机器学习在材料结构与性能预测中的应用综述

doi:10.11896/cldb.20080205

材料导报

2022, Vol. 36

Issue (6): 20080205-12 https://doi.org/10.11896/cldb.20080205

金属与金属基复合材料

机器学习在材料结构与性能预测中的应用综述

侯腾跃¹, 孙炎辉¹, 孙舒鹏¹, 肖瑛¹, 郑雁公², 王兢³, 杜海英⁴, 吴隽新⁴

1 大连民族大学信息与通信工程学院,辽宁大连 116600
2 宁波大学信息科学与工程学院,浙江宁波 315020
3 大连理工大学电子科学与技术学院,辽宁大连116024
4 大连民族大学机电工程学院,辽宁大连 116600

A Review of the Application of Machine Learning in Material Structure and Performance Prediction

HOU Tengyue¹, SUN Yanhui¹, SUN Shupeng¹, XIAO Ying¹, ZHENG Yangong², WANG Jing³, DU Haiying⁴, WU Juanxin⁴

1 College of Information ＆ Communication Engineering, Dalian Minzu University, Dalian 116600,Liaoning, China
2 Faculty of Electrical Engineer and Computer Science, Ningbo University, Ningbo 315020, Zhejiang,China
3 School of Electronic Science and Technology, Dalian University of Technology, Dalian 116024, Liaoning, China
4 College of Mechanical and Electronic Engineering, Dalian Minzu University, Dalian 116600,Liaoning, China

摘要
参考文献
相关文章
推荐阅读
Metrics

下载:

全文 ( PDF ) ( 11039KB )
输出: BibTeX | EndNote (RIS)

摘要材料是时代进步的重要标志,不同的材料结构具有不同的物理、化学性质,进而影响材料的功能特性。为了实现材料的最优化设计,常采用交叉实验的方法,通过开展大量实验探寻材料的最佳结构。该方法步骤繁琐,无法解决涉及高度非线性或大规模组合过程的复杂问题,也很难揭示材料一些罕见特性。随着计算机科学的发展,机器学习作为一种兼顾开发效率以及开发成本的方法,已经逐渐应用于材料发现、结构分析、性质预测、反向设计等诸多领域,并且在材料学研究中展现出惊人的潜力。
然而,机器学习在材料科学中的应用仍存在一些瓶颈。数据集的高效获取、异构型数据集的信息处理、基于轻量化数据集的预测模型建立、材料性能的可靠预测等问题制约着该方向的发展,这些也正是该领域亟需解决的关键问题,同时也是机器学习在材料结构与性能预测中研究的热点与难点。
近年来,关于机器学习在材料中应用的论文数量逐年增长,利用机器学习指导新型高性能材料合成的案例也比比皆是。通过采用支持向量机、神经网络等机器学习算法训练数据集来构建模型,以预测材料的结构、吸附特性、电学特性、催化性能、力学特性和热力学特性等材料性能,大大推动了机器学习在材料科学领域的发展,并且已经取得重要突破。
为了合理地归纳整理该领域的研究成果,指导后续研究,该综述从应用角度出发,讨论了机器学习在材料结构与性能预测中的数据来源、预测模型以及预测结论等,并对机器学习在未来材料领域中的发展进行了展望。

	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
	侯腾跃
	孙炎辉
	孙舒鹏
	肖瑛
	郑雁公
	王兢
	杜海英
	吴隽新

关键词: 机器学习材料结构吸附特性电学特性催化性能力学特性热力学特性

Abstract: Materials are considered as an important indicator of contemporary progress. Materials with different structures have different physical and chemical properties, which influence their functions. Several experiments have been carried out to achieve materials with optimal designs; cross-over trial is such a method that it is usually adopted. However, it is quite complicated, because it is not suitable for highly non-linear or large-scale combination processes, and it also makes it challenging to reveal rare attributes of materials. Recent advancements in computer science and machine learning have enabled the development of methods to coordinate the efficiency and cost of development in fields such as materials discovery, structural analysis, property prediction, and reverse design, demonstrating remarkable untapped potential in materials science.
Machine learning has its limitations, such as the need to ensure efficient collection of data sets, information processing of heterogeneous data sets, establishment of prediction models based on lightweight data sets, and reliability forecasting of properties of materials. Not only are these problems the key issues in the field that urgently need to be resolved, but they also form the crux of research studies on machine learning for the prediction of structures and properties of materials. Thus, solving these problems can boost the progress of materials science.
In recent years, the number of papers on the application of machine learning in material science has increased exponentially. Moreover, several studies have employed machine learning to guide the synthesis of novel materials with superior properties. Vector machines, neural networks, and other machine learning algorithms can be used to form data sets and build models for predicting material properties, such as absorption, electrical properties, catalytic performance, mechanical properties, and thermal performance. These developments have considerably contributed toward the development of materials science and have enabled achievement of major breakthroughs.
This review summarizes findings of machine learning studies for prediction of structures and properties of materials science, discussing data sources, prediction models, and conclusions, and forecasting the development of machine learning in the materials domain in the future.

