Fracture Risk Modeling in Pyrolyzed Phenolic Resin: Microstructure Prediction and Stress Concentration Factor Evolution via CNN-CVAE and FEM

Abstract:

The microstructure of phenolic resin undergoes significant transformation under high-temperature pyrolysis, affecting its mechanical performance and fracture behavior. By combining Convolutional Neural Networks (CNN) and Conditional Variational Autoencoders (CVAE), a generative modeling framework was proposed. Then its suitability to predict microstructure evolution of phenolic resin under varying pyrolysis temperatures was studied. Finite Element Method (FEM) simulations were conducted to analyze stress distributions. Results indicate a significant increase in the area of high stress concentration zones with rising pyrolysis temperature, with pore bridges, sharp edges, and clustered porosity identified as potential fracture initiation sites.

• Periodical: Key Engineering Materials (Volume 1037)
• Pages: 79-92
• DOI: https://doi.org/10.4028/p-XATf9s
• Online since: January 2026
• Authors: Wen Han Chen, Shu Hua Niu, Dan Wang, Cheng Li, Dong Chen, Jian Wei Shi*
• Keywords: Convolutional Neural Networks, Fracture Risk, Microstructure Prediction, Pyrolyzed Phenolic Resin, Stress Concentration Factor

References

[1] Zhao Y, Yan Y, Shen T, Yang Y, Zhao Y, Shang H, Zhang B and Wang D 2024 Robust degradation of tetracycline hydrochloride by electro-assisted activation of peroxymonosulfate over porous cobalt-manganese oxide nanowire array in situ grown on nickel foam J. Environ. Chem. Eng. 12 114662

DOI: 10.1016/j.jece.2024.114662

[2] Wang P, Li D, Wang L, Guo S, Zhao Y, Shang H, Wang D and Zhang B 2024 Ultrafine CoNi alloy nanoparticles anchored on surface-roughened halloysite nanotubes for highly efficient catalytic hydrogenation of 4-nitrophenol Chem. Eng. J. 495 153631

DOI: 10.1016/j.cej.2024.153631

[3] Wang P, Wang L, Zhao Y, Zhang B and Wang D 2024 Progress in Degradation of Volatile Organic Compounds by Catalytic Oxidation: a Review Based on the Kinds of Active Components of Catalysts Water. Air. Soil Pollut. 235 7

DOI: 10.1007/s11270-023-06802-x

[4] Wang D, Zhang H, Ren M, Fan Y, Gao Y, Lv Z Y, Yu Y and Chen J 2020 Electrophilic chlorination of dibenzo-p-dioxin and dibenzofuran over composite copper and iron chlorides and oxides in combustion flue gas Chemosphere 256 127065

DOI: 10.1016/j.chemosphere.2020.127065

[5] Zhou J, Feng X, Zhao Y, Cui R, Wang D and Zhang B 2022 Noble-metal-free CuNi/Co3O4 hybrid nanosheets as efficient and magnetically recyclable catalysts for hydrolysis of ammonia borane J. Alloys Compd. 923 166345

DOI: 10.1016/j.jallcom.2022.166345

[6] Wang D, Zhang H, Fan Y, Cao R, Gao Y and Chen J 2020 Synergistic effect of mixed Cu and Fe oxides and chlorides on electrophilic chlorination of dibenzo-p-dioxin and dibenzofuran Sci. Total Environ. 721 137563

DOI: 10.1016/j.scitotenv.2020.137563

[7] Wang D, Zhang H, Fan Y, Ren M, Cao R and Chen J 2019 Electrophilic Chlorination of Naphthalene in Combustion Flue Gas Environ. Sci. Technol. 53 5741–9

DOI: 10.1021/acs.est.9b00350

[8] Shi J, Boyer G, Mourzenko V and Thovert J-F 2023 A comprehensive numerical model for the pyrolysis of intumescent polymers: Application to EVA-ATH compounds Chem. Eng. Sci. 268 118385

DOI: 10.1016/j.ces.2022.118385

[9] Song C, Jin Y, Gu X and Shi J 2023 A solar-driven self-repairing sponge for efficient recovery of crude oil Colloids Surf. Physicochem. Eng. Asp. 658 130692

DOI: 10.1016/j.colsurfa.2022.130692

[10] Song C, Jiang Z, Gu X, Li H and Shi J 2022 A bilayer solar evaporator with all-in-one design for efficient seawater desalination J. Colloid Interface Sci. 616 709–19

DOI: 10.1016/j.jcis.2022.02.075

[11] Shi J, Boyer G, Mourzenko V and Thovert J-F 2020 Evolutive Models for the Geometry and Heat Conductivity of an Intumescent EVA-ATH Composite during Its Thermal Degradation Materials 13 5258

DOI: 10.3390/ma13225258

[12] J, Yang X, Du K, Guo Q and Bai Z 2025 Effects of structural parameters on the load distribution unevenness in CFRP hybrid bonded-bolted joint Polym. Compos. 46 4688–702

DOI: 10.1002/pc.29269

[13] Chi P, Sun J, Luo X, Cui R and Dong H 2023 Reconstruction of 3D digital rocks with controllable porosity using CVAE-GAN Geoenergy Sci. Eng. 230 212264

DOI: 10.1016/j.geoen.2023.212264

[14] Zhang T, Xia P and Lu F 2021 3D reconstruction of digital cores based on a model using generative adversarial networks and variational auto-encoders J. Pet. Sci. Eng. 207 109151

