.png){kind=icon}
.png){kind=icon}
Return
A novel physics-constrained deep learning framework for the inverse design of assembly contact interfaces
.png){kind=icon}
PRE
AI
L
M
C
T
H
Q
Y
J
DOI：10.1016/j.engappai.2026.114946.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Proposes Phys-ResTranNet for inverse design of assembly interfaces. • Enforces impenetrability constraints via a novel differentiable loss. • Optimized learning rate scheduling enhances model convergence accuracy. • Reduces contact pressure by 15.67% and increases contact area by 45.23%.
Keywords:
inverse design
contact interfaces
physics-constrained
deep learning
impenetrability constraints
Journal
IF:
8
Papers:
5.2K
Citations:
3.5W