journal article·2024-08

Deep alloys: Metal materials empowered by deep learning

Kaiyuan Zheng, Zhongping He, Lun Che, Hong Cheng, Meiling Ge, Tianyu Si, Xiaotian Xu

Publisher page

Abstract

With the rapid development of technologies such as computer science, big data, and artificial intelligence, the emergence of a vast amount of data has brought developmental opportunities. The field of materials science is no exception. A plethora of data from materials science, chemistry, biology, and other areas aids researchers in driving technological innovation. The use of data combined with deep learning significantly enhances the efficiency of scientific researchers. This article reviews the application of deep learning in the following areas of materials science: New Metal Material Design, By analyzing a large amount of material data, physical property data, and previous experimental results, neural networks can predict the performance, stability, and application potential of materials, thereby guiding material scientists to develop new metal alloys more quickly. Material Characterization: Analyzing and interpreting various material characterization data, using image recognition and computer vision technologies to analyze the microstructure of metal materials, and analyzing X-ray diffraction, transmission electron microscopy images, spectroscopy data, etc. Process Optimization in Material Preparation, Electronic Structure Calculation , Material Defect Detection, Applications in Material Structure and Crystallography, Molecular Dynamics Simulation, and Degradation Modeling: Using deep learning neural networks to more rapidly estimate the fatigue life, creep fracture, corrosion rate, etc., of materials under service conditions. Finally, the article discusses the challenges, development prospects, and opportunities of deep learning in the field of materials science.
Source: expertdata · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Machine Learning in Materials Science · Additive Manufacturing Materials and Processes · Welding Techniques and Residual Stresses

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

References (100+)

