Artificial intelligent system for steam boiler diagnosis based on superheater monitoring

Firas Basim Ismail, Hussain H. Al-Kayiem

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Steam Boilers are important equipment in power plants and the boilers trip may lead to the entire plant shutdown. To maintain performance in normal and safe operation conditions, detecting of the possible boiler trips in critical time is crucial. Artificial Neural network applications for steam boilers trips are developed designed and parameterized. In this present study, the developed systems are a fault detection and diagnosis neural network model. Some priori knowledge of the demands in network topology for specific application cases is required by this approach, so that the infinite search space of the problem is limited to a reasonable degree. Both one-hidden-layer and two-hidden-layers network architectures are explored using neural network with trial and error approach. 32 Boiler parameters are identified for the boiler FDDNN analysis. The power plant experience has been imposed to select the most important parameters related to the superheated monitoring contribution on the boiler trip.

Original languageEnglish
Pages (from-to)1566-1572
Number of pages7
JournalJournal of Applied Sciences
Volume11
Issue number9
DOIs
Publication statusPublished - 06 May 2011

Fingerprint

Superheaters
Intelligent systems
Boilers
Steam
Monitoring
Neural networks
Power plants
Plant shutdowns
Network architecture
Fault detection
Failure analysis
Topology

All Science Journal Classification (ASJC) codes

  • General

Cite this

@article{cb0dd3df56764085b97306256eb19563,
title = "Artificial intelligent system for steam boiler diagnosis based on superheater monitoring",
abstract = "Steam Boilers are important equipment in power plants and the boilers trip may lead to the entire plant shutdown. To maintain performance in normal and safe operation conditions, detecting of the possible boiler trips in critical time is crucial. Artificial Neural network applications for steam boilers trips are developed designed and parameterized. In this present study, the developed systems are a fault detection and diagnosis neural network model. Some priori knowledge of the demands in network topology for specific application cases is required by this approach, so that the infinite search space of the problem is limited to a reasonable degree. Both one-hidden-layer and two-hidden-layers network architectures are explored using neural network with trial and error approach. 32 Boiler parameters are identified for the boiler FDDNN analysis. The power plant experience has been imposed to select the most important parameters related to the superheated monitoring contribution on the boiler trip.",
author = "Ismail, {Firas Basim} and Al-Kayiem, {Hussain H.}",
year = "2011",
month = "5",
day = "6",
doi = "10.3923/jas.2011.1566.1572",
language = "English",
volume = "11",
pages = "1566--1572",
journal = "Journal of Applied Sciences",
issn = "1812-5654",
publisher = "Asian Network for Scientific Information",
number = "9",

}

Artificial intelligent system for steam boiler diagnosis based on superheater monitoring. / Ismail, Firas Basim; Al-Kayiem, Hussain H.

In: Journal of Applied Sciences, Vol. 11, No. 9, 06.05.2011, p. 1566-1572.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Artificial intelligent system for steam boiler diagnosis based on superheater monitoring

AU - Ismail, Firas Basim

AU - Al-Kayiem, Hussain H.

PY - 2011/5/6

Y1 - 2011/5/6

N2 - Steam Boilers are important equipment in power plants and the boilers trip may lead to the entire plant shutdown. To maintain performance in normal and safe operation conditions, detecting of the possible boiler trips in critical time is crucial. Artificial Neural network applications for steam boilers trips are developed designed and parameterized. In this present study, the developed systems are a fault detection and diagnosis neural network model. Some priori knowledge of the demands in network topology for specific application cases is required by this approach, so that the infinite search space of the problem is limited to a reasonable degree. Both one-hidden-layer and two-hidden-layers network architectures are explored using neural network with trial and error approach. 32 Boiler parameters are identified for the boiler FDDNN analysis. The power plant experience has been imposed to select the most important parameters related to the superheated monitoring contribution on the boiler trip.

AB - Steam Boilers are important equipment in power plants and the boilers trip may lead to the entire plant shutdown. To maintain performance in normal and safe operation conditions, detecting of the possible boiler trips in critical time is crucial. Artificial Neural network applications for steam boilers trips are developed designed and parameterized. In this present study, the developed systems are a fault detection and diagnosis neural network model. Some priori knowledge of the demands in network topology for specific application cases is required by this approach, so that the infinite search space of the problem is limited to a reasonable degree. Both one-hidden-layer and two-hidden-layers network architectures are explored using neural network with trial and error approach. 32 Boiler parameters are identified for the boiler FDDNN analysis. The power plant experience has been imposed to select the most important parameters related to the superheated monitoring contribution on the boiler trip.

UR - http://www.scopus.com/inward/record.url?scp=79955551656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955551656&partnerID=8YFLogxK

U2 - 10.3923/jas.2011.1566.1572

DO - 10.3923/jas.2011.1566.1572

M3 - Article

VL - 11

SP - 1566

EP - 1572

JO - Journal of Applied Sciences

JF - Journal of Applied Sciences

SN - 1812-5654

IS - 9

ER -