.png){kind=icon}
.png){kind=icon}
Return
A dual-transfer learning framework for predicting mechanical properties of non-circular fiber-reinforced composites with void defects
.png){kind=icon}
PRE
AI
X
P
Y
张
DOI：10.1016/j.compstruct.2025.119932.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A novel dual-transfer learning framework across material systems and void-containing composites. • A multimodal architecture fusing images, structural encodings for different fiber geometry, and material properties for enhanced prediction. • Accurate prediction of homogenized properties for composites with complex, non-circular fiber cross-sections.
Journal
IF:
7.1
Papers:
1.8W
Citations:
8.0W
Organization
Cited Papers