EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Physics-Informed Recurrent Neural Networks with Kinematic Constraints for Large Deformation Metal Forming

Francesco Munzone, Javad Hazrati, Wouter Hakvoort, Redmer van Tijum, Ton van den Boogard

Key Engineering Materials · 16.04.2026 · 1050 · 171-182

DOI: 10.4028/p-ls5ptz ↗

Kurz gefasst

Fachartikel in der Zeitschrift Key Engineering Materials, online erschienen am 16.04.2026. Verfasst von Francesco Munzone und 4 weiteren Autor:innen. Die Arbeit nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Metal-forming is a manufacturing process that involves non-linear elastoplastic deformations to shape a blank into a complex geometry. These processes are governed by numerous parameters, with significant influence on the final product. To analyse the effects of such parameters, large-scale finite element (FE) simulations are often conducted. However, these models are computationally expensive and often unsuitable for real-time analysis. To overcome these limitations, surrogate models have emerged as powerful alternatives. In this study, we propose a physics-informed recurrent neural network framework (PIRNN) to evaluate displacements and strain tensor components. In particular, the latter are not a network output but are obtained through the application of kinematic relations. Given the initial configuration as input and the final configuration as output, it is possible to evaluate the deformation gradient. The impenetrability condition is then injected into the loss to improve the estimation of displacements and strain tensors. The PIRNN model, referred to as a kinematics-informed recurrent neural network, is trained on data generated from FE simulations of a deep-drawing process. The accuracy of the model is evaluated on a test dataset (design points that the model does not see during training) using different error measures. The results show that the proposed KI-RNN model can fairly reproduce the FE simulation results fairly well.

Zitieren

APA

Munzone, F., Hazrati, J., Hakvoort, W., Tijum, R. V., & Boogard, T. V. D. (2026). Physics-Informed Recurrent Neural Networks with Kinematic Constraints for Large Deformation Metal Forming. Key Engineering Materials, 1050, 171-182. https://doi.org/10.4028/p-ls5ptz

Vancouver

Munzone F, Hazrati J, Hakvoort W, Tijum RV, Boogard TVD. Physics-Informed Recurrent Neural Networks with Kinematic Constraints for Large Deformation Metal Forming. Key Engineering Materials. 2026;1050:171-182. doi:10.4028/p-ls5ptz

BibTeX
@article{Munzone2026,
  author = {Munzone, Francesco and Hazrati, Javad and Hakvoort, Wouter and Tijum, Redmer van and Boogard, Ton van den},
  title = {Physics-Informed Recurrent Neural Networks with Kinematic Constraints for Large Deformation Metal Forming},
  journal = {Key Engineering Materials},
  year = {2026},
  volume = {1050},
  pages = {171--182},
  doi = {10.4028/p-ls5ptz}
}
Kostenlos starten →