Condition monitoring and fault detection in wind turbines based on cointegration analysis of SCADA data

Abstract

Abstract This paper presents a new methodology – based on cointegration analysis of Supervisory Control And Data Acquisition (SCADA) data – for condition monitoring and fault diagnosis of wind turbines. Analysis of cointegration residuals – obtained from cointegration process of wind turbine data – is used for operational condition monitoring and automated fault and/or abnormal condition detection. The proposed method is validated using the experimental data acquired from a wind turbine drivetrain with a nominal power of 2 MW under varying environmental and operational conditions. A two-stage cointegration-based procedure is performed on six process parameters of the wind turbine, where data trends have nonlinear characteristics. The method is tested using two case studies with known faults. The results demonstrate that the proposed method can effectively analyse nonlinear data trends, continuously monitor the wind turbine and reliably detect abnormal problems.