Key words: machine learning material structure adsorption properties electrical properties catalytic performance mechanical properties thermodynamic properties

出版日期: 2022-03-25 发布日期: 2022-03-21

ZTFLH:	TP181
	TB34

基金资助: 辽宁省自然科学基金资助项目(20180550634)

通讯作者: syh@dlnu.edu.cn;xiaoying@dlnu.edu.cn

作者简介: 侯腾跃,2019年6月毕业于大连民族大学通信工程专业,获得学士学位。现为大连民族大学硕士研究生,目前主要研究领域为化学传感器。
孙炎辉,大连民族大学信息与通信工程学院工程师、硕士研究生导师。2005年毕业于大连民族大学电子信息工程专业,获学士学位; 2010年毕业于大连海事大学通信与信息系统专业,获硕士学位; 2021年毕业于大连理工大学微电子学与固体电子学专业,获博士学位。2005年加入大连民族大学信息与通信工程学院。目前研究重点是化学传感器和传感材料。致力于将沸石基复合材料或金属氧化物复合材料作为气体传感材料来检测VOC气体。
肖瑛,大连民族大学信息与通信工程学院教授、硕士研究生导师。2001年毕业于哈尔滨工程大学信息处理专业获学士学位,2004年毕业于哈尔滨工程大学通信与信息系统专业,获硕士学位,2006年毕业于哈尔滨工程大学信号与信息处理专业,获得博士研究生学位,2006年加入大连民族大学信息与通信工程学院。目前研究的重点是信号及信息处理,人工智能神经网络及其应用。在理论和算法上均取得了一定成果,发表论文50余篇。

引用本文:

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.
HOU Tengyue, SUN Yanhui, SUN Shupeng, XIAO Ying, ZHENG Yangong, WANG Jing, DU Haiying, WU Juanxin. A Review of the Application of Machine Learning in Material Structure and Performance Prediction. Materials Reports, 2022, 36(6): 20080205-12.

链接本文:

http://www.mater-rep.com/CN/10.11896/cldb.20080205 或 http://www.mater-rep.com/CN/Y2022/V36/I6/20080205

