Machine Learning Prediction of the Critical Cooling Rate for Metallic Glasses from Expanded Datasets and Elemental Features

Afflerbach, Benjamin T.; Francis, Carter; Schultz, Lane E.; Spethson, Janine; Meschke, Vanessa; Strand, Elliot; Ward, Logan; Perepezko, John H.; Thoma, Dan; Voyles, Paul M.; Szlufarska, Izabela; Morgan, Dane

doi:10.1021/acs.chemmater.1c03542

Title: Machine Learning Prediction of the Critical Cooling Rate for Metallic Glasses from Expanded Datasets and Elemental Features

Journal Article · Wed Mar 30 00:00:00 EDT 2022 · Chemistry of Materials

DOI:https://doi.org/10.1021/acs.chemmater.1c03542· OSTI ID:1960007

^[1]; Francis, Carter ^[1]; Schultz, Lane E. ^[1]; Spethson, Janine ^[1];

^[1]; Strand, Elliot ^[1];

^[2]; Perepezko, John H. ^[1]; Thoma, Dan ^[1];

^[1];

^[1]

Univ. of Wisconsin, Madison, WI (United States)
Argonne National Lab. (ANL), Argonne, IL (United States)

In this study, we use a random forest (RF) model to predict the critical cooling rate (R_C) for glass formation of various alloys from features of their constituent elements. The RF model was trained on a database that integrates multiple sources of direct and indirect R_C data for metallic glasses to expand the directly measured R_C database of less than 100 values to a training set of over 2000 values. The model error on 5-fold cross-validation (CV) is 0.66 orders of magnitude in K/s. The error on leave-out-one-group CV on alloy system groups is 0.59 log units in K/s when the target alloy constituents appear more than 500 times in training data. Using this model, we make predictions for the set of compositions with melt-spun glasses in the database and for the full set of quaternary alloys that have constituents which appear more than 500 times in training data. These predictions identify a number of potential new bulk metallic glass systems for future study, but the model is most useful for the identification of alloy systems likely to contain good glass formers rather than detailed discovery of bulk glass composition regions within known glassy systems.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Argonne National Lab. (ANL), Argonne, IL (United States)

Sponsoring Organization:: USDOE; National Science Foundation (NSF)

Grant/Contract Number:: AC02-06CH11357; DMR-1728933

OSTI ID:: 1960007

Journal Information:: Chemistry of Materials, Vol. 34, Issue 7; ISSN 0897-4756

Publisher:: American Chemical Society (ACS)Copyright Statement

Country of Publication:: United States

Language:: English

References (36)

