The use of hidden Markov models for anomaly detection in nuclear core condition monitoring

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Unplanned outages can be especially costly for generation companies operating nuclear facilities. Early detection of deviations from expected performance through condition monitoring can allow a more proactive and managed approach to dealing with ageing plant. This paper proposes an anomaly detection framework incorporating the use of the Hidden Markov Model (HMM) to support the analysis of nuclear reactor core condition monitoring data. Fuel Grab Load Trace (FGLT) data gathered within the UK during routine refueling operations has been seen to provide information relating to the condition of the graphite bricks that comprise the core. Although manual analysis of this data is time consuming and requires considerable expertise, this paper demonstrates how techniques such as the HMM can provide analysis support by providing a benchmark model of expected behavior against which future refueling events may be compared. The presence of anomalous behavior in candidate traces is inferred through the underlying statistical foundation of the HMM which gives an observation likelihood averaged along the length of the input sequence. Using this likelihood measure, the engineer can be alerted to anomalous behaviour, indicating data which might require further detailed examination. It is proposed that this data analysis technique is used in conjunction with other intelligent analysis techniques currently employed to analyse FGLT to provide a greater confidence measure in detecting anomalous behaviour from FGLT data.
LanguageEnglish
Pages453-461
Number of pages9
JournalIEEE Transactions on Nuclear Science
Volume56
Issue number2
DOIs
Publication statusPublished - Apr 2009

Fingerprint

Condition monitoring
Hidden Markov models
anomalies
refueling
Reactor cores
Brick
Outages
reactor cores
bricks
nuclear reactors
Graphite
Aging of materials
engineers
Engineers
confidence
graphite
examination
deviation
Industry

Keywords

  • Markov models
  • nuclear core condition monitoring
  • condition monitoring

Cite this

@article{281a656fc17547378422196c36d3226b,
title = "The use of hidden Markov models for anomaly detection in nuclear core condition monitoring",
abstract = "Unplanned outages can be especially costly for generation companies operating nuclear facilities. Early detection of deviations from expected performance through condition monitoring can allow a more proactive and managed approach to dealing with ageing plant. This paper proposes an anomaly detection framework incorporating the use of the Hidden Markov Model (HMM) to support the analysis of nuclear reactor core condition monitoring data. Fuel Grab Load Trace (FGLT) data gathered within the UK during routine refueling operations has been seen to provide information relating to the condition of the graphite bricks that comprise the core. Although manual analysis of this data is time consuming and requires considerable expertise, this paper demonstrates how techniques such as the HMM can provide analysis support by providing a benchmark model of expected behavior against which future refueling events may be compared. The presence of anomalous behavior in candidate traces is inferred through the underlying statistical foundation of the HMM which gives an observation likelihood averaged along the length of the input sequence. Using this likelihood measure, the engineer can be alerted to anomalous behaviour, indicating data which might require further detailed examination. It is proposed that this data analysis technique is used in conjunction with other intelligent analysis techniques currently employed to analyse FGLT to provide a greater confidence measure in detecting anomalous behaviour from FGLT data.",
keywords = "Markov models, nuclear core condition monitoring , condition monitoring",
author = "B. Stephen and G.M. West and S.J. Galloway and S.D.J. McArthur and J.R. McDonald and D. Towle",
year = "2009",
month = "4",
doi = "10.1109/TNS.2008.2011904",
language = "English",
volume = "56",
pages = "453--461",
journal = "IEEE Transactions on Nuclear Science",
issn = "0018-9499",
number = "2",

}

TY - JOUR

T1 - The use of hidden Markov models for anomaly detection in nuclear core condition monitoring

AU - Stephen, B.

AU - West, G.M.

AU - Galloway, S.J.

AU - McArthur, S.D.J.

AU - McDonald, J.R.

AU - Towle, D.

PY - 2009/4

Y1 - 2009/4

N2 - Unplanned outages can be especially costly for generation companies operating nuclear facilities. Early detection of deviations from expected performance through condition monitoring can allow a more proactive and managed approach to dealing with ageing plant. This paper proposes an anomaly detection framework incorporating the use of the Hidden Markov Model (HMM) to support the analysis of nuclear reactor core condition monitoring data. Fuel Grab Load Trace (FGLT) data gathered within the UK during routine refueling operations has been seen to provide information relating to the condition of the graphite bricks that comprise the core. Although manual analysis of this data is time consuming and requires considerable expertise, this paper demonstrates how techniques such as the HMM can provide analysis support by providing a benchmark model of expected behavior against which future refueling events may be compared. The presence of anomalous behavior in candidate traces is inferred through the underlying statistical foundation of the HMM which gives an observation likelihood averaged along the length of the input sequence. Using this likelihood measure, the engineer can be alerted to anomalous behaviour, indicating data which might require further detailed examination. It is proposed that this data analysis technique is used in conjunction with other intelligent analysis techniques currently employed to analyse FGLT to provide a greater confidence measure in detecting anomalous behaviour from FGLT data.

AB - Unplanned outages can be especially costly for generation companies operating nuclear facilities. Early detection of deviations from expected performance through condition monitoring can allow a more proactive and managed approach to dealing with ageing plant. This paper proposes an anomaly detection framework incorporating the use of the Hidden Markov Model (HMM) to support the analysis of nuclear reactor core condition monitoring data. Fuel Grab Load Trace (FGLT) data gathered within the UK during routine refueling operations has been seen to provide information relating to the condition of the graphite bricks that comprise the core. Although manual analysis of this data is time consuming and requires considerable expertise, this paper demonstrates how techniques such as the HMM can provide analysis support by providing a benchmark model of expected behavior against which future refueling events may be compared. The presence of anomalous behavior in candidate traces is inferred through the underlying statistical foundation of the HMM which gives an observation likelihood averaged along the length of the input sequence. Using this likelihood measure, the engineer can be alerted to anomalous behaviour, indicating data which might require further detailed examination. It is proposed that this data analysis technique is used in conjunction with other intelligent analysis techniques currently employed to analyse FGLT to provide a greater confidence measure in detecting anomalous behaviour from FGLT data.

KW - Markov models

KW - nuclear core condition monitoring

KW - condition monitoring

U2 - 10.1109/TNS.2008.2011904

DO - 10.1109/TNS.2008.2011904

M3 - Article

VL - 56

SP - 453

EP - 461

JO - IEEE Transactions on Nuclear Science

T2 - IEEE Transactions on Nuclear Science

JF - IEEE Transactions on Nuclear Science

SN - 0018-9499

IS - 2

ER -