搜索

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

混杂复合材料等效热传导性能预测的小波-机器学习混合方法

寇雯博 董灏 邹岷强 韩均言 贾西西

引用本文:
Citation:

混杂复合材料等效热传导性能预测的小波-机器学习混合方法

寇雯博, 董灏, 邹岷强, 韩均言, 贾西西

Hybrid wavelet-based learning method of predicting effective thermal conductivities of hybrid composite materials

Kou Wen-Bo, Dong Hao, Zou Min-Qiang, Han Jun-Yan, Jia Xi-Xi
PDF
HTML
导出引用
  • 混杂复合材料是一种新型复合材料, 其复杂的细观结构导致预测其等效热传导性能极富挑战性. 本文结合渐近均匀化方法、小波变换方法和机器学习方法发展了一种新的可以有效预测混杂复合材料等效热传导性能的小波-机器学习混合方法. 该方法主要包括离线多尺度建模和在线机器学习两部分. 首先借助渐近均匀化方法通过离线多尺度建模建立了混杂复合材料的热传导性能材料数据库, 然后利用小波变换方法对离线的材料数据库进行预处理, 接下来分别运用人工神经网络和支持向量回归方法建立混杂复合材料等效热传导性能预测的在线机器学习模型. 最后通过对周期和随机混杂复合材料进行数值实验, 验证了小波-机器学习混合方法的有效性, 数值实验结果表明小波-神经网络混合方法具有最优的预测效果和抗噪能力. 此外, 需要强调的是对于具有高维大规模数据特征的随机混杂复合材料, 小波-机器学习混合方法不仅可以提取离线材料数据库的重要特征, 还可以显著减少在线监督学习的输入数据规模并提高机器学习模型的训练效率及抗噪性能. 本文建立的小波-机器学习混合方法不仅适用于混杂复合材料等效热传导性能的预测, 还可进一步推广应用于复合材料等效物理、力学性能的预测.
    The hybrid composite materials are a new type of composite material. Due to their complex microscopic structures, it is very challenging to predict the equivalent thermal conductivities of hybrid composites. In this paper, an innovative hybrid wavelet-based learning method assisted multiscale analysis is developed to predict the effective thermal conductivities of hybrid composite materials with heterogeneous conductivity by the asymptotic homogenization method, wavelet transform method, and machine learning method. This innovative approach mainly includes two parts: off-line multi-scale modeling and on-line machine learning. Firstly, the material database about thermal transfer performance of hybrid composites is established by the asymptotic homogenization method and off-line multi-scale modeling, and then the off-line material database is preprocessed by the wavelet transform method. Secondly, the artificial neural network and support vector regression method are employed to establish the on-line machine learning model for predicting the equivalent heat conduction properties of hybrid composites. Finally, the effectiveness of the proposed hybrid wavelet-based learning method is verified by numerical experiments on the periodic and random hybrid composites. The numerical results show that the hybrid wavelet-based artificial neural network method owns the optimal capability of parameter prediction and anti-noise. Furthermore, it should be emphasized that the hybrid wavelet-based learning method can not only extract the important features of off-line material database for random hybrid composites with high-dimensional large-scale data features, but also significantly reduce the quantity of input data for ensuring the successful on-line supervised learning and improve the training efficiency and anti-noise performance of the machine learning model. The established hybrid wavelet-based learning method in this paper can not only be used to evaluate the equivalent thermal conductivities of hybrid composite materials, but also further extend to the predicting of the equivalent physical and mechanical properties of composite materials.
      通信作者: 董灏, donghao@mail.nwpu.edu.cn
    • 基金项目: 国家自然科学基金(批准号: 12001414, 61971328)、中国博士后科学基金(批准号: 2018M643573)、陕西省自然科学基金青年科学基金(批准号: 2019JQ-048)和新材料力学理论与应用湖北省重点实验室(武汉理工大学)开放课题(批准号: WUT-TAM202104)资助的课题
      Corresponding author: Dong Hao, donghao@mail.nwpu.edu.cn
    • Funds: Project supported by the National Natural Science Foundation of China (Grant Nos. 12001414, 61971328), the China Postdoctoral Science Foundation (Grant No. 2018M643573), the Young Scientists Fund of the Natural Science Foundation of Shaanxi Province, China (Grant No. 2019JQ-048), and the Open Foundation of Hubei Key Laboratory of Theory and Application of Advanced Materials Mechanics (Wuhan University of Technology), China (Grant No. WUT-TAM202104)
    [1]

