Automated feature validation of trip coil analysis in condition monitoring of circuit breakers

Research output: Contribution to journalConference Contribution

Abstract

Datasets of historical performance metrics can offer valuable insight into an asset fleet’s health. This is especially so in the context to establishing normal behavior and thresholds of acceptable performance for diagnostic purposes. However, plant performance can often be obscured by data quality issues which introduce artefacts that do not pertain to asset health. This paper utilises a supervised ensemble machine-learning approach to automate the process of filtering maintenance data based on their predicted validity. The results are then presented both in terms of classification performance, and the impact on the distributions directly. This helps to ensure engineers are basing their diagnostic decisions on valid data. The accuracy of the filtration process, and its effect on the final thresholds will be discussed. To illustrate, this paper uses data of varying quality on circuit breaker trip tests obtained from operational medium-voltage circuit-breakers spanning several decades with the aim of providing decision support for switchgear diagnostics.
LanguageEnglish
Number of pages6
JournalPHM Society European Conference
Volume4
Issue number1
Publication statusPublished - 1 Jul 2018
EventFourth European Conference of the PHM Society - Utrecht, Netherlands
Duration: 3 Jul 20186 Jul 2018

Fingerprint

Electric circuit breakers
Condition monitoring
Health
Electric switchgear
Learning systems
Engineers
Electric potential

Keywords

  • machine learning
  • circuit breakers
  • performance

Cite this

@article{a40dcacc87a2466a8861d93a903a4ea4,
title = "Automated feature validation of trip coil analysis in condition monitoring of circuit breakers",
abstract = "Datasets of historical performance metrics can offer valuable insight into an asset fleet’s health. This is especially so in the context to establishing normal behavior and thresholds of acceptable performance for diagnostic purposes. However, plant performance can often be obscured by data quality issues which introduce artefacts that do not pertain to asset health. This paper utilises a supervised ensemble machine-learning approach to automate the process of filtering maintenance data based on their predicted validity. The results are then presented both in terms of classification performance, and the impact on the distributions directly. This helps to ensure engineers are basing their diagnostic decisions on valid data. The accuracy of the filtration process, and its effect on the final thresholds will be discussed. To illustrate, this paper uses data of varying quality on circuit breaker trip tests obtained from operational medium-voltage circuit-breakers spanning several decades with the aim of providing decision support for switchgear diagnostics.",
keywords = "machine learning, circuit breakers, performance",
author = "Michael Hosseini and Joseph Helm and Bruce Stephen and McArthur, {Stephen D. J.}",
year = "2018",
month = "7",
day = "1",
language = "English",
volume = "4",
number = "1",

}

Automated feature validation of trip coil analysis in condition monitoring of circuit breakers. / Hosseini, Michael; Helm, Joseph; Stephen, Bruce; McArthur, Stephen D. J.

Vol. 4, No. 1, 01.07.2018.

Research output: Contribution to journalConference Contribution

TY - JOUR

T1 - Automated feature validation of trip coil analysis in condition monitoring of circuit breakers

AU - Hosseini, Michael

AU - Helm, Joseph

AU - Stephen, Bruce

AU - McArthur, Stephen D. J.

PY - 2018/7/1

Y1 - 2018/7/1

N2 - Datasets of historical performance metrics can offer valuable insight into an asset fleet’s health. This is especially so in the context to establishing normal behavior and thresholds of acceptable performance for diagnostic purposes. However, plant performance can often be obscured by data quality issues which introduce artefacts that do not pertain to asset health. This paper utilises a supervised ensemble machine-learning approach to automate the process of filtering maintenance data based on their predicted validity. The results are then presented both in terms of classification performance, and the impact on the distributions directly. This helps to ensure engineers are basing their diagnostic decisions on valid data. The accuracy of the filtration process, and its effect on the final thresholds will be discussed. To illustrate, this paper uses data of varying quality on circuit breaker trip tests obtained from operational medium-voltage circuit-breakers spanning several decades with the aim of providing decision support for switchgear diagnostics.

AB - Datasets of historical performance metrics can offer valuable insight into an asset fleet’s health. This is especially so in the context to establishing normal behavior and thresholds of acceptable performance for diagnostic purposes. However, plant performance can often be obscured by data quality issues which introduce artefacts that do not pertain to asset health. This paper utilises a supervised ensemble machine-learning approach to automate the process of filtering maintenance data based on their predicted validity. The results are then presented both in terms of classification performance, and the impact on the distributions directly. This helps to ensure engineers are basing their diagnostic decisions on valid data. The accuracy of the filtration process, and its effect on the final thresholds will be discussed. To illustrate, this paper uses data of varying quality on circuit breaker trip tests obtained from operational medium-voltage circuit-breakers spanning several decades with the aim of providing decision support for switchgear diagnostics.

KW - machine learning

KW - circuit breakers

KW - performance

UR - https://phmpapers.org/index.php/phme/article/view/453

UR - https://phmpapers.org/index.php/phme/index

M3 - Conference Contribution

VL - 4

IS - 1

ER -