0
Research Papers

Performance Degradation Assessment for Bearing Based on Ensemble Empirical Mode Decomposition and Gaussian Mixture Model

[+] Author and Article Information
Sheng Hong, Baoqing Wang

Science & Technology Laboratory
on Reliability & Environmental Engineering,
School of Reliability and System Engineering,
Beihang University,
No. 37, Xue Yuan Road,
Beijing 100191, China

Guoqi Li

Science & Technology Laboratory
on Reliability & Environmental Engineering,
School of Reliability and System Engineering,
Beihang University,
No. 37 Xue Yuan Road,
Beijing 100191, China
e-mail: gqli@buaa.edu.cn

Qian Hong

Affiliated Clinic of Jiangxi Province,
Huimin Hospital of Jiangxi Province,
No. 146 Beijing West Road,
Nanchang 330046, China

1Corresponding author.

Contributed by the Technical Committee on Vibration and Sound of ASME for publication in the JOURNAL OF VIBRATION AND ACOUSTICS. Manuscript received November 25, 2013; final manuscript received August 5, 2014; published online September 1, 2014. Assoc. Editor: Patrick S. Keogh.

J. Vib. Acoust 136(6), 061006 (Sep 01, 2014) (8 pages) Paper No: VIB-13-1411; doi: 10.1115/1.4028321 History: Received November 25, 2013; Revised August 05, 2014

This paper proposes a novel performance degradation assessment method for bearing based on ensemble empirical mode decomposition (EEMD), and Gaussian mixture model (GMM). EEMD is applied to preprocess the nonstationary vibration signals and get the feature space. GMM is utilized to approximate the density distribution of the lower-dimensional feature space processed by principal component analysis (PCA). The confidence value (CV) is calculated based on the overlap between the distribution of the baseline feature space and that of the testing feature space to indicate the performance of the bearing. The experiment results demonstrate the effectiveness of the proposed method.

FIGURES IN THIS ARTICLE
<>
Copyright © 2014 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 2

Process of equipment performance degradation assessment

Grahic Jump Location
Fig. 1

Sliding window algorithm

Grahic Jump Location
Fig. 3

Bearing test-rig and sensor placement illustration

Grahic Jump Location
Fig. 8

The result of GMM approximation to (a) the baseline feature space, (b) the normal and baseline feature space, and (c) the degraded and baseline feature space

Grahic Jump Location
Fig. 4

The original signal of the bearing

Grahic Jump Location
Fig. 5

The EEMD decomposed results of vibration signal of the bearing

Grahic Jump Location
Fig. 6

Extracted energy features: (a) the energy feature of PC1 and (b) the energy feature of PC2

Grahic Jump Location
Fig. 7

BIC values for normal condition data

Grahic Jump Location
Fig. 9

Features in time-domain (a) RMS, (b) kurtosis, (c) crest factor, and (d) skewness

Grahic Jump Location
Fig. 10

CVs calculated by GMM, time-domain features and SOM

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In