0
Research Papers

Application of the Laplace-Wavelet Combined With ANN for Rolling Bearing Fault Diagnosis

[+] Author and Article Information
Khalid F. Al-Raheem

Department of Mechanical and Industrial Engineering, Caledonian College of Engineering, Sultanate of Oman, P.O. Box No. 2322, CPO Seeb, South Al-Hail 111, Omankhalid@caledonian.edu.om

Asok Roy, D. K. Harrison, Steven Grainger

School of Engineering Science and Design, Glasgow Caledonian University, Cowcaddens Road, Glasgow G4 0BA, Scotland

K. P. Ramachandran

Department of Mechanical and Industrial Engineering, Caledonian College of Engineering, Sultanate of Oman, P.O. Box No. 2322, CPO Seeb, South Al-Hail 111, Oman

J. Vib. Acoust 130(5), 051007 (Aug 14, 2008) (9 pages) doi:10.1115/1.2948399 History: Received May 26, 2007; Revised January 15, 2008; Published August 14, 2008

A new technique for an automated detection and diagnosis of rolling bearing faults is presented. The time-domain vibration signals of rolling bearings with different fault conditions are preprocessed using Laplace-wavelet transform for features’ extraction. The extracted features for wavelet transform coefficients in time and frequency domains are applied as input vectors to artificial neural networks (ANNs) for rolling bearing fault classification. The Laplace-Wavelet shape and the ANN classifier parameters are optimized using a genetic algorithm. To reduce the computation cost, decrease the size, and enhance the reliability of the ANN, only the predominant wavelet transform scales are selected for features’ extraction. The results for both real and simulated bearing vibration data show the effectiveness of the proposed technique for bearing condition identification with very high success rates using minimum input features.

FIGURES IN THIS ARTICLE
<>
Copyright © 2008 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

(a) The complex Laplace wavelet, (b) real part, (c) imaginary part, and (d) its FFT spectrum

Grahic Jump Location
Figure 2

(a) The optimal values for Laplace-wavelet parameters based on maximum kurtosis; (b) GA final population for the CWRU vibration data

Grahic Jump Location
Figure 3

The kurtosis distribution for the Laplace-wavelet transforms scales using (a) Morlet wavelet and (b) Laplace wavelet

Grahic Jump Location
Figure 4

(a) The applied diagnosis system, (b) the input and hidden layers, and (c) the hidden and output layers

Grahic Jump Location
Figure 5

(a) The extracted features’ distribution, (b) ANN learning process, (c) ANN classification MSE, and (d) ANN training/test process, for the CWRU bearing vibration data

Grahic Jump Location
Figure 6

(a) The extracted features’ distribution, (b) ANN learning process, (c) ANN classification MSE, and (d) ANN training/test process, for the simulated bearing vibration data

Grahic Jump Location
Figure 7

(a) The extracted features’ distribution, (b) ANN learning process, (c) ANN classification MSE, and (d) ANN training/test process, for the experimental bearing vibration data

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