.png){kind=icon}
Return
Adaptive machine learning framework: Predicting UHPC performance from data to modelling
.png){kind=icon}
OA
AI
DOI：10.1016/j.rineng.2025.106724.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A broader data set with 20 input variables improves the prediction of UHPC strength. • An interpretable ML framework combines outlier detection, feature selection, and SHAP. • LightGBM achieves the highest accuracy and stability for UHPC compressive strength. • SHAP analysis reveals crucial factors like Age and SF content, guiding material design.
Keywords:
Ultra-High Performance Concrete (UHPC)
Compressive strength
Machine learning (ML)
LightGBM
SHapley Additional explanation (SHAP)
Journal
IF:
7.9
Papers:
1.2W
Citations:
1.7W
Organization
Cited Papers
Advanced machine learning algorithms to evaluate the effects of the raw ingredients on flowability and compressive strength of ultra-high-performance concrete.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAIShareSaveShareSaveShareSavePredicting Ultra-High-Performance Concrete Compressive Strength Using Tabular Generative Adversarial NetworksMATERIALSOAAI
MATERIALSIF3.2
OAAIShareSaveShareSaveShareSave
View more