Sheet Metal Forming has different and wide industrial applications (Automotive, White Goods, Aeronautic, etc....). In the metal forming industry, the simulation of processes and the resulting material behavior is of high importance. Important process parameters (e.g., material flow, temperature range, force required), as well as the resulting material characteristics (e.g., strength, residual stress, temperature resistance), can be supported using FEA to replace costly and uneconomical practical tests.
The re-use of knowledge gained from these FEA simulations in combination with data provided by different sensors is the next step towards the implementation of a Digital Twin. Its integration into the IT architecture of a digital factory is inevitable to increase the efficiency and environmental sustainability of processes and products in manufacturing. Therefore the presented project relies on Reduced Order Models in use of Machine Learning approaches as well as an IoT-based dashboard for the combined visualization of actual data and derived KPIs. As a result, the implemented solution enables significant improvement of capabilities in the considered context.