tube leak detection system for steam boiler at KEV power plant

AU - Ismail, Firas Basim

AU - Singh, Deshvin

AU - Maisurah, N.

AU - Haji Musa, Abu Bakar

PY - 2016/8/29

Y1 - 2016/8/29

N2 - Tube leakage in boilers has been a major contribution to trips which eventually leads to power plant shut downs. Training of network and developing artificial neural network (ANN) models are essential in fault detection in critically large systems. This research focusses on the ANN modelling through training and validation of real data acquired from a sub-critical boiler unit. The artificial neural network (ANN) was used to develop a compatible model and to evaluate the working properties and behaviour of boiler. The training and validation of real data has been applied using the feed-forward with back-propagation (BP). The right combination of number of neurons, number of hidden layers, training algorithms and training functions was run to achieve the best ANN model with lowest error. The ANN was trained and validated using real site data acquired from a coal fired power plant in Malaysia. The results showed that the Neural Network (NN) with one hidden layers performed better than two hidden layer using feed-forward back-propagation network. The outcome from this study give us the best ANN model which eventually allows for early detection of boiler tube leakages, and forecast of a trip before the real shutdown. This will eventually reduce shutdowns in power plants.

AB - Tube leakage in boilers has been a major contribution to trips which eventually leads to power plant shut downs. Training of network and developing artificial neural network (ANN) models are essential in fault detection in critically large systems. This research focusses on the ANN modelling through training and validation of real data acquired from a sub-critical boiler unit. The artificial neural network (ANN) was used to develop a compatible model and to evaluate the working properties and behaviour of boiler. The training and validation of real data has been applied using the feed-forward with back-propagation (BP). The right combination of number of neurons, number of hidden layers, training algorithms and training functions was run to achieve the best ANN model with lowest error. The ANN was trained and validated using real site data acquired from a coal fired power plant in Malaysia. The results showed that the Neural Network (NN) with one hidden layers performed better than two hidden layer using feed-forward back-propagation network. The outcome from this study give us the best ANN model which eventually allows for early detection of boiler tube leakages, and forecast of a trip before the real shutdown. This will eventually reduce shutdowns in power plants.

UR - http://www.scopus.com/inward/record.url?scp=84987790060&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84987790060&partnerID=8YFLogxK

U2 - 10.1051/matecconf/20167400006

DO - 10.1051/matecconf/20167400006

M3 - Conference article

VL - 74

JO - MATEC Web of Conferences

JF - MATEC Web of Conferences

SN - 2261-236X

M1 - 00006

ER -