|
Special Issue:
SPECIAL TOPIC — Machine learning in condensed matter physics
|
| SPECIAL TOPIC—Machine learning in condensed matter physics |
Prev
Next
|
|
|
Accurate Deep Potential model for the Al-Cu-Mg alloy in the full concentration space |
| Wanrun Jiang(姜万润)1,2, Yuzhi Zhang(张与之)3,4, Linfeng Zhang(张林峰)5,†, and Han Wang(王涵)6,‡ |
1 Songshan Lake Materials Laboratory, Dongguan 523808, China;
2 Institute of Physics, Chinese Academy of Sciences, Beijing 100190, China;
3 Beijing Institute of Big Data Research, Beijing 100871, China;
4 Yuanpei College of Peking University, Beijing 100871, China;
5 Program in Applied and Computational Mathematics, Princeton University, Princeton, NJ 08544, USA;
6 Laboratory of Computational Physics, Institute of Applied Physics and Computational Mathematics, Beijing 100088, China |
|
|
|
|
Abstract Combining first-principles accuracy and empirical-potential efficiency for the description of the potential energy surface (PES) is the philosopher's stone for unraveling the nature of matter via atomistic simulation. This has been particularly challenging for multi-component alloy systems due to the complex and non-linear nature of the associated PES. In this work, we develop an accurate PES model for the Al-Cu-Mg system by employing deep potential (DP), a neural network based representation of the PES, and DP generator (DP-GEN), a concurrent-learning scheme that generates a compact set of ab initio data for training. The resulting DP model gives predictions consistent with first-principles calculations for various binary and ternary systems on their fundamental energetic and mechanical properties, including formation energy, equilibrium volume, equation of state, interstitial energy, vacancy and surface formation energy, as well as elastic moduli. Extensive benchmark shows that the DP model is ready and will be useful for atomistic modeling of the Al-Cu-Mg system within the full range of concentration.
|
Received: 27 August 2020
Revised: 12 March 2021
Accepted manuscript online: 24 March 2021
|
|
PACS:
|
07.05.Mh
|
(Neural networks, fuzzy logic, artificial intelligence)
|
| |
34.20.Cf
|
(Interatomic potentials and forces)
|
| |
61.66.Dk
|
(Alloys )
|
| |
82.20.Wt
|
(Computational modeling; simulation)
|
|
| Fund: Project supported by the National Natural Science Foundation of China (Grant No. 11871110), the National Key Research and Development Program of China (Grant Nos. 2016YFB0201200 and 2016YFB0201203), and Beijing Academy of Artificial Intelligence (BAAI). |
Corresponding Authors:
Linfeng Zhang, Han Wang
E-mail: linfeng.zhang.zlf@gmail.com;wang_han@iapcm.ac.cn
|
Cite this article:
Wanrun Jiang(姜万润), Yuzhi Zhang(张与之), Linfeng Zhang(张林峰), and Han Wang(王涵) Accurate Deep Potential model for the Al-Cu-Mg alloy in the full concentration space 2021 Chin. Phys. B 30 050706
|
[1] Dursun T and Soutis C 2014 Mater. Des. 56 862
[2] Wilm A 1911 Metallurgie 8 225
[3] Warren A S 2004 Mater. Forum 28 24
[4] Wang S C and Starink M J 2005 Int. Mater. Rev. 50 193
[5] Andersen S J, Marioara C D, Friis J, Wenner S and Holmestad R 2018 Adv. Phys.: X 3 1479984
[6] Esin V A, Briez L, Sennour M, Köster A, Gratiot E and Crépin J 2021 J. Alloys Compd. 854 157164
[7] Ringer S P, Sofyan B T, Prasad K S and Quan G C 2008 Acta Mater. 56 2147
[8] Marceau R K W, Sha G, Ferragut R, Dupasquier A and Ringer S P 2010 Acta Mater. 58 4923
[9] Styles M J, Marceau R K W, Bastow T J, Brand H E A, Gibson M A and Hutchinson C R 2015 Acta Mater. 98 64
[10] Liu Z, Chen J H, Wang S B, Yuan D, Yin M J and Wu C L 2011 Acta Mater. 59 7396
[11] Zhang J, Huang Y N, Mao C and Peng P 2012 Solid State Commun. 152 2100
[12] Marceau R K W, Sha G, Lumley R N and Ringer S P 2010 Acta Mater. 58 1795
[13] Nagai Y, Murayama M, Tang Z, Nonaka T, Hono K and Hasegawa M 2001 Acta Mater. 49 913
[14] Parel T S, Wang S C and Starink M J 2010 Mater 2010 Mater. Des. 31 S2
[15] Lin Y C, Xia Y, Jiang Y and Li L 2012 Mater. Sci. Eng., A 556 796
[16] Song Y F, Ding X F, Xiao L R, Zhao X J, Cai Z Y, Guo L, Li Y W and Zheng Z Z 2017 J. Alloys Compd. 701 508
[17] Chen Y, Gao N, Sha G, Ringer S P and Starink M J 2016 Acta Mater. 109 202
