The Study of Three-Dimensional Analysis Techniques and Automatic Classification Systems for Wear Particles

[+] Author and Article Information
Z. Peng, T. B. Kirk

Department of Mechanical and Materials Engineering, The University of Western Australia, Nedlands, WA 6907, Australia

J. Tribol 121(1), 169-176 (Jan 01, 1999) (8 pages) doi:10.1115/1.2833799 History: Received December 01, 1997; Revised March 25, 1998; Online January 24, 2008


Although the morphology of wear debris generated in a machine has a direct relationship to wear processes and machine condition, studying wear particles for machine condition monitoring has not been widely applied in Industry as it is time consuming and requires certain expertise of analysts. To overcome these obstacles, automatic wear particle analysis and identification systems need to be developed. In this paper, laser scanning confocal microscopy has been used to obtain three-dimensional images of metallic wear particles. An analysis system has been developed and applied to study the boundary morphology and surface topography of the wear debris. After conducting the image analysis procedure and selecting critical criteria from dozens of available parameters, neural networks and grey systems have been investigated to classify unknown patterns using the numerical descriptors. It is demonstrated that the combination of the image analysis system and automatic classification systems has provided an automatic package for wear particle study which may be applied to industrial applications in the future.

Copyright © 1999 by The American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.





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