Bischoff, PeterPeterBischoffZeh, ChristophChristophZehKroh, ChristophChristophKrohSchuster, ChristianeChristianeSchusterHärtling, ThomasThomasHärtling2022-03-159.11.20212021https://publica.fraunhofer.de/handle/publica/41284910.5162/SMSI2021/D5.110.24406/publica-r-412849Ceramic inks can be used to mark metal sheets in hot forming for track-and-trace purposes. However, the ceramic pigments in the inks can lead to clogging of printer nozzles which results in loss of print quality. Here we report on a predictive maintenance concept including different machine- and deep-learning models as the basis of a print quality assurance strategy. Pixelwise image segmentation leads to detailed information about the printing results. The information is used to train a model, classifying the remaining useful lifetime until insufficient printing results.enpredictive maintenancemachine learninginkjet printingceramic pigmentimage analysis620666conference paper