skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

This content will become publicly available on July 22, 2021

Title: Development of interatomic potential for Al–Tb alloys using a deep neural network learning method

Abstract

An interatomic potential for the Al–Tb alloy around the composition of Al90Tb10 is developed using the deep neural network (DNN) learning method. The atomic configurations and the corresponding total potential energies and forces on each atom obtained from ab initio molecular dynamics (AIMD) simulations are collected to train a DNN model to construct the interatomic potential for the Al–Tb alloy. Here we show that the obtained DNN model can well reproduce the energies and forces calculated by AIMD simulations. Molecular dynamics (MD) simulations using the DNN interatomic potential also accurately describe the structural properties of the Al90Tb10 liquid, such as partial pair correlation functions (PPCFs) and bond angle distributions, in comparison with the results from AIMD simulations. Furthermore, the developed DNN interatomic potential predicts the formation energies of the crystalline phases of the Al–Tb system with an accuracy comparable to ab initio calculations. The structure factors of the Al90Tb10 metallic liquid and glass obtained by MD simulations using the developed DNN interatomic potential are also in good agreement with the experimental X-ray diffraction data. The development of short-range order (SRO) in the Al90Tb10 liquid and the undercooled liquid is also analyzed and three dominant SROs, i.e., Al-centered distorted icosahedron (DISICO)more » and Tb-centered ‘3661’ and ‘15551’ clusters, respectively, are identified.« less

Authors:
ORCiD logo [1];  [1];  [2];  [2];  [2]; ORCiD logo [2]
  1. Zhejiang Univ. of Technology, Hangzhou (China)
  2. Ames Lab., Ames, IA (United States); Iowa State Univ., Ames, IA (United States)
Publication Date:
Research Org.:
Ames Lab., Ames, IA (United States); Iowa State Univ., Ames, IA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES). Materials Sciences & Engineering Division; National Natural Science Foundation of China (NNSFC); Natural Science Foundation of Zhejiang Province
OSTI Identifier:
1660600
Alternate Identifier(s):
OSTI ID: 1647104
Report Number(s):
IS-J-10,306
Journal ID: ISSN 1463-9076
Grant/Contract Number:  
AC02-07CH11358; 11304279; 11104247; LY18E010007
Resource Type:
Accepted Manuscript
Journal Name:
Physical Chemistry Chemical Physics. PCCP (Print)
Additional Journal Information:
Journal Name: Physical Chemistry Chemical Physics. PCCP (Print); Journal Volume: 22; Journal Issue: 33; Journal ID: ISSN 1463-9076
Publisher:
Royal Society of Chemistry
Country of Publication:
United States
Language:
English

Citation Formats

Tang, L., Yang, Z. J., Wen, T. Q., Ho, K. M., Kramer, M. J., and Wang, C. Z. Development of interatomic potential for Al–Tb alloys using a deep neural network learning method. United States: N. p., 2020. Web. doi:10.1039/d0cp01689f.
Tang, L., Yang, Z. J., Wen, T. Q., Ho, K. M., Kramer, M. J., & Wang, C. Z. Development of interatomic potential for Al–Tb alloys using a deep neural network learning method. United States. doi:10.1039/d0cp01689f.
Tang, L., Yang, Z. J., Wen, T. Q., Ho, K. M., Kramer, M. J., and Wang, C. Z. Wed . "Development of interatomic potential for Al–Tb alloys using a deep neural network learning method". United States. doi:10.1039/d0cp01689f.
@article{osti_1660600,
title = {Development of interatomic potential for Al–Tb alloys using a deep neural network learning method},
author = {Tang, L. and Yang, Z. J. and Wen, T. Q. and Ho, K. M. and Kramer, M. J. and Wang, C. Z.},
abstractNote = {An interatomic potential for the Al–Tb alloy around the composition of Al90Tb10 is developed using the deep neural network (DNN) learning method. The atomic configurations and the corresponding total potential energies and forces on each atom obtained from ab initio molecular dynamics (AIMD) simulations are collected to train a DNN model to construct the interatomic potential for the Al–Tb alloy. Here we show that the obtained DNN model can well reproduce the energies and forces calculated by AIMD simulations. Molecular dynamics (MD) simulations using the DNN interatomic potential also accurately describe the structural properties of the Al90Tb10 liquid, such as partial pair correlation functions (PPCFs) and bond angle distributions, in comparison with the results from AIMD simulations. Furthermore, the developed DNN interatomic potential predicts the formation energies of the crystalline phases of the Al–Tb system with an accuracy comparable to ab initio calculations. The structure factors of the Al90Tb10 metallic liquid and glass obtained by MD simulations using the developed DNN interatomic potential are also in good agreement with the experimental X-ray diffraction data. The development of short-range order (SRO) in the Al90Tb10 liquid and the undercooled liquid is also analyzed and three dominant SROs, i.e., Al-centered distorted icosahedron (DISICO) and Tb-centered ‘3661’ and ‘15551’ clusters, respectively, are identified.},
doi = {10.1039/d0cp01689f},
journal = {Physical Chemistry Chemical Physics. PCCP (Print)},
number = 33,
volume = 22,
place = {United States},
year = {2020},
month = {7}
}

Journal Article:
Free Publicly Available Full Text
This content will become publicly available on July 22, 2021
Publisher's Version of Record

Save / Share:

Works referenced in this record:

Accurate force field for molybdenum by machine learning large materials data
journal, September 2017


