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

Energies

Martin Kühn¹  Matthias Wächter¹  Luis Vera-Tudela¹  Joachim Peinke¹  Pedro G. Lind² 

[1]ForWind—Center for Wind Energy Research, Institute of Physics, Carl von Ossietzky University of Oldenburg, Küpkersweg 70, 26129 Oldenburg, Germany

[2]Institut für Physik, Universität Osnabrück, Barbarastrasse 7, 49076 Osnabrück, Germany

关键词: wind turbine;    tower acceleration;    condition monitoring;    signal reconstruction;    neural networks;    stochastic modelling;   

DOI  :  10.3390/en10121944

来源: DOAJ

【 摘 要 】

To 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.

【 授权许可】

Unknown