Next Article in Journal
Separation of BTX Fraction from Reservoir Brines by Sorption onto Hydrophobized Biomass in a Fixed-Bed-Column System
Next Article in Special Issue
Reducing Operational Costs of Offshore HVDC Energy Export Systems Through Optimized Maintenance
Previous Article in Journal
A Novel Load Scheduling Mechanism Using Artificial Neural Network Based Customer Profiles in Smart Grid
Previous Article in Special Issue
Research on the Fault Characteristic of Wind Turbine Generator System Considering the Spatiotemporal Distribution of the Actual Wind Speed
Article

Evaluation of Anomaly Detection of an Autoencoder Based on Maintenace Information and Scada-Data

1
Fraunhofer Institute for Energy Economics and Energy System Technology, Königstor 59, 34119 Kassel, Germany
2
Trianel Windpark Borkum GmbH und Co. KG, Zirkusweg 2, 20359 Hamburg, Germany
3
STEAG Energy Services GmbH, Rüttenscheider Str. 1-3, 45128 Essen, Germany
*
Author to whom correspondence should be addressed.
Current address: Fraunhofer Institute for Energy Economics and Energy System Technology, Königstor 59, 34119 Kassel, Germany.
Energies 2020, 13(5), 1063; https://doi.org/10.3390/en13051063
Received: 20 December 2019 / Revised: 19 February 2020 / Accepted: 20 February 2020 / Published: 29 February 2020
(This article belongs to the Special Issue Maintenance Management of Wind Turbines)
The usage of machine learning techniques is widely spread and has also been implemented in the wind industry in the last years. Many of these techniques have shown great success but need to constantly prove the expectation of functionality. This paper describes a new method to monitor the health of a wind turbine using an undercomplete autoencoder. To evaluate the health monitoring quality of the autoencoder, the number of anomalies before an event has happened are to be considered. The results show that around 35% of all historical events that have resulted into a failure show many anomalies. Furthermore, the wind turbine subsystems which are subject to good detectability are the rotor system and the control system. If only one third of the service duties can be planned in advance, and thereby the scheduling time can be reduced, huge cost saving potentials can be seen. View Full-Text
Keywords: wind turbine; maintenance; autoencoder; machine learning; reliability; data driven model; service; performance wind turbine; maintenance; autoencoder; machine learning; reliability; data driven model; service; performance
Show Figures

Figure 1

MDPI and ACS Style

Lutz, M.-A.; Vogt, S.; Berkhout, V.; Faulstich, S.; Dienst, S.; Steinmetz, U.; Gück, C.; Ortega, A. Evaluation of Anomaly Detection of an Autoencoder Based on Maintenace Information and Scada-Data. Energies 2020, 13, 1063. https://doi.org/10.3390/en13051063

AMA Style

Lutz M-A, Vogt S, Berkhout V, Faulstich S, Dienst S, Steinmetz U, Gück C, Ortega A. Evaluation of Anomaly Detection of an Autoencoder Based on Maintenace Information and Scada-Data. Energies. 2020; 13(5):1063. https://doi.org/10.3390/en13051063

Chicago/Turabian Style

Lutz, Marc-Alexander, Stephan Vogt, Volker Berkhout, Stefan Faulstich, Steffen Dienst, Urs Steinmetz, Christian Gück, and Andres Ortega. 2020. "Evaluation of Anomaly Detection of an Autoencoder Based on Maintenace Information and Scada-Data" Energies 13, no. 5: 1063. https://doi.org/10.3390/en13051063

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop