Surface feature recognition of wear debris

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)


Microscopic wear debris is produced in all machines containing moving parts in contact. The debris (particles), transported by a lubricant from wear sites; carry important information relating to the condition of the machinery. This information is classified by compositional and six morphological attributes of particle size, shape, edge details, color, thickness ratio, and surface texture. The paper describes an automated system for surface features recognition of wear particles by using artificial neural networks. The aim is to classify these particles according to their morphological attributes and by using the information obtained, to predict wear failure modes in engines and other machinery. This approach will enable the manufacturing industry to improve quality, productivity and economy. The procedure reported in this paper is based on gray level cooccurrence matrices, that are used to train a feed-forward neural network classifier in order to distinguish among seven different patterns of wear particles. The patterns are: smooth, rough, striations, holes, pitted, cracked, and serrated. An accuracy classification rate of 94.6% has been achieved and is shown by a confusion matrix.

Original languageEnglish
Title of host publicationAI 2002
Subtitle of host publicationAdvances in Artificial Intelligence - 15th Australian Joint Conference on Artificial Intelligence, Proceedings
EditorsBob McKay, John Slaney
PublisherSpringer Verlag
Number of pages11
ISBN (Print)3540001972, 9783540001973
Publication statusPublished - 2002
Event15th Australian Joint Conference on Artificial Intelligence, AI 2002 - Canberra, Australia
Duration: Dec 2 2002Dec 6 2002

Publication series

NameLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
ISSN (Print)0302-9743


Other15th Australian Joint Conference on Artificial Intelligence, AI 2002

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science


Dive into the research topics of 'Surface feature recognition of wear debris'. Together they form a unique fingerprint.

Cite this