Rolling bearing fault diagnosis based empirical wavelet transform using vibration signal

Abstract

Owing to the relevance and severity of damages caused by rolling bearing faults, the development and application of a robust fault detection methods that offer a high reliable diagnosis in terms of processing and performance are still demanding tasks. In this paper, an application of the empirical wavelet transform (EWT) method is proposed for the vibration signal analysis and fault diagnosis of rolling bearing. This method first detects the Fourier supports of the analyzed signal, build the corresponding wavelet accordingly to those supports, and then filter the signal with the obtained filter bank. The effectiveness of the method is validated using practical vibration signals. The results show that the EWT provides a good performance in the detection of outer and inner race faults.