EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Exploring the Limits of Early Predictive Maintenance in Wind Turbines Applying an Anomaly Detection Technique

Mindaugas Jankauskas iD, Artūras Serackis iD, Martynas Šapurov iD, Raimondas Pomarnacki iD, Algirdas Baskys, Van Khang Hyunh iD, Toomas Vaimann iD, Janis Zakis iD

Sensors · 18.06.2023 · 23 (12) · 5695

DOI: 10.3390/s23125695 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 18.06.2023. Verfasst von Mindaugas Jankauskas und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Communications Technologies, Vilnius Gediminas Technical University, Saulėtekio al. 11, LT-10223 Vilnius, Lithuani…. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EEA and Norway Grants, EEA Grants.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The aim of the presented investigation is to explore the time gap between an anomaly appearance in continuously measured parameters of the device and a failure, related to the end of the remaining resource of the device-critical component. In this investigation, we propose a recurrent neural network to model the time series of the parameters of the healthy device to detect anomalies by comparing the predicted values with the ones actually measured. An experimental investigation was performed on SCADA estimates received from different wind turbines with failures. A recurrent neural network was used to predict the temperature of the gearbox. The comparison of the predicted temperature values and the actual measured ones showed that anomalies in the gearbox temperature could be detected up to 37 days before the failure of the device-critical component. The performed investigation compared different models that can be used for temperature time-series modeling and the influence of selected input features on the performance of temperature anomaly detection.

Schlagwörter

Stichwörter der Autor:innen

SCADAanomalyneural networktemperaturewind turbine

Autor:innen und Institutionen

  • Department of Computer Science and Communications Technologies, Vilnius Gediminas Technical University, Saulėtekio al. 11, LT-10223 Vilnius, Lithuania.
  • State Research Institute Center for Physical Sciences and Technology, Sauletekio Av. 3, LT-10257 Vilnius, Lithuania.
  • Department of Engineering Sciences, University of Agder, Postboks 422, 4604 Kristiansand, Norway.
  • Department of Electrical Power, Engineering and Mechatronics, Tallinn University of Technology, Ehitajate Tee 5, 12616 Tallinn, Estonia.
  • Institute of Industrial Electronics and Electrical Engineering, Riga Technical University, 12/1 Azenes Street, LV-1048 Riga, Latvia.

ORCID-Profile: Mindaugas Jankauskas, Artūras Serackis, Martynas Šapurov, Raimondas Pomarnacki, Van Khang Hyunh, Toomas Vaimann, Janis Zakis

Förderung

  • EEA and Norway Grants
  • EEA Grants

Zitieren

APA

Jankauskas, M., Serackis, A., Šapurov, M., Pomarnacki, R., Baskys, A., Hyunh, V. K., Vaimann, T., & Zakis, J. (2023). Exploring the Limits of Early Predictive Maintenance in Wind Turbines Applying an Anomaly Detection Technique. Sensors, 23(12), 5695. https://doi.org/10.3390/s23125695

Vancouver

Jankauskas M, Serackis A, Šapurov M, Pomarnacki R, Baskys A, Hyunh VK, et al. Exploring the Limits of Early Predictive Maintenance in Wind Turbines Applying an Anomaly Detection Technique. Sensors. 2023;23(12):5695. doi:10.3390/s23125695

BibTeX
@article{Jankauskas2023,
  author = {Jankauskas, Mindaugas and Serackis, Artūras and Šapurov, Martynas and Pomarnacki, Raimondas and Baskys, Algirdas and Hyunh, Van Khang and Vaimann, Toomas and Zakis, Janis},
  title = {Exploring the Limits of Early Predictive Maintenance in Wind Turbines Applying an Anomaly Detection Technique},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {12},
  pages = {5695},
  doi = {10.3390/s23125695}
}
Kostenlos starten →