Development of a Neuroevolution Machine Learning Potential of Al-Cu-Li Alloys
Abstract
:1. Introduction
2. Material and Methods
3. Construction of the NEP for Al-Cu-Li Alloys
3.1. The Main Process of Constructing the NEP
- Sampling structures. For multicomponent alloys, obtaining atomic configurations corresponding to various compositions and atomic ratios is essential. These configurations can be acquired by performing AIMD simulations with variations in composition, temperature, and pressure, followed by equidistant sampling. Alternatively, structural perturbations can also generate additional configurations. Another important sampling method involves retrieving possible structures of the target system from databases, such as the Materials Project. This step is critical for determining whether the NEP potential function can accurately predict the behavior of the target alloy system. The more the collected structures comprehensively cover the potential scenarios of interest, the more accurate the subsequent MD simulations using the NEP function will be. The specific methodology is as follows: (i) AIMD simulations were performed using VASP to sample structures. AIMD simulations for Al-Cu-Li alloys were conducted over a temperature range of 50 K to 2000 K. The initial structures were generally 3 × 3 × 3 face-centered cubic supercells, with compositions (atomic ratios) including pure Al, Cu, and Li, as well as alloys such as Al25Cu50Li25, Al50Cu25Li25, Al50Cu50, Al50Li50, Al95Cu4Li1, and Cu50Li50. The temperature range extended from 50 K to 2000 K, and the pressure conditions included ambient pressure and 10 GPa. (ii) Structures of elemental Al, Cu, and Li, as well as any compounds of these elements, were downloaded from the Materials Project database.
- DFT static calculation. The static DFT calculations were performed with the following parameters: KSPACING = 0.2, ENCUT = 600 eV, EDIFF = 1 × 10−6 eV, ISMEAR = 0, and SIGMA = 0.02. Subsequently, the selected training set structures were uniformly subjected to DFT calculations, and the results were compiled into a training dataset file. This step is the most computationally intensive part of the potential function process, typically accounting for approximately 70% of the total computation.
- Training and validation of the potential function. The data obtained from all the structural calculations in the previous step are organized to create a training set. This set is then used to train the potential function, which is subsequently validated by comparing its results with those from DFT calculations. The accuracy of the potential function is assessed using the root-mean-square error (RMSE) of the energy, force, and potential force.
3.2. Construction of Al-Cu-Li Ternary Alloy Dataset
3.3. Principle of the NEP Model
4. Validation of NEP for Al-Cu-Li Alloys
5. MD Simulation Results and Experimental Validation of Al-Cu-Li Alloys Based on NEP Function
5.1. Dislocation Defect-Induced Inhomogeneous Precipitation
5.2. Dissolution and Secondary Precipitation of the T1 Precipitation Phase
6. Conclusions
- (1)
- Enhance model generalizability and accuracy. By incorporating data with varied chemical compositions and structural morphologies, the model can be adapted to a wider range of alternative alloy systems. Additionally, exploring more advanced neural network architectures, such as graph convolutional networks (GCNs), could help capture complex inter-atomic interactions and further improve prediction accuracy.
- (2)
- Improve training efficiency and data quality. Evolutionary algorithms, such as genetic algorithms and Bayesian optimization, can be employed to intelligently select training data, thus improving model training efficiency. Furthermore, data augmentation techniques (e.g., perturbing atomic positions or simulating structures under different environments) can be introduced during the training process to enhance data diversity, thereby improving the model’s generalization ability.
- (3)
- Enable multi-scale simulation. Combining NEP with coarse-grained models or finite element methods can facilitate multi-scale coupling calculations, providing a more comprehensive simulation of alloy behavior in practical applications.
