Exhaustive search for novel multicomponent alloys with brute force and machine learning

Abstract We present an algorithm for the high-throughput computational discovery of intermetallic compounds in systems with a large number of components. It is particularly important for high entropy alloys (HEAs), where multiple principal elements can form numerous potential intermetallic compounds...

Full description

Saved in:
Bibliographic Details
Main Authors: Viktoriia Zinkovich, Vadim Sotskov, Alexander Shapeev, Evgeny Podryabinkin
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:npj Computational Materials
Online Access:https://doi.org/10.1038/s41524-024-01452-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849221101050134528
author Viktoriia Zinkovich
Vadim Sotskov
Alexander Shapeev
Evgeny Podryabinkin
author_facet Viktoriia Zinkovich
Vadim Sotskov
Alexander Shapeev
Evgeny Podryabinkin
author_sort Viktoriia Zinkovich
collection DOAJ
description Abstract We present an algorithm for the high-throughput computational discovery of intermetallic compounds in systems with a large number of components. It is particularly important for high entropy alloys (HEAs), where multiple principal elements can form numerous potential intermetallic compounds during the condensation process, making it challenging to predict the dominant phase. Our algorithm is based on a brute-force evaluation of candidate structures with a fixed underlying lattice (FCC or BCC) accelerated by machine-learning interatomic potentials. The algorithm takes a set of chemical elements and a crystal lattice type as inputs and produces structures on and near the convex hull of thermodynamically stable structures. The candidate structures are evaluated using the low-rank potential (LRP), trained to reproduce energies of structures equilibrated with density functional theory (DFT). Thanks to extreme computational effectiveness of the LRP, it is feasible to evaluate hundreds of thousands of structures per second, per CPU core. Thus, our algorithm screens a complete set of candidate structures for a given system without missing any configurations. We validated our method on systems with BCC (Nb-W, Nb-Mo-W, V-Nb-Mo-Ta-W) and FCC (Cu-Pt, Cu-Pd-Pt, Cu-Pd-Ag-Pt-Au) lattices and discovered 268 new alloys not reported in the AFLOW database1, which we used as a benchmark.
format Article
id doaj-art-b0f0367efc264e9da90842c567d7971e
institution Kabale University
issn 2057-3960
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series npj Computational Materials
spelling doaj-art-b0f0367efc264e9da90842c567d7971e2024-11-24T12:35:36ZengNature Portfolionpj Computational Materials2057-39602024-11-011011910.1038/s41524-024-01452-xExhaustive search for novel multicomponent alloys with brute force and machine learningViktoriia Zinkovich0Vadim Sotskov1Alexander Shapeev2Evgeny Podryabinkin3Skolkovo Institute of Science and Technology, Skolkovo Innovation CenterSkolkovo Institute of Science and Technology, Skolkovo Innovation CenterSkolkovo Institute of Science and Technology, Skolkovo Innovation CenterSkolkovo Institute of Science and Technology, Skolkovo Innovation CenterAbstract We present an algorithm for the high-throughput computational discovery of intermetallic compounds in systems with a large number of components. It is particularly important for high entropy alloys (HEAs), where multiple principal elements can form numerous potential intermetallic compounds during the condensation process, making it challenging to predict the dominant phase. Our algorithm is based on a brute-force evaluation of candidate structures with a fixed underlying lattice (FCC or BCC) accelerated by machine-learning interatomic potentials. The algorithm takes a set of chemical elements and a crystal lattice type as inputs and produces structures on and near the convex hull of thermodynamically stable structures. The candidate structures are evaluated using the low-rank potential (LRP), trained to reproduce energies of structures equilibrated with density functional theory (DFT). Thanks to extreme computational effectiveness of the LRP, it is feasible to evaluate hundreds of thousands of structures per second, per CPU core. Thus, our algorithm screens a complete set of candidate structures for a given system without missing any configurations. We validated our method on systems with BCC (Nb-W, Nb-Mo-W, V-Nb-Mo-Ta-W) and FCC (Cu-Pt, Cu-Pd-Pt, Cu-Pd-Ag-Pt-Au) lattices and discovered 268 new alloys not reported in the AFLOW database1, which we used as a benchmark.https://doi.org/10.1038/s41524-024-01452-x
spellingShingle Viktoriia Zinkovich
Vadim Sotskov
Alexander Shapeev
Evgeny Podryabinkin
Exhaustive search for novel multicomponent alloys with brute force and machine learning
npj Computational Materials
title Exhaustive search for novel multicomponent alloys with brute force and machine learning
title_full Exhaustive search for novel multicomponent alloys with brute force and machine learning
title_fullStr Exhaustive search for novel multicomponent alloys with brute force and machine learning
title_full_unstemmed Exhaustive search for novel multicomponent alloys with brute force and machine learning
title_short Exhaustive search for novel multicomponent alloys with brute force and machine learning
title_sort exhaustive search for novel multicomponent alloys with brute force and machine learning
url https://doi.org/10.1038/s41524-024-01452-x
work_keys_str_mv AT viktoriiazinkovich exhaustivesearchfornovelmulticomponentalloyswithbruteforceandmachinelearning
AT vadimsotskov exhaustivesearchfornovelmulticomponentalloyswithbruteforceandmachinelearning
AT alexandershapeev exhaustivesearchfornovelmulticomponentalloyswithbruteforceandmachinelearning
AT evgenypodryabinkin exhaustivesearchfornovelmulticomponentalloyswithbruteforceandmachinelearning