Applying design knowledge and machine learning to scada data for classification of wind turbine operating regimes

Braulio Barahona, Cyprien Hoelzl, Eleni N. Chatzi

Abstract: Wind turbines operate under non-stationary dynamic loads to which they constantly adapt by regulating the orientation of the blades and the rotor, as well as the generator torque resulting in characteristic responses (i.e. operating regimes) over a range of operating conditions. We propose a method to classify the operating regimes from coarse resolution data recorded by the turbine supervisory controller (i.e. data from the SCADA system). It relies on design knowledge, and algorithms for dimensionality reduction and classification. High resolution acceleration measurements from a custom structural state monitoring system and a data set of several channels from the SCADA system are used for validation. Estimation of the level of damage accumulated on structural components based on the classification of operating regimes is shown as an application.