elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Datenschutz | Kontakt | English
Schriftgröße: [-] Text [+]

Localization of Fabrics with Computer Vision for Composite Manufacturing

Frommel, Christoph (2024) Localization of Fabrics with Computer Vision for Composite Manufacturing. VISION 2024, 2024-10-08 - 2024-10-10, Stuttgart, Deutschland.

[img] PDF
2MB

Offizielle URL: https://www.messe-stuttgart.de/vision/en/programme/lecture-forums/scientific-vision-days/videos-on-demand?videoId=Qde9mTUgtXY

Kurzfassung

Using fiber reinforced polymers (FRP) in industrial applications typically provides structures with lower weight compared to metals. Investment costs for automated processes are high and so far getting established in aviation applications. To introduce automation solutions together with low investment costs, the European funded project DrapeBot uses industrial robots to assist the worker in the manufacturing of FRPs. The robots are equipped with grippers that can pick up fabrics. Dependent on the size, they are either transported and placed fully by the robot, cooperatively by two robots or cooperatively with one robot and the worker. With this flexibility the automated system can be used for other manufacturing processes which raises machine utilization and thus lowers amortization time. In DrapeBot this approach will be used for aviation, automotive and maritime use cases that all use pick and place processes. To pick up the fabrics the location of the individual cut piece is needed. Computer vision is used to find the cut piece on the respective material carrier. A computer vision system using a monochrome industrial camera to find dry carbon fiber fabrics for aviation use cases was developed in earlier projects at DLR. In DrapeBot the automotive and maritime use cases introduce dry glass fibers as well as carbon fiber prepregs. To find these materials and calculate their positions, changes in the existing system had to be done. Due to the changing environments and materials the monochrome camera with optimized flash for carbon fibers was changed to a color camera using ambient lighting for image acquisition. Each color space of the color image is evaluated individually and contrast optimizations are done to use the existing algorithms for coordinate calculation. With this adapted computer vision system the localization of carbon fiber prepreg materials for the automotive use case was established and experiments with dry glass fibers showed promising results.

elib-URL des Eintrags:https://elib.dlr.de/207652/
Dokumentart:Konferenzbeitrag (Vortrag)
Titel:Localization of Fabrics with Computer Vision for Composite Manufacturing
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Frommel, ChristophChristoph.Frommel (at) dlr.dehttps://orcid.org/0000-0002-3717-1087170159328
Datum:Oktober 2024
Referierte Publikation:Nein
Open Access:Ja
Gold Open Access:Nein
In SCOPUS:Nein
In ISI Web of Science:Nein
Status:veröffentlicht
Stichwörter:automated fiber reinforced parts manufacturing, pick and place, human machine interaction, object recognition
Veranstaltungstitel:VISION 2024
Veranstaltungsort:Stuttgart, Deutschland
Veranstaltungsart:internationale Konferenz
Veranstaltungsbeginn:8 Oktober 2024
Veranstaltungsende:10 Oktober 2024
Veranstalter :Austrian Institute of Technology
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Luftfahrt
HGF - Programmthema:Komponenten und Systeme
DLR - Schwerpunkt:Luftfahrt
DLR - Forschungsgebiet:L CS - Komponenten und Systeme
DLR - Teilgebiet (Projekt, Vorhaben):L - Produktionstechnologien
Standort: Augsburg
Institute & Einrichtungen:Institut für Bauweisen und Strukturtechnologie > Automation und Produktionstechnologie
Hinterlegt von: Frommel, Christoph
Hinterlegt am:23 Okt 2024 16:57
Letzte Änderung:23 Okt 2024 16:57

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
electronic library verwendet EPrints 3.3.12
Gestaltung Webseite und Datenbank: Copyright © Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.