EI、Scopus 收录
中文核心期刊
Bai Xiaowei, Zhao Luyang, Li Liang, Luo Lilong, Yang Jie, Hu Heng. Comparative study on two types of data-driven computational homogenization methods. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(7): 1931-1942. DOI: 10.6052/0459-1879-23-641
Citation: Bai Xiaowei, Zhao Luyang, Li Liang, Luo Lilong, Yang Jie, Hu Heng. Comparative study on two types of data-driven computational homogenization methods. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(7): 1931-1942. DOI: 10.6052/0459-1879-23-641

COMPARATIVE STUDY ON TWO TYPES OF DATA-DRIVEN COMPUTATIONAL HOMOGENIZATION METHODS

  • Received Date: December 28, 2023
  • Accepted Date: April 28, 2024
  • Available Online: April 28, 2024
  • Published Date: April 29, 2024
  • Nowadays the simulation methods for heterogeneous materials and structures are still faced with challenges of complex constitutive modeling and costly multiscale computation, which are expected to be overcome by the emerging data-driven computational homogenization methods. Data-driven computational homogenization method aims to save the labor and time costs for constitutive modeling by means of data science. In the meanwhile, it is able to considerably enhance the online computational efficiency for simulating heterogeneous materials and structures by shifting numerous mesoscopic calculations to the offline stage. Data-driven computational homogenization methods can be roughly summarized into two categories according to the functionals to be solved. The first one is based on energy functional, whose key point is to efficiently capture constitutive relation using artificial intelligence and then obtain the solution in the framework of classical computational mechanics. The other one is based on distance functional, whose specificity lies in directly embedding the material data into mechanical simulations. The extremum of distance functional is used to find the state from the constitutive data set that is closest to satisfying the conservation laws, thus bypassing the step of empirical material modeling. The outline of this paper is organized as follows. At first, the basic procedures for conducting multiscale simulations through above two data-driven computational homogenization methods are briefly recalled. Next, numerical simulations concerning the fiber-reinforced composite structure are conducted by adopting both methods. Based on the obtained results, the influence of the number of data points on the computational efficiency and accuracy is evaluated from both qualitative and quantitative perspectives. Finally, the superiorities and weaknesses of both algorithms for conducting multiscale simulations are discussed in terms of different aspects, such as the algorithm implementation, computational accuracy, computational efficiency and post-processing. The outcomes of this paper are expected to offer theoretical basis for developing techniques to efficiently simulate heterogeneous materials and structures.
  • [1]
    彭向峰, 李录贤. 超弹性材料本构关系的最新研究进展. 力学学报, 2020, 52(5): 1221-1232 (Peng Xiangfeng, Li Luxian. State of the art of constitutive relations of hyperelastic materials. Chinese Journal of Theoretical and Applied Mechanics, 2020, 52(5): 1221-1232 (in Chinese) doi: 10.6052/0459-1879-20-189

    Peng Xiangfeng, Li Luxian. State of the art of constitutive relations of hyperelastic materials. Chinese Journal of Theoretical and Applied Mechanics, 2020, 52(5): 1221-1232 (in Chinese) doi: 10.6052/0459-1879-20-189
    [2]
    阳杰, 徐锐, 黄群等. 数据驱动计算力学研究进展. 固体力学学报, 2020, 41(1): 1-14 (Yang Jie, Xu Rui, Huang Qun, et al. Data-driven computational mechanics: A review. Chinese Journal of Solid Mechanics, 2020, 41(1): 1-14 (in Chinese)

    Yang Jie, Xu Rui, Huang Qun, et al. Data-driven computational mechanics: A review. Chinese Journal of Solid Mechanics, 2020, 41(1): 1-14 (in Chinese)
    [3]
    杨强, 孟松鹤, 仲政等. 力学研究中“大数据”的启示、应用与挑战. 力学进展, 2020, 50(1): 202011 (Yang Qiang, Meng Songhe, Zhong Zheng, et al. Big data in mechanical research: Potentials, applications and challenges. Advances in Mechanics, 2020, 50(1): 202011 (in Chinese) doi: 10.6052/1000-0992-19-002

