Assessing the effects of power quality on partial discharge behaviour through machine learning

V.M. Catterson, S.E. Rudd, S.D.J. McArthur, S. Bahadoorsingh, S.M. Rowland

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

Partial discharge (PD) is commonly used as an indicator of insulation health in high voltage equipment, but research has indicated that power quality, particularly harmonics, can strongly influence the discharge behaviour and the corresponding pattern observed. Unacknowledged variation in harmonics of the excitation voltage waveform can influence the insulation's degradation, leading to possible misinterpretation of diagnostic data and erroneous estimates of the insulation's ageing state, thus resulting in inappropriate asset management decisions. This paper reports on a suite of classifiers for identifying pertinent harmonic attributes from PD data, and presents results of techniques for improving their accuracy. Aspects of PD field monitoring are used to design a practical system for on-line monitoring of voltage harmonics. This system yields a report on the harmonics experienced during the monitoring period.

Conference

Conference7th International Conference on Condition Monitoring and Machinery Failure Prevention Technologies (CM 2010 and MFPT 2010)
CityStratford-upon-Avon, UK
Period22/06/1024/06/10

Fingerprint

Partial discharges
Power quality
Learning systems
Insulation
Monitoring
Electric potential
Asset management
Classifiers
Aging of materials
Health
Degradation

Keywords

  • power quality
  • partial discharge behaviour
  • machine learning
  • condition monitoring

Cite this

Catterson, V. M., Rudd, S. E., McArthur, S. D. J., Bahadoorsingh, S., & Rowland, S. M. (2010). Assessing the effects of power quality on partial discharge behaviour through machine learning. Paper presented at 7th International Conference on Condition Monitoring and Machinery Failure Prevention Technologies (CM 2010 and MFPT 2010), Stratford-upon-Avon, UK, .
Catterson, V.M. ; Rudd, S.E. ; McArthur, S.D.J. ; Bahadoorsingh, S. ; Rowland, S.M. / Assessing the effects of power quality on partial discharge behaviour through machine learning. Paper presented at 7th International Conference on Condition Monitoring and Machinery Failure Prevention Technologies (CM 2010 and MFPT 2010), Stratford-upon-Avon, UK, .13 p.
@conference{8283533627734369a28e4ccf70f6de0d,
title = "Assessing the effects of power quality on partial discharge behaviour through machine learning",
abstract = "Partial discharge (PD) is commonly used as an indicator of insulation health in high voltage equipment, but research has indicated that power quality, particularly harmonics, can strongly influence the discharge behaviour and the corresponding pattern observed. Unacknowledged variation in harmonics of the excitation voltage waveform can influence the insulation's degradation, leading to possible misinterpretation of diagnostic data and erroneous estimates of the insulation's ageing state, thus resulting in inappropriate asset management decisions. This paper reports on a suite of classifiers for identifying pertinent harmonic attributes from PD data, and presents results of techniques for improving their accuracy. Aspects of PD field monitoring are used to design a practical system for on-line monitoring of voltage harmonics. This system yields a report on the harmonics experienced during the monitoring period.",
keywords = "power quality, partial discharge behaviour, machine learning, condition monitoring",
author = "V.M. Catterson and S.E. Rudd and S.D.J. McArthur and S. Bahadoorsingh and S.M. Rowland",
year = "2010",
month = "6",
language = "English",
note = "7th International Conference on Condition Monitoring and Machinery Failure Prevention Technologies (CM 2010 and MFPT 2010) ; Conference date: 22-06-2010 Through 24-06-2010",

}

Catterson, VM, Rudd, SE, McArthur, SDJ, Bahadoorsingh, S & Rowland, SM 2010, 'Assessing the effects of power quality on partial discharge behaviour through machine learning' Paper presented at 7th International Conference on Condition Monitoring and Machinery Failure Prevention Technologies (CM 2010 and MFPT 2010), Stratford-upon-Avon, UK, 22/06/10 - 24/06/10, .

Assessing the effects of power quality on partial discharge behaviour through machine learning. / Catterson, V.M.; Rudd, S.E.; McArthur, S.D.J.; Bahadoorsingh, S.; Rowland, S.M.

2010. Paper presented at 7th International Conference on Condition Monitoring and Machinery Failure Prevention Technologies (CM 2010 and MFPT 2010), Stratford-upon-Avon, UK, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Assessing the effects of power quality on partial discharge behaviour through machine learning

AU - Catterson, V.M.

AU - Rudd, S.E.

AU - McArthur, S.D.J.

AU - Bahadoorsingh, S.

AU - Rowland, S.M.

PY - 2010/6

Y1 - 2010/6

N2 - Partial discharge (PD) is commonly used as an indicator of insulation health in high voltage equipment, but research has indicated that power quality, particularly harmonics, can strongly influence the discharge behaviour and the corresponding pattern observed. Unacknowledged variation in harmonics of the excitation voltage waveform can influence the insulation's degradation, leading to possible misinterpretation of diagnostic data and erroneous estimates of the insulation's ageing state, thus resulting in inappropriate asset management decisions. This paper reports on a suite of classifiers for identifying pertinent harmonic attributes from PD data, and presents results of techniques for improving their accuracy. Aspects of PD field monitoring are used to design a practical system for on-line monitoring of voltage harmonics. This system yields a report on the harmonics experienced during the monitoring period.

AB - Partial discharge (PD) is commonly used as an indicator of insulation health in high voltage equipment, but research has indicated that power quality, particularly harmonics, can strongly influence the discharge behaviour and the corresponding pattern observed. Unacknowledged variation in harmonics of the excitation voltage waveform can influence the insulation's degradation, leading to possible misinterpretation of diagnostic data and erroneous estimates of the insulation's ageing state, thus resulting in inappropriate asset management decisions. This paper reports on a suite of classifiers for identifying pertinent harmonic attributes from PD data, and presents results of techniques for improving their accuracy. Aspects of PD field monitoring are used to design a practical system for on-line monitoring of voltage harmonics. This system yields a report on the harmonics experienced during the monitoring period.

KW - power quality

KW - partial discharge behaviour

KW - machine learning

KW - condition monitoring

UR - http://www.bindt.org/Events/CM_Conferences_&_Seminars/CM_2010_and_MFPT_2010

M3 - Paper

ER -

Catterson VM, Rudd SE, McArthur SDJ, Bahadoorsingh S, Rowland SM. Assessing the effects of power quality on partial discharge behaviour through machine learning. 2010. Paper presented at 7th International Conference on Condition Monitoring and Machinery Failure Prevention Technologies (CM 2010 and MFPT 2010), Stratford-upon-Avon, UK, .