In laminated composite materials design, optimization mainly targets the stacking sequence configuration, which is defined by the lamina thickness and fiber orientations within each layer. Recent studies emphasize the increasing role of Machine Learning in promoting innovative composite designs by facilitating the accurate modeling of essential properties such as strength and stiffness. This study introduces two metamodels that utilize feed-forward artificial neural networks, taking laminate thickness and fiber steering angles as input parameters. The output variables, including strain energy density and the Tsai-Wu failure index, enable the prediction of stacking sequence configurations for laminated materials, a capability confirmed in a case study. The results showcase neural network models with the ability to predict these variables, achieving coefficients of determination above 0.90 for testing data. Consequently, this modeling approach has the potential to be a tool for designers, aiding in decision-making processes for the subsequent optimization of stiffness and strength in structural components made of laminated composite materials.
Brent StrongA. Fundamentals of composites manufacturing : materials, methods and applications. Southfield: Society of Manufacturing Engineers, 2008.
2.
HassanIARamadanHSSalehMA, et al.Hydrogen storage technologies for stationary and mobile applications: review, analysis and perspectives. Renew Sustain Energy Rev2021; 10: 149.
3.
TiwaryAKumarRChohanJS. A review on characteristics of composite and advanced materials used for aerospace applications. Mater Today Proc2022; 51: 865–870.
GurdalZHaftkaRTHajelaP. Design and optimization of laminated composite materials. 1st ed.Hoboken: Wiley, 1999.
6.
SetoodehSAbdallaMMGürdalZ. Design of variable–stiffness laminates using lamination parameters. Compos B Eng2006; 37(4): 301–309.
7.
GhiasiHPasiniDLessardL. Optimum stacking sequence design of composite materials Part I: constant stiffness design. Compos Struct2009; 90(1): 1–11.
8.
GhiasiHFayazbakhshKPasiniD, et al.Optimum stacking sequence design of composite materials. Part II: variable stiffness design. Compos Struct2010; 93(1): 1–13.
9.
KimSAzadMMSongJ, et al.Delamination detection framework for the imbalanced dataset in laminated composite using wasserstein generative adversarial network-based data augmentation. Appl Sci2023; 13: 11837.
10.
AzadMMKimSCheonYB, et al. Intelligent structural health monitoring of composite structures using machine learning, deep learning, and transfer learning: a review. Adv Compos Mater. 2023; 33:2: 162–188.
11.
KhanAAzadMMSohailM, et al.A review of physics-based models in prognostics and health management of laminated composite structures. International Journal of Precision Engineering and Manufacturing-Green Technology2023; 10: 1615–1635.
12.
GuGXChenCTBuehlerMJ. De novo composite design based on machine learning algorithm. Extreme Mechanics Letters2018; 18: 19–28.
13.
GuGXChenCTRichmondDJ, et al.Bioinspired hierarchical composite design using machine learning: simulation, additive manufacturing, and experiment. Mater Horiz2018; 5(5): 939–945.
14.
ChenCTGuGX. Machine learning for composite materials. MRS Communications2019; 9(2): 556–566.
15.
ChenCTGuGX. Generative deep neural networks for inverse materials design using backpropagation and active learning. Adv Sci2020; 7(5): 1902607.
16.
ChenJWanLIsmailY, et al.A micromechanics and machine learning coupled approach for failure prediction of unidirectional CFRP composites under triaxial loading: a preliminary study. Compos Struct2021; 7: 267.
17.
LiaoZQiuCYangJ, et al.Accelerating the layup sequences design of composite laminates via theory-guided machine learning models. Polymers2022; 8(15): 14.
18.
LiuXQinJZhaoK, et al.Design optimization of laminated composite structures using artificial neural network and genetic algorithm. Compos Struct2023; 305: 116500.
19.
Rodríguez-SánchezAELedesma-OrozcoELedesmaS. Part distortion optimization of aluminum-based aircraft structures using finite element modeling and artificial neural networks. CIRP Journal of Manufacturing Science and Technology2020; 31: 595–606.
20.
HullDClyneTW. An introduction to composite materials. Cambridge: Cambridge University Press, 1996.
21.
ReddyJN. Mechanics of laminated composite plates and shells: theory and analysis. 2nd ed.. Boca Raton: CRC Press, 2003.
22.
LegrandXKellyDCroskyA, et al.Optimisation of fibre steering in composite laminates using a genetic algorithm. Compos Struct2006; 75: 524–531.
23.
JustoJTávaraLGarcía-GuzmánL, et al.Characterization of 3D printed long fibre reinforced composites. Compos Struct2018; 185: 537–548.
24.
Leon-BecerraJGonzález-EstradaOASánchez-AcevedoH. Comparison of models to predict mechanical properties of FR-AM composites and a fractographical study. Polymers2022; 9(17): 14.
25.
León-BecerraJHidalgo-Salazar Mì González-EstradaOA. Progressive damage analysis of carbon fiber-reinforced additive manufacturing composites. Int J Adv Des Manuf Technol2023; 126(5): 2617–2631.
26.
León-BecerraJ. Progressive failure analysis of continuous fiber additive manufacturing composites. Newcastle upon Tyne: Sage, 2022.
27.
CamarenaVAA. Optimización de recipientes a presión del tipo III y IV. PhD Thesis. Guanajuato: Universidad de Guanajuato, 2015.
28.
ZhangS. On the accuracy of Reissner-Mindlin plate model for stress boundary conditions. Mathematical Modelling And Numerical Analysis2006; 40: 269–294
29.
ANSYS mechanical APDL: elements reference. Canonsburg: ANSYS, Inc., 2011.
30.
BarberoEJ. Finite element analysis of composite materials using ANSYS. 2nd ed.Boca Raton: CRC Press, 2013.
31.
TsaiSWWuEM. A general theory of strength for anisotropic materials. J Compos Mater1971; 5(1): 58–80.
32.
AggarwalCC. Neural networks and deep learning. New York City: Springer International Publishing, 2018.
33.
GurneyK. An introduction to neural networks. Boca Raton: CRC Press, 1997.
34.
Rodríguez-SánchezAEPlascencia-MoraH. Modeling hysteresis in expanded polystyrene foams under compressive loads using feed-forward neural networks. J Cell Plast2023; 5: 0021955X231174362.
35.
TielemanTHintonG. Divide the gradient by a running average of its recent magnitude. Human and Machine Hearing2012; 4(2): 26.
KneuselR. Practical deep learning. San Francisco: No Starch Press, 2021.
38.
KneuselR. Math for deep learning: what you need to know to understand neural networks. San Francisco: No Starch Press, 2021.
39.
AbadiMAgarwalABarhamP, et al.TensorFlow: large-scale machine learning on heterogeneous systems. Mountain View, CA: Tensorflow, 2015. Software available from tensorflow.org. https://www.tensorflow.org/.