DOI: 10.1016/j.petrol.2021.109151

[15] Han W, Hou Y, Shi J, Meng L and Sapanathan T 2025 Experimental and numerical investigation on the mechanical behavior of 3D star-shaped auxetic structure Compos. Struct. 354 118803

DOI: 10.1016/j.compstruct.2024.118803

[16] Shi J, Yang X, Chen X, Du K, Li C and Yang Y 2024 Numerical and experimental investigation on the load-bearing performance of plain-woven composites hybrid bonded-bolted joints Polym. Compos. 45 1195–207

DOI: 10.1002/pc.27845

[17] Shams R, Masihi M, Boozarjomehry R B and Blunt M J 2020 Coupled generative adversarial and auto-encoder neural networks to reconstruct three-dimensional multi-scale porous media J. Pet. Sci. Eng. 186 106794

DOI: 10.1016/j.petrol.2019.106794

[18] Feng J, Teng Q, Li B, He X, Chen H and Li Y 2020 An end-to-end three-dimensional reconstruction framework of porous media from a single two-dimensional image based on deep learning Comput. Methods Appl. Mech. Eng.

DOI: 10.1016/j.cma.2020.113043

[19] Zhu J-Y, Zhang R, Pathak D, Darrell T, Efros A A, Wang O and Shechtman E 2018 Toward multimodal image-to-image translation

[20] Zhang F, He X, Teng Q, Wu X and Dong X 2022 3D-PMRNN: reconstructing three-dimensional porous media from the two-dimensional image with recurrent neural network J. Pet. Sci. Eng. 208 109652

DOI: 10.1016/j.petrol.2021.109652

[21] Volkhonskiy D, Muravleva E, Sudakov O, Orlov D, Belozerov B, Burnaev E and Koroteev D 2021 Reconstruction of 3D porous media from 2D slices

DOI: 10.1103/physreve.105.025304

[22] Chen D, Noda N-A, Takaki R and Sano Y 2020 Intensity of singular stress fields (ISSFs) in micro-bond test in comparison with ISSFs in pull-out test Int. J. Mech. Sci. 183 105817

DOI: 10.1016/j.ijmecsci.2020.105817

[23] Noda N-A, Chen D and Sano Y 2022 Reference solution and proportional method to calculate intensity of singular stress field (ISSF) at the interface corner where reinforced fiber enters resin matrix Mech. Adv. Mater. Struct. 29 2962–72

DOI: 10.1080/15376494.2021.1882624

[24] Noda N-A, Chen D, Zhang G and Sano Y 2020 Single-fiber pull-out analysis comparing the intensities of singular stress fields (ISSFs) at fiber end/entry points Int. J. Mech. Sci. 165 105196

DOI: 10.1016/j.ijmecsci.2019.105196

[25] Zhang K, Zhang X and Peng K 2025 Evaluating the process operating state taking into consideration operator interventions with application to a hot rolling mill process Control Eng. Pract. 155 106176

DOI: 10.1016/j.conengprac.2024.106176

[26] Yin Z, Tie Y, Duan Y, Li C and Chen D 2022 Impact damage assessment in patch-repaired carbon fiber-reinforced polymer laminates using the nonlinear Lamb wave-mixing technique Polym. Compos. 43 8152–69

DOI: 10.1002/pc.26984

[27] Hoang N Q, Kang S, Yoon H-K and Lee J-S 2024 Enhancing anomaly detection in ground-penetrating radar images through reconstruction loss and high-variability Results Eng. 21 101874

DOI: 10.1016/j.rineng.2024.101874

[28] Zhang X and Jiang L 2024 Conditional variational autoencoder with gaussian process regression recognition for parametric models J. Comput. Appl. Math. 438 115532

DOI: 10.1016/j.cam.2023.115532

[29] Bautista-Valhondo J and Alfaro-Pozo R 2020 Mixed integer linear programming models for Flow Shop Scheduling with a demand plan of job types Cent. Eur. J. Oper. Res. 28 5–23

DOI: 10.1007/s10100-018-0553-8

[30] Shi J, Boyer G, Mourzenko V and Thovert J-F 2018 On the influence of boundary conditions when determining transport coefficients from digital images of porous media 14émes Journées d'Etudes sur les Milieux Poreux (JEMP2018) (Nantes, France)

DOI: 10.1007/s11242-020-01404-1

[31] Zhu W, Chen D, Shi J, Zhang J, Zhao H and Li C 2024 Design and optimization of a temperature controller with low overshoot, fast respond and high COP based on water-source thermoelectric heat pump Appl. Therm. Eng. 242 122473

DOI: 10.1016/j.applthermaleng.2024.122473

[32] Cho Y-J 2024 Weighted intersection over union (wIoU) for evaluating image segmentation Pattern Recognit. Lett. 185 101–7

DOI: 10.1016/j.patrec.2024.07.011

[33] Wong Y M, Yeap P L, Ong A L K, Tuan J K L, Lew W S, Lee J C L and Tan H Q 2024 Machine learning prediction of dice similarity coefficient for validation of deformable image registration Intell.-Based Med. 10 100163

DOI: 10.1016/j.ibmed.2024.100163

[34] Cui K, Song G, Wang W, Liu H, Yang Y, Sun C, Zhao Z, Lin H and Chen D 2024 Force analysis and distribution evolution of Fe3O4 nanoparticles in magnetic fluids Chin. J. Phys. 88 982–90

DOI: 10.1016/j.cjph.2024.02.037