基于第一性原理计算的固溶体合金集成学习设计方法

doi:10.11896/cldb.23030089

材料导报

2024, Vol. 38

Issue (13): 23030089-8 https://doi.org/10.11896/cldb.23030089

金属与金属基复合材料

基于第一性原理计算的固溶体合金集成学习设计方法

张琦祥¹, 苑峻豪¹, 李震², 李文杰³, 孙丹³, 王清^1,*, 董闯¹

1 大连理工大学三束材料改性教育部重点实验室 & 材料科学与工程学院,辽宁大连 116024
2 大连理工大学机械工程学院,辽宁大连 116024
3 中国核动力研究设计院核反应堆系统设计技术重点实验室,成都610213

Integrated Learning Design Method for Solid-Solution Alloys Based on First-principles Calculations

ZHANG Qixiang¹, YUAN Junhao¹, LI Zhen², LI Wenjie³, SUN Dan³, WANG Qing^1,*, DONG Chuang¹

1 Key Laboratory of Materials Modification by Laser,Ion and Electron Beams (Ministry of Education),School of Materials Science and Engineering,Dalian University of Technology,Dalian 116024, Liaoning, China
2 School of Mechanical Engineering,Dalian University of Technology,Dalian 116024,Liaoning, China
3 Science and Technology on Reactor System Design Technology Laboratory,Nuclear Power Institute of China,Chengdu 610213,China

摘要
参考文献
相关文章
推荐阅读
Metrics

下载:

全文 ( PDF ) ( 11329KB )
输出: BibTeX | EndNote (RIS)

摘要基于密度泛函理论的第一性原理方法在考虑了固溶体化学短程序特征后计算得到的合金的基本性质更为可靠。本工作将描述固溶体短程序的团簇加连接原子结构模型嵌入到第一性原理计算中,获得了一系列合金的基本物性数据;构建了数据管理系统,形成成分与性能数据库;进而采用多种机器学习算法构建合金成分与性能的预测模型,并对其进行对比分析;在此基础上,筛选最优算法,以精确预测合金的性能,并实现以性能为目标导向的成分设计;最终形成了一种基于第一性原理计算的固溶体合金集成学习设计方法,并开发出可视化程序软件。该方法有望大幅提升高性能先进合金材料研发的效率。

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张琦祥
	苑峻豪
	李震
	李文杰
	孙丹
	王清
	董闯

关键词: 第一性原理计算团簇结构模型机器学习集成计算方法

Abstract: The first-principles method based on density functional theory (DFT) gives a more reliable calculation of the basic properties of alloys after considering the characteristics of chemical short-range orders (CSRO) of solid solutions.This work embeds the cluster-plus-glue-atom structural model describing the CSRO into first-principles calculations to obtain basic physical properties data for a series of alloys.Then a data management system was constructed to build a composition and performance database.Furthermore,multiple machine learning algorithms were used to construct prediction models for alloy composition and performance,and comparative analysis was performed.Based on this,the optimal algorithm was selected to accurately predict the performance of alloys and achieve composition design guided by performance objectives.Finally,an integrated learning design method for solid solution alloys based on first-principles calculations is integrated,and the visualization program software is developed.The method is expected to significantly improve the efficiency of the development of high-performance advanced alloy materials.

Key words: first-principle cluster structural model machine learning integrated calculation methods

出版日期: 2024-07-10 发布日期: 2024-08-01

ZTFLH:

TG146.8

基金资助: 国家基础加强项目(2021-JCJQ-ZD-030-12)

通讯作者: ^*王清,大连理工大学材料科学与工程学院教授、博士研究生导师。1999年7月山东工业大学焊接专业本科毕业,2002年6月甘肃工业大学材料加工工程专业硕士毕业,2005年11月大连理工大学材料科学与工程专业博士毕业并工作至今。目前主要从事发展合金设计方法和研发先进工程合金材料的研究工作,涉及的合金体系主要有高性能钛/锆合金、导电铜合金、核电反应堆用特种不锈钢、高熵合金等。近五年,主持国家自然科学基金2项,辽宁省自然科学基金1项,中国核动力设计研究院国家重点实验室基金2项;作为骨干,参加国家十三五重点研发计划2项,国家自然科学基金重点项目和面上项目3项,国家科技计划国际合作专项项目1项等;参加企业合作项目4项。在Scripta Materials、Scientific Reports、Materials & Design等期刊上发表文章80余篇,申请和授权专利20余项;多次在本领域内重要国内外学术会议做邀请报告。wangq@dlut.edu.cn

作者简介: 张琦祥,2020年6月于大连交通大学获得工学学士学位。现为大连理工大学材料科学与工程学院博士研究生,在王清教授的指导下进行研究。目前主要研究领域为基于第一性原理计算的固溶体合金设计方法。

引用本文:

张琦祥, 苑峻豪, 李震, 李文杰, 孙丹, 王清, 董闯. 基于第一性原理计算的固溶体合金集成学习设计方法[J]. 材料导报, 2024, 38(13): 23030089-8.
ZHANG Qixiang, YUAN Junhao, LI Zhen, LI Wenjie, SUN Dan, WANG Qing, DONG Chuang. Integrated Learning Design Method for Solid-Solution Alloys Based on First-principles Calculations. Materials Reports, 2024, 38(13): 23030089-8.