    沈观林, 胡更开, 刘彬 2013 复合材料力学 (第2版) (北京: 清华大学出版社) 第159−161页

    Shen G L, Hu G K, Liu B 2013 Mechanics of Composite Materials (2nd Ed.) (Beijing: Tsinghua University Press) pp159−161 (in Chinese)

    [2]

    Hashin Z 1983 Int. J. Appl. Mech. 50 481Google Scholar

    [3]

    Levin V M 1967 Mech. Solids 2 58

    [4]

    Yang Q, Becker W 2004 CMES-Comput. Model. Eng. 6 319Google Scholar

    [5]

    Islam M R, Pramila A 1999 J. Compos. Mater. 33 1699Google Scholar

    [6]

    Yu Y, Cui J, Han F, Chen Y 2008 Comput. Exp. Simul. Eng. Sci. 2 19

    [7]

    Yu Y, Cui J, Han F 2009 Comput. Mater. Sci. 46 151Google Scholar

    [8]

    Ernesto I R, Manuel E C, Julián B C 2016 J. Braz. Soc. Mech. Sci. 38 1333Google Scholar

    [9]

    Eduardo S N, Manuel E C, Julián B C 2017 Int. J. Eng. Sci. 119 205Google Scholar

    [10]

    Bensoussan A, Lions J L, Papanicolaou G 2011 Asymptotic Analysis for Periodic Structures (2nd Ed.) (Vol. 374) (Rhode Island: American Mathematical Society) pp13−19

    [11]

    Sundararaghavan V, Nicholas Z 2005 Comput. Mater. Sci. 32 223Google Scholar

    [12]

    Liu R, Yabansu Y C, Agrawal A, Kalidindi S R, Choudhary A N 2015 Integr. Mater. Manuf. Innov. 4 1Google Scholar

    [13]

    Sun Y, Bai H, Li M, Wang W 2017 J. Phys. Chem. Lett. 8 3434Google Scholar

    [14]

    Kondo R, Yamakawa S, Masuoka Y, Tajima S, Asahi R 2017 Acta Mater. 141 29Google Scholar

    [15]

    Cang R, Li H, Yao H, Jiao Y, Ren Y 2018 Comput. Mater. Sci. 150 212Google Scholar

    [16]

    Bessa M A, Bostanabad R, Liu Z, Hu A, Apley D W, Brinson C, Chen W, Liu W K 2017 Comput. Meth. Appl. Mech. 320 633Google Scholar

    [17]

    Benyelloul K, Aourag H 2013 Comput. Mater. Sci. 77 330Google Scholar

    [18]

    Li X, Liu Z, Cui S, Luo C, Li C, Zhuang Z 2019 Comput. Meth. Appl. Mech. 347 735Google Scholar

    [19]

    Balokas G, Czichon S, Rolfes R 2018 Compos. Struct. 183 550Google Scholar

    [20]

    Liu Z, Wu C 2019 J. Mech. Phys. Solids 127 20

    [21]

    Rong Q, Wei H, Huang X, Bao H 2019 Compos. Sci. Technol. 184 107861Google Scholar

    [22]

    Li Y, Cui J 2004 Chin. J. Comput. Mech. 21 540Google Scholar

    [23]

    李友云 2004 博士学位论文 (北京: 中国科学院数学与系统科学研究院)

    Li Y Y 2004 Ph. D. Dissertation (Beijing: Academy of mathematics and Systems Sciences, Chinese Academy of Sciences) (in Chinese)

    [24]

    Zhang Y, Wong Y S, Deng J, Anton C, Gabos S, Zhang W, et al. 2016 Biodata Min. 9 19Google Scholar