Show source-provided references
1. A perspective on corrosion of multi-principal element alloys10.1038/s41529-021-00163-8 ↗
2. Elemental partitioning and corrosion resistance of Ni–Cr alloys revealed by accurate ab-initio thermodynamic and electrochemical calculations10.1038/s41529-023-00414-w ↗
3. Nemoshkalenko · 1979
4. Investigation on mechanical properties and corrosion resistance of Ti-modified AA5083 aluminum alloy for aerospace and automotive applications10.1038/s41598-023-38510-1 ↗
5. Understanding and design of metallic alloys guided by phase-field simulations10.1038/s41524-023-01038-z ↗
6. Additive manufacturing of alloys with programmable microstructure and properties10.1038/s41467-023-42326-y ↗
7. Design of refractory multi-principal-element alloys for high-temperature applications10.1038/s41524-023-01095-4 ↗
8. Composition design and optimization of Fe-C-Mn-Al steel based on machine learning10.1039/D3CP05453E ↗
9. Machine learning guided BCC or FCC phase prediction in high entropy alloys10.1016/j.jmrt.2024.01.257 ↗
10. Deep learning in alloy material microstructures: application and prospects
11. Additive manufacturing of titanium alloys – enabling re-manufacturing of aerospace and biomedical components10.1016/j.mee.2022.111935 ↗
12. The state of the art for wire arc additive manufacturing process of titanium alloys for aerospace applications10.1007/s11665-022-07128-1 ↗
13. High-strength titanium alloys for aerospace engineering applications: a review on melting-forging process10.1016/j.msea.2022.143260 ↗
14. A review on additive manufacturing of titanium alloys for aerospace applications: directed energy deposition and beyond Ti-6Al-4V10.1007/s11837-021-04670-6 ↗
15. Comprehensive review on alloy design, processing, and performance ofβTitanium alloys as biomedical materials10.1080/09506608.2020.1735829 ↗
16. Role of Ta in improving corrosion resistance of titanium alloys under highly reducing condition10.1016/j.jmrt.2023.02.158 ↗
17. Effect of Y Content on precipitation behavior, oxidation and mechanical properties of as-cast high-temperature titanium alloys10.3390/ma16134784 ↗
18. Nickel hydrogen gas batteries: from aerospace to grid-scale energy storage applications
19. Performance of painted and non-painted non-woven nickel-coated carbon fibers for lightning strike protection of composite aircraft
20. A comparative study on the performance of nickel-based technologies for lightning strike protection of composite aircraft
21. Surface integrity of conventional and additively manufactured nickel superalloys: a review
22. Song · 2020
23. Joining of lightweight sandwich sheets to aluminium using self-pierce riveting10.1016/j.matdes.2006.08.003 ↗
24. Research on hub lightweight based on lightweight materials10.1088/1757-899X/677/2/022076 ↗
25. Energy consumption of lightweight to passenger cars using aluminum alloy from life cycle perspective
26. Ren · 2019
27. A novel heterogeneous multi-wire indirect arc directed energy deposition for in-situ synthesis Al-Zn-Mg-Cu alloy: process, microstructure and mechanical properties
28. Molecular dynamics simulation and experimental study of tin growth in SAC lead-free microsolder joints under thermo-mechanical-electrical coupling
29. High-precision laser powder bed fusion processing of pure copper
30. WC-Co-Re cemented carbides: structure, properties and potential applications10.1016/j.ijrmhm.2018.10.001 ↗
31. Sintering of tungsten carbide cermets with an iron-based ternary alloy binder: processing and thermodynamic considerations10.1016/j.ijrmhm.2018.05.008 ↗
32. Thermal properties of cemented carbides used for metal cutting10.1016/j.ijrmhm.2022.106097 ↗
33. Cemented carbide tools and moulds for wear-resistant applications in Japan10.1016/j.ijrmhm.2023.106477 ↗
34. An investigation on eddy current pulsed thermography to detect surface cracks on the tungsten carbide matrix of polycrystalline diamond compact bit10.3390/app7040429 ↗
35. Applications of magnesium alloys for aerospace: a review10.1016/j.jma.2023.09.015 ↗
36. The potential of SLM technology for processing magnesium alloys in aerospace industry10.1007/s43452-020-00033-1 ↗
37. Recent developments in high-pressure die-cast magnesium alloys for automotive and future applications10.1016/j.jma.2022.10.001 ↗
38. Тhe use of aluminium and magnesium alloys in automotive lightweight technologies10.1007/s12206-023-0712-2 ↗
39. Rare earth permanent magnets and their place in the future economy10.1016/j.eng.2019.12.007 ↗
40. Investigation of rare earth particulate on tribological and mechanical properties of Al-6061 alloy composites for aerospace application10.1016/j.jmrt.2019.06.025 ↗
41. Effect of rare earth Ce on the microstructure and mechanical properties of 34CrNiMo6 steel for wind turbine main shaft
42. Effect of rare earth oxide additives on the performance of NiMH batteries10.1016/j.jallcom.2005.04.069 ↗
43. ImageNet classification with deep convolutional neural networks10.1145/3065386 ↗
44. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
45. Recurrent neural networks and three-point bending test on the identification of material hardening parameters10.3390/met14010084 ↗
46. Attention is all you need