链接本文:

http://www.mater-rep.com/CN/10.11896/cldb.23030089 或 http://www.mater-rep.com/CN/Y2024/V38/I13/23030089

1 George E P, Raabe D, Ritchie R O. Nature Reviews Materials, 2019, 4, 515.
2 Inoue A, Shen B L, Chang C T. Acta Materialia, 2004, 52(14), 4093.
3 Yeh J W, Chen S K, Lin S J. Advanced Engineering Materials, 2004, 6(5), 299.
4 Long M, Rack H J. Biomaterials, 1998, 19, 1621.
5 Hohenberg P, Kohn W. Physical Review, 1964, 136(3B), B864.
6 Kohn W, Sham L J. Physical Review, 1965, 140(4A), A1133.
7 Marshal A, Pradeep K G, Music D, et al. Scientific Reports, 2019, 9(1), 7864.
8 Yu P, Zhuang Y, Chou J P, et al. Scientific Reports, 2019, 9(1), 10940.
9 Zhang R P, Zhao S T, Ding J, et al. Nature, 2020, 581(7808), 283.
10 Santodonato L J, Zhang Y, Feygenson M, et al. Nature Communications, 2015, 6(1), 5964.
11 Ding D J, Yu Q, Asta M, et al. Proceedings of the National Academy of Sciences, 2018, 115(36), 8919.
12 Sobieraj D, Wróbel J S, Rygier T, et al. Physical Chemistry Chemical Physics, 2020, 22(41), 23929.
13 Chen S, Aitken Z H, Pattamatta S, et al. Acta Materialia, 2021, 206, 116638.
14 Guo W, Dmowski W, Noh J, et al. Metallurgical and Materials Transactions A, 2013, 44(5), 1994.
15 Singh P, Smirnov A V, Johnson D D. Physical Review B, 2015, 91(22), 224204.
16 Tian F Y, Lin D Y, Gao X Y, et al. The Journal of Chemical Physics, 2020, 153(3), 034101.
17 Zunger A, Wei S H, Ferreira L G. Physical Review Letters, 1990, 65(3), 35.
18 Wu J W, Yang Z, Xian J W, et al. Frontiers in Materials, 2020, 7, 590143.
19 Hong H L, Wang Q, Dong C, et al. Scientific Reports, 2014, 4(1), 7065.
20 Pang C, Jiang B, Shi Y, et al. Journal of Alloys and Compounds, 2015, 652, 63.
21 Ma Y, Wang Q, Li C L, et al. Scripta Materialia, 2018, 144, 64.
22 Dong C, Wang Q, Qiang J B, et al. Journal of Physics D: Applied Physics, 2007, 40(15), R273.
23 Ma Y, Wang Q, Jiang B B, et al. Acta Materialia, 2018, 147, 213.
24 Li Z, Zhang R, Zha Q, et al. Progress in Natural Science: Materials International, 2014, 24(1), 35.
25 Wang Q, Han J C, Liu Y F, et al. Scripta Materialia, 2021, 190, 40.
26 Yuan J H, Liu Y F, Li Z, et al. Journal of Phase Equilibria and Diffusion, 2021, 42, 647.
27 Wang W Y, Shang S L, Wang Y, et al. npj Computational Materials, 2017, 3, 23.
28 Wu W, Sun Q. Scientia Sinica (Physica, Mechanica & Astronomica), 2018, 48(10), 58(in Chinese).
吴炜, 孙强. 中国科学:物理学力学天文学, 2018, 48(10), 58.
29 Liu L M. The Journal of New Industrialization, 2015, 5(12), 71 (in Chinese).
刘利民. 新型工业化, 2015, 5(12), 71.
30 Kirklin S, Saal J E, Meredig B, et al. npj Computational Materials, 2015, 1(1), 15010.
31 Saal J E, Kirklin S, Aykol M, et al. JOM (Journal of Occupational Medicine and Toxicology), 2013, 65(11), 1501.
32 Wang D S, Amsler M, Vinay I H, et al. Acta Materialia, 2018, 158, 65.
33 Zhu D Q, Wu L. Modern Distance Education Research, 2019, 31(6), 14 (in Chinese).
朱德全, 吴虑. 现代远程教育研究, 2019, 31(6), 14.
34 Shen C G, Wang C C, Wei X L, et al. Acta Materialia, 2019, 179, 201.
35 Chen T Q, Guestrin C. In:Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, San Francisco California, 2016, pp.785.
36 Davis L. Handbook of genetic algorithms, Van Nostrand Reinhold, New York, 1991.
37 Yang F, Li Z, Wang Q, et al. npj Computational Materials, 2020, 6(1), 101.
38 Thomas H. An Introduction to statistics with Python, Springer International Publishing AG, Switzerland, 2022.
39 Kreibich J A. Using SQLite, O'Reilly Media, 2010.
40 Pedregosa F, Varoquaux G, Gramfort A, et al. Journal of Machine Learning Research, 2011, 12, 2825.
41 Pan J, Yoshikawa A, Yamamura M. In:2022 4th International Conference on Communications, Information System and Computer Engineering (CISCE). Shenzhen, China, 2022.
42 Takeuchi A, Inoue A. Materials Transactions, 2005, 46(12), 2817.
43 Jiang B B, Wang Q, Dong C, et al. Scientific Reports, 2019, 9(1), 3404.
44 Pang C, Wang Q, Zhang R Q, et al. Materials Science and Engineering A, 2015, 626, 369.
45 Kresse G, Furthmüller J. Computational Materials Science, 1996, 6(1), 15.
46 Kresse G, Furthmüller J. Physical Review B, 1996, 54(16), 11169.
47 Kresse G, Hafner J. Physical Review B, 1993, 47, 588.
48 Kresse G, Hafner J. Physical Review B, 1994, 49, 14251.
49 Hall S R, Allen F H, Brown I D. Acta Crystallographic Section A, 1991, A47, 655.
50 Dan Porter. Dans_Diffraction(v1. 8. 2), https:∥doi. org/10. 5281/zenodo. 3859501.
51 Wang V, Xu N, Liu J C, et al. Computer Physics Communications, 2021, 267, 108033.
52 McKinney Wes. Python for data analysis, second edition, O'Reilly Media, 2017.
53 Yuan J H, Wang Q, Li Z, et al. Computational Materials Science, 2021, 194, 110472.
54 Breiman L. Machine Learning, 2001, 45(1), 5.
55 Hearst M A, Dumais S T, Osuna E, et al. IEEE Intelligent Systems, 1998, 13(4), 18.
56 Claesen M, Moor B D. In:The XI Metaheuristics International Conference in Agadir. Morocco, 2015.
57 Akiba T, Sano S, Yanase T, et al. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, 2019, pp.2623.
58 Monkhorst H J, Pack J D. Physical Review B, 1976, 13, 5188.
59 BLÖCHL P E. Physical Review B, 1994, 50, 17953.
60 Shen C G, Wang C C, Wei X L, et al. Acta Materialia, 2019, 179, 201.
61 Yuan J H, Dong D D, Wang Q, et al. Rare Metal Materials and Engineering, 2020, 49(1), 225(in Chinese).
苑峻豪, 董丹丹, 王清, 等. 稀有金属材料与工程, 2020, 49(1), 225.
62 Bostrom W A. Development and properties of uranium-base alloys corrosion resistant in high temperature water. Part I. alloys without protective cladding, Westinghouse Electric Corp. Atomic Power Div., Pittsburgh, 1955.

