Fault Prediction and Classification for a Doubly-Fed Induction Generator based Wind Turbine by using Random Forest Classifier

A detailed holistic doubly fed induction generator (DFIG) based wind turbine model is developed by interfacing FAST with Simulink. The effects of power converter faults on the mechanical systems are investigated and the collected simulation dataset is then evaluated under fault-free, and different faulty, scenarios. Then, this paper considers Random Forest Classifier as an efficient faulty prognosis through examination of the dataset. This method allows power converter faults to be predicted, and classified, in advance of their occurrences.