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

TL;DR

This paper investigates non-stationarity in wind turbine SCADA data by analyzing correlation matrices, revealing state-dependent structures influenced by wind speed, and proposes an automated method to account for these variations in failure detection.

Contribution

It introduces a methodology using correlation matrices and clustering to detect non-stationarity in wind turbine data related to operational states and wind speed.

Findings

Correlation structures vary with wind speed and turbine states.

Clustering reveals distinct operational states based on correlation matrices.

Method enables automated pre-processing considering non-stationarity.

Abstract

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 a quantitative assessment of non-stationarity in mutual dependencies of different types of data. We show that a clustering algorithm applied to the correlation matrices reveals distinct correlation structures for different states. Looking first at only one and then at multiple turbines, the main dependence of these states is shown to be on wind speed. This is in accordance with known turbine control systems, which change the behavior of the turbine depending on the available wind speed. We model the boundary wind speeds separating the states based on the clustering solution. Our analysis shows that for high frequency data the control mechanisms of a turbine lead to detectable non-stationarity in the correlation matrix. The presented methodology allows accounting for this with an automated pre-processing by sorting new data based on wind speed and comparing it to the respective operational state, thereby taking the non-stationarity into account for an analysis.