Prediction of Mechanical Properties of High-Entropy Carbide (Ti0.2Zr0.2Hf0.2Nb0.2Ta0.2)C with the Use of Machine Learning Potential

IF 1.1 4区化学 Q4 CHEMISTRY, PHYSICAL

Doklady Physical Chemistry Pub Date : 2024-04-13 DOI:10.1134/S0012501624600049

N. S. Pikalova, I. A. Balyakin, A. A. Yuryev, A. A. Rempel

{"title":"Prediction of Mechanical Properties of High-Entropy Carbide (Ti0.2Zr0.2Hf0.2Nb0.2Ta0.2)C with the Use of Machine Learning Potential","authors":"N. S. Pikalova, I. A. Balyakin, A. A. Yuryev,  A. A. Rempel","doi":"10.1134/S0012501624600049","DOIUrl":null,"url":null,"abstract":"The six-component high-entropy carbide (HEC) (Ti0.2Zr0.2Hf0.2Nb0.2Ta0.2)C has been studied. The electronic structure was calculated using the ab initio VASP package for a 512-atom supercell constructed with the use of special quasi-random structures. The artificial neural network potential (ANN potential) was obtained by deep machine learning. The quality of the ANN potential was estimated by standard deviations of energies, forces, and virials. The generated ANN potential was used in the LAMMPS classical molecular dynamics software to analyze both the defect-free model of the alloy comprising 4096 atoms and, for the first time, the model of the polycrystalline HEC composed of 4603 atoms. Simulation of uniaxial cell tension was carried out, and elastic coefficients, bulk modulus, elastic modulus, and Poisson’s ratio were determined. The obtained values are in good agreement with experimental and calculated data, which indicates a good predictive ability of the generated ANN potential.","PeriodicalId":532,"journal":{"name":"Doklady Physical Chemistry","volume":null,"pages":null},"PeriodicalIF":1.1000,"publicationDate":"2024-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Doklady Physical Chemistry","FirstCategoryId":"92","ListUrlMain":"https://link.springer.com/article/10.1134/S0012501624600049","RegionNum":4,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}

引用次数: 0

Abstract

The six-component high-entropy carbide (HEC) (Ti_0.2Zr_0.2Hf_0.2Nb_0.2Ta_0.2)C has been studied. The electronic structure was calculated using the ab initio VASP package for a 512-atom supercell constructed with the use of special quasi-random structures. The artificial neural network potential (ANN potential) was obtained by deep machine learning. The quality of the ANN potential was estimated by standard deviations of energies, forces, and virials. The generated ANN potential was used in the LAMMPS classical molecular dynamics software to analyze both the defect-free model of the alloy comprising 4096 atoms and, for the first time, the model of the polycrystalline HEC composed of 4603 atoms. Simulation of uniaxial cell tension was carried out, and elastic coefficients, bulk modulus, elastic modulus, and Poisson’s ratio were determined. The obtained values are in good agreement with experimental and calculated data, which indicates a good predictive ability of the generated ANN potential.

Abstract Image

查看原文本刊更多论文

利用机器学习潜能预测高熵硬质合金（Ti0.2Zr0.2Hf0.2Nb0.2Ta0.2）C 的力学性能

摘要研究了六组分高熵碳化物（HEC）（Ti0.2Zr0.2Hf0.2Nb0.2Ta0.2）C。电子结构的计算使用了ab initio VASP软件包，该软件包通过使用特殊的准随机结构构建了一个512原子的超级囚室。人工神经网络势（ANN 势）是通过深度机器学习获得的。人工神经网络势的质量是通过能量、力和virials的标准偏差来估算的。生成的人工神经网络势被用于 LAMMPS 经典分子动力学软件，以分析由 4096 个原子组成的无缺陷合金模型，并首次分析由 4603 个原子组成的多晶 HEC 模型。对单轴单元张力进行了模拟，并测定了弹性系数、体积模量、弹性模量和泊松比。所得数值与实验和计算数据非常吻合，这表明生成的 ANN 电位具有良好的预测能力。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Doklady Physical Chemistry 化学-物理化学

CiteScore

1.50

自引率

0.00%

发文量

审稿时长

6-12 weeks

期刊介绍： Doklady Physical Chemistry is a monthly journal containing English translations of current Russian research in physical chemistry from the Physical Chemistry sections of the Doklady Akademii Nauk (Proceedings of the Russian Academy of Sciences). The journal publishes the most significant new research in physical chemistry being done in Russia, thus ensuring its scientific priority. Doklady Physical Chemistry presents short preliminary accounts of the application of the state-of-the-art physical chemistry ideas and methods to the study of organic and inorganic compounds and macromolecules; polymeric, inorganic and composite materials as well as corresponding processes. The journal is intended for scientists in all fields of chemistry and in interdisciplinary sciences.