Partial discharge pattern classification of angled point-oil-pressboard degradation

A. Abubakar Mas'ud, B.G. Stewart, S.G. McMeekin, A. Nesbitt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper compares single network (SNN) and ensemble neural network (ENN) capabilities to recognize and distinguish surface discharges between two point-interface-pressboard arrangements with point angles of 100 and 450. The training fingerprints for both the SNN and ENN comprise statistical parameters from the measurement of the surface discharge patterns captured over a period of 15 hours. The results shows that there is minimal statistical variability for surface discharges from a 450 point-interface-pressboard angles in comparison to that of 100, which shows different behavior over a similar degradation period. In comparison to the widely applied SNN, the ENN also consistently provides improved recognition of PD patterns while the SNN actually shows improved discrimination potential between the two point-oil-pressboard degradation angle geometries.
Original languageEnglish
Title of host publication2013 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP)
PublisherIEEE
Pages1217 - 1220
Number of pages4
ISBN (Electronic)978-1-4799-2597-1
ISBN (Print)978-1-4799-2598-8
DOIs
Publication statusPublished - 20 Oct 2013

Fingerprint

Surface discharges
Partial discharges
Pattern recognition
Neural networks
Degradation
Geometry
Oils

Keywords

  • single network
  • SNN
  • ensemble neural network
  • ENN

Cite this

Mas'ud, A. A., Stewart, B. G., McMeekin, S. G., & Nesbitt, A. (2013). Partial discharge pattern classification of angled point-oil-pressboard degradation. In 2013 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP) (pp. 1217 - 1220). IEEE. https://doi.org/10.1109/CEIDP.2013.6748222
Mas'ud, A. Abubakar ; Stewart, B.G. ; McMeekin, S.G. ; Nesbitt, A. / Partial discharge pattern classification of angled point-oil-pressboard degradation. 2013 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP). IEEE, 2013. pp. 1217 - 1220
@inproceedings{bf2ba5e3b99840d9946ad1d0d36424ba,
title = "Partial discharge pattern classification of angled point-oil-pressboard degradation",
abstract = "This paper compares single network (SNN) and ensemble neural network (ENN) capabilities to recognize and distinguish surface discharges between two point-interface-pressboard arrangements with point angles of 100 and 450. The training fingerprints for both the SNN and ENN comprise statistical parameters from the measurement of the surface discharge patterns captured over a period of 15 hours. The results shows that there is minimal statistical variability for surface discharges from a 450 point-interface-pressboard angles in comparison to that of 100, which shows different behavior over a similar degradation period. In comparison to the widely applied SNN, the ENN also consistently provides improved recognition of PD patterns while the SNN actually shows improved discrimination potential between the two point-oil-pressboard degradation angle geometries.",
keywords = "single network, SNN, ensemble neural network, ENN",
author = "Mas'ud, {A. Abubakar} and B.G. Stewart and S.G. McMeekin and A. Nesbitt",
year = "2013",
month = "10",
day = "20",
doi = "10.1109/CEIDP.2013.6748222",
language = "English",
isbn = "978-1-4799-2598-8",
pages = "1217 -- 1220",
booktitle = "2013 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP)",
publisher = "IEEE",

}

Mas'ud, AA, Stewart, BG, McMeekin, SG & Nesbitt, A 2013, Partial discharge pattern classification of angled point-oil-pressboard degradation. in 2013 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP). IEEE, pp. 1217 - 1220. https://doi.org/10.1109/CEIDP.2013.6748222

Partial discharge pattern classification of angled point-oil-pressboard degradation. / Mas'ud, A. Abubakar; Stewart, B.G.; McMeekin, S.G.; Nesbitt, A.

2013 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP). IEEE, 2013. p. 1217 - 1220.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Partial discharge pattern classification of angled point-oil-pressboard degradation

AU - Mas'ud, A. Abubakar

AU - Stewart, B.G.

AU - McMeekin, S.G.

AU - Nesbitt, A.

PY - 2013/10/20

Y1 - 2013/10/20

N2 - This paper compares single network (SNN) and ensemble neural network (ENN) capabilities to recognize and distinguish surface discharges between two point-interface-pressboard arrangements with point angles of 100 and 450. The training fingerprints for both the SNN and ENN comprise statistical parameters from the measurement of the surface discharge patterns captured over a period of 15 hours. The results shows that there is minimal statistical variability for surface discharges from a 450 point-interface-pressboard angles in comparison to that of 100, which shows different behavior over a similar degradation period. In comparison to the widely applied SNN, the ENN also consistently provides improved recognition of PD patterns while the SNN actually shows improved discrimination potential between the two point-oil-pressboard degradation angle geometries.

AB - This paper compares single network (SNN) and ensemble neural network (ENN) capabilities to recognize and distinguish surface discharges between two point-interface-pressboard arrangements with point angles of 100 and 450. The training fingerprints for both the SNN and ENN comprise statistical parameters from the measurement of the surface discharge patterns captured over a period of 15 hours. The results shows that there is minimal statistical variability for surface discharges from a 450 point-interface-pressboard angles in comparison to that of 100, which shows different behavior over a similar degradation period. In comparison to the widely applied SNN, the ENN also consistently provides improved recognition of PD patterns while the SNN actually shows improved discrimination potential between the two point-oil-pressboard degradation angle geometries.

KW - single network

KW - SNN

KW - ensemble neural network

KW - ENN

UR - http://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=30978

U2 - 10.1109/CEIDP.2013.6748222

DO - 10.1109/CEIDP.2013.6748222

M3 - Conference contribution

SN - 978-1-4799-2598-8

SP - 1217

EP - 1220

BT - 2013 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP)

PB - IEEE

ER -

Mas'ud AA, Stewart BG, McMeekin SG, Nesbitt A. Partial discharge pattern classification of angled point-oil-pressboard degradation. In 2013 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP). IEEE. 2013. p. 1217 - 1220 https://doi.org/10.1109/CEIDP.2013.6748222