1 Rajan K. Annual Review of Materials Research, 2015, 45, 153.
2 Jain A,Ong S P,Hautier G,et al. APL Mater,2013, 1(1), 1049.
3 Correa-Baena J P, Hippalgaonkar K, van Duren J, et al. Joule,2018,2(8), 1410.
4 Agrawal A, Deshpande P D, Cecen A, et al. Integrating Materials and Manufacturing Innovation, 2014, 3(1), 90.
5 Karak S K, Chatterjee S, Bandopadhyay S. Powder Technology, 2015, 274, 217.
6 Pilania G, Mannodi-Kanakkithodi A, Uberuaga B P, et al. Scientific Reports, 2016, 6 (1), 19735.
7 Jinnouchi R, Asahi R. Journal of Physical Chemistry Letters, 2017, 8(17), 4279.
8 Zhou T, Jhamb S, Liang X, et al. Chemical Engineering Science, 2018, 183, 95.
9 Aghaji M Z, Fernandez M, Boyd P G, et al. European Journal of Inorganic Chemistry, 2016, 2016(27), 4505.
10 Sharma V, Wang C, Lorenzini R G, et al. Nature Communications, 2014, 5 (1), 4845.
11 Madaan N, Shiju N R, Rothenberg G. Catalysis Science & Technology, 2016,6, 125.
12 Gómez-Bombarelli R, Aguilera-Iparraguirre J, Hirzel T D, et al. Nature Materials, 2016, 15 (10), 1120.
13 Stanev V, Oses C, Kusne A G, et al. npj Computational Materials, 2018, 4 (1), 29.
14 Olivares-Amaya R. Energy & Environmental Science, 2011,4(12),4849.
15 Zhang X, Cui J, Zhang K, et al. Journal of Chemical Information & Mo-deling, 2019, 59 (11), 4636.
16 Moliner M, Román-Leshkov Y, Corma A. Accounts of Chemical Research, 2019, 52 (10), 2971.
17 Jensen Z, Kim E, Kwon S, et al. ACS Central Science, 2019,5(5), 892.
18 Balachandran P, Emery A, Gubernatis J, et al. American Physical Society, 2018, 2(4), 043802.
19 Ali A, Park H, Mall R, et al. Chemistry of Materials, 2020, 32(7), 2998.
20 Ghanshyam P, Balachandran P V, Chiho K, et al. Frontiers in Materials, 2016, 3, 19.
21 Park H, Mall R, Alharbi F H, et al. Journal of Physical Chemistry A, 2019, 123(33), 7323.
22 Ono L K, Juarez-Perez E J, Qi Y. ACS Applied Materials & Interfaces, 2017, 9(36), 30197.
23 Charles B, Dillon J, Weber O J, et al. Journal of Materials Chemistry A, 2017, 5, 22495.
24 Saliba M, Matsui T, Seo J Y, et al. Energy & Environmental Science, 2016, 9(6), 1989.
25 Oliynyk A O, Mar A. Accounts of Chemical Research, 2018, 51(1), 59.
26 Oliynyk A O, Adutwum L A, Rudyk B W, et al. Journal of the American Chemical Society, 2017, 139(49), 17870.
27 Hautier G, Fischer C C, Jain A, et al. Chemistry of Materials, 2010, 22(12), 3762.
28 Balachandran P V, Theiler J, Rondinelli J M, et al. Scientific Reports, 2015, 5(1), 13285.
29 Legrain F, Carrete J, Roekeghem A V, et al. The Journal of Physical Chemistry B, 2018, 122(2), 625.
30 Oliynyk A O, Antono E, Sparks T D, et al. Chemistry of Materials, 2016, 28(20), 7324.
31 Takahashi K, Takahashi L. Journal of Physical Chemistry Letters, 2019, 10(2), 283.
32 Kim E, Huang K, Saunders A, et al. Chemistry of Materials, 2017, 29(21), 9436.
33 Frey N C, Wang J, Vega Bellido G I, et al. ACS Nano, 2019, 13(3), 3031.
34 Zhao Y, Cui Y, Xiong Z, et al. ACS Omega, 2020, 5(7), 3596.
35 Ohno H, Mukae Y. The Journal of Physical Chemistry C, 2016, 120(42), 23963.
36 Toyao T, Suzuki K, Kikuchi S, et al. Journal of Physical Chemistry C Nanomaterials & Interfaces, 2018,122(15), 8315.
37 Fanourgakis G S, Gkagkas K, Tylianakis E, et al. The Journal of Physical Chemistry A, 2019, 123(28), 6080.
38 Zhou L. Energy Sources, 2019, 41 (13-18), 1960.
39 Fernandez M, Barnard A S. ACS Combinatorial Science, 2016, 18(5), 243.
40 Fernandez M, Boyd P G, Daff T D, et al. Journal of Physical Chemistry Letters,2014,5(17), 3056.
41 Sendek A D, Cubu K E D, Antoniuk E R, et al. Chemistry of Materials, 2019, 31(2), 342.
42 Zhang Y, He X, Chen Z, et al. Nature Communications, 2019, 10(1), 5260.
43 Joshi R P, Eickholt J L, Li L, et al. ACS Applied Materials & Interfaces,2019,11(20), 18494.
44 Eremin R A, Zolotarev P N, Ivanshina O Y, et al. The Journal of Physical Chemistry C, 2017, 121(51), 28293.
45 Choudhary K, Bercx M, Jiang J, et al. Chemistry of Materials, 2019, 31(15), 5900.
46 Zeeshan A, Xie T, Chinmay M, et al. ACS Central Science, 2018,4(8), 996.
47 Mannodi-Kanakkithodi A, Pilania G, Huan T D, et al. Scientific Reports, 2016, 6(1), 20952.
48 Mannodi-Kanakkithodi A, Chandrasekaran A, Kim C, et al. Materials Today, 2017, 21(7), 785.
49 Kim C, Pilania G, Ramprasad R. Journal of Physical Chemistry C, 2016,120(27), 14575.
50 Williams T, McCullough K, Lauterbach J A. Chemistry of Materials, 2020, 32(1), 157.
51 Rueck M, Garlyyev B, Mayr F, et al. The Journal of Physical Chemistry Letters, 2020, 11(5), 1773.
52 Tran K, Ulissi Z W. Nature Catalysis, 2018, 1(9), 696.
53 Thornton A W, Winkler D A, Liu M S, et al. RSC Advances, 2015, 5, 44361.
54 Ulissi Z W, Tang M T, Xiao J, et al. ACS Catalysis, 2017, 7(10), 6600.
55 Li Z, Ma X, Xin H. Catalysis Today, 2017, 280, 232.
56 Li Z, Wang S, Wei S C, et al. Journal of Materials Chemistry A, 2017, 5, 24131.
57 Zhang Y, Ling C. npj Computational Materials, 2018, 4(1), 25.
58 Pronobis W, Tkatchenko A,Müller K R. Journal of Chemical Theory & Computation, 2018, 14(6), 2991.
59 Brańka A C, Heyes D M. Physica Status Solidi, 2009,246(9), 2063.
60 Coudert F X. Physical Chemistry Chemical Physics Pccp, 2013, 15(38), 16012.
61 Pophale R, Cheeseman P A, Deem M W. Physical Chemistry Chemical Physics, 2011, 13(27), 12407.
62 Gaillac R, Chibani S, Coudert F X. Chemistry of Materials, 2020, 32(6), 2653.
63 Evans J D, Coudert F X. Chemistry of Materials, 2017, 29(18), 7833.
64 Tehrani A M, Oliynyk A O, Parry M, et al. Journal of the American Chemical Society, 2018, 140(31), 9844.
65 Wang X Y, Han D, Hong Y, et al. ACS Omega, 2019, 4(6), 10121.
66 Gallagher B, Rever M, Loveland D, et al. Materials & Design, 2020, 190, 108541.
67 Deng Z, Chen C,Tran R, et al. Physical Review Materials, 2017, 1(4), 043603.
68 Niu C, Rao Y, Windl W, et al. npj Computational Materials,2019, 5(1), 120.
69 Teichert G H, Natarajan A R, Garikipati K, et al. Computer Methods in Applied Mechanics and Engineering, 2019, 353, 201.
70 Schmidt J, Shi J, Borlido P, et al. Chemistry of Materials, 2017, 29(12), 5090.
71 Schleder G R, Acosta C M, Fazzio A. ACS Applied Materials & Interfaces, 2020,12(18), 20149.
72 Isayev O, Oses C, Toher C, et al. Nature Communications, 2017,8(1),15679.

