A Convolutional‑Neural‑Network Surrogate for Steady‑State Radiative Heating in Thermoforming
DOI:
https://doi.org/10.15377/2409-5826.2025.12.5Keywords:
Digital twin, Thermoforming, Radiative heat transfer, Finite‑element simulation, Convolutional neural networkAbstract
Thermoforming is widely used to produce lightweight packaging and durable components, yet controlling the temperature field during the heating stage remains challenging. Finite‑element models that capture conduction, convection and diffuse‑radiative exchange provide accurate predictions, but their high computational cost precludes real‑time optimization and digital‑twin deployment. In this study a convolutional‑neural‑network (CNN) surrogate is developed to predict steady‑state temperature distributions for a polymer sheet heated by an array of radiative heaters. A parametric study sampled heater temperature distributions, sheet thicknesses and initial temperatures, and a nonlinear finite‑element model was discretized and used to compute steady‑state temperature fields. The resulting dataset of input vectors and temperature maps served to train a fully convolutional neural network, whose weights were optimized with the Adam algorithm by minimizing the mean‑squared error. On a held‑out test set the surrogate achieved a coefficient of determination of 0.96 and a mean relative error less than 3%, while producing predictions in under 1 second—an order‑of‑magnitude speedup relative to the finite‑element solver. Gradient‑based inversion of the trained network successfully recovered heater temperature distributions that reproduced target temperature fields, even under simulated heater failures, demonstrating the feasibility of fault‑tolerant control. These results show that the proposed CNN surrogate bridges high‑fidelity simulation and real‑time control, enabling digital‑twin implementations for thermoforming and providing a foundation for future extensions to transient heating and experimental validation.
Downloads
References
Incropera FP, DeWitt DP, Bergman TL, Lavine AS. Fundamentals of heat and mass transfer. 6th ed. Hoboken (NJ): John Wiley & Sons; 2007.
Díaz Sierra EF, Cruz De Jesus FM, Jiménez José JJ, Lebrón Santana A, Nuñez Ríos JJ, Traverso Avilés LM. Machine learning surrogate dynamical system model for thermal energy storage. LACCEI Int Multi-Conf Eng Educ Technol. 2024; 1(1): 1795. https://doi.org/10.18687/LACCEI2024.1.1.1795 DOI: https://doi.org/10.18687/LACCEI2024.1.1.1795
Johnston G. Digital Twins. The Case for Policy Use. Energy Systems Catapult; 2023.
Throne JL. Radiant heat transfer in thermoforming. SPE ANTEC Tech Papers. 1995; 41: 000.
Nam GJ, Ahn KH, Lee JW. Three-dimensional simulation of thermoforming process and its comparison with experiments. Polym Eng Sci. 2000; 40(10): 2232-40. https://doi.org/10.1002/pen.11355 DOI: https://doi.org/10.1002/pen.11355
Ragoubi A, Ducloud G, Agazzi A, Dewailly P, Le Goff R. Modeling the thermoforming process of a complex geometry based on a thermo-visco-hyperelastic model. J Manuf Mater Process. 2024; 8(1): 33. https://doi.org/10.3390/jmmp8010033 DOI: https://doi.org/10.3390/jmmp8010033
Hosseinionari H, Ramezankhani M, Seethaler R, Milani AS. Development of a computationally efficient model of the heating phase in thermoforming process based on the experimental radiation pattern of heaters. J Manuf Mater Process. 2023; 7(1): 48. https://doi.org/10.3390/jmmp7010048 DOI: https://doi.org/10.3390/jmmp7010048
Schneider T, Beiderwellen Bedrikow A, Dietsch M, Voelkel K, Pflaum H, Stahl K. Machine learning based surrogate models for the thermal behavior of multi-plate clutches. Appl Syst Innov. 2022; 5(5): 97. https://doi.org/10.3390/asi5050097 DOI: https://doi.org/10.3390/asi5050097
Laugksch K, Rousseau P, Laubscher R. A PINN surrogate modeling methodology for steady-state integrated thermofluid systems modeling. Math Comput Appl. 2023; 28(2): 52. https://doi.org/10.3390/mca28020052 DOI: https://doi.org/10.3390/mca28020052
Tahmasebi Moradi A, Ren V, Le-Creurer B, Mang C, Yagoubi M. Feasibility study of CNNs and MLPs for radiation heat transfer in 2-D furnaces with spectrally participative gases. arXiv preprint arXiv:2506.08033. 2025.
