Simulation Modeling, Artificial Intelligence and Digital Twins for Decision Making in Production and Logistics

Permanent URI for this collection

https://hdl.handle.net/10125/109881

Browse

Recent Submissions

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    A Digital Twin of an Industry 4.0 Learning Laboratory to Enable Simultaneous Over-the-Air (OTA) Updates of the Control
    (2025-01-07) Mukku, Vasu Dev; Tangirala, Sri Girish; Reggelin, Tobias; Lang, Sebastian
    Dynamic and modular factory layouts enable manufacturers to more easily adapt their factory layouts, allowing for quick adjustments to manufacturing processes in response to changing customer preferences. These physical changes in production layout and processes necessitate updates to the control logic of manufacturing modules. Simultaneous Over-the-Air (OTA) updates facilitate rapid and remote changes in control logic, eliminating the need for control engineers to be physically present at the factory site. Additionally, OTA updates enable the control logic of all production modules (e.g., machines) to be updated simultaneously, without the need to manually update each production element individually. This paper demonstrates how a digital twin can enable simultaneous OTA updates of the control logic of production modules, using an Industry 4.0 learning laboratory based on Fischertechnik as an example. We utilized the Unity Engine to create the digital twin and employed the SUIT module of RIOT-OS to update the physical production system, while tracking the manufacturing process through CoAP messages.
  • Thumbnail Image
    Item
    Metamodel-based Simulation Optimization Using Machine Learning for Solving Production Planning Problems in the Automotive Industry
    (2025-01-07) Schweitzer, Felicia; Habel, Lars; Canaviri Vilca, Oscar Jhonny; Kulzer, Tobias; Wenzel, Sigrid
    Due to the rising complexity of production systems in the automotive industry, simulation has become an established tool for analyzing dynamic systems. However, once the number of parameter combinations rises exponentially, the generation and evaluation of all possible solutions gets impractical. While the combination of simulation and optimization has a long tradition in academic research, its adoption in the automotive industry remains limited, often due to the high execution time associated with optimization experiments. To enable more efficient decision- making, this paper explores the integration of machine learning and optimization for simulation optimization. Specifically, it focuses on the use of metamodels incorporating various machine learning algorithms and metaheuristics to optimize two production planning problems with multiple parameter classes. The presented approach enables decision-makers to conduct a rapid assessment of complex production systems.
  • Thumbnail Image
    Item
    Industrial Insights: Evaluating a Hierarchical Digital Twin in an Industrial Production Setting
    (2025-01-07) Marahrens, Tamino; Finke, Christian; Groth, Michael; Schumann, Matthias
    This paper evaluates a prototypical hierarchical digital twin (HDT) for industrial production environments, addressing the gap in practical evaluations of digital twin concepts. The HDT integrates data from various production levels, offering a comprehensive virtual representation of the physical production environment. A qualitative interview study was conducted with 14 practitioners from different industrial sectors to assess the HDT's utility and gather feedback. The study identified key data classes, performance indicators, and functions necessary for effective HDT implementation. Results indicate that the HDT provides significant benefits in monitoring, simulation, and control of production processes, aligning with scientific perspectives while highlighting practical enhancements. This evaluation informs future HDT development and implementation strategies in industrial settings.
  • Thumbnail Image
    Item