Non-stationarity in correlation matrices for wind turbine SCADA-data and implications for failure detection

Modern utility-scale wind turbines are equipped with a Supervisory Control And Data Acquisition (SCADA) system gathering vast amounts of operational data that can be used for analysis to improve operation and maintenance of turbines. We analyze high frequency SCADA-data from the Thanet offshore wind farm in the UK and evaluate Pearson correlation matrices for a variety of observables with a moving time window. This renders possible an assessment of non-stationarity in mutual dependencies of different types of data. Drawing from our experience in other complex systems, such as financial markets and traffic, we show this by employing a hierarchical $k$-means clustering algorithm on the correlation matrices. The different clusters exhibit distinct typical correlation structures to which we refer as states. Looking first at only one and later at multiple turbines, the main dependence of these states is shown to be on wind speed. In accordance, we identify them as operational states arising from different settings in the turbine control system based on the available wind speed. We model the boundary wind speeds separating the states based on the clustering solution. This allows the usage of our methodology as a pre-processing for analysis, e.g. failure detection or prediction, by sorting new data based on wind speed and comparing it to the respective operational state, thereby taking the non-stationarity into account.