{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T21:40:01Z","timestamp":1748986801130,"version":"3.41.0"},"reference-count":27,"publisher":"Walter de Gruyter GmbH","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Finite Element Analysis (FEA) simulation results of sheet metal forming processes are highly sensitive to changes in component geometry, as any alteration requires a complete re-computation of the forming process. Surrogate models, trained on FEA simulation data, offer a promising alternative by providing faster, approximated solutions that mitigate these disadvantages. While being computationally efficient, surrogate models also offer other advantages like differentiability, which is crucial for optimization tasks. However, the effective processing of FEA simulation data for training data-driven surrogate models remains challenging due to their complexity and size. Existing methods often rely on low-order data such as depth images exported from FEA simulations, limiting the surrogate models\u2019 area of application. In contrast, data like 3D point clouds extracted from the FEA mesh, are more general and extensible to complex areas. Additionally, they present opportunities for bridging the Sim2Real gap by fine-tuning the model using transfer learning with point cloud data obtained from physical sensors. This paper introduces a novel approach using 3D point cloud data from FEA forming simulations to train surrogate models. In this paper we demonstrate the effectiveness of this method based on a two stage sheet metal forming process involving deep-drawing and trimming of a box-shaped component, with the goal of predicting the springback. Using machine learning architectures such as PointNet++ and Dynamic Graph Convolutional Neural Networks, we demonstrate that 3D geometric representations not only capture problem complexity more generally than 2D images but also achieve the same results as 2D state-of-the-art surrogate models.<\/jats:p>","DOI":"10.1515\/auto-2024-0116","type":"journal-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T06:56:14Z","timestamp":1744181774000},"page":"261-270","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing FEA sheet metal forming simulations through 3D geometric data-driven surrogate modeling"],"prefix":"10.1515","volume":"73","author":[{"given":"Sebastian","family":"Baum","sequence":"first","affiliation":[{"name":"Institute of Industrial Automation and Software Engineering , University of Stuttgart , Pfaffenwaldring 47, 70550 Stuttgart , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pascal","family":"Heinzelmann","sequence":"additional","affiliation":[{"name":"Institute for Metal Forming Technology , University of Stuttgart , Holzgartenstrasse 17, 70174 Stuttgart , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathias","family":"Liewald","sequence":"additional","affiliation":[{"name":"Institute for Metal Forming Technology , University of Stuttgart , Holzgartenstrasse 17, 70174 Stuttgart , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Weyrich","sequence":"additional","affiliation":[{"name":"Institute of Industrial Automation and Software Engineering , University of Stuttgart , Pfaffenwaldring 47, 70550 Stuttgart , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"374","published-online":{"date-parts":[[2025,4,8]]},"reference":[{"key":"2025060320585675882_j_auto-2024-0116_ref_001","doi-asserted-by":"crossref","unstructured":"E. Doege and B.