IMR OpenIR
Accelerated design for elastocaloric performance in NiTi-based alloys through machine learning
Tian, Xiaohua1; Zhao, Qiu1; Zhang, Kun2,3; Li, Hongxing2; Han, Binglun2; Shi, Dingding1; Zhou, Liwen1; Ma, Tianyou2; Wang, Cheng2; Wen, Qinlong4; Tan, Changlong2
Corresponding AuthorZhang, Kun(kunzhang@hrbust.edu.cn)
2022-01-07
Source PublicationJOURNAL OF APPLIED PHYSICS
ISSN0021-8979
Volume131Issue:1Pages:10
AbstractNiTi-based shape memory alloys (SMAs) are regarded as one of the most promising materials for engineering applications of elastocaloric refrigeration. A critical mission is to efficiently explore the new NiTi-based SMAs with large adiabatic temperature change (& UDelta;T-ad). We proposed a new material design method that combines highly correlated microscale physical information (volume change, & UDelta; V) into machine learning to predict & UDelta;T-ad of NiTi-based alloys. First, we tightly coupled machine learning with first-principles calculations to accelerate receiving lattice parameters before and after the phase transformation and predict the & UDelta; V, which shows excellent performance with the coefficient of determination R-2 > 0.99. Then, relevant features, including the & UDelta; V, are considered to predict the & UDelta;T-ad in NiTi-based SMAs. Moreover, due to the small dataset, the principal component analysis and the independent component analysis are added. We evaluate the performance of three machine learning models [Lasso regression, support vector regression, and decision tree regression (DTR)]. Finally, the DTR model exhibits a high accuracy for predicting & UDelta;T-ad (R-2 > 0.9). Introducing the feature of & UDelta; V into the machine learning process can improve the accuracy and efficiency of model design. Further, this work paves the way to accelerate the discovery of new excellent materials for practical applications of elastocaloric refrigeration.
Funding OrganizationNational Natural Science Foundation of China (NNSFC) ; China Postdoctoral Science Foundation
DOI10.1063/5.0068290
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China (NNSFC)[51971085] ; National Natural Science Foundation of China (NNSFC)[51871083] ; National Natural Science Foundation of China (NNSFC)[52001101] ; China Postdoctoral Science Foundation[2021M693229]
WOS Research AreaPhysics
WOS SubjectPhysics, Applied
WOS IDWOS:000744570400010
PublisherAIP Publishing
Citation statistics
Document Type期刊论文
Identifierhttp://ir.imr.ac.cn/handle/321006/173602
Collection中国科学院金属研究所
Corresponding AuthorZhang, Kun
Affiliation1.Harbin Univ Sci & Technol, Sch Elect & Elect Engn, Harbin 150080, Peoples R China
2.Harbin Univ Sci & Technol, Sch Sci, Harbin 150080, Peoples R China
3.Chinese Acad Sci, Inst Met Res, Shenyang Natl Lab Mat Sci, 72 Wenhua Rd, Shenyang 110016, Liaoning, Peoples R China
4.Northwestern Polytech Univ, State Key Lab Solidificat Proc, Xian 710072, Peoples R China
Recommended Citation
GB/T 7714
Tian, Xiaohua,Zhao, Qiu,Zhang, Kun,et al. Accelerated design for elastocaloric performance in NiTi-based alloys through machine learning[J]. JOURNAL OF APPLIED PHYSICS,2022,131(1):10.
APA Tian, Xiaohua.,Zhao, Qiu.,Zhang, Kun.,Li, Hongxing.,Han, Binglun.,...&Tan, Changlong.(2022).Accelerated design for elastocaloric performance in NiTi-based alloys through machine learning.JOURNAL OF APPLIED PHYSICS,131(1),10.
MLA Tian, Xiaohua,et al."Accelerated design for elastocaloric performance in NiTi-based alloys through machine learning".JOURNAL OF APPLIED PHYSICS 131.1(2022):10.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Tian, Xiaohua]'s Articles
[Zhao, Qiu]'s Articles
[Zhang, Kun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Tian, Xiaohua]'s Articles
[Zhao, Qiu]'s Articles
[Zhang, Kun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Tian, Xiaohua]'s Articles
[Zhao, Qiu]'s Articles
[Zhang, Kun]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.