journal article·2021-01Open access

Machine learning-assisted discovery of strong and conductive Cu alloys: Data mining from discarded experiments and physical features

Qingkun Zhao, Huiya Yang, Jiabin Liu, Haofei Zhou, Hongtao Wang, Wei Yang

Materials & Design· Volume 197

Abstract

Copper alloys with high strength and electrical conductivity are ideal candidates for a wide range of civilian and engineering applications. Traditional methods of alloy design, such as “trial and error” experiments, are costly and time-consuming, limiting the discovery of Cu alloys. Machine learning (ML)-based technology facilitates a better understanding on inter-relationships within massive experimental datasets, and shortens the development cycle of new alloy systems. Herein, we propose a method of material design based on ML to discover high-performance Cu alloys. The ML models are trained from “discarded” experimental data that show undesirable hardness and/or electrical conductivity. We constructed effective Gaussian process regression-based models successfully from limited training data by engaging additional features. The predicted Cu alloys were experimentally synthesized and characterized, exhibiting superior hardness or electrical conductivity with respect to original training data. The increase of hardness is due to precipitation of second-phase Co-Ti and Fe-Ti compounds during aging, while the rise of electrical conductivity is caused by a purification effect of the precipitates on Cu matrix. The impact of physical features on ML models was further evaluated by a genetic algorithm. Our findings suggest that ML holds great potential for developing high-performance Cu alloys.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Machine Learning in Materials Science · Hydrogen embrittlement and corrosion behaviors in metals · Advanced Materials Characterization Techniques

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

References (53)

