Composition driven machine learning for unearthing high-strength lightweight multi-principal element alloys
Source abstract
Abstract
High-strength, lightweight alloys are highly desired in the aerospace, automotive and marine industries. The optimization of such alloys is a multifaceted process, characterized by the consideration of diverse objectives and constraints. Various optimization methodologies exist, spanning from intricate first-principle approaches to the application of sophisticated machine learning algorithms. These algorithms might incorporate input features encompassing elemental composition, microstructural attributes, and thermodynamic properties to enhance prediction accuracies. In this work, we aim to streamline this complexity by employing solely the alloy`s elemental composition as the input feature for the machine learning algorithm, improving the hardness while reducing the density of the alloy. We have curated a comprehensive database comprising 544 multi-principal element alloys and developed a robust surrogate model based on these compositions. This composition-driven model is subsequently coupled with principal component analysis (PCA) to facilitate the selection process. Remarkably, through a mere three iterations involving 14 samples, we successfully identified an alloy with an effective specific hardness surpassing the training database maximum by 8.6 %. The proposed composition-driven machine learning delineates a simplified approach for conducting optimization across multiple target material properties.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: High Entropy Alloys Studies · Additive Manufacturing Materials and Processes · Advanced materials and composites
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (59)
Show source-provided references
1. Nanostructured high-entropy alloys with multiple principal elements: novel alloy design concepts and outcomes10.1002/adem.200300567 ↗
2. Microstructural development in equiatomic multicomponent alloys10.1016/j.msea.2003.10.257 ↗
3. Corrosion characteristics of high entropy alloys10.1179/1743284715Y.0000000026 ↗
4. Corrosion of high entropy alloys10.1038/s41529-017-0009-y ↗
5. Passivation of a corrosion resistant high entropy alloy in non-oxidizing sulfate solutions10.1016/j.actamat.2018.10.026 ↗
6. Metastable high-entropy dual-phase alloys overcome the strength–ductility trade-off10.1038/nature17981 ↗
7. Microstructural evolution, electrochemical and corrosion properties of AlxCoCrFeNiTiy high entropy alloys10.1016/j.matdes.2019.107698 ↗
8. Expanded dataset of mechanical properties and observed phases of multi-principal element alloys10.1038/s41597-020-00768-9 ↗
9. Materials informatics for the screening of multi-principal elements and high-entropy alloys10.1038/s41467-019-10533-1 ↗
10. Machine-learning phase prediction of high-entropy alloys10.1016/j.actamat.2019.03.012 ↗
11. Machine learning-based inverse design for single-phase high entropy alloys10.1063/5.0109491 ↗
12. Artificial neural network approach for microhardness prediction of eight component FeCoNiCrMnVAlNb eutectic high entropy alloys10.1016/j.msea.2020.140059 ↗
13. Prediction of the composition and hardness of high-entropy alloys by machine learning10.1007/s11837-019-03704-4 ↗
14. Modelling and prediction of hardness in multi-component alloys: a combined machine learning, first principles and experimental study10.1016/j.jallcom.2020.156959 ↗
15. A machine learning-based alloy design system to facilitate the rational design of high entropy alloys with enhanced hardness10.1016/j.actamat.2021.117431 ↗
16. Artificial neural network approach to predict the mechanical properties of Cu–Sn–Pb–Zn–Ni cast alloys10.1016/j.matdes.2008.05.019 ↗
17. First-principles and machine learning predictions of elasticity in severely lattice-distorted high-entropy alloys with experimental validation10.1016/j.actamat.2019.09.026 ↗
18. Machine learning-assisted optimization of multi-metal hydroxide electrocatalysts for overall water splitting10.1039/D3MH00788J ↗
19. Solid-solution phase formation rules for multi-component alloys10.1002/adem.200700240 ↗
20. Machine learning assisted modelling and design of solid solution hardened high entropy alloys10.1016/j.matdes.2021.110177 ↗
21. Machine learning assisted design of high entropy alloys with desired property10.1016/j.actamat.2019.03.010 ↗
22. High-throughput design of high-performance lightweight high-entropy alloys10.1038/s41467-021-24523-9 ↗
23. Microstructure exploration and an artificial neural network approach for hardness prediction in AlCrFeMnNiWx High-Entropy Alloys10.1016/j.jallcom.2020.153766 ↗
24. Computational design of light and strong high entropy alloys (HEA): obtainment of an extremely high specific solid solution hardening10.1016/j.scriptamat.2018.07.024 ↗
25. Machine learning assisted composition effective design for precipitation strengthened copper alloys10.1016/j.actamat.2021.117118 ↗
26. Taking the human out of the loop: a review of bayesian optimization10.1109/JPROC.2015.2494218 ↗
27. Rasmussen · 2006
28. Mapping pareto fronts for efficient multi-objective materials discovery10.20517/jmi.2023.02 ↗
29. J. Wu, S. Toscano-Palmerin, P. Frazier, A. Wilson, Practical Multi-fidelity Bayesian Optimization for Hyperparameter Tuning, 35th Conference on Uncertainty in Artificial Intelligence, UAI 2019, 2019.
