Ceramic 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 deeplearning 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.

Detailed information on the condition of large-character inkjet printers can be acquired by using intermediate results from standardized matrix code grading. This approach allows monitoring each individual printer nozzle which is of high importance if ceramic inks are used for printing. Inks containing ceramic pigments tend to clog printer nozzles more rapidly which may lead to loss of print quality. In several application areas such as hot metal forming code quality must be guaranteed which can be achieved with the approach reported here.

No abstract