Data-driven proactive and predictive maintenance of power distribution systems

Lasse Kappel Mortensen; Hamid Reza Shaker; Christian Veje

Data-driven proactive and predictive maintenance of power distribution systems

Lasse Kappel Mortensen^*, Hamid Reza Shaker, Christian Veje

^*Kontaktforfatter

Publikation: Bidrag til tidsskrift › Konferenceabstrakt i tidsskrift › Forskning › peer review

Abstract

Motivated by the inefficient preventive and corrective maintenance strategies typically employed in nowadays power
distribution systems and the advances in machine learning, this poster paper proposes research that aims to enable the
application of predictive maintenance strategies in power distribution systems. Predictive maintenance relies on
continuous monitoring of the power system to provide timely fault warnings, so remedial actions can be taken before
permanent failures occur. Because fault data can be scarce for power distribution systems and the employment of highfidelity sensors can be lacking, this poster paper proposes the use of data-driven models that can be developed with
limited fault data or using data with a low sampling frequency.

Originalsprog	Engelsk
Artikelnummer	P2
Tidsskrift	Energy Informatics
Vol/bind	4
Udgave nummer	Suppl. 1
ISSN	2520-8942
Status	Udgivet - 24. sep. 2021
Begivenhed	1st Energy Informatics.Academy Conference Asia - Ph.d. workshop - Sino Danish Center Sustainable Energy, Beijing, Kina Varighed: 28. maj 2021 → 28. maj 2021 Konferencens nummer: 1 https://www.energyinformatics.academy/eia-asia-2021-conference

Workshop

Workshop	1st Energy Informatics.Academy Conference Asia - Ph.d. workshop
Nummer	1
Lokation	Sino Danish Center Sustainable Energy
Land/Område	Kina
By	Beijing
Periode	28/05/2021 → 28/05/2021
Internetadresse	https://www.energyinformatics.academy/eia-asia-2021-conference

Dokumenter og links

https://energyinformatics.springeropen.com/articles/10.1186/s42162-021-00145-9#Sec9Licens: CC BY

1 Afsluttet

Smart Fault Prediction and Location for Distribution Grids
Shaker, H. R. (CoPI)
01/03/2020 → 01/03/2023
Projekter: Projekt › Forskning

Citationsformater

@article{e04a7f20c0c64f118ce29a30d7079252,

title = "Data-driven proactive and predictive maintenance of power distribution systems",

abstract = "Motivated by the inefficient preventive and corrective maintenance strategies typically employed in nowadays power distribution systems and the advances in machine learning, this poster paper proposes research that aims to enable the application of predictive maintenance strategies in power distribution systems. Predictive maintenance relies on continuous monitoring of the power system to provide timely fault warnings, so remedial actions can be taken before permanent failures occur. Because fault data can be scarce for power distribution systems and the employment of highfidelity sensors can be lacking, this poster paper proposes the use of data-driven models that can be developed with limited fault data or using data with a low sampling frequency.",

author = "Mortensen, {Lasse Kappel} and Shaker, {Hamid Reza} and Christian Veje",

year = "2021",

month = sep,

day = "24",

language = "English",

volume = "4",

journal = "Energy Informatics",

issn = "2520-8942",

publisher = "Springer",

number = "Suppl. 1",

note = "1st Energy Informatics.Academy Conference Asia - Ph.d. workshop, EI.A Asia 2021 ; Conference date: 28-05-2021 Through 28-05-2021",

url = "https://www.energyinformatics.academy/eia-asia-2021-conference",

}

TY - ABST

T1 - Data-driven proactive and predictive maintenance of power distribution systems

AU - Mortensen, Lasse Kappel

AU - Shaker, Hamid Reza

AU - Veje, Christian

N1 - Conference code: 1

PY - 2021/9/24

Y1 - 2021/9/24

N2 - Motivated by the inefficient preventive and corrective maintenance strategies typically employed in nowadays power distribution systems and the advances in machine learning, this poster paper proposes research that aims to enable the application of predictive maintenance strategies in power distribution systems. Predictive maintenance relies on continuous monitoring of the power system to provide timely fault warnings, so remedial actions can be taken before permanent failures occur. Because fault data can be scarce for power distribution systems and the employment of highfidelity sensors can be lacking, this poster paper proposes the use of data-driven models that can be developed with limited fault data or using data with a low sampling frequency.

AB - Motivated by the inefficient preventive and corrective maintenance strategies typically employed in nowadays power distribution systems and the advances in machine learning, this poster paper proposes research that aims to enable the application of predictive maintenance strategies in power distribution systems. Predictive maintenance relies on continuous monitoring of the power system to provide timely fault warnings, so remedial actions can be taken before permanent failures occur. Because fault data can be scarce for power distribution systems and the employment of highfidelity sensors can be lacking, this poster paper proposes the use of data-driven models that can be developed with limited fault data or using data with a low sampling frequency.

M3 - Conference abstract in journal

SN - 2520-8942

VL - 4

JO - Energy Informatics

JF - Energy Informatics

IS - Suppl. 1

M1 - P2

T2 - 1st Energy Informatics.Academy Conference Asia - Ph.d. workshop

Y2 - 28 May 2021 through 28 May 2021

ER -

Data-driven proactive and predictive maintenance of power distribution systems

Abstract

Workshop

Dokumenter og links

Fingeraftryk

Relaterede projekter

Smart Fault Prediction and Location for Distribution Grids

Citationsformater