Association rule mining-based dissolved gas analysis for fault diagnosis of power transformers

Z. Yang, W. H. Tang, A. Shintemirov, Q. H. Wu

Research output: Contribution to journalArticle

73 Citations (Scopus)

Abstract

This paper presents a novel association rule mining (ARM)-based dissolved gas analysis (DGA) approach to fault diagnosis (FD) of power transformers. In the development of the ARM-based DGA approach, an attribute selection method and a continuous datum attribute discretization method are used for choosing user-interested ARM attributes from a DGA data set, i.e. the items that are employed to extract association rules. The given DGA data set is composed of two parts, i.e. training and test DGA data sets. An ARM algorithm namely Apriori-Total From Partial is proposed for generating an association rule set (ARS) from the training DGA data set. Afterwards, an ARS simplification method and a rule fitness evaluation method are utilized to select useful rules from the ARS and assign a fitness value to each of the useful rules, respectively. Based upon the useful association rules, a transformer FD classifier is developed, in which an optimal rule selection method is employed for selecting the most accurate rule from the classifier for diagnosing a test DGA record. For comparison purposes, five widely used FD methods are also tested with the same training and test data sets in experiments. Results show that the proposed ARM-based DGA approach is capable of generating a number of meaningful association rules, which can also cover the empirical rules defined in industry standards. Moreover, a higher FD accuracy can be achieved with the association rule-based FD classifier, compared with that derived by the other methods.

Original languageEnglish
Pages (from-to)597-610
Number of pages14
JournalIEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews
Volume39
Issue number6
DOIs
Publication statusPublished - Nov 2009
Externally publishedYes

Fingerprint

Gas fuel analysis
Power transformers
Association rules
Failure analysis
Classifiers

Keywords

  • Apriori-TFP
  • Association rule mining
  • Bootstrap
  • Dissolved gas analysis
  • Fault diagnosis
  • Power transformer

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Human-Computer Interaction
  • Information Systems
  • Software

Cite this

Association rule mining-based dissolved gas analysis for fault diagnosis of power transformers. / Yang, Z.; Tang, W. H.; Shintemirov, A.; Wu, Q. H.

In: IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews, Vol. 39, No. 6, 11.2009, p. 597-610.

Research output: Contribution to journalArticle

@article{ae5f3a0d861b4536a53da811f701db69,
title = "Association rule mining-based dissolved gas analysis for fault diagnosis of power transformers",
abstract = "This paper presents a novel association rule mining (ARM)-based dissolved gas analysis (DGA) approach to fault diagnosis (FD) of power transformers. In the development of the ARM-based DGA approach, an attribute selection method and a continuous datum attribute discretization method are used for choosing user-interested ARM attributes from a DGA data set, i.e. the items that are employed to extract association rules. The given DGA data set is composed of two parts, i.e. training and test DGA data sets. An ARM algorithm namely Apriori-Total From Partial is proposed for generating an association rule set (ARS) from the training DGA data set. Afterwards, an ARS simplification method and a rule fitness evaluation method are utilized to select useful rules from the ARS and assign a fitness value to each of the useful rules, respectively. Based upon the useful association rules, a transformer FD classifier is developed, in which an optimal rule selection method is employed for selecting the most accurate rule from the classifier for diagnosing a test DGA record. For comparison purposes, five widely used FD methods are also tested with the same training and test data sets in experiments. Results show that the proposed ARM-based DGA approach is capable of generating a number of meaningful association rules, which can also cover the empirical rules defined in industry standards. Moreover, a higher FD accuracy can be achieved with the association rule-based FD classifier, compared with that derived by the other methods.",
keywords = "Apriori-TFP, Association rule mining, Bootstrap, Dissolved gas analysis, Fault diagnosis, Power transformer",
author = "Z. Yang and Tang, {W. H.} and A. Shintemirov and Wu, {Q. H.}",
year = "2009",
month = "11",
doi = "10.1109/TSMCC.2009.2021989",
language = "English",
volume = "39",
pages = "597--610",
journal = "IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews",
issn = "1094-6977",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Association rule mining-based dissolved gas analysis for fault diagnosis of power transformers

AU - Yang, Z.

AU - Tang, W. H.

AU - Shintemirov, A.

AU - Wu, Q. H.

PY - 2009/11

Y1 - 2009/11

N2 - This paper presents a novel association rule mining (ARM)-based dissolved gas analysis (DGA) approach to fault diagnosis (FD) of power transformers. In the development of the ARM-based DGA approach, an attribute selection method and a continuous datum attribute discretization method are used for choosing user-interested ARM attributes from a DGA data set, i.e. the items that are employed to extract association rules. The given DGA data set is composed of two parts, i.e. training and test DGA data sets. An ARM algorithm namely Apriori-Total From Partial is proposed for generating an association rule set (ARS) from the training DGA data set. Afterwards, an ARS simplification method and a rule fitness evaluation method are utilized to select useful rules from the ARS and assign a fitness value to each of the useful rules, respectively. Based upon the useful association rules, a transformer FD classifier is developed, in which an optimal rule selection method is employed for selecting the most accurate rule from the classifier for diagnosing a test DGA record. For comparison purposes, five widely used FD methods are also tested with the same training and test data sets in experiments. Results show that the proposed ARM-based DGA approach is capable of generating a number of meaningful association rules, which can also cover the empirical rules defined in industry standards. Moreover, a higher FD accuracy can be achieved with the association rule-based FD classifier, compared with that derived by the other methods.

AB - This paper presents a novel association rule mining (ARM)-based dissolved gas analysis (DGA) approach to fault diagnosis (FD) of power transformers. In the development of the ARM-based DGA approach, an attribute selection method and a continuous datum attribute discretization method are used for choosing user-interested ARM attributes from a DGA data set, i.e. the items that are employed to extract association rules. The given DGA data set is composed of two parts, i.e. training and test DGA data sets. An ARM algorithm namely Apriori-Total From Partial is proposed for generating an association rule set (ARS) from the training DGA data set. Afterwards, an ARS simplification method and a rule fitness evaluation method are utilized to select useful rules from the ARS and assign a fitness value to each of the useful rules, respectively. Based upon the useful association rules, a transformer FD classifier is developed, in which an optimal rule selection method is employed for selecting the most accurate rule from the classifier for diagnosing a test DGA record. For comparison purposes, five widely used FD methods are also tested with the same training and test data sets in experiments. Results show that the proposed ARM-based DGA approach is capable of generating a number of meaningful association rules, which can also cover the empirical rules defined in industry standards. Moreover, a higher FD accuracy can be achieved with the association rule-based FD classifier, compared with that derived by the other methods.

KW - Apriori-TFP

KW - Association rule mining

KW - Bootstrap

KW - Dissolved gas analysis

KW - Fault diagnosis

KW - Power transformer

UR - http://www.scopus.com/inward/record.url?scp=77955092273&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955092273&partnerID=8YFLogxK

U2 - 10.1109/TSMCC.2009.2021989

DO - 10.1109/TSMCC.2009.2021989

M3 - Article

VL - 39

SP - 597

EP - 610

JO - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews

JF - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews

SN - 1094-6977

IS - 6

ER -