journal article·2021-06-03Open access

Mechanical behavior predictions of additively manufactured microstructures using functional Gaussian process surrogates

Robert Saunders, Celia Butler, John Michopoulos, Dimitris Lagoudas, Alaa Elwany, Amit Bagchi

npj Computational Materials· Volume 7· Issue 1

Abstract

Abstract Relational linkages connecting process, structure, and properties are some of the most sought after goals in additive manufacturing (AM). This is desired especially because the microstructural grain morphologies of AM components can be vastly different than their conventionally manufactured counterparts. Furthermore, data collection at the microscale is costly. Consequently, this work describes and demonstrates a methodology to link microstructure morphology to mechanical properties using functional Gaussian process surrogate models in a directed graphical network capable of achieving near real-time property predictions with single digit error magnitudes when predicting full stress–strain histories of a given microstructure. This methodology is presented and demonstrated using computationally generated microstructures and results from crystal plasticity simulations on those microstructures. The surrogate model uses grain-level microstructural descriptors rather than whole microstructure descriptors so that properties of new, arbitrary microstructures can be predicted. The developed network has the potential to scale to predict mechanical properties of grain structures that would be infeasible to simulate using finite element methods.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Additive Manufacturing Materials and Processes · Additive Manufacturing and 3D Printing Technologies · Machine Learning in Materials Science

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (68)

