人工神经网络在材料科学中的研究进展

doi:10.11896/cldb.19080073

Abstract
Figure/Table
References
Related Citation (1)

Download:

Full Text ( PDF ) (5907KB)
Export: BibTeX | EndNote (RIS)

Abstract The traditional “trial and error” material research methods have the disadvantages of long cycle, high cost and great contingency, which can't meet the needs of modern material research and development. It has become a research hotspot all over the world to improve the pertinence of research and development, shorten the cycle of material research and development, and reduce the cost of material research and development. With the continuous accumulation of data and the continuous development of computer technology, data intensive material scientific discovery has gradually become the fourth paradigm of scientific research. It is the current research trend of materials to find the “gene” that can reflect the material's intrinsic characteristics from a large number of data. The artificial neural network method is widely used in the field of materials science because of its advantages of self-learning, associative storage and high-speed search for optimal solution. Researchers use machine learning models such as artificial neural network to mine the experimental or theoretical calculation data of materials under the guidance of expert experience and theory, it can be transformed into reliable knowledge and can assist intelligent decision-making, so as to establish a one-to-one mapping relationship between microstructure and macro performance of materials.
In the early days, artificial neural network was mainly used to find the relationship between the macro parameters of materials and the macro performance of materials, such as the composition design of materials, the optimization of process parameters, and the search of environmental para-meters that affect the performance of materials. With the development of computer technology and the rise of computer simulation, artificial neural network was used to learn the calculation results of the first principle. It is used to describe the interaction between the systems at the atomic scale, so as to achieve the balance between the calculation speed and accuracy. The convolution neural network methods, such as a deep neural network method, has unique advantages in image processing, which makes it more widely used in the field of material characterization, such as microstructure identification and reconstruction in SEM and TEM. With the help of artificial neural network and other methods, it is a possible way to realize the ultimate goal of material design to realize the cross scale relationship between micro, meso and macro properties of materials.
This paper reviews the development history of artificial neural network, explains the principle of BP neural network and convolution neural network which are widely used in the field of materials at present, summarizes the application of artificial neural network in the field of material macro performance, calculation simulation, material characterization, etc., probes into the shortcomings of the application of artificial neural network in the field of materials, and finally discusses the development trend of artificial neural network in materials research.

Key words： artificial neural network BP neural network (BP-NN) performance prediction machine learning convolutional network

Published: 17 November 2020

CLC number:	TP183
	TB3

Fund:This work was supported by the National Key Research and Development Program of China (2016YFB0301100), Natural Science Foundation of Chongqing (cstc2017jcyjBX0040), National Natural Science Foundation of China (51531002), National Defense Basic Scientific Research Program of China (JCKY2017201C016).

About author:: Jing Kang, a master student, graduated from Chongqing University in 2017 with a bachelor's degree. Now as a master student in Chongqing University, under the guidance of Professor Aitao Tang. The research is carried out on the application of artificial neural networks in material science.
Aitao Tang, Ph.D., professor, doctoral supervisor. Key researchers of National Engineering Research Center for Magnesium Alloys. Focusing on magnesium alloy, aluminum alloy and composite materials. Mainly engaged in material database, material simulation and high performance materials research. In 1984, she gra-duated from the department of metallurgy of Chongqing University. In 2004, she received her Ph.D. degree at the School of Materials of Chongqing University. She ser-ved as the teaching staff of five undergraduate courses and one postgraduate course successively. She is the backbone teacher of the applied course of computer in material science and engineering. As the holder, she won a second prize of national science and technology progress award, a first prize of science and technology progress award of the ministry of education, a first prize of science and technology progress award of a Chinese university, and a third prize of Chongqing science and technology progress award. And has obtained a number of national authorized invention patents, published more than 60 important thesis.

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	KANG Jing
	MI Xiaoxi
	WANG Hailian
	WU Lu
	SUN Kai
	TANG Aitao1

Cite this article:

KANG Jing,MI Xiaoxi,WANG Hailian, et al. Research Progress of Artificial Neural Networks in Material Science[J]. Materials Reports, 2020, 34(21): 21172-21179.

URL:

http://www.mater-rep.com/EN/10.11896/cldb.19080073 OR http://www.mater-rep.com/EN/Y2020/V34/I21/21172

