Roller Bearing Performance Degradation Assessment Based on Fusion of Multiple Features of Electrostatic Sensors.

Ying Zhang,Hongfu Zuo,Anchen Wang

doi:10.3390/s19040824

Abstract

This paper presents a new method to assess the performance degradation of roller bearings based on the fusion of multiple features, with the aim of improving the early degradation detection ability of the electrostatic monitoring system. At first, a set of feature parameters of the electrostatic monitoring system indicating the normal state of the bearings are extracted from the perspective of the time domain, frequency domain and complexity. Then, the parameter set is processed to reduce the dimensions and eliminate the redundancy using spectral regression. With the processed features, a Gaussian mixed model is established to gauge the health of the bearing, providing the distance value obtained using Bayesian inference as a quantitative indicator for assessing the performance degradation. The method is applied to access the life of a bearing in which the mechanic fatigue is artificially accelerated. The test results show that the proposed method can better reflect the degradation process of the bearing compared to other evaluation methods. This enables the electrostatic monitoring technique to detect the degradation of the bearing earlier than the vibration monitoring, providing a powerful tool for the condition monitoring of roller bearings.

Highlights

Rolling bearings are one of the key components in rotating machinery, the degradation or failure of which will affect the performance of the whole machine, or even cause unplanned outage, resulting in economic losses or even mass casualties; its condition monitoring and diagnosis have always been a research focus [1]
Akhand Rai proposed a novel method for bearing performance degradation assessment based on an amalgamation of empirical mode decomposition (EMD) and k-medoids clustering; the results demonstrated that the method could confirm the early stage defect [21]
In our previous work [9], we found that Permutation Entropy (PE) could significantly bring forward the time when early faults are detected in electrostatic monitoring sensors, and PE can be used as a useful supplement to the features of electrostatic monitoring

Summary

Introduction

Rolling bearings are one of the key components in rotating machinery, the degradation or failure of which will affect the performance of the whole machine, or even cause unplanned outage, resulting in economic losses or even mass casualties; its condition monitoring and diagnosis have always been a research focus [1]. Henao summarized the application of the current signature analysis and advanced digital signal processing method in the diagnosis of electrical machines [2]. Frosini proposed a novel technique based on the stray flux measurement in different positions around the electrical machine [3]. A high-sensitivity monitoring technique based on electrostatic induction has emerged as a promising technique for the condition monitoring of roller bearings. It is based on electrostatic induction, and the advantage of this technique is that it measures a direct product of the fault, rather than secondary effects, such as increased vibration or temperature exceedance [5]. Harvey and Craig [5,6] implemented electrostatic wear-site sensors on a bearing test rig to evaluate their effectiveness in detecting bearing faults, using the root mean square (RMS) value of Sensors 2019, 19, 824; doi:10.3390/s19040824 www.mdpi.com/journal/sensors

Methods

Results

Conclusion