A DATA MINING STUDY FOR CONDITION MONITORING ON WIND TURBINE BLADES USING HOEFFDING TREE ALGORITHM THROUGH STATISTICAL AND HISTOGRAM FEATURES

This paper presents an algorithmic classification of different faults which occur in variable wind turbine blade. The faults like blade bend, blade cracks, blade erosion, hub-blade loose connection and pitch angle twist were considered. Initially statistical and histogram features were extracted from the signal and required parameters were selected using J48 algorithm. Later, hoeffding tree algorithm (HTA) was chosen to classify the faults. The performance of HTA is compared with respect to the statistical features and histogram features. A better technique is suggested for condition monitoring of wind turbine blade.