Development and implementation of intelligent condition monitoring system for steam turbine trips

Firas Basim Ismail, Rahmat Izaizi B. Ismail, Pin Jern Ker

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Sustainable initiatives are increasingly getting attention from the research community and one of the aspects in achieving sustainable development is to enhance the efficiency and optimize the technology used to generate and utilize energy. Fault detection and diagnosis is a critical optimization factor in power generation sector. Early faults detection ensures that correct mitigation measures can be taken, whilst false alarms should be eschewed to avoid unnecessary cost of operation, interruption and downtime. Pure Intelligent Condition Monitoring System (ICMS) represented by artificial neural network (ANN), developed by training the network with real operational data, may be proven to be useful for realtime monitoring of a power plant. In this work, an integrated data preparation method has been proposed and the development of ANN models to detect steam turbine trip for Malaysia MNJ power station will be presented. Two models adopting feed forward with back propagation ANN were trained with real data from the MNJ station. The developed models were capable of detecting the specific trip within a period of 32 minutes before the actual trip occurrence, which is considered to provide good and satisfactory early fault detection.

Original languageEnglish
Pages (from-to)14275-14283
Number of pages9
JournalARPN Journal of Engineering and Applied Sciences
Volume11
Issue number24
Publication statusPublished - 01 Jan 2016

Fingerprint

Condition monitoring
Steam turbines
Fault detection
Neural networks
Backpropagation
Failure analysis
Power generation
Sustainable development
Power plants
Monitoring
Costs

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

@article{1c5c2e4d11304a31bbeb7ec6ca4ebe51,
title = "Development and implementation of intelligent condition monitoring system for steam turbine trips",
abstract = "Sustainable initiatives are increasingly getting attention from the research community and one of the aspects in achieving sustainable development is to enhance the efficiency and optimize the technology used to generate and utilize energy. Fault detection and diagnosis is a critical optimization factor in power generation sector. Early faults detection ensures that correct mitigation measures can be taken, whilst false alarms should be eschewed to avoid unnecessary cost of operation, interruption and downtime. Pure Intelligent Condition Monitoring System (ICMS) represented by artificial neural network (ANN), developed by training the network with real operational data, may be proven to be useful for realtime monitoring of a power plant. In this work, an integrated data preparation method has been proposed and the development of ANN models to detect steam turbine trip for Malaysia MNJ power station will be presented. Two models adopting feed forward with back propagation ANN were trained with real data from the MNJ station. The developed models were capable of detecting the specific trip within a period of 32 minutes before the actual trip occurrence, which is considered to provide good and satisfactory early fault detection.",
author = "Ismail, {Firas Basim} and Ismail, {Rahmat Izaizi B.} and Ker, {Pin Jern}",
year = "2016",
month = "1",
day = "1",
language = "English",
volume = "11",
pages = "14275--14283",
journal = "ARPN Journal of Engineering and Applied Sciences",
issn = "1819-6608",
publisher = "Asian Research Publishing Network (ARPN)",
number = "24",

}

Development and implementation of intelligent condition monitoring system for steam turbine trips. / Ismail, Firas Basim; Ismail, Rahmat Izaizi B.; Ker, Pin Jern.

In: ARPN Journal of Engineering and Applied Sciences, Vol. 11, No. 24, 01.01.2016, p. 14275-14283.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Development and implementation of intelligent condition monitoring system for steam turbine trips

AU - Ismail, Firas Basim

AU - Ismail, Rahmat Izaizi B.

AU - Ker, Pin Jern

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Sustainable initiatives are increasingly getting attention from the research community and one of the aspects in achieving sustainable development is to enhance the efficiency and optimize the technology used to generate and utilize energy. Fault detection and diagnosis is a critical optimization factor in power generation sector. Early faults detection ensures that correct mitigation measures can be taken, whilst false alarms should be eschewed to avoid unnecessary cost of operation, interruption and downtime. Pure Intelligent Condition Monitoring System (ICMS) represented by artificial neural network (ANN), developed by training the network with real operational data, may be proven to be useful for realtime monitoring of a power plant. In this work, an integrated data preparation method has been proposed and the development of ANN models to detect steam turbine trip for Malaysia MNJ power station will be presented. Two models adopting feed forward with back propagation ANN were trained with real data from the MNJ station. The developed models were capable of detecting the specific trip within a period of 32 minutes before the actual trip occurrence, which is considered to provide good and satisfactory early fault detection.

AB - Sustainable initiatives are increasingly getting attention from the research community and one of the aspects in achieving sustainable development is to enhance the efficiency and optimize the technology used to generate and utilize energy. Fault detection and diagnosis is a critical optimization factor in power generation sector. Early faults detection ensures that correct mitigation measures can be taken, whilst false alarms should be eschewed to avoid unnecessary cost of operation, interruption and downtime. Pure Intelligent Condition Monitoring System (ICMS) represented by artificial neural network (ANN), developed by training the network with real operational data, may be proven to be useful for realtime monitoring of a power plant. In this work, an integrated data preparation method has been proposed and the development of ANN models to detect steam turbine trip for Malaysia MNJ power station will be presented. Two models adopting feed forward with back propagation ANN were trained with real data from the MNJ station. The developed models were capable of detecting the specific trip within a period of 32 minutes before the actual trip occurrence, which is considered to provide good and satisfactory early fault detection.

UR - http://www.scopus.com/inward/record.url?scp=85009160454&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009160454&partnerID=8YFLogxK

M3 - Article

VL - 11

SP - 14275

EP - 14283

JO - ARPN Journal of Engineering and Applied Sciences

JF - ARPN Journal of Engineering and Applied Sciences

SN - 1819-6608

IS - 24

ER -