Vibration-based fault diagnosis of a rotor bearing system using artificial neural network and support vector machine

This paper presents the vibration analysis of the healthy and cracked rotor supported on various faulty bearings. In rotating machines, one of the main causes of breakdown is faults in ball bearings. This study is mainly focused on fault diagnosis of rotor bearing system using artificial neural network (ANN) and support vector machine (SVM). The vibration response is obtained and analysed for the healthy and cracked rotor with the various defects of ball bearings. The specific defects considered on bearings are: crack in outer race, inner race with spall and corrosion pitting in balls. Statistical methods are used to extract features and to reduce the dimensionality of original vibration features. A comparative experimental study of the effectiveness of ANN and SVM is carried out. The results show that for this study, ANN is a better classifier than SVM.