Research Papers: Design Automation

Microstructural Materials Design Via Deep Adversarial Learning Methodology

[+] Author and Article Information
Zijiang Yang

Department of Electrical Engineering
and Computer Science,
Northwestern University,
Evanston, IL 60208
e-mail: zijiangyang2016@u.northwestern.edu

Xiaolin Li

Theoretical and Applied Mechanics,
Northwestern University,
Evanston, IL 60208
e-mail: xiaolinli2018@u.northwestern.edu

L. Catherine Brinson

Department of Mechanical Engineering
and Materials Science,
Duke University,
Durham, NC 27708
e-mail: cate.brinson@duke.edu

Alok N. Choudhary

Department of Electrical Engineering and
Computer Science,
Northwestern University,
Evanston, IL 60208
e-mail: a-choudhary@northwestern.edu

Wei Chen

Department of Mechanical Engineering,
Northwestern University,
Evanston, IL 60208
e-mail: weichen@northwestern.edu

Ankit Agrawal

Department of Electrical Engineering and
Computer Science,
Northwestern University,
Evanston, IL 60208
e-mail: ankitag@eecs.northwestern.edu

1Z. Yang and X. Li contributed equally to this work.

2Corresponding authors.

Contributed by the Design Automation Committee of ASME for publication in the JOURNAL OF MECHANICAL DESIGN. Manuscript received March 24, 2018; final manuscript received July 25, 2018; published online October 1, 2018. Special Editor: Carolyn Seepersad.

J. Mech. Des 140(11), 111416 (Oct 01, 2018) (10 pages) Paper No: MD-18-1252; doi: 10.1115/1.4041371 History: Received March 24, 2018; Revised July 25, 2018

Identifying the key microstructure representations is crucial for computational materials design (CMD). However, existing microstructure characterization and reconstruction (MCR) techniques have limitations to be applied for microstructural materials design. Some MCR approaches are not applicable for microstructural materials design because no parameters are available to serve as design variables, while others introduce significant information loss in either microstructure representation and/or dimensionality reduction. In this work, we present a deep adversarial learning methodology that overcomes the limitations of existing MCR techniques. In the proposed methodology, generative adversarial networks (GAN) are trained to learn the mapping between latent variables and microstructures. Thereafter, the low-dimensional latent variables serve as design variables, and a Bayesian optimization framework is applied to obtain microstructures with desired material property. Due to the special design of the network architecture, the proposed methodology is able to identify the latent (design) variables with desired dimensionality, as well as capturing complex material microstructural characteristics. The validity of the proposed methodology is tested numerically on a synthetic microstructure dataset and its effectiveness for microstructural materials design is evaluated through a case study of optimizing optical performance for energy absorption. Additional features, such as scalability and transferability, are also demonstrated in this work. In essence, the proposed methodology provides an end-to-end solution for microstructural materials design, in which GAN reduces information loss and preserves more microstructural characteristics, and the GP-Hedge optimization improves the efficiency of design exploration.

Copyright © 2018 by ASME
Your Session has timed out. Please sign back in to continue.