47. Graph convolutional neural networks with global attention for improved materials property prediction10.1039/D0CP01474E ↗
48. Scaling deep learning for materials discovery10.1038/s41586-023-06735-9 ↗
49. Gavrikov · Visualkeras · 2020
50. Brownlee · 2023
51. Bidirectional LSTM-CRF models for sequence tagging
52. Encoding the atomic structure for machine learning in materials science
53. Trinajstic · 1983
54. Reciprocal complementary wiener numbers of non-caterpillars10.4236/am.2016.73020 ↗
55. Utilización de personajes en materiales de estudio y su vinculación con las carreras de Informática y la escuela media
56. Introduction to graph theory
57. Molecular fluorescence, principles and applications
58. Todeschini · 2009 · 1257
59. Universal fragment descriptors for predicting properties of inorganic crystals10.1038/ncomms15679 ↗
60. Identify crystal structures by a new paradigm based on graph theory for building materials big data10.1007/s11426-019-9502-5 ↗
61. Applying machine learning techniques to predict the properties of energetic materials10.1038/s41598-018-27344-x ↗
62. Rupp · 2011
63. Assessment and validation of machine learning methods for predicting molecular atomization energies10.1021/ct400195d ↗
64. Machine learning predictions of molecular properties: accurate many-body potentials and nonlocality in chemical space10.1021/acs.jpclett.5b00831 ↗
65. A survey of quantitative descriptions of molecular structure
66. Topology-based machine learning strategy for cluster structure prediction10.1021/acs.jpclett.0c00974 ↗
67. Quantifying similarity of pore-geometry in nanoporous materials
68. Unsupervised discovery of solid-state lithium ion conductors10.1038/s41467-019-13214-1 ↗
69. Vaswani · 2017
70. Understanding LSTM -- a tutorial into long short-term memory recurrent
71. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties10.1103/PhysRevLett.120.145301 ↗
72. Graph networks as a universal machine learning framework for molecules and crystals
73. Predicting elastic modulus of porous La0.6Sr0.4Co0.2Fe0.8O3-δ cathodes from microstructures via FEM and deep learning10.1016/j.ijhydene.2021.04.033 ↗
74. Enhanced structural integrity of Laser Powder Bed Fusion based AlSi10Mg parts by attaining defect free melt pool formations10.1038/s41598-023-43718-2 ↗
75. Laser powder bed fusion of Ti-6Al-2Sn-4Zr-6Mo alloy and properties prediction using deep learning approaches10.3390/ma14082056 ↗
76. Experimental investigation and development of a deep learning framework to predict process-induced surface roughness in additively manufactured aluminum alloys10.1007/s40194-022-01445-8 ↗
77. Phase formation prediction of high-entropy alloys: a deep learning study10.1016/j.jmrt.2022.01.172 ↗
78. Machine learning for phase selection in multi-principal element alloys10.1016/j.commatsci.2018.04.003 ↗
79. Deep learning-based phase prediction of high-entropy alloys: optimization, generation, and explanation
80. Measurement and calculation of surface tension for undercooled liquid nickel and its alloy10.1063/1.3187793 ↗
81. Machine learning enhanced empirical potentials for metals and alloys10.1016/j.cpc.2021.108132 ↗
82. Atom-centered symmetry functions for constructing high-dimensional neural network potentials
83. Tutorial: deep learning prediction of thermophysical properties for liquid multicomponent alloys10.1063/5.0173250 ↗
84. Physical metallurgy guided deep learning for yield strength of hot-rolled steel based on the small labeled dataset
85. Deep learning model for predicting hardness distribution in laser heat treatment of AISI H13 tool steel10.1016/j.applthermaleng.2019.01.050 ↗
86. Feature extraction and microstructural classification of hot stamping ultra-high strength steel by machine learning10.1007/s11837-022-05265-5 ↗
87. A detailed study of convolutional neural networks for the identification of microstructure
88. Leveraging EBSD data by deep learning for bainite, ferrite and martensite segmentation
89. A generic high-throughput microstructure classification and quantification method for regular SEM images of complex steel microstructures combining EBSD labeling and deep learning
90. Deep Learning for automated phase segmentation in EBSD maps
91. Automated classification of big X-ray diffraction data using deep learning models10.1038/s41524-023-01164-8 ↗
92. Deep learning for visualization and novelty detection in large X-ray diffraction datasets10.1038/s41524-021-00575-9 ↗
93. Wang, S., et al., Deep learning accelerated determination of hydride locations in metal nanoclusters. Angew. Chem.. 60(22)..10.1002/anie.202100407 ↗
94. Adaptively driven X-ray diffraction guided by machine learning for autonomous phase identification10.1038/s41524-023-00984-y ↗
95. Deep learning for visualization and novelty detection in large X-ray diffraction datasets
96. Liu · 2020
97. DeepXRD, a deep learning model for predicting XRD spectrum from material composition10.1021/acsami.2c05812 ↗
98. A deep learning approach to powder X‐ray diffraction pattern analysis: addressing generalizability and perturbation issues simultaneously10.1002/aisy.202300140 ↗
99. Experimental investigation of material properties of Al-Sic-fly ash composite
100. Real-time prediction and adaptive adjustment of continuous casting based on deep learning10.1038/s44172-023-00084-1 ↗