    [25]

    Wong Y, Lee B, Wong T 2001 Intell. Data Anal. 5 59Google Scholar

    [26]

    Mallat S G 1989 IEEE Trans. Pattern. Anal. 11 674Google Scholar

    [27]

    Alemohammad M, Stroud J R, Bosworth B T, Foster M A 2017 Opt. Express 25 9802Google Scholar

    [28]

    Pathak R S 2009 The Wavelet Transform (1st Ed.) (Vol. 4) (Singapore: World Scientific) pp21−37

    [29]

    周志华 2016 机器学习 (第1版) (北京: 清华大学出版社) 第97−107页

    Zhou Z H 2016 Machine Learning (1st Ed.) (Beijing: Tsinghua University Press) pp97−107 (in Chinese)

    [30]

    Smola A J, Schölkopf B 2004 Stat. Comput. 1 4Google Scholar

  • 图 1  混杂复合材料计算机模型 (a) 周期混杂复合材料I; (b) 周期混杂复合材料II; (c) 随机混杂复合材料

    Fig. 1.  Computer geometric models: (a) Periodic hybrid composite material I; (b) periodic hybrid composite material II; (c) random hybrid composite material.

    图 2  三层小波分解示意图

    Fig. 2.  Schematic of three-level wavelet decomposition.

    图 3  人工神经网络方法示意图 (a) 神经元模型; (b) 多层前馈神经网络模型

    Fig. 3.  Schematic of artificial neural network: (a) The neuron model; (b) the multilayer feedforward ANN model.

    图 4  机器学习混合方法流程图

    Fig. 4.  Flowchart of hybrid wavelet-based learning method.

    图 5  三种混杂复合材料1000个随机样本的等效热传导系数分布图 (a) 周期混杂复合材料I; (b) 周期混杂复合材料II; (c) 随机混杂复合材料

    Fig. 5.  Effective thermal conductivity distribution of 1000 RVE samples of three kinds of hybrid composite materials: (a) Periodic hybrid composite material I; (b) periodic hybrid composite material II; (c) random hybrid composite material.

    图 6  十折交叉验证过程示意图

    Fig. 6.  Schematic of 10-fold cross-validation.

    图 7  三种混杂复合材料训练集误差和验证集误差随迭代次数变化曲线图 (a) 周期混杂复合材料I; (b) 周期混杂复合材料II; (c) 随机混杂复合材料

    Fig. 7.  Training error and cross-validation error descend as the training iteration increases for three kinds of hybrid composite materials: (a) Periodic hybrid composite material I; (b) periodic hybrid composite material II; (c) random hybrid composite material

    图 8  三种混杂复合材料训练集和测试集上的相对误差分布图 (a) 周期混杂复合材料I; (b) 周期混杂复合材料II; (c) 随机混杂复合材料

    Fig. 8.  Frequency distribution of training error and test error of three kinds of hybrid composite materials: (a) Periodic hybrid composite material I; (b) periodic hybrid composite material II; (c) random hybrid composite material.

    图 9  三种混杂复合材料参数网格搜索示意图, 其中标记√处为最终确定的最优参数组合 (a) 周期混杂复合材料I; (b) 周期混杂复合材料II; (c) 随机混杂复合材料

    Fig. 9.  Grid search diagram of three kinds of hybrid composite materials’ parameters, where the final optimal combination of parameters is marked with √: (a) Periodic hybrid composite material I; (b) periodic hybrid composite material II; (c) random hybrid composite material.

    图 10  三种混杂复合材料训练集和测试集上的相对误差分布图 (a) 周期混杂复合材料I; (b) 周期混杂复合材料II; (c) 随机混杂复合材料

    Fig. 10.  Frequency distribution of training error and test error of three kinds of hybrid composite materials: (a) Periodic hybrid composite material I; (b) periodic hybrid composite material II; (c) random hybrid composite material.

