Abstract
The main objective of this research is to develop a robust Bayesian machine learning (ML) model capable of predicting and characterizing the structural heterogeneity in metallic glasses (MGs). The model is constructed using input data obtained from molecular dynamics simulations of CuZr MGs, encompassing a wide range of alloying compositions and simulation parameters. The ML model utilized crucial output variables: the 2D fractal dimension (with a fractal exponent ranging from 1.55 to 1.81) and correlation function (correlation length spanning from 1.1 to 4.05 nm), demonstrating inverse and direct relationships with the degree of heterogeneity, respectively. The results demonstrate the model's high predictive performance, with accuracy values of 0.9398 for the fractal dimension and 0.9639 for the correlation length. It is noteworthy that the correlation length proves to be a reliable indicator for low to intermediate levels of structural heterogeneity, while the fractal dimension effectively characterizes high-level heterogeneity in MGs. Moreover, the integration of both indicators complements each other in accurately predicting structural heterogeneity. Additionally, the developed ML model showcases its versatility in effectively characterizing MG samples exposed to diverse treatments, such as annealing and rejuvenation processes.
Similar content being viewed by others
References
Samavatian M, Gholamipour R, Amadeh A A, and Mirdamadi S, Mater. Sci. Eng. A 753 (2019) 218.
Lin Y, Dai J, Yang Z Z, Jiang S S, Xu Q H, Wang Y G, Chen F G, and Jain A, J. Alloys Compd. 936 (2023) 168268.
Supriyono, Surendar A, Thangavelu L, Arzehgar Z, Pokrovskii M V, Neganov D A, Goncharov D K, and Mohanty H, Trans. Indian Inst. Met. 74 (2021) 1721.
Wang T, Zhou Y, and Zhang L, J. Non. Cryst. Solids 603 (2023) 122115.
Di S, Ke H, Wang Q, Zhou J, Zhao Y, and Shen B, Mater. Des. 222 (2022) 111074.
Vishwanadh B, and Tewari R, Trans. Indian Inst. Met. 75 (2022) 997.
Han X, Gu Y, Yao Y, Kong L, Li L, and Yan F, Res. Surf. Interfaces 10 (2023) 100094.
Liang T, Yu Q, Yin Z, Chen S, Liu Y, Yang Y, Lou H, Shen B, Zeng Z, and Zeng Q, Materials (Basel) 15 (2022) 6319.
Xu F, Liu Y Z, Sun X, Peng J F, Ding Y H, Huo J T, Wang J Q, and Gao M, Appl. Surf. Sci. 611 (2023) 155730.
Sun Q, Miskovic D M, and Ferry M, J. Mater. Sci. Technol. 104 (2022) 214.
Samavatian M, Gholamipour R, Amadeh A A, and Samavatian V, Phys. B Condens. Matter 595 (2020) 412390.
Wang D P, Qiao J C, and Liu C T, Mater. Res. Lett. 7 (2019) 305–311.
Mahmoud Z H, Barazandeh H, Mostafavi S M, Ershov K, Goncharov A, Kuznetsov A S, Kravchenko O D, and Zhu Y, J. Mater. Res. Technol. 11 (2021) 2015.
Kosiba K, Şopu D, Scudino S, Zhang L, Bednarcik J, and Pauly S, Int. J. Plast. 119 (2019) 156.
Brink T, and Albe K, Acta Mater. 156 (2018) 205.
Şopu D, Scudino S, Bian X L, Gammer C, and Eckert J, Scr. Mater. 178 (2020) 57.
Scudino S, Bian J J, Shakur Shahabi H, Şopu D, Sort J, Eckert J, and Liu G, Sci. Rep. 8 (2018) 9174.
Zhu F, Song S, Reddy K M, Hirata A, and Chen M, Nat. Commun. 9 (2018) 1.
Wang N, Ding J, Yan F, Asta M, Ritchie R O, and Li L, NPJ Comput. Mater. 4 (2018) 19.
Samavatian M, Gholamipour R, Bokov D O, Suksatan W, Samavatian V, and Mahmoodan M, J. Non. Cryst. Solids 578 (2022) 121344.
Wu Y, Xu B, Zhang X, and Guan P, Acta Mater. 247 (2023) 118741.
