Rolling element bearing health diagnosis – A comparative study of statistical features

Abstract

Rolling Element Bearing (REB) fault diagnosis is a widely researched theme. In this work, the raw vibration signal is denoised using Modified Kurtosis Hybrid Thresholding Rule (MKHTR). The denoised signal is subjected to Discrete Wavelet Transforms (DWT) and seventeen statistical features are extracted from the wavelet coefficients. Statistical Features selected using Kernel Fisher Discriminant Analysis (KFDA) are analysed using independent samples test and Mann Whitney U test to distinguish between a healthy and defective REB. Weibull negative log likelihood (WNLL) distinguishes between a healthy and defective REB at the significance level of 0.01 irrespective of the location of the defect. The methodology and outcomes of this study is expected to motivate the researchers to identify the statistical features that distinguish between a healthy and unhealthy REB.