AI-guided Multi-objective Predicting and Evaluating of SCC Based on Random Forest

Abstract

Self-compacting concrete (SCC) has unique properties that make it a promising alternative to traditional concrete. However, its prediction and design remain challenging due to the complex interaction of multiple factors. Traditional methods are limited in scope, and often inaccurate. This study presents a multi-objective predicting and evaluating model for SCC using machine learning techniques, particularly random forest algorithm. The model predicts flowability, mechanical property, and durability using nine critical features. The dataset used in this study consisted of 376 samples, and the model achieved high accuracy for predicting all three performance indicators, with R² values of 0.94 for compressive strength, 0.92 for slump flow, and 0.94 for rapid chloride permeability. The importance analysis results suggest that the weight of binder and sand are the two most critical factors that affect SCC properties. This approach provides a valuable tool for engineers and researchers in the field of concrete science and technology, improving the quality and durability of concrete structures.