The digital progress monitoring of manual assembly processes at goods with huge dimensions is a challenging task. The paper presents an approach using 3D-image sensors for gesture control and progress recognition. The developed system is able to avoid time and effort consuming walks of workers between assembly objects and computer terminals. Progress recognition of assembly processes is realized by interpreting the movements of the workers’ hands and by detecting the passing of defined coordinates within the assembly and warehouse areas.
To reduce CO2-emissions lightweight structures needs to be implemented in all transport applications. At the same time, low-weight and high performance materials must provide safety and reliability, at economical prices. Extended Non-Destructive Testing (ENDT) contributes to safeguarding the performance of adhesively joined load-critical structures, permitting to steadily monitor adherent surfaces prior to bonding and to detect adhesion properties of bonded components.In the present work, approaches exceeding the state-of-the-art of innovative ENDT techniques like robot-based Laser-Induced Breakdown Spectroscopy (LIBS) are presented. Furthermore, automated, AI-based image processing and evaluation methods for surface quality inspection are shown, aiming at overcoming today's limitations concerning handling, evaluation speed and reliability of results. First results of automated in-line surface quality assurance approaches for assessing multi material adherent surfaces are highlighted.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.