基于混合学习算法的材料计算数据误差估计

doi:10.16182/j.issn1004731x.joss.201810030

系统仿真学报 ›› 2018, Vol. 30 ›› Issue (10): 3843-3853.doi: 10.16182/j.issn1004731x.joss.201810030

基于混合学习算法的材料计算数据误差估计

王娟^1,2, 杨小渝¹, 王宗国¹, 任杰^1,2, 赵旭山¹

1. 中国科学院计算机网络信息中心北京 100190;
2. 中国科学院大学北京 100049

收稿日期:2016-09-08 修回日期:2016-12-19 出版日期:2018-10-10 发布日期:2019-01-04
作者简介:王娟(1984-),女,北京,博士,研究方向为人工智能,材料信息学;杨小渝(1968-),男,北京,博士,研究员,研究方向为科研信息化,材料信息学,科学数据管理。
基金资助:
国家自然科学基金 (61472394, 11547177)

Error Estimation for Material Simulation Data Based on Hybrid Learning Algorithm

Wang Juan^1,2, Yang Xiaoyu¹, Wang Zongguo¹, Ren Jie^1,2, Zhao Xushan¹

1. Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2016-09-08 Revised:2016-12-19 Online:2018-10-10 Published:2019-01-04

摘要/Abstract

摘要： 鉴于低误差的基于密度泛函理论的材料计算模拟数据在新材料设计与发现中的重要性,提出一种基于BP神经网络和粒子群优化(particle swarm optimization, PSO)混合学习算法的材料计算数据误差估计建模方法。结合PSO的全局搜索和BP算法的局部搜索优点,将不含速度项的简化PSO算法和BP算法相结合,提出一种PSO和BP混合的学习方法(tsPSO-BP),用于训练材料计算模拟数据误差估计神经网络模型,并以立方晶系二元合金弹性常数计算模拟数据误差估计为应用实例。应用结果表明tsPSO-BP训练后的弹性常数计算模拟误差预测神经网络模型预测的C₁₁,C₁₂和C₄₄的计算模拟数据误差的准确率分别达到88.19%,87.83%和88.26%。

关键词: 材料计算模拟数据误差估计, 神经网络, 粒子群优化, BP算法, 混合学习方法

Abstract: In order to obtain high quality material simulation data from Density Functional Theory material calculation software package, a modeling method based on BP neural network was proposed to build model estimating the error of material simulation data. A novel hybrid algorithm combining simple particle swarm optimization algorithm that excludes speed item with BP algorithm, also referred to tsPSO-BP, was proposed to optimize the connection weights of the BP neural network. The hybrid learning algorithm not only makes use of strong global searching ability of the PSO, but also strong local searching ability of the BP algorithm. The BP neural network model was trained using tsPSO-BP on the dataset of experimental and calculation data of elastic constants for binary alloys with cubic crystal system, and the results show that the prediction accuracy of the error of C₁₁, C₁₂ and C₄₄ were 88.19%, 87.83% and 88.26%, respectively.

Key words: error estimation for material simulation data, neural network, particle swarm optimization, BP algorithm, hybrid learning algorithm

中图分类号:

王娟, 杨小渝, 王宗国, 任杰, 赵旭山. 基于混合学习算法的材料计算数据误差估计[J]. 系统仿真学报, 2018, 30(10): 3843-3853.

Wang Juan, Yang Xiaoyu, Wang Zongguo, Ren Jie, Zhao Xushan. Error Estimation for Material Simulation Data Based on Hybrid Learning Algorithm[J]. Journal of System Simulation, 2018, 30(10): 3843-3853.

