Publication Date:
2024-04-11
Description:
The increasing use of automated laser welding processes causes high demands on process monitoring. This work demonstrates methods that use a camera mounted on the focussing optics to perform pre-, in-, and post-process monitoring of welding processes. The implementation uses machine learning methods. All algorithms consider the integration into industrial processes. These challenges include a small database, limited industrial manufacturing inference hardware, and user acceptance.
Keywords:
CNN; stacked dilated U-Net; semantic segmentation; hairpin technology; laser welding; quality assurance; machine learning; Qualitätssicherung; semantische Segmentierung; Hairpin Technologie; Laserschweißen; Maschinelles Lernen; Künstliche Intelligenz
;
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TH Energy technology and engineering::THR Electrical engineering
Language:
English
Format:
image/jpeg
Permalink