Weld bead detection based on 3D geometric features and machine learning approaches

14 p.

Bibliographic Details
Authors: Rodríguez Gonzálvez, Pablo, Rodríguez-Martín, Manuel
Format: article
Status:Published version
Publication Date:2019
Country:España
Institution:Universidad de León
Repository:BULERIA. Repositorio Institucional de la Universidad de León
OAI Identifier:oai:buleria.unileon.es:10612/12349
Online Access:http://hdl.handle.net/10612/12349
https://doi.org/10.1109/ACCESS.2019.2891367
Access Level:Open access
Keyword:Ingenierías
Welding
Machine learning
Decision tree
Weld bead
Photogrammetry
3D model
Non-destructive testing
id ES_044301a100fb26c2cdbe26ff4ba62ae3
oai_identifier_str oai:buleria.unileon.es:10612/12349
network_acronym_str ES
network_name_str España
repository_id_str
spelling Weld bead detection based on 3D geometric features and machine learning approachesRodríguez Gonzálvez, PabloRodríguez-Martín, ManuelIngenieríasWeldingMachine learningDecision treeWeld beadPhotogrammetry3D modelNon-destructive testing14 p.Weld bead detection is essential for automated welding inspection processes. The non-invasive passive techniques, such as photogrammetry, are quickly evolving to provide a 3D point cloud with submillimeter precision and spatial resolution. However, its application in weld visual inspection has not been extensively studied. The derived 3D point clouds, despite the lack of topological information, store significant information for the weld-plaque segmentation. Although the weld bead detection is being carried out over images or based on laser profiles, its characterization by means of 3D geometrical features has not been assessed. Moreover, it is possible to combine machine learning approaches and the 3D features in order to realize the full potential of the weld bead segmentation of 3D submillimeter point clouds. In this paper, the novelty is focused on the study of 3D features on real cases to identify the most relevant ones for weld bead detection on the basis of the information gain. For this novel contribution, the influence of neighborhood size for covariance matrix computation, decision tree algorithms, and split criteria are analyzed to assess the optimal results. The classification accuracy is evaluated by the degree of agreement of the classified data by the kappa index and the area under the receiver operating characteristic (ROC) curve. The experimental results show that the proposed novel methodology performs better than 0.85 for the kappa index and better than 0.95 for ROC area.SIIEEEIngeniería Cartografica, Geodesica y FotogrametriaEscuela Superior y Tecnica de Ingenieros de Minas2019info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://hdl.handle.net/10612/12349https://doi.org/10.1109/ACCESS.2019.2891367reponame:BULERIA. Repositorio Institucional de la Universidad de Leóninstname:Universidad de LeónInglésinfo:eu-repo/semantics/openAccessoai:buleria.unileon.es:10612/123492026-06-24T12:43:27Z
dc.title.none.fl_str_mv Weld bead detection based on 3D geometric features and machine learning approaches
title Weld bead detection based on 3D geometric features and machine learning approaches
spellingShingle Weld bead detection based on 3D geometric features and machine learning approaches
Rodríguez Gonzálvez, Pablo
Ingenierías
Welding
Machine learning
Decision tree
Weld bead
Photogrammetry
3D model
Non-destructive testing
title_short Weld bead detection based on 3D geometric features and machine learning approaches
title_full Weld bead detection based on 3D geometric features and machine learning approaches
title_fullStr Weld bead detection based on 3D geometric features and machine learning approaches
title_full_unstemmed Weld bead detection based on 3D geometric features and machine learning approaches
title_sort Weld bead detection based on 3D geometric features and machine learning approaches
dc.creator.none.fl_str_mv Rodríguez Gonzálvez, Pablo
Rodríguez-Martín, Manuel
author Rodríguez Gonzálvez, Pablo
author_facet Rodríguez Gonzálvez, Pablo
Rodríguez-Martín, Manuel
author_role author
author2 Rodríguez-Martín, Manuel
author2_role author
dc.contributor.none.fl_str_mv Ingeniería Cartografica, Geodesica y Fotogrametria
Escuela Superior y Tecnica de Ingenieros de Minas
dc.subject.none.fl_str_mv Ingenierías
Welding
Machine learning
Decision tree
Weld bead
Photogrammetry
3D model
Non-destructive testing
topic Ingenierías
Welding
Machine learning
Decision tree
Weld bead
Photogrammetry
3D model
Non-destructive testing
description 14 p.
publishDate 2019
dc.date.none.fl_str_mv 2019
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10612/12349
https://doi.org/10.1109/ACCESS.2019.2891367
url http://hdl.handle.net/10612/12349
https://doi.org/10.1109/ACCESS.2019.2891367
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv IEEE
publisher.none.fl_str_mv IEEE
dc.source.none.fl_str_mv reponame:BULERIA. Repositorio Institucional de la Universidad de León
instname:Universidad de León
instname_str Universidad de León
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_ 1869402781581836288
score 15,300719

Similar Items