Robust condition monitoring of rolling element bearings using de-noising and envelope analysis with signal decomposition techniques

Abstract

This study presents a robust condition monitoring methodology for rolling element bearings that employs a novel empirical mode decomposition (EMD)-based method to eliminate high-level noise from an acoustic emission (AE) signal and a discrete wavelet packet transform (DWPT)-based envelope analysis technique to effectively search for symptoms of defective bearings. First, the proposed EMD-based de-noising scheme enhances the signal-to-noise ratio by using a Naïve Bayes classifier that partitions intrinsic mode functions (IMFs) into noise-dominant and noise-free categories, employing a soft-thresholding-based noise reduction technique for the noise-dominant IMFs, finally obtaining a de-noised acoustic emission (AE) signal via the reconstruction process using both de-noised IMFs and noise-free IMFs. The de-noised AE signal is then decomposed into a set of uniformly spaced sub-bands using three-level DWPT, and the most informative sub-band is determined for early detection of bearing failures. The performance of the proposed condition monitoring scheme is compared with the performance of conventional methods in terms of mean-peak ratio (MPR), which is a metric used to evaluate the degree of defectiveness of the bearings. The experimental results show that the proposed method outperforms the conventional schemes by achieving up to 23.48% higher MPR values, even in a very noisy environment.