Accelerated design of Fe-based soft magnetic materials using machine learning and stochastic optimization
Source abstract
Abstract
Machine learning was utilized to efficiently boost the development of soft magnetic materials. The design process includes building a database composed of published experimental results, applying machine learning methods on the database, identifying the trends of magnetic properties in soft magnetic materials, and accelerating the design of next-generation soft magnetic nanocrystalline materials through the use of numerical optimization. Machine learning regression models were trained to predict magnetic saturation ($B_S$), coercivity ($H_C$) and magnetostriction ($λ$), with a stochastic optimization framework being used to further optimize the corresponding magnetic properties. To verify the feasibility of the machine learning model, several optimized soft magnetic materials -- specified in terms of compositions and thermomechanical treatments -- have been predicted and then prepared and tested, showing good agreement between predictions and experiments, proving the reliability of the designed model. Two rounds of optimization-testing iterations were conducted to search for better properties.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Metallic Glasses and Amorphous Alloys · Magnetic Properties and Applications · Magnetic Properties of Alloys
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (95)
Show source-provided references
1. New Fe-based soft magnetic alloys composed of ultrafine grain structure10.1063/1.342149 ↗
2. Nanocrystalline soft magnetic alloys two decades of progress10.1016/B978-0-444-59593-5.00004-0 ↗
3. Modern soft magnets: Amorphous and nanocrystalline materials10.1016/j.actamat.2012.10.040 ↗
4. Grain structure and magnetism of nanocrystalline ferromagnets10.1109/20.42292 ↗
5. Soft magnetic Ni-Fe and Co-Fe alloys-some physical and metallurgical aspects10.1016/0304-8853(80)90592-2 ↗
6. New nanocrystalline high-remanence Nd-Fe-B alloys by rapid solidification10.1016/0304-8853(93)90475-H ↗
7. The exchange-spring magnet: a new material principle for permanent magnets10.1109/20.102931 ↗
8. Combined machine learning and CALPHAD approach for discovering processing-structure relationships in soft magnetic alloys10.1016/j.commatsci.2018.04.008 ↗
9. Crystallization process of Fe based amorphous alloys: Mechanical and magnetic properties10.1002/1521-396X(200202)189:3<877::AID-PSSA877>3.0.CO;2-G ↗
10. Soft magnetic properties of bcc Fe-Au-X-Si-B (X=early transition metal) alloys with fine grain structure10.2320/matertrans1989.30.947 ↗
11. Influence of microstructure on the magnetic and mechanical behaviour of amorphous and nanocrystalline FeNbB alloy10.1088/0953-8984/14/18/307 ↗
12. Grain size dependence of coercivity and permeability in nanocrystalline ferromagnets10.1109/20.104389 ↗
13. Microstructure evolution and soft magnetic properties of Fe72−xNbxAl5Ga2P11C6B4 (x=0,2) metallic glasses10.1088/0022-3727/35/18/303 ↗
14. High saturation magnetization and soft magnetic properties of bcc Fe-Zr-B alloys with ultrafine grain structure10.2320/matertrans1989.31.743 ↗
15. Influence of Cr additions in magnetic properties and crystallization process of amorphous iron based alloys10.1063/1.1485109 ↗
16. Magnetic properties of nanocrystalline Fe-based soft magnetic alloys10.1557/PROC-232-183 ↗
17. On the role of aluminum in Finemet10.1023/A:1014494907198 ↗
18. Soft magnetic properties of nanocrystalline bcc Fe-Zr-B and Fe-M-B-Cu (M=transition metal) alloys with high saturation magnetization10.1063/1.350006 ↗
19. Nanostructure formation and soft magnetic properties evolution in Fe91−xWxB9 amorphous alloys10.1016/S0921-5107(01)00934-5 ↗
20. Magnetic properties of fine crystalline Fe-P-C-Cu-X alloys10.1063/1.350008 ↗
21. Evolution of magnetic, structural and mechanical properties in FeSiBNbCuAlGe system10.1016/S0921-4526(02)00715-9 ↗
22. Low core loss of a bcc Fe86Zr7B6Cu1 alloy with nanoscale grain size10.2320/matertrans1989.32.551 ↗
23. Influence of P substitution for B on the structure and properties of nanocrystalline Fe73.5Si15.5Nb3Cu1B7−xPx alloys10.1016/S0921-4526(02)01741-6 ↗
24. Effects of Al on the magnetic properties of nanocrystalline Fe73.5Cu1Nb3Si13.5B9 alloys10.1063/1.352574 ↗
