Prognostics & health management oriented data analytics suite for transformer health monitoring

Jose Ignacio Aizpurua; Brian G. Stewart; Stephen D. J. McArthur

Prognostics & health management oriented data analytics suite for transformer health monitoring

Jose Ignacio Aizpurua, Brian G. Stewart, Stephen D. J. McArthur

Research output: Contribution to journal › Article › peer-review

50 Downloads (Pure)

Abstract

Condition monitoring of power transformers is crucial for the reliable and cost-effective operation of the power grid. The unexpected failure of a transformer can lead to different consequences ranging from a lack of export capability, with the corresponding economic penalties, to catastrophic failure, with the associated health, safety, and economic effects. With the advance of machine learning techniques, it is possible to enhance traditional transformer health monitoring techniques with data-driven and expert-based prognostics and health management (PHM) applications. Accordingly, this paper reviews the experience of the authors in the implementation of machine learning methods for transformer condition monitoring.

Original language	English
Pages (from-to)	1-9
Number of pages	9
Journal	Transformers Magazine
Publication status	Published - 28 Nov 2022

Keywords

machine learning
data analytics
transformer health monitoring
anomaly detection
diagnostics
prognostics

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

Aizpurua-etal-Transformers-2022-Prognostics-health-management-oriented-data-analytics-suite-for-transformer-health-monitoringAccepted author manuscript, 909 KBLicence: Strath_1

Cite this

@article{cb2de2fa6fe64e0799286cc479584d0e,

title = "Prognostics & health management oriented data analytics suite for transformer health monitoring",

abstract = "Condition monitoring of power transformers is crucial for the reliable and cost-effective operation of the power grid. The unexpected failure of a transformer can lead to different consequences ranging from a lack of export capability, with the corresponding economic penalties, to catastrophic failure, with the associated health, safety, and economic effects. With the advance of machine learning techniques, it is possible to enhance traditional transformer health monitoring techniques with data-driven and expert-based prognostics and health management (PHM) applications. Accordingly, this paper reviews the experience of the authors in the implementation of machine learning methods for transformer condition monitoring.",

keywords = "machine learning, data analytics, transformer health monitoring, anomaly detection, diagnostics, prognostics",

author = "Aizpurua, {Jose Ignacio} and Stewart, {Brian G.} and McArthur, {Stephen D. J.}",

note = "Published in Special Issue - ML & AI",

year = "2022",

month = nov,

day = "28",

language = "English",

pages = "1--9",

journal = "Transformers Magazine",

}

TY - JOUR

T1 - Prognostics & health management oriented data analytics suite for transformer health monitoring

AU - Aizpurua, Jose Ignacio

AU - Stewart, Brian G.

AU - McArthur, Stephen D. J.

N1 - Published in Special Issue - ML & AI

PY - 2022/11/28

Y1 - 2022/11/28

N2 - Condition monitoring of power transformers is crucial for the reliable and cost-effective operation of the power grid. The unexpected failure of a transformer can lead to different consequences ranging from a lack of export capability, with the corresponding economic penalties, to catastrophic failure, with the associated health, safety, and economic effects. With the advance of machine learning techniques, it is possible to enhance traditional transformer health monitoring techniques with data-driven and expert-based prognostics and health management (PHM) applications. Accordingly, this paper reviews the experience of the authors in the implementation of machine learning methods for transformer condition monitoring.

AB - Condition monitoring of power transformers is crucial for the reliable and cost-effective operation of the power grid. The unexpected failure of a transformer can lead to different consequences ranging from a lack of export capability, with the corresponding economic penalties, to catastrophic failure, with the associated health, safety, and economic effects. With the advance of machine learning techniques, it is possible to enhance traditional transformer health monitoring techniques with data-driven and expert-based prognostics and health management (PHM) applications. Accordingly, this paper reviews the experience of the authors in the implementation of machine learning methods for transformer condition monitoring.

KW - machine learning

KW - data analytics

KW - transformer health monitoring

KW - anomaly detection

KW - diagnostics

KW - prognostics

UR - https://transformers-magazine.com/magazine/prognostics-and-health-management-oriented-data-analytics-suite-for-transformer-health-monitoring/

UR - https://transformers-magazine.com/

M3 - Article

SP - 1

EP - 9

JO - Transformers Magazine

JF - Transformers Magazine

ER -

Prognostics & health management oriented data analytics suite for transformer health monitoring

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Hybrid transformer prognostics framework for enhanced probabilistic predictions in renewable energy applications

Probabilistic forecasting informed failure prognostics framework for improved RUL prediction under uncertainty: a transformer case study

Uncertainty-aware fusion of probabilistic classifiers for improved transformer diagnostics

Cite this