Detection of rotor imbalance, including root cause, severity and location

This paper presents a new way of detecting imbalances on wind turbine rotors, by using a harmonic analysis of the rotor response in the fixed frame. The method is capable of distinguishing among different root causes of the imbalance. In addition, the imbalance severity and location, i.e. the affected blade, can be identified. The automatic classification of the imbalance problem is obtained by using a neural network. The performance of the method is illustrated with the help of different fault scenarios, within a high-fidelity simulation environment.