25. Low-temperature magnetic properties and the crystallization behavior of FINEMET alloy10.1063/1.1565829 ↗
26. Crystallization of Fe-Si-B-Ga-Nb amorphous alloy10.1016/0921-5093(94)90259-3 ↗
27. Optimization of soft magnetic properties in nanoperm type alloys10.1016/S0928-4931(02)00234-5 ↗
28. Magnetic properties and microstructure of nanocrystalline bcc Fe-MB (M=Zr, Hf, Nb) alloys10.1016/0304-8853(94)90559-2 ↗
29. Nanocrystallization of soft magnetic Finemet-type amorphous ribbons10.1016/S0924-4247(03)00177-8 ↗
30. Magnetic properties of very high permeability, low coercivity, and high electrical resistivity in Fe87Zr7B5Ag1 amorphous alloy10.1063/1.359284 ↗
31. Influence of substitutions on crystallization and magnetic properties of Finemet-based nanocrystalline alloys and thin films10.1007/s10582-004-0078-3 ↗
32. Soft magnetic Fe-Zr-Si-B alloys with nanocrystalline structure10.2320/matertrans1989.36.689 ↗
33. Magnetic properties and structural evolution of FINEMET alloys with Ge addition10.1016/j.physb.2004.09.050 ↗
34. Influence of heat treatment on magnetostrictions of Finemet Fe73.5Cu1Nb3Si3.5B910.1016/S0921-5093(97)80078-0 ↗
35. Origin of the magnetic anisotropy induced by stress annealing in Fe-based nanocrystalline alloy10.1063/1.1901807 ↗
36. Survey of magnetic properties during and after amorphous-nanocrystalline transformation
37. The effect of Zn, Ag and Au substitution for Cu in Finemet on the crystallization and magnetic properties10.1016/j.jmmm.2006.01.057 ↗
38. Temperature dependence of the magnetostriction in α-Fe100−xSix and FINEMET type alloys
39. New high-Bs Fe-based nanocrystalline soft magnetic alloys10.1143/JJAP.46.L477 ↗
40. Magnetic properties and microstructure of nanocrystalline Fe-based alloys
41. Structure and soft magnetic properties of V-doped Finemet-type alloys10.1016/j.jallcom.2006.12.133 ↗
42. Mössbauer study of the magnetic properties of nanocrystalline Fe80.5Nb7B12.5 alloy10.1063/1.370363 ↗
43. Structure and magnetic properties of Fe
44. Evolution of structure and magnetic properties with annealing temperature in novel Al-containing alloys based on Finemet10.1016/S0304-8853(99)00196-1 ↗
45. New Fe-metalloids based nanocrystalline alloys with high Bs of 1.9 T and excellent magnetic softness10.1063/1.3058624 ↗
46. Magnetic properties and nanocrystallization of a Fe63.5Cr10Si13.5B9Cu1Nb3 alloy10.1016/S0304-8853(99)00188-2 ↗
47. Stress-induced magnetic and structural anisotropy of nanocrystalline Fe-based alloys10.1063/1.3506538 ↗
48. Contribution of the crystalline phase Fe100−xSix to the temperature dependence of magnetic properties of FINEMET-type alloys10.1109/20.825825 ↗
49. Effects of substitution of Mo for Nb on less-common properties of Finemet alloys10.1016/j.jmmm.2010.05.025 ↗
50. Structure and magnetic properties of Fe73.5Ag1Nb3Si13.5B9 alloy10.1007/s11741-000-0017-x ↗
51. Microstructure and magnetic properties of Fe72.5Cu1M2V2Si13.5B9 (M=Nb, Mo, (NbMo), (MoW)) nanocrystalline alloys10.1016/j.jmmm.2010.05.008 ↗
52. Magnetic properties of ultrasoft-nanocomposite FeAlSiBNbCu alloys10.1016/S0304-8853(00)00132-3 ↗
53. Low core losses and magnetic properties of Fe85−86Si1−2B8P4Cu1 nanocrystalline alloys with high B for power applications10.1063/1.3535169 ↗
54. Devitrification process of FeSiBCuNbX nanocrystalline alloys: Mössbauer study of the intergranular phase10.1088/0953-8984/12/37/308 ↗
55. High Bs Fe84−xSi4B8P4Cux (x = 0-1.5) nanocrystalline alloys with excellent magnetic softness10.1063/1.3535290 ↗
56. Structure and magnetic properties of nanocrystalline soft ferromagnets10.1023/A:1011040419703 ↗
57. Fe-B-P-Cu nanocrystalline soft magnetic alloys with high Bs10.1016/j.jallcom.2010.12.104 ↗
58. On determination of volume fraction of crystalline phase in partially crystallized amorphous and nanocrystalline materials10.1023/A:1004852117700 ↗
59. Nanocrystalline soft magnetic Fe-Si-B-P-Cu alloys with high B of 1.8-1.9 T contributable to energy saving10.1109/TMAG.2011.2175210 ↗
60. Effective magnetic anisotropy and internal demagnetization investigations in soft magnetic nanocrystalline alloys10.1016/S0304-8853(99)00600-9 ↗
61. Influence of microstructure on soft magnetic properties of low coreloss and high Bs Fe85Si2B8P4Cu1 nanocrystalline alloy10.1063/1.4868188 ↗