参考文献

[1] National Science and Technology. Materials Genome Initiative for Global Competitiveness [R]. Washington DC, USA: Office of Science and Technology Policy, 2011.
[2] Hohenberg P, Kohn W.Inhomogeneous Electron Gas[J]. Physical Review (S1550-2376), 1964, 136(3B): B864-B871.
[3] Parr R G, Yang W.Density-Functional Theory of atoms and molecules [M]. New York, USA: Oxford University Press, 1989.
[4] 王娟, 杨小渝, 王宗国, 等. SQS二元合金设计的高通量方法和技术研究[J]. 计算机工程与科学, 2016, 38(255): 401-410.
Wang Juan, Yang Xiaoyu, Wang Zongguo, et al.A high-throughput Computational Approach for SQS Binary Alloy Design[J]. Computer Engineering & Science, 2016, 38(3):401-410.
[5] 王卓, 杨小渝, 郑宇飞, 等. 材料基因组框架下的材料集成设计及信息平台初探[J]. 科学通报, 2013, 58(35): 3733-3742.
Wang Zhuo, Yang Xiaoyu, Zheng Yufei, et al.Integrated Materials Design and Informatics Platform within the Materials Genome Framework[J]. Chin Sci Bull (Chin Ver), 2013, 58: 3733-3742.
[6] Xiujung Wang, Lihong Hu, Laiho Wong, et al.A Combined First-principles Calculation and Neural Networks Correction Approach for Evaluating Gibbs Energy of Formation[J]. Molecular Simulation (S0892-7022), 2004, 30(1): 9-15.
[7] Ozerdem M S, Kolukisa S.Artificial Neural Network Approach to Predict the Mechanical Properties of Cu-Sn-Pb-Zn-Ni cast alloys[J]. Materials & Design (S0264-1275), 2009, 30(3): 764-769.
[8] 邓万宇, 郑庆华, 陈琳, 等. 神经网络极速学习方法研究[J]. 计算机学报, 2010, 33(2): 279-287.
Deng Wanyu, Zheng Qinglin, Chen Lin, et al.Research on Extreme Learning of Neural Networks[J]. Chinese Journal of Computers, 2010, 33(2): 279-287.
[9] Rumelhart D E, Hinton G E, Williams R J.Learning Representations by Back-propagating Errors [M]. USA: MIT Press, 1986: 533-536.
[10] Kennedy J, Eberhart R C.Particle Swarm Optimization [C]// Proc. of the IEEE Conf. on Neural Networks, IV. Perth, Australia: IEEE Press, 1995: 1942-1948.
[11] Shi Y, Eberhart R C.A Modified Particle Swarm Optimizer[C]// Proc of the 1998 IEEE ECP. Piscataway, NJ, USA: IEEE, 1998: 69-73.
[12] 胡旺, 李志蜀. 一种更简化而高效的粒子群优化算法[J]. 软件学报, 2007, 18(4): 861-868.
Hu Wang, Li Zhishu.A Simpler and More Effective Particle Swarm Optimization Algorithm[J]. Journal of Software, 2007, 18(4): 861-868.
[13] 张捍东, 陶刘送. 粒子群优化BP算法在液压系统故障诊断中应用[J]. 系统仿真学报, 2016, 28(5): 1186-1190.
Zhang Handong, Tao Liusong.Application of PSO-BP Algorithm in Hydraulic System Fault Diagnosis[J]. Journal of System Simulation (S1004-731X), 2016, 28(5): 1186-1190.
[14] 曾万里, 危韧勇, 陈红玲. 基于改进PSO算法的BP神经网络的应用研究[J]. 计算机技术与发展, 2008, 18(4): 49-51.
Zeng Wanli, Wei Renyong, Chen Hongling.Research and Application of BP Neural Network Based on Improved PSO Algorithm[J]. Computer Technology and Development, 2008, 18(4): 49-51.
[15] Wang Z, Zhao X, Wan B, et al.Research of BP Neural Network based on Improved Particle Swarm Optimization Algorithm[J]. Journal of Networks (S1796-2056), 2013, 8(4): 947-954.
[16] Zhang J R, Zhang J, Loc T M, et al.A Hybrid Particle Swarm Optimization-Backpropagation Algorithm for Feedforward Neural Network Training[J]. Applied Mathematics and Computation (S0096-3003), 2007, 185(2): 1026-1037.
[17] Han F, Gu T Y, Ju S G.An Improved Hybrid Algorithm Based on PSO and BP for Feedforward Neural Networks[J]. International Journal of Digital Content Technology and its Application (S1975-9339), 2011, 5(2): 106-115.
[18] 阎守胜. 固体物理基础 [M]. 北京: 北京大学出版社, 2011: 42-43.
Yan Shousheng.Solid State Physics [M]. Beijing, China: Peking University Press, 2011: 42-43.
[19] Gritsenko O V, Schipper P R T, Baerends E J. Approximation of the Exchange-Correlation Kohn-Sham Potential with a Statistical Average of Different Orbital Model Potentials[J]. Chemical Physics Letters (S0009-2614), 1999, 302(3-4): 199-207.

