Cargando…

A Novel Approach to the Holistic 3D Characterization of Weld Seams—Paving the Way for Deep Learning-Based Process Monitoring

In an industrial environment, the quality assurance of weld seams requires extensive efforts. The most commonly used methods for that are expensive and time-consuming destructive tests, since quality assurance procedures are difficult to integrate into production processes. Beyond that, available te...

Descripción completa

Detalles Bibliográficos
Autores principales: Schmoeller, Maximilian, Stadter, Christian, Kick, Michael Karl, Geiger, Christian, Zaeh, Michael Friedrich
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8619111/
https://www.ncbi.nlm.nih.gov/pubmed/34832330
http://dx.doi.org/10.3390/ma14226928
_version_ 1784604910885535744
author Schmoeller, Maximilian
Stadter, Christian
Kick, Michael Karl
Geiger, Christian
Zaeh, Michael Friedrich
author_facet Schmoeller, Maximilian
Stadter, Christian
Kick, Michael Karl
Geiger, Christian
Zaeh, Michael Friedrich
author_sort Schmoeller, Maximilian
collection PubMed
description In an industrial environment, the quality assurance of weld seams requires extensive efforts. The most commonly used methods for that are expensive and time-consuming destructive tests, since quality assurance procedures are difficult to integrate into production processes. Beyond that, available test methods allow only the assessment of a very limited set of characteristics. They are either suitable for determining selected geometric features or for locating and evaluating internal seam defects. The presented work describes an evaluation methodology based on microfocus X-ray computed tomography scans (µCT scans) which enable the 3D characterization of weld seams, including internal defects such as cracks and pores. A 3D representation of the weld contour, i.e., the complete geometry of the joint area in the component with all quality-relevant geometric criteria, is an unprecedented novelty. Both the dimensions of the weld seam and internal defects can be revealed, quantified with a resolution down to a few micrometers and precisely assigned to the welded component. On the basis of the methodology developed within the framework of this study, the results of the scans performed on the alloy AA 2219 can be transferred to other aluminum alloys. In this way, the data evaluation framework can be used to obtain extensive reference data for the calibration and validation of inline process monitoring systems employing Deep Learning-based data processing in the scope of subsequent work.
format Online
Article
Text
id pubmed-8619111
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-86191112021-11-27 A Novel Approach to the Holistic 3D Characterization of Weld Seams—Paving the Way for Deep Learning-Based Process Monitoring Schmoeller, Maximilian Stadter, Christian Kick, Michael Karl Geiger, Christian Zaeh, Michael Friedrich Materials (Basel) Article In an industrial environment, the quality assurance of weld seams requires extensive efforts. The most commonly used methods for that are expensive and time-consuming destructive tests, since quality assurance procedures are difficult to integrate into production processes. Beyond that, available test methods allow only the assessment of a very limited set of characteristics. They are either suitable for determining selected geometric features or for locating and evaluating internal seam defects. The presented work describes an evaluation methodology based on microfocus X-ray computed tomography scans (µCT scans) which enable the 3D characterization of weld seams, including internal defects such as cracks and pores. A 3D representation of the weld contour, i.e., the complete geometry of the joint area in the component with all quality-relevant geometric criteria, is an unprecedented novelty. Both the dimensions of the weld seam and internal defects can be revealed, quantified with a resolution down to a few micrometers and precisely assigned to the welded component. On the basis of the methodology developed within the framework of this study, the results of the scans performed on the alloy AA 2219 can be transferred to other aluminum alloys. In this way, the data evaluation framework can be used to obtain extensive reference data for the calibration and validation of inline process monitoring systems employing Deep Learning-based data processing in the scope of subsequent work. MDPI 2021-11-16 /pmc/articles/PMC8619111/ /pubmed/34832330 http://dx.doi.org/10.3390/ma14226928 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Schmoeller, Maximilian
Stadter, Christian
Kick, Michael Karl
Geiger, Christian
Zaeh, Michael Friedrich
A Novel Approach to the Holistic 3D Characterization of Weld Seams—Paving the Way for Deep Learning-Based Process Monitoring
title A Novel Approach to the Holistic 3D Characterization of Weld Seams—Paving the Way for Deep Learning-Based Process Monitoring
title_full A Novel Approach to the Holistic 3D Characterization of Weld Seams—Paving the Way for Deep Learning-Based Process Monitoring
title_fullStr A Novel Approach to the Holistic 3D Characterization of Weld Seams—Paving the Way for Deep Learning-Based Process Monitoring
title_full_unstemmed A Novel Approach to the Holistic 3D Characterization of Weld Seams—Paving the Way for Deep Learning-Based Process Monitoring
title_short A Novel Approach to the Holistic 3D Characterization of Weld Seams—Paving the Way for Deep Learning-Based Process Monitoring
title_sort novel approach to the holistic 3d characterization of weld seams—paving the way for deep learning-based process monitoring
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8619111/
https://www.ncbi.nlm.nih.gov/pubmed/34832330
http://dx.doi.org/10.3390/ma14226928
work_keys_str_mv AT schmoellermaximilian anovelapproachtotheholistic3dcharacterizationofweldseamspavingthewayfordeeplearningbasedprocessmonitoring
AT stadterchristian anovelapproachtotheholistic3dcharacterizationofweldseamspavingthewayfordeeplearningbasedprocessmonitoring
AT kickmichaelkarl anovelapproachtotheholistic3dcharacterizationofweldseamspavingthewayfordeeplearningbasedprocessmonitoring
AT geigerchristian anovelapproachtotheholistic3dcharacterizationofweldseamspavingthewayfordeeplearningbasedprocessmonitoring
AT zaehmichaelfriedrich anovelapproachtotheholistic3dcharacterizationofweldseamspavingthewayfordeeplearningbasedprocessmonitoring
AT schmoellermaximilian novelapproachtotheholistic3dcharacterizationofweldseamspavingthewayfordeeplearningbasedprocessmonitoring
AT stadterchristian novelapproachtotheholistic3dcharacterizationofweldseamspavingthewayfordeeplearningbasedprocessmonitoring
AT kickmichaelkarl novelapproachtotheholistic3dcharacterizationofweldseamspavingthewayfordeeplearningbasedprocessmonitoring
AT geigerchristian novelapproachtotheholistic3dcharacterizationofweldseamspavingthewayfordeeplearningbasedprocessmonitoring
AT zaehmichaelfriedrich novelapproachtotheholistic3dcharacterizationofweldseamspavingthewayfordeeplearningbasedprocessmonitoring