Wind Turbine Generator Short Circuit Fault Detection Using a Hybrid Approach of Wavelet Transform and Naïve Bayes Classifier

Wind turbines are subjected to several failure modes during their operation. A wind turbine drivetrain generally consists of rotor, bearings, low and high-speed shafts, gearbox, brakes, and generator. Single phase-to-phase and single phase-to-ground faults are among common electrical failure modes in the generator. In this paper, feature extraction has been performed using the Discrete Wavelet Transform (DWT) to detect the electrical faults in the wind turbine generator. A two-stage prediction process is proposed using Naïve Bayes Classifier (NBC), where the healthy and faulty modes are first determined, followed by classifying the types of electrical faults. Three-phase stator currents are used as fault detection signals. The performance of the proposed algorithm has been evaluated in Simulink for a 1659 kW wind turbine drivetrain.