DGA: A novel strategy for key gases identification in power transformers

Matias Meira; Ignacio Carlucho; Rul Alvarez; Leonardo Catalano; Gerardo Acosta

doi:10.1109/EIC47619.2020.9158662

DGA: A novel strategy for key gases identification in power transformers

Matias Meira, Ignacio Carlucho, Rul Alvarez, Leonardo Catalano, Gerardo Acosta

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

2 Citations (Scopus)

Abstract

There are several proposals for the dissolved gas analysis (DGA) of power transformers through the use of artificial intelligence. All these proposals, based on fuzzy logic, knowledge-based systems and neural networks, among others, are oriented to the diagnosis of the equipment based on the expert knowledge obtained over the years. This paper proposes a new approach in the use of neural networks, not for transformer diagnosis, but rather for the identification of key gases in mineral oil-immersed transformers. The proposal is tested on the dielectric oil of mineral origin traditionally used in transformers since its expected behavior is known. The key gases identified with this proposal coincide with those found in the literature, so the strategy is efficient. However, the potential of the work relies on the application to natural esters, field still under investigation.

Original language	English
Title of host publication	2020 IEEE Electrical Insulation Conference
Publisher	IEEE
Pages	290-293
Number of pages	4
ISBN (Electronic)	9781728154855
DOIs	https://doi.org/10.1109/EIC47619.2020.9158662
Publication status	Published - 5 Aug 2020
Event	2020 IEEE Electrical Insulation Conference - Knoxville, United States Duration: 22 Jun 2020 → 3 Jul 2020

Conference

Conference	2020 IEEE Electrical Insulation Conference
Abbreviated title	EIC 2020
Country/Territory	United States
City	Knoxville
Period	22/06/20 → 3/07/20

Keywords

artificial intelligence
DGA
dielectric fluids
mineral oil
natural ester
neural networks
transformers

ASJC Scopus subject areas

Energy Engineering and Power Technology
Electrical and Electronic Engineering
Safety, Risk, Reliability and Quality
Electronic, Optical and Magnetic Materials

Access to Document

10.1109/EIC47619.2020.9158662

Cite this

@inproceedings{38cdd039c4634c10ae99708af8c2ef39,

title = "DGA: A novel strategy for key gases identification in power transformers",

abstract = "There are several proposals for the dissolved gas analysis (DGA) of power transformers through the use of artificial intelligence. All these proposals, based on fuzzy logic, knowledge-based systems and neural networks, among others, are oriented to the diagnosis of the equipment based on the expert knowledge obtained over the years. This paper proposes a new approach in the use of neural networks, not for transformer diagnosis, but rather for the identification of key gases in mineral oil-immersed transformers. The proposal is tested on the dielectric oil of mineral origin traditionally used in transformers since its expected behavior is known. The key gases identified with this proposal coincide with those found in the literature, so the strategy is efficient. However, the potential of the work relies on the application to natural esters, field still under investigation.",

keywords = "artificial intelligence, DGA, dielectric fluids, mineral oil, natural ester, neural networks, transformers",

author = "Matias Meira and Ignacio Carlucho and Rul Alvarez and Leonardo Catalano and Gerardo Acosta",

note = "Funding Information: ACKNOWLEDGMENT This research was supported by the CONICET; the UNCPBA, the IITREE of UNLP and the ANPCYT. We also gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan X Pascal GPU used for this research. Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE Electrical Insulation Conference, EIC 2020 ; Conference date: 22-06-2020 Through 03-07-2020",

year = "2020",

month = aug,

day = "5",

doi = "10.1109/EIC47619.2020.9158662",

language = "English",

pages = "290--293",

booktitle = "2020 IEEE Electrical Insulation Conference",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - DGA: A novel strategy for key gases identification in power transformers

AU - Meira, Matias

AU - Carlucho, Ignacio

AU - Alvarez, Rul

AU - Catalano, Leonardo

AU - Acosta, Gerardo

N1 - Funding Information: ACKNOWLEDGMENT This research was supported by the CONICET; the UNCPBA, the IITREE of UNLP and the ANPCYT. We also gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan X Pascal GPU used for this research. Publisher Copyright: © 2020 IEEE.

PY - 2020/8/5

Y1 - 2020/8/5

N2 - There are several proposals for the dissolved gas analysis (DGA) of power transformers through the use of artificial intelligence. All these proposals, based on fuzzy logic, knowledge-based systems and neural networks, among others, are oriented to the diagnosis of the equipment based on the expert knowledge obtained over the years. This paper proposes a new approach in the use of neural networks, not for transformer diagnosis, but rather for the identification of key gases in mineral oil-immersed transformers. The proposal is tested on the dielectric oil of mineral origin traditionally used in transformers since its expected behavior is known. The key gases identified with this proposal coincide with those found in the literature, so the strategy is efficient. However, the potential of the work relies on the application to natural esters, field still under investigation.

AB - There are several proposals for the dissolved gas analysis (DGA) of power transformers through the use of artificial intelligence. All these proposals, based on fuzzy logic, knowledge-based systems and neural networks, among others, are oriented to the diagnosis of the equipment based on the expert knowledge obtained over the years. This paper proposes a new approach in the use of neural networks, not for transformer diagnosis, but rather for the identification of key gases in mineral oil-immersed transformers. The proposal is tested on the dielectric oil of mineral origin traditionally used in transformers since its expected behavior is known. The key gases identified with this proposal coincide with those found in the literature, so the strategy is efficient. However, the potential of the work relies on the application to natural esters, field still under investigation.

KW - artificial intelligence

KW - DGA

KW - dielectric fluids

KW - mineral oil

KW - natural ester

KW - neural networks

KW - transformers

UR - http://www.scopus.com/inward/record.url?scp=85092132423&partnerID=8YFLogxK

U2 - 10.1109/EIC47619.2020.9158662

DO - 10.1109/EIC47619.2020.9158662

M3 - Conference contribution

AN - SCOPUS:85092132423

SP - 290

EP - 293

BT - 2020 IEEE Electrical Insulation Conference

PB - IEEE

T2 - 2020 IEEE Electrical Insulation Conference

Y2 - 22 June 2020 through 3 July 2020

ER -

DGA: A novel strategy for key gases identification in power transformers

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this