Fault Frequency Identification of Rolling Bearing Using Reinforced Ensemble Local Mean Decomposition

Bo Qin,Juanjuan Zhang,Quanyi Luo,Zixian Li,Yan Qin,Manuel Pineda-Sanchez

doi:10.1155/2021/2744193

Abstract

The vibration signal of rolling bearing exhibits the characteristics of energy attenuation and complex time-varying modulation caused by the transmission with multiple interfaces and complex paths. In view of this, strong ambient noise easily masks faulty signs of rolling bearings, resulting in inaccurate identification or even totally missing the real fault frequencies. To overcome this problem, we propose a reinforced ensemble local mean decomposition method to capture and screen the essential faulty frequencies of rolling bearing, further boosting fault diagnosis accuracy. Firstly, the vibration signal is decomposed into a series of preliminary features through ensemble local mean decomposition, and then the frequency components above the average level are energy-enhanced. In this way, principal frequency components related to rolling bearing failure can be identified with the fast spectral kurtosis algorithm. Finally, the efficacy of the proposed approach is verified through both a benchmark case and a practical platform. The results show that the selected fault characteristic components are accurate, and the identification and diagnosis of rolling bearing status are improved. Especially for the signals with strong noise, the proposed method still could accurately diagnose fault frequency.

Highlights

With the merits of low skin friction drag, high rotation speed, and standardized size, rolling bearings, referred to as ball bearings, have been extensively deployed in mechanical transmission systems [1], including but not limited to highspeed trains, vehicles, and wind turbines
Results and Discussion is section verifies the efficacy of the proposed method through two cases. e first one is a benchmark provided by the Case Western Reserve University (CWRU) [23,24,25]. e second one is a self-built test platform to measure the vibration signal of the rolling bearing. e detailed information about data processing, testing result, and conclusion will be carefully illustrated
Based on the SIEMENS-LMS Test Lab multichannel data acquisition instrument and the diagnostic comprehensive test platform of Spectra Quest, we developed a testing system as shown in Figure 9 to collect vibration data of the rolling bearing. e experimental data were further used to verify the efficacy of the proposed algorithm

Summary

Introduction

With the merits of low skin friction drag, high rotation speed, and standardized size, rolling bearings, referred to as ball bearings, have been extensively deployed in mechanical transmission systems [1], including but not limited to highspeed trains, vehicles, and wind turbines. The rolling bearings are used in harsh conditions, such as frequent turn on and off, time-varying load, and so on. Coupled with multiple negative factors, these complex working conditions make the cages, inner raceways, and outer rollers of rolling bearings prone to fall into failure. Erefore, it becomes an urgent demand for a timely and accurate health evaluation method for rolling bearing, providing safe and efficient operation of the concerned transmission system. To determine the location and degree of rolling bearing failure, it extracts fault frequency from the abundant state information in the measured vibration signal. Vibration signals of rolling bearings measured on industrial sites show energy attenuation and complex timevarying modulation characteristics after being transmitted through multiple interfaces and complex paths. The essential components of early failures are often

Methods

Results

Conclusion