University of PardubiceFaculty of Transport Engineering

University

Employees
|
Students
Česky

Publication detail

Wear debris image analysis

Authors: Machalík Stanislav | Juránek Roman | Zemčík Pavel

Year: 2013

Type of publication: odborná kniha

Publisher name: Univerzita Pardubice

Place: Pardubice

Page from-to: nestránkováno

Titles:

Language	Name	Abstract	Keywords
cze	Obrazová analýza částic opotřebení	Cílem této knihy je popsat možnosti využití obrazové analýzy v kombinaci s metodou analytické ferrografie a blíže představit nově vyvinutý automatický klasifikátor ? nástroj pro automatickou klasifikaci částic, který se ze vzorových obrazů částic učí klasifikovat obrazy částic pořízených metodou analytické ferrografie.	Obrazová; analýza; částic; opotřebení
eng	Wear debris image analysis	The wear debris of various engineering equipment (such as combustion engines, gearboxes, etc.) consists of particles of metal which can be obtained in lubricants used in such machine parts. The analysis the the wear particles is very important for early detection and prevention of failures in engineering equipment. The analysis is often done through the classi cation of individual wear particles obtained by analytical ferrography. In this paper, we present a study of feature extraction methods for a classi cation of the wear particles based on visual similarity (using supervised machine learning). The contribution of the paper is the comparison of nine selected feature types in the context of three state-of-the-art learning models. The second contribution is the large public database of binary images of particles which can be used for further experiments. The paper describes the dataset, methods of classi cation, demonstrates experimental results, and draws conclusions.	Wear; debris; image; analysis