Strong classification system for wear identification on milling processes using computer vision and ensemble learning

Metallic pieces are typically machined by continuous tool passes, which usually causes regular patterns in the form of straight edges in the surface of the pieces. An irregular pattern on the surface of the piece implies a decrease of the quality of the machined piece. In this paper, we propose an a...

Descripción completa

Detalles Bibliográficos
Autores: Riego Del Castillo, Virginia, Castejón Limas, Manuel, Sánchez González, Lidia, Fernández Robles, Laura, Pérez García, Hilde, Díez González, Javier, Guerrero Higueras, Ángel Manuel
Tipo de recurso: artículo
Estado:Versión enviada para evaluación y publicación
Fecha de publicación:2021
País:España
Institución:Ajuntament de Barcelona
Repositorio:BULERIA. Repositorio Institucional de la Universidad de León
OAI Identifier:oai:buleria.unileon.es:10612/18274
Acceso en línea:https://hdl.handle.net/10612/18274
Access Level:acceso abierto
Palabra clave:Ingenierías
classifier, machine learning
clasificador
id ES_66ef889653e4c60f9df0ea077e3befb3
oai_identifier_str oai:buleria.unileon.es:10612/18274
network_acronym_str ES
network_name_str España
repository_id_str
spelling Strong classification system for wear identification on milling processes using computer vision and ensemble learningSistema con clasificador fuerte para la identificación del desgaste en mecanizado usando visión por computador y ensemble learningRiego Del Castillo, VirginiaCastejón Limas, ManuelSánchez González, LidiaFernández Robles, LauraPérez García, HildeDíez González, JavierGuerrero Higueras, Ángel ManuelIngenieríasclassifier, machine learningclasificadorMetallic pieces are typically machined by continuous tool passes, which usually causes regular patterns in the form of straight edges in the surface of the pieces. An irregular pattern on the surface of the piece implies a decrease of the quality of the machined piece. In this paper, we propose an acquisition system and a machine-vision based method to describe the texture of the inner and outer surfaces of machined pieces with cylindrical holes. In order to capture images of the hole surface, we used a microscope camera connected to a rigid industrial boroscope. Considering the extracted texture descriptors, a significant correlation is shown. Consequently, the feature vector is reduced and then classified by several algorithms using an exhaustive grid search strategy with 10 fold cross validation. Best results are achieved with the Extremely Randomized Trees classifier with a mean test score on the hold out set of 92.98%, what improves previous research and meets the requirements of the field.SIMinisterio de Economía, Industria y CompetitividadElsevierProyectos de IngenieriaEscuela de Ingenierias Industrial, Informática y Aeroespacial2021info:eu-repo/semantics/articleinfo:eu-repo/semantics/submittedVersionhttps://hdl.handle.net/10612/18274reponame:BULERIA. Repositorio Institucional de la Universidad de Leóninstname:Ajuntament de BarcelonaInglésDPI2016-79960-C3-2-P.http://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:buleria.unileon.es:10612/182742026-06-24T12:43:27Z
dc.title.none.fl_str_mv Strong classification system for wear identification on milling processes using computer vision and ensemble learning
Sistema con clasificador fuerte para la identificación del desgaste en mecanizado usando visión por computador y ensemble learning
title Strong classification system for wear identification on milling processes using computer vision and ensemble learning
spellingShingle Strong classification system for wear identification on milling processes using computer vision and ensemble learning
Riego Del Castillo, Virginia
Ingenierías
classifier, machine learning
clasificador
title_short Strong classification system for wear identification on milling processes using computer vision and ensemble learning
title_full Strong classification system for wear identification on milling processes using computer vision and ensemble learning
title_fullStr Strong classification system for wear identification on milling processes using computer vision and ensemble learning
title_full_unstemmed Strong classification system for wear identification on milling processes using computer vision and ensemble learning
title_sort Strong classification system for wear identification on milling processes using computer vision and ensemble learning
dc.creator.none.fl_str_mv Riego Del Castillo, Virginia
Castejón Limas, Manuel
Sánchez González, Lidia
Fernández Robles, Laura
Pérez García, Hilde
Díez González, Javier
Guerrero Higueras, Ángel Manuel
author Riego Del Castillo, Virginia
author_facet Riego Del Castillo, Virginia
Castejón Limas, Manuel
Sánchez González, Lidia
Fernández Robles, Laura
Pérez García, Hilde
Díez González, Javier
Guerrero Higueras, Ángel Manuel
author_role author
author2 Castejón Limas, Manuel
Sánchez González, Lidia
Fernández Robles, Laura
Pérez García, Hilde
Díez González, Javier
Guerrero Higueras, Ángel Manuel
author2_role author
author
author
author
author
author
dc.contributor.none.fl_str_mv Proyectos de Ingenieria
Escuela de Ingenierias Industrial, Informática y Aeroespacial
dc.subject.none.fl_str_mv Ingenierías
classifier, machine learning
clasificador
topic Ingenierías
classifier, machine learning
clasificador
description Metallic pieces are typically machined by continuous tool passes, which usually causes regular patterns in the form of straight edges in the surface of the pieces. An irregular pattern on the surface of the piece implies a decrease of the quality of the machined piece. In this paper, we propose an acquisition system and a machine-vision based method to describe the texture of the inner and outer surfaces of machined pieces with cylindrical holes. In order to capture images of the hole surface, we used a microscope camera connected to a rigid industrial boroscope. Considering the extracted texture descriptors, a significant correlation is shown. Consequently, the feature vector is reduced and then classified by several algorithms using an exhaustive grid search strategy with 10 fold cross validation. Best results are achieved with the Extremely Randomized Trees classifier with a mean test score on the hold out set of 92.98%, what improves previous research and meets the requirements of the field.
publishDate 2021
dc.date.none.fl_str_mv 2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/submittedVersion
format article
status_str submittedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/10612/18274
url https://hdl.handle.net/10612/18274
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv DPI2016-79960-C3-2-P.
dc.rights.none.fl_str_mv http://creativecommons.org/licenses/by-nc-nd/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:BULERIA. Repositorio Institucional de la Universidad de León
instname:Ajuntament de Barcelona
instname_str Ajuntament de Barcelona
reponame_str BULERIA. Repositorio Institucional de la Universidad de León
collection BULERIA. Repositorio Institucional de la Universidad de León
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869409853115465728
score 15.301629

Similares en LA Referencia