    Yang Qiang, Meng Songhe, Zhong Zheng, et al. Big data in mechanical research: Potentials, applications and challenges. Advances in Mechanics, 2020, 50(1): 202011 (in Chinese) doi: 10.6052/1000-0992-19-002
    [4]
    李想, 严子铭, 柳占立. 机器学习与计算力学的结合及应用初探. 科学通报, 2019, 64(7): 635-648 (Li Xiang, Yan Ziming, Liu Zhanli. Combination and application of machine learning and computational mechanics. Chinese Science Bulletin, 2019, 64(7): 635-648 (in Chinese) doi: 10.1360/N972019-00005

    Li Xiang, Yan Ziming, Liu Zhanli. Combination and application of machine learning and computational mechanics. Chinese Science Bulletin, 2019, 64(7): 635-648 (in Chinese) doi: 10.1360/N972019-00005
    [5]
    张峻铭, 杨伟东, 李岩. 人工智能在复合材料研究中的应用. 力学进展, 2021, 51(4): 865-900 (Zhang Junming, Yang Weidong, Li Yan. Application of artificial intelligence in composite materials. Advances in Mechanics, 2021, 51(4): 865-900 (in Chinese) doi: 10.6052/1000-0992-21-019

    Zhang Junming, Yang Weidong, Li Yan. Application of artificial intelligence in composite materials. Advances in Mechanics, 2021, 51(4): 865-900 (in Chinese) doi: 10.6052/1000-0992-21-019
    [6]
    Liu X, Tian S, Tao F, et al. A review of artificial neural networks in the constitutive modeling of composite materials. Composites Part B, 2021, 224: 109152 doi: 10.1016/j.compositesb.2021.109152
    [7]
    Kirchdoerfer T, Ortiz M. Data-driven computational mechanics. Computer Methods in Applied Mechanics and Engineering, 2016, 304: 81-101 doi: 10.1016/j.cma.2016.02.001
    [8]
    Ghaboussi J, Garrett J, Wu X. Knowledge-based modeling of material behavior with neural networks. Journal of Engineering Mechanics, 1991, 117: 132-153
    [9]
    Ghaboussi J, Sidarta DE. New nested adaptive neural networks (NANN) for constitutive modeling. Computers and Geotechnics, 1998, 22: 29-52 doi: 10.1016/S0266-352X(97)00034-7
    [10]
    Hashash YMA, Jung S, Ghaboussi J. Numerical implementation of a neural network based material model in finite element analysis. International Journal for Numerical Methods in Engineering, 2004, 59: 989-1005 doi: 10.1002/nme.905
    [11]
    Furukawa T, Yagawa G. Implicit constitutive modelling for viscoplasticity using neural networks. International Journal for Numerical Methods in Engineering, 1998, 43: 195-219 doi: 10.1002/(SICI)1097-0207(19980930)43:2<195::AID-NME418>3.0.CO;2-6
    [12]
    Al-Haik M, Hussaini M, Garmestani H. Prediction of nonlinear viscoelastic behavior of polymeric composites using an artificial neural network. International Journal of Plasticity, 2006, 22: 1367-1392 doi: 10.1016/j.ijplas.2005.09.002
    [13]
    Li Q, Cinbiz MN, Zhang Y, et al. Robust deep learning framework for constitutive relations modeling. Acta Materialia, 2023, 254: 118959 doi: 10.1016/j.actamat.2023.118959
    [14]
    Le BA, Yvonnet J, He QC. Computational homogenization of nonlinear elastic materials using neural networks. International Journal for Numerical Methods in Engineering, 2015, 104: 1061-1084 doi: 10.1002/nme.4953
    [15]
    Yang H, Guo X, Tang S, et al. Derivation of heterogeneous material laws via data-driven principal component expansions. Computational Mechanics, 2019, 64: 365-379 doi: 10.1007/s00466-019-01728-w
    [16]
    Huang DZ, Xu K, Farhat C, et al. Learning constitutive relations from indirect observations using deep neural networks. Journal of Computational Physics, 2020, 416: 109491 doi: 10.1016/j.jcp.2020.109491
    [17]
    Xu K, Darve E. Physics constrained learning for data-driven inverse modelling from sparse observations. Journal of Computational Physics, 2022, 453: 110938 doi: 10.1016/j.jcp.2021.110938
    [18]
    Xu K, Tartakovsky AM, Burghardt J, et al. Learning viscoelasticity models from indirect data using deep neural networks. Computer Methods in Applied Mechanics and Engineering, 2021, 387: 114124 doi: 10.1016/j.cma.2021.114124
    [19]
    杨航. 基于力学先验知识的数据驱动弹性和弹塑性本构建模方法研究. [博士论文]. 大连: 大连理工大学, 2022 (Yang Hang. A research on data-driven elastic and elastoplastic constitutive modeling method based on prior knowledge of mechanics. [PhD Thesis]. Dalian: Dalian University of Technology, 2022 (in Chinese)

