×

Recommended by

Indexed by

Machine learning potential for the Cu-W system

Manura Liyanage1*, Vladyslav Turlo1*, W. A. Curtin2,3*

1 Laboratory for Advanced Materials Processing, Empa - Swiss Federal Laboratories for Materials Science and Technology, Thun, Switzerland

2 National Centre for Computational Design and Discovery of Novel Materials MARVEL, Ecole Polytechnique Federale de Lausanne, CH-1015 Lausanne, Switzerland

3 School of Engineering, Brown University, Providence, RI 02906 USA

* Corresponding authors emails: pandula.liyanage@epfl.ch, vladyslav.turlo@empa.ch, william.curtin@epfl.ch
DOI10.24435/materialscloud:1m-0s [version v1]

Publication date: Jul 18, 2024

How to cite this record

Manura Liyanage, Vladyslav Turlo, W. A. Curtin, Machine learning potential for the Cu-W system, Materials Cloud Archive 2024.107 (2024), https://doi.org/10.24435/materialscloud:1m-0s

Description

Combining the excellent thermal and electrical properties of Cu with the high abrasion resistance and thermal stability of W, Cu-W nanoparticle-reinforced metal matrix composites and nano-multilayers (NMLs) are finding applications as brazing fillers and shielding material for plasma and radiation. Due to the large lattice mismatch between fcc Cu and bcc W, these systems have complex interfaces that are beyond the scales suitable for ab initio methods, thus motivating the development of chemically accurate interatomic potentials. Here, a neural network potential (NNP) for Cu-W is developed within the Behler-Parrinello framework using a curated training dataset that captures metallurgically-relevant local atomic environments. The Cu-W NNP accurately predicts (i) the metallurgical properties (elasticity, stacking faults, dislocations, thermodynamic behavior) in elemental Cu and W, (ii) energies and structures of Cu-W intermetallics and solid solutions, and (iii) a range of fcc Cu/bcc W interfaces, and exhibits physically-reasonable behavior for solid W/liquid Cu systems. As will be demonstrated in forthcoming work, this near-ab initio-accurate NNP can be applied to understand complex phenomena involving interface-driven processes and properties in Cu-W composites.

Materials Cloud sections using this data

No Explore or Discover sections associated with this archive record.

Files

File name Size Description
CuW_reference_dataset_Quantun_ESPRESSO.zip
MD5md5:948fd4a817d75606c25f5930d27f978a
4.6 GiB Reference structures used in developing the NNP
NNP_potentials_01-20.zip
MD5md5:bfaf300c9ebf9bbef9e2431b79bf79cb
1.0 MiB All neural network potentials developed in this study
README.txt
MD5md5:a595b8d521ae35b4bff6123fe4253a7b
2.6 KiB Descriptions of the data

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

Journal reference (The development and the validation of the neural network potentoal developed with the provided dataset is presented in the paper)

Keywords

Nanomultilayer Neural network potentials Copper-tungsten MARVEL molecular dynamics simulation

Version history:

2024.107 (version v1) [This version] Jul 18, 2024 DOI10.24435/materialscloud:1m-0s