Optimization of laminated composite materials configuration using neural networks and simulated annealing

Authors

DOI:

https://doi.org/10.20983/culcyt.2024.3.2.6

Keywords:

composite materials, artificial neural networks, optimization, simulated anneling, objective function

Abstract

The optimization of laminated composite materials is one of the main challenges in the design of structural components or systems due to the influence of multiple parameters on their performance and mechanical response to deformation. This research uses a metamodel based on artificial neural networks to predict performance indices, specifically the Tsai-Wu failure index, from the configuration of a laminated composite material subject to loads, considering thicknesses and fiber orientations. The metamodel feeds an objective function designed to improve the configuration of a part by optimizing fiber orientations. A simulated annealing algorithm adapted for laminated composite materials is combined with neural networks, generating a solution space that offers the designer a wide range of options to approach the analysis of the problem. The reported method is an efficient alternative to the traditional method of analyzing laminated composite materials, streamlining the process, and expanding the configuration possibilities available for selection.

Downloads

Download data is not yet available.

Author Biographies

Julio César Galvis Chacón, Universidad de Guanajuato

Universidad de Guanajuato, Departamento de Ingeniería Mecánica, División de Ingenierías Campus Irapuato-Salamanca

Alejandro E. Rodríguez-Sánchez, Universidad Panamericana

Ha sido investigador y profesor universitario de programas de ingeniería en diversas universidades e instituciones públicas y privadas de México, entre las que se destacan la Universidad Panamericana, Campus Guadalajara, la Universidad de Guanajuato y el Tecnológico Nacional de México. Es miembro del Sistema Nacional de Investigadores, nivel I, del Consejo Nacional de Humanidades, Ciencias y Tecnologías (CONAHCYT) de México. Actualmente es investigador en el área de la ingeniería y el análisis de materiales, y ha contribuido a la misma mediante el uso de métodos de inteligencia artificial para modelado y análisis de materiales complejos. Es autor del libro Redes Neuronales Artificiales: Principios y Aplicaciones.

Elías Rigoberto Ledesma Orozco, Universidad de Guanajuato

Professor-researcher, Universidad de Guanajuato, Departamento de Ingeniería Mecánica, División de Ingenierías Campus Irapuato-Salamanca

References

P. K. Mallick, Fiber-Reinforced Composites: Materials, Manufacturing, and Design, 3.ª ed. Boca Raton: CRC Press, 2007.

T. W. Clyne y D. Hull, An Introduction to Composite Materials, 3.ª ed. Cambridge: Cambridge University Press, 2019. doi: 10.1017/9781139050586.

P. Beardmore y C. F. Johnson, “The potential for composites in structural automotive applications”, Compos Sci Technol, vol. 26, n.º 4, pp. 251-281, 1986, doi: 10.1016/0266-3538(86)90002-3.

O. Bas, E. Ates y F. Ozturk, “Thermoplastic Composite Materials for the Aerospace Industry”, RDMS, vol. 15, n.º 5, 2021, doi: 10.31031/rdms.2021.15.000872.

J. Zhang, G. Lin, U. Vaidya y H. Wang, “Past, present and future prospective of global carbon fibre composite developments and applications”, Compos B Eng, vol. 250, p. 110463, 2023, doi: 10.1016/j.compositesb.2022.110463.

I. A. Hassan, H. S. Ramadan, M. A. Saleh y D. Hissel, “Hydrogen storage technologies for stationary and mobile applications: Review, analysis and perspectives”, Renew. Sustain. Energy Rev., vol. 149, art. 111311, oct. 2021, doi: 10.1016/j.rser.2021.111311.

C. Jenkins y S. Khanna, Mechanics of materials: a modern integration of mechanics and materials in structural design, 1.ª ed. Academic Press, 2005.

S. W. Tsai y E. M. Wu, “A General Theory of Strength for Anisotropic Materials”, J Compos Mater, vol. 5, n.º 1, pp. 58-80, 1971, doi: 10.1177/002199837100500106.

