Data-Driven Wind Turbine Power Generation Performance Monitoring

This research investigates the wind turbine power generation performance monitoring based on SCADA data. The proposed approach identifies turbines with weakened power generation performance through assessing the wind power curve profiles. Profiles which statistically summarize the curvatures and shapes of a wind power curve over consecutive time intervals are constructed by fitting power curve models into SCADA datasets with a least square method. To monitor variations of wind power curve profiles over time, the multivariate and residual approaches are introduced and applied. Two blind industrial studies are conducted to validate the effectiveness of the proposed monitoring approach and the study results demonstrate a high accuracy of detecting abnormal power curve profiles of wind turbines as well as their associated time intervals.