Novel prediction-reliability based graphical DGA technique using multi-layer perceptron network & gas ratio combination algorithm

Kingshuk Chatterjee, Subham Dawn, Vinay K. Jadoun, R. K. Jarial

Research output: Contribution to journalArticle

Abstract

Dissolved gas analysis (DGA) is among the most essential techniques for diagnosis of incipient faults in power transformers. Here, a novel graphical DGA technique is proposed in which fault zones are distinguished based on certainty of prediction. The Duval Pentagon 1 and gas ratio combination methods are two most recent techniques with high prediction accuracy. In the Duval Pentagon 1, the rigidly separated distinct fault zones reduce the flexibility of analysis because the fault distributions themselves are not that strictly separated. This also prevents the full utilisation of the information available from the distribution patterns of the graphical representation. This problem has been addressed by overlapping individual fault zones and overlapping them using a multi-layer perceptron (MLP) network with fuzzy class boundaries. Then, in the regions, where multiple fault zones overlap, a modified gas ratio combination method is applied. Finally, a fuzzy decision-making system is developed for predicting the fault using information from both graphical distribution and gas ratios. The combined accuracy of the regions of certainty has been found exceptionally high (98.36%) compared to the regions of uncertainty (58.97%), whereas the overall prediction accuracy of the proposed technique is found comparatively higher (83%) than both the existing methods.

Original languageEnglish
Pages (from-to)836-842
Number of pages7
JournalIET Science, Measurement and Technology
Volume13
Issue number6
DOIs
Publication statusPublished - 01-08-2019

Fingerprint

dissolved gases
self organizing systems
Gas fuel analysis
gas analysis
Multilayer neural networks
predictions
Gases
gases
distribution (property)
Power transformers
decision making
transformers
flexibility
Decision making

All Science Journal Classification (ASJC) codes

  • Atomic and Molecular Physics, and Optics
  • Electrical and Electronic Engineering

Cite this

@article{644775916f2d4fa98d33543b8f1bc12a,
title = "Novel prediction-reliability based graphical DGA technique using multi-layer perceptron network & gas ratio combination algorithm",
abstract = "Dissolved gas analysis (DGA) is among the most essential techniques for diagnosis of incipient faults in power transformers. Here, a novel graphical DGA technique is proposed in which fault zones are distinguished based on certainty of prediction. The Duval Pentagon 1 and gas ratio combination methods are two most recent techniques with high prediction accuracy. In the Duval Pentagon 1, the rigidly separated distinct fault zones reduce the flexibility of analysis because the fault distributions themselves are not that strictly separated. This also prevents the full utilisation of the information available from the distribution patterns of the graphical representation. This problem has been addressed by overlapping individual fault zones and overlapping them using a multi-layer perceptron (MLP) network with fuzzy class boundaries. Then, in the regions, where multiple fault zones overlap, a modified gas ratio combination method is applied. Finally, a fuzzy decision-making system is developed for predicting the fault using information from both graphical distribution and gas ratios. The combined accuracy of the regions of certainty has been found exceptionally high (98.36{\%}) compared to the regions of uncertainty (58.97{\%}), whereas the overall prediction accuracy of the proposed technique is found comparatively higher (83{\%}) than both the existing methods.",
author = "Kingshuk Chatterjee and Subham Dawn and Jadoun, {Vinay K.} and Jarial, {R. K.}",
year = "2019",
month = "8",
day = "1",
doi = "10.1049/iet-smt.2018.5397",
language = "English",
volume = "13",
pages = "836--842",
journal = "IET Science, Measurement and Technology",
issn = "1751-8822",
publisher = "Institution of Engineering and Technology",
number = "6",

}

Novel prediction-reliability based graphical DGA technique using multi-layer perceptron network & gas ratio combination algorithm. / Chatterjee, Kingshuk; Dawn, Subham; Jadoun, Vinay K.; Jarial, R. K.

In: IET Science, Measurement and Technology, Vol. 13, No. 6, 01.08.2019, p. 836-842.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Novel prediction-reliability based graphical DGA technique using multi-layer perceptron network & gas ratio combination algorithm

AU - Chatterjee, Kingshuk

AU - Dawn, Subham

AU - Jadoun, Vinay K.

AU - Jarial, R. K.

PY - 2019/8/1

Y1 - 2019/8/1

N2 - Dissolved gas analysis (DGA) is among the most essential techniques for diagnosis of incipient faults in power transformers. Here, a novel graphical DGA technique is proposed in which fault zones are distinguished based on certainty of prediction. The Duval Pentagon 1 and gas ratio combination methods are two most recent techniques with high prediction accuracy. In the Duval Pentagon 1, the rigidly separated distinct fault zones reduce the flexibility of analysis because the fault distributions themselves are not that strictly separated. This also prevents the full utilisation of the information available from the distribution patterns of the graphical representation. This problem has been addressed by overlapping individual fault zones and overlapping them using a multi-layer perceptron (MLP) network with fuzzy class boundaries. Then, in the regions, where multiple fault zones overlap, a modified gas ratio combination method is applied. Finally, a fuzzy decision-making system is developed for predicting the fault using information from both graphical distribution and gas ratios. The combined accuracy of the regions of certainty has been found exceptionally high (98.36%) compared to the regions of uncertainty (58.97%), whereas the overall prediction accuracy of the proposed technique is found comparatively higher (83%) than both the existing methods.

AB - Dissolved gas analysis (DGA) is among the most essential techniques for diagnosis of incipient faults in power transformers. Here, a novel graphical DGA technique is proposed in which fault zones are distinguished based on certainty of prediction. The Duval Pentagon 1 and gas ratio combination methods are two most recent techniques with high prediction accuracy. In the Duval Pentagon 1, the rigidly separated distinct fault zones reduce the flexibility of analysis because the fault distributions themselves are not that strictly separated. This also prevents the full utilisation of the information available from the distribution patterns of the graphical representation. This problem has been addressed by overlapping individual fault zones and overlapping them using a multi-layer perceptron (MLP) network with fuzzy class boundaries. Then, in the regions, where multiple fault zones overlap, a modified gas ratio combination method is applied. Finally, a fuzzy decision-making system is developed for predicting the fault using information from both graphical distribution and gas ratios. The combined accuracy of the regions of certainty has been found exceptionally high (98.36%) compared to the regions of uncertainty (58.97%), whereas the overall prediction accuracy of the proposed technique is found comparatively higher (83%) than both the existing methods.

UR - http://www.scopus.com/inward/record.url?scp=85069755484&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069755484&partnerID=8YFLogxK

U2 - 10.1049/iet-smt.2018.5397

DO - 10.1049/iet-smt.2018.5397

M3 - Article

AN - SCOPUS:85069755484

VL - 13

SP - 836

EP - 842

JO - IET Science, Measurement and Technology

JF - IET Science, Measurement and Technology

SN - 1751-8822

IS - 6

ER -