Big Data in Industrial Printing

Permanent URI for this collection

https://publicdata.fdm.uni-wuppertal.de/handle/1/42

This research project investigates what information can be extracted from large amounts of inline sensor data collected by printing presses and to what extent machine learning methods can help in processing and interpreting this data. Machine learning in the context of industrial printing, with its application-specific features, is not yet very widespread. The resulting questions are being addressed in close cooperation with the printing industry.

Specifically, in an interdisciplinary industry research project the dynamic process fluctuations are being investigated together with a paper manufacturer, a printing company and a system manufacturer for web guiding, register control and quality assurance systems using the example of a productive roll-to-roll gravure printing press. Using a dataset (MSDIRPP) of over 40,000 km of printed cardboard produced in this project, application-specific methods are being developed to automatically detect hidden patterns in web run, register quality or winding quality. The knowledge gained from the project should contribute to a better understanding of the process, which can be used, for example, to optimize product quality, reduce waste or predict maintenance.

Browse

Browsing Big Data in Industrial Printing by Title

  • Item
    Multivariate Sensor Dataset of an Industrial Rotogravure Printing Press (MSDIRPP)
    (University of Wuppertal, 2022-05-31) Tobias Enk
    We present a multivariate sensor dataset for machine learning research in context of industrial print application. The dataset contains 7608 rolls of pre-processed multivariate sensor data of a single production scale rotogravure printing press. The data volume corresponds to 43.181 km of printed paperboard and paper. For each roll we provide high-resolution sampled inline sensor data, machine condition labels and several meta information. Besides basic information like machine speed the dataset contains web movement data such as web edge and web tension measurements, material measurement like web moisture and print quality data such as register measurements in cross and machine direction for 11 print units. We publish the dataset to provide data researchers a strong baseline dataset for several applications in industrial printing.