.png){kind=icon}
返回
Deep learning-based high-throughput mesomechanical analysis framework for particulate composites
.png){kind=icon}
PRE
AI
DOI：10.1016/j.conbuildmat.2026.145403.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
• Deep learning based high-throughput mesomechanical analysis framework was proposed. • Pixelated random particle generation method was developed. • High-throughput analysis of 3000 asphalt concrete mesostructures was conducted. • Framework enables efficient exploration of mesostructure-response relationships.
期刊
IF:
8
论文数:
4.5W
被引数:
27.9W
机构
引用论文
Expanding Design Spaces in Digital Composite Materials: A Multi‐Input Deep Learning Approach Enhanced by Transfer Learning and Multi‐kernel Network扩展数字复合材料的设空间：一种通过迁移学习和多核网络增强的多输入深度学习方法
OAAI
OAAI分享收藏Uncertainty quantification of compressive after impact strength in laminated composites using improved Bayesian ResNet deep learning model复合材料冲击后压缩强度的不确定性量化，采用改进的贝叶斯ResNet深度学习模型.png)
POLYMER COMPOSITES
POLYMER COMPOSITESIF4.7
PREAI
分享收藏Investigating Dimensional Effects on Predicting Burning Rates of Heterogeneous Solid PropellantsAIAA Journal
AIAA JournalIF0
PREAI
分享收藏A framework for data-driven analysis of materials under uncertainty: Countering the curse of dimensionality不确定性下材料的数据驱动分析框架: 应对维数的诅咒
OAAI
OAAI分享收藏
查看更多内容