Year: 2026
Type: article
Abstract: Shortening development cycles of formed sheet metal components requires bridging the gap between numerical sheet metal forming simulation and the actual manufacturing process. Springback effects currently cause substantial discrepancies between simulated predictions and physical outcomes, resulting in time-consuming manual tool tryouts. To address this simulation-to-reality gap, this paper proposes a Delta Model that corrects finite element simulation results using learned deviations from real measurement data. By training with the newly acquired ‘Real Deep Drawing and Cutting’ (RDDAC) dataset, which synchronizes experimental 3D point cloud measurements with corresponding simulations, this Delta Model significantly improves prediction accuracy. Furthermore, by capturing complex geometric deviations and weighting various influence factors, this data-driven approach facilitates automated and robust active surface design across component geometries.
Source: Production Engineering
Institution: University of Stuttgart
Language: English
Subfield: Mechanical Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,290
Funder: Universität Stuttgart
OpenAlex ID: W7236412806