    表 1  周期型混杂复合材料的材料数据库

    Table 1.  Database for periodic hybrid composite material

    样本编号 数据特征 数据标签
    样本1 $kc_1$ $kc_2$ $km$ $r_1$ $r_2$ $\widehat k$
    $\cdots$ $\cdots$ $\cdots$ $\cdots$ $\cdots$ $\cdots$ $\cdots$
    样本n $kc_1$ $kc_2$ $km$ $r_1$ $r_2$ $\widehat k$
    下载: 导出CSV

    表 2  随机型混杂复合材料的材料数据库

    Table 2.  Database for random hybrid composite material

    样本编号 数据特征 数据标签
    样本1 $k^1_{x_1 x_2}$ $k^2_{x_1 x_2}$ $\cdots$ $k^m_{x_1 x_2}$ $\widehat k$
    $\cdots$ $\cdots$ $\cdots$ $\cdots$ $\cdots$ $\cdots$
    样本n $k^1_{x_1 x_2}$ $k^2_{x_1 x_2}$ $\cdots$ $k^m_{x_1 x_2}$ $\widehat k$
    下载: 导出CSV

    表 3  随机型混杂复合材料新的材料数据库

    Table 3.  New database for random hybrid composite material.

    样本编号 数据特征 数据标签
    样本1 $CA_3$ $\widehat k$
    $\cdots$ $\cdots$ $\cdots$
    样本n $CA_3$ $\widehat k$
    下载: 导出CSV

    表 4  两种小波-机器学习混合方法抗噪性能分析

    Table 4.  Anti-noise performance analysis of two kinds of hybrid wavelet-based learning methods.

    方法 模型参数 Cv训练误差 Cv验证误差 训练误差 测试误差 训练时间/s 测试时间/s
    ANN 1250-1024-512-512-256-1 1.708% 5.760% 1.360% 3.973% 100.345 0.061
    ANN-I 1250-1024-512-512-256-1 1.516% 5.948% 1.671% 4.496% 100.517 0.089
    ANN-II 1250-1024-512-512-256-1 1.349% 5.404% 1.683% 4.427% 101.160 0.071
    ANN-III 1250-1024-512-512-256-1 1.550% 5.862% 1.285% 4.810% 100.270 0.059
    SVR C = 1和$\varepsilon=10^{-2}$ 2.658% 9.257% 2.664% 8.156% 0.780 0.171
    SVR-I C = 1和$\varepsilon=10^{-2}$ 2.664% 9.268% 2.660% 8.160% 0.710 0.187
    SVR-II C = 1和$\varepsilon=10^{-2}$ 2.659% 9.265% 2.673% 8.150% 0.696 0.159
    SVR-III C = 1和$\varepsilon=10^{-2}$ 2.677% 9.124% 2.675% 8.099% 0.694 0.166
    下载: 导出CSV
  • [1]

    沈观林, 胡更开, 刘彬 2013 复合材料力学 (第2版) (北京: 清华大学出版社) 第159−161页

    Shen G L, Hu G K, Liu B 2013 Mechanics of Composite Materials (2nd Ed.) (Beijing: Tsinghua University Press) pp159−161 (in Chinese)

    [2]

    Hashin Z 1983 Int. J. Appl. Mech. 50 481Google Scholar

    [3]

    Levin V M 1967 Mech. Solids 2 58

    [4]

    Yang Q, Becker W 2004 CMES-Comput. Model. Eng. 6 319Google Scholar

    [5]

    Islam M R, Pramila A 1999 J. Compos. Mater. 33 1699Google Scholar

    [6]

    Yu Y, Cui J, Han F, Chen Y 2008 Comput. Exp. Simul. Eng. Sci. 2 19

    [7]

    Yu Y, Cui J, Han F 2009 Comput. Mater. Sci. 46 151Google Scholar

    [8]

    Ernesto I R, Manuel E C, Julián B C 2016 J. Braz. Soc. Mech. Sci. 38 1333Google Scholar

    [9]

    Eduardo S N, Manuel E C, Julián B C 2017 Int. J. Eng. Sci. 119 205Google Scholar

    [10]