Show source-provided references
1. Panchal, J. H., Kalidindi, S. R. & McDowell, D. L. Key computational modeling issues in integrated computational materials engineering. Comput. Aided Des. 45, 4–25 (2013).10.1016/j.cad.2012.06.006 ↗
2. Lim, H. et al. Incorporating physically-based microstructures in materials modeling: bridging phase field and crystal plasticity frameworks. Model. Simul. Mater. Sci. Eng. 24, 045016 (2016).10.1088/0965-0393/24/4/045016 ↗
3. Diehl, M. et al. Identifying structure-property relationships through DREAM.3D representative volume elements and DAMASK crystal plasticity simulations: an integrated computational materials engineering approach. JOM 69, 848–855 (2017).10.1007/s11837-017-2303-0 ↗
4. Kalidindi, S. R. & De Graef, M. Materials data science: current status and future outlook. Annu. Rev. Mater. Res. 45, 171–193 (2015).10.1146/annurev-matsci-070214-020844 ↗
5. Agrawal, A. & Choudhary, A. Perspective: Materials informatics and big data: realization of the "fourth paradigm" of science in materials science. APL Mater. 4, 053208 (2016).10.1063/1.4946894 ↗
6. McDowell, D. L. & LeSar, R. A. The need for microstructure informatics in process-structure-property relations. MRS Bull. 41, 587–593 (2016).10.1557/mrs.2016.163 ↗
7. Kalidindi, S. R., Medford, A. J. & McDowell, D. L. Vision for data and informatics in the future materials innovation ecosystem. JOM 68, 2126–2137 (2016).10.1007/s11837-016-2036-5 ↗
8. Ramprasad, R., Batra, R., Pilania, G., Mannodi-Kanakkithodi, A. & Kim, C. Machine learning in materials informatics: recent applications and prospects. NPJ Comput. Mater. 3, 54 (2017).10.1038/s41524-017-0056-5 ↗
9. Dimiduk, D. M., Holm, E. A. & Niezgoda, S. R. Perspectives on the impact of machine learning, deep learning, and artificial intelligence on materials, processes, and structures engineering. Integr. Mater. Manuf. Innov. 7, 157–172 (2018).10.1007/s40192-018-0117-8 ↗
10. Lookman, T., Balachandran, P. V., Xue, D. & Yuan, R. Active learning in materials science with emphasis on adaptive sampling using uncertainties for targeted design. NPJ Comput. Mater. 5, 21 (2019).10.1038/s41524-019-0153-8 ↗
11. Brough, D. B., Wheeler, D., Warren, J. A. & Kalidindi, S. R. Microstructure-based knowledge systems for capturing process-structure evolution linkages. Curr. Opin. Solid State Mater. Sci. 21, 129–140 (2017).10.1016/j.cossms.2016.05.002 ↗
12. Paulson, N. H., Priddy, M. W., McDowell, D. L. & Kalidindi, S. R. Reduced-order structure-property linkages for polycrystalline microstructures based on 2-point statistics. Acta Mater. 129, 428–438 (2017).10.1016/j.actamat.2017.03.009 ↗
13. Yang, Z. et al. Deep learning approaches for mining structure-property linkages in high contrast composites from simulation datasets. Comput. Mater. Sci. 151, 278–287 (2018).10.1016/j.commatsci.2018.05.014 ↗
14. Khosravani, A., Cecen, A. & Kalidindi, S. R. Development of high throughput assays for establishing process-structure-property linkages in multiphase polycrystalline metals: application to dual-phase steels. Acta Mater. 123, 55–69 (2017).10.1016/j.actamat.2016.10.033 ↗
15. DebRoy, T. et al. Additive manufacturing of metallic components—process, structure and properties. Prog. Mater. Sci. 92, 112–224 (2018).10.1016/j.pmatsci.2017.10.001 ↗
16. Herzog, D., Seyda, V., Wycisk, E. & Emmelmann, C. Additive manufacturing of metals. Acta Mater. 117, 371–392 (2016).10.1016/j.actamat.2016.07.019 ↗
17. Francois, M. et al. Modeling of additive manufacturing processes for metals: challenges and opportunities. Curr. Opin. Solid State Mater. Sci. 21, 198–206 (2017).10.1016/j.cossms.2016.12.001 ↗
18. Gao, W. et al. The status, challenges, and future of additive manufacturing in engineering. Comput. Aided Des. 69, 65–89 (2015).10.1016/j.cad.2015.04.001 ↗
19. Wang, Y. M. et al. Additively manufactured hierarchical stainless steels with high strength and ductility. Nat. Mater. 17, 63–71 (2018).10.1038/nmat5021 ↗
20. Smith, J. et al. Linking process, structure, property, and performance for metal-based additive manufacturing: computational approaches with experimental support. Comput. Mech. 57, 583–610 (2016).10.1007/s00466-015-1240-4 ↗
21. Markl, M. & Körner, C. Multiscale modeling of powder bed-based additive manufacturing. Annu. Rev. Mater. Res. 46, 93–123 (2016).10.1146/annurev-matsci-070115-032158 ↗
22. Mukherjee, T. & DebRoy, T. A digital twin for rapid qualification of 3D printed metallic components. Appl. Mater. Today 14, 59–65 (2019).10.1016/j.apmt.2018.11.003 ↗
23. Yan, W. et al. An integrated process-structure-property modeling framework for additive manufacturing. Comput. Methods Appl. Mech. Eng. 339, 184–204 (2018).10.1016/j.cma.2018.05.004 ↗