Show source-provided references
1. Microstructure and properties of fine grained Cu-Cr-Zr alloys after termo-mechanical treatments10.1515/rams-2018-0020 ↗
2. A high strength and high electrical conductivity Cu-Cr-Zr alloy fabricated by cryorolling and intermediate aging treatment10.1016/j.msea.2016.10.087 ↗
3. Ultrafine grained copper alloy sheets having both high strength and high electric conductivity10.1016/j.matlet.2009.05.021 ↗
4. Additively manufactured hierarchical stainless steels with high strength and ductility10.1038/nmat5021 ↗
5. Tuning element distribution, structure and properties by composition in high-entropy alloys10.1038/s41586-019-1617-1 ↗
6. Extra strengthening and work hardening in gradient nanotwinned metals10.1126/science.aau1925 ↗
7. Three-dimensional high-entropy alloy–polymer composite nanolattices that overcome the strength–recoverability trade-off10.1021/acs.nanolett.8b01241 ↗
8. Modulating the prestrain history to optimize strength and ductility in CoCrFeMnNi high-entropy alloy10.1016/j.scriptamat.2019.01.012 ↗
9. Microstructure evolution of Cu–0.2Mg alloy during continuous extrusion process10.1557/jmr.2015.237 ↗
10. Microstructure and properties of Cu–2.3Fe–0.03P alloy during thermomechanical treatments10.1016/S1003-6326(15)63757-8 ↗
11. Crystallography and morphology of nanosized Cr particles in a Cu–0.2% Cr alloy10.1016/S1359-6454(99)00411-5 ↗
12. Effect of cold rolling reduction rate on mechanical properties and electrical conductivity of Cu–Ni–Si alloy prepared by temperature controlled mold continuous casting10.1016/j.msea.2019.138068 ↗
13. Mechanical alloying of high-strength copper alloys containing TiB2 and Al2O3 dispersoid particles10.1016/0956-716X(94)90267-4 ↗
14. Parameter free quantitative analysis of atom probe data by correlation functions: application to the precipitation in Al-Zn-Mg-Cu10.1016/j.scriptamat.2018.05.024 ↗
15. Age-hardening of Cu-Ti alloys
16. Microstructure evolution and quench sensitivity of Cu-10Ni-3Al-0.8Si alloy during isothermal treatment10.1557/jmr.2015.12 ↗
17. Microstructure and properties of a novel Cu-Ni-Co-Si-Mg alloy with super-high strength and conductivity10.1016/j.msea.2018.12.075 ↗
18. Machine learning properties of binary wurtzite superlattices10.1007/s10853-018-1987-z ↗
19. Representation of compounds for machine learning prediction of physical properties10.1103/PhysRevB.95.144110 ↗
20. Predicting the effective thermal conductivities of composite materials and porous media by machine learning methods10.1016/j.ijheatmasstransfer.2018.08.082 ↗
21. How to represent crystal structures for machine learning: towards fast prediction of electronic properties10.1103/PhysRevB.89.205118 ↗
22. Machine learning phase prediction of high-entropy alloys10.1016/j.actamat.2019.03.012 ↗
23. Machine learning for phase selection in multi-principle element alloys10.1016/j.commatsci.2018.04.003 ↗
24. Phase prediction in high entropy alloys with a rational selection of materials descriptors and machine learning models10.1016/j.actamat.2019.11.067 ↗
25. Machine learning assisted design of high entropy alloys with desired property10.1016/j.actamat.2019.03.010 ↗
26. Machine learning as a contributor to physics: understanding Mg alloys10.1016/j.matdes.2019.107759 ↗
27. Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel10.1016/j.actamat.2019.08.033 ↗
28. Machine learning approach for prediction and understanding of glass-forming ability10.1021/acs.jpclett.7b01046 ↗
29. A machine learning approach for engineering bulk metallic glass alloys10.1016/j.actamat.2018.08.002 ↗
30. Accelerated discovery of metallic glasses through iteration of machine learning and high-throughput experiments10.1126/sciadv.aaq1566 ↗
31. Machine learning aided study of sintered density in Cu-Al alloy10.1016/j.commatsci.2018.07.049 ↗
32. Machine learning for hierarchical predication of elastic properties in Fe-Cr-Al system10.1016/j.commatsci.2019.04.051 ↗
33. Accelerated design of novel W-free high-strength Co-base superalloys with extremely wide γ/γ’ region by machine learning and CALPHAD methods10.1016/j.actamat.2020.01.004 ↗
34. A property-oriented design strategy for high performance copper alloys via machine learning10.1038/s41524-019-0227-7 ↗
35. Rasmussen · 2006
36. Effective design space exploration of gradient nanostructured materials using active learning based surrogate models10.1016/j.matdes.2019.108085 ↗
37. Scikit-learn: machine learning in Python
38. No free lunch theorems for optimization10.1109/4235.585893 ↗
39. Principle component analysis10.1038/nmeth.4346 ↗
40. Prediction of composite microstructures stress-strain curves using convolutional neural networks10.1016/j.matdes.2020.108509 ↗
41. Kinetics analysis of precipitation in a quasi-binary Cu-1 at.% CoTi alloy10.1007/s10973-007-8551-4 ↗
42. Precipitation in Cu-rich Co-Ti ternary alloys10.1002/pssa.2211340107 ↗
43. Precipitation behavior of Cu-3.0 Ni-0.72 Si alloy10.1016/j.actamat.2018.12.047 ↗
44. Measurement of the diffusion coefficient of cobalt in copper10.1002/pssa.2210860217 ↗
45. Ultrastrong steel via minimal lattice misfit and high-density nanoprecipitation[J]10.1038/nature22032 ↗
46. Effect of boron and cerium on corrosion resistance of Cu-Fe-P alloy10.1007/s11665-016-1918-6 ↗
47. An assessment of the lattice strain in the CrMnFeCoNi high-entropy alloy10.1016/j.actamat.2016.09.032 ↗
48. Effect of lattice distortion on solid solution strengthening of BCC high-entropy alloys10.1016/j.jmst.2017.07.013 ↗
49. Studies of electrical resistivity of an annealed Cu-Fe composite10.1063/1.4803716 ↗
50. The effect of solid solution W additions on the mechanical properties of nanocrystalline Ni10.1016/S1359-6454(02)00427-5 ↗
51. Modelling solid solution hardening in high entropy alloys10.1016/j.actamat.2014.11.014 ↗
52. Effects of Al addition on structural evolution and tensile properties of the FeCoNiCrMn high-entropy alloy system10.1016/j.actamat.2013.09.037 ↗
53. Friedrich · 2006