Bridging the simulation-to-reality gap in sheet metal forming via delta modeling

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.

Authors

Institutions

Publication Details

Journal
Production Engineering
Published
2026-11-18
DOI
https://doi.org/10.1007/s11740-026-01474-y
Primary Topic
Metal Forming Simulation Techniques
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Bridging the simulation-to-reality gap in sheet metal forming via delta modeling

Mathias Liewald, Sebastian Baum, Michael Weyrich, Kim Rouven Riedmüller et al.
4 links
Production Engineering
Metal Forming Simulation Techniques
article

Bridging the simulation-to-reality gap in sheet metal forming via delta modeling

Mathias Liewald, Sebastian Baum, Michael Weyrich, Kim Rouven Riedmüller, Pascal Heinzelmann
article en

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.

Production EngineeringVol. 21(1)
University of Stuttgart (DE)
Universität Stuttgart
Metal Forming Simulation Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon