Improving the accuracy of transformer DGA diagnosis in the presence of conflicting evidence

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

doi:10.1109/EIC.2017.8004698

Improving the accuracy of transformer DGA diagnosis in the presence of conflicting evidence

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

Electronic And Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

4 Citations (Scopus)

84 Downloads (Pure)

Abstract

Transformers are critical assets for the reliable and cost-effective operation of the power grid. Transformers may fail if condition monitoring does not identify degraded conditions in time. Dissolved Gas Analysis (DGA) focuses on the examination of the dissolved gasses in the transformer oil and there exist different methods for transformer fault diagnosis based on different analyses of the gassing levels. However, these methods can give conflicting results, and it is not always clear which model is most accurate in a given situation. This paper presents a novel evidence combination framework for DGA based on Bayesian networks. Bayesian network models embed expert knowledge along with learned data patterns and evidence combination which aids in the consistency of analysis. The effectiveness of the proposed framework is validated using the IEC TC 10 dataset with a maximum diagnosis accuracy of 88.3%.

Original language	English
Title of host publication	2017 IEEE Electrical Insulation Conference (EIC)
Place of Publication	Piscataway, NJ
Publisher	IEEE
Number of pages	4
ISBN (Print)	9781509039654
DOIs	https://doi.org/10.1109/EIC.2017.8004698
Publication status	Published - 18 Aug 2017
Event	IEEE Electrical Insulation Conference 2017 - Sheraton, Baltimore, United States Duration: 11 Jun 2017 → 14 Jun 2017 http://electricalinsulationconference.com/

Conference

Conference	IEEE Electrical Insulation Conference 2017
Abbreviated title	EIC 2017
Country/Territory	United States
City	Baltimore
Period	11/06/17 → 14/06/17
Internet address	http://electricalinsulationconference.com/

Keywords

dissolved gas analysis
DGA
transformer diagnosis
condition monitoring
Bayesian networks
evidence combination
ensembles

Access to Document

10.1109/EIC.2017.8004698

Aizpurua-etal-EIC-2017-Improving-the-accuracy-of-transformer-DGA-diagnosisAccepted author manuscript, 404 KB

4 Citations
1 Article

Improved power transformer condition monitoring under uncertainty through soft computing and probabilistic health index
Aizpurua, J. I., Stewart, B. G., McArthur, S. D. J., Lambert, B., Cross, J. G. & Catterson, V. M., 8 Jun 2019, In: Applied Soft Computing. 85, 15 p., 105530.
Research output: Contribution to journal › Article › peer-review

Open Access
File
6 Citations (Scopus)

111 Downloads (Pure)

Cite this

@inproceedings{1e4cce6ada084dd790ec483ff9c019a7,

title = "Improving the accuracy of transformer DGA diagnosis in the presence of conflicting evidence",

abstract = "Transformers are critical assets for the reliable and cost-effective operation of the power grid. Transformers may fail if condition monitoring does not identify degraded conditions in time. Dissolved Gas Analysis (DGA) focuses on the examination of the dissolved gasses in the transformer oil and there exist different methods for transformer fault diagnosis based on different analyses of the gassing levels. However, these methods can give conflicting results, and it is not always clear which model is most accurate in a given situation. This paper presents a novel evidence combination framework for DGA based on Bayesian networks. Bayesian network models embed expert knowledge along with learned data patterns and evidence combination which aids in the consistency of analysis. The effectiveness of the proposed framework is validated using the IEC TC 10 dataset with a maximum diagnosis accuracy of 88.3%.",

keywords = "dissolved gas analysis, DGA, transformer diagnosis, condition monitoring, Bayesian networks, evidence combination, ensembles",

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 = "{\textcopyright} 2017 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; IEEE Electrical Insulation Conference 2017, EIC 2017 ; Conference date: 11-06-2017 Through 14-06-2017",

year = "2017",

month = aug,

day = "18",

doi = "10.1109/EIC.2017.8004698",

language = "English",

isbn = "9781509039654",

booktitle = "2017 IEEE Electrical Insulation Conference (EIC)",

publisher = "IEEE",

url = "http://electricalinsulationconference.com/",

}

Aizpurua, JI, Catterson, VM, Stewart, BG , McArthur, SDJ, Lambert, B, Ampofo, B, Pereira, G & Cross, JG 2017, Improving the accuracy of transformer DGA diagnosis in the presence of conflicting evidence. in 2017 IEEE Electrical Insulation Conference (EIC). IEEE, Piscataway, NJ, IEEE Electrical Insulation Conference 2017, Baltimore, United States, 11/06/17. https://doi.org/10.1109/EIC.2017.8004698

TY - GEN

T1 - Improving the accuracy of transformer DGA diagnosis in the presence of conflicting evidence

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 - © 2017 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 - 2017/8/18

Y1 - 2017/8/18

N2 - Transformers are critical assets for the reliable and cost-effective operation of the power grid. Transformers may fail if condition monitoring does not identify degraded conditions in time. Dissolved Gas Analysis (DGA) focuses on the examination of the dissolved gasses in the transformer oil and there exist different methods for transformer fault diagnosis based on different analyses of the gassing levels. However, these methods can give conflicting results, and it is not always clear which model is most accurate in a given situation. This paper presents a novel evidence combination framework for DGA based on Bayesian networks. Bayesian network models embed expert knowledge along with learned data patterns and evidence combination which aids in the consistency of analysis. The effectiveness of the proposed framework is validated using the IEC TC 10 dataset with a maximum diagnosis accuracy of 88.3%.

AB - Transformers are critical assets for the reliable and cost-effective operation of the power grid. Transformers may fail if condition monitoring does not identify degraded conditions in time. Dissolved Gas Analysis (DGA) focuses on the examination of the dissolved gasses in the transformer oil and there exist different methods for transformer fault diagnosis based on different analyses of the gassing levels. However, these methods can give conflicting results, and it is not always clear which model is most accurate in a given situation. This paper presents a novel evidence combination framework for DGA based on Bayesian networks. Bayesian network models embed expert knowledge along with learned data patterns and evidence combination which aids in the consistency of analysis. The effectiveness of the proposed framework is validated using the IEC TC 10 dataset with a maximum diagnosis accuracy of 88.3%.

KW - dissolved gas analysis

KW - DGA

KW - transformer diagnosis

KW - condition monitoring

KW - Bayesian networks

KW - evidence combination

KW - ensembles

U2 - 10.1109/EIC.2017.8004698

DO - 10.1109/EIC.2017.8004698

M3 - Conference contribution book

SN - 9781509039654

BT - 2017 IEEE Electrical Insulation Conference (EIC)

PB - IEEE

CY - Piscataway, NJ

T2 - IEEE Electrical Insulation Conference 2017

Y2 - 11 June 2017 through 14 June 2017

ER -

Improving the accuracy of transformer DGA diagnosis in the presence of conflicting evidence

Abstract

Conference

Keywords

Access to Document

Fingerprint

Research output

Improved power transformer condition monitoring under uncertainty through soft computing and probabilistic health index

Cite this