Application of Machine Learning to Predict Grain Boundary Embrittlement in Metals by Combining Bonding-Breaking and Atomic Size Effects

doi:10.3390/ma13010179

	Application of Machine Learning to Predict Grain Boundary Embrittlement in Metals by Combining Bonding-Breaking and Atomic Size Effects
	Wu, Xuebang 1; Wang, Yu-xuan 1,2; He, Kan-ni 1,2; Li, Xiangyan 1; Liu, Wei 1; Zhang, Yange 1; Xu, Yichun 1; Liu, Changsong 1
刊名	MATERIALS
	2020
卷号	13
关键词	grain boundary embrittlement machine learning strengthening energy support vector machine artificial neural network
DOI	10.3390/ma13010179
通讯作者	Wu, Xuebang(xbwu@issp.ac.cn) ; Liu, Changsong(csliu@issp.ac.cn)
英文摘要	The strengthening energy or embrittling potency of an alloying element is a fundamental energetics of the grain boundary (GB) embrittlement that control the mechanical properties of metallic materials. A data-driven machine learning approach has recently been used to develop prediction models to uncover the physical mechanisms and design novel materials with enhanced properties. In this work, to accurately predict and uncover the key features in determining the strengthening energies, three machine learning methods were used to model and predict strengthening energies of solutes in different metallic GBs. In addition, 142 strengthening energies from previous density functional theory calculations served as our dataset to train three machine learning models: support vector machine (SVM) with linear kernel, SVM with radial basis function (RBF) kernel, and artificial neural network (ANN). Considering both the bond-breaking effect and atomic size effect, the nonlinear kernel based SVR model was found to perform the best with a correlation of r(2) similar to 0.889. The size effect feature shows a significant improvement to prediction performance with respect to using bond-breaking effect only. Moreover, the mean impact value analysis was conducted to quantitatively explore the relative significance of each input feature for improving the effective prediction.
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[11735015] ; National Natural Science Foundation of China[51871207] ; National Natural Science Foundation of China[11575229] ; National Natural Science Foundation of China[51671185] ; National Natural Science Foundation of China[U1832206] ; Anhui Provincial Natural Science Foundation[1908085J17]
WOS关键词	ZINC-INDUCED EMBRITTLEMENT ; SEGREGATION ; 1ST-PRINCIPLES
WOS研究方向	Materials Science
语种	英语
出版者	MDPI
WOS记录号	WOS:000515499300179
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Anhui Provincial Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/103957]
专题	中国科学院合肥物质科学研究院
通讯作者	Wu, Xuebang; Liu, Changsong
作者单位	1.Chinese Acad Sci, Inst Solid State Phys, Key Lab Mat Phys, Hefei 230031, Peoples R China 2.Univ Sci & Technol China, Dept Mat Sci & Engn, Hefei 230026, Peoples R China
推荐引用方式 GB/T 7714	Wu, Xuebang,Wang, Yu-xuan,He, Kan-ni,et al. Application of Machine Learning to Predict Grain Boundary Embrittlement in Metals by Combining Bonding-Breaking and Atomic Size Effects[J]. MATERIALS,2020,13.
APA	Wu, Xuebang.,Wang, Yu-xuan.,He, Kan-ni.,Li, Xiangyan.,Liu, Wei.,...&Liu, Changsong.(2020).Application of Machine Learning to Predict Grain Boundary Embrittlement in Metals by Combining Bonding-Breaking and Atomic Size Effects.MATERIALS,13.
MLA	Wu, Xuebang,et al."Application of Machine Learning to Predict Grain Boundary Embrittlement in Metals by Combining Bonding-Breaking and Atomic Size Effects".MATERIALS 13(2020).