    Yang Hang. A research on data-driven elastic and elastoplastic constitutive modeling method based on prior knowledge of mechanics. [PhD Thesis]. Dalian: Dalian University of Technology, 2022 (in Chinese)
    [20]
    Linka K, Hillgärtner M, Abdolazizi KP, et al. Constitutive artificial neural networks: A fast and general approach to predictive data-driven constitutive modeling by deep learning. Journal of Computational Physics, 2021, 429: 110010 doi: 10.1016/j.jcp.2020.110010
    [21]
    杨航, 李丽坤, 刘道平等. 数据驱动梯度结构材料弹塑性本构. 固体力学学报, 2021, 42(3): 233-240 (Yang Hang, Li Likun, Liu Daoping, et al. Data-driven elastoplastic constitutive model for gradient structure materials. Chinese Journal of Solid Mechanics, 2021, 42(3): 233-240 (in Chinese)

    Yang Hang, Li Likun, Liu Daoping, et al. Data-driven elastoplastic constitutive model for gradient structure materials. Chinese Journal of Solid Mechanics, 2021, 42(3): 233-240 (in Chinese)
    [22]
    Nguyen LTK, Keip MA. A data-driven approach to nonlinear elasticity. Computers and Structures, 2018, 194: 97-115 doi: 10.1016/j.compstruc.2017.07.031
    [23]
    Platzer A, Leygue A, Stainier L, et al. Finite element solver for data-driven finite strain elasticity. Computer Methods in Applied Mechanics and Engineering, 2021, 379: 113756 doi: 10.1016/j.cma.2021.113756
    [24]
    Zheng Z, Zhang Z, Ye H, et al. Distance minimizing based data-driven computational method for the finite deformation of hyperelastic materials. International Journal for Numerical Methods in Engineering, 2023, 124: 2315-2340 doi: 10.1002/nme.7212
    [25]
    Eggersmann R, Kirchdoerfer T, Reese S, et al. Model-free data-driven inelasticity. Computer Methods in Applied Mechanics and Engineering, 2019, 350: 81-99 doi: 10.1016/j.cma.2019.02.016
    [26]
    Zhou Y, Zhan H, Zhang W, et al. A new data-driven topology optimization framework for structural optimization. Computers and Structures, 2020, 239: 106310 doi: 10.1016/j.compstruc.2020.106310
    [27]
    Xu R, Yang J, Yan W, et al. Data-driven multiscale finite element method: From concurrence to separation. Computer Methods in Applied Mechanics and Engineering, 2020, 363: 112893 doi: 10.1016/j.cma.2020.112893
    [28]
    Feyel F. A multilevel finite element method (FE2) to describe the response of highly non-linear structures using generalized continua. Computer Methods in Applied Mechanics and Engineering, 2003, 192: 3233-3244 doi: 10.1016/S0045-7825(03)00348-7
    [29]
    Huang W, Xu R, Yang J, et al. Data-driven multiscale simulation of FRP based on material twins. Composite Structures, 2021, 256: 113013 doi: 10.1016/j.compstruct.2020.113013
    [30]
    Tang S, Zhang G, Yang H, et al. MAP123: A data-driven approach to use 1D data for 3D nonlinear elastic materials modeling. Computer Methods in Applied Mechanics and Engineering, 2019, 357: 112587 doi: 10.1016/j.cma.2019.112587
    [31]
    Tang S, Li Y, Qiu H, et al. MAP123-EP: A mechanistic-based data-driven approach for numerical elastoplastic analysis. Computer Methods in Applied Mechanics and Engineering, 2020, 364: 112955 doi: 10.1016/j.cma.2020.112955
    [32]
    Xu Y, Yang J, Bai X, et al. Material database construction for data-driven computing via a continuous path-following method. Composite Structures, 2023, 319: 117187 doi: 10.1016/j.compstruct.2023.117187
    [33]
    Damil N, Potier-Ferry M. A new method to compute perturbed bifurcations: Application to the buckling of imperfect elastic structures. International Journal of Engineering Science, 1990, 28: 943-957 doi: 10.1016/0020-7225(90)90043-I
    [34]
    Li L, Shao Q, Yang Y, et al. A database construction method for data-driven computational mechanics of composites. International Journal of Mechanical Sciences, 2023, 249: 108232 doi: 10.1016/j.ijmecsci.2023.108232
    [35]
    Kim S, Shin H. Data-driven multiscale finite-element method using deep neural network combined with proper orthogonal decomposition. Engineering with Computers, 2024, 40: 661-675 doi: 10.1007/s00366-023-01813-y
    [36]
    张玉辉, 姜清辉. 距离最小化数据驱动计算方法中平衡因子取值影响研究. 工程力学, 2022, 39(6): 11-20 (Zhang Yuhui, Jiang Qinghui. The influence of the balance factor in the distance-minimizing data-driven computational method. Engineering Mechanics, 2022, 39(6): 11-20 (in Chinese) doi: 10.6052/j.issn.1000-4750.2021.03.0199

