A stochastic multiscale method for the prediction of the thermal conductivity of Polymer nanocomposites through hybrid machine learning algorithms
Source abstract
Abstract
Abstract In this paper, we propose a hybrid machine learning method to predict the thermal conductivity of polymeric nanocomposites (PNCs). Therefore, a combination of artificial neural network (ANN) and particle swarm optimization (PSO) is applied to estimate the relationship between variable input and output parameters. The ANN is used for modeling the composite while PSO improves the prediction performance through an optimized global minimum search. We select the thermal conductivity of the fibers and the matrix, the kapitza resistance, volume fraction and aspect ratio as input parameters. The output is the macroscopic (homogenized) thermal conductivity of the composite. The results show that the PSO significantly improves the predictive ability of this hybrid intelligent algorithm, which outperforms traditional neural networks.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Thermal properties of materials · Composite Material Mechanics · Carbon Nanotubes in Composites
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (44)
Show source-provided references
1. Thermal conductivity of polymer-based composites: Fundamentals and applications10.1016/j.progpolymsci.2016.03.001 ↗
2. Average stress in matrix and average elastic energy of materials with misfitting inclusions10.1016/0001-6160(73)90064-3 ↗
3. Effective conductivity of anisotropic two-phase composite media10.1103/PhysRevB.39.4504 ↗
4. A step-by-step method of rule-of-mixture of fiber-and particle-reinforced composite materials10.1016/S0263-8223(98)00033-6 ↗
5. Modelling and analysis of effective thermal conductivity for polymer composites with sheet-like nanoparticles10.1007/s10853-018-2816-0 ↗
6. Multiscale micromechanical modeling of polymer/clay nanocomposites and the effective clay particle10.1016/j.polymer.2003.10.100 ↗
7. Hyperbolic heat conduction and thermoelastic solution of functionally graded cnt reinforced cylindrical panel subjected to heat pulse10.1016/j.ijsolstr.2018.12.030 ↗
8. Modeling of two-phase random composite materials by finite element, mori–tanaka and strong contrast methods10.1016/j.compositesb.2012.05.015 ↗
9. Yang · 2019
10. Quantitative study of interface/interphase in epoxy/graphene-based nanocomposites by combining stem and eels10.1021/acsami.6b12915 ↗
11. Direct observation of polymer sheathing in carbon nanotube- polycarbonate composites10.1021/nl0345973 ↗
12. Experimental characterization methods for thermal contact resistance: a review10.1016/j.applthermaleng.2017.10.163 ↗
13. Stochastic modelling of clay/epoxy nanocomposites10.1016/j.compstruct.2014.07.009 ↗
14. A data-driven computational homogenization method based on neural networks for the nonlinear anisotropic electrical response of graphene/polymer nanocomposites10.1007/s00466-018-1643-0 ↗
15. Application of machine learning to predict the multiaxial strain-sensing response of cnt-polymer composites10.1016/j.carbon.2019.02.001 ↗
16. Artificial intelligence design algorithm for nanocomposites optimized for shear crack resistance10.1088/2399-1984/ab36f0 ↗
17. On the problem of local minima in backpropagation10.1109/34.107014 ↗
18. The prediction of self-healing capacity of bacteria-based concrete using machine learning approaches
19. Using pso-ga algorithm for training artificial neural network to forecast solar space heating system parameters10.1016/j.applthermaleng.2018.10.070 ↗
20. Prediction of energetic performance of a building integrated photovoltaic/thermal system thorough artificial neural network and hybrid particle swarm optimization models10.1016/j.enconman.2019.01.005 ↗
21. Injection molding process optimization of a bi-aspheric lens using hybrid artificial neural networks10.1016/j.measurement.2018.10.066 ↗
22. Kennedy J, Eberhart R. Particle swarm optimization (pso). In Proc. IEEE International Conference on Neural Networks, Perth, Australia, 1995, pp. 1942–1948.10.1109/ICNN.1995.488968 ↗
23. Low-temperature synthesis of high-purity single-walled carbon nanotubes from alcohol10.1016/S0009-2614(02)00838-2 ↗
24. Enhanced thermal conductivity of ethylene glycol with single-walled carbon nanotube inclusions10.1016/j.ijheatmasstransfer.2012.03.001 ↗
25. Dc and ac conductivity in epoxy resin/multiwall carbon nanotubes percolative system10.1002/pc.20981 ↗
26. Prediction of the effective thermal conductivity of carbon nanotube-reinforced polymer systems10.1002/pc.22859 ↗
27. Modeling kapitza resistance of two-phase composite material10.1016/j.compstruct.2016.06.025 ↗
28. Stochastic multiscale modeling of heat conductivity of polymeric clay nanocomposites10.1016/j.mechmat.2019.103280 ↗
29. Interphase effect on the elastic and thermal conductivity response of polymer nanocomposite materials: 3d finite element study10.1016/j.commatsci.2012.11.035 ↗
30. Small sample sensitivity analysis techniques for computer models. with an application to risk assessment10.1080/03610928008827996 ↗
31. The role of latin hypercube sampling method in reliability engineering
32. Keitel H. Bewertungsmethoden für die Prognosequalität von Kriechmodellen des Betons, doctoralthesis, Bauhaus-Universität Weimar, 2012. 10.25643/bauhaus-universitaet.1556.
33. Dimensional crossover of thermal transport in few-layer graphene10.1038/nmat2753 ↗
34. Thermal and electrical conductivity of single-and multi-walled carbon nanotube-epoxy composites10.1016/j.compscitech.2005.10.016 ↗
35. Energy dissipation in graphene field-effect transistors10.1021/nl803883h ↗
36. Combined molecular dynamics-finite element multiscale modeling of thermal conduction in graphene epoxy nanocomposites10.1016/j.carbon.2013.04.048 ↗
37. Stochastic multi-scale modeling of cnt/polymer composites10.1016/j.commatsci.2010.08.036 ↗
38. Calculated thermal properties of single-walled carbon nanotube suspensions10.1021/jp710021n ↗
39. Heat transfer in high volume fraction cnt nanocomposites: Effects of inter-nanotube thermal resistance10.1016/j.cplett.2011.04.005 ↗
40. Kennedy J, Eberhart R. Particle swarm optimization. In Proceedings of ICNN’95 - International Conference on Neural Networks, volume 4, 1995, pp. 1942–1948 vol 4. DOI: 10.1109/ICNN.1995.488968.10.1109/ICNN.1995.488968 ↗
41. Kohavi R, et al. A study of cross-validation and bootstrap for accuracy estimation and model selection, in: Ijcai, volume 14, Montreal, Canada, 1995, pp. 1137–1145.
42. Assessing model fit by cross-validation10.1021/ci025626i ↗
43. Linear model selection by cross-validation10.1080/01621459.1993.10476299 ↗
44. No free lunch theorems for optimization10.1109/4235.585893 ↗