Accelerated discovery of metallic glasses through iteration of machine learning and high-throughput experiments Ren, Fang; Ward, Logan; Williams, Travis Science Advances, Vol. 4, Issue 4 https://doi.org/10.1126/sciadv.aaq1566	journal	April 2018
Gold based bulk metallic glass Schroers, Jan; Lohwongwatana, Boonrat; Johnson, William L. Applied Physics Letters, Vol. 87, Issue 6 https://doi.org/10.1063/1.2008374	journal	August 2005
Bulk Metallic Glasses with Functional Physical Properties Wang, W. H. Advanced Materials, Vol. 21, Issue 45 https://doi.org/10.1002/adma.200901053	journal	December 2009
Combinatorial measurement of critical cooling rates in aluminum-base metallic glass forming alloys Liu, Naijia; Ma, Tianxing; Liao, Chaoqun Scientific Reports, Vol. 11, Issue 1 https://doi.org/10.1038/s41598-021-83384-w	journal	February 2021
Preparation, thermal stability and magnetic properties of Fe–Co–Ni–Zr–Mo–B bulk metallic glass Liu, D. Y.; Sun, W. S.; Zhang, H. F. Intermetallics, Vol. 12, Issue 10-11 https://doi.org/10.1016/j.intermet.2004.04.014	journal	October 2004
Fabrication and Mechanical Properties of Mg₆₅Cu₁₅Ag₅Pd₅Gd₁₀ Bulk Metallic Glass Men, Hua; Kim, Won Tae; Kim, Do Hyang MATERIALS TRANSACTIONS, Vol. 44, Issue 10 https://doi.org/10.2320/matertrans.44.2141	journal	January 2003
Critical cooling rate and thermal stability for a Ti–Zr–Ni–Cu–Be metallic glass Huang, Yongjiang; Shen, Jun; Chen, John J. J. Journal of Alloys and Compounds, Vol. 477, Issue 1-2 https://doi.org/10.1016/j.jallcom.2008.11.017	journal	May 2009
Predicting the glass formation of metallic glasses using machine learning approaches Li, Zhuang; Long, Zhilin; Lei, Shan Computational Materials Science, Vol. 197 https://doi.org/10.1016/j.commatsci.2021.110656	journal	September 2021
Critical feature space for predicting the glass forming ability of metallic alloys revealed by machine learning Deng, Binghui; Zhang, Yali Chemical Physics, Vol. 538 https://doi.org/10.1016/j.chemphys.2020.110898	journal	October 2020
Quantifying the origin of metallic glass formation Johnson, W. L.; Na, J. H.; Demetriou, M. D. Nature Communications, Vol. 7, Issue 1 https://doi.org/10.1038/ncomms10313	journal	January 2016
Effect of replacing Nb with (Mo and Zr) on glass forming ability, magnetic and mechanical properties of FeCoBSiNb bulk metallic glass Ramasamy, Parthiban; Stoica, M.; Bera, S. Journal of Alloys and Compounds, Vol. 707 https://doi.org/10.1016/j.jallcom.2016.11.408	journal	June 2017
How Many Bulk Metallic Glasses Are There? Li, Yanglin; Zhao, Shaofan; Liu, Yanhui ACS Combinatorial Science, Vol. 19, Issue 11 https://doi.org/10.1021/acscombsci.7b00048	journal	September 2017
The effect of the melt-spinning processing parameters on the rate of cooling Tkatch, Victor I.; Limanovskii, Alexander I.; Denisenko, Sergey N. Materials Science and Engineering: A, Vol. 323, Issue 1-2 https://doi.org/10.1016/S0921-5093(01)01346-6	journal	January 2002
High glass-forming ability correlated with fragility of Mg–Cu(Ag)–Gd alloys Zheng, Qiang; Xu, Jian; Ma, Evan Journal of Applied Physics, Vol. 102, Issue 11 https://doi.org/10.1063/1.2821755	journal	December 2007
An assessment of binary metallic glasses: correlations between structure, glass forming ability and stability Miracle, D. B.; Louzguine-Luzgin, D. V.; Louzguina-Luzgina, L. V. International Materials Reviews, Vol. 55, Issue 4 https://doi.org/10.1179/095066010X12646898728200	journal	July 2010
A two-step fused machine learning approach for the prediction of glass-forming ability of metallic glasses Zhang, Y. X.; Xing, G. C.; Sha, Z. D. Journal of Alloys and Compounds, Vol. 875 https://doi.org/10.1016/j.jallcom.2021.160040	journal	September 2021
The Materials Simulation Toolkit for Machine learning (MAST-ML): An automated open source toolkit to accelerate data-driven materials research Jacobs, Ryan; Mayeshiba, Tam; Afflerbach, Ben Computational Materials Science, Vol. 176 https://doi.org/10.1016/j.commatsci.2020.109544	journal	April 2020
Machine learning prediction of elastic properties and glass-forming ability of bulk metallic glasses Xiong, Jie; Zhang, Tong-Yi; Shi, San-Qiang MRS Communications, Vol. 9, Issue 02 https://doi.org/10.1557/mrc.2019.44	journal	April 2019
Critical cooling rate and thermal stability of Fe–Co–Zr–Y–Cr–Mo–B amorphous alloy Chen, Q. J.; Fan, H. B.; Shen, J. Journal of Alloys and Compounds, Vol. 407, Issue 1-2 https://doi.org/10.1016/j.jallcom.2005.06.031	journal	January 2006
Machine learning-based glass formation prediction in multicomponent alloys Liu, Xiaodi; Li, Xin; He, Quanfeng Acta Materialia, Vol. 201 https://doi.org/10.1016/j.actamat.2020.09.081	journal	December 2020
