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.
Similar content being viewed by others
References
C. Ortiz and M.C. Boyce: Bioinspired structural materials. Science 319, 1053 (2008).
U.G.K. Wegst, H. Bai, E. Saiz, A.P. Tomsia, and R.O. Ritchie: Bioinspired structural materials. Nat. Mater. 14, 23 (2015).
H.D. Espinosa, J.E. Rim, F. Barthelat, and M.J. Buehler: Merger of structure and material in nacre and bone—perspectives on de novo biomimetic materials. Prog. Mater. Sci. 54, 1059 (2009).
M.A. Meyers, J. McKittrick, and P-Y. Chen: Structural biological materials: critical mechanics-materials connections. Science 339, 773 (2013).
X. Wei, M. Naraghi, and H.D. Espinosa: Optimal length scales emerging from shear load transfer in natural materials: application to carbon-based nanocomposite design. ACS Nano 6, 2333 (2012).
G.X. Gu, F. Libonati, S.D. Wettermark, and M.J. Buehler: Printing nature: unraveling the role of nacre’s mineral bridges. J. Mech. Behav. Biomed. Mater. 76, 135 (2017).
F. Libonati, G.X. Gu, Z. Qin, L. Vergani, and M.J. Buehler: Bone-inspired materials by design: toughness amplification observed using 3D printing and testing. Adv. Eng. Mater. 18, 1354 (2016).
Y. Kim, Y. Kim, T.I. Lee, T.S. Kim, and S. Ryu: An extended analytic model for the elastic properties of platelet-staggered composites and its application to 3D printed structures. Compos. Struct. 189, 27 (2018).
P. Tran, T.D. Ngo, A. Ghazlan, and D. Hui: Bimaterial 3D printing and numerical analysis of bio-inspired composite structures under in-plane and transverse loadings. Composites, Part B 108, 210 (2017).
P. Zhang, M.A. Heyne, and A.C. To: Biomimetic staggered composites with highly enhanced energy dissipation: modeling, 3D printing, and testing. J. Mech. Phys. Solids 83, 285 (2015).
G.X. Gu, M. Takaffoli, and M.J. Buehler: Hierarchically enhanced impact resistance of bioinspired composites. Adv. Mater. 29, 1 (2017).
B. Ji and H. Gao: Mechanical properties of nanostructure of biological materials. J. Mech. Phys. Solids 52, 1963 (2004).
H. Jeong, S. Signetti, T.S. Han, and S. Ryu: Phase field modeling of crack propagation under combined shear and tensile loading with hybrid formulation. Comput. Mater. Sci. 155, 483 (2018).
C. Miehe, M. Hofacker, and F. Welschinger: A phase field model for rateindependent crack propagation: robust algorithmic implementation based on operator splits. Comput. Methods Appl. Mech. Eng. 199, 2765 (2010).
C. Miehe, F. Welschinger, and M. Hofacker: Thermodynamically consistent phase-field models of fracture: variational principles and multi-field FE implementations. Int. J. Numer. Methods Eng. 83, 1273 (2010).
H. Amor, J.J. Marigo, and C. Maurini: Regularized formulation of the variational brittle fracture with unilateral contact: numerical experiments. J. Mech. Phys. Solids 57, 1209 (2009).
C. Kuhn and R. Müller: A continuum phase field model for fracture. Eng. Fract. Mech. 77, 3625 (2010).
B. Bourdin, G.A. Francfort, and J.J. Marigo: The variational approach to fracture. J. Elast. 91, 5 (2008).
A. Krizhevsky, I. Sutskever and G.E. Hinton: ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 84 (2017).
Y. Lecun, Y. Bengio, and G. Hinton: Deep learning. Nature 521, 436 (2015).
T. Jo, J. Hou, J. Eickholt, and J. Cheng: Improving protein fold recognition by deep learning networks. Sci. Rep. 5, 1 (2015).
L. Wei and E. Roberts: Neural network control of focal position during time-lapse microscopy of cells. Sci. Rep. 8, 1 (2018).
M. Paganini, L. De Oliveira, and B. Nachman: CaloGAN: simulating 3D high energy particle showers in multilayer electromagnetic calorimeters with generative adversarial networks. Phys. Rev. D 97, 14021 (2018).
P.Z. Hanakata, E.D. Cubuk, D.K. Campbell, and H.S. Park: Accelerated search and design of stretchable graphene kirigami using machine learning. Phys. Rev. Lett. 121, 255304 (2018).
G.X. Gu, C.T. Chen, and M.J. Buehler: De novo composite design based on machine learning algorithm. Extreme Mech. Lett. 18, 19 (2018).
G.X. Gu, C.T. Chen, D.J. Richmond, and M.J. Buehler: Bioinspired hierarchical composite design using machine learning: simulation, additive manufacturing, and experiment. Mater. Horiz. 5, 939 (2018).
L. Breiman: Random forests. Mach. Learn. 45, 5 (2001).
F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Pretenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825 (2011).
F. Chollet: Keras: the python deep learning library. Astrophysics Source Code Library (2018).
D.P. Kingma and J. Ba: Adam: A method for stochastic optimization, in International Conference on Learning Representation (2015).
D. Erhan, Y. Bengio, A. Courville, and P. Vincent: Visualizing higher-layer features of a deep network. Département d’Informatique Rech. Opérationnelle, Tech. Rep. 1341 No. 1341, 1 (2009).
Y. Nesterov: A method for solving the convex programming problem with convergence rate O(1/k 2). Dokl. Akad. Nauk SSSR 269, 543 (1983).
B. Zoph and Q. Le: Neural architecture search with reinforcement learning, in International Conference on Learning Representations (2017).
S. Ioffe and C. Szegedy: 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.
M.D. Zeiler and R. Fergus: in Visualizing and understanding convolutional Networks, in European Conference on Computer Vision 2014, edited by D. Fleet, T. Pajdla, B. Schiele, T. Tuytelaars (13th European Conf. on Comp. Vision 8689, Zurich, Switzerland, 2014), p. 818.
Acknowledgments
The authors acknowledge support from the Regents of the University of California, Berkeley and the Extreme Science and Engineering Discovery Environment (XSEDE) Bridges system at the Pittsburgh Supercomputing Center (PSC) through allocation TG-DMR180085, which is supported by National Science Foundation grant number ACI-1548562. The authors also acknowledge support from the Savio computational cluster resource provided by the Berkeley Research Computing program. Additionally, the authors acknowledge support by the Basic Science Research Program (2016R1C1B2011979) and Creative Materials Discovery Program (2016M3D1A1900038) through the National Research Foundation of Korea (NRF), as well as the support by the KAIST-funded Global Singularity Research Program for 2019 (N11190118).
Author information
Authors and Affiliations
Corresponding authors
Supplementary material
Supplementary material
The supplementary material for this article can be found at https://doi.org/10.1557/mrc.2019.49
Rights and permissions
About this article
Cite this article
Yang, C., Kim, Y., Ryu, S. et al. Using convolutional neural networks to predict composite properties beyond the elastic limit. MRS Communications 9, 609–617 (2019). https://doi.org/10.1557/mrc.2019.49
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1557/mrc.2019.49