Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
https://doi.org/10.21256/zhaw-20433
Publikationstyp: | Konferenz: Paper |
Art der Begutachtung: | Peer review (Publikation) |
Titel: | Early fault detection based on wind turbine SCADA data using convolutional neural networks |
Autor/-in: | Ulmer, Markus Jarlskog, Eskil Pizza, Gianmarco Manninen, Jaakko Goren Huber, Lilach |
et. al: | No |
DOI: | 10.36001/phme.2020.v5i1.1217 10.21256/zhaw-20433 |
Tagungsband: | PHME 2020 : Proceedings of the 5th European Conference of the PHM Society |
Band(Heft): | 5 |
Heft: | 1 |
Angaben zur Konferenz: | 5th European Conference of the Prognostics and Health Management Society, Virtual Conference, 27-31 July 2020 |
Erscheinungsdatum: | Jul-2020 |
Verlag / Hrsg. Institution: | PHM Society |
ISBN: | 978-1-936263-32-5 |
Sprache: | Englisch |
Schlagwörter: | Fault detection; Fault diagnostics; Predictive maintenance; Wind turbines; Machine learning; Deep learning; Convolutional neural networks |
Fachgebiet (DDC): | 006: Spezielle Computerverfahren |
Zusammenfassung: | Early fault detection in wind turbines using the widely available SCADA data has been receiving growing interest due to its cost-effectiveness. As opposed to the large variety of fault detection methods based on high resolusion vibration data, the use of 10-minute SCADA data alone does not require any additional hardware or data storage solutions and would be immediately implementable in most wind farms. However, the strong variability of these data is challenging and requires significant improvements of existing methods to ensure early and reliable fault detection and isolation. Here we suggest to use Convolutional Neural Networks (CNNs) to enhance the detection accuracy and robustness. We demonstrate the superiority of the CNN model over standard fully connected neural networks (FCNN) using examples for faults with very different time dependent characteristics: an abruptly evolving and a slowly degrading fault. We show that the CNN is able to detect the faults earlier and with a higher accuracy and robustness of prediction than the FCNN model. We then extend the CNN model to a multi-output CNN (CNNm) which provides early fault detection based on a multitude of output variables simultaneously. We show that with the same training time and a similar detection quality as the single output CNN, the CNNm model is an ideal candidate for a practical and scalable fault detection algorithm based on already available 10-minute SCADA data for wind turbines. |
URI: | https://digitalcollection.zhaw.ch/handle/11475/20433 |
Volltext Version: | Publizierte Version |
Lizenz (gemäss Verlagsvertrag): | CC BY 3.0: Namensnennung 3.0 Unported |
Departement: | School of Engineering |
Organisationseinheit: | Institut für Datenanalyse und Prozessdesign (IDP) |
Publiziert im Rahmen des ZHAW-Projekts: | Machine Learning Based Fault Detection for Wind Turbines |
Enthalten in den Sammlungen: | Publikationen School of Engineering |
Dateien zu dieser Ressource:
Datei | Beschreibung | Größe | Format | |
---|---|---|---|---|
2020_Ulmer_etal_Early-fault-detection_PHM-Society.pdf | 1.41 MB | Adobe PDF | Öffnen/Anzeigen |
Zur Langanzeige
Ulmer, M., Jarlskog, E., Pizza, G., Manninen, J., & Goren Huber, L. (2020). Early fault detection based on wind turbine SCADA data using convolutional neural networks [Conference paper]. PHME 2020 : Proceedings of the 5th European Conference of the PHM Society, 5(1). https://doi.org/10.36001/phme.2020.v5i1.1217
Ulmer, M. et al. (2020) ‘Early fault detection based on wind turbine SCADA data using convolutional neural networks’, in PHME 2020 : Proceedings of the 5th European Conference of the PHM Society. PHM Society. Available at: https://doi.org/10.36001/phme.2020.v5i1.1217.
M. Ulmer, E. Jarlskog, G. Pizza, J. Manninen, and L. Goren Huber, “Early fault detection based on wind turbine SCADA data using convolutional neural networks,” in PHME 2020 : Proceedings of the 5th European Conference of the PHM Society, Jul. 2020, vol. 5, no. 1. doi: 10.36001/phme.2020.v5i1.1217.
ULMER, Markus, Eskil JARLSKOG, Gianmarco PIZZA, Jaakko MANNINEN und Lilach GOREN HUBER, 2020. Early fault detection based on wind turbine SCADA data using convolutional neural networks. In: PHME 2020 : Proceedings of the 5th European Conference of the PHM Society. Conference paper. PHM Society. Juli 2020. ISBN 978-1-936263-32-5
Ulmer, Markus, Eskil Jarlskog, Gianmarco Pizza, Jaakko Manninen, and Lilach Goren Huber. 2020. “Early Fault Detection Based on Wind Turbine SCADA Data Using Convolutional Neural Networks.” Conference paper. In PHME 2020 : Proceedings of the 5th European Conference of the PHM Society. Vol. 5. PHM Society. https://doi.org/10.36001/phme.2020.v5i1.1217.
Ulmer, Markus, et al. “Early Fault Detection Based on Wind Turbine SCADA Data Using Convolutional Neural Networks.” PHME 2020 : Proceedings of the 5th European Conference of the PHM Society, vol. 5, no. 1, PHM Society, 2020, https://doi.org/10.36001/phme.2020.v5i1.1217.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.