E-PreMa | Improved manufacturability assessment of sheet metal parts in the early design phase using machine learning

Due to increasing cost pressure and short development cycles in the automotive sector, there is a need to increase the efficiency of processes. This also affects the development of sheet metal parts. When designing new sheet metal parts, various design approaches are pursued in the early development stage whose subsequent manufacturability can hardly be assessed objectively. This leads to high additional costs and time delays due to the further development of parts that cannot be manufactured later. Therefore, a software prototype is to be developed in the E-PreMa project, which can predict the manufacturability already in the early development phase and also shows suitable development approaches. The underlying methodology is a coupling of FEM simulations, machine learning, shape optimization and further data engineering methods.

The resulting software is intended to provide design engineers with a reproducible assistance to consider business and technical requirements in component design. This is intended to reduce expensive and time-consuming undesirable developments.

The project is funded by the Central Innovation Program for SMEs (ZIM) of the German Federal Ministry for Economic Affairs and Energy (BMWi).