[1]	王博, 盛鹏, 徐丽, 李圣驿, 白会涛, 李慧, 薛晴. 材料基因工程技术在电工材料研发中的应用与展望[J]. 材料导报, 2024, 38(13): 23020098-17.
[2]	龙武剑, 罗盛禹, 程博远, 冯甘霖, 李利孝. 机器学习算法用于自密实混凝土性能设计的研究进展[J]. 材料导报, 2024, 38(11): 22110224-10.
[3]	高志玉, 樊献金, 高思达, 薛维华. 基于多模型机器学习的合金结构钢回火力学性能研究[J]. 材料导报, 2023, 37(6): 21090025-7.
[4]	余瑞, 张永安, 李亚楠, 李锡武, 李志辉, 闫丽珍, 温凯, 熊柏青. Zn对Al-Mg-Si合金时效析出相稳定性影响的第一性原理研究[J]. 材料导报, 2023, 37(4): 21040034-5.
[5]	王世杰, 杨杰, 马硕, 韩硕, 王龙, 段国林. 机器学习在功能梯度材料设计-制备中的应用综述[J]. 材料导报, 2023, 37(21): 22030237-9.
[6]	才文文, 贺勇, 张敏, 史俊杰. AZrX₃(A=Ba, Ca;X=S, Se,Te)钙钛矿结构及光电特性的第一性原理研究[J]. 材料导报, 2023, 37(2): 21070076-6.
[7]	徐潇航, 胡张莉, 刘加平, 李文伟, 刘建忠. 基于机器学习回归模型的三峡大坝混凝土强度预测[J]. 材料导报, 2023, 37(2): 22010068-9.
[8]	余春秀, 王云凯, 贺子娟, 李玮, 陈家林, 李世鸿, 李俊鹏. 电子封装用环氧胶粘剂改性研究进展[J]. 材料导报, 2023, 37(15): 21120084-10.
[9]	张鹏军, 陈国祥, 安国, 刘迎港. 铁修饰二碲化钼吸附氮化物的气敏特性研究[J]. 材料导报, 2023, 37(12): 21110219-6.
[10]	王勇, 张微微, 李永存, 张旭昀, 孙丽丽. 第一性原理计算在电化学腐蚀中的应用研究进展[J]. 材料导报, 2023, 37(12): 21110046-11.
[11]	李孝晨, 丁文艺, 朱霄汉, 郑明杰. 基于机器学习的RAFM钢中子辐照脆化预测模型研究[J]. 材料导报, 2023, 37(1): 22010142-7.
[12]	杜青铉, 张宇航, 孙伟豪, 刘蕊, 庄尧量, 夏军武. 基于混合模型的煤矸石透水混凝土透水系数预测[J]. 材料导报, 2022, 36(Z1): 22040077-5.
[13]	赵巍, 花福安, 李建平. 基于机器学习的Laves相生成焓预测研究[J]. 材料导报, 2022, 36(Z1): 21120179-5.
[14]	侯腾跃, 孙炎辉, 孙舒鹏, 肖瑛, 郑雁公, 王兢, 杜海英, 吴隽新. 机器学习在材料结构与性能预测中的应用综述[J]. 材料导报, 2022, 36(6): 20080205-12.
[15]	杨绍斌, 刘雪丽,张旭, 唐树伟. 羟基化平板孔中水合钠离子去溶剂化的第一性原理计算[J]. 材料导报, 2022, 36(1): 20110132-7.