-A. Behrens, Handbuch Umformtechnik: Grundlagen, Technologien, Maschinen, 2nd ed. Berlin, Heidelberg, Springer, 2010.","DOI":"10.1007\/978-3-642-04249-2"},{"key":"2025060320585675882_j_auto-2024-0116_ref_002","doi-asserted-by":"crossref","unstructured":"H. R. Attar, L. Zhu, and N. Li, \u201cDeep learning enabled tool compensation for addressing shape distortion in sheet metal stamping,\u201d in Mocellin (Ed.) \u2013 Proceedings of the 14th International, 2023, pp. 48\u201358 [Online]. Available at: https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-42093-1_5.","DOI":"10.1007\/978-3-031-42093-1_5"},{"key":"2025060320585675882_j_auto-2024-0116_ref_003","doi-asserted-by":"crossref","unstructured":"T. Trzepiecinski and H. G. Lemu, \u201cPrediction of springback in the air V-bending of metallic sheets,\u201d IOP Conf. Ser. Mater. Sci. Eng., vol.\u00a0645, no.\u00a01, p.\u00a012011, 2019. https:\/\/doi.org\/10.1088\/1757-899X\/645\/1\/012011.","DOI":"10.1088\/1757-899X\/645\/1\/012011"},{"key":"2025060320585675882_j_auto-2024-0116_ref_004","doi-asserted-by":"crossref","unstructured":"L. Zhu and N. Li, \u201cSpringback prediction for sheet metal cold stamping using convolutional neural networks,\u201d in 2022 Workshop on Electronics Communication Engineering., vol. 12720, pp. 278\u2013283, 2023. https:\/\/doi.org\/10.1117\/12.2675249.","DOI":"10.1117\/12.2675249"},{"key":"2025060320585675882_j_auto-2024-0116_ref_005","doi-asserted-by":"crossref","unstructured":"H. R. Attar, A. Foster, and N. Li, \u201cDevelopment of a deep learning platform for sheet stamping geometry optimisation under manufacturing constraints,\u201d Eng. Appl. Artif. Intell., vol. 123, 2023. https:\/\/doi.org\/10.1016\/j.engappai.2023.106295.","DOI":"10.1016\/j.engappai.2023.106295"},{"key":"2025060320585675882_j_auto-2024-0116_ref_006","doi-asserted-by":"crossref","unstructured":"H. R. Attar, A. Foster, and N. Li, \u201cOptimisation of panel component regions subject to hot stamping constraints using a novel deep-learning-based platform,\u201d IOP Conf. Ser. Mater. Sci. Eng., vol.\u00a01270, no.\u00a01, p.\u00a012123, 2022. https:\/\/doi.org\/10.1088\/1757-899X\/1270\/1\/012123.","DOI":"10.1088\/1757-899X\/1270\/1\/012123"},{"key":"2025060320585675882_j_auto-2024-0116_ref_007","doi-asserted-by":"crossref","unstructured":"I. El Mrabti, A. Touache, A. El Hakimi, and A. Chamat, \u201cComparison of artificial neural network model and response surface methodology for springback prediction,\u201d in 10th International Conference on Manufacturing Science and Education \u2013 MSE 2021, vol. 343, no. MATEC Web Conf., 2021. https:\/\/doi.org\/10.1051\/matecconf\/202134303012.","DOI":"10.1051\/matecconf\/202134303012"},{"key":"2025060320585675882_j_auto-2024-0116_ref_008","doi-asserted-by":"crossref","unstructured":"B. Xu, L. Li, Z. Wang, H. Zhou, and D. Liu, \u201cPrediction of springback in local bending of hull plates using an optimized backpropagation neural network,\u201d Mech. Sci., vol.\u00a012, no.\u00a02, pp.\u00a0777\u2013789, 2021. https:\/\/doi.org\/10.5194\/ms-12-777-2021.","DOI":"10.5194\/ms-12-777-2021"},{"key":"2025060320585675882_j_auto-2024-0116_ref_009","doi-asserted-by":"crossref","unstructured":"H. R. Attar and N. Li, \u201cOptimisation of deep drawn corners subject to hot stamping constraints using a novel deep-learning-based platform,\u201d IOP Conf. Ser. Mater. Sci. Eng., vol.\u00a01238, no.\u00a01, p.