[1]	Wang H, Xiang Y, Xiang X D, et al.Science & Technology Review, 2015, 33(10), 13(in Chinese).
	汪洪, 向勇, 项晓东, 等.科技导报, 2015, 33 (10), 13.
[2]	He P, Lin P P.Materials Review A: Review Papers, 2019, 33(1), 156(in Chinese).
	何鹏, 林盼盼.材料导报:综述篇, 2019, 33(1), 156
[3]	Himanen L, Geurts A, Foster A S, et al.Advanced Science, DOI: 10.1002/advs.201900808.
[4]	Agrawal A, Choudhary A.APL Materials, DOI: 10.1063/1.4946894.
[5]	Li B, Du Y, et al.Materials China, 2018, 37(7), 264(in Chinese)
	李波, 杜勇, 等.中国材料进展, 2018, 37(7), 264
[6]	Bird C L, Frey J G.Chemical Socical Reviews, 2013, 42(16), 6754.
[7]	Hosni M, Abnane I, Idri A, et al.Computer Methods and Programs in Biomedicine, 2019, 177, 89.
[8]	Savas S, Topaloglu N, Kazci O, et al.Journal of Medical Systems, DOI: 10.1007/s10916-019-1421-3.
[9]	Mater A C, Coote M L.Journal of Chemical Information and Modeling, 2019, 59(6), 2545.
[10]	Ranade R, Alqahtani S, Farooq A, et al. Fuel, 2019, 251, 276.
[11]	Mehrpouya M, Gisario A, Huang H, et al.Optics and Laser Technology, 2019, 118, 159.
[12]	Chen G, Wang H Y, Bezold A, et al. Composite Structures, 2019, 223(SEP), 110.951.1.
[13]	Ramachandra S, Durodola J F, Fellows N A, et al.International Journal of Fatigue, 2019, 126, 112.
[14]	Gubaev K, Podryabinkin E V, Hart G L W, et al.Computational Mate-rials Science, 2019, 156, 148.
[15]	Jin H P, Yang W Y, Yan L.Proceedings of the Estonian Academy of Sciences, 2012, 61(4), 296.
[16]	Maier W F, Stowe K, Sieg S.Angewandte Chemie Internation Edition, 2007, 46(32), 6016.
[17]	Huang N C. Application of artificial neural network in rubber damper design. Master's Thesis, Qingdao University of Science and Technology, China, 2018(in Chinese).
	黄年昌. 人工神经网络技术在橡胶减振器设计中的应用研究. 硕士学位论文, 青岛科技大学, 2018.
[18]	Mcculloch W S, Pitts W. Bulletin of Mathematical Biology, 1990, 52(1-2), 99.
[19]	Han M.Artificial neural network foundation, Dalian University of Techno-logy Press, China, 2014(in Chinese).
	韩敏.人工神经网络基础, 大连理工大学出版社, 2014.
[20]	Dai Y W, Lei Z Y.Computer and Modernization, 2016(11), 67(in Chinese).
	戴永伟, 雷志勇.计算机与现代化, 2016(11), 67.
[21]	Zhang Y Z.Cognitive Systems Research, 2019, 57, 228.
[22]	Chen Y, Ma H W, Dong M.Insight, 2018, 60(4), 194.
[23]	Majumder H, Maity K.Applied Soft Computing, 2018, 70, 665.
[24]	Yazdanmehr M, Anijdan S H M, Bahrami A.Computational Materials Science, 2009, 44(4), 1218.
[25]	Zhu H W. Research of the nonlinear identification algorithm for the thermal process system. Master's Thesis, North China Electric Power University, China, 2018(in Chinese).
	朱洪伟. 热工系统的非线性辨识算法研究. 硕士学位论文, 华北电力大学, 2018.
[26]	Armaghani D J, Shoib R S N S B, Faizi K, et al.Neural Computing & Applications, 2017, 28(2), 391.
[27]	Hinton G E, Salakhutdinov R R.Science, 2006, 313(5786), 504.
[28]	Zhou Z H. Machine learning, Tsinghua University Press, China, 2016(in Chinese).
	周志华. 机器学习, 清华大学出版社, 2016.
[29]	Liu Y, Zhou X L, Hu Z K, et al.China Forestry Science and Technology, 2019, 4(1), 115(in Chinese).
	刘英, 周晓林, 胡忠康, 等.林业工程学报, 2019, 4(1), 115.
[30]	Tung Tran, Ramakanth Kavuluru. Journal of Biomedical Informatics, 2019, 75, S138.
[31]	Amin-Naji M, Aghagolzadeh A, Ezoji M.Information Fusion, 2019, 51, 201.
[32]	Liu B, Tang A T, et al.Materials Review B:Research Papers, 2011, 28(9), 117(in Chinese).
	刘彬, 汤爱涛, 潘复生,等.材料导报:研究篇, 2011, 28(9), 117.
[33]	Hu X B, Wang J C, Wang Y Y, et al.Computational Materials Science, 2018, 155, 331.
[34]	Paul S, Bhattacharjee S.International Journal of Modeling Simulation and Scientific Computing, 2018, 9(6), S1.