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Rioja, R.J.; Liu, J. The evolution of Al-Li base products for aerospace and space applications. Metall. Mater. Trans. A 2012, 43, 3325–3337. [Google Scholar] [CrossRef]
- Chinh, N.Q.; Murashkin, M.Y.; Bobruk, E.V.; Lábár, J.L.; Gubicza, J.; Kovács, Z.; Ahmed, A.Q.; Maier-Kiener, V.; Valiev, R.Z. Ultralow-temperature superplasticity and its novel mechanism in ultrafine-grained Al alloys. Mater. Res. Lett. 2021, 9, 475–482. [Google Scholar] [CrossRef]
- Wang, F.; Li, Y.; Chen, X.; Zhao, H.; Yaqoob, K.; Du, Y.; Wang, Z.; Song, M. Superior strength–ductility combination in Al alloys via dislocation gradient structure. Mater. Res. Lett. 2023, 11, 347–353. [Google Scholar] [CrossRef]
- Li, Y.; Li, H.; Katgerman, L.; Du, Q.; Zhang, J.; Zhuang, L. Recent advances in hot tearing during casting of aluminium alloys. Prog. Mater. Sci. 2021, 117, 100741. [Google Scholar] [CrossRef]
- Zhao, R.; Wang, S.; Kong, Z.; Xu, Y.; Fu, K.; Peng, P.; Wu, C. Development of a neuroevolution machine learning potential of Pd-Cu-Ni-P alloys. Mater. Des. 2023, 231, 112012. [Google Scholar] [CrossRef]
- Unke, O.T.; Chmiela, S.; Sauceda, H.E.; Gastegger, M.; Poltavsky, I.; Schutt, K.T.; Tkatchenko, A.; Muller, K.R. Machine learning force fields. Chem. Rev. 2021, 121, 10142–10186. [Google Scholar] [CrossRef]
- Liu, Y.; Mo, Y. Assessing the accuracy of machine learning interatomic potentials in predicting the elemental orderings: A case study of Li-Al alloys. Acta Mater. 2024, 268, 119742. [Google Scholar] [CrossRef]
- Mishin, Y. Machine-learning interatomic potentials for materials science. Acta Mater. 2021, 214, 116980. [Google Scholar] [CrossRef]
- Fedik, N.; Zubatyuk, R.; Kulichenko, M.; Lubbers, N.; Smith, J.S.; Nebgen, B.; Messerly, R.; Li, Y.W.; Boldyrev, A.I.; Barros, K.; et al. Extending machine learning beyond interatomic potentials for predicting molecular properties. Nat. Rev. Chem. 2022, 6, 653–672. [Google Scholar] [CrossRef]
- Zuo, Y.; Chen, C.; Li, X.; Deng, Z.; Chen, Y.; Behler, J.; Csányi, G.; Shapeev, A.V.; Thompson, A.P.; Wood, M.A.; et al. Performance and cost assessment of machine learning interatomic potentials. J. Phys. Chem. A 2020, 124, 731–745. [Google Scholar] [CrossRef]
- Deringer, V.L.; Csányi, G. Machine learning based interatomic potential for amorphous carbon. Phys. Rev. B 2017, 95, 094203. [Google Scholar] [CrossRef]
- Li, X.-G.; Hu, C.; Chen, C.; Deng, Z.; Luo, J.; Ong, S.P. Quantum-accurate spectral neighbor analysis potential models for Ni-Mo binary alloys and fcc metals. Phys. Rev. B 2018, 98, 094104. [Google Scholar] [CrossRef]
- Mortazavi, B.; Silani, M.; Podryabinkin, E.V.; Rabczuk, T.; Zhuang, X.; Shapeev, A.V. First-principles multiscale modeling of mechanical properties in graphene/borophene heterostructures empowered by machine-learning interatomic potentials. Adv. Mater. 2021, 33, 2102807. [Google Scholar] [CrossRef] [PubMed]
- Zhang, L.; Han, J.; Wang, H.; Car, R.E.W. Deep potential molecular dynamics: A scalable model with the accuracy of quantum mechanics. Phys. Rev. Lett. 2018, 120, 143001. [Google Scholar] [CrossRef]
- Wang, X.; Wang, Y.; Wang, J.; Pan, S.; Lu, Q.; Wang, H.T.; Xing, D.; Sun, J. Pressure stabilized lithium-aluminum compounds with both superconducting and superionic behaviors. Phys. Rev. Lett. 2022, 129, 246403. [Google Scholar] [CrossRef]
