Technical Briefs

An Approach for the Construction of Entropy Measure and Energy Map in Machine Fault Diagnosis

[+] Author and Article Information
R. Tafreshi

Department of Mechanical Engineering, Texas A&M University at Qatar, P.O. Box 136 College Station, TX, 77844, USArtafreshi@tamu.edu

F. Sassani

Department of Mechanical Engineering, University of British Columbia, V6T 1Z4 Vancouver, BC, Canadasassani@mech.ubc.ca

H. Ahmadi1

Department of Electrical and Computer Engineering, University of British Columbia, V6T 1Z2 Vancouver, BC, Canadanoubari@ece.ubc.ca

G. Dumont

Department of Electrical and Computer Engineering, University of British Columbia, V6T 1Z2 Vancouver, BC, Canadaguyd@ece.ubc.ca


Also with the Department of Electrical and Computer Engineering University of Tehran, Center of Excellence in Intelligent Signal Processing.

J. Vib. Acoust 131(2), 024501 (Feb 13, 2009) (7 pages) doi:10.1115/1.2980367 History: Received June 29, 2005; Revised July 02, 2008; Published February 13, 2009

This paper presents a novel wavelet-based methodology for feature extraction and classification. To compare the performance of the proposed approach with major existing methods, a number of sets of real-world machine data acquired by mounting accelerometer sensors on the cylinder head of an engine have been extensively tested. The developed method not only bypasses the demerits of the previous techniques but also demonstrates superior performance.

Copyright © 2009 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Figure 1

Decomposition tree in a wavelet packet

Grahic Jump Location
Figure 2

One cycle of three classes of vertical vibrations with spark timings of −23deg, −33deg, and −10deg of crank angle, in stoichiometric conditions, 1500rpm and 25kHz sampling rates. The vertical axis unit is g.

Grahic Jump Location
Figure 3

Histograms and mean-std plots of training and testing data for three classes

Grahic Jump Location
Figure 4

Fast Fourier transform of vertical vibrations in combustion zone with 25kHz sampling rate and three classes of spark timing: −23deg, −33deg, and −10deg of crank angle

Grahic Jump Location
Figure 5

The first eight bases selected by MLDB using Coiflet1

Grahic Jump Location
Figure 6

Discriminant measure of the complete orthogonal 128 bases

Grahic Jump Location
Figure 7

LDB classification percentage error versus MLDB for the 32 different analyzing wavelets listed above



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