Detection of super-high-frequency partial discharge by using neural networks

Qingshan Shan, Shahzad Ahmed Bhatti, Ian A. Glover, Robert Atkinson, Richard Rutherford

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A system has been developed for the detection of super-high-frequency (SHF) partial discharge (PD) at frequencies up to 6 GHz. The system consists of three antennas for capturing PDs and a fast digital oscilloscope for sampling data. One of the antennas is a disk-cone antenna with frequency range below 710 MHz. The other two half TEM horn antennas have been designed and constructed for the frequency range 716 MHz - 5 GHz. To extend the frequency range up to 6 GHz, a methodology has been developed by compensating amplitude-response to frequency-magnitude. The compensation is realised by using multilayer feed-forward neural networks to equalise on amplitude-response. A direct sampling method is used to log the captured PD data. This PD detection system has been implemented to measure PDs at a 400 kV electrical substation (Strathaven, Scottish Power Ltd).

Original languageEnglish
Pages (from-to)442-447
Number of pages6
JournalInsight: Non-Destructive Testing and Condition Monitoring
Volume51
Issue number8
DOIs
Publication statusPublished - 1 Aug 2009
Externally publishedYes

Fingerprint

Partial discharges
Antennas
Neural networks
Sampling
Horn antennas
Feedforward neural networks
Multilayer neural networks
Cones
Transmission electron microscopy

Cite this

Shan, Qingshan ; Bhatti, Shahzad Ahmed ; Glover, Ian A. ; Atkinson, Robert ; Rutherford, Richard. / Detection of super-high-frequency partial discharge by using neural networks. In: Insight: Non-Destructive Testing and Condition Monitoring. 2009 ; Vol. 51, No. 8. pp. 442-447.
@article{beb9d323d5f143bfb334be99bb8c72c2,
title = "Detection of super-high-frequency partial discharge by using neural networks",
abstract = "A system has been developed for the detection of super-high-frequency (SHF) partial discharge (PD) at frequencies up to 6 GHz. The system consists of three antennas for capturing PDs and a fast digital oscilloscope for sampling data. One of the antennas is a disk-cone antenna with frequency range below 710 MHz. The other two half TEM horn antennas have been designed and constructed for the frequency range 716 MHz - 5 GHz. To extend the frequency range up to 6 GHz, a methodology has been developed by compensating amplitude-response to frequency-magnitude. The compensation is realised by using multilayer feed-forward neural networks to equalise on amplitude-response. A direct sampling method is used to log the captured PD data. This PD detection system has been implemented to measure PDs at a 400 kV electrical substation (Strathaven, Scottish Power Ltd).",
keywords = "Neural network, Partial discharge, Super high frequency, TEM horn",
author = "Qingshan Shan and Bhatti, {Shahzad Ahmed} and Glover, {Ian A.} and Robert Atkinson and Richard Rutherford",
year = "2009",
month = "8",
day = "1",
doi = "10.1784/insi.2009.51.8.442",
language = "English",
volume = "51",
pages = "442--447",
journal = "Insight: Non-Destructive Testing and Condition Monitoring",
issn = "1354-2575",
publisher = "British Institute of Non-Destructive Testing",
number = "8",

}

Detection of super-high-frequency partial discharge by using neural networks. / Shan, Qingshan; Bhatti, Shahzad Ahmed; Glover, Ian A.; Atkinson, Robert; Rutherford, Richard.

In: Insight: Non-Destructive Testing and Condition Monitoring, Vol. 51, No. 8, 01.08.2009, p. 442-447.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Detection of super-high-frequency partial discharge by using neural networks

AU - Shan, Qingshan

AU - Bhatti, Shahzad Ahmed

AU - Glover, Ian A.

AU - Atkinson, Robert

AU - Rutherford, Richard

PY - 2009/8/1

Y1 - 2009/8/1

N2 - A system has been developed for the detection of super-high-frequency (SHF) partial discharge (PD) at frequencies up to 6 GHz. The system consists of three antennas for capturing PDs and a fast digital oscilloscope for sampling data. One of the antennas is a disk-cone antenna with frequency range below 710 MHz. The other two half TEM horn antennas have been designed and constructed for the frequency range 716 MHz - 5 GHz. To extend the frequency range up to 6 GHz, a methodology has been developed by compensating amplitude-response to frequency-magnitude. The compensation is realised by using multilayer feed-forward neural networks to equalise on amplitude-response. A direct sampling method is used to log the captured PD data. This PD detection system has been implemented to measure PDs at a 400 kV electrical substation (Strathaven, Scottish Power Ltd).

AB - A system has been developed for the detection of super-high-frequency (SHF) partial discharge (PD) at frequencies up to 6 GHz. The system consists of three antennas for capturing PDs and a fast digital oscilloscope for sampling data. One of the antennas is a disk-cone antenna with frequency range below 710 MHz. The other two half TEM horn antennas have been designed and constructed for the frequency range 716 MHz - 5 GHz. To extend the frequency range up to 6 GHz, a methodology has been developed by compensating amplitude-response to frequency-magnitude. The compensation is realised by using multilayer feed-forward neural networks to equalise on amplitude-response. A direct sampling method is used to log the captured PD data. This PD detection system has been implemented to measure PDs at a 400 kV electrical substation (Strathaven, Scottish Power Ltd).

KW - Neural network

KW - Partial discharge

KW - Super high frequency

KW - TEM horn

UR - http://www.scopus.com/inward/record.url?scp=70349138914&partnerID=8YFLogxK

U2 - 10.1784/insi.2009.51.8.442

DO - 10.1784/insi.2009.51.8.442

M3 - Article

VL - 51

SP - 442

EP - 447

JO - Insight: Non-Destructive Testing and Condition Monitoring

JF - Insight: Non-Destructive Testing and Condition Monitoring

SN - 1354-2575

IS - 8

ER -