    Bensoussan A, Lions J L, Papanicolaou G 2011 Asymptotic Analysis for Periodic Structures (2nd Ed.) (Vol. 374) (Rhode Island: American Mathematical Society) pp13−19

    [11]

    Sundararaghavan V, Nicholas Z 2005 Comput. Mater. Sci. 32 223Google Scholar

    [12]

    Liu R, Yabansu Y C, Agrawal A, Kalidindi S R, Choudhary A N 2015 Integr. Mater. Manuf. Innov. 4 1Google Scholar

    [13]

    Sun Y, Bai H, Li M, Wang W 2017 J. Phys. Chem. Lett. 8 3434Google Scholar

    [14]

    Kondo R, Yamakawa S, Masuoka Y, Tajima S, Asahi R 2017 Acta Mater. 141 29Google Scholar

    [15]

    Cang R, Li H, Yao H, Jiao Y, Ren Y 2018 Comput. Mater. Sci. 150 212Google Scholar

    [16]

    Bessa M A, Bostanabad R, Liu Z, Hu A, Apley D W, Brinson C, Chen W, Liu W K 2017 Comput. Meth. Appl. Mech. 320 633Google Scholar

    [17]

    Benyelloul K, Aourag H 2013 Comput. Mater. Sci. 77 330Google Scholar

    [18]

    Li X, Liu Z, Cui S, Luo C, Li C, Zhuang Z 2019 Comput. Meth. Appl. Mech. 347 735Google Scholar

    [19]

    Balokas G, Czichon S, Rolfes R 2018 Compos. Struct. 183 550Google Scholar

    [20]

    Liu Z, Wu C 2019 J. Mech. Phys. Solids 127 20

    [21]

    Rong Q, Wei H, Huang X, Bao H 2019 Compos. Sci. Technol. 184 107861Google Scholar

    [22]

    Li Y, Cui J 2004 Chin. J. Comput. Mech. 21 540Google Scholar

    [23]

    李友云 2004 博士学位论文 (北京: 中国科学院数学与系统科学研究院)

    Li Y Y 2004 Ph. D. Dissertation (Beijing: Academy of mathematics and Systems Sciences, Chinese Academy of Sciences) (in Chinese)

    [24]

    Zhang Y, Wong Y S, Deng J, Anton C, Gabos S, Zhang W, et al. 2016 Biodata Min. 9 19Google Scholar

    [25]

    Wong Y, Lee B, Wong T 2001 Intell. Data Anal. 5 59Google Scholar

    [26]

    Mallat S G 1989 IEEE Trans. Pattern. Anal. 11 674Google Scholar

    [27]

    Alemohammad M, Stroud J R, Bosworth B T, Foster M A 2017 Opt. Express 25 9802Google Scholar

    [28]

    Pathak R S 2009 The Wavelet Transform (1st Ed.) (Vol. 4) (Singapore: World Scientific) pp21−37

    [29]

    周志华 2016 机器学习 (第1版) (北京: 清华大学出版社) 第97−107页

    Zhou Z H 2016 Machine Learning (1st Ed.) (Beijing: Tsinghua University Press) pp97−107 (in Chinese)

    [30]