\u00a012066, 2022. https:\/\/doi.org\/10.1088\/1757-899X\/1238\/1\/012066.","DOI":"10.1088\/1757-899X\/1238\/1\/012066"},{"key":"2025060320585675882_j_auto-2024-0116_ref_010","doi-asserted-by":"crossref","unstructured":"H. R. Attar, A. Foster, and N. Li, \u201cImplicit neural representations of sheet stamping geometries with small-scale features,\u201d Eng. Appl. Artif. Intell., vol. 123, 2023. https:\/\/doi.org\/10.1016\/j.engappai.2023.106482.","DOI":"10.1016\/j.engappai.2023.106482"},{"key":"2025060320585675882_j_auto-2024-0116_ref_011","unstructured":"M. M. Bronstein, J. Bruna, T. Cohen, and P. Veli\u010dkovi\u0107, \u201cGeometric deep learning: grids, groups, graphs, geodesics, and gauges,\u201d 2021 [Online]. Available at: http:\/\/arxiv.org\/pdf\/2104.13478."},{"key":"2025060320585675882_j_auto-2024-0116_ref_012","unstructured":"P. Veli\u010dkovi\u0107, G. Cucurull, A. Casanova, A. Romero, P. Li\u00f2, and Y. Bengio, \u201cGraph attention networks,\u201d 2017 [Online]. Available at: http:\/\/arxiv.org\/pdf\/1710.10903."},{"key":"2025060320585675882_j_auto-2024-0116_ref_013","unstructured":"M. M. Bronstein, J. Bruna, Y. LeCun, A. Szlam, and P. Vandergheynst, \u201cGeometric deep learning: going beyond euclidean data,\u201d 2016 [Online]. Available at: http:\/\/arxiv.org\/pdf\/1611.08097."},{"key":"2025060320585675882_j_auto-2024-0116_ref_014","doi-asserted-by":"crossref","unstructured":"R. Radonjic and M. Liewald, \u201cApproaches for springback reduction when forming ultra high-strength sheet metals,\u201d IOP Conf. Ser. Mater. Sci. Eng., vol.\u00a0159, no.\u00a01, p.\u00a012028, 2016. https:\/\/doi.org\/10.1088\/1757-899X\/159\/1\/012028.","DOI":"10.1088\/1757-899X\/159\/1\/012028"},{"key":"2025060320585675882_j_auto-2024-0116_ref_015","doi-asserted-by":"crossref","unstructured":"\u00c1. B\u00e1rk\u00e1nyi, T. Chov\u00e1n, S. N\u00e9meth, and J. Abonyi, \u201cModelling for digital twins \u2013 potential role of surrogate models,\u201d Processes, vol.\u00a09, no.\u00a03, p.\u00a0476, 2021. https:\/\/doi.org\/10.3390\/pr9030476.","DOI":"10.3390\/pr9030476"},{"key":"2025060320585675882_j_auto-2024-0116_ref_016","doi-asserted-by":"crossref","unstructured":"C. P. Kohar, L. Greve, T. K. Eller, D. S. Connolly, and K. Inal, \u201cA machine learning framework for accelerating the design process using CAE simulations: an application to finite element analysis in structural crashworthiness,\u201d Comput. Methods Appl. Mech. Eng., vol. 385, 2021. https:\/\/doi.org\/10.1016\/j.cma.2021.114008.","DOI":"10.1016\/j.cma.2021.114008"},{"key":"2025060320585675882_j_auto-2024-0116_ref_017","unstructured":"M. R. Singer, \u201cNeuartige Versuchsmethodik zur verbesserten Modellierung der Reibung in der Blechumformung,\u201d Dissertation, Institute for Metal Forming Technology, University of Stuttgart, Stuttgart, 2019."},{"key":"2025060320585675882_j_auto-2024-0116_ref_018","doi-asserted-by":"crossref","unstructured":"P. Mulidr\u00e1n, E. Spi\u0161\u00e1k, M. Tom\u00e1\u0161, J. Varga, and J. Majernikov\u00e1, \u201cThe effect of material models on springback prediction,\u201d (in En;en), Strength Mater., vol.\u00a053, no.\u00a06, pp.\u00a0961\u2013965, 2021. https:\/\/doi.org\/10.1007\/s11223-022-00364-9.","DOI":"10.1007\/s11223-022-00364-9"},{"key":"2025060320585675882_j_auto-2024-0116_ref_019","doi-asserted-by":"crossref","unstructured":"H. Ma and Z. Wang, \u201cThe influence of the Bauschinger effect on springback prediction for dual phase steel,\u201d SAE Tech. Pap., 2006. https:\/\/doi.org\/10.4271\/2006-01-0145.","DOI":"10.4271\/2006-01-0145"},{"key":"2025060320585675882_j_auto-2024-0116_ref_020","doi-asserted-by":"crossref","unstructured":"T. Trzepiecinski and H. Lemu, \u201cEffect of computational parameters on springback prediction by numerical simulation,\u201d Metals, vol.