Condition Monitoring of Wind Turbine Main Bearing Using SCADA Data and Informed by the Principle of Energy Conservation

Abstract

This work improves a condition monitoring approach for wind turbine main bearings based on data from the supervisory control and data acquisition system, and on the principle of energy conservation. Previous works have proposed a main bearing temperature parametric model which residue in respect to measured data was used to detect main bearing degradation. Such an approach allowed detections with anticipation of the failure of around one month for the analyzed case studies, showing therefore a good potential for industrial applications. The present work investigates a relaxed formulation of the parametric model and introduces a novel detection criterion based on the model coefficients. This new formulation is evaluated within an operating wind farm, showing improved detection capabilities, and longer anticipation of failures.