In situ condition monitoring of floating offshorewind turbines using kurtosis anddeep-learning-based approaches

Abstract

This study introduces a comparison between a kurtosis analysis and a deep-learning-based approach for condition monitoring of a floating offshore wind turbine. The study uses in situ measurements from a 2.3 MW floating offshore wind turbine named Zefyros, deployed approximately 11 km off the coast of Norway. The first method employs the statistical metric of kurtosis to detect unusual behaviours within a signal by identifying variations in the signal distribution. The second method employs a deep-learning procedure based on an autoencoder approach, which transforms inputs into a reduced-dimensional latent space and then uses the encoded information to produce outputs identical to the inputs. One month of SCADA and high-frequency measurements obtained thanks to S-Morpho sensors were used in the study. Due to limitations in the accessible SCADA information, the anomaly scenario was simplified to detecting whether the turbine rotor was rotating or not. Both tested methodologies can accurately detect unwanted downtime periods, with the ground truth based on rotor rotations per minute (RPM) measurements. The autoencoder method shows promising results, delivering more accurate outcomes than the kurtosis analysis on this in situ measurement dataset. This study is a first step toward a more general use of autoencoders for wind turbine condition monitoring. The latent space built by the autoencoder can be leveraged to detect other types of unusual behaviour, with few labelled data.