\u00a07, no.\u00a09, p.\u00a0380, 2017. https:\/\/doi.org\/10.3390\/met7090380.","DOI":"10.3390\/met7090380"},{"key":"2025060320585675882_j_auto-2024-0116_ref_021","doi-asserted-by":"crossref","unstructured":"A. Hamdi, S. Giancola, and B. Ghanem, \u201cMVTN: multi-view transformation network for 3D shape recognition,\u201d 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1\u201311, 2021. https:\/\/doi.org\/10.1109\/iccv48922.2021.00007.","DOI":"10.1109\/ICCV48922.2021.00007"},{"key":"2025060320585675882_j_auto-2024-0116_ref_022","unstructured":"C. R. Qi, L. Yi, H. Su, and L. J. Guibas, \u201cPointNet++: deep hierarchical feature learning on point sets in a metric space,\u201d 2017 [Online]. Available at: http:\/\/arxiv.org\/pdf\/1706.02413."},{"key":"2025060320585675882_j_auto-2024-0116_ref_023","unstructured":"Y. Wang, Y. Sun, Z. Liu, S. E. Sarma, M. M. Bronstein, and J. M. Solomon, \u201cDynamic graph CNN for learning on point clouds,\u201d 2018 [Online]. Available at: http:\/\/arxiv.org\/pdf\/1801.07829."},{"key":"2025060320585675882_j_auto-2024-0116_ref_024","unstructured":"Papers with Code, ModelNet40 Benchmark (3D Point Cloud Classification) [Online]. https:\/\/paperswithcode.com\/sota\/3d-point-cloud-classification-on-modelnet40?p=pointweb-enhancing-local-neighborhood [accessed: Nov. 11, 2024]."},{"key":"2025060320585675882_j_auto-2024-0116_ref_025","doi-asserted-by":"crossref","unstructured":"S. S. Mohammadi, Y. Wang, and A. D. Bue, \u201cPointview-GCN: 3D shape classification with multi-view point clouds,\u201d in IEEE International Conference on Image (ICIP), 2023, pp. 3103\u20133107.","DOI":"10.1109\/ICIP42928.2021.9506426"},{"key":"2025060320585675882_j_auto-2024-0116_ref_026","doi-asserted-by":"crossref","unstructured":"B. Zettl, et al.., \u201cImprovement of process control in sheet metal forming by considering the gradual properties of the initial sheet metal,\u201d J. Strain Anal. Eng. Des., vol.\u00a058, no.\u00a08, pp.\u00a0605\u2013620, 2023. https:\/\/doi.org\/10.1177\/03093247231166035.","DOI":"10.1177\/03093247231166035"},{"key":"2025060320585675882_j_auto-2024-0116_ref_027","doi-asserted-by":"crossref","unstructured":"Y. Zhao, H. Li, H. Zhou, H. R. Attar, T. Pfaff, and N. Li, \u201cA review of graph neural network applications in mechanics-related domains,\u201d 2024 [Online]. Available at: http:\/\/arxiv.org\/pdf\/2407.11060.","DOI":"10.1007\/s10462-024-10931-y"}],"container-title":["at - Automatisierungstechnik"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/auto-2024-0116\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/auto-2024-0116\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T20:59:11Z","timestamp":1748984351000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/auto-2024-0116\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,1]]},"references-count":27,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4,8]]},"published-print":{"date-parts":[[2025,4,28]]}},"alternative-id":["10.1515\/auto-2024-0116"],"URL":"https:\/\/doi.org\/10.1515\/auto-2024-0116","relation":{},"ISSN":["0178-2312","2196-677X"],"issn-type":[{"type":"print","value":"0178-2312"},{"type":"electronic","value":"2196-677X"}],"subject":[],"published":{"date-parts":[[2025,4,1]]}}}