E. J. Hearn, “Strain energy”, en Mechanics of Materials 1: An Introduction to the Mechanics of Elastic and Plastic Deformation of Solids and Structural, 3.ª ed., E. J. Hearn, ed. Oxford: Butterworth-Heinemann, 1997, cap. 11, pp. 254-296. doi: 10.1016/B978-075063265-2/50012-8.

H. Ghiasi, K. Fayazbakhsh, D. Pasini y L. Lessard, “Optimum stacking sequence design of composite materials Part II: Variable stiffness design”, Compos. Struct., vol. 93, n.º 1. pp. 1-13, dic. 2010, doi: 10.1016/j.compstruct.2010.06.001.

H. Ghiasi, D. Pasini y L. Lessard, “Optimum stacking sequence design of composite materials Part I: Constant stiffness design”, Compos. Struct., vol. 90, n.º 1, pp. 1-11, sept. 2009, doi: 10.1016/j.compstruct.2009.01.006.

S. Setoodeh, M. M. Abdalla y Z. Gürdal, “Design of variable–stiffness laminates using lamination parameters”, Compos B Eng, vol. 37, n.º 4, pp. 301-309, 2006, doi: 10.1016/j.compositesb.2005.12.001.

R. T. L. Ferreira, I. A. Ashcroft, S. Li y P. Zhuo, “Optimisation of Fibre-Paths in Composites Produced by Additive Manufacturing”, en EngOpt 2018 Proceedings of the 6th International Conference on Engineering Optimization, Springer International Publishing, 2019, pp. 1083-1094, doi: 10.1007/978-3-319-97773-7_94.

G. X. Gu, C. T. Chen y M. J. Buehler, “De novo composite design based on machine learning algorithm”, Extreme Mech Lett, vol. 18, pp. 19-28, en. 2018, doi: 10.1016/j.eml.2017.10.001.

C.-T. Chen y G. X. Gu, “Machine learning for composite materials”, MRS Commun, vol. 9, n.º 2, pp. 556-566, jun. 2019, doi: 10.1557/mrc.2019.32.

G. X. Gu, C.-T. Chen, D. J. Richmond y M. J. Buehler, “Bioinspired hierarchical composite design using machine learning: Simulation, additive manufacturing, and experiment”, Mater Horiz, vol. 5, n.º 5, pp. 939-945, sept. 2018, doi: 10.1039/c8mh00653a.

C.-T. Chen y G. X. Gu, “Generative Deep Neural Networks for Inverse Materials Design Using Backpropagation and Active Learning”, Adv. Sci., vol. 7, n.º 5, mar. 2020, doi: 10.1002/advs.201902607.

J. Chen, L. Wan, Y. Ismail, J. Ye y D. Yang, “A micromechanics and machine learning coupled approach for failure prediction of unidirectional CFRP composites under triaxial loading: A preliminary study”, Compos Struct, vol. 267, art. 113876, jul. 2021, doi: 10.1016/j.compstruct.2021.113876.

Z. Liao, C. Qiu, J. Yang, J. Yang y L. Yang, “Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models”, Polymers, vol. 14, n.º 15, ag. 2022, doi: 10.3390/polym14153229.

E. Ledesma-Orozco, J. C. Galvis-Chacón y A. E. Rodríguez-Sánchez, “Neural networks modeling of strain energy density and Tsai-Wu index in laminated composites”, J Compos Mater, vol. 58, n.º 10, feb. 2024, doi: 10.1177/00219983241235856.

J. N. Reddy, Mechanics of Laminated Composite Plates and Shells: Theory and Analysis, 2.ª ed. Boca Raton: CRC Press, 2003, doi: 10.1201/b12409.

J. Leon-Becerra, O. A. González-Estrada y H. Sánchez-Acevedo, “Comparison of Models to Predict Mechanical Properties of FR-AM Composites and a Fractographical Study”, Polymers, vol. 14, n.º 17, sept. 2022, doi: 10.3390/polym14173546.

