Prediction of vacancy formation energies at tungsten grain boundaries from local structure via machine learning method
文献类型:期刊论文
作者 | Wang, Yuxuan1,2; Li, Xiaolin1,2; Li, Xiangyan1; Zhang, Yuxiang1,2; Zhang, Yange1; Xu, Yichun1; Lei, Yawei1; Liu, C. S.1; Wu, Xuebang1 |
刊名 | JOURNAL OF NUCLEAR MATERIALS |
出版日期 | 2022-02-01 |
卷号 | 559 |
ISSN号 | 0022-3115 |
关键词 | Vacancy formation energy Machine learning Tungsten Symmetry tilt grain boundary Support vector machine Cross validation |
DOI | 10.1016/j.jnucmat.2021.153412 |
通讯作者 | Li, Xiangyan(xiangyanli@issp.ac.cn) ; Wu, Xuebang(xbwu@issp.ac.cn) |
英文摘要 | Grain boundary (GB) plays a crucial role in the mechanical properties and irradiation resistance of nuclear materials. It is thus essential to understand and predict the defect properties near GBs. Here, we present a framework for predicting vacancy formation energy (E-V(f) ) near GBs in tungsten (W) by machine learning (ML) technique. The E-V(f) values of 4496 atomic sites near 46 types of [001] symmetry tilt GB (STGB) in W are calculated as database and eight appropriate variables are selected to characterizing the surrounding atomic configuration and location of atomic sites. Via the support vector machine with the radial basis kernel function (RBF-SVM), the good predicted results of cross validation (CV) and generalized verification prove the suitability and effectiveness of the selected variables and RBF-SVM method. Beside, due to their big differences in dislocation arrangement and atomic configuration, the STGBs need to be divided into three types, high angle, low angle-I and low angle-II STGBs, for adopting the Separate CV, and their predicted accuracies were found to have big improvements. Because the present method adopts geometrical factors, such as spatial size characteristic, density and location, as descriptors for the ML analysis, it is robust and general to other materials such as alpha-Fe, and beneficial to predict and understand the vacancy formation near interfaces. (C) 2021 Elsevier B.V. All rights reserved. |
WOS关键词 | MOLECULAR-DYNAMICS ; RADIATION-DAMAGE ; POINT-DEFECTS ; FISSION ; METALS |
资助项目 | National Key Research and Development Program of China[2017YFE0302400] ; National Key Research and Development Program of China[2017YFA0402800] ; National Natural Science Foundation of China[52171084] ; National Natural Science Foundation of China[11735015] ; National Natural Science Foundation of China[51871207] ; National Natural Science Foundation of China[U1832206] ; Anhui Provincial Natural Science Foundation[1908085J17] |
WOS研究方向 | Materials Science ; Nuclear Science & Technology |
语种 | 英语 |
出版者 | ELSEVIER |
WOS记录号 | WOS:000799085700003 |
资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China ; Anhui Provincial Natural Science Foundation |
源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/131127] |
专题 | 中国科学院合肥物质科学研究院 |
通讯作者 | Li, Xiangyan; Wu, Xuebang |
作者单位 | 1.Chinese Acad Sci, Inst Solid State Phys, Key Lab Mat Phys, HFIPS, Hefei 230031, Peoples R China 2.Univ Sci & Technol China, Hefei 230026, Peoples R China |
推荐引用方式 GB/T 7714 | Wang, Yuxuan,Li, Xiaolin,Li, Xiangyan,et al. Prediction of vacancy formation energies at tungsten grain boundaries from local structure via machine learning method[J]. JOURNAL OF NUCLEAR MATERIALS,2022,559. |
APA | Wang, Yuxuan.,Li, Xiaolin.,Li, Xiangyan.,Zhang, Yuxiang.,Zhang, Yange.,...&Wu, Xuebang.(2022).Prediction of vacancy formation energies at tungsten grain boundaries from local structure via machine learning method.JOURNAL OF NUCLEAR MATERIALS,559. |
MLA | Wang, Yuxuan,et al."Prediction of vacancy formation energies at tungsten grain boundaries from local structure via machine learning method".JOURNAL OF NUCLEAR MATERIALS 559(2022). |
入库方式: OAI收割
来源:合肥物质科学研究院
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。