62. Magnetostriction of the Fe73.5Cu1Ta2Nb1Si13.5B9 alloy10.1016/S0304-8853(00)00297-3 ↗
63. Investigation of microstructure and magnetic properties of Fe81Si4B12−xP2Cu1Mx (M = Cr, Mn and V; x = 0, 1, 2, 3) melt spun ribbons10.1016/j.jallcom.2014.10.202 ↗
64. Structure and magnetic behaviour of Fe-Cu-Nb-Si-B-Al alloys10.1016/S0304-8853(00)00201-8 ↗
65. Structure and magnetic properties of Si-rich FeAlSiBNbCu alloys10.1016/j.jnoncrysol.2014.12.035 ↗
66. Study of Fe-Zr-U-B and Fe-Zr-U-Cu-B nanocrystalline alloys10.1016/S0304-8853(00)00199-2 ↗
67. Effect of Nb addition on the magnetic properties and microstructure of FePCCu nanocrystalline alloy10.1007/s10854-015-2950-2 ↗
68. Saturation magnetization and amorphous Curie point changes during the early stage of amorphous-nanocrystalline transformation of a FINEMET-type alloy10.1016/S0304-8853(00)00189-X ↗
69. A correlation between the magnetic and structural properties of isochronally annealed Cu-free FINEMET alloy with composition Fe72B19.2Si4.8Nb410.1007/s00339-014-8729-0 ↗
70. Optimisation of soft magnetic properties in Fe-Cu-X-Si13B9 (X= Cr, Mo, Zr) amorphous alloys10.1016/S0304-8853(01)00349-3 ↗
71. Development of FeSiBNbCu nanocrystalline soft magnetic alloys with high Bs and good manufacturability10.1007/s11664-016-4643-x ↗
72. Nanocrystallite compositions for Al-and Mo-containing Finemet-type alloys10.1016/S0022-3093(01)00546-4 ↗
73. Effect of substitution of Cu by Au and Ag on nanocrystallization behavior of Fe83.3Si4B8P4Cu0.7 soft magnetic alloy10.1016/j.jallcom.2016.05.027 ↗
74. Mo-containing Finemet alloys: Microstructure and magnetic properties10.1016/S0022-3093(01)00598-1 ↗
75. Core loss analysis of finemet type nanocrystalline alloy ribbon with different thickness10.1016/j.pnsc.2017.09.002 ↗
76. Thermo-magnetic transitions in two-phase nanostructured materials10.1109/20.951133 ↗
77. Study on soft magnetic properties of Finemet-type nanocrystalline alloys with Mo substituting for Nb10.1002/pssa.201700074 ↗
78. Microstructure and properties of nanocrystalline Fe-Zr-Nb-B soft magnetic alloys with low magnetostriction10.1016/S1359-6454(01)00274-9 ↗
79. Soft magnetic Fe-Si-B-Cu nanocrystalline alloys with high Cu concentrations10.1016/j.jallcom.2017.06.128 ↗
80. Structural relaxation processes in FeSiB-Cu(Nb, X), X = Mo, V, Zr, Nb glassy alloys10.1016/S0921-5093(00)01501-X ↗
81. Role of Mo addition on structure and magnetic properties of the Fe85Si2B8P4Cu1 nanocrystalline alloy10.1016/j.jnoncrysol.2017.12.003 ↗
82. Correlation between structure, magnetic properties and MI effect during the nanocrystallisation process of FINEMET type alloys10.1016/S0921-4526(01)00468-9 ↗
83. Local structure, nucleation sites and crystallization behavior and their effects on magnetic properties of Fe81SixB10P8−xCu1 (x=0-8)10.1038/s41598-018-19665-8 ↗
84. A. Rohatgi, Webplotdigitizer (Version 4.1), 2018, https://automeris.io/WebPlotDigitizer.
85. W. Koehrsen, feature-selector, 2018, https://github.com/WillKoehrsen/feature-selector.
86. Lightgbm: A highly efficient gradient boosting decision tree
87. Scikit-learn: Machine learning in Python
88. Random forests10.1023/A:1010933404324 ↗
89. Using random forest to learn imbalanced data
90. Can machine learning find extraordinary materials?10.1016/j.commatsci.2019.109498 ↗
91. Evaluating explorative prediction power of machine learning algorithms for materials discovery using k-fold forward cross-validation10.1016/j.commatsci.2019.109203 ↗
92. Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces10.1023/A:1008202821328 ↗
93. Multi-objective optimization in material design and selection10.1016/S1359-6454(99)00304-3 ↗
94. A. Wang, S. Kauwe, R. Murdock, T. Sparks, Compositionally-restricted attention-based network for materials property prediction (2020). https://chemrxiv.org/articles/Compositionally-Restricted_Attention-Based_Network_for_Materials_Property_Prediction/11869026. 10.26434/chemrxiv.11869026.v1.10.26434/chemrxiv.11869026.v1 ↗
95. Machine learning approach to fe-based soft magnetic nanocrystalline materials design, 2020, https://github.com/yuhaowang2018/Machine_learning_approach_to_Iron_based_soft_magnetic_nanocrystalline_materials_design.