Vertically Integrated Digital Twins for Manufacturing

Aims & Scope

While digital twin technologies are increasingly applied at individual process or system levels, a key open challenge lies in their vertical integration across manufacturing hierarchies. This special session aims to explore challenges, architectures, and methodologies for vertically integrated digital twins that consistently link process and system-level models in manufacturing systems. The session emphasizes cross-level model coupling, data and semantic consistency, and coordinated analysis and decision-making across digital twin layers. Contributions addressing theoretical foundations, integration frameworks, and industrial implementations are particularly encouraged.

The session will focus on the following points:
• Concepts, reference architectures, and standards for vertically integrated digital twins
• Cross-scale coupling of process and system digital twin models
• Case studies and lessons learned from vertically integrated manufacturing digital twins


------

Your valuable insights are welcome! 

We cordially invite interested researchers to contact us for details and presentation applications at: secretariat@idea-global.net

Session Chairs

Presentations

  • Assistant professor
    Università di Catania
    Title: A digital twin architecture for dispatching in semiconductor
    Abstract The present work presents a new digital twin architecture specifically designed for wafer lot dispatching in semiconductor manufacturing systems. Acknowledgment: The work presented has received funding from the Chips Joint Undertaking (JU) under grant agreement No. 101097296. The JU receives support from the European Union’s Horizon EU research and innovation programs and Austria, Belgium, Denmark, Finland, France, Germany, Greece, Hungary, Israel, Italy, Netherlands, Romania, Sweden, Switzerland and Turkey.
  • Post Doc Researcher
    Università degli Studi di Napoli
    Title: Soft sensors for Sustainable Manufacturing technologies
    Abstract The present work develops soft sensors to enable digital twins for Sustainable Manufacturing technologies.
  • Assistant professor
    Politecnico di Torino
    Title: Process mining system discovery for synchronous digital Twins in manufacturing
    Abstract The present work develops process mining system discovery techniques to automatically create digital twins in manufacturing systems characterized by conveyors.
  • PhD researcher
    KU Leuven
    Title: Advanced Modelling and Validation Methods for Digital Twins of Circular Production Systems
    Abstract This project explores advanced methods to extend the critical functionalities of digital twins for production planning and control of complex systems. Key research areas include datadriven model generation and the short-term, robust model validation. The developed methods are tested in both digital environments and realistic prototypical setups, ensuring their applicability and reliability in dynamic production contexts.
  • PhD researcher
    KU Leuven
    Title: Human-centric digital twins for adaptive production control: a framework from data to decision support
    Abstract This research proposes a novel human-centric digital twin framework for dynamic assembly line rebalancing. The framework integrates real-time data from multiple sources, including IoT, Manufacturing Execution Systems (MES), Enterprise Resource Planning (ERP) systems, and wearable devices, to provide a comprehensive view of machine states, material flows, and human performance metrics. A hybrid data fusion is developed, to establish relationships between physiological signals and human performance. Preliminary results on simple manufacturing systems are shown in a digital-to-digital information loop.
  • Professor
    University of Padova
    Title: A qualification-informed digital twin for adaptive startup tuning in injection molding
    Abstract Injection-molding changeovers trigger production startups where parameters are re-tuned to recover “no visible defects”, generating scrap when qualification settings are reused without adaptation. This work develops a qualification-informed digital twin for startup decision support by capturing defect–parameter sensitivities and updating recommendations with vision-based feedback. Two twin instantiations trained on the same dataset are compared: an interpretable predictive model with delta-anchored tuning and a retrieval-grounded assistant reusing qualification trajectories for constrained updates. On an ABS socket-cover across hydraulic and electric machines and three viscosities, the digital-twin guidance cuts median runs-to-quality by 86% and mean startup scrap by 92% versus the industrial baseline.