Improving the diagnosis of incipient faults in power transformers using dissolved gas analysis and multi layer perceptron

S. Nkosi; P. Bokoro

doi:10.1109/ISIE.2019.8781242

Improving the diagnosis of incipient faults in power transformers using dissolved gas analysis and multi layer perceptron

S. Nkosi, P. Bokoro

Electrical and Electronic Engineering Technology

University of Johannesburg

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

2 Citations (Scopus)

Abstract

In this work, a ten year gas production records, obtained from Rodgers ratio codes for gas concentration of H₂, CH₄, C₂H₆, C₂H₄ and C₂H₂, in a 795 MVA 20/400 kV rated power transformer are used in MLP for improving the diagnosis accuracy of incipient faults (partial discharge, thermal faults, low and high energy discharges, etc...). Numerical modelling of DGA-sourced data was achieved using MATLAB platform. Performance validation for the neural network was assessed in terms of the regression fit (R), the MSE and the MAPE. Results show 2.51 % as optimal value of MAPE which indicate a reasonable accuracy of ANN technique in the prediction of incipient faults.

Original language	English
Title of host publication	Proceedings - 2019 IEEE 28th International Symposium on Industrial Electronics, ISIE 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	112-117
Number of pages	6
ISBN (Electronic)	9781728136660
DOIs	https://doi.org/10.1109/ISIE.2019.8781242
Publication status	Published - Jun 2019
Event	28th IEEE International Symposium on Industrial Electronics, ISIE 2019 - Vancouver, Canada Duration: 12 Jun 2019 → 14 Jun 2019

Publication series

Name	IEEE International Symposium on Industrial Electronics
Volume	2019-June

Conference

Conference	28th IEEE International Symposium on Industrial Electronics, ISIE 2019
Country/Territory	Canada
City	Vancouver
Period	12/06/19 → 14/06/19

Keywords

component
formatting
insert
style
styling

ASJC Scopus subject areas

Electrical and Electronic Engineering
Control and Systems Engineering

Access to Document

10.1109/ISIE.2019.8781242

Cite this

Nkosi, S., & Bokoro, P. (2019). Improving the diagnosis of incipient faults in power transformers using dissolved gas analysis and multi layer perceptron. In Proceedings - 2019 IEEE 28th International Symposium on Industrial Electronics, ISIE 2019 (pp. 112-117). Article 8781242 (IEEE International Symposium on Industrial Electronics; Vol. 2019-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISIE.2019.8781242

Nkosi, S. ; Bokoro, P. / Improving the diagnosis of incipient faults in power transformers using dissolved gas analysis and multi layer perceptron. Proceedings - 2019 IEEE 28th International Symposium on Industrial Electronics, ISIE 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 112-117 (IEEE International Symposium on Industrial Electronics).

@inproceedings{123ddae26cb04e55b9f135e393d4ec4e,

title = "Improving the diagnosis of incipient faults in power transformers using dissolved gas analysis and multi layer perceptron",

abstract = "In this work, a ten year gas production records, obtained from Rodgers ratio codes for gas concentration of H2, CH4, C2H6, C2H4 and C2H2, in a 795 MVA 20/400 kV rated power transformer are used in MLP for improving the diagnosis accuracy of incipient faults (partial discharge, thermal faults, low and high energy discharges, etc...). Numerical modelling of DGA-sourced data was achieved using MATLAB platform. Performance validation for the neural network was assessed in terms of the regression fit (R), the MSE and the MAPE. Results show 2.51 % as optimal value of MAPE which indicate a reasonable accuracy of ANN technique in the prediction of incipient faults.",

keywords = "component, formatting, insert, style, styling",

author = "S. Nkosi and P. Bokoro",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 28th IEEE International Symposium on Industrial Electronics, ISIE 2019 ; Conference date: 12-06-2019 Through 14-06-2019",

year = "2019",

month = jun,

doi = "10.1109/ISIE.2019.8781242",

language = "English",

series = "IEEE International Symposium on Industrial Electronics",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "112--117",

booktitle = "Proceedings - 2019 IEEE 28th International Symposium on Industrial Electronics, ISIE 2019",

address = "United States",

}

Nkosi, S & Bokoro, P 2019, Improving the diagnosis of incipient faults in power transformers using dissolved gas analysis and multi layer perceptron. in Proceedings - 2019 IEEE 28th International Symposium on Industrial Electronics, ISIE 2019., 8781242, IEEE International Symposium on Industrial Electronics, vol. 2019-June, Institute of Electrical and Electronics Engineers Inc., pp. 112-117, 28th IEEE International Symposium on Industrial Electronics, ISIE 2019, Vancouver, Canada, 12/06/19. https://doi.org/10.1109/ISIE.2019.8781242

Improving the diagnosis of incipient faults in power transformers using dissolved gas analysis and multi layer perceptron. / Nkosi, S.; Bokoro, P.
Proceedings - 2019 IEEE 28th International Symposium on Industrial Electronics, ISIE 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 112-117 8781242 (IEEE International Symposium on Industrial Electronics; Vol. 2019-June).

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

TY - GEN

T1 - Improving the diagnosis of incipient faults in power transformers using dissolved gas analysis and multi layer perceptron

AU - Nkosi, S.

AU - Bokoro, P.

PY - 2019/6

Y1 - 2019/6

N2 - In this work, a ten year gas production records, obtained from Rodgers ratio codes for gas concentration of H2, CH4, C2H6, C2H4 and C2H2, in a 795 MVA 20/400 kV rated power transformer are used in MLP for improving the diagnosis accuracy of incipient faults (partial discharge, thermal faults, low and high energy discharges, etc...). Numerical modelling of DGA-sourced data was achieved using MATLAB platform. Performance validation for the neural network was assessed in terms of the regression fit (R), the MSE and the MAPE. Results show 2.51 % as optimal value of MAPE which indicate a reasonable accuracy of ANN technique in the prediction of incipient faults.

AB - In this work, a ten year gas production records, obtained from Rodgers ratio codes for gas concentration of H2, CH4, C2H6, C2H4 and C2H2, in a 795 MVA 20/400 kV rated power transformer are used in MLP for improving the diagnosis accuracy of incipient faults (partial discharge, thermal faults, low and high energy discharges, etc...). Numerical modelling of DGA-sourced data was achieved using MATLAB platform. Performance validation for the neural network was assessed in terms of the regression fit (R), the MSE and the MAPE. Results show 2.51 % as optimal value of MAPE which indicate a reasonable accuracy of ANN technique in the prediction of incipient faults.

KW - component

KW - formatting

KW - insert

KW - style

KW - styling

UR - http://www.scopus.com/inward/record.url?scp=85070613947&partnerID=8YFLogxK

U2 - 10.1109/ISIE.2019.8781242

DO - 10.1109/ISIE.2019.8781242

M3 - Conference contribution

AN - SCOPUS:85070613947

T3 - IEEE International Symposium on Industrial Electronics

SP - 112

EP - 117

BT - Proceedings - 2019 IEEE 28th International Symposium on Industrial Electronics, ISIE 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 28th IEEE International Symposium on Industrial Electronics, ISIE 2019

Y2 - 12 June 2019 through 14 June 2019

ER -

Nkosi S, Bokoro P. Improving the diagnosis of incipient faults in power transformers using dissolved gas analysis and multi layer perceptron. In Proceedings - 2019 IEEE 28th International Symposium on Industrial Electronics, ISIE 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 112-117. 8781242. (IEEE International Symposium on Industrial Electronics). doi: 10.1109/ISIE.2019.8781242

Improving the diagnosis of incipient faults in power transformers using dissolved gas analysis and multi layer perceptron

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this