Anomaly detection of wind turbines based on stationarity analysis of SCADA data
Phong B. Dao, Tomasz Barszcz, Wiesław J. Staszewski
Abstract
This study presents a stationarity-based method, based on sliding window principle, for wind turbine monitoring and anomaly detection. Initially, the window is formed with a reference data set collected from a wind turbine under healthy condition. During the monitoring process, the data window is regularly updated with the latest samples recorded by the SCADA system. The Augmented Dickey-Fuller (ADF) test is exploited to compute the stationary statistical characteristics of the data within the window at each updating step. Any abrupt changes in the ADF t-statistics indicate the fault occurrence. The method can simultaneously monitor various parameters without using normal behaviour models. Its monitoring and fault detection mechanism relies on the consecutive accumulation of variations in stationarity of SCADA signals in the data window over time. Through the validation using two SCADA data sets, the method has proven its capability in monitoring wind turbines and detecting faults at the early stage.