Fault Detection of Wind Turbine Pitch Motors Based on Ensemble Learning Approach

Abstract Machine learning-based condition monitoring of wind turbines’ critical components is an active area research, especially for pitch systems, which suffer from a high failure rate. In this work, we successfully predicted and detected the high-temperature fault electric motor by analyzing SCADA data through ensemble approach. For that, normal behavior models to predict temperature were constructed respectively three motors gradient boosting tree regression. Residual evolution before reported was studied sliding window A Shewhart control chart applied detect anomalies temperature. The proposed approach gave early warning potential around ten days prior system.