Requirements for Numeric Models as Sources of Synthetic Data for Predicting Real-World Data Sets in Sheet Metal Forming Processes

Simple item page
dc.contributor.author Schumann, Markus
dc.contributor.author Moske, Jonas
dc.contributor.author Wüst, Antonia
dc.contributor.author Kersting, Kristian
dc.contributor.author Groche, Peter
dc.date.accessioned 2026-03-18T07:39:07Z
dc.date.created 2024-08-29
dc.date.issued 2026-03-18
dc.description In the field of forming technology, synthetic data generated by finite element (FE) simulations is increasingly being used to train machine learning (ML) models for quality prediction. However, the predictive accuracy on real-world process data is often limited by the so-called “reality gap” between simulated and measured signals. This study investigates how simulation model complexity influences the suitability of synthetic data for training ML models that generalize to real progressive deep drawing processes, as demonstrated using an symmetric deep-drawn part. Three representative simulation configurations of increasing complexity (L1–L3) are implemented and evaluated against experimental data collected under production conditions using sensor-integrated tools. The analysis covers multiple ML tasks, including classification of pre-process connector cut geometries, detection of process disturbances, separation of subtle geometry variants, assessment of feature transfer robustness, and saliency-based interpretation of signal regions. The results show that simple models (L1) enable robust classification of failures such as material damage within synthetic domains though their transferability to real data is restricted. Although the are computationally more expensive, higher complexity level (L2 and L3) better capture the effects of pre-processing and deformation-history, improving domain alignment and supporting physically meaningful model interpretation. Saliency map analysis reveals that models trained on synthetic data emphasize different signal regions than models trained on real data. This underscores the importance of task-relevant signal fidelity. The findings provide quantitative guidance for selecting an adequate level of simulation complexity in the context of manufacturing processes in the sheet metal working industry and demonstrate that the underlying principles apply across a broader spectrum of modelling configurations. Measurement is always the punch force for the deep drawing state. Time series from simulation and real world experiments. The folder structure is as follows: force curves deepdrawing simulation levels - Level 1 Simulation - Raw Data (CSV) - Augmentation (CSV) - Level 2 Simulation - Raw Data (CSV) - Augmentation (CSV) - Level 3 Simulation - Raw Data (CSV) - Augmentation (CSV) Real force curves 80 SPM - Geometry 1.tdms - Geometry 2.tdms - Geometry 3.tdms - Geometry reference.tdms - channel names.txt Simulation force curves of damaged cups - Raw Data (CSV) - Augmentation (CSV) Simultion force curves of excentric cups - Raw Data (CSV) - Augmentation (CSV)
dc.identifier.uri https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/5068
dc.identifier.uri https://doi.org/10.48328/tudatalib-2171
dc.language.iso en
dc.rights.licenseODbL-1.0 (https://opendatacommons.org/licenses/odbl/1.0/)
dc.subject synthetic data
dc.subject finite element simulation
dc.subject machine learning
dc.subject forming processes
dc.subject deep drawing
dc.subject reality gap
dc.subject model complexity
dc.subject connector geometry
dc.subject damage detection
dc.subject damage detection
dc.subject process monitoring
dc.subject saliency analysis
dc.subject.classification 4.11-02
dc.subject.ddc 670
dc.title Requirements for Numeric Models as Sources of Synthetic Data for Predicting Real-World Data Sets in Sheet Metal Forming Processes
dc.type Dataset
dcterms.accessRights openAccess
person.identifier.orcid 0009-0002-3928-6707
person.identifier.orcid 0009-0005-7836-3447
person.identifier.orcid 0009-0005-8636-1337
person.identifier.orcid #PLACEHOLDER_PARENT_METADATA_VALUE#
person.identifier.orcid #PLACEHOLDER_PARENT_METADATA_VALUE#
tuda.agreements true
tuda.project DFG | GR1818/84-1 | Optimierung des Wirk
tuda.unit TUDa

Files

Original bundle

Now showing 1 - 1 of 1
NameDescriptionSizeFormat
Requirements_for_Numeric_Models_as_Source_of_Synthetic_Data_DATASET.zip2.92 GBZIP-Archivdateien Download
Simple item page

Collections