Machine-learning model for prediction of martensitic transformation temperature in NiMnSn-based ferromagnetic shape memory alloys

doi:10.1016/j.commatsci.2022.111811

IMR OpenIR

	Machine-learning model for prediction of martensitic transformation temperature in NiMnSn-based ferromagnetic shape memory alloys
	Tian, Xiaohua 1; Shi, Dingding 1; Zhang, Kun 2,3; Li, Hongxing 2; Zhou, Liwen 1; Ma, Tianyou 4; Wang, Cheng 4; Wen, Qinlong 5; Tan, Changlong 2
通讯作者	Zhang, Kun(kunzhang@hrbust.edu.cn) ; Tan, Changlong(changlongtan@hrbust.edu.cn)
	2022-12-01
发表期刊	COMPUTATIONAL MATERIALS SCIENCE
ISSN	0927-0256
卷号	215 页码:7
摘要	Martensitic transformation temperature (TM) of NiMnSn-based ferromagnetic shape memory alloys (FSMAs) is crucial to identifying the operating range of an application. From a materials design point of view, an efficient method that can predict the TM accurately should be strongly pursued, to meet various applications with different operating temperatures. In this paper, we demonstrate that machine learning (ML) can rapidly and accurately predict the TM in NiMnSn-based FSMAs. We evaluate the performance of four machine learning models, including Random Forest Regressor (RFR), Support Vector Regression (SVR), Linear Regression (LR), and XGBRegressor (XGBR) model. Three important features of Numa , Arc , and avg Ven are selected as the optimal feature combination for building the model. Moreover, to ensure the best generalization ability of the model, multiple methods of cross-validation (Leave-One-Out Cross-Validation, 3-fold Cross-Validation, and 5-fold Cross -Validation) are used. Finally, the XGBR model exhibits the best performance for predicting the TM (R2 = 0.903 and RMSE = 5.4, R25f = 0.869 and R23f = 0.838). The results of small deviation and variance proven that the XGBR model, proposed in this work, is suitable to be used to predict the TM of unknown NiMnSn-based FSMAs. This work is expected to promote the targeted design of FSMAs.
关键词	Ferromagnetic shape memory alloys Martensitic transformation temperature Machine learning NiMnSn-based alloys XGBRegressor
资助者	National Natural Science Foundation of China ; China Postdoctoral Science Foundation
DOI	10.1016/j.commatsci.2022.111811
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China ; China Postdoctoral Science Foundation ; [51971085] ; [51871083] ; [52001101] ; [52271172] ; [2021M693229]
WOS研究方向	Materials Science
WOS类目	Materials Science, Multidisciplinary
WOS记录号	WOS:000870259700006
出版者	ELSEVIER
引用统计	被引频次：5[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.imr.ac.cn/handle/321006/176362
专题	中国科学院金属研究所
通讯作者	Zhang, Kun; Tan, Changlong
作者单位	1.Harbin Univ Sci & Technol, Sch Elect & Elect Engn, Harbin 150080, Peoples R China 2.Harbin Univ Sci & Technol, Sch Mat Sci & Chem Engn, Harbin 150040, Peoples R China 3.Chinese Acad Sci, Inst Met Res, Shenyang Natl Lab Mat Sci, Shenyang 110016, Peoples R China 4.Harbin Univ Sci & Technol, Sch Sci, Harbin 150080, Peoples R China 5.Northwestern Polytech Univ, State Key Lab Solidificat Proc, Xian 710072, Peoples R China
推荐引用方式 GB/T 7714	Tian, Xiaohua,Shi, Dingding,Zhang, Kun,et al. Machine-learning model for prediction of martensitic transformation temperature in NiMnSn-based ferromagnetic shape memory alloys[J]. COMPUTATIONAL MATERIALS SCIENCE,2022,215:7.
APA	Tian, Xiaohua.,Shi, Dingding.,Zhang, Kun.,Li, Hongxing.,Zhou, Liwen.,...&Tan, Changlong.(2022).Machine-learning model for prediction of martensitic transformation temperature in NiMnSn-based ferromagnetic shape memory alloys.COMPUTATIONAL MATERIALS SCIENCE,215,7.
MLA	Tian, Xiaohua,et al."Machine-learning model for prediction of martensitic transformation temperature in NiMnSn-based ferromagnetic shape memory alloys".COMPUTATIONAL MATERIALS SCIENCE 215(2022):7.