Comparison of the supervised machine learning techniques using WPT for the fault diagnosis of cylindrical roller bearing

In this paper, a comparative study of the Artificial Intelligence (AI) techniques for condition monitoring cylindrical roller bearing is presented. For feature selection, wavelet analysis applied using ‘sym2’ as mother wavelet. Nine features are considered training and evaluation AI then effectiveness compared. Bearing sample data consists four different conditions having defective inner race, outer defects on healthy bearing. preparation bearing, laser machine used introduction micro size surfaces. Support Vector Machine (SVM), neural network (ANN), logistic regression with ranking method purpose their identifying major purpose. Feature new way filtering right in sequence training. results, Logistic found more accurate comparison ANN SVM