Distinct Fault Analysis of Induction Motor Bearing Using Frequency Spectrum Determination and Support Vector Machine

Abstract

In modern industrial environment, the demand for condition monitoring and maintenance management for the induction motor has increased. Among all the components of the induction motor, bearing is the critical component and the fault occurring in it has to be considered as a major issue. Usually, the bearing fault can be detected by the vibrational analysis. However, this method has a disadvantage that location of the equipment is not always easily accessible, and also it is quite costly. Thus, in this paper, an experiment for detecting the fault in the bearing of a three phase induction motor is achieved by the frequency selection in the stator-current spectrum. Their feature was evaluated by the fast Fourier transform and the diagnosis was performed by a support vector machine. Experimental results were obtained considering two types of outer raceway bearing faults at different load conditions and promising results were obtained.