基于混合学习算法的材料计算数据误差估计

Error Estimation for Material Simulation Data Based on Hybrid Learning Algorithm

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张森, 张孟炎, 邵敬平, 普杰信. 基于随机策略搜索的多机三维路径规划方法[J]. 系统仿真学报, 2022, 34(6): 1286-1295.
[2]	张立峰, 王会忍. 基于卷积神经网络及有限元仿真的电容层析成像图像重建[J]. 系统仿真学报, 2022, 34(4): 712-718.
[3]	康旭, 张晓峰. 基于生成对抗神经网络的雷达遥感数据增广方法[J]. 系统仿真学报, 2022, 34(4): 920-927.
[4]	周思锦, 陈棣成, 涂耿, 姜大志. 基于个性化和记忆机制的多模态情感计算模型[J]. 系统仿真学报, 2022, 34(4): 745-758.
[5]	孙晓安, 栾小丽, 刘飞. 基于智能优化灰色模型的电子固废预测[J]. 系统仿真学报, 2022, 34(3): 536-542.
[6]	魏娟, 游磊, 郭阳勇, 唐志海. 基于小波神经网络的多楼层疏散模型[J]. 系统仿真学报, 2022, 34(2): 269-277.
[7]	敖邦乾, 杨莎, 令狐金卿, 叶振环. 基于级联神经网络疲劳驾驶检测系统设计[J]. 系统仿真学报, 2022, 34(2): 323-333.
[8]	魏腾飞, 潘庭龙. 基于改进PSO优化LSTM网络的短期电力负荷预测[J]. 系统仿真学报, 2021, 33(8): 1866-1874.
[9]	赵瑛, 陆耀, 张健, 梁启弟, 龙炜. 基于深度神经网络的多视角人体动作识别[J]. 系统仿真学报, 2021, 33(5): 1019-1030.
[10]	刘晓琳, 吴竟祎. 飞机舵机电液加载系统控制补偿器设计与仿真[J]. 系统仿真学报, 2021, 33(5): 1031-1038.
[11]	于广宇, 董学平, 王祥民, 甘敏. 弹性网下基于LSTM的分解炉出口温度预测[J]. 系统仿真学报, 2021, 33(5): 1078-1085.
[12]	方群, 陈绪凯, 何昕, 祝玉军, 刘毅杨, 方阳阳, 李贺举. 基于SWIPT无线协作网络的中继选择算法研究[J]. 系统仿真学报, 2021, 33(4): 801-808.
[13]	仝卫国, 庞雪纯, 朱赓宏. 基于卷积神经网络的气液两相流流型识别方法[J]. 系统仿真学报, 2021, 33(4): 883-891.
[14]	邵诚, 孙宏远, 张林. 基于PSO-LSSVM的反舰导弹自控弹道仿真[J]. 系统仿真学报, 2021, 33(4): 918-926.
[15]	冯新扬, 邵超. 跨卷积网络特征融合的SAR图像目标识别[J]. 系统仿真学报, 2021, 33(3): 554-561.