Health Degradation Monitoring of Rolling Element Bearing by Growing Self- Organizing Mapping and Clustered Support Vector Machine

Yiwei Cheng,Xinyu Shao,Kui Hu,Yuanhang Wang,Haiping Zhu,Jun Wu

doi:10.1109/access.2019.2937999

Abstract

Health degradation monitoring of rolling element bearing (REB) is of great significance to ensure safety and availability of mechanical equipment. This paper presents a new online health degradation monitoring method of REB based on growing self-organizing mapping (GSOM) and clustered support vector machine (CSVM). In the proposed method, multidimensional health degradation features of the REB are extracted to reflect health degradation process, including time-domain statistical features, frequency spectrum features, intrinsic mode function energy features, wavelet packet frequency band energy features. Multiple GSOMs are utilized to adaptively fuse each kind of the extracted features for the health indices. CSVM is constructed to achieve accurate health status identification of the REB. A health degradation experimental case of the REB is analyzed to demonstrate the effectiveness of the proposed method. The results show that the proposed method has obvious superior performance compared to other existing methods.

Highlights

Rolling element bearing (REB) is one of the most widely used parts in mechanical equipment, which is a precise mechanical element to change the sliding friction between the running shaft and the shaft seat into rolling friction so as to reduce friction loss [1], [2]
The features of REB are first extracted from the vibration signal, including Time-domain statistical feature (TDSF), Frequency spectrum feature (FSF), intrinsic mode function energy features (IMFEFs) and wavelet packet frequency band energy features (WPFBEFs)
The monitoring vibration signals at each time are collected in turn, and all kinds of features of the signals are extracted at the same time

Summary

INTRODUCTION

Rolling element bearing (REB) is one of the most widely used parts in mechanical equipment, which is a precise mechanical element to change the sliding friction between the running shaft and the shaft seat into rolling friction so as to reduce friction loss [1], [2]. Kim et al [9] utilized support vector machine to estimate the health state probability of REB degradation process. Ma et al [10] proposed a health state identification method for REB based on Weibull distribution and deep belief network. Chen et al [12] introduced a deep convolutional neural network-based health state identification method which can effectively identify the health status of REB and gear. A new health degradation monitoring method of REB is proposed based on growing self-organizing mapping (GSOM) and clustered support vector machine (CSVM). 3) An improved SVM model named CSVM is constructed to achieve accurate health state identification of REB, which tackles data in a divide-and-conquer way to realize faster training.

BACKGROUND

INTRINSIC MODE FUNCTION ENERGY FEATURE

WAVELET PACKET FREQUENCY BAND ENERGY FEATURE

CLUSTERED SUPPORT VECTOR MACHINES FOR HEALTH DEGRADATION IDENTIFICATION

Findings

CONCLUSION