An Improved Empirical Wavelet Transform and Refined Composite Multiscale Dispersion Entropy-Based Fault Diagnosis Method for Rolling Bearing

Jinde Zheng,Kuosheng Jiang,Haiyang Pan,Siqi Huang

doi:10.1109/access.2019.2940627

Abstract

The vibration signals collected by the sensor often have non-stationary and non-linear characteristics owing to the complexity of working environment of rolling bearing, so it is difficult to obtain useful and stable vibration information for diagnosis. Empirical Wavelet Transform (EWT) can effectively decompose non-stationary and nonlinear signals, but it is not suitable for signal analysis of bearing with a complicated spectrum. In this paper, an improved EWT (IEWT) method is proposed by developing a new segmentation approach. Meanwhile, the IEWT is compared with empirical mode decomposition (EMD) and EWT to verify the superiority of IEWT in decomposition accuracy. By combining with the refined composite multiscale dispersion entropy (RCMDE), which is a powerful nonlinear tool for irregularity measurement of vibration signals, a new diagnosis method based on IEWT, RCMDE, multi-cluster feature selection and support vector machine is proposed. Then the method is applied to analysis of bearing in this paper and the results show that the new method has higher identifying rate and better performance than that of the methods of RCMDE combining with EMD or EWT. Also, the superiority of RCMDE to dispersion entropy and multiscale dispersion entropy is investigated, together with the superiority of MCFS for feature selection.

Highlights

Rolling bearing is an important component of rotating machines and its operating state affects the normal operation of the equipment
The proposed improved EWT (IEWT) method differs from Empirical Wavelet Transform (EWT) in that it is based on the maxima envelope to overcome the limitations of original EWT
A new fault diagnosis method based on IEWT, refined composite multiscale dispersion entropy (RCMDE), Multi-Cluster Feature Selection (MCFS) and Support Vector Machine (SVM) for rolling bearing is proposed in this paper and applied to experimental analysis of rolling bearing

Summary

INTRODUCTION

Rolling bearing is an important component of rotating machines and its operating state affects the normal operation of the equipment. J. Zheng et al.: IEWT and RCMDE-Based Fault Diagnosis Method for Rolling Bearing it can effectively decompose the collected original vibration signals into several intrinsic mode functions distributed from high frequency to low frequency. To overcome the deficiencies of the maximal midpoint position segmentation method in the original EWT, combined with the vibration signals characteristics of rolling bearings, an improved empirical wavelet transform (IEWT) is proposed based on spectral maxima envelope. The analysis accuracy of the certain frequency bands is improved by this segmentation method, it affects the analysis effect of the EWT method on other frequency ranges

IMPROVED EMPIRICAL WAVELET TRANSFORM METHOD

THE ROLLING BEARING FAULT DIAGNOSIS METHOD BASED ON IEWT AND RCMDE

EXPERIMENTAL DATA ANALYSIS OF ROLLING BEARING

CONCLUSION