journal article·2021-11Open access

Molecular simulation-derived features for machine learning predictions of metal glass forming ability

Benjamin T. Afflerbach, Lane Schultz, John H. Perepezko, Paul M. Voyles, Izabela Szlufarska, Dane Morgan

Abstract

We have developed models of metallic alloy glass forming ability based on newly computationally accessible features obtained from molecular dynamics simulations. In this work we showed that it is possible to increase the predictive value of GFA models by using input features obtained from molecular dynamics simulations. Such features require only relatively straightforward and scalable simulations, making them significantly easier and less expensive to obtain than experimental measurements. We generated a database of molecular dynamics critical cooling rates along with associated candidate features that are inspired from previous research on GFA. Out of the list of 9 proposed GFA features, we identify two as being the most important to performance through a LASSO model. Enthalpy of crystallization and icosahedral-like fraction at 100 K showed promise because they enable a significant improvement to model performance and because they are accessible to flexible ab initio quantum mechanical methods readily applicable to almost all systems. This advancement in computationally accessible features for machine learning predictions GFA will enable future models to more accurately predict new glass forming alloys.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Metallic Glasses and Amorphous Alloys · Phase-change materials and chalcogenides · Glass properties and applications

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

References (39)

Show source-provided references
1. Non-crystalline structure in solidified Gold-Silicon alloys10.1038/187869b0 ↗
2. Metallic glasses as structural materials10.1016/j.scriptamat.2005.09.051 ↗
3. Bulk Metallic Glasses: Formation and Applications
4. Bulk metallic glasses with functional physical properties10.1002/adma.200901053 ↗
5. Y. Li, S. Zhao, Y. Liu, P. Gong, J. Schroers, How Many Bulk Metallic Glasses Are There?, (2017) 687–693. doi:10.1021/acscombsci.7b00048.10.1021/acscombsci.7b00048 ↗
6. Stabilization of metallic supercooled liquid and bulk amorphous alloys10.1016/S1359-6454(99)00300-6 ↗
7. F. Ren L. Ward T. Williams K.J. Laws C. Wolverton J. Hattrick-Simpers A. Mehta Accelerated discovery of metallic glasses through iteration of machine learning and high-throughput experiments Sci. Adv. 4 4 2018 eaaq1566 10.1126/sciadv.aaq1566.10.1126/sciadv.aaq1566 ↗
8. A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
9. A machine learning approach for engineering bulk metallic glass alloys10.1016/j.actamat.2018.08.002 ↗
10. A machine-learning approach to predicting and understanding the properties of amorphous metallic alloys10.1016/j.matdes.2019.108378 ↗
11. Fast Parallel Algorithms for Short – Range Molecular Dynamics10.1006/jcph.1995.1039 ↗
12. Highly optimized embedded-atom-method potentials for fourteen FCC metals10.1103/PhysRevB.83.134118 ↗
13. Under what conditions can a glass be formed?10.1080/00107516908204405 ↗
14. Atomic packing density and its influence on the properties of Cu-Zr amorphous alloys10.1016/j.scriptamat.2007.07.019 ↗
15. On the role of Sm in solidification of Al-Sm metallic glasses10.1016/j.scriptamat.2016.06.045 ↗
16. Atomic packing and short-to-medium-range order in metallic glasses10.1038/nature04421 ↗
17. Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis10.1016/j.commatsci.2012.10.028 ↗
18. A DFT study on the heredity-induced coalescence of icosahedral basic clusters in the rapid solidification10.1016/j.commatsci.2014.12.024 ↗
19. Clustering, microalloying and mechanical properties in Cu/Zr-based glassy models by molecular dynamics simulations and ab-initio computations, in10.1016/j.jallcom.2011.11.038 ↗
20. Microalloying effects in ternary Cu-Zr-X (X=Be, Mg, Al, Si, P, Nb, Ag) icosahedral clusters and super-clusters from Density Functional Theory computations10.1016/j.poly.2017.05.001 ↗
21. A. Hirata L.J. Kang T. Fujita B. Klumov K. Matsue M. Kotani A.R. Yavari M.W. Chen 341 6144 2013 376 379.10.1126/science.1232450 ↗
22. Diffusion in zeolites10.1016/S0167-2991(06)81893-8 ↗
23. Ab initio molecular dynamics simulation of interstitial diffusion in Ni-Cr alloys and implications for radiation induced segregation10.1016/j.jnucmat.2013.10.022 ↗
24. Are Hints about Glass Forming Ability Hidden in the Liquid Structure?10.1016/j.actamat.2019.04.001 ↗
25. Thermodynamics of the stability of amorphous alloys of two transition metals10.1016/0022-5088(88)90391-8 ↗
26. Applications of an extended Miedema’s model for ternary alloys10.1016/j.jallcom.2009.07.062 ↗
27. The Materials Simulation Toolkit for Machine learning (MAST-ML): An automated open source toolkit to accelerate data-driven materials research10.1016/j.commatsci.2020.109544 ↗
28. Scikit-learn: Machine Learning in Python
29. A new criterion for predicting the glass-forming ability of bulk metallic glasses10.1016/j.jallcom.2008.07.087 ↗
30. A new mathematical expression for the relation between characteristic temperature and glass-forming ability of metallic glasses10.1016/j.jnoncrysol.2019.119829 ↗
31. New criteria of glass forming ability, thermal stability and characteristic temperatures for various bulk metallic glass systems10.1016/j.msea.2007.01.033 ↗
32. Bulk metallic glasses10.1016/j.mser.2004.03.001 ↗
33. Critical evaluation of glass forming ability criteria10.1179/1743284715Y.0000000104 ↗
34. On the heating rate dependence of crystallization temperatures of metallic glasses10.1063/1.3457336 ↗
35. Crystallization of fcc and bcc liquid metals studied by molecular dynamics simulation10.3390/met10111532 ↗
36. Binary Cu–Zr Bulk Metallic Glasses10.1088/0256-307X/21/5/039 ↗
37. Structural mechanism of the enhanced glass-forming ability in multicomponent alloys with positive heat of mixing10.1038/srep38098 ↗
38. Structural origin of the enhancement in glass-forming ability of binary Ni-Nb metallic glasses10.1016/j.jnoncrysol.2021.120834 ↗
39. Structural origin of the high glass-forming ability of Ce70Ga10Cu20 alloys10.1039/C8CP07478J ↗