Generalized Gradient Approximation Made Simple
journal, October 1996

  • Perdew, John P.; Burke, Kieron; Ernzerhof, Matthias
  • Physical Review Letters, Vol. 77, Issue 18, p. 3865-3868
  • DOI: 10.1103/PhysRevLett.77.3865

Unique metallic glass formability and ultra-high tensile strength in AlNiFeGd alloys
journal, February 1993


Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set
journal, July 1996


Cooling rate dependence of structural order in Al90Sm10 metallic glass
journal, July 2016

  • Sun, Yang; Zhang, Yue; Zhang, Feng
  • Journal of Applied Physics, Vol. 120, Issue 1
  • DOI: 10.1063/1.4955223

Characterization of a marginal glass former alloy solidified in gas atomized powders
journal, August 2008

  • Kalay, Y. E.; Chumbley, L. S.; Anderson, I. E.
  • Materials Science and Engineering: A, Vol. 490, Issue 1-2
  • DOI: 10.1016/j.msea.2008.02.032

Amorphous, nanoquasicrystalline and nanocrystalline alloys in Al-based systems
journal, December 1998


Etude de la structure magnetique du compose TbAl par diffraction neutronique
journal, February 1968


Neue Perowskitcarbide
journal, March 1967

  • Haschke, H.; Nowotny, H.; Benesovsky, F.
  • Monatshefte für Chemie - Chemical Monthly, Vol. 98, Issue 2
  • DOI: 10.1007/BF00899941

Rare earth-aluminium intermetallic compounds of the form RAl and R3Al2
journal, March 1965


Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set
journal, October 1996


The crystal structure of rare-earth aluminium compounds R2Al
journal, May 1971


Fast Parallel Algorithms for Short-Range Molecular Dynamics
journal, March 1995


Local chemical and topological order in Al–Tb and its role in controlling nanocrystal formation
journal, February 2012


Structural analysis of R2Ni17−xAlx intermetallic compounds
journal, May 1985


Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
journal, July 2013

  • Jain, Anubhav; Ong, Shyue Ping; Hautier, Geoffroy
  • APL Materials, Vol. 1, Issue 1
  • DOI: 10.1063/1.4812323

Mechanical properties of partially crystallized aluminum based amorphous alloys
journal, March 1999


Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces
journal, April 2007


Effect of high pressure on the crystal structures of lanthanide trialuminides
journal, May 1975


Crystal structure of equiatomic ternary compounds: lanthanide-transition metal aluminides
journal, September 1984


Neural network interatomic potential for the phase change material GeTe
journal, May 2012


Development of interatomic potentials appropriate for simulation of devitrification of Al 90 Sm 10 alloy
journal, April 2015

  • Mendelev, M. I.; Zhang, F.; Ye, Z.
  • Modelling and Simulation in Materials Science and Engineering, Vol. 23, Issue 4
  • DOI: 10.1088/0965-0393/23/4/045013

Canonical dynamics: Equilibrium phase-space distributions
journal, March 1985


Discovery of a meta-stable Al–Sm phase with unknown stoichiometry using a genetic algorithm
journal, June 2014


Atomistic cluster alignment method for local order mining in liquids and glasses
journal, November 2010


DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
journal, July 2018


Soft self-consistent pseudopotentials in a generalized eigenvalue formalism
journal, April 1990


Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons
journal, April 2010


Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials
journal, January 2016

  • Shapeev, Alexander V.
  • Multiscale Modeling & Simulation, Vol. 14, Issue 3
  • DOI: 10.1137/15M1054183

Development of a deep machine learning interatomic potential for metalloid-containing Pd-Si compounds
journal, November 2019


Discovery of a metastable Al20Sm4 phase
journal, March 2015

  • Ye, Z.; Zhang, F.; Sun, Y.
  • Applied Physics Letters, Vol. 106, Issue 10
  • DOI: 10.1063/1.4914399

Synthesis and Properties of Metallic Glasses That Contain Aluminum
journal, September 1988


Analysis of nanocrystal development in Al-Y-Fe and Al-Sm glasses
journal, September 1996


Metallic Glasses
journal, March 1995


Machine learning of accurate energy-conserving molecular force fields
journal, May 2017

  • Chmiela, Stefan; Tkatchenko, Alexandre; Sauceda, Huziel E.
  • Science Advances, Vol. 3, Issue 5
  • DOI: 10.1126/sciadv.1603015

A unified formulation of the constant temperature molecular dynamics methods
journal, July 1984

  • Nosé, Shuichi
  • The Journal of Chemical Physics, Vol. 81, Issue 1
  • DOI: 10.1063/1.447334

Implementation of the projector augmented-wave method in the ABINIT code: Application to the study of iron under pressure
journal, April 2008


Phase equilibria in aluminium-rich alloys of aluminium-gadolinium and aluminium-terbium
journal, October 1967


Deep Potential Molecular Dynamics: A Scalable Model with the Accuracy of Quantum Mechanics
journal, April 2018


The structure of two polymorphic forms of YAl 3
journal, November 1967


New Amorphous Al-Y, Al-La and Al-Ce Alloys Prepared by Melt Spinning
journal, May 1988

  • Inoue, Akihisa; Ohtera, Katsumasa; Masumoto, Tsuyoshi
  • Japanese Journal of Applied Physics, Vol. 27, Issue Part 2, No. 5
  • DOI: 10.1143/JJAP.27.L736

Cooling rate dependence of structural order in Ni 62 Nb 38 metallic glass
journal, January 2018

  • Wen, Tongqi; Sun, Yang; Ye, Beilin
  • Journal of Applied Physics, Vol. 123, Issue 4
  • DOI: 10.1063/1.5019681