[18] Singh C V and Warner D H 2010 Acta Mater. 58 5797
[19] Singh C V, Mateos A J and Warner D H 2011 Scr. Mater. 64 398
[20] Bourgeois L, Zhang Y, Zhang Z Z, Chen Y Q and Medhekar N V 2020 Nat. Commun. 11 1248
[21] Prakash A, Guénolé J, Wang J, Müller J, Spiecker E, Mills M J, Povstugar I, Choi P, Raabe D and Bitzek E 2015 Acta Mater. 92 33
[22] Car R and Parrinello M 1985 Phys. Rev. Lett. 55 2471
[23] Kohn W and Sham L J 1965 Phys. Rev. 140 A1133
[24] Bourgeois L, Dwyer C, Weyland M, Nie J F and Muddle B C 2011 Acta Mater. 59 7043
[25] Jones J E 1924 Proc. R. Soc. A 106 463
[26] Stillinger F H and Weber T A 1985 Phys. Rev. B 31 5262
[27] Daw M S and Baskes M I 1984 Phys. Rev. B 29 6443
[28] Baskes M 1992 Phys. Rev. B 46 2727
[29] Pascuet M I and Fernandez J R 2015 J. Nucl. Mater. 467 229
[30] Choudhary K, Liang T, Chernatynskiy A V, Lu Z, Goyal A, Phillpot S R and Sinnott S B 2015 J. Phys.: Condens. Matter 27 015003
[31] Mendelev M I and King A H 2013 Philos. Mag. 93 1268
[32] Asadi E, Zaeem M A, Nouranian S and Baskes M I 2015 Acta Mater. 86 169
[33] Etesami S A and Asadi E 2018 J. Phys. Chem. Solids 112 61
[34] Zhou X W, Johnson R A and Wadley H N G 2004 Phys. Rev. B 69 144113
[35] Sun D Y, Mendelev M I, Becker C A, Kudin K N, Haxhimali T, Asta M, Hoyt J J, Karma A and Srolovitz D J 2006 Phys. Rev. B 73 024116
[36] Wilson S R and Mendelev M I 2016 J. Chem. Phys. 144 144707
[37] Liu X Y, Liu C L and Borucki L 1999 Acta Mater. 47 3227
[38] Apostol F and Mishin Y 2011 Phys. Rev. B 83 054116
[39] Zhou X W, Ward D K and Foster M E 2016 J. Alloys Compd. 680 752
[40] Liu X Y, Ohotnicky P, Adams J, Rohrer C and Hyland R 1997 Surf. Sci. 373 357
[41] Liu X Y and Adams J B 1998 Acta Mater. 46 3467
[42] Mendelev M I, Asta M, Rahman M J and Hoyt J J 2009 Philos. Mag. 89 3269
[43] Jelinek B, Groh S, Horstemeyer M F, Houze J, Kim S G, Wagner G J, Moitra A and Baskes M I 2012 Phys. Rev. B 85 245102
[44] Zhang L F, Lin D Y, Wang H, Car R and E W N 2019 Phys. Rev. Mater. 3 023804
[45] Behler J and Parrinello M 2007 Phys. Rev. Lett. 98 146401
[46] Bartók A P, Payne M C, Kondor R and Csányi G 2010 Phys. Rev. Lett. 104 136403
[47] Schütt K, Kindermans P J, Felix H E S, Chmiela S, Tkatchenko A and Müller K R 2017 in Advances in Neural Information Processing Systems (NIPS) p. 992
[48] Han J Q, Zhang L F, Car R and E W N 2018 Commun. Comput. Phys. 23 629
[49] Zhang L F, Han J Q, Wang H, Car R and E W N 2018 Phys. Rev. Lett. 120 143001
[50] Zhang L F, Han J Q, Wang H, Saidi W A, Car R and E W N 2018 in Advances of the Neural Information Processing Systems (NIPS) p. 4436
[51] Barron A R 1993 IEEE Transactions on Information theory 39 930
[52] Han J Q, Zhang L F, Car R and E W N 2020 Sci. China Math. 63 2233
[53] Andrade M F C, Ko H Y, Zhang L, Car R and Selloni A 2020 Chem. Sci. 11 2335
[54] Dai F Z, Wen B, Sun Y, Xiang H and Zhou Y 2020 J. Mater. Sci. Technol. 43 168
[55] Zhang Y Z, Wang H D, Chen W J, Zeng J Z, Zhang L F, Wang H and E W N 2020 Comput. Phys. Commun. 253 107206
[56] Plimpton S 1995 J. Comput. Phys. 117 1
[57] Kresse G and Furthmüller J 1996 Phys. Rev. B 54 11169
[58] Kresse G and Furthmüller J 1996 Comput. Mater. Sci. 6 15
[59] Perdew J P, Burke K and Ernzerhof M 1996 Phys. Rev. Lett. 77 3865
[60] Perdew J P, Burke K and Ernzerhof M 1997 Phys. Rev. Lett. 78 1396
[61] Blochl P E 1994 Phys. Rev. B 50 17953
[62] Kresse G and Joubert D 1999 Phys. Rev. B 59 1758
[63] Monkhorst H J and Pack J D 1976 Phys. Rev. B 13 5188
[64] Methfessel M and Paxton A 1989 Phys. Rev. B 40 3616
[65] Wang H, Zhang L F, Han J Q and E W N 2018 Comput. Phys. Commun. 228 178
[66] Kingma D and Ba J 2015 in Proceedings of the International Conference on Learning Representations (ICLR)
[67] Abadi M, Agarwal A, Barham P, et al. 2015 arXiv:1603.04467 [cs.DC]
[68] Model and data can be download at http://dplibrary.deepmd.net/#/project_details?project_id=202010.002
[69] Ong S P, Richards W D, Jain A, Hautier G, Kocher M, Cholia S, Gunter D, Chevrier V L, Persson K A and Ceder G 2013 Comput. Mater. Sci. 68 314
[70] Zimmermann N E R, Horton M K, Jain A and Haranczyk M 2017 Front. Mater. 4 34 |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
