Publication detail

Research of Imgae Features for Classification of Wear Debris

MACHALÍK, S. JURÁNEK, R. ZEMČÍK, P.

Original Title

Research of Imgae Features for Classification of Wear Debris

English Title

Research of Imgae Features for Classification of Wear Debris

Type

journal article - other

Language

en

Original Abstract

The wear debris of various engineering equipment (such as combustion engines, gearboxes, etc.) consists of particles of metal which can be obtained from lubricants used in such machine parts. The analysis the wear particles is very important for early detection and prevention of failures in engineering equipment. The analysis is often done through classification of individual wear particles obtained by analytical ferrography. In this paper, we present a study of feature extraction methods for a classification of the wear particles based on visual similarity (using supervised machine learning). The main contribution of the paper is the comparison of nine selected feature types in the context of three state-of-the-art learning models. Another contribution is the large public database of binary images of particles which can be used for further experiments.

English abstract

The wear debris of various engineering equipment (such as combustion engines, gearboxes, etc.) consists of particles of metal which can be obtained from lubricants used in such machine parts. The analysis the wear particles is very important for early detection and prevention of failures in engineering equipment. The analysis is often done through classification of individual wear particles obtained by analytical ferrography. In this paper, we present a study of feature extraction methods for a classification of the wear particles based on visual similarity (using supervised machine learning). The main contribution of the paper is the comparison of nine selected feature types in the context of three state-of-the-art learning models. Another contribution is the large public database of binary images of particles which can be used for further experiments.

Keywords

Wear Debris, Classification, Supervised Machine Learning, SVM, Linear Regression,Features, PCA, HOG, LBP

RIV year

2012

Released

01.02.2012

Publisher

NEUVEDEN

Location

NEUVEDEN

Pages from

479

Pages to

493

Pages count

15

BibTex


@article{BUT91470,
  author="Stanislav {Machalík} and Roman {Juránek} and Pavel {Zemčík}",
  title="Research of Imgae Features for Classification of Wear Debris",
  annote="The wear debris of various engineering equipment (such as combustion engines,
gearboxes, etc.) consists of particles of metal which can be obtained from
lubricants used in such machine parts. The analysis the wear particles is very
important for early detection and prevention of failures in engineering
equipment. The analysis is often done through classification of individual wear
particles obtained by analytical ferrography. In this paper, we present a study
of feature extraction methods for a classification of the wear particles based on
visual similarity (using supervised machine learning). The main contribution of
the paper is the comparison of nine selected feature types in the context of
three state-of-the-art learning models. Another contribution is the large public
database of binary images of particles which can be used for further
experiments.",
  address="NEUVEDEN",
  chapter="91470",
  edition="NEUVEDEN",
  howpublished="print",
  institution="NEUVEDEN",
  number="1",
  volume="20",
  year="2012",
  month="february",
  pages="479--493",
  publisher="NEUVEDEN",
  type="journal article - other"
}