.png){kind=icon}
.png){kind=icon}
Return
Structural dependency-aware generative design of elastic metasurfaces via pseudo-supervised attention-based transformer
.png){kind=icon}
PRE
AI
T
D
J
S
B
S
DOI：10.1016/j.cma.2026.119041.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Deep learning-based inverse design framework eliminates iterative optimization. • The PSAT captures structural interdependencies via an attention-based mechanism. • Pseudo-supervised prediction enables parallel generation with physical feasibility. • Joint training strategy for forward and inverse models reduces training costs by 36%
Keywords:
deep learning
inverse design
attention mechanism
generative design
elastic metasurfaces
Journal
IF:
7.3
Papers:
1.3W
Citations:
5.6W
Organization
Cited Papers