[1]	宋庆功, 常斌斌, 董珊珊, 顾威风, 康建海, 王明超, 刘志锋. 机器学习及其在材料研发中的作用[J]. 材料导报, 2022, 36(1): 20080139-7.
[2]	陈卫英, 陈真勇, 杨在君, 匙峰, 黎云祥. 胶原-乙酸混合溶液静电纺丝可纺性及电纺胶原膜力学特性评估[J]. 材料导报, 2021, 35(z2): 516-519.
[3]	郑健飞, 朱思龙, 聂龙辉. Cu₂O/g-C₃N₄异质结光催化材料的研究进展[J]. 材料导报, 2021, 35(Z1): 33-41.
[4]	张猛, 花福安, 赵巍. 基于机器学习的高熵合金生成相预测研究[J]. 材料导报, 2021, 35(Z1): 331-335.
[5]	郑玉杰, 梁鑫斌, 张起, 孙文博, 施童超, 杜鹃, 孙宽. 基于分子指纹及机器学习回归模型的有机光伏材料效率预测[J]. 材料导报, 2021, 35(8): 8207-8212.
[6]	龙泽清, 宋慧, 张光明. 卤氧化铋光催化剂改性及应用研究进展[J]. 材料导报, 2021, 35(5): 5067-5074.
[7]	毛韦达, 赵林. 溶胶凝胶法合成La_0.5Sr_0.5Co_0.8Mn_0.2O_3-δ钙钛矿及其催化性质[J]. 材料导报, 2021, 35(24): 24001-24005.
[8]	夏伟, 许金余, 聂良学, 王志航, 黄哲, 姚廒. 冲击荷载下纳米碳纤维混凝土的动态受压力学特性[J]. 材料导报, 2021, 35(22): 22063-22071.
[9]	王立辉, 孙刚, 李丹, 夏惠芬, 李文卓, 许天寒, 张红玉, 张思琪. 新型抗盐聚合物溶液的性能及驱油效果评价[J]. 材料导报, 2021, 35(2): 2171-2177.
[10]	米晓希, 汤爱涛, 朱雨晨, 康靓, 潘复生. 机器学习技术在材料科学领域中的应用进展[J]. 材料导报, 2021, 35(15): 15115-15124.
[11]	汪海波, 徐成, 王梦想, 徐颖. 碳化龄期对水泥砂浆动态力学特性影响试验研究[J]. 材料导报, 2021, 35(12): 12087-12091.
[12]	王运, 张昌明, 张昱. 航空Al7050合金的静动态力学特性研究及JC本构模型构建[J]. 材料导报, 2021, 35(10): 10096-10102.
[13]	盖海东, 冯春花, 董一娇, 赵倩, 李东旭. 纳米压痕技术应用于水泥基材料的研究进展[J]. 材料导报, 2020, 34(7): 7107-7114.
[14]	吴雷, 彭犇, 周军, 刘长波, 岳昌盛, 田玮, 宋永辉, 姜磊. 碳基非贵金属电催化剂研究进展[J]. 材料导报, 2020, 34(23): 23009-23019.
[15]	蒋招绣, 高光发. 碳化硼陶瓷的力学特性和破坏行为研究进展[J]. 材料导报, 2020, 34(23): 23064-23073.

