Machine Learning Algorithms to Estimate Composite Mechanical Properties

  • Janaina Gomide Universidade Federal do Rio de Janeiro
  • Lucas Vignoli Universidade Federal do Rio de Janeiro
  • Yuri Macedo Universidade Federal do Rio de Janeiro

Resumo


Estruturas feitas de materiais compósitos têm sido implementadas em diversos setores como transporte, construção civil, marítimo e aeroespacial. O foco deste estudo são os compósitos unidirecionais que possuem 5 propriedades independentes. A obtenção dessas propriedades pode ser feita experimentalmente, numericamente e analiticamente. Neste artigo vamos propor uma forma alternativa de estimar essas propriedades, usando algoritmos de aprendizado de máquina. O objetivo deste artigo é avaliar algoritmos de aprendizado de máquina para gerar a estimativa dessas 5 propriedades de compósitos. Experimentos foram realizados com dois conjuntos de dados distintos e os resultados obtidos foram satisfatórios.

Referências

Benzarti, K., Cangemi, L., and Dal Maso, F. (2001). Transverse properties of unidirectional glass/epoxy composites: influence of fibre surface treatments. Composites Part A: Applied Science and Manufacturing, 32(2):197–206.

Bledzki, A., Kessler, A., Rikards, R., and Chate, A. (1999). Determination of elastic constants of glass/epoxy unidirectional laminates by the vibration testing of plates. Composites Science and Technology, 59(13):2015–2024.

Bravo-Castillero, J., Guinovart-Díaz, R., Rodríguez-Ramos, R., Sabina, F. J., and Brenner, R. (2012). Unified analytical formulae for the effective properties of periodic fibrous composites. Materials Letters, 73:68–71.

Camanho, P., Maimí, P., and Dávila, C. (2007). Prediction of size effects in notched laminates using continuum damage mechanics. Composites Science and Technology, 67(13):2715–2727.

Géron, A. (2019). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. O’Reilly Media.

Guo, P., Meng, W., Xu, M., Li, V. C., and Bao, Y. (2021). Predicting mechanical properties of high-performance fiber-reinforced cementitious composites by integrating micromechanics and machine learning. Materials, 14(12):3143.

Huang, H. and Talreja, R. (2005). Effects of void geometry on elastic properties of unidirectional fiber reinforced composites. Composites Science and Technology, 65(13):1964–1981.

Huang, Z.-m. (2001). Micromechanical prediction of ultimate strength of transversely isotropic fibrous composites. International journal of solids and structures, 38(22-23):4147–4172.

Kaddour, A. and Hinton, M. (2012). Input data for test cases used in benchmarking triaxial failure theories of composites. Journal of Composite Materials, 46(19-20):2295–2312.

Kaddour, A., Hinton, M., Smith, P., and Li, S. (2013). The background to the third world-wide failure exercise. Journal of Composite Materials, 47(20-21):2417–2426.

Kriz, R. and Stinchcomb, W. (1979). Elastic moduli of transversely isotropic graphite fibers and their composites. Experimental Mechanics, 19(2):41–49.

Lee, J. and Soutis, C. (2007). A study on the compressive strength of thick carbon fibre–epoxy laminates. Composites Science and Technology, 67(10):2015–2026.

Li, W., Cai, H., and Zheng, J. (2014). Characterization of strength of carbon fiber reinforced polymer composite based on micromechanics. Polymers and Polymer Composites, 22(2):105–116.

Merayo, D., Rodríguez-Prieto, A., and Camacho, A. M. (2020). Prediction of physical and mechanical properties for metallic materials selection using big data and artificial neural networks. IEEE Access, 8:13444–13456.

Pathan, M., Ponnusami, S., Pathan, J., Pitisongsawat, R., Erice, B., Petrinic, N., and Tagarielli, V. (2019). Predictions of the mechanical properties of unidirectional fibre composites by supervised machine learning. Scientific reports, 9(1):1–10.

Rajput, R., Raut, A., and Setti, S. G. (2022). Prediction of mechanical properties of aluminium metal matrix hybrid composites synthesized using stir casting process by machine learning. Materials Today: Proceedings, 59:1735–1742.

Schaefer, J., Werner, B., and Daniel, I. M. (2014). Strain-rate-dependent failure of a toughened matrix composite. Experimental Mechanics, 54(6):1111–1120.

Shahinur, S. and Hasan, M. (2020). Natural fiber and synthetic fiber composites: Comparison of properties, performance, cost and environmental benefits.

Soden, P., Hinton, M., and Kaddour, A. (1998). Lamina properties, lay-up configurations and loading conditions for a range of fibre-reinforced composite laminates. Composites Science and Technology, 58(7):1011–1022.

Tsai, S. and Hahn, H. (1980). Introduction to composite materials, technomic publ. Co., Westport.

Ventura, A. M. F. (2009). Os compósitos e a sua aplicação na reabilitação de estruturas metálicas. Ciência & Tecnologia dos Materiais, 21(3-4):10–19.

Vignoli, L. L., Savi, M. A., Pacheco, P. M., and Kalamkarov, A. L. (2019). Comparative analysis of micromechanical models for the elastic composite laminae. Composites Part B: Engineering, 174:106961.

Wang, W., Wang, H., Zhou, J., Fan, H., and Liu, X. (2021). Machine learning prediction of mechanical properties of braided-textile reinforced tubular structures. Materials & Design, 212:110181.

Yim, J. H. and Gillespie Jr, J. (2000). Damping characteristics of 0° and 90° as4/3501-6 unidirectional laminates including the transverse shear effect. Composite Structures, 50(3):217–225.
Publicado
25/09/2023
Como Citar

Selecione um Formato
GOMIDE, Janaina; VIGNOLI, Lucas; MACEDO, Yuri. Machine Learning Algorithms to Estimate Composite Mechanical Properties. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 20. , 2023, Belo Horizonte/MG. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 461-472. ISSN 2763-9061. DOI: https://doi.org/10.5753/eniac.2023.234255.