Machine learning predicts concrete strength under temperature stress

Researchers have developed a data-driven framework using machine learning to predict the compressive strength of fiber-reinforced high-performance concrete under varying temperatures. The study evaluated eight models, finding that ensemble methods like gradient boosting and extreme gradient boosting performed best, achieving an R^2 of 0.903. Explainability techniques revealed temperature as the most significant factor affecting strength, followed by aggregate and water content, with strength decreasing as temperature rises. A Python-based GUI was created for easy prediction using the developed models. AI

IMPACT Provides a precise and comprehensible methodology for evaluating temperature-dependent compressive strength, facilitating data-driven design of concrete.

RANK_REASON Academic paper detailing a new methodology and findings. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• arXiv
• Fiber-Reinforced High-Performance Concrete
• gradient boosting
• Hugging Face
• Partial Dependence Analysis
• Python
• Shapley Additive Explanations
• XGBoost

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →