Normal Behaviour Models for Wind Turbine Vibrations: Comparison of Neural Networks and a Stochastic Approach

DC FieldValueLanguage
dc.contributor.authorLind, Pedro G.
dc.contributor.authorVera-Tudela, Luis
dc.contributor.authorWaehter, Matthias
dc.contributor.authorKuehn, Martin
dc.contributor.authorPeinke, Joachim
dc.date.accessioned2021-12-23T16:11:22Z-
dc.date.available2021-12-23T16:11:22Z-
dc.date.issued2017
dc.identifier.urihttps://osnascholar.ub.uni-osnabrueck.de/handle/unios/9671-
dc.description.abstractTo monitor wind turbine vibrations, normal behaviour models are built to predict tower top accelerations and drive-train vibrations. Signal deviations from model prediction are labelled as anomalies and are further investigated. In this paper we assess a stochastic approach to reconstruct the 1 Hz tower top acceleration signal, which was measured in a wind turbine located at the wind farm Alpha Ventus in the German North Sea. We compare the resulting data reconstruction with that of a model based on a neural network, which has been previously reported as a data-mining algorithm suitable for reconstructing this signal. Our results present evidence that the stochastic approach outperforms the neural network in the high frequency domain (1 Hz). Although neural network retrieves accurate step-forward predictions, with low mean square errors, the stochastic approach predictions better preserve the statistics and the frequency components of the original signal, retaining high accuracy levels. The implementation of our stochastic approach is available as open source code and can easily be adapted for other situations involving stochastic data reconstruction. Based on our findings we argue that such an approach could be implemented in signal reconstruction for monitoring purposes or for abnormal behaviour detection.
dc.description.sponsorshipGerman Federal Ministry of Economic Affairs and Energy; State of Lower Saxony as part of the research project ``Probabilistic load description, monitoring, and reduction for the next generation of offshore wind turbines (OWEA Loads)'' [0325577B]; Ministry of Science and Culture of Lower Saxony in the project ``Ventus Efficiens'' [ZN3024]; Deutsche ForschungsgemeinschaftGerman Research Foundation (DFG) [MA 1636/9-1]; Osnabruck University; This work was partly funded by the German Federal Ministry of Economic Affairs and Energy and the State of Lower Saxony as part of the research project ``Probabilistic load description, monitoring, and reduction for the next generation of offshore wind turbines (OWEA Loads)'', grant number 0325577B, and also by the Ministry of Science and Culture of Lower Saxony in the project ``Ventus Efficiens'' (ZN3024). Additionally, financial support from the Deutsche Forschungsgemeinschaft (MA 1636/9-1) and the Open Access Publishing Fund of Osnabruck University is gratefully acknowledged. The authors also thank Senvion SE for providing the data here analyzed.
dc.language.isoen
dc.publisherMDPI
dc.relation.ispartofENERGIES
dc.subjectcondition monitoring
dc.subjectEnergy & Fuels
dc.subjectneural networks
dc.subjectsignal reconstruction
dc.subjectstochastic modelling
dc.subjectSYSTEMS
dc.subjecttower acceleration
dc.subjectwind turbine
dc.titleNormal Behaviour Models for Wind Turbine Vibrations: Comparison of Neural Networks and a Stochastic Approach
dc.typejournal article
dc.identifier.doi10.3390/en10121944
dc.identifier.isiISI:000423156900015
dc.description.volume10
dc.description.issue12
dc.contributor.orcid0000-0002-0775-7423
dc.contributor.orcid0000-0002-8176-666X
dc.contributor.orcid0000-0003-0506-9288
dc.contributor.researcheridAAB-9194-2021
dc.contributor.researcheridG-5124-2010
dc.contributor.researcheridQ-1664-2016
dc.identifier.eissn19961073
dc.publisher.placeST ALBAN-ANLAGE 66, CH-4052 BASEL, SWITZERLAND
dcterms.isPartOf.abbreviationEnergies
dcterms.oaStatusGreen Submitted, gold
Show simple item record

Google ScholarTM

Check

Altmetric