Structural descriptors evaluation for MoTa mechanical properties prediction with machine learning

IF 1.9 4区材料科学 Q3 MATERIALS SCIENCE, MULTIDISCIPLINARY

Modelling and Simulation in Materials Science and Engineering Pub Date : 2024-01-09 DOI:10.1088/1361-651x/ad1cd1

Tingpeng Tao, Shu Li, Dechuang Chen, Shuai Li, Dongrong Liu, Xin Liu, Minghua Chen

引用次数: 0

Abstract

Considering all possible crystal structures is essential in computer simulations of alloy properties, but using Density Functional Theory (DFT) is computationally impractical. To address this, four structural descriptors were evaluated using machine learning (ML) models to predict formation energy, elasticity and hardness of MoTa alloys. A total of 612 configurations were generated by the Clusters Approach to Statistical Mechanics (CASM) software and their corresponding material properties were calculated by DFT. As input features of ML models, the CORR and SOAP performed best (R2 > 0.90, some up to 0.99), followed by ACSF, while CM performed worst. Furthermore, SOAP shows excellent performance in extrapolation for larger supercell structures of the MoTa alloy system and transfer learning for the MoNb alloy system.

查看原文本刊更多论文

利用机器学习评估钽锰酸锂机械性能的结构描述符

在对合金特性进行计算机模拟时，必须考虑所有可能的晶体结构，但使用密度泛函理论（DFT）在计算上并不现实。为了解决这个问题，我们使用机器学习（ML）模型对四种结构描述符进行了评估，以预测钼钽合金的形成能、弹性和硬度。统计力学聚类方法（CASM）软件共生成了 612 种构型，并通过 DFT 计算了其相应的材料属性。作为 ML 模型的输入特征，CORR 和 SOAP 表现最好（R2 > 0.90，有些高达 0.99），其次是 ACSF，而 CM 表现最差。此外，SOAP 在对 MoTa 合金体系的较大超晶胞结构进行外推以及对 MoNb 合金体系进行迁移学习方面表现出色。

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

Modelling and Simulation in Materials Science and Engineering 工程技术-材料科学：综合

CiteScore

3.30

自引率

5.60%

发文量

审稿时长

1.7 months

期刊介绍： Serving the multidisciplinary materials community, the journal aims to publish new research work that advances the understanding and prediction of material behaviour at scales from atomistic to macroscopic through modelling and simulation. Subject coverage: Modelling and/or simulation across materials science that emphasizes fundamental materials issues advancing the understanding and prediction of material behaviour. Interdisciplinary research that tackles challenging and complex materials problems where the governing phenomena may span different scales of materials behaviour, with an emphasis on the development of quantitative approaches to explain and predict experimental observations. Material processing that advances the fundamental materials science and engineering underpinning the connection between processing and properties. Covering all classes of materials, and mechanical, microstructural, electronic, chemical, biological, and optical properties.