- Ying, P.; Dong, H.; Liang, T.; Fan, Z.; Zhong, Z.; Zhang, J. Atomistic insights into the mechanical anisotropy and fragility of monolayer fullerene networks using quantum mechanical calculations and machine-learning molecular dynamics simulations. Extrem. Mech. Lett. 2023, 58, 101929. [Google Scholar] [CrossRef]
- Ying, P.; Dong, H.; Liang, T.; Fan, Z.; Zhong, Z.; Zhang, J. Anisotropic and high thermal conductivity in monolayer quasi-hexagonal fullerene: A comparative study against bulk phase fullerene. Int. J. Heat Mass Transf. 2023, 206, 123943. [Google Scholar]
- Xie, Y.; Bu, M.; Lu, G. Local structure and thermophysical property prediction for CaCl2-KCl molten salt with machine learning potentials. Mater. Today Commun. 2024, 41, 110243. [Google Scholar] [CrossRef]
- Wang, S.; Zhang, C.; Li, X.; Huang, H.; Wang, J. First-principle investigation on the interfacial structure evolution of the δ’/θ’/δ’ composite precipitates in Al-Cu-Li alloys. J. Mater. Sci. Technol. 2020, 58, 205–214. [Google Scholar] [CrossRef]
- Fan, Z.; Wang, Y.; Ying, P.; Song, K.; Wang, J.; Wang, Y.; Zeng, Z.; Xu, K.; Lindgren, E.; Rahm, J.M.; et al. GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations. J. Chem. Phys. 2022, 157, 114801. [Google Scholar] [CrossRef]
- Fan, Z.; Chen, W.; Vierimaa, V.; Harju, A. Efficient molecular dynamics simulations with many-body potentials on graphics processing units. Comput. Phys. Commun. 2017, 218, 10–16. [Google Scholar] [CrossRef]
- Thompson, A.P.; Aktulga, H.M.; Berger, R.; Bolintineanu, D.S.; Brown, W.M.; Crozier, P.S.; In’t Veld, P.J.; Kohlmeyer, A.; Moore, S.G.; Nguyen, T.D.; et al. LAMMPS-a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales. Comput. Phys. Commun. 2022, 271, 108171. [Google Scholar] [CrossRef]
- Stukowski, A. Visualization and analysis of atomistic simulation data with OVITO—The Open Visualization Tool. Model. Simul. Mater. Sci. Eng. 2009, 18, 015012. [Google Scholar] [CrossRef]
- Fan, Z.; Wang, Y.; Ying, P.; Song, K.; Wang, J.; Wang, Y.; Zeng, Z.; Xu, K.; Lindgren, E.; Rahm, J.M.; et al. Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport. Phys. Rev. B 2021, 104, 104309. [Google Scholar] [CrossRef]
- Fan, Z. Improving the accuracy of the neuroevolution machine learning potential for multi-component systems. J. Phys. Condens. Matter 2022, 34, 125902. [Google Scholar] [CrossRef]
- Mao, A.; Xiang, H.; Ran, X.; Li, Y.; Jin, X.; Yu, H.; Gu, X. Plasma arc discharge synthesis of multicomponent Co-Cr-Cu-Fe-Ni nanoparticles. J. Alloys Compd. 2019, 775, 1177–1183. [Google Scholar] [CrossRef]
- Araullo-Peters, V.; Gault, B.; De Geuser, F.; Deschamps, A.; Cairney, J.M. Microstructural evolution during ageing of Al–Cu–Li–x alloys. Acta Mater. 2014, 66, 199–208. [Google Scholar] [CrossRef]
- Cassada, W.A.; Shiflet, G.J.; Starke, E.A. The effect of plastic deformation on Al2CuLi(T1) precipitation. Metall. Trans. A 1991, 22, 299–306. [Google Scholar] [CrossRef]
- Ringer, S.P.; Muddle, B.C.; Polmear, I.J. Effects of cold work on precipitation in Al-Cu-Mg-(Ag) and Al-Cu-Li-(Mg-Ag) alloys. Metall. Mater. Trans. A 1995, 26, 1659–1671. [Google Scholar] [CrossRef]
- Gable, B.M.; Zhu, A.W.; Csontos, A.A.; Starke, E.A., Jr. The role of plastic deformation on the competitive microstructural evolution and mechanical properties of a novel Al–Li–Cu–X alloy. J. Light Met. 2001, 1, 1–14. [Google Scholar] [CrossRef]
- Rodgers, B.I.; Prangnell, P.B. Quantification of the influence of increased pre-stretching on microstructure-strength relationships in the Al–Cu–Li alloy AA2195. Acta Mater. 2016, 108, 55–67. [Google Scholar] [CrossRef]
