Investigation of a test rig based on smart vision sensors for automated inspection of press-hardened automotive body components

Defects such as cracks, overlaps and impressions are prevalent in the manufacturing of press-hardened automotive body components. The prevailing industrial practices rely on manual visual inspections, which are both costly and less effective, thereby posing a risk of undetected defects. To address t...

Full description

Saved in:
Bibliographic Details
Main Authors: Simon Fabio, Werner Thomas, Weidemann Andreas, Guilleaume Christina, Brosius Alexander
Format: Article
Language:English
Published: EDP Sciences 2025-01-01
Series:MATEC Web of Conferences
Subjects:
Online Access:https://www.matec-conferences.org/articles/matecconf/pdf/2025/02/matecconf_iddrg2025_01088.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730710516006912
author Simon Fabio
Werner Thomas
Weidemann Andreas
Guilleaume Christina
Brosius Alexander
author_facet Simon Fabio
Werner Thomas
Weidemann Andreas
Guilleaume Christina
Brosius Alexander
author_sort Simon Fabio
collection DOAJ
description Defects such as cracks, overlaps and impressions are prevalent in the manufacturing of press-hardened automotive body components. The prevailing industrial practices rely on manual visual inspections, which are both costly and less effective, thereby posing a risk of undetected defects. To address these challenges, the potential of smart vision sensors for automated component inspection is being investigated. A dedicated test rig was constructed for the purpose of studying the key influencing factors on the output similarity values of the image processing system. These factors include the temperature of the component subsequent to the processing stage and the exposure to the light conditions during the inspection. The performance of the system was evaluated using confusion matrices in order to assess precision and repeatability. For the deformation and crack defect types discrepancies were not observed between the actual and predicted classifications. For the purpose of a practical acceptance of the test system, a left-tailed hypothesis test is carried out for the overlap defect type. The results of the study demonstrate the potential of inspection systems to improve accurate defect detection, thereby paving the way for their implementation in production environments.
format Article
id doaj-art-1ecb1aaba7a34fdbb69fab5c76c38057
institution DOAJ
issn 2261-236X
language English
publishDate 2025-01-01
publisher EDP Sciences
record_format Article
series MATEC Web of Conferences
spelling doaj-art-1ecb1aaba7a34fdbb69fab5c76c380572025-08-20T03:08:47ZengEDP SciencesMATEC Web of Conferences2261-236X2025-01-014080108810.1051/matecconf/202540801088matecconf_iddrg2025_01088Investigation of a test rig based on smart vision sensors for automated inspection of press-hardened automotive body componentsSimon Fabio0Werner Thomas1Weidemann Andreas2Guilleaume Christina3Brosius Alexander4TUD Dresden University of Technology, Chair of Forming and Machining TechnologyTUD Dresden University of Technology, Chair of Forming and Machining TechnologyMAGNA International Stanztechnik GmbHTUD Dresden University of Technology, Chair of Forming and Machining TechnologyTUD Dresden University of Technology, Chair of Forming and Machining TechnologyDefects such as cracks, overlaps and impressions are prevalent in the manufacturing of press-hardened automotive body components. The prevailing industrial practices rely on manual visual inspections, which are both costly and less effective, thereby posing a risk of undetected defects. To address these challenges, the potential of smart vision sensors for automated component inspection is being investigated. A dedicated test rig was constructed for the purpose of studying the key influencing factors on the output similarity values of the image processing system. These factors include the temperature of the component subsequent to the processing stage and the exposure to the light conditions during the inspection. The performance of the system was evaluated using confusion matrices in order to assess precision and repeatability. For the deformation and crack defect types discrepancies were not observed between the actual and predicted classifications. For the purpose of a practical acceptance of the test system, a left-tailed hypothesis test is carried out for the overlap defect type. The results of the study demonstrate the potential of inspection systems to improve accurate defect detection, thereby paving the way for their implementation in production environments.https://www.matec-conferences.org/articles/matecconf/pdf/2025/02/matecconf_iddrg2025_01088.pdfpress hardeningdigital image processingsmart vision sensorsautomated inspection
spellingShingle Simon Fabio
Werner Thomas
Weidemann Andreas
Guilleaume Christina
Brosius Alexander
Investigation of a test rig based on smart vision sensors for automated inspection of press-hardened automotive body components
MATEC Web of Conferences
press hardening
digital image processing
smart vision sensors
automated inspection
title Investigation of a test rig based on smart vision sensors for automated inspection of press-hardened automotive body components
title_full Investigation of a test rig based on smart vision sensors for automated inspection of press-hardened automotive body components
title_fullStr Investigation of a test rig based on smart vision sensors for automated inspection of press-hardened automotive body components
title_full_unstemmed Investigation of a test rig based on smart vision sensors for automated inspection of press-hardened automotive body components
title_short Investigation of a test rig based on smart vision sensors for automated inspection of press-hardened automotive body components
title_sort investigation of a test rig based on smart vision sensors for automated inspection of press hardened automotive body components
topic press hardening
digital image processing
smart vision sensors
automated inspection
url https://www.matec-conferences.org/articles/matecconf/pdf/2025/02/matecconf_iddrg2025_01088.pdf
work_keys_str_mv AT simonfabio investigationofatestrigbasedonsmartvisionsensorsforautomatedinspectionofpresshardenedautomotivebodycomponents
AT wernerthomas investigationofatestrigbasedonsmartvisionsensorsforautomatedinspectionofpresshardenedautomotivebodycomponents
AT weidemannandreas investigationofatestrigbasedonsmartvisionsensorsforautomatedinspectionofpresshardenedautomotivebodycomponents
AT guilleaumechristina investigationofatestrigbasedonsmartvisionsensorsforautomatedinspectionofpresshardenedautomotivebodycomponents
AT brosiusalexander investigationofatestrigbasedonsmartvisionsensorsforautomatedinspectionofpresshardenedautomotivebodycomponents