Machine learning-enabled design of Fe-based bulk metallic glasses for superior thermal neutron absorption properties
Source abstract
Abstract
The pressing demand for innovative Fe-based amorphous alloys that excel in both glass-forming ability (GFA) and neutron-absorption has led to the exploration of novel alloying concepts incorporating high levels of B and Gd. In this study, we utilized AutoGluon, an advance autoML framework, to pinpoint the optimal feature sets for predicting the D max in Fe-based bulk metallic glasses (BMGs), effectively excluding characteristic temperatures from our analysis. This approach was validated across a dataset of 241 data points, achieving an R 2 of 0.817 and an MSE of 1.88. Further, we applied the SHAP method to determine critical conditions that enhance GFA, aligning these with the feature distribution of the extrapolated BMGs. Consequently, we successfully fabricated the alloy (Fe 0.72B 0.22Nb 0.04Cr 0.02) 96.5Gd 3.5, which not only reached a D max of 3 mm but also exhibited superior neutron absorption properties. This research enhances our understanding of GFA and supports the development of innovative Fe-based BMGs with optimized material properties.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Metallic Glasses and Amorphous Alloys · Glass properties and applications · Pigment Synthesis and Properties
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (68)
Show source-provided references
1. Control mechanism of gadolinium-rich precipitates in new nuclear shielding FeCrNi alloys10.1016/j.scriptamat.2023.115575 ↗
2. Extending damage accumulation of commercial reactor irradiated 316 stainless steel with ion irradiation10.1016/j.jnucmat.2024.154989 ↗
3. Unveiling the pitting corrosion mechanism of borated stainless steel in the wet storage environment of spent nuclear fuels10.1016/j.actamat.2023.119477 ↗
4. Enhanced strength-ductility synergy in brittle high borated steel by tailoring strain hardening behaviour10.1016/j.scriptamat.2023.115398 ↗
5. The advancement of Neutron-shielding materials for the transportation and storage of spent nuclear fuel10.3390/ma15093255 ↗
6. Corrosion resistance of amorphous Fe49.7Cr17.7Mn1.9Mo7.4W1.6B15.2C3.8Si2. coating - a new criticality-controlled material
7. Applications in the nuclear industry for thermal spray amorphous metal and ceramic coatings10.1007/s11661-009-9830-4 ↗
8. Fabrication and characterization of Fe-based amorphous coatings prepared by high-velocity arc spraying10.1016/j.matdes.2015.04.027 ↗
9. Thermal, magnetic and magnetocaloric properties of FeErNbB metallic glasses with high glass-forming ability10.1016/j.jnoncrysol.2019.03.005 ↗
10. Effect of solute atoms on glass-forming ability for Fe–Y–B alloy: an ab initio molecular dynamics study10.1016/j.actamat.2014.04.070 ↗
11. Gd effect on microstructure and properties of the Modified-690 alloy for function structure integrated thermal neutron shielding10.1016/j.net.2023.01.018 ↗
12. Suppression of crystallization during high velocity impact quenching of alumina droplets: observations and characterization10.1016/j.msea.2006.11.132 ↗
13. A machine-learning approach to predicting and understanding the properties of amorphous metallic alloys10.1016/j.matdes.2019.108378 ↗
14. Data-driven glass-forming ability criterion for bulk amorphous metals with data augmentation10.1016/j.jmst.2021.12.056 ↗
15. Determination of glass forming ability of bulk metallic glasses based on machine learning10.1016/j.commatsci.2021.110480 ↗
16. Insights into metal glass forming ability based on data-driven analysis10.1016/j.matdes.2023.112129 ↗
17. A new mathematical expression for the relation between characteristic temperature and glass-forming ability of metallic glasses10.1016/j.jnoncrysol.2019.119829 ↗
18. A two-step fused machine learning approach for the prediction of glass-forming ability of metallic glasses10.1016/j.jallcom.2021.160040 ↗
19. An effective framework for predicting performance of solid-solution copper alloys using a feature engineering technique in machine learning10.3390/met13101641 ↗
20. Relationship between the widths of supercooled liquid regions and bond parameters of Mg-based bulk metallic glasses10.1016/S0022-3093(03)00155-8 ↗
21. Solid-solution phase formation rules for multi-component alloys10.1002/adem.200700240 ↗
22. Prediction of high-entropy stabilized solid-solution in multi-component alloys10.1016/j.matchemphys.2011.11.021 ↗
23. Correlation between volumetric change and glass-forming ability of metallic glass-forming alloys
24. A valence electron concentration criterion for glass-formation ability of metallic liquids10.1063/1.1571984 ↗
25. A general-purpose machine learning framework for predicting properties of inorganic materials10.1038/npjcompumats.2016.28 ↗
26. N. Erickson, J. Mueller, A. Shirkov, H. Zhang, P. Larroy, M. Li, A. SmolaAutoGluon-Tabular Robust and Accurate AutoML for Structured Data, 7th ICML Workshop on Automated Machine Learning (2020)2020.
