Abhinav C. P. Jain^1*, Daniel Marchand^1*, Albert Glensk^1*, Michele Ceriotti^2*, W. A. Curtin^1*

1 Institute of Mechanical Engineering, École Polytechnique Fédérale de Lausanne, CH-1015, Vaud, Switzerland

2 Institute of Materials Engineering, École Polytechnique Fédérale de Lausanne, CH-1015, Vaud, Switzerland

* Corresponding authors emails: abhinav.jain@epfl.ch, daniel.marchand@epfl.ch, albert.glensk@epfl.ch, michele.ceriotti@epfl.ch, william.curtin@epfl.ch

DOI10.24435/materialscloud:k1-rv [version v1]

Publication date: Feb 09, 2021

How to cite this record

Abhinav C. P. Jain, Daniel Marchand, Albert Glensk, Michele Ceriotti, W. A. Curtin, Machine learning for metallurgy: a neural network potential for Al-Mg-Si, Materials Cloud Archive 2021.32 (2021), https://doi.org/10.24435/materialscloud:k1-rv

Description

High-strength metal alloys achieve their performance via careful control of the nucleation, growth, and kinetics of precipitation. Alloy mechanical properties are then controlled by atomic scale phenomena such as shearing of the precipitates by dislocations. Atomistic modeling to understand the operative mechanisms requires length and time scales far larger than those accessible by first-principles methods. Here, a family of Behler-Parinello neural-network potentials (NNPs) for the Al-Mg-Si system is developed to enable quantitative studies of Al-6xxx alloys. The NNP is trained on metallurgically-important quantities computed by first principles density functional theory (DFT) leading to high fidelity predictions of intermetallic compounds, elastic constants, dilute solid-solution energetics, precipitate/matrix interfaces, Al stacking fault energies, antisite defect energies, and other quantities. A preliminary examination of early-stage clustering kinetics and energetics in Al-6xxx is then made, showing the formation of low-energy Mg-Si structures and the trapping of vacancies in these clusters. The Generalized Stacking Fault Energy surfaces (GSFE) for the three prevalent β" precipitate compositions in peak-aged Al-6xxx are then computed with the NNP, and are validated by DFT computations at key points. The NNP thus shows significant transferability across structures, making it a powerful approach for chemically-accurate simulations of metallurgical phenomena in Al-Mg-Si alloys.

Materials Cloud sections using this data

Files

File name	Size	Description
Al-Mg-Si_potential.tar.gz MD5md5:a5b77951975c0bca9a9b90d50b59fb78	2.3 MiB	Al-Mg-Si NNP potentials
Al-Mg-Si_nnp_repo.tar.gz MD5md5:9cdb52764968a18d6fa2ba71e679f96c	204.8 MiB	A repository of all neural network potentials allong with training and testing data
Lammps_runs.tar.gz MD5md5:e599c8b2b6d3226e6787cec551ef5ae7	623.2 KiB	The input and output files for LAMMPS runs performed on selected clusters extracted from KMC calculations
kmc_runs.tar.gz MD5md5:ffc7908fe42198b55e790f26291bc1c6	183.1 MiB	The input and output files for 4 different off lattice KMC runs.
README.txt MD5md5:86f1a28282510a9bdef1215be104ace6	984 Bytes	README file

License

Files and data are licensed under the terms of the following license: Creative Commons Attribution 4.0 International.
Metadata, except for email addresses, are licensed under the Creative Commons Attribution Share-Alike 4.0 International license.

External references

Keywords

Aluminum Machine Learning Metallurgy MARVEL/DD2