A Neural Network Approach to Predict Gibbs Free Energy of Ternary Solid Solutions

Journal of Phase Equilibria and Diffusion - Tập 43 Số 6 - Trang 916-930 - 2022
Laiu, Paul1, Yang, Ying2, Lupo Pasini, Massimiliano3, Choi, Jong Youl1, Shin, Dongwon2
1Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, USA
2Materials Science and Technology Division, Oak Ridge National Laboratory, Oak Ridge, USA
3Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, USA

Tóm tắt

We present a data-centric deep learning (DL) approach using neural networks (NNs) to predict the thermodynamics of ternary solid solutions. We explore how NNs can be trained with a dataset of Gibbs free energies computed from a CALPHAD database to predict ternary systems as a function of composition and temperature. We have chosen the energetics of the FCC solid solution phase in 226 binaries consisting of 23 elements at 11 different temperatures to demonstrate the feasibility. The number of binary data points included in the present study is 102,000. We select six ternaries to augment the binary dataset to investigate their influence on the NN prediction accuracy. We examine the sensitivity of data sampling on the prediction accuracy of NNs over selected ternary systems. It is anticipated that the current DL workflow can be further elevated by integrating advanced descriptors beyond the elemental composition and more curated training datasets to improve prediction accuracy and applicability.

Tài liệu tham khảo

C. T. Sims, in Superalloys 1984 (Fifth International Symposium) (TMS, 1984), pp. 399–419. citation_title=CALPHAD (Calculation of Phase Diagrams): A Comprehensive Guide; citation_publication_date=1998; citation_id=CR2; citation_author=N Saunders; citation_author=AP Miodownik; citation_publisher=Pergamon citation_journal_title=Prog. Mater. Sci.; citation_author=YA Chang, S Chen, F Zhang, X Yan, F Xie, R Schmid-Fetzer, WA Oates; citation_volume=49; citation_publication_date=2004; citation_pages=313; citation_doi=10.1016/S0079-6425(03)00025-2; citation_id=CR3 C. Zhang and Y. Yang, MRS Bull. 2022, 47, p 1–10. citation_journal_title=Nat. Commun.; citation_title=Physical Descriptor for the Gibbs Energy of Inorganic Crystalline Solids and Temperature-Dependent Materials Chemistry; citation_author=CJ Bartel, SL Millican, AM Deml, JR Rumptz, W Tumas, AW Weimer, AM Holder; citation_volume=9; citation_issue=1; citation_publication_date=2018; citation_pages=1-10; citation_doi=10.1038/s41467-018-06682-4; citation_id=CR5 citation_journal_title=J. Phys. Chem. A; citation_author=J Yoon, E Choi, K Min; citation_volume=125; citation_publication_date=2021; citation_pages=10103; citation_doi=10.1021/acs.jpca.1c05292; citation_id=CR6 citation_journal_title=ACS Omega; citation_author=Y Mao, H Yang, Y Sheng, J Wang, R Ouyang, C Ye, J Yang, W Zhang; citation_volume=6; citation_publication_date=2021; citation_pages=14533; citation_doi=10.1021/acsomega.1c01517; citation_id=CR7 citation_journal_title=Integr. Mater. Manuf. Innov.; citation_author=SK Kauwe, J Graser, A Vazquez, TD Sparks; citation_volume=7; citation_publication_date=2018; citation_pages=43; citation_doi=10.1007/s40192-018-0108-9; citation_id=CR8 citation_journal_title=NPJ Comput. Mater.; citation_author=CJ Bartel, A Trewartha, Q Wang, A Dunn, A Jain, G Ceder; citation_volume=6; citation_publication_date=2020; citation_pages=1; citation_doi=10.1038/s41524-020-00362-y; citation_id=CR9 citation_journal_title=NPJ Comput. Mater.; citation_author=J Peng, Y Yamamoto, JA Hawk, E Lara-Curzio, D Shin; citation_volume=6; citation_publication_date=2020; citation_pages=141; citation_doi=10.1038/s41524-020-00407-2; citation_id=CR10 citation_journal_title=Acta Mater.; citation_author=D Shin, Y Yamamoto, MP Brady, S Lee, JA Haynes; citation_volume=168; citation_publication_date=2019; citation_pages=321; citation_doi=10.1016/j.actamat.2019.02.017; citation_id=CR11 citation_journal_title=Comput. Mater. Sci.; citation_title=A Machine Learning Approach to Predict Thermal Expansion of Complex Oxides; citation_author=J Peng, NH Gunda, CA Bridges, S Lee, JA Haynes, D Shin; citation_volume=210; citation_publication_date=2022; citation_pages=111034; citation_doi=10.1016/j.commatsci.2021.111034; citation_id=CR12 citation_journal_title=NPJ Mater. Degrad.; citation_title=Data Analytics Approach to Predict High-Temperature Cyclic Oxidation Kinetics of NiCr-Based Alloys; citation_author=J Peng, R Pillai, M Romedenne, BA Pint, G Muralidharan, J Allen Haynes, D Shin; citation_volume=5; citation_issue=1; citation_publication_date=2021; citation_pages=1-8; citation_doi=10.1038/s41529-021-00188-z; citation_id=CR13 citation_journal_title=Sci. Technol. Adv. Mater.; citation_author=S Lee, J Peng, D Shin, YS Choi; citation_volume=20; citation_publication_date=2019; citation_pages=972; citation_doi=10.1080/14686996.2019.1671140; citation_id=CR14 citation_journal_title=Acta Mater.; citation_author=W Huang, P Martin, HL