Thornton, K. , Nola, S. , Garcia, R. E. , Asta, M. , and Olson, G. , 2009, “ Computational Materials Science and Engineering Education: A Survey of Trends and Needs,” JOM, 61(10), p. 12. [CrossRef]
Olson, G. B. , 1997, “ Computational Design of Hierarchically Structured Materials,” Science, 277(5330), pp. 1237–1242. [CrossRef]
Saito, T. , 2013, Computational Materials Design, Vol. 34, Springer Science & Business Media, Berlin, Germany.
Kuehmann, C. , and Olson, G. , 2009, “ Computational Materials Design and Engineering,” Mater. Sci. Technol., 25(4), pp. 472–478. [CrossRef]
Vickers, J. , 2015, “ Materials Genome Initiative,” Energy Efficiency & Renewable Energy, Washington, DC.
Agrawal, A. , and Choudhary, A. , 2016, “ Perspective: Materials Informatics and Big Data: Realization of the “Fourth Paradigm” of Science in Materials Science,” APL Mater., 4(5), p. 053208. [CrossRef]
Zhao, H. , Li, X. , Zhang, Y. , Schadler, L. S. , Chen, W. , and Brinson, L. C. , 2016, “ Perspective: Nanomine: A Material Genome Approach for Polymer Nanocomposites Analysis and Design,” APL Mater., 4(5), p. 053204. [CrossRef]
Wang, Y. , Zhang, Y. , Zhao, H. , Li, X. , Huang, Y. , Schadler, L. S. , Chen, W. , and Brinson, L. C. , 2018, “ Identifying Interphase Properties in Polymer Nanocomposites Using Adaptive Optimization,” Compos. Sci. Technol., 162(7), pp. 146–155.
Paul, D. , and Robeson, L. M. , 2008, “ Polymer Nanotechnology: Nanocomposites,” Polymers, 49(15), pp. 3187–3204. [CrossRef]
Natarajan, B. , Li, Y. , Deng, H. , Brinson, L. C. , and Schadler, L. S. , 2013, “ Effect of Interfacial Energetics on Dispersion and Glass Transition Temperature in Polymer Nanocomposites,” Macromolecules, 46(7), pp. 2833–2841. [CrossRef]
Hassinger, I. , Li, X. , Zhao, H. , Xu, H. , Huang, Y. , Prasad, A. , Schadler, L. , Chen, W. , and Brinson, L. C. , 2016, “ Toward the Development of a Quantitative Tool for Predicting Dispersion of Nanocomposites Under Non-Equilibrium Processing Conditions,” J. Mater. Sci., 51(9), pp. 4238–4249. [CrossRef]
Brough, D. B. , Wheeler, D. , Warren, J. A. , and Kalidindi, S. R. , 2017, “ Microstructure-Based Knowledge Systems for Capturing Process-Structure Evolution Linkages,” Curr. Opin. Solid State Mater. Sci., 21(3), pp. 129–140. [CrossRef]
Liu, R. , Yabansu, Y. C. , Yang, Z. , Choudhary, A. N. , Kalidindi, S. R. , and Agrawal, A. , 2017, “ Context Aware Machine Learning Approaches for Modeling Elastic Localization in Three-Dimensional Composite Microstructures,” Integr. Mater. Manuf. Innov., 6, p. 160.
Yang, Z. , Yabansu, Y. C. , Al-Bahrani, R. , Liao, W-K. , Choudhary, A. N. , Kalidindi, S. R. , and Agrawal, A. , 2018, “ Deep Learning Approaches for Mining Structure-Property Linkages in High Contrast Composites From Simulation Datasets,” Comput. Mater. Sci., 151, pp. 278–287. [CrossRef]
Yu, S. , Zhang, Y. , Wang, C. , Lee, W-K. , Dong, B. , Odom, T. W. , Sun, C. , and Chen, W. , 2017, “ Characterization and Design of Functional Quasi-Random Nanostructured Materials Using Spectral Density Function,” ASME J. Mech. Des., 139(7), p. 071401. [CrossRef]
Fullwood, D. T. , Niezgoda, S. R. , Adams, B. L. , and Kalidindi, S. R. , 2010, “ Microstructure Sensitive Design for Performance Optimization,” Prog. Mater. Sci., 55(6), pp. 477–562. [CrossRef]
Bostanabad, R. , Zhang, Y. , Li, X. , Kearney, T. , Brinson, L. C. , Apley, D. W. , Liu, W. K. , and Chen, W. , “ Computational Microstructure Characterization and Reconstruction: Review of the State-of-the-Art Techniques,” Prog. Mater. Sci., 95, pp. 1–41.
Jiao, Y. , Stillinger, F. , and Torquato, S. , 2007, “ Modeling Heterogeneous Materials Via Two-Point Correlation Functions: Basic Principles,” Phys. Rev. E, 76(3), p. 031110. [CrossRef]
Xu, H. , Dikin, D. , Burkhart, C. , and Chen, W. , 2014, “ Descriptor-Based Methodology for Statistical Characterization and 3d Reconstruction of Microstructural Materials,” Comput. Mater. Sci., 85, pp. 206–216. [CrossRef]
Jiang, Z. , Chen, W. , and Burkhart, C. , 2013, “ Efficient 3d Porous Microstructure Reconstruction Via Gaussian Random Field and Hybrid Optimization,” J. Microsc., 252(2), pp. 135–148. [CrossRef] [PubMed]
Bostanabad, R. , Bui, A. T. , Xie, W. , Apley, D. W. , and Chen, W. , 2016, “ Stochastic Microstructure Characterization and Reconstruction Via Supervised Learning,” Acta Mater., 103, pp. 89–102. [CrossRef]
Cang, R. , Xu, Y. , Chen, S. , Liu, Y. , Jiao, Y. , and Ren, M. Y. , 2017, “ Microstructure Representation and Reconstruction of Heterogeneous Materials Via Deep Belief Network for Computational Material Design,” ASME J. Mech. Des., 139(7), p. 071404. [CrossRef]
Li, X. , Zhang, Y. , Zhao, H. , Burkhart, C. , Brinson, L. C. , and Chen, W. , 2018, “ A Transfer Learning Approach for Microstructure Reconstruction and Structure-Property Predictions,” preprint arXiv: 02784. https://arxiv.org/abs/1805.02784
Lubbers, N. , Lookman, T. , and Barros, K. , 2017, “ Inferring Low-Dimensional Microstructure Representations Using Convolutional Neural Networks,” Phys. Rev. E, 96(5), p. 052111. [CrossRef] [PubMed]
Paulson, N. H. , Priddy, M. W. , McDowell, D. L. , and Kalidindi, S. R. , 2017, “ Reduced-Order Structure-Property Linkages for Polycrystalline Microstructures Based on 2-Point Statistics,” Acta Mater., 129, pp. 428–438. [CrossRef]
Xu, H. , Liu, R. , Choudhary, A. , and Chen, W. , 2015, “ A Machine Learning-Based Design Representation Method for Designing Heterogeneous Microstructures,” ASME J. Mech. Des., 137(5), p. 051403. [CrossRef]
Kingma, D. P. , and Welling, M. , 2014, “ Auto-Encoding Variational Bayes,” preprint arXiv: 1312.6114. https://arxiv.org/abs/1312.6114
