Prediction of the friction torque of scaled blade bearings in a test rig using machine learning

Abstract

Blade bearing friction torque is a required parameter for the design of a pitch actuator, and deviations from a bearing’s initial torque can be utilized for condition monitoring of the bearing. The torque of large-scale bearings can, however, be difficult to predict due to quality fluctuations in the production of these large-scale components. Therefore, this paper employs machine learning approaches to predict the torque of a given set of bearings in a controlled test environment based on measurement data from that same set of bearings. Possible applications of the model include use for condition monitoring by checking for deviations from the bearing’s initial behavior.