In nanocomposites, debonding originates at the interface between reinforcing particles and the matrix. Since experimental characterization and computational modeling of particle debonding are highly resource-intensive, the development of efficient predictive strategies is essential. In this study, a machine learning framework is proposed to predict debonding evolution using data obtained from finite element simulations. A multiscale modeling approach using representative volume elements (RVEs) was implemented to analyze debonding in the interface area of polyethylene–graphene nanocomposites. Debonding at the interface between graphene nanosheets and the polymer was modeled using a cohesive-zone model defined by traction–separation curves. Cohesive-zone parameters for polyethylene-graphene were sourced from molecular dynamics simulations. RVEs were generated with a Python script and analyzed using the Abaqus explicit solver. The study examined the effects of volume fraction, aspect ratio, and loading conditions on particle debonding. The results closely matched the published literature and effectively captured the trends in debonding behavior. A dataset comprising input parameters (e.g., volume fraction, aspect ratio) and the corresponding output (debonding percentage) was fed into a 10-layer artificial neural network. The network was trained using a gradient descent algorithm with various activation functions. The trained model demonstrated reasonable generalization capabilities with minimal overfitting. Subsequently, the model was used to predict debonding percentages for unseen input data. The results accurately captured the trends in debonding behavior for varying volume fractions and aspect ratios. The observed discrepancies were attributed to the limited dataset and the absence of debonding in specific samples.
Tabandeh-KhorshidMKumarAOmraniE, et al. Synthesis, characterization, and properties of graphene reinforced metal-matrix nanocomposites. Compos B Eng2020; 183: 107664.
2.
ThostensonETLiCChouT-W. Nanocomposites in context. Compos Sci Technol2005; 65(3–4): 491–516.
3.
PottsJRDreyerDRBielawskiCW, et al. Graphene-based polymer nanocomposites. Polymer2011; 52(1): 5–25.
4.
Alizadeh, SahraeiAAyatiMBaniassadiM, et al. AC and DC electrical behavior of MWCNT/epoxy nanocomposite near percolation threshold: equivalent circuits and percolation limits. J Appl Phys2018; 123(10): 105109.
5.
YousefiESheidaeiAMahdaviM, et al. Effect of nanofiller geometry on the energy absorption capability of coiled carbon nanotube composite material. Compos Sci Technol2017; 153: 222–231.
6.
SeibertJPfallerSRiesM. Investigation of the influence of nano-sized particles on the entanglement distribution of a generic polymer nanocomposite using molecular dynamics. Math Mech Solids2024; 29(3): 596–611.
7.
FukushimaHDrzalLRookB, et al. Thermal conductivity of exfoliated graphite nanocomposites. J Therm Anal Calorim2006; 85: 235–238.
8.
XiaXWengGJ. Dual percolations of electrical conductivity and electromagnetic interference shielding in progressively agglomerated CNT/polymer nanocomposites. Math Mech Solids2021; 26(8): 1120–1137.
9.
AhmadiMSaxenaP. Analytical modeling of the electrical conductivity of CNT-filled polymer nanocomposites. Math Mech Solids2025; 30(2): 428–449.
10.
DesmoratB. Energy theorems for micromorphic media. Math Mech Complex Syst2025; 14(1): 1–10.
11.
dell’IsolaFEugsterSRFedeleR, et al. Second-gradient continua: from Lagrangian to Eulerian and back. Math Mech Solids2022; 27(12): 2715–2750.
12.
CuomoMContrafattoLGrecoL. A cohesive interface model with degrading friction coefficient. Math Mech Complex Syst2024; 12(2): 113–133.
13.
IqbalAASakibNIqbalAP, et al. Graphene-based nanocomposites and their fabrication, mechanical properties and applications. Materialia2020; 12: 100815.
14.
PapageorgiouDGKinlochIAYoungRJ. Mechanical properties of graphene and graphene-based nanocomposites. Prog Mater Sci2017; 90: 75–127.
15.
ZiolkowskiP. Computational complexity and its influence on predictive capabilities of machine learning models for concrete mix design. Materials2023; 16(17): 5956.
16.
KushchVShmegeraSBrøndstedP, et al. Numerical simulation of progressive debonding in fiber reinforced composite under transverse loading. Int J Eng Sci2011; 49(1): 17–29.
17.
ZhangBYangZSunX, et al. A virtual experimental approach to estimate composite mechanical properties: modeling with an explicit finite element method. Comput Mater Sci2010; 49(3): 645–651.
18.
OrificiACHerszbergIThomsonRS. Review of methodologies for composite material modelling incorporating failure. Compos Struct2008; 86(1–3): 194–210.
