Loading [MathJax]/extensions/tex2jax.js

Impact of using text classifiers for standardising maintenance data of wind turbines on reliability calculations

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autorschaft

  • Julia Walgern
  • Katharina Beckh
  • Neele Hannes
  • Martin Horn

Organisationseinheiten

Externe Organisationen

  • Fraunhofer-Institut für Windenergiesysteme (IWES)
  • University of Strathclyde
  • Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme (IAIS)
  • Rheinisch-Westfälische Technische Hochschule Aachen (RWTH)
  • Fraunhofer-Institut für Energiewirtschaft und Energiesystemtechnik (IEE)
  • Technical University of Denmark

Details

OriginalspracheEnglisch
Seiten (von - bis)3463-3479
Seitenumfang17
FachzeitschriftIET renewable power generation
Jahrgang18
Ausgabenummer15
PublikationsstatusVeröffentlicht - 18 Nov. 2024

Abstract

This study delves into the challenge of efficiently digitalising wind turbine maintenance data, traditionally hindered by non-standardised formats necessitating manual, expert intervention. Highlighting the discrepancies in past reliability studies based on different key performance indicators (KPIs), the paper underscores the importance of consistent standards, like RDS-PP, for maintenance data categorisation. Leveraging on established digitalisation workflows, we investigate the efficacy of text classifiers in automating the categorisation process against conventional manual labelling. Results indicate that while classifiers exhibit high performance for specific datasets, their general applicability across diverse wind farms is limited at the present stage. Furthermore, differences in failure rate KPIs derived from manual versus classifier-processed data reveal uncertainties in both methods. The study suggests that enhanced clarity in maintenance reporting and refined designation systems can lead to more accurate KPIs.

ASJC Scopus Sachgebiete

Ziele für nachhaltige Entwicklung

Zitieren

Impact of using text classifiers for standardising maintenance data of wind turbines on reliability calculations. / Walgern, Julia; Beckh, Katharina; Hannes, Neele et al.
in: IET renewable power generation, Jahrgang 18, Nr. 15, 18.11.2024, S. 3463-3479.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Walgern J, Beckh K, Hannes N, Horn M, Lutz MA, Fischer K et al. Impact of using text classifiers for standardising maintenance data of wind turbines on reliability calculations. IET renewable power generation. 2024 Nov 18;18(15):3463-3479. doi: 10.1049/rpg2.13151
Walgern, Julia ; Beckh, Katharina ; Hannes, Neele et al. / Impact of using text classifiers for standardising maintenance data of wind turbines on reliability calculations. in: IET renewable power generation. 2024 ; Jahrgang 18, Nr. 15. S. 3463-3479.
Download
@article{0b676300102649b1aa4b242cd3049ce3,
title = "Impact of using text classifiers for standardising maintenance data of wind turbines on reliability calculations",
abstract = "This study delves into the challenge of efficiently digitalising wind turbine maintenance data, traditionally hindered by non-standardised formats necessitating manual, expert intervention. Highlighting the discrepancies in past reliability studies based on different key performance indicators (KPIs), the paper underscores the importance of consistent standards, like RDS-PP, for maintenance data categorisation. Leveraging on established digitalisation workflows, we investigate the efficacy of text classifiers in automating the categorisation process against conventional manual labelling. Results indicate that while classifiers exhibit high performance for specific datasets, their general applicability across diverse wind farms is limited at the present stage. Furthermore, differences in failure rate KPIs derived from manual versus classifier-processed data reveal uncertainties in both methods. The study suggests that enhanced clarity in maintenance reporting and refined designation systems can lead to more accurate KPIs.",
keywords = "data acquisition, data analysis, reliability, sensitivity analysis, statistical analysis, wind power plants, wind turbines",
author = "Julia Walgern and Katharina Beckh and Neele Hannes and Martin Horn and Lutz, {Marc Alexander} and Katharina Fischer and Athanasios Kolios",
note = "Publisher Copyright: {\textcopyright} 2024 The Author(s). IET Renewable Power Generation published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.",
year = "2024",
month = nov,
day = "18",
doi = "10.1049/rpg2.13151",
language = "English",
volume = "18",
pages = "3463--3479",
journal = "IET renewable power generation",
issn = "1752-1416",
publisher = "Institution of Engineering and Technology",
number = "15",

}

Download

TY - JOUR

T1 - Impact of using text classifiers for standardising maintenance data of wind turbines on reliability calculations

AU - Walgern, Julia

AU - Beckh, Katharina

AU - Hannes, Neele

AU - Horn, Martin

AU - Lutz, Marc Alexander

AU - Fischer, Katharina

AU - Kolios, Athanasios

N1 - Publisher Copyright: © 2024 The Author(s). IET Renewable Power Generation published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.

PY - 2024/11/18

Y1 - 2024/11/18

N2 - This study delves into the challenge of efficiently digitalising wind turbine maintenance data, traditionally hindered by non-standardised formats necessitating manual, expert intervention. Highlighting the discrepancies in past reliability studies based on different key performance indicators (KPIs), the paper underscores the importance of consistent standards, like RDS-PP, for maintenance data categorisation. Leveraging on established digitalisation workflows, we investigate the efficacy of text classifiers in automating the categorisation process against conventional manual labelling. Results indicate that while classifiers exhibit high performance for specific datasets, their general applicability across diverse wind farms is limited at the present stage. Furthermore, differences in failure rate KPIs derived from manual versus classifier-processed data reveal uncertainties in both methods. The study suggests that enhanced clarity in maintenance reporting and refined designation systems can lead to more accurate KPIs.

AB - This study delves into the challenge of efficiently digitalising wind turbine maintenance data, traditionally hindered by non-standardised formats necessitating manual, expert intervention. Highlighting the discrepancies in past reliability studies based on different key performance indicators (KPIs), the paper underscores the importance of consistent standards, like RDS-PP, for maintenance data categorisation. Leveraging on established digitalisation workflows, we investigate the efficacy of text classifiers in automating the categorisation process against conventional manual labelling. Results indicate that while classifiers exhibit high performance for specific datasets, their general applicability across diverse wind farms is limited at the present stage. Furthermore, differences in failure rate KPIs derived from manual versus classifier-processed data reveal uncertainties in both methods. The study suggests that enhanced clarity in maintenance reporting and refined designation systems can lead to more accurate KPIs.

KW - data acquisition

KW - data analysis

KW - reliability

KW - sensitivity analysis

KW - statistical analysis

KW - wind power plants

KW - wind turbines

UR - http://www.scopus.com/inward/record.url?scp=85208241329&partnerID=8YFLogxK

U2 - 10.1049/rpg2.13151

DO - 10.1049/rpg2.13151

M3 - Article

AN - SCOPUS:85208241329

VL - 18

SP - 3463

EP - 3479

JO - IET renewable power generation

JF - IET renewable power generation

SN - 1752-1416

IS - 15

ER -