journal article·2020-06

Accelerating the Discovery of New DP Steel Using Machine Learning-Based Multiscale Materials Simulations

Abdallah A. Chehade, Tarek M. Belgasam, Georges Ayoub, Hussein M. Zbib

Publisher page

Abstract

In recent years, the use of dual-phase (DP) steels by the automotive industry has been growing rapidly, motivated by government policies prompting the production of fuel-efficient vehicles. While it is of high interest for the transportation industry to design and discover different grades of DP steels exhibiting desirable mechanical properties, this requires exploring a large number of DP steel microstructure combinations. Expensive trial-and-error-based experimentations and multiscale materials simulations are two conventional approaches that have been widely adopted in the field of materials design and discovery. Yet, it is challenging to use such approaches for fast materials design and discovery when considering the computational and cost limitations, as it is computationally infeasible and intractable to use multiscale materials models to characterize the mechanical properties of millions of different microstructures. To address this major limitation in material design, a Gaussian process is developed to accelerate the discovery of the mechanical properties of different DP steels by evolving the microstructure parameters using a limited number of numerical simulations (using a multiscale materials model). A Gaussian process is a machine learning technique that is trained to find nontrivial correlations between a set of inputs (microstructure properties) to predict a desired output (mechanical property). The proposed Gaussian process not only accelerates the prediction of the desired mechanical properties of millions of multiscale materials simulations but also offers uncertainty quantification around its predictions. These merits make the Gaussian process a very reliable, robust, and practical solution for material design exploration. The proposed framework combining multiscale simulations and the Gaussian process is used to discover the microstructural design of DP steel with maximum tensile toughness. The results showed the effectiveness and robustness of the proposed method in comparison to benchmark methods.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Mineral Processing and Grinding · Machine Learning in Materials Science · Metallurgy and Material Forming

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

References (46)