- Decreus, B.; Deschamps, A.; De Geuser, F.; Donnadieu, P.; Sigli, C.; Weyland, M. The influence of Cu/Li ratio on precipitation in Al–Cu–Li–x alloys. Acta Mater. 2013, 61, 2207–2218. [Google Scholar] [CrossRef]
- Donnadieu, P.; Shao, Y.; De Geuser, F.; Botton, G.A.; Lazar, S.; Cheynet, M.; De Boissieu, M.; Deschamps, A. Atomic structure of T1 precipitates in Al–Li–Cu alloys revisited with HAADF-STEM imaging and small-angle X-ray scattering. Acta Mater. 2011, 59, 462–472. [Google Scholar] [CrossRef]
- Dorin, T.; Deschamps, A.; De Geuser, F.; Lefebvre, W.; Sigli, C. Quantitative description of the T1 formation kinetics in an Al–Cu–Li alloy using differential scanning calorimetry, small-angle X-ray scattering and transmission electron microscopy. Philos. Mag. 2014, 94, 1012–1030. [Google Scholar] [CrossRef]
- Prasad, K.S.; Prasad, N.E.; Gokhale, A.A. Microstructure and precipitate characteristics of aluminum–lithium alloys. In Aluminium-Lithium Alloys; Elsevier: Amsterdam, The Netherlands, 2014; pp. 99–137. [Google Scholar] [CrossRef]
- Kang, S.B.; Lim, C.Y.; Kim, H.W.; Mao, J.F. Microstructure evolution and hardening behavior of 2024 aluminum alloy processed by the severe plastic deformation. In Materials Science Forum; Trans Tech Publications Ltd.: Zurich, Switzerland, 2002; Volume 396, pp. 1163–1168. [Google Scholar]
- Oh-Ishi, K.; Hashi, Y.; Sadakata, A.; Kaneko, K.; Horita, Z.; Langdon, T.G. Microstructural control of an Al-Mg-Si alloy using equal-channel angular pressing. In Materials Science Forum; Trans Tech Publications Ltd.: Zurich, Switzerland, 2002; Volume 396, pp. 333–338. [Google Scholar]
- Berbon, P.B.; Furukawa, M.; Horita, Z.; Nemoto, M.; Langdon, T.G. Influence of pressing speed on microstructural development in equal-channel angular pressing. Metall. Mater. Trans. A 1999, 30, 1989–1997. [Google Scholar] [CrossRef]
- Zhu, Y.T.; Lowe, T.C.; Langdon, T.G. Performance and applications of nanostructured materials produced by severe plastic deformation. Scr. Mater. 2004, 51, 825–830. [Google Scholar] [CrossRef]
Composition (%) | Cu | Li | Mn | Zr | Mg | Fe | Si | Al |
2.8 | 1.4 | 0.3 | 0.1 | 0.03 | 0.04 | 0.02 | Bal. |
Step | Temperature (°C) | Load/N | Time/Min |
---|---|---|---|
1 | 35 | 200 | 2 |
2 | 35 | 5 | |
3 | 155/210/260 | 18 × 60 | |
4 | 50 | 2 | |
5 | 50 | 200 | 2 |
Boundary Condition | Parameters |
---|---|
periodic boundary condition (X, Y, Z) | P, P, P (P: periodic boundary condition) |
simulated pressure | 220 MPa |
simulated temperature | 90, 155, 210, 260 °C |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Chen, F.; Wang, H.; Jiang, Y.; Zhan, L.; Yang, Y. Development of a Neuroevolution Machine Learning Potential of Al-Cu-Li Alloys. Metals 2025, 15, 48. https://doi.org/10.3390/met15010048
Chen F, Wang H, Jiang Y, Zhan L, Yang Y. Development of a Neuroevolution Machine Learning Potential of Al-Cu-Li Alloys. Metals. 2025; 15(1):48. https://doi.org/10.3390/met15010048
Chicago/Turabian StyleChen, Fei, Han Wang, Yanan Jiang, Lihua Zhan, and Youliang Yang. 2025. "Development of a Neuroevolution Machine Learning Potential of Al-Cu-Li Alloys" Metals 15, no. 1: 48. https://doi.org/10.3390/met15010048
APA StyleChen, F., Wang, H., Jiang, Y., Zhan, L., & Yang, Y. (2025). Development of a Neuroevolution Machine Learning Potential of Al-Cu-Li Alloys. Metals, 15(1), 48. https://doi.org/10.3390/met15010048