30. Parallel bayesian optimization of multiple noisy objectives with expected hypervolume improvement
31. L. Andre KY, M.-B. Flore, O. Aleksandr, X. Jiaxun, V.-G. Eleonore, L. Yee-Fun, G. Abhishek, L. Qianxiao, O. Yew Soon, K. Saif A, H. Kedar, Evolution-guided Bayesian optimization for constrained multi-objective optimization in self-driving labs, ChemRxiv (2023).
32. Database on the mechanical properties of high entropy alloys and complex concentrated alloys10.1016/j.dib.2018.11.111 ↗
33. Progress of artificial neural networks applications in hydrogen production10.1016/j.cherd.2022.03.030 ↗
34. Do machine learning platforms provide out-of-the-box reproducibility?10.1016/j.future.2021.06.014 ↗
35. Dietterich · 2000 · 1
36. Neural Networks
37. B. Charles, C. Julien, K. Koray, W. Daan, Weight Uncertainty in Neural Network, PMLR, pp. 1613-1622.
38. Parallelizing exploration-exploitation tradeoffs in gaussian process bandit optimization
39. A taxonomy of global optimization methods based on response surfaces10.1023/A:1012771025575 ↗
40. P.I. Frazier, A Tutorial on Bayesian Optimization, 2018, p. arXiv:1807.02811.10.1287/educ.2018.0188 ↗
41. Principal components analysis and partial least squares regression10.1016/0898-5529(89)90004-3 ↗
42. Reinforcement learning: a10.1613/jair.301 ↗
43. M. Ali, PyCaret: An open source, low-code machine learning library in Python, 2020.
44. Extrapolative bayesian optimization with gaussian process and neural network ensemble surrogate models10.1002/aisy.202170077 ↗
45. G. Louppe, M. Kumar, Bayesian optimization with skopt. https://scikit-optimize.github.io/stable/auto_examples/bayesian-optimization.html, 2016).
46. Enhanced hardness and fracture toughness of the laser-solidified FeCoNiCrCuTiMoAlSiB0.5 high-entropy alloy by martensite strengthening10.1016/j.scriptamat.2013.05.020 ↗
47. S.M. Lundberg, S.-I. Lee, A Unified Approach to Interpreting Model Predictions, in: I. Guyon, U.V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, R. Garnett (Eds.) Curran Associates, Inc., 2017.
48. Aluminium alloys as structural material: a review of research10.1016/j.engstruct.2020.111372 ↗
49. Titanium alloys and their machinability—a review10.1016/S0924-0136(96)00030-1 ↗
50. Vanadium is an optimal element for strengthening in both fcc and bcc high-entropy alloys10.1016/j.actamat.2020.01.062 ↗
51. Al-Fe-Ti (aluminum-iron-titanium)10.1361/105497102770331613 ↗
52. Structural transition with loss of symmetry in Ti–M–Al based G-phases (MFe and Co)10.1016/j.intermet.2005.12.001 ↗
53. The Al–Cr–Fe system–phases and phase equilibria in the Al-rich corner10.1016/S0925-8388(96)02719-3 ↗
54. The Fe-A1-Ti system10.1007/BF02667305 ↗
55. Characterization of the Fe-rich corner of Al–Fe–Si–Ti10.1016/j.intermet.2013.03.007 ↗
56. Structure and properties of Fe–Al–Ti intermetallic alloys10.1016/S0966-9795(00)00101-1 ↗
57. Assessment of the Al–Fe–Ti system10.1016/j.intermet.2005.11.026 ↗
58. Tribo-oxidation of Ti-Al-Fe and Ti-Al-Mn cladding layers obtained by non-vacuum electron beam treatment10.1016/j.surfcoat.2021.127442 ↗
59. Deformation behaviour and oxidation resistance of single-phase and two-phase L21-ordered Fe–Al–Ti alloys10.1016/j.intermet.2004.03.017 ↗