Zhuang; citation_volume=169; citation_publication_date=2019; citation_pages=225; citation_doi=10.1016/j.actamat.2019.03.012; citation_id=CR15 citation_journal_title=ACS Nano; citation_author=M Ziatdinov, O Dyck, A Maksov, X Li, X Sang, K Xiao, RR Unocic, R Vasudevan, S Jesse, SV Kalinin; citation_volume=11; citation_publication_date=2017; citation_pages=12742; citation_doi=10.1021/acsnano.7b07504; citation_id=CR16 citation_journal_title=Nat. Mater.; citation_author=SV Kalinin, BG Sumpter, RK Archibald; citation_volume=14; citation_publication_date=2015; citation_pages=973; citation_doi=10.1038/nmat4395; citation_id=CR17 citation_journal_title=J. Phys. Condens. Matter; citation_author=X Chong, S-L Shang, AM Krajewski, JD Shimanek, W Du, Y Wang, J Feng, D Shin, AM Beese, Z-K Liu; citation_volume=33; citation_publication_date=2021; citation_pages=295702; citation_doi=10.1088/1361-648X/ac0195; citation_id=CR18 citation_journal_title=Nat. Rev. Mater.; citation_author=GLW Hart, T Mueller, C Toher, S Curtarolo; citation_volume=6; citation_publication_date=2021; citation_pages=730; citation_doi=10.1038/s41578-021-00340-w; citation_id=CR19 citation_journal_title=Calphad; citation_author=JO Andersson, T Helander, L Höglund, P Shi, B Sundman; citation_volume=26; citation_publication_date=2002; citation_pages=273; citation_doi=10.1016/S0364-5916(02)00037-8; citation_id=CR20 citation_journal_title=J. Phase Equilibria. Diffus.; citation_author=H Mao, HL Chen, Q Chen; citation_volume=38; citation_publication_date=2017; citation_pages=353; citation_doi=10.1007/s11669-017-0570-7; citation_id=CR21 A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Köpf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala, 33rd Conference on Neural Information Processing Systems, vol. 32. (2019). https://proceedings.neurips.cc/paper/2019/file/bdbca288fee7f92f2bfa9f7012727740-Paper.pdf . K. He, X. Zhang, S. Ren, and J. Sun, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016), pp. 770–778. D.P. Kingma and J. Ba, in 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings 1 (2014). citation_journal_title=J. Alloys Compd.; citation_title=Some Guidelines for Thermodynamic Optimisation of Phase Diagrams; citation_author=KH Kumar, P Wollants; citation_volume=320; citation_issue=2; citation_publication_date=2001; citation_pages=189-198; citation_doi=10.1016/S0925-8388(00)01491-2; citation_id=CR25 citation_journal_title=Calphad; citation_author=D Shin, Z-K Liu; citation_volume=32; citation_publication_date=2008; citation_pages=74; citation_doi=10.1016/j.calphad.2007.09.002; citation_id=CR26 citation_journal_title=Phys. Rev. B; citation_author=D Shin, A Walle, Y Wang, Z-K Liu; citation_volume=76; citation_publication_date=2007; citation_pages=144204; citation_doi=10.1103/PhysRevB.76.144204; citation_id=CR27 citation_journal_title=Phys. Rev. Lett.; citation_author=C Jiang, BP Uberuaga; citation_volume=116; citation_publication_date=2016; citation_pages=105501; citation_doi=10.1103/PhysRevLett.116.105501; citation_id=CR28 citation_journal_title=Acta Mater.; citation_author=C Wen, Y Zhang, C Wang, D Xue, Y Bai, S Antonov, L Dai, T Lookman, Y Su; citation_volume=170; citation_publication_date=2019; citation_pages=109; citation_doi=10.1016/j.actamat.2019.03.010; citation_id=CR29 citation_journal_title=Mater. Sci. Technol. (United Kingdom); citation_author=S Guo; citation_volume=31; citation_publication_date=2015; citation_pages=1223; citation_doi=10.1179/1743284715Y.0000000018; citation_id=CR30 L. Ward, A. Agrawal, A. Choudhary, and C. Wolverton, npj Comp. Mater., 2016, 2(1), pp. 1–7. citation_journal_title=Calphad; citation_author=AT Dinsdale; citation_volume=15; citation_publication_date=1991; citation_pages=317; citation_doi=10.1016/0364-5916(91)90030-N; citation_id=CR32 citation_journal_title=J. Alloys Compd.; citation_author=I Ansara, N Dupin, HL Lukas, B Sundman; citation_volume=247; citation_publication_date=1997; citation_pages=20; citation_doi=10.1016/S0925-8388(96)02652-7; citation_id=CR33 citation_journal_title=Calphad; citation_author=N Dupin, I Ansara, B Sundman; citation_volume=25; citation_publication_date=2001; citation_pages=279; citation_doi=10.1016/S0364-5916(01)00049-9; citation_id=CR34 citation_journal_title=Calphad; citation_author=SM Liang, R Schmid-Fetzer; citation_volume=51; citation_publication_date=2015; citation_pages=252; citation_doi=10.1016/j.calphad.2015.10.004; citation_id=CR35 I. Ansara, A.T. Dinsdale, and M.H. Rand, in COST 507: Definition of Thermochemical and Thermophysical Properties to Provide a Database for the Development of New Light Alloys. Thermochemical Database for Light Metal Alloys, vol 2 (European Cooperation in the Field of Scientific and Technical Research, 1998) citation_journal_title=J. Phase Equilibria. Diffus.; citation_author=J Huang, B Yang, H Chen, H Wang; citation_volume=36; citation_publication_date=2015; citation_pages=357; citation_doi=10.1007/s11669-015-0390-6; citation_id=CR37