Hostname: page-component-7dd5485656-s6l46 Total loading time: 0 Render date: 2025-10-30T16:29:43.114Z Has data issue: false hasContentIssue false
  • English
  • Français

Using convolutional neural networks to predict composite properties beyond the elastic limit

Published online by Cambridge University Press:  25 April 2019

Charles Yang ,
Youngsoo Kim ,
Seunghwa Ryu  and
Grace X. Gu
Charles Yang
Affiliation:
Department of Mechanical Engineering, University of California, Berkeley, CA 94720, USA
Youngsoo Kim
Affiliation:
Department of Mechanical Engineering & KI for the NanoCentury, Korea Advanced Institute of Science and Technology, Daejeon 34141, Republic of Korea
Seunghwa Ryu*
Affiliation:
Department of Mechanical Engineering & KI for the NanoCentury, Korea Advanced Institute of Science and Technology, Daejeon 34141, Republic of Korea
Grace X. Gu*
Affiliation:
Department of Mechanical Engineering, University of California, Berkeley, CA 94720, USA
*
Address all correspondence to Seunghwa Ryu at ryush@kaist.ac.kr and Grace X. Gu at ggu@berkeley.edu
Address all correspondence to Seunghwa Ryu at ryush@kaist.ac.kr and Grace X. Gu at ggu@berkeley.edu
Get access

Abstract

Composites are ubiquitous throughout nature and often display both high strength and toughness, despite the use of simple base constituents. In the hopes of recreating the high-performance of natural composites, numerical methods such as finite element method (FEM) are often used to calculate the mechanical properties of composites. However, the vast design space of composites and computational cost of numerical methods limit the application of high-throughput computing for optimizing composite design, especially when considering the entire failure path. In this work, the authors leverage deep learning (DL) to predict material properties (stiffness, strength, and toughness) calculated by FEM, motivated by DL's significantly faster inference speed. Results of this study demonstrate potential for DL to accelerate composite design optimization.

Information

Type
Artificial Intelligence Research Letters
Information
MRS Communications , Volume 9 , Issue 2 , June 2019 , pp. 609 - 617
Copyright
Copyright © Materials Research Society 2019 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

Footnotes

*

These authors contributed equally to this work.