[1]	Yanzhen WANG, Mingming CHEN, Chengyang WANG. Preparation and Electrochemical Properties Characterization of High-rate SiO₂/C Composite Materials[J]. Materials Reports, 2018, 32(3): 357 -361 .
[2]	Yimeng XIA, Shuai WU, Feng TAN, Wei LI, Qingmao WEI, Chungang MIN, Xikun YANG. Effect of Anionic Groups of Cobalt Salt on the Electrocatalytic Activity of Co-N-C Catalysts[J]. Materials Reports, 2018, 32(3): 362 -367 .
[3]	Qingshun GUAN,Jian LI,Ruyuan SONG,Zhaoyang XU,Weibing WU,Yi JING,Hongqi DAI,Guigan FANG. A Survey on Preparation and Application of Aerogels Based on Nanomaterials[J]. Materials Reports, 2018, 32(3): 384 -390 .
[4]	Lijing YANG,Zhengxian LI,Chunliang HUANG,Pei WANG,Jianhua YAO. Producing Hard Material Coatings by Laser-assisted Cold Spray:a Technological Review[J]. Materials Reports, 2018, 32(3): 412 -417 .
[5]	Zhiqiang QIAN,Zhijian WU,Shidong WANG,Huifang ZHANG,Haining LIU,Xiushen YE,Quan LI. Research Progress in Preparation of Superhydrophobic Coatings on Magnesium Alloys and Its Application[J]. Materials Reports, 2018, 32(1): 102 -109 .
[6]	Wen XI,Zheng CHEN,Shi HU. Research Progress of Deformation Induced Localized Solid-state Amorphization in Nanocrystalline Materials[J]. Materials Reports, 2018, 32(1): 116 -121 .
[7]	Xing LIANG, Guohua GAO, Guangming WU. Research Development of Vanadium Oxide Serving as Cathode Materials for Lithium Ion Batteries[J]. Materials Reports, 2018, 32(1): 12 -33 .
[8]	Hao ZHANG,Yongde HUANG,Yue GUO,Qingsong LU. Technological and Process Advances in Robotic Friction Stir Welding[J]. Materials Reports, 2018, 32(1): 128 -134 .
[9]	Laima LUO, Mengyao XU, Xiang ZAN, Xiaoyong ZHU, Ping LI, Jigui CHENG, Yucheng WU. Progress in Irradiation Damage of Tungsten and Tungsten AlloysUnder Different Irradiation Particles[J]. Materials Reports, 2018, 32(1): 41 -46 .
[10]	Fengsen MA,Yan YU,Jie ZHANG,Haibo CHEN. A State-of-the-art Review of Cytotoxicity Evaluation of Biomaterials[J]. Materials Reports, 2018, 32(1): 76 -85 .

Viewed

Full text

Abstract

Cited

Shared

Discussed