Power transformer dissolved gas analysis through Bayesian networks and hypothesis testing

Jose Ignacio Aizpurua, Victoria M. Catterson, Brian G. Stewart, Stephen D. J. McArthur, Brandon Lambert, Bismark Ampofo, Gavin Pereira, James G. Cross

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Accurate diagnosis of power transformers is critical for the reliable and cost-effective operation of the power grid. Presently there are a range of methods and analytical models for transformer fault diagnosis based on dissolved gas analysis. However, these methods give conflicting results and they are not able to generate uncertainty information associated with the diagnostics outcome. In this situation it is not always clear which model is the most accurate. This paper presents a novel multiclass probabilistic diagnosis framework for dissolved gas analysis based on Bayesian networks and hypothesis testing. Bayesian network models embed expert knowledge, learn patterns from data and infer the uncertainty associated with the diagnostics outcome, and hypothesis testing aids in the data selection process. The effectiveness of the proposed framework is validated using the IEC TC 10 dataset and is shown to have a maximum diagnosis accuracy of 88.9%.
LanguageEnglish
Pages494-506
Number of pages12
JournalIEEE Transactions on Dielectrics and Electrical Insulation
Volume25
Issue number2
DOIs
Publication statusPublished - 19 Apr 2018

Fingerprint

Gas fuel analysis
Power transformers
Bayesian networks
Testing
Failure analysis
Analytical models
Costs
Uncertainty

Keywords

  • dissolved gas analysis
  • transformer diagnosis
  • condition monitoring
  • Bayesian networks
  • normality test
  • probabilistic diagnostics

Cite this

Aizpurua, Jose Ignacio ; Catterson, Victoria M. ; Stewart, Brian G. ; McArthur, Stephen D. J. ; Lambert, Brandon ; Ampofo, Bismark ; Pereira, Gavin ; Cross, James G. / Power transformer dissolved gas analysis through Bayesian networks and hypothesis testing. In: IEEE Transactions on Dielectrics and Electrical Insulation. 2018 ; Vol. 25, No. 2. pp. 494-506.
@article{fcf3eed5ce65467782ebb1efb55f2f10,
title = "Power transformer dissolved gas analysis through Bayesian networks and hypothesis testing",
abstract = "Accurate diagnosis of power transformers is critical for the reliable and cost-effective operation of the power grid. Presently there are a range of methods and analytical models for transformer fault diagnosis based on dissolved gas analysis. However, these methods give conflicting results and they are not able to generate uncertainty information associated with the diagnostics outcome. In this situation it is not always clear which model is the most accurate. This paper presents a novel multiclass probabilistic diagnosis framework for dissolved gas analysis based on Bayesian networks and hypothesis testing. Bayesian network models embed expert knowledge, learn patterns from data and infer the uncertainty associated with the diagnostics outcome, and hypothesis testing aids in the data selection process. The effectiveness of the proposed framework is validated using the IEC TC 10 dataset and is shown to have a maximum diagnosis accuracy of 88.9{\%}.",
keywords = "dissolved gas analysis, transformer diagnosis, condition monitoring, Bayesian networks, normality test, probabilistic diagnostics",
author = "Aizpurua, {Jose Ignacio} and Catterson, {Victoria M.} and Stewart, {Brian G.} and McArthur, {Stephen D. J.} and Brandon Lambert and Bismark Ampofo and Gavin Pereira and Cross, {James G.}",
note = "{\circledC} 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2018",
month = "4",
day = "19",
doi = "10.1109/TDEI.2018.006766",
language = "English",
volume = "25",
pages = "494--506",
journal = "IEEE Transactions on Dielectrics and Electrical Insulation",
issn = "1070-9878",
number = "2",

}

Power transformer dissolved gas analysis through Bayesian networks and hypothesis testing. / Aizpurua, Jose Ignacio; Catterson, Victoria M.; Stewart, Brian G.; McArthur, Stephen D. J.; Lambert, Brandon; Ampofo, Bismark; Pereira, Gavin; Cross, James G.

In: IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 25, No. 2, 19.04.2018, p. 494-506.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Power transformer dissolved gas analysis through Bayesian networks and hypothesis testing

AU - Aizpurua, Jose Ignacio

AU - Catterson, Victoria M.

AU - Stewart, Brian G.

AU - McArthur, Stephen D. J.

AU - Lambert, Brandon

AU - Ampofo, Bismark

AU - Pereira, Gavin

AU - Cross, James G.

N1 - © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2018/4/19

Y1 - 2018/4/19

N2 - Accurate diagnosis of power transformers is critical for the reliable and cost-effective operation of the power grid. Presently there are a range of methods and analytical models for transformer fault diagnosis based on dissolved gas analysis. However, these methods give conflicting results and they are not able to generate uncertainty information associated with the diagnostics outcome. In this situation it is not always clear which model is the most accurate. This paper presents a novel multiclass probabilistic diagnosis framework for dissolved gas analysis based on Bayesian networks and hypothesis testing. Bayesian network models embed expert knowledge, learn patterns from data and infer the uncertainty associated with the diagnostics outcome, and hypothesis testing aids in the data selection process. The effectiveness of the proposed framework is validated using the IEC TC 10 dataset and is shown to have a maximum diagnosis accuracy of 88.9%.

AB - Accurate diagnosis of power transformers is critical for the reliable and cost-effective operation of the power grid. Presently there are a range of methods and analytical models for transformer fault diagnosis based on dissolved gas analysis. However, these methods give conflicting results and they are not able to generate uncertainty information associated with the diagnostics outcome. In this situation it is not always clear which model is the most accurate. This paper presents a novel multiclass probabilistic diagnosis framework for dissolved gas analysis based on Bayesian networks and hypothesis testing. Bayesian network models embed expert knowledge, learn patterns from data and infer the uncertainty associated with the diagnostics outcome, and hypothesis testing aids in the data selection process. The effectiveness of the proposed framework is validated using the IEC TC 10 dataset and is shown to have a maximum diagnosis accuracy of 88.9%.

KW - dissolved gas analysis

KW - transformer diagnosis

KW - condition monitoring

KW - Bayesian networks

KW - normality test

KW - probabilistic diagnostics

UR - http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=94

U2 - 10.1109/TDEI.2018.006766

DO - 10.1109/TDEI.2018.006766

M3 - Article

VL - 25

SP - 494

EP - 506

JO - IEEE Transactions on Dielectrics and Electrical Insulation

T2 - IEEE Transactions on Dielectrics and Electrical Insulation

JF - IEEE Transactions on Dielectrics and Electrical Insulation

SN - 1070-9878

IS - 2

ER -