Calculations of Mixing Enthalpy and Mismatch Entropy for Ternary Amorphous Alloys Takeuchi, Akira; Inoue, Akihisa Materials Transactions, JIM, Vol. 41, Issue 11 https://doi.org/10.2320/matertrans1989.41.1372	journal	January 2000
Ti–Cu–Ni shape memory bulk metallic glass composites Gargarella, P.; Pauly, S.; Song, K. K. Acta Materialia, Vol. 61, Issue 1 https://doi.org/10.1016/j.actamat.2012.09.042	journal	January 2013
Recent Progress in Bulk Glassy Alloys Inoue, Akihisa; Takeuchi, Akira MATERIALS TRANSACTIONS, Vol. 43, Issue 8 https://doi.org/10.2320/matertrans.43.1892	journal	January 2002
A new criterion for predicting the glass-forming ability of bulk metallic glasses Long, Zhilin; Wei, Hongqin; Ding, Yanhuan Journal of Alloys and Compounds, Vol. 475, Issue 1-2 https://doi.org/10.1016/j.jallcom.2008.07.087	journal	May 2009
Formation of Ti–Zr–Cu–Ni bulk metallic glasses Lin, X. H.; Johnson, W. L. Journal of Applied Physics, Vol. 78, Issue 11 https://doi.org/10.1063/1.360537	journal	December 1995
A machine learning approach for engineering bulk metallic glass alloys Ward, Logan; O'Keeffe, Stephanie C.; Stevick, Joseph Acta Materialia, Vol. 159 https://doi.org/10.1016/j.actamat.2018.08.002	journal	October 2018
Are hints about glass forming ability hidden in the liquid structure? Wang, Juan; Agrawal, Anupriya; Flores, Katharine Acta Materialia, Vol. 171 https://doi.org/10.1016/j.actamat.2019.04.001	journal	June 2019
Septenary Zr–Hf–Ti–Al–Co–Ni–Cu high-entropy bulk metallic glasses with centimeter-scale glass-forming ability Wada, Takeshi; Jiang, Jing; Yubuta, Kunio Materialia, Vol. 7 https://doi.org/10.1016/j.mtla.2019.100372	journal	September 2019
Thermodynamics and Kinetics of Bulk Metallic Glass Busch, R.; Schroers, J.; Wang, W. H. MRS Bulletin, Vol. 32, Issue 8 https://doi.org/10.1557/mrs2007.122	journal	August 2007
A machine-learning approach to predicting and understanding the properties of amorphous metallic alloys Xiong, Jie; Shi, San-Qiang; Zhang, Tong-Yi Materials & Design, Vol. 187 https://doi.org/10.1016/j.matdes.2019.108378	journal	February 2020
Noncontact measurement of crystallization behavior, specific volume, and viscosity of bulk glass-forming Zr-Al-Co-(Cu) alloys Mukherjee, S.; Kang, H. -G.; Johnson, W. L. Physical Review B, Vol. 70, Issue 17 https://doi.org/10.1103/PhysRevB.70.174205	journal	November 2004
Crystallization characteristics of Fe‐Zr metallic glasses from Fe ₄ ₃ Zr ₅ ₇ to Fe ₂ ₀ Zr ₈ ₀ Altounian, Z.; Volkert, C. A.; Strom‐Olsen, J. O. Journal of Applied Physics, Vol. 57, Issue 6 https://doi.org/10.1063/1.334455	journal	March 1985
A general-purpose machine learning framework for predicting properties of inorganic materials Ward, Logan; Agrawal, Ankit; Choudhary, Alok npj Computational Materials, Vol. 2, Issue 1 https://doi.org/10.1038/npjcompumats.2016.28	journal	August 2016
A predictable glass forming ability expression by statistical learning and evolutionary intelligence Tripathi, Manwendra K.; Chattopadhyay, P. P.; Ganguly, Subhas Intermetallics, Vol. 90 https://doi.org/10.1016/j.intermet.2017.06.008	journal	November 2017
Exceptionally high glass-forming ability of an FeCoCrMoCBY alloy Shen, Jun; Chen, Qingjun; Sun, Jianfei Applied Physics Letters, Vol. 86, Issue 15 https://doi.org/10.1063/1.1897426	journal	April 2005
Can machine learning identify the next high-temperature superconductor? Examining extrapolation performance for materials discovery Meredig, Bryce; Antono, Erin; Church, Carena Molecular Systems Design & Engineering, Vol. 3, Issue 5 https://doi.org/10.1039/C8ME00012C	journal	January 2018

Similar Records

Evaluation and comparison of benchmark QSAR models to predict a relevant REACH endpoint: The bioconcentration factor (BCF)

Journal Article · Sun Feb 15 00:00:00 EST 2015 · Environmental Research · OSTI ID:1960007

Gissi, Andrea; Lombardo, Anna; Roncaglioni, Alessandra; +4 more

Ch3MS-RF: a random forest model for chemical characterization and improved quantification of unidentified atmospheric organics detected by chromatography–mass spectrometry techniques

Journal Article · Fri Jun 24 00:00:00 EDT 2022 · Atmospheric Measurement Techniques (Online) · OSTI ID:1960007

Franklin, Emily B.; Yee, Lindsay D.; Aumont, Bernard; +3 more

Annual Report: Fuels (30 September 2012)

Technical Report · Sun Sep 30 00:00:00 EDT 2012 · OSTI ID:1960007

Link, Dirk; Morreale, Bryan

Related Subjects

36 MATERIALS SCIENCE
Alloys
Amorphous materials
Biological databases
Elements
Mathematical methods

Title: Machine Learning Prediction of the Critical Cooling Rate for Metallic Glasses from Expanded Datasets and Elemental Features

Citation Formats

References (36)

Similar Records

Related Subjects