Elastic metamaterial design based on deep learning and gradient optimization

被引：0
作者：
Xiao, Li [1 ,2 ]
Cao, Zhigang [1 ,3 ]
Lu, Haoran [1 ]
Huang, Zhijian [1 ]
Cai, Yuanqiang [1 ]
机构：
[1] Coastal and Urban Geotechnical Engineering Research Center, Zhejiang University, Hangzhou
[2] Center for Balance Architecture, Zhejiang University, Hangzhou
[3] The Architectural Design and Research Institute, Zhejiang University Co. Ltd, Hangzhou
来源：
Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science) | 2024年 / 58卷 / 09期
关键词：
band gap; deep learning; elastic metamaterial; gradient optimization; material selection;
D O I：
10.3785/j.issn.1008-973X.2024.09.014
中图分类号：
学科分类号：
摘要：
A novel design method based on deep learning and gradient optimization was proposed to establish a flexible and general framework for fast iterative design of elastic metamaterials and achieve simultaneous optimization of topology structure and material considering material discretization. The design network composed of variational autoencoders and band gap neural network was developed as the framework, and auto-differentiation techniques and gradient optimization algorithms were employed to iteratively tune the design variables with the gradient information. Furthermore, a co-optimization strategy was further proposed to consider the material discretization, so that the structure was optimized while the optimal material was selected from the material depot. Band gap width maximization under constraints and on-demand design were carried out respectively, and the effects of simultaneous optimization and topological configuration were explored. Results showed that the simultaneous optimization provided superior performance compared to separate optimization of materials and topology structures. Additionally, the multilayer configuration can achieve basic units with smaller sizes under the same objectives and material composition. Furthermore, the numerical simulation results of frequency and time domain analyses showed that the designed elastic metamaterials exhibited significant vibration damping performance in the target band gap range. © 2024 Zhejiang University. All rights reserved.
引用
收藏
页码：1892 / 1901
页数：9
相关论文
共 35 条
  • [21] LIU C, YU G., Inverse design of locally resonant metabarrier by deep learning with a rule-based topology dataset, Computer Methods in Applied Mechanics and Engineering, 394, (2022)
  • [22] LIU C, YU G., Deep learning-based topology design of periodic barrier for full-mode waves, Construction and Building Materials, 314, (2022)
  • [23] LIU D, TAN Y, KHORAM E, Et al., Training deep neural networks for the inverse design of nanophotonic structures [J], ACS Photonics, 5, 4, pp. 1365-1369, (2018)
  • [24] ABUEIDDA D W, ALMASRI M, AMMOURAH R, Et al., Prediction and optimization of mechanical properties of composites using convolutional neural networks, Composite Structures, 227, (2019)
  • [25] CUI X, WANG S, HU S., A method for optimal design of automotive body assembly using multi-material construction [J], Materials and Design, 29, 2, pp. 381-387, (2008)
  • [26] XIAO L, CAO Z, LU H, Et al., Optimal design of one-dimensional elastic metamaterials through deep convolutional neural network and genetic algorithm, Structures, 57, (2023)
  • [27] pp. 270-276, (2017)
  • [28] CAMLEY R, DJAFARIROUHANI B, DOBRZYNSKI L, Et al., Transverse elastic-waves in periodically layered infinite, semi-infinite, and slab media [J], Journal of Vacuum Science and Technology B, Woodbury: Amer Inst Physics, 1, 2, pp. 371-375, (1983)
  • [29] LUO C, NING S, LIU Z, Et al., Interactive inverse design of layered phononic crystals based on reinforcement learning, Extreme Mechanics Letters, 36, (2020)
  • [30] KINGMA D P, WELLING M., Auto-encoding variational bayes
1234