Generalization of human-centered AI applications for production optimization (GeMeKI)

Key Info

Basic Information

01.08.2021 to 31.07.2024
Organizational Unit:
Chair of Machine Tools, Automation and Control
Federal Ministry of Education and Research BMBF

Research partner

    • aiXbrain GmbH ( Consortium leader )
    • Franz Pauli GmbH & Co. KG
    • Fraunhofer-Institut für Produktionstechnologie IPT
    • meastream GmbH
    • Miele & Cie. KG
    • MT Analytics GmbH
    • Siemens AG
    • Starrag Technology GmbH
    • WEISS Spindeltechnologie GmbH
    • XENON Automatisierungstechnik GmbH
    • YOUSE GmbH




Oliver Petrovic



+49 241 80 27456



The increasingly growing demand for diversity of product variants, quality and sustainability poses enormous challenges for the manufacturing technology of German companies. Artificial intelligence (AI) technologies offer great potential to meet these challenges with increases in flexibility, quality and productivity. Due to the high requirements on data quantity and quality as well as the mostly poor transferability of the solutions, the exploitation of these potentials has so far been limited to stand-alone solutions in large-scale production.

One possible solution lies in the development of transferable systems through the holistic consideration of the key factors of humans, AI and production equipment in human-centered AI applications. The aim of the cooperative project GeMeKI is therefore to explore this approach in order to sustainably improve the performance, flexibility and efficiency of complex manufacturing systems. For this purpose, three use cases of the manufacturing processes joining, cutting and forming are being considered in parallel. In the process, new forms of human-AI interaction, process-related sensor integration and successive data refinement are being developed as the basis of a digital value chain.

Through the combinatorial consideration of the triad as a learning overall system, hybrid intelligence systems are created in which the complementary strengths of experts and AI are combined. On the one hand, AI learns from humans by involving them in the training processes of the models, and on the other hand, process transparency is increased by processing the data in user-friendly AI assistance systems. Transferring the experience of experts into digital services thus shifts the barrier to entry for tapping the productivity potential of AI in the direction of smaller batch sizes.