A digital twin mirrors a machine or a process in software, closely enough to supervise and improve it.
Overview
A digital twin is more than a 3D model: it is fed by live data from the machine, so that what you see on screen is what is happening on the shop floor. How well it does that depends on the data link, on the update rate and on the latency between machine and model.
At TU Wien I work on twins for robotic and machining cells: a virtualised framework that links a mobile robot and a CNC machine with their digital representation over a private 5G network, so that machining can be supervised remotely.
The same idea carries over to quality. Measurement data that stay attached to the part and its model make inspection results usable for design and process planning.
Topics
Virtualised frameworks for supervising robots and machine tools
Data links: update rate, latency and synchronisation
Data-driven manufacturing for Industry 4.0 and 5.0
Digital transformation of small and medium-sized manufacturers
Digital twin of the quality assurance task: measured data linked to the part and its nominal model
Try it
A twin is only as good as its link to the machine. Raise the update rate or cut the latency and it follows more closely.
Dark line: the machine. Stepped blue line: its twin.
The model samples a machine signal at the update rate and shows it late by the latency. The tracking error is the root mean square difference between machine and twin, relative to the signal range.
Questions
What limits the accuracy of a digital twin?
Mostly the link to the real system: how often the twin is updated, how long the data take to arrive and how good the sensors are. A twin that updates ten times per second with 40 ms of delay follows a slow axis well and a fast one poorly.
Is a digital twin the same as a simulation?
No. A simulation runs on assumed inputs. A digital twin is connected to a real machine and is updated by its data while it runs.
Related projects
AI5innovation
Digital innovation hub services that bring artificial intelligence into manufacturing companies, the follow-up of AI5production.
European Digital Innovation Hub, project lead at TU Wien
Ongoing 2025 - 2028
GIGABOT
A 5G-based autonomous mobile robot for remote work in the manufacturing industry.
FFG Breitband Austria 2030, project manager
Completed 2024 - 2026
AI5production
AI-driven digital transformation of small and medium-sized manufacturers on the way to Industry 5.0.
European Digital Innovation Hub, Digital Europe Programme and FFG, subproject lead
Completed 2022 - 2025
5G use case
An industrial use case for connected production in a private 5G campus network.
Research cooperation with Hutchison Drei Austria, subproject lead
Completed 2021 - 2024
Publications on this topic 10
2026
Integrating 5G-enabled mobile robotics for remote supervision in CNC machining via a virtualized frameworkBodur, O., Badhan, T., Demir, N., Bhupathiraju, S. S. M. K. V., Spettel, S. and Bleicher, F.CIRP Journal of Manufacturing Science and Technology, 71, 698-710.PDFDOI 10.1016/j.cirpj.2026.10.008
2026
From Data-Driven Production to Autonomous Manufacturing Systems: Tagungsband zum 7. Wiener Produktionstechnik Kongress (WPK 2026)Bleicher, F., Bodur, O. and Trautner, T. F. (Eds.)ISBN 978-3-9505584-1-8, TU Wien, Institute of Production Engineering and Photonic Technologies.PDFDOI 10.5281/zenodo.22954665
2026
Towards Advanced ManufacturingBleicher, F., Prießnitz, M., Wallner, B., Habersohn, C., Bodur, O., Kügerl, L., Greitler, J.-A., Wurm, F., Badhan, T., Zink, F. and Trautner, T.Presentation, Bilaterales Partnertreffen TU Wien IFT & Plansee SE 2026, Reutte, 8 May 2026.reposiTUm
2026
Von der datengetriebenen Fertigung zur Autonomen FertigungszelleBleicher, F., Wallner, B., Habersohn, C., Bodur, O., Badhan, T., Trautner, T. and Kügerl, L.Keynote, Intertool 2026, Wels, 22 April 2026.reposiTUm
2026
Towards Advanced Manufacturing CellsBleicher, F., Wallner, B., Habersohn, C., Bodur, O., Kügerl, L., Greitler, J.-A., Wurm, F., Badhan, T. J. and Trautner, T.Presentation, Plansee Meeting, Vienna, 10 April 2026.reposiTUm
2025
Integrating 5G-Enabled Robotics for Remote Supervision in Smart Factories: A Virtualized FrameworkBodur, O., Badhan, T. J., Bhupathiraju, S. S. M. K. V., Diaz, R., Wallner, B. J., Demirci, T., Spettel, S., Rotheneder, L., Belletti, R., Akkılıç, T. E., Nal, D., Egin, I. N., Poszvek, G. and Bleicher, F.Proceedings of the 13th UTIS International Congress on Machining, pp. 1-11.reposiTUm
2025
Towards Advanced Control of Manufacturing CellsBleicher, F., Wallner, B. J., Habersohn, C., Bodur, O., Kügerl, L., Greitler, J.-A., Wurm, F., Badhan, T. J. and Trautner, T. F.Proceedings of the 13th UTIS International Congress on Machining, Antalya.reposiTUm
2025
Zukunft der Automatisierung. Customizable Production - towards autonomous systemsBleicher, F., Trautner, T. F. and Bodur, O.Conference presentation, FESTO Innovation Day 2025, Zell am See, 16 September 2025.reposiTUm
2025
MX Machining Transformation: Data driven manufacturingBleicher, F., Trautner, T. F., Habersohn, C., Kügerl, L., Greitler, J.-A. and Bodur, O.Conference presentation, 1st DMG MORI research conference, Nara, Japan, 13 March 2025.reposiTUm
2024
Twin Transition in Manufacturing: Wiener Produktionstechnik Kongress 2024Bleicher, F., Bodur, O. and Trautner, T. F. (Eds.)Vol. 6, TU Wien, Institute of Production Engineering and Photonic Technologies.PDFDOI 10.5281/zenodo.13885006reposiTUm