19.
GenoeseAGenoeseARizziNL, et al. On the in-plane failure and post-failure behaviour of pristine and perforated single-layer graphene sheets. Math Mech Solids2019; 24(11): 3418–3443.
20.
BheemreddyVChandrashekharaKDharaniLR, et al. Modeling of fiber pull-out in continuous fiber reinforced ceramic composites using finite element method and artificial neural networks. Comput Mater Sci2013; 79: 663–673.
21.
WangKChenLWuJ, et al. Epoxy nanocomposites with highly exfoliated clay: mechanical properties and fracture mechanisms. Macromolecules2005; 38(3): 788–800.
22.
ChenHXueQZhengQ, et al. Influence of nanotube chirality, temperature, and chemical modification on the interfacial bonding between carbon nanotubes and polyphenylacetylene. J Phys Chem C2008; 112(42): 16514–16520.
23.
LiaoKLiS. Interfacial characteristics of a carbon nanotube–polystyrene composite system. Appl Phys Lett2001; 79(25): 4225–4227.
JiangL. A cohesive law for carbon nanotube/polymer interface accounting for chemical covalent bonds. Math Mech Solids2010; 15(7): 718–732.
26.
SafaeiMSheidaeiABaniassadiM, et al. An interfacial debonding-induced damage model for graphite nanoplatelet polymer composites. Comput Mater Sci2015; 96: 191–199.
27.
AwasthiAPLagoudasDCHammerandDC. Modeling of graphene–polymer interfacial mechanical behavior using molecular dynamics. Model Simul Mater Sci Eng2008; 17(1): 015002.
28.
SafaeiMPourbandariDKarimiM, et al. Developing a multiscale approach for damage analysis of functionalized-GNP/PET nanocomposite. J Mater Sci2024; 59(7): 2907–2923.
29.
MorganDJacobsR. Opportunities and challenges for machine learning in materials science. Annu Rev Mater Res2020; 50(1): 71–103.
30.
Champa-BujaicoEGarcía-DíazPDíez-PascualAM. Machine learning for property prediction and optimization of polymeric nanocomposites: a state-of-the-art. Int J Mol Sci2022; 23(18): 10712.
31.
AdesinaOJamiruTDaniyanIA, et al. Mechanical property prediction of SPS processed GNP/PLA polymer nanocomposite using artificial neural network. Cogent Engineering2020; 7(1): 1720894.
32.
YuM-HKimH-S. Deep-learning based damage sensing of carbon fiber/polypropylene composite via addressable conducting network. Compos Struct2021; 267: 113871.
33.
ChróścielewskiJDell’IsolaFEremeyevVA, et al. On rotational instability within the nonlinear six-parameter shell theory. Int J Solids Struct2020; 196: 179–189.
34.
GiorgioIDe, AngeloMTurcoE, et al. A Biot–Cosserat two-dimensional elastic nonlinear model for a micromorphic medium. Contin Mech Thermodyn2020; 32(5): 1357–1369.
35.
GiorgioIDell’IsolaFMisraA. Chirality in 2D Cosserat media related to stretch-micro-rotation coupling with links to granular micromechanics. Int J Solids Struct2020; 202: 28–38.
36.
GiorgioIHildFGeramiE, et al. Experimental verification of 2D Cosserat chirality with stretch-micro-rotation coupling in orthotropic metamaterials with granular motif. Mech Res Commun2022; 126: 104020.
37.
La ValleG. A new deformation measure for the nonlinear micropolar continuum. Zeitschrift Für Angewandte Mathematik Und Physik2022; 73(2): 78.
38.
ShiraniMGiorgioIAstoriD, et al. A mixed Cosserat and higher gradient formulation for fibrous tissues and biomaterials. Int J Solids Struct2025; 324: 113671.
39.
AlibertJ-JSeppecherPDell’IsolaF. Truss modular beams with deformation energy depending on higher displacement gradients. Math Mech Solids2003; 8(1): 51–73.
40.
CiallellaAD’AnnibaleFDel VescovoD, et al. Deformation patterns in a second-gradient lattice annular plate composed of “Spira mirabilis” fibers: A. Ciallella et al. Contin Mech Thermodyn2023; 35(4): 1561–1580.
41.
Dell’IsolaFEremeyevVKorolenkoV, et al. Deformation of an elastic second gradient spherical body under equatorial line density of dead forces. Eur J Mech Solids2024; 103: 105153.
42.
