Publication detail

Analysis Wear Debris Through Classification

JURÁNEK, R. MACHALÍK, S. ZEMČÍK, P.

Original Title

Analysis Wear Debris Through Classification

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

This paper introduces a novel method of wear debris analysis through classification of the particles based on machine learning. Wear debris consists of particles of metal found in e.g. lubricant oils used in engineering equipment.  Analytical ferrography is one of methods for wear debris analysis and it is very important for early detection or even prevention of failures in engineering equipment, such as combustion engines, gearboxes, etc.  The proposed novel method relies on classification of wear debris particles into several classes defined by the origin of such particles. Unlike the earlier methods, the proposed classification approach is based on visual similarity of the particles and supervised machine learning. The paper describes the method itself, demonstrates its experimental results, and draws conclusions.

Keywords

Wear, Wear Debris, Classification, AdaBoost, CS-LBP, LBP

Authors

JURÁNEK, R.; MACHALÍK, S.; ZEMČÍK, P.

RIV year

2011

Released

22. 8. 2011

Publisher

Springer Verlag

Location

Heidelberg

ISBN

978-3-642-23686-0

Book

Proceedings of Advanced Concepts of Inteligent Vision Systems (ACIVS 2011)

Edition

Lecture Notes in Computer Science

Pages from

273

Pages to

283

Pages count

11

BibTex

@inproceedings{BUT76367,
  author="Roman {Juránek} and Stanislav {Machalík} and Pavel {Zemčík}",
  title="Analysis Wear Debris Through Classification",
  booktitle="Proceedings of Advanced Concepts of Inteligent Vision Systems (ACIVS 2011)",
  year="2011",
  series="Lecture Notes in Computer Science",
  volume="6915",
  pages="273--283",
  publisher="Springer Verlag",
  address="Heidelberg",
  isbn="978-3-642-23686-0"
}