Surrogate model of the thermoforming of fiber reinforced thermoplastics

Surrogate model of the thermoforming of fiber reinforced thermoplastics


download PDF

Abstract. In the thermoforming process shearing of fiber reinforced thermoplastics (FRTP) leads to wrinkle formation and is therefore one of the most critical deformation mechanism. The target value to predict wrinkle formation is the shear angle which is considered in this paper. To predict the shear angle distribution during the thermoforming of FRTPs a Convolutional Neural Network (CNN) is used. The approach is based on the consideration of the principal curvature characteristics, resulting in the reduction of any complex geometry to planar, parabolic, elliptical, semi-spherical and hyperbolic areas. In similar research, CNNs are trained for each specific geometry. In this work, the CNN refers to a database of the mentioned curvature characteristics. In theory, all forming geometries can be created from these, which is why the CNN is enabled to predict the forming result of any complex geometry. In this paper, the benchmark geometry of a double dome is selected as the validation geometry and the error in the prediction of the shear angle is compared with the results of numerical forming simulations performed.

Thermoforming, Composite Forming, Machine Learning, Artificial Neural Networks, Surrogate Modelling

Published online 4/19/2023, 8 pages
Copyright © 2023 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA

Citation: MIDDELHOFF Jan, UJVARI Csenger, HÜRKAMP André, DRÖDER Klaus, Surrogate model of the thermoforming of fiber reinforced thermoplastics, Materials Research Proceedings, Vol. 28, pp 385-392, 2023


The article was published as article 42 of the book Material Forming

Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.

[1] C. Hopmann, M. Walter, Einführung in die Kunststoffverarbeitung, Carl Hanser Verlag GmbH & Co. KG, 2015.
[2] R. Azzouz, S. Allaoui, R. Moulart, Composite preforming defects: a review and a classification, Int. J. Mater. Form. 14 (2021) 1259-1278.
[3] U. Breuer, M. Neitzel, V. Ketzer, R. Reinicke, Deep drawing of fabric-reinforced thermoplastics: Wrinkle formation and their reduction, Polym. Compos. 17 (1996) 643-647.
[4] K. Dröder, Prozesstechnologie zur Herstellung von FVK-Metall-Hybriden, Springer Berlin Heidelberg, Berlin, Heidelberg, 2020.
[5] J. Middelhoff, A. Hürkamp, K. Dröder, Numerical Modelling of a Demonstrator to Investigate Geometric Parameter Influences on the Thermoforming of Fiber-Reinforced Thermoplastics, Proceedings of the 20th European Conference on Composite Materials, ECCM20, Lausanne, Switzerland, 2022
[6] C. Zimmerling, D. Dörr, F. Henning, L. Karger, A meta-model based approach for rapid formability estimation of continuous fibre reinforced components, AIP Conference Proceedings, Volume 1960(1), 2018, pp. 020042.
[7] S. Coutandin, Prozessstrategien für das automatisierte Preforming von bebinderten textilen Halbzeugen mit einem segmentierten Werkzeugsystem, Dissertation, Shaker Verlag
[8] C. Zimmerling, D. Trippe, B. Fengler, L. Karger, An approach for rapid prediction of textile draping results for variable composite component geometries using deep neural networks. In: Proceedings of the 22nd International ESAFORM Conference on Material Forming: ESAFORM 2019, AIP Publishing, 2019, pp. 20007
[9] W. Kühnel, Differentialgeometrie: Kurven – Flächen – Mannigfaltigkeiten, 5., aktualisierte Auflage, Springer eBook Collection. Vieweg+Teubner, Wiesbaden, 2010
[10] A. Hürkamp, R. Lorenz, T. Ossowski, B.-A. Behrens, K. Dröder, Simulation-based digital twin for the manufacturing of thermoplastic composites, Procedia CIRP 100 (2021) 1-6.
[11] P. Boisse, R. Akkerman, P. Carlone, L. Kärger, S.L. Lomov, J.A. Sherwood, Advances in composite forming through 25 years of ESAFORM, Int. J. Mater. Form. 15 (2022).
[12] M. Grubenmann, J. Heingärtner, P. Hora, D. Bassan, Influence of temperature on in-plane and out-of-plane mechanical behaviour of GFRP composite. J. Phys.: Conf. Ser. 1063 (2018) 12146.
[13] S. Kollmannsberger, D. D’Angella, M. Jokeit, L. Hermann, Deep Learning in Computational Mechanics: An Introductory Course (Studies in Computational Intelligence, 977), Springer International Publishing, Cham, 2021
[14] S. Ioffe, C. Szegedy, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, In: International Conference on machine learning, 2015 pp. 448-456.