Rolling element bearings multi-fault classification based on the wavelet denoising and support vector machine

Citation:

S. Abbasion, A. Rafsanjani, N. Irani, and A. Farshidianfar. 2007. “Rolling element bearings multi-fault classification based on the wavelet denoising and support vector machine.” Mechanical Systems and Signal Processing, 21, 7, Pp. 2933-2945. Publisher's Version

Abstract:

Due to the importance of rolling bearings as one of the most widely used industrial machinery elements, development of proper monitoring and fault diagnosis procedure to prevent malfunctioning and failure of these elements during operation is necessary. For rolling bearing fault detection, it is expected that a desired time–frequency analysis method has good computational efficiency, and has good resolution in both, time and frequency domains. The point of interest of this investigation is the presence of an effective method for multi-fault diagnosis in such systems with optimizing signal decomposition levels by using wavelet analysis and support vector machine (SVM). The system that is under study is an electric motor which has two rolling bearings, one of them is next to the output shaft and the other one is next to the fan and for each of them there is one normal form and three false forms, which make 8 forms for study. The results that we achieved from wavelet analysis and SVM are fully in agreement with empirical result.