fischertechnik Training Factory Industry 4.0 at the University of Potsdam

Optimising neural networks in production control with fischertechnik

10/14/2024
Waldachtal

Research into the application of artificial intelligence in production control is being simulated at the University of Potsdam with a factory simulation tool by fischertechnik. 

Marcus Grum is a junior professor of Business Information Systems specialising in AI-based application systems. He is leaning over a model that measures approximately one metre by one metre, made of fischertechnik parts. Marcus Grum watches with fascination as a red block of wood is transported from a small high-bay rack to various production stations by conveyor belt. This simulation model by fischertechnik is used at universities and training facilities to simulate the ordering, production and delivery processes in digitalised and interconnected process steps.

The fischertechnik Training Factory Industry 4.0 was used in combination with other simulation tools and a neural twin to simulate global production control processes at the University of Potsdam. One research project simulated the production of marmalade manufactured at four different global production sites that all run on the same IT systems. 

The simulation looked at every aspect of the process, from procuring the fruit to the distribution to the customers. The fischertechnik Training Factory Industry 4.0 was one of the four interconnected haptic production stations that simulated processes such as storing the fruit, loading the fruit into the cooker to make the marmalade and filling the jars before shipping the product. 

The haptic model was connected to a neural network (ANN – Artificial Neural Network). “Using the model, we carried out a series of tests and experiments that delivered results and flagged production inefficiencies. These results allowed us to understand how inefficiencies such as these can be prevented”, Prof Grum explains. Last year, the young scientist was honoured by the Werner-von-Siemens-Ring Foundation for developing a methodological approach that allows machine and business processes to be modelled using artificial neural networks (ANN).

Future research will focus on the empirical testing of neural network instructions and corresponding management interventions that emerge in real-time production. “This is another area where the factory simulation tool by fischertechnik will come into play”, Prof Grum says.

Further information on fischertechnik’s factory simulation models: Simulation models for industry and universities - fischertechnik

Sandra Roth
Press relations officer fischertechnik,
fischer Consulting,
fischer Innomation,
fischer Innovative Moulds
cd-blue-6cb57c5b6-q8jfl