Goodfellow, I. , Pouget-Abadie, J. , Mirza, M. , Xu, B. , Warde-Farley, D. , Ozair, S. , Courville, A. , and Bengio, Y. , 2014, “ Generative Adversarial Nets,” Advances in Neural Information Processing Systems, Neural Information Processing Systems, Montreal, Canada, pp. 2672–2680.
Makhzani, A. , Shlens, J. , Jaitly, N. , Goodfellow, I. , and Frey, B. , 2016, “ Adversarial Autoencoders,” preprint arXiv:1511.05644. https://arxiv.org/abs/1511.05644
Dumoulin, V. , Belghazi, I. , Poole, B. , Lamb, A. , Arjovsky, M. , Mastropietro, O. , and Courville, A. , 2017, “ Adversarially Learned Inference,” preprint arXiv:1606.00704. https://arxiv.org/abs/1606.00704
Cang, R. , Li, H. , Yao, H. , Jiao, Y. , and Ren, Y. , 2018, “ Improving Direct Physical Properties Prediction of Heterogeneous Materials From Imaging Data Via Convolutional Neural Network and a Morphology-Aware Generative Model,” preprint arxiv:1712.03811. https://arxiv.org/abs/1712.03811
Guo, T. , Lohan, D. J. , Cang, R. , Ren, M. Y. , and Allison, J. T. , 2018, “ An Indirect Design Representation for Topology Optimization Using Variational Autoencoder and Style Transfer,” AIAA Paper No. AIAA 2018-0804.
Mosser, L. , Dubrule, O. , and Blunt, M. J. , 2017, “ Reconstruction of Three-Dimensional Porous Media Using Generative Adversarial Neural Networks,” Phys. Rev. E, 96(4), p. 043309. [CrossRef] [PubMed]
Mosser, L. , Dubrule, O. , and Blunt, M. J. , 2017, “ Stochastic Reconstruction of an Oolitic Limestone by Generative Adversarial Networks,” preprint arXiv:1712.02854. https://arxiv.org/abs/1712.02854
Osborne, M. J. , and Rubinstein, A. , 1994, A Course in Game Theory, MIT Press, Cambridge, MA.
Radford, A. , Metz, L. , and Chintala, S. , 2016, “ Unsupervised Representation Learning With Deep Convolutional Generative Adversarial Networks,” preprint arXiv:1511.06434. https://arxiv.org/abs/1511.06434
Ioffe, S. , and Szegedy, C. , 2015, “ Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” International Conference on Machine Learning, Lille, France, July 6–11, pp. 448–456.
Nair, V. , and Hinton, G. E. , 2010, “ Rectified Linear Units Improve Restricted Boltzmann Machines,” 27th International Conference on Machine Learning (ICML-10), Haifa, Israel, June 21–24, pp. 807–814.
Maas, A. L. , Hannun, A. Y. , and Ng, A. Y. , 2013, “ Rectifier Nonlinearities Improve Neural Network Acoustic Models,” 30th International Conference on Machine Learning (ICML), Atlanta, Georgia, June 16–21. https://ai.stanford.edu/~amaas/papers/relu_hybrid_icml2013_final.pdf
Salimans, T. , Goodfellow, I. , Zaremba, W. , Cheung, V. , Radford, A. , and Chen, X. , 2016, “ Improved Techniques for Training Gans,” 30th Conference on Neural Information Processing Systems (NIPS), Barcelona, Spain, Dec. 5–8, pp. 2234–2242.
Gatys, L. , Ecker, A. S. , and Bethge, M. , 2015, “ Texture Synthesis Using Convolutional Neural Networks,” 28th International Conference on Neural Information Processing Systems, Montreal, QC, Canada, Dec. 7–12, pp. 262–270.
Simonyan, K. , and Zisserman, A. , 2015, “ Very Deep Convolutional Networks for Large-Scale Image Recognition,” preprint arXiv:1409.1556.
Zhao, J. , Mathieu, M. , and LeCun, Y. , 2017, “ Energy-Based Generative Adversarial Network,” preprint arXiv:1609.03126.
Kingma, D. P. , and Ba, J. , 2017, “ Adam: A Method for Stochastic Optimization,” preprint arXiv:1412.6980.
Lu, B. , and Torquato, S. , 1992, “ Lineal-Path Function for Random Heterogeneous Materials,” Phys. Rev. A, 45(2), p. 922. [CrossRef] [PubMed]
McKay, M. D. , Beckman, R. J. , and Conover, W. J. , 2000, “ A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output From a Computer Code,” Technometrics, 42(1), pp. 55–61. [CrossRef]
Rasmussen, C. E. , 2004, “ Gaussian Processes in Machine Learning,” Advanced Lectures on Machine Learning, Springer, Berlin, pp. 63–71.
Hoffman, M. D. , Brochu, E. , and de Freitas, N. , 2011, “ Portfolio Allocation for Bayesian Optimization,” Twenty-Seventh Conference on Uncertainty in Artificial Intelligence, Barcelona, Spain, July 14–17, pp. 327–336.
Jones, D. R. , Schonlau, M. , and Welch, W. J. , 1998, “ Efficient Global Optimization of Expensive Black-Box Functions,” J. Global Optim., 13(4), pp. 455–492. [CrossRef]
Kushner, H. J. , 1964, “ A New Method of Locating the Maximum Point of an Arbitrary Multipeak Curve in the Presence of Noise,” J. Basic Eng., 86(1), pp. 97–106. [CrossRef]
Auer, P. , 2002, “ Using Confidence Bounds for Exploitation-Exploration Trade-Offs,” J. Mach. Learn. Res., 3, pp. 397–422.
Chen, X. , Duan, Y. , Houthooft, R. , Schulman, J. , Sutskever, I. , and Abbeel, P. , 2016, “ Infogan: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets,” Advances in Neural Information Processing Systems, Barcelona, Spain, pp. 2172–2180.
Yosinski, J. , Clune, J. , Bengio, Y. , and Lipson, H. , 2014, “ How Transferable Are Features in Deep Neural Networks?,” 27th International Conference on Neural Information Processing Systems, Montreal, QC, Canada, Dec. 8–13, pp. 3320–3328.
Lee, W.-K. , Yu, S. , Engel, C. J. , Reese, T. , Rhee, D. , Chen, W. , and Odom, T. W. , 2017, “ Concurrent Design of Quasi-Random Photonic Nanostructures,” Proc. Natl. Acad. Sci., 114(33), pp. 8734–8739. [CrossRef]
He, K. , Zhang, X. , Ren, S. , and Sun, J. , 2016, “ Deep Residual Learning for Image Recognition,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, June 27–30, pp. 770–778.
Mnih, V. , Heess, N. , Graves, A. , et al. .2014, “ Recurrent Models of Visual Attention,” 27th International Conference on Neural Information Processing Systems, Montreal, QC, Canada, Dec. 8–13, pp. 2204–2212.