27. Lightgbm: a highly efficient gradient boosting decision tree
28. Extremely randomized trees10.1007/s10994-006-6226-1 ↗
29. Random forests10.1023/A:1010933404324 ↗
30. FlexiPrune: a pytorch tool for flexible CNN pruning policy selection10.1016/j.softx.2024.101858 ↗
31. Deep learning-based multi-target regression for traffic-related air pollution forecasting
32. AutoGluon: A revolutionary framework for landslide hazard analysis10.1016/j.nhres.2021.07.002 ↗
33. Feature selection using a sinusoidal sequence combined with mutual information
34. Mutual information-based radiomic feature selection with SHAP explainability for breast cancer diagnosis10.1016/j.rineng.2024.103071 ↗
35. Study on gamma shielding polymer composites reinforced with different sizes and proportions of tungsten particles using MCNP code10.1016/j.pnucene.2019.03.033 ↗
36. The design, microstructure and mechanical properties of a novel Gd2O3/6061Al neutron shielding composite10.1016/j.vacuum.2019.01.004 ↗
37. Overcoming the challenge of the data imbalance for prediction of the glass forming ability in bulk metallic glasses
38. A unified approach to interpreting model predictions
39. Effect of W addition on the glass forming ability and mechanical properties of Fe-based metallic glass10.1016/j.jallcom.2017.10.104 ↗
40. Role of Nb in glass formation of Fe–Cr–Mo–C–B–Nb BMGs10.1016/j.jallcom.2014.03.095 ↗
41. Correlation between glass transition temperature and melting temperature in metallic glasses10.1016/j.matdes.2014.04.021 ↗
42. Universal criterion for metallic glass formation10.1016/S0921-5093(97)80041-X ↗
43. Glass formability of ferrous- and aluminum-based structural metallic alloys10.1016/S0022-3093(02)02000-8 ↗
44. Modified efficient cluster packing model for calculating alloy compositions with high glass forming ability
45. The influence of Nb and Zr on glass-formation ability in the ternary Fe–Nb–B and Fe–Zr–B and quaternary Fe–(Nb,Zr)–B alloy systems10.1557/JMR.2008.0055 ↗
46. The effect of Y on glass forming ability10.1016/j.scriptamat.2005.03.042 ↗
47. Stabilization of metallic supercooled liquid and bulk amorphous alloys10.1016/S1359-6454(99)00300-6 ↗
48. Classification of bulk metallic glasses by atomic size difference, heat of mixing and period of constituent elements and its application to characterization of the main alloying element10.2320/matertrans.46.2817 ↗
49. Synthesis of iron-based bulk metallic glasses as nonferromagnetic amorphous steel alloys10.1063/1.1599636 ↗
50. A Cu-based amorphous alloy with a simultaneous improvement in its glass forming ability and plasticity10.1007/BF03027818 ↗
51. Susceptibility of passive film stability to the pore defect for HVAF-sprayed Fe-based amorphous coatings10.1007/s11666-023-01540-2 ↗
52. Cooling rates in splat cooling10.1016/0025-5416(67)90013-4 ↗
53. Numerical simulation of nucleation, solidification, and microstructure formation in thermal spraying10.1016/j.ijheatmasstransfer.2003.11.030 ↗
54. Corrosion-resistant Gd particles-doped Fe-based amorphous coatings with excellent neutron absorption properties10.1016/j.corsci.2024.112376 ↗
55. Quantitative evaluation of critical cooling rate for metallic glasses10.1016/S0921-5093(00)01446-5 ↗
56. Thermodynamic properties of amorphous solids —glass formation and glass transition— (Overview)10.2320/matertrans1989.36.777 ↗
57. Calculations of mixing enthalpy and mismatch entropy for ternary amorphous alloys10.2320/matertrans1989.41.1372 ↗
58. Super-high strength of over 4000 MPa for Fe-based bulk glassy alloys in [(Fe1−xCox)0.75B0.2Si0.05]96Nb4 system10.1016/j.actamat.2004.05.022 ↗
59. C. T., Fe- and Co-based bulk glassy alloys with ultrahigh strength of over 4000MPa10.1016/j.intermet.2006.01.038 ↗
60. Corrosion behavior of Fe-based ferromagnetic (Fe, Ni)–B–Si–Nb bulk glassy alloys in aqueous electrolytes10.1016/j.jnoncrysol.2008.06.009 ↗
61. Effect of Y addition on thermal stability and the glass forming ability in Fe–Nb–B–Si bulk glassy alloy10.1016/j.msea.2006.07.073 ↗
62. Effects of Cu substitution for Fe on the glass-forming ability and soft magnetic properties for Fe-based bulk metallic glasses10.1016/j.jmmm.2014.01.014 ↗
63. Ductile Fe–Nb–B bulk metallic glass with ultrahigh strength10.1063/1.2949747 ↗
64. Enhancement of plastic deformation in FeCoNbB bulk metallic glass with superhigh strength10.1016/j.intermet.2012.09.018 ↗
65. Glass forming ability, mechanical and magnetic properties in Fe–W–Y–B alloys10.1016/j.msea.2009.11.042 ↗
66. Formation of bulk metallic glasses in the Fe–M–Y–B (M = transition metal) system10.1016/j.jallcom.2007.09.063 ↗
67. Fe-B-Si-Nb bulk metallic glasses with high strength above 4000 MPa and distinct plastic elongation10.2320/matertrans.45.1214 ↗
68. Splat cooling and metastable phases10.1088/0034-4885/36/11/002 ↗