wir bieten...
Dekobild im Seitenkopf ISMLL
Projects & Cooperations / IIP-Ecosphere:

Next Level Ecosphere for Intelligent Industrial Production

The vision of this project is the full automation of production based on networked, intelligent, autonomous systems to increase productivity, flexibility, robustness and efficiency. The aim of the implementation phase is therefore to establish a new type of ecosystem - the Next Level Ecosphere for Intelligent Industrial Production (IIP-Ecosphere) - which will enable a "next level" in intelligent production.

Today's ecosystems and business models in production severely limit the development towards autonomous and intelligent production. One example is the relationship between users and suppliers of tool condition monitoring systems. These systems are integrated into the user's machines and are designed to detect process faults. Any further use of the data or cooperation between companies often does not occur due to the above-mentioned obstacles. In contrast, systems from different suppliers with different competencies (e.g. error monitoring, process optimization) are available "as-a-service" in the IIP-Ecosphere.

As further participants of the ecosystem, tool manufacturers, for example, can use the process data for tool optimization or for "pay-per-use" business models. The IIP-Ecosphere generates high innovation potential by interlocking across process chains and hierarchical levels of production. Thus, service providers can use aggregated information about defects on the machining process level in the IIP-Ecosphere to offer users an autonomous optimization of detailed process planning (process parameters) and a flexible allocation to resources on the level of production planning and control.

Only this combined view of the different levels will lead to a comprehensive increase in productivity and increased efficiency.

In addition, the AI methods of the IIP-Ecosphere enable relevant actors in process chains (developers, users, machine manufacturers, sensor manufacturers) to usefully link production data from a wide range of processes from initial and forming processes to finishing and to further develop the underlying AI methods and production technologies (e.g. sensor components, process knowledge) across companies.

Leibniz Universität Hannover
Friedrich-Alexander Universität Erlangen-Nürnberg
Salt and Pepper

Prof. Schmidt-Thieme
Hadi S. Jomaa