Thermal field estimation in CFRTP composites using an attention-enhanced U-Net
Source abstract
Abstract
Abstract This study presents a surrogate model based on the convolutional U-Net architecture to predict the thermal field in a carbon fibre-reinforced thermoplastic tape at the microscale during brief and localized heating. Leveraging microstructure data within a machine learning framework, the proposed model aims to enhance the accuracy of temperature field predictions at a low computational cost. The incorporation of a co-attention mechanism to handle image channels of different nature significantly improves precision, resulting in a strong correlation between the model’s predictions and the ground truth obtained from the numerical solution of the heat equation. This capability enables rapid assessment of diverse microstructures, facilitating optimization and real-time applications in manufacturing settings.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Ultrasonics and Acoustic Wave Propagation · Thermal properties of materials · High voltage insulation and dielectric phenomena
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (32)
Show source-provided references
1. Yao S-S, Jin F-L, Rhee KY, Hui D, Park S-J (2018) Recent advances in carbon-fiber-reinforced thermoplastic composites: a review. Compos Part B: Engineering 142:241–25010.1016/j.compositesb.2017.12.007 ↗
2. Teltschik J, Matter J, Woebbeking S, Jahn K, Adasme YB, Paepegem WV, Drechsler K, Tallawi M (2024) Review on recycling of carbon fibre reinforced thermoplastics with a focus on polyetheretherketone. Compos A: Appl Sci Manuf 18410.1016/j.compositesa.2024.108236 ↗
3. Wazeer A, Das A, Abeykoon C, Sinha A, Karmakar A (2023) Composites for electric vehicles and automotive sector: a review. Green Energy Intell Transp 2:10004310.1016/j.geits.2022.100043 ↗
4. Condé-Wolter J, Ruf MG, Liebsch A, Lebelt T, Koch I, Drechsler K, Gude M (2023) Hydrogen permeability of thermoplastic composites and liner systems for future mobility applications. Compos A: Appl Sci Manuf 16710.1016/j.compositesa.2023.107446 ↗
5. Ismail KBM, Kumar MA, Mahalingam S, Raj B, Kim J (2024) Carbon fiber-reinforced polymers for energy storage applications. J Energy Storage 8410.1016/j.est.2024.110931 ↗
6. Murray RE, Beach R, Barnes D, Snowberg D, Berry D, Rooney S, Jenks M, Gage B, Boro T, Wallen S, Hughes S (2021) Structural validation of a thermoplastic composite wind turbine blade with comparison to a thermoset composite blade. Renew Energy 164:1100–110710.1016/j.renene.2020.10.040 ↗
7. Zhang J, Lin G, Vaidya U, Wang H (2023) Past, present and future prospective of global carbon fibre composite developments and applications. Compos Part B: Engineering 25010.1016/j.compositesb.2022.110463 ↗
8. Karandikar HM, Mistree F (1992) Tailoring composite materials through optimal selection of their constituents. J Mech Des 114:451–45810.1115/1.2926573 ↗
9. Whitaker S (1999) The method of volume averaging, vol 13. Springer, Netherlands10.1007/978-94-017-3389-2 ↗
10. Torquato S (2002) Random heterogeneous materials, vol 16. Springer, New York10.1007/978-1-4757-6355-3 ↗
11. Hyer MW, Waas AM (2018) Micromechanics of linear elastic continuous fiber composites, pp 295–326. Elsevier10.1016/B978-0-12-803581-8.09880-5 ↗
12. Chung D (2017) Processing-structure-property relationships of continuous carbon fiber polymer-matrix composites. Mater Sci Eng: R: Reports 113:1–2910.1016/j.mser.2017.01.002 ↗
13. Baskaran A, Kautz EJ, Chowdhary A, Ma W, Yener B, Lewis DJ (2021) The adoption of image-driven machine learning for microstructure characterization and materials design: a perspective. arXiv:2105.0972910.1007/s11837-021-04805-9 ↗
14. Peng X-L, Fathidoost M, Lin B, Yang Y, Xu B-X (2024) What can machine learning help with microstructure-informed materials modeling and design? arXiv:2405.1839610.1557/s43577-024-00797-4 ↗
15. Tafreshi OA, Hoa SV, Shadmehri F, Hoang DM, Rosca D (2019) Heat transfer analysis of automated fiber placement of thermoplastic composites using a hot gas torch. Adv Manuf: Polym Compos Sci 5:206–223
16. Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WM, Frangi AF (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. TU München, pp 234–24110.1007/978-3-319-24574-4_28 ↗
17. Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press
18. Santos JE, Xu D, Jo H, Landry CJ, Prodanović M, Pyrcz MJ (2020) Poreflow-net: a 3d convolutional neural network to predict fluid flow through porous media. Adv Water Resour 13810.1016/j.advwatres.2020.103539 ↗
19. Wu J, Yin X, Xiao H (2018) Seeing permeability from images: fast prediction with convolutional neural networks. Sci Bull 63:1215–122210.1016/j.scib.2018.08.006 ↗
20. Marcato A, Santos JE, Boccardo G, Viswanathan H, Marchisio D, Prodanović M (2023) Prediction of local concentration fields in porous media with chemical reaction using a multi scale convolutional neural network. Chem Eng J vol 45510.1016/j.cej.2022.140367 ↗
21. Xu J, Wei H, Bao H (2023) Physics-informed neural networks for studying heat transfer in porous media. Int J Heat Mass Transfer 217:12467110.1016/j.ijheatmasstransfer.2023.124671 ↗
22. Guo X, Li W, Iorio F (2016) Convolutional neural networks for steady flow approximation. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 481–490, ACM10.1145/2939672.2939738 ↗
23. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. arXiv:1706.03762
24. Luo Y, Liang C, Qin S, Liu J, Fu Q, Yang S (2024) A two-branch encoder-decoder network for image tampering localization. Appl Soft Comput 16410.1016/j.asoc.2024.111992 ↗
25. Zhou H, Qi L, Huang H, Yang X, Wan Z, Wen X (2022) Canet: co-attention network for rgb-d semantic segmentation. Pattern Recognit vol 12410.1016/j.patcog.2021.108468 ↗
26. Liu B, Li B, Sreeram V, Li S (2024) Mbt-unet: Multi-branch transform combined with unet for semantic segmentation of remote sensing images. Remote Sens vol 1610.3390/rs16152776 ↗
27. Zienkiewicz O, Taylor R, Zhu JZ (2013) The finite element method: its basis and fundamentals: Seventh Edition. Butterworth-Heinemann
28. Godsil C, Royle G (2001) Algebraic graph theory. Springer, New York10.1007/978-1-4613-0163-9 ↗
29. Johnson C (1987) Numerical solution of partial differential equations by the finite element method. Dover Publications
30. Chen J, Xu X, Zhou J, Li B (2022) Interfacial thermal resistance: past, present, and future. Rev Mod Phys 9410.1103/RevModPhys.94.025002 ↗
31. Ma R, Chen S, Whang Q (2022) Lightweight monocular depth estimation. arXiv:2212.11363
32. Wang Z, Bovik A, Sheikh H, Simoncelli E (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13:600–61210.1109/TIP.2003.819861 ↗