Wang Q, and Jain A, Nat. Commun. 10 (2019) 5537.
Liu C, Wang Y, Wang Y, Islam M, Hwang J, Wang Y, and Fan Y, Acta Mater. 259 (2023) 119281.
Wang Q, Ding J, Zhang L, Podryabinkin E, Shapeev A, and Ma E, NPJ Comput. Mater. 6 (2020) 194.
Şopu D, Yuan X, Moitzi F, Spieckermann F, Bian X, and Eckert J, Appl. Mater. Today 22 (2021) 100958.
Gao R, Hui X, Fang H Z, Liu X J, Chen G L, and Liu Z K, Comput. Mater. Sci. 44 (2008) 802.
Fan Z, Ding J, and Ma E, Mater. Today 40 (2020) 48.
Li F, Liu X J, Hou H Y, Chen G, Chen G L, and Li M, Intermetallics 17 (2009) 98.
Çağin T, Kimura Y, Qi Y, Li H, Ikeda H, Johnsonb W L, and Goddard W A, MRS Online Proc. Libr. 554 (1998) 43.
Hu Y C, Li F X, Li M Z, Bai H Y, and Wang W H, Nat. Commun. 6 (2015) 8310.
Zhu F, Nguyen H K, Song S X, Aji D P B, Hirata A, Wang H, Nakajima K, and Chen M W, Nat. Commun. 7 (2016) 11516.
Sun Q, Miskovic D M, Laws K, Kong H, Geng X, and Ferry M, Appl. Surf. Sci. 533 (2020) 147453.
Yang Y, Zeng J F, Volland A, Blandin J J, Gravier S, and Liu C T, Acta Mater. 60 (2012) 5260.
Sarkar N K, Vishwanadh B, Prajapat C L, Babu P D, Ravikumar G, Dey G K, Voyles P M, Tewari R, and Mishra P K, Mater. Today Commun. 25 (2020) 101427.
Ma D, Stoica A D, and Wang X-L, Nat. Mater. 8 (2009) 30.
Samavatian V, Fotuhi-Firuzabad M, Samavatian M, Dehghanian P, and Blaabjerg F, Sci. Rep. 10 (2020) 14821.
Asrav T, and Aydin E, Comput. Chem. Eng. 173 (2023) 108195.
Ke X, and Duan Y, Constr. Build. Mater. 270 (2021) 121424.
Chilenski M A, Greenwald M, Marzouk Y, Howard N T, White A E, Rice J E, and Walk J R, Nucl. Fusion 55 (2015) 23012.
Duan Y, Cooling C, Ahn J S, Jackson C, Flint A, Eaton M D, and Bluck M J, Int. J. Heat Fluid Flow 80 (2019) 108497.
Seeger M, Int. J. Neural Syst. 14 (2004) 69.
Rasmussen C E, Gaussian processes in machine learning, in: Adv. Lect. Mach. Learn. ML Summer Sch. 2003, Canberra, Aust. Febr. 2–14, 2003, Tübingen, Ger. August 4–16, 2003, Revis. Lect., Springer, (2004), p. 63.
Roberts S, Osborne M, Ebden M, Reece S, Gibson N, and Aigrain S, Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 371 (2013) 20110550.
Gao F, and Han L, Comput. Optim. Appl. 51 (2012) 259–277.
Yang Z Z, Zhu L, Ye L X, Gao X, Jiang S S, Yang H, and Wang Y G, J. Non. Cryst. Solids 571 (2021) 121078.
Li S, Zhang H, Dai D, Ding G, Wei X, and Guo Y, J. Alloys Compd. 782 (2019) 110–118.
Wang M, Lü S, Wu S, and Guo W, J. Alloys Compd. 945 (2023) 169294.
Deshmukh A A, Bhatt J G, Gade P M, and Pal S, J. Mol. Model. 27 (2021) 1.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The author has no conflicts of interest to declare.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Li, H., Mohanty, H. Characterizing Structural Heterogeneity in Metallic Glasses: A Molecular Dynamics-Guided Machine Learning Approach. Trans Indian Inst Met 77, 767–778 (2024). https://doi.org/10.1007/s12666-023-03170-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12666-023-03170-2