    Zhang Yuhui, Jiang Qinghui. The influence of the balance factor in the distance-minimizing data-driven computational method. Engineering Mechanics, 2022, 39(6): 11-20 (in Chinese) doi: 10.6052/j.issn.1000-4750.2021.03.0199
    [37]
    Nguyen LTK, Aydin RC, Cyron CJ. Accelerating the distance-minimizing method for data-driven elasticity with adaptive hyperparameters. Computational Mechanics, 2022, 70: 621-638 doi: 10.1007/s00466-022-02183-w
    [38]
    Bai X, Yang J, Yan W, et al. A data-driven approach for instability analysis of thin composite structures. Computers and Structures, 2022, 273: 106898 doi: 10.1016/j.compstruc.2022.106898
    [39]
    Eggersmann R, Stainier L, Ortiz M, et al. Efficient data structures for model-free data-driven computational mechanics. Computer Methods in Applied Mechanics and Engineering, 2021, 382: 113855 doi: 10.1016/j.cma.2021.113855
    [40]
    Kuang Z, Yan W, Yu K, et al. Data-driven computing for nonlinear problems of composite structures based on sub-domain search technique. Computers and Structures, 2023, 279: 106982 doi: 10.1016/j.compstruc.2023.106982
    [41]
    Yang J, Xu R, Hu H, et al. Structural-Genome-Driven computing for composite structures. Composite Structures, 2019, 215: 446-453 doi: 10.1016/j.compstruct.2019.02.064
    [42]
    Yan W, Huang W, Huang Q, et al. Data-driven multiscale method for composite plates. Computational Mechanics, 2022, 70: 1025-1040 doi: 10.1007/s00466-022-02195-6
    [43]
    Hui Y, Bai X, Yang Y, et al. A data-driven CUF-based beam model based on the tree-search algorithm. Composite Structures, 2022, 300: 116123 doi: 10.1016/j.compstruct.2022.116123
    [44]
    Yang J, Huang W, Huang Q, et al. An investigation on the coupling of data-driven computing and model-driven computing. Computer Methods in Applied Mechanics and Engineering, 2022, 393: 114798 doi: 10.1016/j.cma.2022.114798
    [45]
    Yang J, Li P, Zhang Y, et al. Unified functional based data-model-coupling computing for composite materials and structures. Composite Structures, 2023, 312: 116840 doi: 10.1016/j.compstruct.2023.116840
    [46]
    徐锐. 面向复合材料结构的计算均匀化方法研究. [博士论文]. 武汉: 武汉大学. 2020 (Xu Rui. A research on computational homogenization for composite structures. [PhD Thesis]. Wuhan: Wuhan University, 2020 (in Chinese)

