Real-time rolling bearing power loss in wind turbine gearbox modeling and prediction based on calculations and artificial neural network

Abstract

This paper investigates the bearing power loss in gearbox for wind turbines under actual operating wind speed. Actual power loss values are calculated using calibrated SKF model for three different wind turbine gearbox oils. The gearbox applied load at each operating step is determined by using the wind turbine power curve. Wind data from experiments in Cameroon are used for validation. The back-propagation neural network is designed for actual power loss modeling and predicting desired values. The achieved results revealed that the bearing power loss is highly influenced by the wind turbine operating parameters, capacity, and oil. The difference between actual and neural network predicted bearing power loss values under real-time operating parameters showed the effectiveness of the proposed approach.