Graded multiscale topology optimization using neural networks

被引:18
|
作者
Chandrasekhar, Aaditya [1 ]
Sridhara, Saketh [1 ]
Suresh, Krishnan [1 ]
机构
[1] Univ Wisconsin, Dept Mech Engn, Madison, WI 53706 USA
基金
美国国家科学基金会;
关键词
Multiscale topology optimization; Graded microstructure; Neural networks; Automatic differentiation; LEVEL-SET; NONUNIFORM MICROSTRUCTURES; CELLULAR STRUCTURES; DESIGN; HOMOGENIZATION;
D O I
10.1016/j.advengsoft.2022.103359
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
In this paper, we propose a novel graded multiscale topology optimization framework by exploiting the unique classification capacity of neural networks. The salient features of this framework include: (1) the number of design variables is only weakly dependent on the number of pre-selected microstructures, (2) it guarantees partition of unity while discouraging microstructure mixing, (3) it supports automatic differentiation, thereby eliminating manual sensitivity analysis, and (4) it supports high-resolution re-sampling, leading to smoother variation of microstructure topologies. The proposed framework is illustrated through several examples.
引用
收藏
页数:10
相关论文
共 50 条
  • [41] OPTIMIZATION USING NEURAL NETWORKS
    TAGLIARINI, GA
    CHRIST, JF
    PAGE, EW
    IEEE TRANSACTIONS ON COMPUTERS, 1991, 40 (12) : 1347 - 1358
  • [42] Topology optimization of multiscale elastoviscoplastic structures
    Fritzen, Felix
    Xia, Liang
    Leuschner, Matthias
    Breitkopf, Piotr
    INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING, 2016, 106 (06) : 430 - 453
  • [43] Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
    Xu, Kaidi
    Chen, Hongge
    Liu, Sijia
    Chen, Pin-Yu
    Weng, Tsui-Wei
    Hong, Mingyi
    Lin, Xue
    PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 3961 - 3967
  • [44] On neural networks for generating better local optima in topology optimization
    Herrmann, Leon
    Sigmund, Ole
    Li, Viola Muning
    Vogl, Christian
    Kollmannsberger, Stefan
    STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2024, 67 (11)
  • [45] Multiscale topology optimization of structures by using isogeometrical level set approach
    Aminzadeh, Masoud
    Tavakkoli, Seyed Mehdi
    FINITE ELEMENTS IN ANALYSIS AND DESIGN, 2024, 235
  • [46] Adaptive multiscale image denoising using neural networks
    Srinivasan, M
    Annadurai, S
    2004 INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING & COMMUNICATIONS (SPCOM), 2004, : 140 - 143
  • [47] Coupling of scales in a multiscale simulation using neural networks
    Unger, Joerg F.
    Koenke, Carsten
    COMPUTERS & STRUCTURES, 2008, 86 (21-22) : 1994 - 2003
  • [48] Efficient structure topology optimization by using the multiscale finite element method
    Hui Liu
    Yiqiang Wang
    Hongming Zong
    Michael Yu Wang
    Structural and Multidisciplinary Optimization, 2018, 58 : 1411 - 1430
  • [49] Multiscale optimal design method of acoustic metamaterials using topology optimization
    Kurioka, Hiromasa
    Nakayama, Nari
    Furuta, Kozo
    Noguchi, Yuki
    Izui, Kazuhiro
    Yamada, Takayuki
    Nishiwaki, Shinji
    INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING, 2023, 124 (13) : 2995 - 3024
  • [50] Efficient structure topology optimization by using the multiscale finite element method
    Liu, Hui
    Wang, Yiqiang
    Zong, Hongming
    Wang, Michael Yu
    STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2018, 58 (04) : 1411 - 1430