Multifault diagnosis of rolling element bearings using a wavelet kurtogram and vector median-based feature analysis

Abstract

This paper presents a comprehensive multifault diagnosis methodology for incipient rolling element bearing failures. This is done by combining a wavelet packet transform- (WPT-) based kurtogram and a new vector median-based feature analysis technique. The proposed approach first extracts useful features that are characteristic of the bearing health condition from the time domain, frequency domain, and envelope power spectrum of incoming acoustic emission (AE) signals by using a WPT-based kurtogram. Then, an enhanced feature analysis approach based on the linear discriminant analysis (LDA) technique is used to select the most discriminant bearing fault features from the original feature set. These selected fault features are used by a Naïve Bayes (NB) classifier to classify the bearing fault conditions. The performance of the proposed methodology is tested and validated under various bearing fault conditions on an experimental test rig and compared with conventional state-of-the-art approaches. The proposed bearing fault diagnosis methodology yields average classification accuracies of 91.11%, 96.67%, 98.89%, 99.44%, and 98.61% at rotational speeds of 300, 350, 400, 450, and 500 rpm, respectively.