Analysis of power transformer dissolved gas data using the self-organizing map

K F Thang, R K Aggarwal, A J McGrail, D G Esp

Research output: Contribution to journalArticle

72 Citations (Scopus)

Abstract

Incipient faults in power transformers can degrade the oil and cellulose insulation, leading to the formation of dissolved gases. Even though established approaches that relate these dissolved gas information to the condition of power transformers are already developed, it is discussed in this paper that they still contain some limitations. In view of that, this paper introduces an alternative approach for the analysis of dissolved gas data, which can produce more convincing interpretation and fault diagnosis. The proposed approach, which is based on the data mining methodology and the self-organizing map, has been compared and validated using conventional interpretation schemes and real fault-cases, thereby proven to be capable of enhancing the condition monitoring of power transformers.
LanguageEnglish
Pages1241-1248
Number of pages8
JournalIEEE Transactions on Power Delivery
Volume18
Issue number4
StatusPublished - 2003

Fingerprint

Power transformers
Self organizing maps
Gases
Condition monitoring
Failure analysis
Data mining
Insulation
Cellulose

Keywords

  • data mining
  • chemical analysis
  • incipient faults
  • cellulose insulation
  • power engineering computing
  • self-organising feature maps
  • oil insulation
  • power transformer insulation
  • fault diagnosis
  • transformer oil
  • condition monitoring
  • self-organizing map
  • power transformers
  • dissolved gas analysis

Cite this

Analysis of power transformer dissolved gas data using the self-organizing map. / Thang, K F; Aggarwal, R K; McGrail, A J; Esp, D G.

In: IEEE Transactions on Power Delivery, Vol. 18, No. 4, 2003, p. 1241-1248.

Research output: Contribution to journalArticle

@article{5537b34ce5104969a353113502eb82b8,
title = "Analysis of power transformer dissolved gas data using the self-organizing map",
abstract = "Incipient faults in power transformers can degrade the oil and cellulose insulation, leading to the formation of dissolved gases. Even though established approaches that relate these dissolved gas information to the condition of power transformers are already developed, it is discussed in this paper that they still contain some limitations. In view of that, this paper introduces an alternative approach for the analysis of dissolved gas data, which can produce more convincing interpretation and fault diagnosis. The proposed approach, which is based on the data mining methodology and the self-organizing map, has been compared and validated using conventional interpretation schemes and real fault-cases, thereby proven to be capable of enhancing the condition monitoring of power transformers.",
keywords = "data mining, chemical analysis, incipient faults, cellulose insulation, power engineering computing, self-organising feature maps, oil insulation, power transformer insulation, fault diagnosis, transformer oil, condition monitoring, self-organizing map, power transformers, dissolved gas analysis",
author = "Thang, {K F} and Aggarwal, {R K} and McGrail, {A J} and Esp, {D G}",
year = "2003",
language = "English",
volume = "18",
pages = "1241--1248",
journal = "IEEE Transactions on Power Delivery",
issn = "0885-8977",
publisher = "IEEE",
number = "4",

}

TY - JOUR

T1 - Analysis of power transformer dissolved gas data using the self-organizing map

AU - Thang, K F

AU - Aggarwal, R K

AU - McGrail, A J

AU - Esp, D G

PY - 2003

Y1 - 2003

N2 - Incipient faults in power transformers can degrade the oil and cellulose insulation, leading to the formation of dissolved gases. Even though established approaches that relate these dissolved gas information to the condition of power transformers are already developed, it is discussed in this paper that they still contain some limitations. In view of that, this paper introduces an alternative approach for the analysis of dissolved gas data, which can produce more convincing interpretation and fault diagnosis. The proposed approach, which is based on the data mining methodology and the self-organizing map, has been compared and validated using conventional interpretation schemes and real fault-cases, thereby proven to be capable of enhancing the condition monitoring of power transformers.

AB - Incipient faults in power transformers can degrade the oil and cellulose insulation, leading to the formation of dissolved gases. Even though established approaches that relate these dissolved gas information to the condition of power transformers are already developed, it is discussed in this paper that they still contain some limitations. In view of that, this paper introduces an alternative approach for the analysis of dissolved gas data, which can produce more convincing interpretation and fault diagnosis. The proposed approach, which is based on the data mining methodology and the self-organizing map, has been compared and validated using conventional interpretation schemes and real fault-cases, thereby proven to be capable of enhancing the condition monitoring of power transformers.

KW - data mining

KW - chemical analysis

KW - incipient faults

KW - cellulose insulation

KW - power engineering computing

KW - self-organising feature maps

KW - oil insulation

KW - power transformer insulation

KW - fault diagnosis

KW - transformer oil

KW - condition monitoring

KW - self-organizing map

KW - power transformers

KW - dissolved gas analysis

M3 - Article

VL - 18

SP - 1241

EP - 1248

JO - IEEE Transactions on Power Delivery

T2 - IEEE Transactions on Power Delivery

JF - IEEE Transactions on Power Delivery

SN - 0885-8977

IS - 4

ER -