[1]	Lanyan LIU,Jun SONG,Bowen CHENG,Wenchi XUE,Yunbo ZHENG. Research Progress in Preparation of Lignin-based Carbon Fiber[J]. Materials Reports, 2018, 32(3): 405 -411 .
[2]	Haoqi HU,Cheng XU,Lijing YANG,Henghua ZHANG,Zhenlun SONG. Recent Advances in the Research of High-strength and High-conductivity CuCrZr Alloy[J]. Materials Reports, 2018, 32(3): 453 -460 .
[3]	Yanchun ZHAO,Congyu XU,Xiaopeng YUAN,Jing HE,Shengzhong KOU,Chunyan LI,Zizhou YUAN. Research Status of Plasticity and Toughness of Bulk Metallic Glass[J]. Materials Reports, 2018, 32(3): 467 -472 .
[4]	Xinxing ZHOU,Shaopeng WU,Xiao ZHANG,Quantao LIU,Song XU,Shuai WANG. Molecular-scale Design of Asphalt Materials[J]. Materials Reports, 2018, 32(3): 483 -495 .
[5]	Yongtao TAN, Lingbin KONG, Long KANG, Fen RAN. Construction of Nano-Au@PANI Yolk-shell Hollow Structure Electrode Material and Its Electrochemical Performance[J]. Materials Reports, 2018, 32(1): 47 -50 .
[6]	Ping ZHU,Guanghui DENG,Xudong SHAO. Review on Dispersion Methods of Carbon Nanotubes in Cement-based Composites[J]. Materials Reports, 2018, 32(1): 149 -158 .
[7]	Fangyuan DONG,Shansuo ZHENG,Mingchen SONG,Yixin ZHANG,Jie ZHENG,Qing QIN. Research Progress of High Performance ConcreteⅠ:Raw Materials and Mix Proportion Design Method[J]. Materials Reports, 2018, 32(1): 159 -166 .
[8]	Guiqin HOU,Yunkai LI,Xiaoyan WANG. Research Progress of Zinc Ferrite as Photocatalyst[J]. Materials Reports, 2018, 32(1): 51 -57 .
[9]	Jianxiang DING,Zhengming SUN,Peigen ZHANG,Wubian TIAN,Yamei ZHANG. Current Research Status and Outlook of Ag-based Contact Materials[J]. Materials Reports, 2018, 32(1): 58 -66 .
[10]	Jing WANG,Hongke LIU,Pingsheng LIU,Li LI. Advances in Hydrogel Nanocomposites with High Mechanical Strength[J]. Materials Reports, 2018, 32(1): 67 -75 .

Viewed

Full text

Abstract

Cited

Shared

Discussed