0
Research Papers

Feature Selection for Fault Detection in Rolling Element Bearings Using Mutual Information

[+] Author and Article Information
Karthik Kappaganthu1

Sr. Controls & Diagnostics Research Engineer,  Advanced Engineering, Cummins Inc., Columbus, IN 47201 e-mail: karthik.kappaganthu@cummins.com

C. Nataraj

Professor and Chair,  Department of Mechanical Engineering, Villanova University, Villanova, PA 19085 e-mail: nataraj@villanova.edu

1

Corresponding author.

J. Vib. Acoust 133(6), 061001 (Sep 09, 2011) (11 pages) doi:10.1115/1.4003400 History: Received July 08, 2010; Revised October 30, 2010; Published September 09, 2011; Online September 09, 2011

Rolling element bearings are among the key components in many rotating machineries. It is hence necessary to determine the condition of the bearing with a reasonable degree of confidence. Many techniques have been developed for bearing fault detection. Each of these techniques has its own strengths and weaknesses. In this paper, various features are compared for detecting inner and outer race defects in rolling element bearings. Mutual information between the feature and the defect is used as a quantitative measure of quality. Various time, frequency, and time-frequency domain features are compared and ranked according to their cumulative mutual information content, and an optimal feature set is determined for bearing classification. The performance of this optimal feature set is evaluated using an artificial neural network with one hidden layer. An overall classification accuracy of 97% was obtained over a range of rotating speeds.

FIGURES IN THIS ARTICLE
<>
Copyright © 2011 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 7

DWT (detail) of a defect-free bearing signal

Grahic Jump Location
Figure 8

DWT (detail) of a bearing signal with an outer race defect

Grahic Jump Location
Figure 9

DWT (detail) of a bearing signal with an inner race defect

Grahic Jump Location
Figure 10

Dependence of DWT detail energy on rotating speed

Grahic Jump Location
Figure 1

Algorithm for feature selection

Grahic Jump Location
Figure 2

Experimental setup

Grahic Jump Location
Figure 3

FFT of the measured outer race defect bearing signal

Grahic Jump Location
Figure 4

Feature extraction for a defect-free bearing

Grahic Jump Location
Figure 5

Feature extraction for a bearing with an outer race defect

Grahic Jump Location
Figure 6

Feature extraction for a bearing with an inner race defect

Grahic Jump Location
Figure 11

Mutual information for outer race defect classification

Grahic Jump Location
Figure 12

Mutual information for inner race defect classification

Grahic Jump Location
Figure 13

Classification performance on validation data for outer race defect classification

Grahic Jump Location
Figure 14

Classification performance on validation data for inner race defect classification

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