Structured representation of simulation and annotation data for machine learning in forming technologies

Production Engineering, vol. 20

Abstract

Abstract The use of machine learning (ML) in manufacturing requires structured, especially standardized, access to both simulation data and domain knowledge. This paper introduces a JSON-based data format for representing synthetic force-time series alongside expert annotations. The schema captures simulation metadata, tool and material parameters, and allows explicit expert knowledge, such as failure indicators, to be linked to signal segments. The proposed structure enables process-aware ML methods that leverage both domain knowledge and raw data for improved learning and generalization. A deep drawing use case illustrates how the format facilitates knowledge-guided learning. The approach aims to bridge the gap between real and simulated production data, supporting scalable integration in modern manufacturing systems.

Authors 9

1. Markus Schumann corresponding

   Technische Universität Darmstadt

   Affiliation as printed

   Institute for Production Engineering and Forming Machines (PtU), Technical University of Darmstadt, Otto-Berndt-Straße 2, Darmstadt, 64287, Hessen, Germany

2. Jonas Moske

   Technische Universität Darmstadt

   Affiliation as printed

   Institute for Production Engineering and Forming Machines (PtU), Technical University of Darmstadt, Otto-Berndt-Straße 2, Darmstadt, 64287, Hessen, Germany

3. Antonia Wüst

   Technische Universität Darmstadt

   Affiliation as printed

   AIML Lab, Technical University Darmstadt, Hochschulstraße 1, Darmstadt, 64289, Germany

4. Felix Divo

   Technische Universität Darmstadt

   Affiliation as printed

   AIML Lab, Technical University Darmstadt, Hochschulstraße 1, Darmstadt, 64289, Germany

5. Daria Gelbich Aachen Manufacturing Technology Institute (MTI)

   RWTH Aachen University

   Affiliation as printed

   Manufacturing Technology Institute (MTI), RWTH Aachen University, Campus Boulevard 30, Aachen, 52074, Germany

6. Philipp Niemietz Aachen Manufacturing Technology Institute (MTI)

   RWTH Aachen University

   Affiliation as printed

   Manufacturing Technology Institute (MTI), RWTH Aachen University, Campus Boulevard 30, Aachen, 52074, Germany

7. Kristian Kersting

   Technische Universität Darmstadt · German Research Centre for Artificial Intelligence · Hessian Center for Artificial Intelligence

   Affiliation as printed

   AIML Lab, Technical University Darmstadt, Hochschulstraße 1, Darmstadt, 64289, Germany

   German Research Center for AI (DFKI), Landwehrstraße 50A, Darmstadt, 64293, Germany

   Hessian Center for AI (hessian.AI), Technical University Darmstadt, Karolinenplatz 5, Darmstadt, 64289, Germany

8. Thomas Bergs Aachen Fraunhofer Institute for Production Technology Manufacturing Technology Institute (MTI)

   Fraunhofer Institute for Production Technology IPT · RWTH Aachen University

   Affiliation as printed

   Fraunhofer Institute for Production Technology (IPT), Steinbachstrasse 17, Aachen, 52074, Germany

   Manufacturing Technology Institute (MTI), RWTH Aachen University, Campus Boulevard 30, Aachen, 52074, Germany

9. Peter Groche

   Technische Universität Darmstadt

   Affiliation as printed

   Institute for Production Engineering and Forming Machines (PtU), Technical University of Darmstadt, Otto-Berndt-Straße 2, Darmstadt, 64287, Hessen, Germany