Optimizing operations of flexible assembly systems: demonstration of a digital twin concept with optimized planning and control, sensors and visualization

Thomas Sobottka (), Christoph Halbwidl, Alexander Gaal, Matthias Nausch, Benedikt Fuchs, Philipp Hold and Leonhard Czarnetzki
Additional contact information
Thomas Sobottka: Fraunhofer Austria Research GmbH
Christoph Halbwidl: Fraunhofer Austria Research GmbH
Alexander Gaal: Fraunhofer Austria Research GmbH
Matthias Nausch: Fraunhofer Austria Research GmbH
Benedikt Fuchs: Fraunhofer Austria Research GmbH
Philipp Hold: Fraunhofer Austria Research GmbH
Leonhard Czarnetzki: Fraunhofer Austria Research GmbH

Journal of Intelligent Manufacturing, 2025, vol. 36, issue 8, No 8, 5375-5395

Abstract: Abstract This paper presents the development of an optimized planning and control method for flexible manufacturing and assembly systems. While the significant potential of flexible manufacturing concepts to help producers adapt to market developments is recognized, the complexity of the flexible systems and the need to optimally plan and control them is a major obstacle in their practical implementation. Thus, this paper aims to develop a comprehensive digital planning method, based on a digital twin and to demonstrate the feasibility of the approach for practical application scenarios. The approach consists of four modules: (1) a simulation-based optimization module that applies reinforcement learning and genetic algorithms to optimize the module configuration and job routing in cellular reconfigurable manufacturing systems; (2) a synchronization module that links the physical and virtual systems via sensors and event handling; (3) a sensor module that enables a continuous status update for the digital twin; and (4) a visualization module that communicates the optimized plans and control measures to the shop floor staff. The demonstrator implementation and evaluation are implemented in a learning factory. The results include solutions for the method components and demonstrate their successful interaction in a digital twin, while also pointing towards the current technology readiness and future work required to transfer this demonstrator implementation to a full-scale industrial implementation.

Keywords: Flexible manufacturing systems; Digital twin; IoT sensors; Reinforcement learning; AI; Simulation (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10845-024-02537-6 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:36:y:2025:i:8:d:10.1007_s10845-024-02537-6

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-024-02537-6

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().