24. Yan, W. et al. Data-driven multi-scale multi-physics models to derive process-structure-property relationships for additive manufacturing. Comput. Mech. 61, 521–541 (2018).10.1007/s00466-018-1539-z ↗
25. Roters, F. et al. Overview of constitutive laws, kinematics, homogenization and multiscale methods in crystal plasticity finite-element modeling: theory, experiments, applications. Acta Mater. 58, 1152–1211 (2010).10.1016/j.actamat.2009.10.058 ↗
26. Segurado, J., Lebensohn, R. A. & LLorca, J. Computational Homogenization of Polycrystals. In Advances in Applied Mechanics: Volume 51 (ed Hussein, M. I.) 1–114 (Elsevier, 2018).10.1016/bs.aams.2018.07.001 ↗
27. Jones, R. E., Templeton, J. A., Sanders, C. M. & Ostien, J. T. Machine learning models of plastic flow based on representation theory. Comput. Model. Eng. Sci. 117, 309–342 (2018).
28. Wang, K., Sun, W. & Du, Q. A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation. Comput. Mech. 64, 467–499 (2019).10.1007/s00466-019-01723-1 ↗
29. Wang, K. & Sun, W. Meta-modeling game for deriving theory-consistent, microstructure-based traction-separation laws via deep reinforcement learning. Comput. Methods Appl. Mech. Eng. 346, 216–241 (2019).10.1016/j.cma.2018.11.026 ↗
30. Jung, J., Yoon, J. I., Park, H. K., Kim, J. Y. & Kim, H. S. An efficient machine learning approach to establish structure-property linkages. Comput. Mater. Sci. 156, 17–25 (2019).10.1016/j.commatsci.2018.09.034 ↗
31. Jung, J., Yoon, J. I., Park, H. K., Kim, J. Y. & Kim, H. S. Bayesian approach in predicting mechanical properties of materials: Application to dual phase steels. Mater. Sci. Eng. A Struct. Mater. 743, 382–390 (2019).10.1016/j.msea.2018.11.106 ↗
32. Reimann, D. et al. Modeling macroscopic material behavior with machine learning algorithms trained by micromechanical simulations. Front. Mater. 6, 3513–3520 (2019).10.3389/fmats.2019.00181 ↗
33. Whelan, G. & McDowell, D. L. Machine learning-enabled uncertainty quantification for modeling structure-property linkages for fatigue critical engineering alloys using an ICME workflow. Integr. Mater. Manuf. Innov. 9, 376–393 (2020).10.1007/s40192-020-00192-2 ↗
34. Liu, Z. & Wu, C. Exploring the 3D architectures of deep material network in data-driven multiscale mechanics. J. Mech. Phys. Solids 127, 20–46 (2019).10.1016/j.jmps.2019.03.004 ↗
35. Frankel, A., Tachida, K. & Jones, R. Prediction of the evolution of the stress field of polycrystals undergoing elastic-plastic deformation with a hybrid neural network model. Mach. Learn. Sci. Technol. 1, 035005 (2020).10.1088/2632-2153/ab9299 ↗
36. Frankel, A., Jones, R., Alleman, C. & Templeton, J. Predicting the mechanical response of oligocrystals with deep learning. Comput. Mater. Sci. 169, 109099 (2019).10.1016/j.commatsci.2019.109099 ↗
37. Morris, J. S. Functional regression. Annu. Rev. Stat. Appl. 2, 321–359 (2015).10.1146/annurev-statistics-010814-020413 ↗
38. Ramsay, J. O. & Silverman, B. W. Functional Data Analysis. Springer Series in Statistics, 2nd edn (Springer New York, 2005).10.1007/b98888 ↗
39. Ferraty, F. & Vieu, P. Nonparametric Functional Data Analysis. Springer Series in Statistics (Springer New York, 2006).
40. Ling, N. & Vieu, P. Nonparametric modelling for functional data: selected survey and tracks for future. Statistics 52, 934–949 (2018).10.1080/02331888.2018.1487120 ↗
41. Morris, M. D. Gaussian surrogates for computer models with time-varying inputs and outputs. Technometrics 54, 42–50 (2012).10.1080/00401706.2012.648870 ↗
42. Tang, X., Hong, Z., Hu, Y. & Lian, H. Gaussian process models for non parametric functional regression with functional responses. Commun. Stat. Theory Methods 44, 3428–3445 (2015).10.1080/03610926.2013.847101 ↗
43. Poynor, V. & Munch, S. Combining functional data with hierarchical Gaussian process models. Environ. Ecol. Stat. 24, 175–199 (2017).10.1007/s10651-017-0366-2 ↗
44. Yang, J., Cox, D. D., Lee, J. S., Ren, P. & Choi, T. Efficient Bayesian hierarchical functional data analysis with basis function approximations using Gaussian-Wishart processes. Biometrics 73, 1082–1091 (2017).10.1111/biom.12705 ↗
45. Luo, L., Yao, Y., Gao, F. & Zhao, C. Mixed-effects Gaussian process modeling approach with application in injection molding processes. J. Process Control 62, 37–43 (2018).10.1016/j.jprocont.2017.12.003 ↗
46. Betancourt, J. et al. Gaussian process metamodeling of functional-input code for coastal flood hazard assessment. Reliab. Eng. Syst. Saf. 198, 106870 (2020).10.1016/j.ress.2020.106870 ↗
