Development of an intelligent system for detection of exhaust gas temperature anomalies in gas turbines

A.D. Kenyon, V.M. Catterson, S.D.J. McArthur

Research output: Contribution to journalArticle

63 Downloads (Pure)

Abstract

An unplanned outage can be costly for a utility, and gas turbines are expensive pieces of equipment to repair or replace. It is therefore vital that anomalous behaviour is flagged before damage can occur that may cause a prolonged outage. An anomaly detection system is proposed for gas turbines to monitor the related parameters and raise alarms when anomalies are identified. The proposed system incorporates machine learning algorithms based on artificial neural networks (ANN). By using ANNs trained on normal plant behaviour, it is possible to identify anomalous behaviour by the high residuals between actual and predicted outputs. Within this paper, the data mining methodology is described and the process followed before arriving at the successful approach is documented. Results from testing the approach on an industrial case study are presented and, based on these results, areas for further development are identified. It is intended to deploy the system along with several other algorithms as part of a multi-agent system for plant-wide condition monitoring. This paper will focus on the design and testing of the developed anomaly detection system.
Original languageEnglish
JournalInsight: The Journal of the British Institute of Non-Destructive Testing
Volume52
Issue number8
Publication statusPublished - Aug 2010

Fingerprint

Intelligent systems
Exhaust gases
Outages
Gas turbines
Condition monitoring
Testing
Multi agent systems
Learning algorithms
Data mining
Learning systems
Repair
Neural networks
Temperature

Keywords

  • intelligent systems
  • detection
  • exhaust gas temperature
  • gas turbines

Cite this

@article{59d3574061ab4f83b775e41e8a9bdddf,
title = "Development of an intelligent system for detection of exhaust gas temperature anomalies in gas turbines",
abstract = "An unplanned outage can be costly for a utility, and gas turbines are expensive pieces of equipment to repair or replace. It is therefore vital that anomalous behaviour is flagged before damage can occur that may cause a prolonged outage. An anomaly detection system is proposed for gas turbines to monitor the related parameters and raise alarms when anomalies are identified. The proposed system incorporates machine learning algorithms based on artificial neural networks (ANN). By using ANNs trained on normal plant behaviour, it is possible to identify anomalous behaviour by the high residuals between actual and predicted outputs. Within this paper, the data mining methodology is described and the process followed before arriving at the successful approach is documented. Results from testing the approach on an industrial case study are presented and, based on these results, areas for further development are identified. It is intended to deploy the system along with several other algorithms as part of a multi-agent system for plant-wide condition monitoring. This paper will focus on the design and testing of the developed anomaly detection system.",
keywords = "intelligent systems, detection, exhaust gas temperature, gas turbines",
author = "A.D. Kenyon and V.M. Catterson and S.D.J. McArthur",
note = "Paper presented at CM 2010-MFPT 2010, the Seventh International Conference on Condition Monitoring and Machinery Failure Prevention Technologies, Stratford-upon-Avon, June 2010",
year = "2010",
month = "8",
language = "English",
volume = "52",
journal = "Insight: The Journal of the British Institute of Non-Destructive Testing",
issn = "1354-2575",
number = "8",

}

TY - JOUR

T1 - Development of an intelligent system for detection of exhaust gas temperature anomalies in gas turbines

AU - Kenyon, A.D.

AU - Catterson, V.M.

AU - McArthur, S.D.J.

N1 - Paper presented at CM 2010-MFPT 2010, the Seventh International Conference on Condition Monitoring and Machinery Failure Prevention Technologies, Stratford-upon-Avon, June 2010

PY - 2010/8

Y1 - 2010/8

N2 - An unplanned outage can be costly for a utility, and gas turbines are expensive pieces of equipment to repair or replace. It is therefore vital that anomalous behaviour is flagged before damage can occur that may cause a prolonged outage. An anomaly detection system is proposed for gas turbines to monitor the related parameters and raise alarms when anomalies are identified. The proposed system incorporates machine learning algorithms based on artificial neural networks (ANN). By using ANNs trained on normal plant behaviour, it is possible to identify anomalous behaviour by the high residuals between actual and predicted outputs. Within this paper, the data mining methodology is described and the process followed before arriving at the successful approach is documented. Results from testing the approach on an industrial case study are presented and, based on these results, areas for further development are identified. It is intended to deploy the system along with several other algorithms as part of a multi-agent system for plant-wide condition monitoring. This paper will focus on the design and testing of the developed anomaly detection system.

AB - An unplanned outage can be costly for a utility, and gas turbines are expensive pieces of equipment to repair or replace. It is therefore vital that anomalous behaviour is flagged before damage can occur that may cause a prolonged outage. An anomaly detection system is proposed for gas turbines to monitor the related parameters and raise alarms when anomalies are identified. The proposed system incorporates machine learning algorithms based on artificial neural networks (ANN). By using ANNs trained on normal plant behaviour, it is possible to identify anomalous behaviour by the high residuals between actual and predicted outputs. Within this paper, the data mining methodology is described and the process followed before arriving at the successful approach is documented. Results from testing the approach on an industrial case study are presented and, based on these results, areas for further development are identified. It is intended to deploy the system along with several other algorithms as part of a multi-agent system for plant-wide condition monitoring. This paper will focus on the design and testing of the developed anomaly detection system.

KW - intelligent systems

KW - detection

KW - exhaust gas temperature

KW - gas turbines

UR - http://www.bindt.org/Publications/Insight_Journal

M3 - Article

VL - 52

JO - Insight: The Journal of the British Institute of Non-Destructive Testing

JF - Insight: The Journal of the British Institute of Non-Destructive Testing

SN - 1354-2575

IS - 8

ER -