J. León-Becerra, M. Á. Hidalgo-Salazar y O. A. González-Estrada, “Progressive damage analysis of carbon fiber-reinforced additive manufacturing composites”, Int J Adv Manuf Technol, vol. 126, n.º 5, pp. 2617-2631, 2023, doi: 10.1007/s00170-023-11256-w.

E. J. Barbero, Finite element analysis of composite materials using ANSYS, 2.ª ed. Boca Raton: CRC Press, 2013, doi: 10.1201/b16295.

S. Zhang, “On the accuracy of Reissner-Mindlin plate model for stress boundary conditions”, Mathematical Modelling and Numerical Analysis, vol. 40, n.º 2, 2006, doi: 10.1051/m2an:2006014.

C. C. Aggarwal, Neural Networks and Deep Learning. Springer International Publishing, 2018, doi: 10.1007/978-3-319-94463-0.

A. E. Rodríguez-Sánchez y H. Plascencia-Mora, “Modeling hysteresis in expanded polystyrene foams under compressive loads using feed-forward neural networks”, J. Cell. Plast., vol. 59, n.º 4, may. 2023, doi: 10.1177/0021955X231174362.

M. Abadi et al., “TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems”, arXiv, art. arXiv.1603.04467, mar. 2016, doi: 10.48550/arXiv.1603.04467.

V. A. Alcántar, “Optimización de recipientes a presión del Tipo III y IV”, tesis doctoral, Universidad de Guanajuato, Salamanca, Guanajuato, 2015.

N. S. Nise, Control Systems Engineering, 6.ª ed. Hoboken, NJ: John Wiley & Sons, 2011.

D. T. Pham y D. Karaboga, Intelligent Optimisation Techniques, 1.ª ed. Londres: Springer London, 2000.

S. Kirkpatrick, C. D. Gelatt y M. P. Vecchi, “Optimization by Simulated Annealing”, Science, vol. 220, n.º 4598, pp. 671-680, may. 1983, doi: 10.1126/science.220.4598.671.

N. Metropolis, A. W. Rosenbluth, M. N. Rosenbluth, A. H. Teller y E. Teller, “Equation of State Calculations by Fast Computing Machines”, J Chem Phys, vol. 21, n.º 6, pp. 1087-1092, jun. 1953, doi: 10.1063/1.1699114.

P. J. M. Laarhoven y E. H. L. Aarts, Simulated annealing: theory and applications. EUA: Kluwer Academic Publishers, 1987.

S. Ledesma, G. Aviña y R. Sanchez, “Practical Considerations for Simulated Annealing Implementation”, en Simulated Annealing, C. M. Tan, ed. Rijeka: IntechOpen, 2008, cap. 20, doi: 10.5772/5560.

CULCYT vol. 21, núm. 3

Downloads

Published

2024-10-28

How to Cite

[1]
J. C. Galvis Chacón, A. E. Rodríguez-Sánchez, and E. R. Ledesma Orozco, “Optimization of laminated composite materials configuration using neural networks and simulated annealing”, Cult. Científ. y Tecnol., vol. 21, no. 3, pp. 53–65, Oct. 2024.

Issue

Vol. 21 No. 3 (2024): September-December 2024

Section

Artículos

License

Copyright (c) 2024 Julio César Galvis Chacón, Alejandro E. Rodríguez-Sánchez, Elías Rigoberto Ledesma Orozco

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Todos los contenidos de CULCYT se distribuyen bajo una licencia de uso y distribución “Creative Commons Reconocimiento-No Comercial 4.0 Internacional” (CC-BY-NC). Puede consultar desde aquí la versión informativa de la licencia.

Los autores/as que soliciten publicar en esta revista, aceptan los términos siguientes: a) los/las autores/as conservarán sus derechos de autor y garantizarán a la revista el derecho de primera publicación de su obra; y b) se permite y recomienda a los/las autores/as agregar enlaces de sus artículos en CULCYT en la página web de su institución o en la personal, debido a que ello puede generar intercambios interesantes y aumentar las citas de su obra publicada.