1. ZHAW digitalcollection
  2. School of Engineering
  3. Publikationen
  4. Publikationen School of Engineering
Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-22774
Full metadata record
DC FieldValueLanguage
dc.contributor.authorZgraggen, Jannik-
dc.contributor.authorUlmer, Markus-
dc.contributor.authorJarlskog, Eskil-
dc.contributor.authorPizza, Gianmarco-
dc.contributor.authorGoren Huber, Lilach-
dc.date.accessioned2021-07-02T14:13:21Z-
dc.date.available2021-07-02T14:13:21Z-
dc.date.issued2021-06-29-
dc.identifier.isbn978-1-936263-34-9de_CH
dc.identifier.urihttps://papers.phmsociety.org/index.php/phme/article/view/2835de_CH
dc.identifier.urihttps://digitalcollection.zhaw.ch/handle/11475/22774-
dc.descriptionBest Paper Awardde_CH
dc.description.abstractImplementing machine learning and deep learning algorithms for wind turbine (WT) fault detection (FD) based on 10-minute SCADA data has become a relevant opportunity to reduce the operation and maintenance costs of wind farms. The development of practically implementable algorithms requires addressing the issue of their scalabililty to large wind farms. Two of the main challenges here are reducing the training times and enabling training with scarce or limited data. Both of these challenges can be addressed with the help of transfer learning (TL) methods, in which a base model is trained on a source WT and the learned knowledge is transferred to a target WT. In this paper we suggest three TL frameworks designed to transfer a semi-supervised FD task between turbines. As a base model we use a Convolutional Neural Network (CNN) which has been proven to perform well on the single turbine FD task. We test the three TL frameworks for transfer between WTs from the same farm and from different farms. We conclude that for the purpose of scaling up training for large farms, a simple TL based on linear regression transformation of the target predictions is an attractive high performance solution. For the challenging task of cross-farm TL based on scarce target data we show that a TL framework using combined linear regression and error-correction CNN outperforms the other methods. We demonstrate a scheme that enables the evaluation of different TL frameworks for FD without the need for labeled faults.de_CH
dc.language.isoende_CH
dc.publisherPHM Societyde_CH
dc.rightshttp://creativecommons.org/licenses/by/3.0/de_CH
dc.subjectPredictive maintenancede_CH
dc.subjectDeep learningde_CH
dc.subjectTransfer learningde_CH
dc.subjectWind turbinede_CH
dc.subjectRenewable energyde_CH
dc.subjectAnomaly detectionde_CH
dc.subject.ddc006: Spezielle Computerverfahrende_CH
dc.subject.ddc620: Ingenieurwesende_CH
dc.titleTransfer learning approaches for wind turbine fault detection using deep learningde_CH
dc.typeKonferenz: Paperde_CH
dcterms.typeTextde_CH
zhaw.departementSchool of Engineeringde_CH
zhaw.organisationalunitInstitut für Datenanalyse und Prozessdesign (IDP)de_CH
dc.identifier.doi10.21256/zhaw-22774-
zhaw.conference.details6th European Conference of the Prognostics and Health Management Society, online, 28 June - 2 July 2021de_CH
zhaw.funding.euNode_CH
zhaw.issue1de_CH
zhaw.originated.zhawYesde_CH
zhaw.pages.start12de_CH
zhaw.publication.statuspublishedVersionde_CH
zhaw.volume6de_CH
zhaw.publication.reviewPeer review (Publikation)de_CH
zhaw.title.proceedingsProceedings of the European Conference of the PHM Society 2021de_CH
zhaw.webfeedDatalabde_CH
zhaw.funding.zhawMachine Learning Based Fault Detection for Wind Turbinesde_CH
zhaw.author.additionalNode_CH
zhaw.display.portraitYesde_CH
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2021_Zgraggen-etal_Transfer-learning-approach-wind-turbine-fault-detection.pdf2.53 MBAdobe PDFThumbnail
View/Open
Show simple item record
Zgraggen, J., Ulmer, M., Jarlskog, E., Pizza, G., & Goren Huber, L. (2021). Transfer learning approaches for wind turbine fault detection using deep learning [Conference paper]. Proceedings of the European Conference of the PHM Society 2021, 6(1), 12. https://doi.org/10.21256/zhaw-22774
Zgraggen, J. et al. (2021) ‘Transfer learning approaches for wind turbine fault detection using deep learning’, in Proceedings of the European Conference of the PHM Society 2021. PHM Society, p. 12. Available at: https://doi.org/10.21256/zhaw-22774.
J. Zgraggen, M. Ulmer, E. Jarlskog, G. Pizza, and L. Goren Huber, “Transfer learning approaches for wind turbine fault detection using deep learning,” in Proceedings of the European Conference of the PHM Society 2021, Jun. 2021, vol. 6, no. 1, p. 12. doi: 10.21256/zhaw-22774.
ZGRAGGEN, Jannik, Markus ULMER, Eskil JARLSKOG, Gianmarco PIZZA und Lilach GOREN HUBER, 2021. Transfer learning approaches for wind turbine fault detection using deep learning. In: Proceedings of the European Conference of the PHM Society 2021 [online]. Conference paper. PHM Society. 29 Juni 2021. S. 12. ISBN 978-1-936263-34-9. Verfügbar unter: https://papers.phmsociety.org/index.php/phme/article/view/2835
Zgraggen, Jannik, Markus Ulmer, Eskil Jarlskog, Gianmarco Pizza, and Lilach Goren Huber. 2021. “Transfer Learning Approaches for Wind Turbine Fault Detection Using Deep Learning.” Conference paper. In Proceedings of the European Conference of the PHM Society 2021, 6:12. PHM Society. https://doi.org/10.21256/zhaw-22774.
Zgraggen, Jannik, et al. “Transfer Learning Approaches for Wind Turbine Fault Detection Using Deep Learning.” Proceedings of the European Conference of the PHM Society 2021, vol. 6, no. 1, PHM Society, 2021, p. 12, https://doi.org/10.21256/zhaw-22774.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.