Show source-provided references
1. 1. T. Belgasam and H. Zbib: J. Eng. Mater. Technol., 2018, vol. 140, p. 031006.10.1115/1.4039292 ↗
2. T.M. Belgasam and H.M. Zbib (2018) Metall. Mater. Trans. A, vol. 49, pp. 1–22.10.1007/s11661-018-4563-x ↗
3. 3. A.-P. Pierman, O. Bouaziz, T. Pardoen, P.J. Jacques, and L. Brassart: Acta Mater., 2014, vol. 73, pp. 298–311.10.1016/j.actamat.2014.04.015 ↗
4. 4. R.G. Davies: Metall. Trans. A, 1978, vol. 9, pp. 671–9.10.1007/BF02659924 ↗
5. 5. N.J. Kim and G. Thomas: Metall. Trans. A, 1981, vol. 12, pp. 483–9.10.1007/BF02648546 ↗
6. A.R. Marder: Metall. Trans. A 1982, vol. 13A, pp. 85–92.10.1007/BF02642418 ↗
7. 7. H.-C. Chen and G.-H. Cheng: J. Mater. Sci., 1989, vol. 24, pp. 1991–4.10.1007/BF02385411 ↗
8. 8. Y. Tomita: J. Mater. Sci., 1990, vol. 25, pp. 5179–84.10.1007/BF00580148 ↗
9. Z.H. Cong, N. Jia, X. Sun, Y. Ren, J. Almer, and Y.D. Wang: Metall. Mater. Trans. A, 2009, vol. 40, pp. 1383–7.10.1007/s11661-009-9824-2 ↗
10. 10. X. Sun, K.S. Choi, W.N. Liu, and M.A. Khaleel: Int. J. Plast., 2009, vol. 25, pp. 1888–909.10.1016/j.ijplas.2008.12.012 ↗
11. 11. P.J. Jacques, Q. Furnemont, S. Godet, T. Pardoen, K.T. Conlon, and F. Delannay: Philos. Mag., 2006, vol. 86, pp. 2371–92.10.1080/14786430500529359 ↗
12. 12. W. Woo, V.T. Em, E.-Y. Kim, S.H. Han, Y.S. Han, and S.-H. Choi: Acta Mater., 2012, vol. 60, pp. 6972–81.10.1016/j.actamat.2012.08.054 ↗
13. S Kuang, Yl Kang, H Yu, RD Liu (2009) Int. J. Miner. Metall. Mater. 16:393–98.10.1016/S1674-4799(09)60070-4 ↗
14. 14. S.K. Paul and M. Mukherjee: Comput. Mater. Sci., 2014, vol. 84, pp. 1–12.10.1016/j.commatsci.2013.11.039 ↗
15. 15. S. Berbenni, V. Favier, X. Lemoine, and M. Berveiller: Mater. Sci. Eng. A, 2004, vol. 372, pp. 128–36.10.1016/j.msea.2003.11.010 ↗
16. M. Mazinani and W.J. Poole (2007) Metall. Mater. Trans. A 38:328–39.10.1007/s11661-006-9023-3 ↗
17. 17. M. Delincé, Y. Bréchet, J.D. Embury, M.G.D. Geers, P.J. Jacques, and T. Pardoen: Acta Mater., 2007, vol. 55, pp. 2337–50.10.1016/j.actamat.2006.11.029 ↗
18. 18. L. Brassart, I. Doghri, and L. Delannay: Int. J. Mater. Form., 2009, vol. 2, pp. 447–50.10.1007/s12289-009-0526-5 ↗
19. K.S. Choi, W.N. Liu, X. Sun, and M.A. Khaleel (2009) Metall. Mater. Trans. A Phys. Metall. Mater. Sci. 40:796–809.10.1007/s11661-009-9792-6 ↗
20. 20. V. Uthaisangsuk, U. Prahl, and W. Bleck: Eng. Fract. Mech., 2011, vol. 78, pp. 469–86.10.1016/j.engfracmech.2010.08.017 ↗
21. 21. J. Kadkhodapour, A. Butz, S. Ziaei-Rad, and S. Schmauder: Int. J. Plast., 2011, vol. 27, pp. 1103–25.10.1016/j.ijplas.2010.12.001 ↗
22. 22. S.K. Paul and A. Kumar: Comput. Mater. Sci., 2012, vol. 63, pp. 66–74.10.1016/j.commatsci.2012.05.061 ↗
23. 23. E.-Y. Kim, H.S. Yang, S.H. Han, J.H. Kwak, and S.-H. Choi: Met. Mater. Int., 2012, vol. 18, pp. 573–82.10.1007/s12540-012-4030-y ↗
24. 24. M. Amirmaleki, J. Samei, D.E. Green, I. van Riemsdijk, and L. Stewart: Mech. Mater., 2016, vol. 101, pp. 27–39.10.1016/j.mechmat.2016.07.011 ↗
25. T. Belgasam, H. Zbib (2013) Comput. Mater. Sci. 21:26.
26. 26. W. Wang, M. Li, C. He, X. Wei, D. Wang, and H. Du: Mater. Des., 2013, vol. 47, pp. 510–21.10.1016/j.matdes.2012.12.068 ↗
27. R. Alturk, S. Mates, Z. Xu, and F. Abu-farha: in TMS 2017 146th Annual Meeting & Exhibition Supplemental Proceedings, 2017, pp. 243–54.10.1007/978-3-319-51493-2_24 ↗
28. 28. S.K. Paul: Mater. Des., 2013, vol. 44, pp. 397–406.10.1016/j.matdes.2012.08.023 ↗
29. 29. E. Cadoni, N.K. Singh, D. Forni, M.K. Singha, and N.K. Gupta: Eur. Phys. J. Spec. Top., 2016, vol. 225, pp. 409–21.10.1140/epjst/e2016-02638-3 ↗
30. 30. C.C. Tasan, M. Diehl, D. Yan, M. Bechtold, F. Roters, L. Schemmann, C. Zheng, N. Peranio, D. Ponge, M. Koyama, K. Tsuzaki, and D. Raabe: Annu. Rev. Mater. Res., 2014, vol. 45, pp. 391–431.10.1146/annurev-matsci-070214-021103 ↗
31. 31. T. Belgasam and H. Zbib: Metall. Mater. Trans. A, 2017, vol. 48, pp. 6153-6177. .10.1007/s11661-017-4351-z ↗
32. 32. V. Tarigopula, O.S. Hopperstad, M. Langseth, A.H. Clausen, and F. Hild: Int. J. Solids Struct., 2008, vol. 45, pp. 601–19.10.1016/j.ijsolstr.2007.08.021 ↗
33. T. Belgasam: in 15th International LS-DYNA® Users Conference, 2018, pp. 1–8.
34. C.E. Rasmussen: Gaussian Processes in Machine Learning, Springer, Berlin, Heidelberg, 2004, pp. 63–71. https://doi.org/10.1007/978-3-540-28650-9_410.1007/978-3-540-28650-9_4 ↗
35. T. Choi, T. Choi, and T. Choi: Gaussian Process Regression Analysis for Functional Data, Chapman and Hall/CRC, 2011.
36. D. Alòs, Elisa, 1 2; and Mazet, Olivier; Nualart: Ann. Probab., 2001, vol. 29, pp. 766–801.10.1214/aop/1008956692 ↗
37. T. V. Nguyen and E. V. Bonilla: in Proceedings of the Thirtieth Conference Conference on Uncertainty in Artificial Intelligence, AUAI Press, Quebec City, 2014, pp. 643–52.
38. 38. M.A. Álvarez and N.D. Lawrence: J. Mach. Learn. Res., 2011, vol. 12, pp. 1459–500.
39. 39. N. Lawrence: J. Mach. Learn. Res., 2005, vol. 6, pp. 1783–816.
40. M. Alvarez and N.D. Lawrence: Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics, vol. 5, 2009, pp. 9–16. http://proceedings.mlr.press/v5/alvarez09a.html.
41. M.A. Álvarez, L. Rosasco, and N.D. Lawrence: Found. Trends® Mach. Learn., 2012, vol. 4, pp. 195–266.10.1561/2200000036 ↗
42. 42. A. Ho, J. Citrin, F. Auriemma, C. Bourdelle, F.J. Casson, H.-T. Kim, P. Manas, G. Szepesi, H. Weisen, and J. Contributors: Nucl. Fusion, 2019, vol. 59, p. 056007.10.1088/1741-4326/ab065a ↗
43. 43. S. Shirota and A.E. Gelfand: Ann. Appl. Stat., 2017, vol. 11, pp. 481–503.10.1214/16-AOAS960 ↗
44. 44. B. Wang and Z. Mao: Appl. Soft Comput., 2019, vol. 76, pp. 505–16.10.1016/j.asoc.2018.12.029 ↗
45. 45. H. Topa, Á. Jónás, R. Kofler, C. Kosiol, and A. Honkela: Bioinformatics, 2015, vol. 31, pp. 1762–70.10.1093/bioinformatics/btv014 ↗
46. J. Dykeman, D. Hoydick, T. Link, and H. Mitsuji: SAE Tech. Pap., https://doi.org/10.4271/2009-01-0794.10.4271/2009-01-0794 ↗