The artificial intelligence algorithms have been trained so well in advance that they can suggest optimal designs very quickly in the development process of mechanical structures without the need for physical simulations. In this way, they can support the structural optimization processes.
Plaschkies, P.; Schumacher, A.; Vaculin, O. Accelerated Virtual Evaluation of Restraint System Performance forVehicle Occupants with Varying Bodies
15. Freiberger Crashworkshop
2024
Trilling, J.; Schumacher, A.; Zhou, M. Reinforcement learning based agents for improving layouts of automotive crash structures
Applied Intelligence (54) :1751--1769
2024
DOI: 10.1007/s10489-024-05276-6
Pakiman, A.; Garcke, J.; Schumacher, A. Knowledge discovery assistants for crash simulations with graph algorithms and energy absorption features
Applied Intelligence, 53 (16) :19217--19236
2023
ISSN: 0924-669X
DOI: 10.1007/s10489-022-04371-w
Kracker, D.; Dhanasekaran, Revan Kumar; Schumacher, A.; Garcke, J. Method for automated detection of outliers in crash simulations
International Journal of Crashworthiness, 28 (1) :96--107
2023
ISSN: 1358-8265
DOI: 10.1080/13588265.2022.2074634
Plaschkies, F.; Possoli, K.; Vaculin, O.; Schumacher, A.; Andrade, P. Evaluation Approach for Machine Learning Concepts in Occupant Protection Based on Multi-Attribute Decision Making
27th International Technical Conference on the Enhanced Safety of Vehicles (ESV)
2023
Schumacher, A. State of the art in using deep learning algorithms and expert knowledge schemes for supporting mathematical optimization procedures
Automotive CAE Grand Challenge 2022
2022
Plaschkies, F.; Vaculin, O.; Pelisson, A.A. Schnelle Abschätzung des Crashverhaltens von Insassen unter Berücksichtigung der Vielfalt des Menschen: Robustheit, Datenintensität und Vorhersagekraft von Metamodellen
13. VDI-Tagung Fahrzeugsicherheit
2022
DOI: 10.51202/9783181023877-313
Trilling, J.; Schumacher, A.; Zhou, M. Generation of designs for local stiffness increase of crash loaded extrusion profiles with reinforcement learning
Proceedings of the NAFEMS-Conference on Machine Learning and Artificial Intelligence in CFD and Structural Analysis, Seite 56--66
2022
Trilling, J.; Schumacher, A. Einsatz von Reinforcement Learning zur lokalen Versteifung von Extrusionsprofilen in Crashlastfällen
NAFEMS-Online-Magazin, Zeitschrift für numerische Simulation und angrenzende Gebiete (62) :59--70
2022
Pakiman, A.; Garcke, J.; Schumacher, A. Data Representation of Crash Scenarios by Graph Structures
13th European LS-DYNA Conference & Users Meeting
2021
Mertler, S.; Schumacher, A. Reduced Order Modeling for Correlation Analysis of Crash Structures
Automotive CAE Grand Challenge 2020
2020
Kracker, D.; Garcke, J.; Schumacher, A.; Schwanitz, P. Automatic analysis of crash simulations with dimensionality reduction algorithms such as PCA and t-SNE
16th Intl. LS-DYNA Users Conference
2020
Diez, C.; Kunze, P.; Toewe, D.; Wieser, C.; Harzheim, L. Big-Data based rule-finding for analysis of crash simulations
In Schumacher, A. and Vietor, T. and Fiebig, S. and Bletzinger, K.-U. and Maute, K., Editor, Advances in Structural and Multidisciplinary Optimization aus Springer eBook Collection Engineering
Seite 396--410
Herausgeber: Springer, Cham
2018
DOI: 10.1007/978-3-319-67988-4_31
ISBN: 978-3-319-67988-4
Diez, C.; Wieser, C.; Harzheim, L.; Schumacher, A. Automated Generation of Robustness Knowledge for selected Crash Structures
14. LS-DYNA-Forum
2016
Diez, C.; Harzheim, L.; Schumacher, A. Effiziente Wissensgenerierung zur Robustheitsuntersuchung von Fahrzeugstrukturen mittels Modellreduktion und Ähnlichkeitsanalyse
SIMVEC Simulation und Erprobung in der Fahrzeugentwicklung 2016
Herausgeber: VDI Verlag
2016
DOI: 10.51202/9783181022795-137
ISBN: 9783181022795
Schumacher, A.; Ortmann, C. Combining state of the art meta-models for predicting the behavior of non-linear crashworthiness structures for shape and sizing optimizations
11th World Congress on Structural and Multidisciplinary Optimisation, Seite 477--482
2015
Dissertations:
- Dr.-Ing. Constantin Diez (2018): Process for Extraction of Knowledge from Crash Simulations by means of Dimensionality Reduction and Rule Mining [https://d-nb.info/1182555063/34]
- Dr.-Ing. Stefan Mertler (2022): Comparative Analysis of Crash Simulation Results using Generative Nonlinear Dimensionality Reduction, Shaker Verlag, ISBN: 978-3-8440-8761-1
- Dr.-Ing. David Kracker (2024): Automatisierte Auswertung von Crashsimulationen unterschiedlicher Fahrzeug-Entwicklungsständen mit Methoden des maschinellen Lernens. Shaker Verlag, ISBN: 978-3-8440-9424-4 Download
- Dr.-Ing. Jens Trilling (2024): Unterstützung der Graphen- und Heuristikbasierten Topologieoptimierung crashbelasteter Strukturen durch Reinforcement Learning Download