Peng JZ, Liu X, Aubry N, Chen Z, Wu WT. Data-driven modeling of geometry-adaptive steady heat transfer based on convolutional neural networks: heat convection. arXiv preprint arXiv:2101.03692. 2021. https://doi.org/10.3390/fluids6120436 DOI: https://doi.org/10.3390/fluids6120436
Bokil G, Geyer TF, Wolff S. Towards convolutional neural networks for heat exchangers in electrified aircraft. In: Proceedings of the Deutscher Luft- und Raumfahrtkongress 2023; October 2023; Stuttgart, Germany. https://doi.org/10.2514/6.2024-4108 DOI: https://doi.org/10.2514/6.2024-4108
Guo X, Li W, Iorio F. Convolutional neural networks for steady flow approximation. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '16). San Francisco, CA, USA; 2016 Aug 13-17. p. 481-90. ACM. https://doi.org/10.1145/2939672.2939738 DOI: https://doi.org/10.1145/2939672.2939738
Sun Y, Elhanashi A, Ma H, Chiarelli MR. Heat conduction plate layout optimization using physics-driven convolutional neural networks. Appl Sci. 2022; 12(21): 10986. https://doi.org/10.3390/app122110986 DOI: https://doi.org/10.3390/app122110986
Stipsitz M, Sanchis-Alepuz H. Approximating the steady-state temperature of 3D electronic systems with convolutional neural networks. Math Comput Appl. 2022; 27(1): 7. https://doi.org/10.3390/mca27010007 DOI: https://doi.org/10.3390/mca27010007
Parsons Q, Nowak D, Bortz M, Johnson T, Mark A, Edelvik F. Machine learning surrogates for the optimization of curing ovens. Eng Appl Artif Intell. 2024; 133(Pt C): 108086. https://doi.org/10.1016/j.engappai.2024.108086 DOI: https://doi.org/10.1016/j.engappai.2024.108086
Sabathiel S, Sanchis-Alepuz H, Wilson AS, Reynvaan J, Stipsitz M. Neural network-based reconstruction of steady-state temperature systems with unknown material composition. Sci Rep. 2024; 14: 22265. https://doi.org/10.1038/s41598-024-73380-1 DOI: https://doi.org/10.1038/s41598-024-73380-1
Fiala V, Pechánek R. Surrogate-based heat transfer modeling for important parts in a fully enclosed traction motor. Exp Therm Fluid Sci. 2025; 107: 9649–62. https://doi.org/10.1007/s00202-025-02993-0 DOI: https://doi.org/10.1007/s00202-025-02993-0
Turan E, Konuşkan Y, Yıldırım N, Tunçalp D, İnan M, Yasin O, et al. Digital twin modelling for optimizing the material consumption: a case study on sustainability improvement of thermoforming process. Sustain Comput Inform Syst. 2022; 35: 100655. https://doi.org/10.1016/j.suscom.2022.100655 DOI: https://doi.org/10.1016/j.suscom.2022.100655
Dhondt G. The finite element method for three-dimensional thermomechanical applications. Hoboken (NJ): Wiley; 2004. https://doi.org/10.1002/0470021217 DOI: https://doi.org/10.1002/0470021217
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Erhan Turan, Buryan Turan, Alper Sametoğlu
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
All the published articles are licensed under the terms of the Creative Commons Attribution Non-Commercial License (CC BY-NC 4.0) which permits unrestricted, non-commercial use, distribution and reproduction in any medium, provided the work is properly cited.