Grahic Jump Location
Fig. 3

The composition of loss function and information flow in the proposed architecture

Grahic Jump Location
Fig. 2

The architecture of the proposed GAN

Grahic Jump Location
Fig. 1

The flowchart of the proposed design methodology

Grahic Jump Location
Fig. 4

Examples of original (training) microstructures and microstructures produced by the generator

Grahic Jump Location
Fig. 5

Comparison of correlation functions of original microstructures and microstructures generated by the proposed generator: (a) two-point correlation function and (b) lineal-path correlation function

Grahic Jump Location
Fig. 6

The integration of Gaussian process metamodeling and GP-Hedge Bayesian optimization

Grahic Jump Location
Fig. 8

The comparison of the optical absorption property between (1) 30 randomly generated microstructures, (2) 30 microstructures generated by the trained generator, and (3) optimal design

Grahic Jump Location
Fig. 9

An illustration of microstructures of different sizes generated by the scalable generator: (a) 64 × 64, (b) 96 × 96, (c) 128 × 128, (d) 192 × 192, (e) 256 × 356, and (f) 512 × 512

Grahic Jump Location
Fig. 10

The comparison of the MAE for training from scratch and transfer learning. Outliers, higher error and variance are observed from the results of “training from scratch” control group.

Grahic Jump Location
Fig. 7

The microstructure optimization history and microstructure designs indicated at selected iterations



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In