Page 176 - Read Online
P. 176
Page 12 of 24 He et al. Microstructures 2023;3:2023037 https://dx.doi.org/10.20517/microstructures.2023.29
CGAN Applying CGAN to generate sound insulation structure. The 2021
generated structure may not fully conform to physical laws,
[115]
and the dataset may have a few duplicate samples
Advanced control of TNN TNN effectively handles the increase in non-inconsistency of 2021
[116]
wave propagation the dataset caused by non-local coupling effects
characteristics
TNN Introducing probability sampling in the middle layer of TNN, 2022
gaussian the design parameters have high flexibility, diversity, and
[117]
sampling robustness
TNN A probabilistic model is a powerful tool to solve data 2021
gaussian inconsistency and has strong robustness to sensitive
sampling parameter design [118]
CNN Employing CNN to achieve inverse design of metasurfaces 2021
GA based on multi-point sound pressure and the accuracy report
[119]
is better than GA
MLP Replace the physical unit with MLP and transfer the input 2021
response, material properties, and output response of the
[104]
whole system through the connection between MLPs
MLP MLP captures the relationship between the input and output 2022
wave responses of physical units to construct the overall
structure and replace the time-consuming numerical
[120]
simulation process
Optimizing Clustering Through clustering algorithms, topological classification is 2020
topological states carried out according to the real characteristics of the
system, without prior knowledge and calculation of
[121]
topological invariant
MLP Inverse design of phononic plate with anticipated bandgap 2021
width and topological property Using MLP. The quality of the
edge state can be freely controlled through the preset
[122]
bandgap width
TNN TNN overcomes data inconsistency and supports inverse 2022
design structures based on topological properties to achieve
custom interface states [105]