    Xu Rui. A research on computational homogenization for composite structures. [PhD Thesis]. Wuhan: Wuhan University, 2020 (in Chinese)
    [47]
    Friedman JH, Bentley JL, Finkel RA. An algorithm for finding best matches in logarithmic expected time. ACM Transactions on Mathematical Software, 1977, 3: 209-226 doi: 10.1145/355744.355745
    [48]
    Karniadakis GE, Kevrekidis IG, Lu L, et al. Physics-informed machine learning. Nature Reviews Physics, 2021, 3: 422-440 doi: 10.1038/s42254-021-00314-5
  • Related Articles

    [1]Gong Jingfeng, Chen Sicheng, Xuan Lingkuan, Li Chenqi, Zhang Yue. FUNCTIONALLY GRADED MATERIAL DATA DRIVEN CELL-VERTEX FINITE VOLUME METHOD[J]. Chinese Journal of Theoretical and Applied Mechanics, 2025, 57(1): 136-147. DOI: 10.6052/0459-1879-24-303
    [2]Feng Yixin, Peng Hui, Luo Wei. RESEARCH ON PARAMETER IDENTIFICATION OF COMPOSITE MATERIALS BY COMBINATION OF SELF-CONSISTENT CLUSTER ANALYSIS, NEURAL NETWORK AND BAYESIAN OPTIMIZATION[J]. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(11): 3333-3350. DOI: 10.6052/0459-1879-24-246
    [3]Ji Shunying. Preface of Theme Articles on Computation Mechanics of Granular Materials[J]. Chinese Journal of Theoretical and Applied Mechanics, 2021, 53(9): 2355-2356. DOI: 10.6052/0459-1879-21-428
    [4]Zhuo Xiaoxiang, Liu Hui, Chu Xihua, Xu Yuanjie. A GENERALIZED MULTISCALE FINITE ELEMENT METHOD FOR DYNAMIC ANALYSIS OF HETEROGENEOUS MATERIAL[J]. Chinese Journal of Theoretical and Applied Mechanics, 2016, 48(2): 378-386. DOI: 10.6052/0459-1879-15-211
    [5]Shengwang Hao, Ju Sun. A sensitive precursor to catastrophic failure in heterogeneous brittle materials[J]. Chinese Journal of Theoretical and Applied Mechanics, 2008, 40(3): 339-344. DOI: 10.6052/0459-1879-2008-3-2007-552
    [6]Jun Zhou, Youhe Zhou. A new simple method of implicit time integration for dynamic problems of engineering structures[J]. Chinese Journal of Theoretical and Applied Mechanics, 2007, 39(1): 91-99. DOI: 10.6052/0459-1879-2007-1-2006-167
    [7]Z.Y. Gao, Tongxi Yu, D. Karagiozova. Finite element simulation on the mechanical properties of MHS materials[J]. Chinese Journal of Theoretical and Applied Mechanics, 2007, 39(1): 65-75. DOI: 10.6052/0459-1879-2007-1-2006-198
    [8]Microscopic heterogeneity and macroscopic mechanical behavior of a polycrystalline material[J]. Chinese Journal of Theoretical and Applied Mechanics, 2004, 36(6): 714-723. DOI: 10.6052/0459-1879-2004-6-2003-444
    [9]HOMOGENIZATION METHOD OF STRESS ANALYSIS OF COMPOSITE STRUCTURES[J]. Chinese Journal of Theoretical and Applied Mechanics, 1997, 29(3): 306-313. DOI: 10.6052/0459-1879-1997-3-1995-230
    [10]基于变形动力学模型的黏弹性材料本构关系[J]. Chinese Journal of Theoretical and Applied Mechanics, 1993, 25(3): 375-379. DOI: 10.6052/0459-1879-1993-3-1995-655
  • Cited by

    Periodical cited type(2)

    1. 龚京风,陈思成,宣领宽,李晨琦,张跃. 功能梯度材料数据驱动格点型有限体积法. 力学学报. 2025(01): 136-147 . 本站查看
    2. 冯易鑫 ,彭辉 ,罗威 . 聚类分析-神经网络-贝叶斯优化联合识别复合材料参数研究. 力学学报. 2024(11): 3333-3350 . 本站查看

    Other cited types(0)

Catalog

    Article Metrics

    Article views (342) PDF downloads (124) Cited by(2)
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return