References

1.Ortiz, C. and Boyce, M.C.: Bioinspired structural materials. Science 319, 1053 (2008).Google Scholar
2.Wegst, U.G.K., Bai, H., Saiz, E., Tomsia, A.P., and Ritchie, R.O.: Bioinspired structural materials. Nat. Mater. 14, 23 (2015).Google Scholar
3.Espinosa, H.D., Rim, J.E., Barthelat, F., and Buehler, M.J.: Merger of structure and material in nacre and bone—perspectives on de novo biomimetic materials. Prog. Mater. Sci. 54, 1059 (2009).Google Scholar
4.Meyers, M.A., McKittrick, J., and Chen, P-Y.: Structural biological materials: critical mechanics-materials connections. Science 339, 773 (2013).Google Scholar
5.Wei, X., Naraghi, M., and Espinosa, H.D.: Optimal length scales emerging from shear load transfer in natural materials: application to carbon-based nanocomposite design. ACS Nano 6, 2333 (2012).Google Scholar
6.Gu, G.X., Libonati, F., Wettermark, S.D., and Buehler, M.J.: Printing nature: unraveling the role of nacre's mineral bridges. J. Mech. Behav. Biomed. Mater. 76, 135 (2017).Google Scholar
7.Libonati, F., Gu, G.X., Qin, Z., Vergani, L., and Buehler, M.J.: Bone-inspired materials by design: toughness amplification observed using 3D printing and testing. Adv. Eng. Mater. 18, 1354 (2016).Google Scholar
8.Kim, Y., Kim, Y., Lee, T.I., Kim, T.S., and Ryu, S.: An extended analytic model for the elastic properties of platelet-staggered composites and its application to 3D printed structures. Compos. Struct. 189, 27 (2018).Google Scholar
9.Tran, P., Ngo, T.D., Ghazlan, A., and Hui, D.: Bimaterial 3D printing and numerical analysis of bio-inspired composite structures under in-plane and transverse loadings. Composites, Part B 108, 210 (2017).Google Scholar
10.Zhang, P., Heyne, M.A., and To, A.C.: Biomimetic staggered composites with highly enhanced energy dissipation: modeling, 3D printing, and testing. J. Mech. Phys. Solids 83, 285 (2015).Google Scholar
11.Gu, G.X., Takaffoli, M., and Buehler, M.J.: Hierarchically enhanced impact resistance of bioinspired composites. Adv. Mater. 29, 1 (2017).Google Scholar
12.Ji, B. and Gao, H.: Mechanical properties of nanostructure of biological materials. J. Mech. Phys. Solids 52, 1963 (2004).Google Scholar
13.Jeong, H., Signetti, S., Han, T.S., and Ryu, S.: Phase field modeling of crack propagation under combined shear and tensile loading with hybrid formulation. Comput. Mater. Sci. 155, 483 (2018).Google Scholar
14.Miehe, C., Hofacker, M., and Welschinger, F.: A phase field model for rate-independent crack propagation: robust algorithmic implementation based on operator splits. Comput. Methods Appl. Mech. Eng. 199, 2765 (2010).Google Scholar
15.Miehe, C., Welschinger, F., and Hofacker, M.: Thermodynamically consistent phase-field models of fracture: variational principles and multi-field FE implementations. Int. J. Numer. Methods Eng. 83, 1273 (2010).Google Scholar
16.Amor, H., Marigo, J.J., and Maurini, C.: Regularized formulation of the variational brittle fracture with unilateral contact: numerical experiments. J. Mech. Phys. Solids 57, 1209 (2009).Google Scholar
17.Kuhn, C. and Müller, R.: A continuum phase field model for fracture. Eng. Fract. Mech. 77, 3625 (2010).Google Scholar
18.Bourdin, B., Francfort, G.A., and Marigo, J.J.: The variational approach to fracture. J. Elast. 91, 5 (2008).Google Scholar
19.Krizhevsky, A., Sutskever, I. and Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 84 (2017).Google Scholar
20.Lecun, Y., Bengio, Y., and Hinton, G.: Deep learning. Nature 521, 436 (2015).Google Scholar
21.Jo, T., Hou, J., Eickholt, J., and Cheng, J.: Improving protein fold recognition by deep learning networks. Sci. Rep. 5, 1 (2015).Google Scholar
22.Wei, L. and Roberts, E.: Neural network control of focal position during time-lapse microscopy of cells. Sci. Rep. 8, 1 (2018).Google Scholar
23.Paganini, M., De Oliveira, L., and Nachman, B.: CaloGAN: simulating 3D high energy particle showers in multilayer electromagnetic calorimeters with generative adversarial networks. Phys. Rev. D 97, 14021 (2018).Google Scholar
24.Hanakata, P.Z., Cubuk, E.D., Campbell, D.K., and Park, H.S.: Accelerated search and design of stretchable graphene kirigami using machine learning. Phys. Rev. Lett. 121, 255304 (2018).Google Scholar
25.Gu, G.X., Chen, C.T., and Buehler, M.J.: De novo composite design based on machine learning algorithm. Extreme Mech. Lett. 18, 19 (2018).Google Scholar
26.Gu, G.X., Chen, C.T., Richmond, D.J., and Buehler, M.J.: Bioinspired hierarchical composite design using machine learning: simulation, additive manufacturing, and experiment. Mater. Horiz. 5, 939 (2018).Google Scholar
27.Breiman, L.: Random forests. Mach. Learn. 45, 5 (2001).Google Scholar
28.Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Pretenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825 (2011).Google Scholar
29.Chollet, F.: Keras: the python deep learning library. Astrophysics Source Code Library (2018).Google Scholar
30.Kingma, D.P. and Ba, J.: Adam: A method for stochastic optimization, in International Conference on Learning Representation (2015).Google Scholar
31.Erhan, D., Bengio, Y., Courville, A., and Vincent, P.: Visualizing higher-layer features of a deep network. Département d'Informatique Rech. Opérationnelle, Tech. Rep. 1341 No. 1341, 1 (2009).Google Scholar
32.Nesterov, Y.: A method for solving the convex programming problem with convergence rate O(1/k^2). Dokl. Akad. Nauk SSSR 269, 543 (1983).Google Scholar
33.Zoph, B. and Le, Q.: Neural architecture search with reinforcement learning, in International Conference on Learning Representations (2017).Google Scholar
34.Ioffe, S. and Szegedy, C.: Batch normalization: accelerating network training by reducing covariate shift, in International Conference on Machine Learning, edited by F. Bach and D. Blei (Proc. of Mach. Learn. Res. 37, Lille, France, 2015 ) p. 448.Google Scholar
35.Zeiler, M.D. and Fergus, R.: in Visualizing and understanding convolutional Networks, in European Conference on Computer Vision 2014, edited by Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (13th European Conf. on Comp. Vision 8689, Zurich, Switzerland, 2014 ), p. 818.Google Scholar
Supplementary material: PDF

Yang et al. supplementary material

Table S1 and Figures S1-S4

Download Yang et al. supplementary material(PDF)
PDF 353.7 KB