[35]	Maleki E, Unal O, Kashyzadeh K R.International Journal of Fatigue, 2018, 116(S1), 48.
[36]	Chu L H, Wang L, Li H Y, et al.Journal of Netshape Forming Enginee-ring, 2007, 9(6), 125(in Chinese).
	储林华, 王练, 李恒羽, 等.精密成形工程, 2007, 9(6), 125.
[37]	Patowari P K, Saha P, Mishra P K.International Journal of Advanced Manufacturing Technology, 2010, 51(5-8), 627.
[38]	Li C, Kui B, Wang J W, et al.Journal of Netshape Forming Engineering, 2007, 9(5), 134(in Chinese).
	李超, 槐宝, 王继伟, 等.精密成形工程, 2007, 9(5), 134.
[39]	Hua L Y, Xia Q X, Yu G F, et al.Journal of Netshape Forming Enginee-ring, 2007, 9(1),103(in Chinese).
	华路延, 夏琴香,俞高峰, 等.精密成形工程, 2007, 9(1), 103.
[40]	Millán-Ocampo D, Arianna P B, González-Rodríguez J, et al.Entropy, 2018, 20(6), 409.
[41]	Thankachan T, Prakash K S, Pleass C D, et al.International Journal of Hydrogen Energy, 2017, 42(47), 28612.
[42]	Kemp R, Cottrell G A, Bhadeshia H K D H, et al. Journal of Nuclear Materials,2006, 348(3), 311.
[43]	Mathew J, Parfitt D, Wilford K, et al. Journal of Nuclear Materials, 2018, 502(S1), 311.
[44]	Wu X J, Yang J L.Bulletin of National Natural Science Foundation of China, 2018, 32(1), 85 ( in Chinese).
	武晓君, 杨金龙.中国科学基金, 2018, 32(1), 85.
[45]	Deng J K. Atomistic simulations of aging effects in shape memory alloys. Doctor's Thesis, Xi'an Jiaotong Univeisity, China, 2011.
	邓俊楷. 形状记忆合金中时效效应的原子模拟. 博士学位论文, 西安交通大学, 2011.
[46]	Car R, Parrinello M.Physical Review Letters, 1985, 55(22), 2471.
[47]	Malinov S, Sha W. JOM, 2005, 57(11), 54.
[48]	Seko A, Takahashi A, Tanaka I.Physical Review B, DOI:10.1103/PhysRevB.92.054113.
[49]	Ye W, Chen C, Wang Z, et al. Nature Communications, 2018, 9(1), 3800.
[50]	Zong H X, Pilania G, Ding X D, et al.Npj Computational Materials, DOI: 10.1038/s41524-018-0103-x.
[51]	Terentyev D, Bonny G, Castin N, et al.Journal of Nuclear Materials, 2011, 409(2), 167.
[52]	Pascuet M I, Castin N, Becquart C S, et al.Journal of Nuclear Materials, 2011, 412(1), 106.
[53]	Castin N, Messina L, Domain C, et al.Physical Review B, DOI: 10.1103/PhysRevB.95.214117.
[54]	Castin N, Pascuet M I, Messina L, et al.Computational Materials Science, 2018, 148, 116.
[55]	Botu V, Batra R, Chapman J, et al.Journal of Physical Chemistry C, 2017, 121(1), 511.
[56]	Pun G P P, Batra R, Ramprasad R, et al.Nature Communications, 2019, 10(1), 2339.
[57]	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.
[58]	Hautier G, Fischer C C, Jain A, et al. Chemistry of Materials, 2010, 22(12), 3762.
[59]	Park W B, Chung J, Jung J, et al.IUCrJ, 2017, 4, 486.
[60]	Oviedo F, Ren Z, Sun S, et al.Npj Computational Materials, DOI: 10.1038/s41524-019-0196-x.
[61]	Vecsei P M, Choo K, Chang J, et al.Physical Review B, DOI: 10.1103/PhysRevB.99.245120.
[62]	Chen L L, Wei B, et al.High Power Laser and Particle Beams, 2018, 30(9), 117(in Chinese).
	陈乐林, 魏彪, 等.强激光与粒子束, 2018, 30(9), 117.
[63]	De AlbuquerqueV H C, Cortez P C, De Alexandria A R, et al. Nondestructive Testing and Evaluation, 2008, 23(4), 273.
[64]	Iwahori Y, Kawanaka H, Fukui S, et al.Journal of Intelligent Manufacturing, 2005, 16(6), 715.
[65]	Coquelin L, Fischer N, Feltin N, et al.Materials Research Express, DOI: 10.1088/2053-1591/ab1bb4.
[66]	Barry T J, Kesharaju M, Nagarajah C R, et al.Journal of Composite Materials, 2016, 50(7), 861.
[67]	Madsen J, Liu P, Kling J, et al.Advanced Theory and Simulations, DOI: 10.1002/adts.201800037.
[68]	Chen F-C, Jahanshahi M R.Ieee Transactions on Industrial Electronics, 2018, 65(5), 4392.
[69]	Paulic M, Mocnik D, Ficko M, et al.Tehnicki Vjesnik-Technical Gazette, 2015, 22(6), 1419.