EugsterSRDell’IsolaFFedeleR, et al. Piola transformations in second-gradient continua. Mech Res Commun2022; 120: 103836.
43.
FedeleRLucianoR. A recursive formula to compute Lagrangian actions corresponding to an Eulerian edge h-force in elastic materials with a sufficiently high grade. Math Mech Complex Syst2024; 12(4): 389–410.
44.
FedeleRSteigmannDJ. Lagrangian and Eulerian formulations of second-grade elasticity via convected coordinates. Math Mech Complex Syst2025; 13(3): 377–389.
45.
GiorgioI. Lattice shells composed of two families of curved Kirchhoff rods: an archetypal example, topology optimization of a cycloidal metamaterial. Contin Mech Thermodyn2021; 33(4): 1063–1082.
46.
RapisardaA. A kinematic swarm-based approach for simulating stress-strain curves. Math Mech Complex Syst2025; 13(2): 99–125.
47.
MoschiniSTurcoE. Towards the synthesis of planar beams whose deformation energy depends on the third gradient of displacement. Math Mech Complex Syst2024; 12(4): 573–597.
48.
Murcia TerranovaL. Planar one-dimensional continua whose energy depends on the gradient of curvature: an overview of their applications in metamaterials design. Math Mech Complex Syst2025; 13(2): 127–166.
49.
ReiherJCGiorgioIBertramA. Finite-element analysis of polyhedra under point and line forces in second-strain gradient elasticity. J Eng Mech2017; 143(2): 04016112.
50.
Dell’IsolaFAndreausUPlacidiL. At the origins and in the vanguard of peridynamics, non-local and higher-gradient continuum mechanics: an underestimated and still topical contribution of Gabrio Piola. Math Mech Solids2015; 20(8): 887–928.
51.
MenciMNataliniRPaulT. Microscopic, kinetic and hydrodynamic hybrid models of collective motions with chemotaxis: a numerical study. Math Mech Complex Syst2023; 12(1): 47–83.
52.
PolizzottoCFuschiPPisanoAA. Nonlocal strain gradient elastic beam models with two-step differential approach and decoupling of standard and extra boundary conditions, I. Math Mech Complex Syst2022; 10(3): 205–231.
53.
PolizzottoCFuschiPPisanoAA. Absolute and relative size effects within nonlocal strain gradient elastic beam models, II. Math Mech Complex Syst2022; 10(3): 233–244.
54.
BittencourtFFCabralEF. Exploring the chaotic behavior of quasistatic strength and fatigue tests for structural laminates of composite materials. Math Mech Complex Syst2025; 13(4): 417–435.
55.
PlacidiLBarchiesiEdell’IsolaandF, et al. On a hemi-variational formulation for a 2D elasto-plastic-damage strain gradient solid with granular microstructure. Math Eng2022; 5: 1–24.
56.
PlacidiLBarchiesiEMisraA. A strain gradient variational approach to damage: a comparison with damage gradient models and numerical results. Math Mech Complex Syst2018; 6(2): 77–100.
57.
PlacidiLMisraABarchiesiE. Simulation results for damage with evolving microstructure and growing strain gradient moduli. Contin Mech Thermodyn2019; 31(4): 1143–1163.
58.
RosciniFRezaeiNPlacidiL. A damage elasto-plastic discrete model for the nonlinear characterization of pullout tests. Math Mech Complex Syst2025; 13(1): 73–97.
59.
SafaeiMKarimiMRPourbandariD, et al. Multiscale investigation of debonding behavior in anisotropic graphene–polyethylene metamaterial nanocomposites. Contin Mech Thermodyn2024; 36(6): 1767–1785.
DaiGMishnaevskyLJr. Damage evolution in nanoclay-reinforced polymers: a three-dimensional computational study. Compos Sci Technol2013; 74: 67–77.
62.
ReederJR. 3-D mixed mode delamination fracture criteria–an experimentalist’s perspective. In: American Society for Composites 21st annual technical conference, Dearborn, MI, 17–20 September, 2006.
63.
LiWDichiaraABaiJ. Carbon nanotube–graphene nanoplatelet hybrids as high-performance multifunctional reinforcements in epoxy composites. Compos Sci Technol2013; 74: 221–227.
64.
ReddyCDRajendranSLiewK. Equilibrium configuration and continuum elastic properties of finite sized graphene. Nanotechnology2006; 17(3): 864.
65.
KarimiMAbriniaKHamdiaKM, et al. Effects of functional group type and coverage on the interfacial strength and load transfer of graphene-polyethylene nanocomposites: a molecular dynamics simulation. Applied Physics A2022; 128(4): 341.
