Multi-objective optimization for high-performance Fe-based metallic glasses via machine learning approach

doi:10.1016/j.jallcom.2023.170793

CORC > 力学研究所 > 中国科学院力学研究所 > 非线性力学国家重点实验室

	Multi-objective optimization for high-performance Fe-based metallic glasses via machine learning approach
	Zhang, Yuxing ; Xie, Shejuan ; Guo, Wei ; Ding, Jun ; Poh, Leong Hien ; Sha ZD(沙振东)
刊名	JOURNAL OF ALLOYS AND COMPOUNDS
	2023-10-15
卷号	960 页码:170793
关键词	Fe-based metallic glass Machine learning Critical casting size Saturation magnetization Plasticity
ISSN号	0925-8388
DOI	10.1016/j.jallcom.2023.170793
英文摘要	Fe-based metallic glasses (MGs) are a class of promising soft magnetic materials that have received great attention in transformer industries. However, it is challenging to achieve a balance between saturation magnetization (Bs), glass-forming ability and plasticity due to their contradictory correlations in Fe-based MGs, which severely hinders the development of new Fe-based MGs with advanced performances. Inspired by the significant development in machine learning technology, we herein propose a multi-objective op-timization strategy to search for Fe-based MGs with optimal combinations of critical casting size (Dmax), Bs, and plasticity. The objective functions are built in combination with neural network models for pre-dicting Dmax and Bs, as well as empirical formula for plasticity. The effect of number of hidden layers is investigated and the dropout regularization method employed to improve the prediction performance. Our results show that the predictions of Bs and Dmax by using alloy composition as the sole input perform well, as evidenced by their r2 values of 0.963 and 0.874, respectively. Multi-objective optimization based on the genetic algorithm is executed to obtain the Pareto front and Pareto-optimal solutions. The Pareto-optimal alloys predicted for the Fe83C1BxSiyP16-x-y and FexCoyNi72-x-yB19.2Si4.8Nb4 systems are in good agreement with those reported in experiments. This work thus showcases potential applications for the design of high-performance Fe-MGs against conflicting objectives. & COPY; 2023 Elsevier B.V. All rights reserved.
分类号	一类
WOS研究方向	Chemistry, Physical ; Materials Science, Multidisciplinary ; Metallurgy & Metallurgical Engineering
语种	英语
WOS记录号	WOS:001015251300001
资助机构	National Natural Science Foundation of China [11972278] ; opening fund of the State Key Laboratory of Nonlinear Mechanics
其他责任者	Sha, ZD (corresponding author), Xi An Jiao Tong Univ, Sch Aerosp Engn, State Key Lab Strength & Vibrat Mech Struct, Xian 710049, Peoples R China. ; Poh, LH (corresponding author), Natl Univ Singapore, Dept Civil & Environm Engn, 1 Engn Dr 2,E1A-07-03, Singapore 117576, Singapore.
内容类型	期刊论文
源URL	[http://dspace.imech.ac.cn/handle/311007/92412]
专题	力学研究所_非线性力学国家重点实验室
作者单位	1.{Sha Zhen-Dong} Chinese Acad Sci Inst Mech State Key Lab Nonlinear Mech Beijing 100190 Peoples R China 2.{Poh Leong Hien} Natl Univ Singapore Dept Civil & Environm Engn 1 Engn Dr 2E1A-07-03 Singapore 117576 Singapore 3.{Ding Jun} Xi An Jiao Tong Univ Ctr Alloy Innovat & Design State Key Lab Mech Behav Mat Xian 710049 Peoples R China 4.{Guo Wei} Huazhong Univ Sci & Technol State Key Lab Mat Proc & Die & Mould Technol 1037 Luoyu Rd Wuhan 430074 Peoples R China 5.{Zhang Yu-Xing} China Elect Technol Grp Corp Res Inst 52 Hangzhou 310000 Peoples R China 6.{Zhang Yu-Xing, Xie She-Juan, Sha Zhen-Dong} Xi An Jiao Tong Univ Sch Aerosp Engn State Key Lab Strength & Vibrat Mech Struct Xian 710049 Peoples R China
推荐引用方式 GB/T 7714	Zhang, Yuxing,Xie, Shejuan,Guo, Wei,et al. Multi-objective optimization for high-performance Fe-based metallic glasses via machine learning approach[J]. JOURNAL OF ALLOYS AND COMPOUNDS,2023,960:170793.
APA	Zhang, Yuxing,Xie, Shejuan,Guo, Wei,Ding, Jun,Poh, Leong Hien,&沙振东.(2023).Multi-objective optimization for high-performance Fe-based metallic glasses via machine learning approach.JOURNAL OF ALLOYS AND COMPOUNDS,960,170793.
MLA	Zhang, Yuxing,et al."Multi-objective optimization for high-performance Fe-based metallic glasses via machine learning approach".JOURNAL OF ALLOYS AND COMPOUNDS 960(2023):170793.