Page 180 - Read Online
P. 180
Page 16 of 24 He et al. Microstructures 2023;3:2023037 https://dx.doi.org/10.20517/microstructures.2023.29
Table 3. A brief overview of design based on static characteristics in mechanical meta-structures
Design Algorithm Meta-structure and Performance Description Year
Type
2D CNN The inverse design of high toughness hierarchical structures based 2018
structure on CNN greatly saves computational time compared to traditional
[131]
finite element methods .
CNN Effectively searching for the optimal cutting mode for stretchable 2018
graphene kirigami structures under given yield strain and stress
conditions based on CNN models [132] .
Supervised Generate the structure by passing potential variables to the decoder. 2020
AE It is expected to find new structures, but the prediction of mechanics
[133]
performance beyond the dataset may be biased .
CNN for predicting 2D metamaterials with the best mechanical 2020
CNN
properties. The model exhibits robustness in terms of accuracy and
[134]
inference time .
DCGAN Combine DCGAN and CNN for designing microstructures. The 2019
CNN model has high efficiency and can flexibly control geometric
[135]
constraints .
CNN Combining CNN and GA can find Pareto's optimal structural design 2021
GA using a relatively small dataset, even with complex nonlinear
constraints [136] .
CNN Inverse design of 2D metamaterial based on predefined Poisson's 2022
GAN
ratio. The model can generate structures beyond the dataset and
exhibit responses similar to real structures [137] .