Current-based trip coil analysis of circuit breakers for fault diagnosis

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

Abstract

Trip coil current trace analysis is commonly used in the condition monitoring of circuit breakers. Its effective implementation enables an unobtrusive method of diagnosis, reducing costs and increasing safety. Conventional methods of analysis rely on the extraction of knowledge-driven, time-based features from the trace, followed by diagnosis through an expert system. Many utility companies rely on the automated feature extraction capabilities provided within the trip coil current recorder. This paper highlights markers of potentially poor circuit breaker health missed when relying solely on such time-based analysis. A supplementary, data-driven method focusing on identifying such cases using machine learning techniques is introduced and demonstrated in this paper. Additionally, attention is drawn to the susceptibility of incorrect feature extraction by the recorders when subject to some of the explained current-based abnormalities.
LanguageEnglish
Title of host publication2018 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe)
Place of PublicationPiscataway, NJ
PublisherIEEE
Number of pages6
ISBN (Electronic)9781538645055
DOIs
Publication statusPublished - 13 Dec 2018
Event8th IEEE PES Innovative Smart Grid Technologies Conference - Sarajevo, Bosnia and Herzegovina
Duration: 21 Oct 201825 Oct 2018

Conference

Conference8th IEEE PES Innovative Smart Grid Technologies Conference
CountryBosnia and Herzegovina
CitySarajevo
Period21/10/1825/10/18

Fingerprint

Electric circuit breakers
Failure analysis
Feature extraction
Trace analysis
Condition monitoring
Expert systems
Learning systems
Health
Costs
Industry

Keywords

  • circuit breakers
  • fault diagnosis
  • machine learning

Cite this

Hosseini, M., Stephen, B., McArthur, S. D. J., & Helm, J. (2018). Current-based trip coil analysis of circuit breakers for fault diagnosis. In 2018 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe) Piscataway, NJ: IEEE. https://doi.org/10.1109/ISGTEurope.2018.8571478
Hosseini, Michael ; Stephen, Bruce ; McArthur, Stephen D. J. ; Helm, Joseph. / Current-based trip coil analysis of circuit breakers for fault diagnosis. 2018 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe). Piscataway, NJ : IEEE, 2018.
@inproceedings{159893b58e3448a2bbd91b7006ce9997,
title = "Current-based trip coil analysis of circuit breakers for fault diagnosis",
abstract = "Trip coil current trace analysis is commonly used in the condition monitoring of circuit breakers. Its effective implementation enables an unobtrusive method of diagnosis, reducing costs and increasing safety. Conventional methods of analysis rely on the extraction of knowledge-driven, time-based features from the trace, followed by diagnosis through an expert system. Many utility companies rely on the automated feature extraction capabilities provided within the trip coil current recorder. This paper highlights markers of potentially poor circuit breaker health missed when relying solely on such time-based analysis. A supplementary, data-driven method focusing on identifying such cases using machine learning techniques is introduced and demonstrated in this paper. Additionally, attention is drawn to the susceptibility of incorrect feature extraction by the recorders when subject to some of the explained current-based abnormalities.",
keywords = "circuit breakers, fault diagnosis, machine learning",
author = "Michael Hosseini and Bruce Stephen and McArthur, {Stephen D. J.} and Joseph Helm",
year = "2018",
month = "12",
day = "13",
doi = "10.1109/ISGTEurope.2018.8571478",
language = "English",
booktitle = "2018 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe)",
publisher = "IEEE",

}

Hosseini, M, Stephen, B, McArthur, SDJ & Helm, J 2018, Current-based trip coil analysis of circuit breakers for fault diagnosis. in 2018 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe). IEEE, Piscataway, NJ, 8th IEEE PES Innovative Smart Grid Technologies Conference, Sarajevo, Bosnia and Herzegovina, 21/10/18. https://doi.org/10.1109/ISGTEurope.2018.8571478

Current-based trip coil analysis of circuit breakers for fault diagnosis. / Hosseini, Michael; Stephen, Bruce; McArthur, Stephen D. J.; Helm, Joseph.

2018 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe). Piscataway, NJ : IEEE, 2018.

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

TY - GEN

T1 - Current-based trip coil analysis of circuit breakers for fault diagnosis

AU - Hosseini, Michael

AU - Stephen, Bruce

AU - McArthur, Stephen D. J.

AU - Helm, Joseph

PY - 2018/12/13

Y1 - 2018/12/13

N2 - Trip coil current trace analysis is commonly used in the condition monitoring of circuit breakers. Its effective implementation enables an unobtrusive method of diagnosis, reducing costs and increasing safety. Conventional methods of analysis rely on the extraction of knowledge-driven, time-based features from the trace, followed by diagnosis through an expert system. Many utility companies rely on the automated feature extraction capabilities provided within the trip coil current recorder. This paper highlights markers of potentially poor circuit breaker health missed when relying solely on such time-based analysis. A supplementary, data-driven method focusing on identifying such cases using machine learning techniques is introduced and demonstrated in this paper. Additionally, attention is drawn to the susceptibility of incorrect feature extraction by the recorders when subject to some of the explained current-based abnormalities.

AB - Trip coil current trace analysis is commonly used in the condition monitoring of circuit breakers. Its effective implementation enables an unobtrusive method of diagnosis, reducing costs and increasing safety. Conventional methods of analysis rely on the extraction of knowledge-driven, time-based features from the trace, followed by diagnosis through an expert system. Many utility companies rely on the automated feature extraction capabilities provided within the trip coil current recorder. This paper highlights markers of potentially poor circuit breaker health missed when relying solely on such time-based analysis. A supplementary, data-driven method focusing on identifying such cases using machine learning techniques is introduced and demonstrated in this paper. Additionally, attention is drawn to the susceptibility of incorrect feature extraction by the recorders when subject to some of the explained current-based abnormalities.

KW - circuit breakers

KW - fault diagnosis

KW - machine learning

U2 - 10.1109/ISGTEurope.2018.8571478

DO - 10.1109/ISGTEurope.2018.8571478

M3 - Conference contribution book

BT - 2018 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe)

PB - IEEE

CY - Piscataway, NJ

ER -

Hosseini M, Stephen B, McArthur SDJ, Helm J. Current-based trip coil analysis of circuit breakers for fault diagnosis. In 2018 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe). Piscataway, NJ: IEEE. 2018 https://doi.org/10.1109/ISGTEurope.2018.8571478