.png){kind=icon}
.png){kind=icon}
Return
A multilabel framework for automated identification of coexisting failure mechanisms in FESEM images of basalt fiber-reinforced epoxy composites
.png){kind=icon}
PRE
AI
M
K
K
DOI：10.1016/j.compositesa.2026.110154.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Automated multilabel identification of eight coexisting composite failure mechanisms. • Quantified correlations among coexisting matrix-, fiber-, and interface-related failure mechanisms. • Transfer learning (ResNet50) outperformed conventional machine learning models in multilabel classification.• Grad-CAM enhances the interpretability of multilabel failure predictions.
Journal
IF:
8.9
Papers:
8.6K
Citations:
4.5W
Organization
Cited Papers