0
Technical Briefs

A Combination of WKNN to Fault Diagnosis of Rolling Element Bearings

[+] Author and Article Information
Yaguo Lei

State Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong University, Xi’an 710049, P. R. Chinaleiyaguo@gmail.com

Zhengjia He, Yanyang Zi

State Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong University, Xi’an 710049, P. R. China

J. Vib. Acoust 131(6), 064502 (Nov 20, 2009) (6 pages) doi:10.1115/1.4000478 History: Received October 31, 2008; Revised August 28, 2009; Published November 20, 2009

This paper presents a new method for fault diagnosis of rolling element bearings, which is developed based on a combination of weighted K nearest neighbor (WKNN) classifiers. This method uses wavelet packet transform based on the lifting scheme to preprocess the vibration signals before feature extraction. Time- and frequency-domain features are all extracted to represent the operation conditions of the bearings totally. Sensitive features are selected after feature extraction. And then, multiple classifiers based on WKNN are combined to overcome the two disadvantages of KNN and therefore it may enhance the classification accuracy. The experimental results of the proposed method to fault diagnosis of the rolling element bearings show that this method enables the detection of abnormalities in bearings and at the same time identification of fault categories and levels.

FIGURES IN THIS ARTICLE
<>
Copyright © 2009 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Flowchart of the proposed method

Grahic Jump Location
Figure 2

Experiment system

Grahic Jump Location
Figure 3

Experiment results using individual KNN classifiers and the proposed method for different fault categories

Grahic Jump Location
Figure 4

Experiment results using individual KNN classifiers and the proposed method for different fault levels

Grahic Jump Location
Figure 5

Sensitivity measurements of 150 features of data set F

Grahic Jump Location
Figure 6

Experiment results using individual KNN classifiers and the proposed method for different fault categories and levels

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