47. Li, J., Jin, R. & Yu, H. Z. Integration of physically-based and data-driven approaches for thermal field prediction in additive manufacturing. Mater. Des. 139, 473–485 (2018).10.1016/j.matdes.2017.11.028 ↗
48. Wang, B. & Xu, A. Gaussian process methods for nonparametric functional regression with mixed predictors. Comput. Stat. Data. Anal. 131, 80–90 (2019).10.1016/j.csda.2018.07.009 ↗
49. Conti, S. & O’Hagan, A. Bayesian emulation of complex multi-output and dynamic computer models. J. Stat. Plan. Inference 140, 640–651 (2010).10.1016/j.jspi.2009.08.006 ↗
50. Kennedy, M. Predicting the output from a complex computer code when fast approximations are available. Biometrika 87, 1–13 (2000).10.1093/biomet/87.1.1 ↗
51. Forrester, A. I., Sóbester, A. & Keane, A. J. Multi-fidelity optimization via surrogate modelling. Proc. R. Soc. Lond. A Math. Phys. Sci. 463, 3251–3269 (2007).
52. Le Gratiet, L. & Cannamela, C. Cokriging-based sequential design strategies using fast cross-validation techniques for multi-fidelity computer codes. Technometrics 57, 418–427 (2015).10.1080/00401706.2014.928233 ↗
53. Mangal, A. & Holm, E. A. Applied machine learning to predict stress hotspots I: face centered cubic materials. Int. J. Plast. 111, 122–134 (2018).10.1016/j.ijplas.2018.07.013 ↗
54. Bostanabad, R. et al. Computational microstructure characterization and reconstruction: review of the state-of-the-art techniques. Prog. Mater. Sci. 95, 1–41 (2018).10.1016/j.pmatsci.2018.01.005 ↗
55. Rodgers, T. M., Lim, H. & Brown, J. A. Three-dimensional additively manufactured microstructures and their mechanical properties. JOM 72, 75–82 (2020).10.1007/s11837-019-03808-x ↗
56. Saunders, R. N., Achuthan, A., Iliopoulos, A. P., Michopoulos, J. G. & Bagchi, A. Effects of the microstructural Grain Size and Aspect Ratio on the Mechanical Properties of Additively Manufactured Parts Via Computational Analysis (Defense Technical Information Center, 2020).
57. Michopoulos, J. G. et al. Towards computational synthesis of microstructural crystalline morphologies for additive manufacturing applications. In 37th Computers and Information in Engineering Conference, Vol. 1, V001T02A030–V001T02A030 (American Society of Mechanical Engineers, 2017).10.1115/DETC2017-68149 ↗
58. Birnbaum, A. J., Steuben, J. C., Barrick, E. J., Iliopoulos, A. P. & Michopoulos, J. G. Intrinsic strain aging, Σ3 boundaries, and origins of cellular substructure in additively manufactured 316L. Addit. Manuf. 29, 100784 (2019).
59. Achuthan, A., Iliopoulos, A. P., Michopoulos, J. G., Saunders, R. & Bagchi, A. Towards a constitutive model that encapsulates microstructural features induced by powder additive manufacturing. In 37th Computers and Information in Engineering Conference, Vol. 1, 1–11 (American Society of Mechanical Engineers, 2017).10.1115/DETC2017-67591 ↗
60. Qidwai, S. M. et al. Estimating the response of polycrystalline materials using sets of weighted statistical volume elements. Acta Mater. 60, 5284–5299 (2012).10.1016/j.actamat.2012.06.026 ↗
61. Knezevic, M., Al-Harbi, H. F. & Kalidindi, S. R. Crystal plasticity simulations using discrete Fourier transforms. Acta Mater. 57, 1777–1784 (2009).10.1016/j.actamat.2008.12.017 ↗
62. Roters, F. et al. DAMASK—The Düsseldorf Advanced Material Simulation Kit for modeling multi-physics crystal plasticity, thermal, and damage phenomena from the single crystal up to the component scale. Comput. Mater. Sci. 158, 420–478 (2019).10.1016/j.commatsci.2018.04.030 ↗
63. Taheri Andani, M., Karamooz-Ravari, M. R., Mirzaeifar, R. & Ni, J. Micromechanics modeling of metallic alloys 3D printed by selective laser melting. Mater. Des. 137, 204–213 (2018).10.1016/j.matdes.2017.10.026 ↗
64. Taheri Andani, M., Ghodrati, M., Karamooz-Ravari, M. R., Mirzaeifar, R. & Ni, J. Damage modeling of metallic alloys made by additive manufacturing. Mater. Sci. Eng. A Struct. Mater. 743, 656–664 (2019).10.1016/j.msea.2018.11.125 ↗
65. Titsias, M. Variational learning of inducing variables in sparse Gaussian processes. In Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics, Vol. 5 of Proceedings of Machine Learning Research (eds. van Dyk, D. & Welling, M) 567–574 (PMLR, 2009).
66. Hensman, J., Fusi, N. & Lawrence, N. D. Gaussian processes for big data. In Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence, 282–290 (2013).
67. Steuben, J., Michopoulos, J., Iliopoulos, A. & Turner, C. Inverse characterization of composite materials via surrogate modeling. Compos. Struct. 132, 694–708 (2015).10.1016/j.compstruct.2015.05.029 ↗
68. Rasmussen, C. E. & Williams, C. K. I. Regression. In Gaussian Processes for Machine Learning (The MIT Press, 2005).10.7551/mitpress/3206.001.0001 ↗