    Smola A J, Schölkopf B 2004 Stat. Comput. 1 4Google Scholar

  • [1] 王建海, 钱建强, 窦志鹏, 林锐, 许泽宇, 程鹏, 王丞, 李磊, 李英姿. 基于小波变换的多频静电力显微镜动态过程测量方法. 物理学报, 2022, 71(9): 096801. doi: 10.7498/aps.71.20212095
    [2] 刘欣宇, 杨苏辉, 廖英琦, 林学彤. 基于小波变换的激光水下测距. 物理学报, 2021, 70(18): 184205. doi: 10.7498/aps.70.20210569
    [3] 马原, 吕群波, 刘扬阳, 钱路路, 裴琳琳. 基于主成分变换的图像稀疏度估计方法. 物理学报, 2013, 62(20): 204202. doi: 10.7498/aps.62.204202
    [4] 赵辽英, 马启良, 厉小润. 基于HIS 小波变换和MOPSO的全色与多光谱图像融合. 物理学报, 2012, 61(19): 194204. doi: 10.7498/aps.61.194204
    [5] 余海军, 杜建明, 张秀兰. 相干态的小波变换. 物理学报, 2012, 61(16): 164205. doi: 10.7498/aps.61.164205
    [6] 宋军, 许业军, 范洪义. 奇偶二项式光场态的小波变换. 物理学报, 2011, 60(8): 084208. doi: 10.7498/aps.60.084208
    [7] 张淑娜, 罗震岳, 沈伟东, 刘旭, 章岳光. 利用白光干涉技术测量块状材料的群折射率. 物理学报, 2011, 60(1): 014221. doi: 10.7498/aps.60.014221
    [8] 甘甜, 冯少彤, 聂守平, 朱竹青. 基于分块DCT变换编码的小波域多幅图像融合算法. 物理学报, 2011, 60(11): 114205. doi: 10.7498/aps.60.114205
    [9] 符懋敬, 庄建军, 侯凤贞, 宁新宝, 展庆波, 邵毅. 基于小波变换的人体步态序列提取. 物理学报, 2010, 59(6): 4343-4350. doi: 10.7498/aps.59.4343
    [10] 任磊, 陈祥光, 刘春涛. 基于小波变换的时域介电谱分析及其应用. 物理学报, 2009, 58(3): 2035-2041. doi: 10.7498/aps.58.2035
    [11] 赵文山, 何怡刚. 一种改进的开关电流滤波器实现小波变换的方法. 物理学报, 2009, 58(2): 843-851. doi: 10.7498/aps.58.843
    [12] 邓玉强, 曹士英, 于 靖, 徐 涛, 王清月, 张志刚. 小波变换提取放大超短脉冲载波-包络相位的研究. 物理学报, 2008, 57(11): 7017-7021. doi: 10.7498/aps.57.7017
    [13] 胡沁春, 何怡刚, 郭迪新, 李宏民. 基于开关电流技术的小波变换的滤波器电路实现. 物理学报, 2006, 55(2): 641-647. doi: 10.7498/aps.55.641
    [14] 邓玉强, 吴祖斌, 陈盛华, 柴 路, 王清月, 张志刚. 自参考光谱相干法的小波变换相位重建. 物理学报, 2005, 54(8): 3716-3721. doi: 10.7498/aps.54.3716
    [15] 赵 莉, 冯 稷, 翟光杰, 张利华. 小波变换在心磁信号处理中的应用. 物理学报, 2005, 54(4): 1943-1949. doi: 10.7498/aps.54.1943
    [16] 邓玉强, 邢岐荣, 郎利影, 柴 路, 王清月, 张志刚. THz波的小波变换频谱分析. 物理学报, 2005, 54(11): 5224-5227. doi: 10.7498/aps.54.5224
    [17] 邓玉强, 张志刚, 柴 路, 王清月. 小波变换重建超短脉冲光谱相位的误差分析. 物理学报, 2005, 54(9): 4176-4181. doi: 10.7498/aps.54.4176
    [18] 汪 渊, 白宣羽, 徐可为. 基于小波变换Cu-W薄膜表面形貌表征与硬度值分散性评价. 物理学报, 2004, 53(7): 2281-2286. doi: 10.7498/aps.53.2281
    [19] 游荣义, 陈 忠, 徐慎初, 吴伯僖. 基于小波变换的混沌信号相空间重构研究. 物理学报, 2004, 53(9): 2882-2888. doi: 10.7498/aps.53.2882
    [20] 宋菲君, 赵文杰, S. Jutamulia, 宋建力, 姚思一, 王 栋. Haar-Gaussian小波变换在边缘测量中的应用. 物理学报, 2003, 52(12): 3055-3060. doi: 10.7498/aps.52.3055
计量
  • 文章访问数:  5741
  • PDF下载量:  136
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-07-08
  • 修回日期:  2020-10-05
  • 上网日期:  2021-01-15
  • 刊出日期:  2021-02-05

/

返回文章
返回