Online conditional anomaly detection in multivariate data for transformer monitoring

Victoria M. Catterson, Stephen D. J. McArthur, Graham Moss

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

Retrofitting condition monitoring systems to aging plant can be problematic, since the particular signature of normal behavior will vary from unit to unit. This paper describes a technique for anomaly detection within the context of the conditions experienced by an in-service transformer, such as loading, seasonal weather, and network configuration. The aim is to model the aged but normal behavior for a given transformer, while reducing the potential for anomalies to be erroneously detected. The paper describes how this technique has been applied to two transmission transformers in the U.K. A case study of 12 months of data is given, with detailed analysis of anomalies detected during that time.
LanguageEnglish
Pages2556–2564
Number of pages9
JournalIEEE Transactions on Power Delivery
Volume25
Issue number4
DOIs
Publication statusPublished - 1 Oct 2010

Fingerprint

Retrofitting
Condition monitoring
Aging of materials
Monitoring

Keywords

  • anomaly detection
  • multivariate data
  • transformer monitoring
  • monitoring
  • power transformers
  • fault diagnosis

Cite this

@article{64e5440689764e23abd7ce87d9e19360,
title = "Online conditional anomaly detection in multivariate data for transformer monitoring",
abstract = "Retrofitting condition monitoring systems to aging plant can be problematic, since the particular signature of normal behavior will vary from unit to unit. This paper describes a technique for anomaly detection within the context of the conditions experienced by an in-service transformer, such as loading, seasonal weather, and network configuration. The aim is to model the aged but normal behavior for a given transformer, while reducing the potential for anomalies to be erroneously detected. The paper describes how this technique has been applied to two transmission transformers in the U.K. A case study of 12 months of data is given, with detailed analysis of anomalies detected during that time.",
keywords = "anomaly detection, multivariate data, transformer monitoring, monitoring, power transformers, fault diagnosis",
author = "Catterson, {Victoria M.} and McArthur, {Stephen D. J.} and Graham Moss",
year = "2010",
month = "10",
day = "1",
doi = "10.1109/TPWRD.2010.2049754",
language = "English",
volume = "25",
pages = "2556–2564",
journal = "IEEE Transactions on Power Delivery",
issn = "0885-8977",
number = "4",

}

Online conditional anomaly detection in multivariate data for transformer monitoring. / Catterson, Victoria M.; McArthur, Stephen D. J.; Moss, Graham.

In: IEEE Transactions on Power Delivery, Vol. 25, No. 4, 01.10.2010, p. 2556–2564.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Online conditional anomaly detection in multivariate data for transformer monitoring

AU - Catterson, Victoria M.

AU - McArthur, Stephen D. J.

AU - Moss, Graham

PY - 2010/10/1

Y1 - 2010/10/1

N2 - Retrofitting condition monitoring systems to aging plant can be problematic, since the particular signature of normal behavior will vary from unit to unit. This paper describes a technique for anomaly detection within the context of the conditions experienced by an in-service transformer, such as loading, seasonal weather, and network configuration. The aim is to model the aged but normal behavior for a given transformer, while reducing the potential for anomalies to be erroneously detected. The paper describes how this technique has been applied to two transmission transformers in the U.K. A case study of 12 months of data is given, with detailed analysis of anomalies detected during that time.

AB - Retrofitting condition monitoring systems to aging plant can be problematic, since the particular signature of normal behavior will vary from unit to unit. This paper describes a technique for anomaly detection within the context of the conditions experienced by an in-service transformer, such as loading, seasonal weather, and network configuration. The aim is to model the aged but normal behavior for a given transformer, while reducing the potential for anomalies to be erroneously detected. The paper describes how this technique has been applied to two transmission transformers in the U.K. A case study of 12 months of data is given, with detailed analysis of anomalies detected during that time.

KW - anomaly detection

KW - multivariate data

KW - transformer monitoring

KW - monitoring

KW - power transformers

KW - fault diagnosis

UR - http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=61

U2 - 10.1109/TPWRD.2010.2049754

DO - 10.1109/TPWRD.2010.2049754

M3 - Article

VL - 25

SP - 2556

EP - 2564

JO - IEEE Transactions on Power Delivery

T2 - IEEE Transactions on Power Delivery

JF - IEEE Transactions on Power Delivery

SN - 0885-8977

IS - 4

ER -