Use of interpretable machine learning approaches for quantificationally understanding the performance of steel fiber-reinforced recycled aggregate concrete: From the perspective of compressive strength and splitting tensile strength

In this study, four machine learning (ML) algorithms, namely Support Vector Machine (SVM), Back-propagation Artificial Neural Network (BP-ANN), Adaptive Boosting (AdaBoost), and Gradient Boosted Regression Tree (GBRT), were employed to conduct an in-depth analysis of the global estimation model of the compressive strength and splitting tensile strength of steel fiber recycled aggregate concrete (SFR-RAC). A database containing 465 compressive strength sets and 339 splitting tensile strength sets with different mix proportions was established, and the ML model was trained and tested in combination with Bayesian optimization. The effects of multiple components on the strength of SFR-RAC were studied using partial correlation analysis and SHapley Additive exPlanations (SHAP) analysis. The results showed that AdaBoost and GBRT performed well according to the evaluation indicators, and the deviation between the predicted data and the actual data remained within 20%. The developed models were quantitatively analyzed to study the relationship between characteristics and compressive/splitting tensile strengths, and recommendations were given for key parameters in the SFR-RAC mix proportion. This study suggests improving the modeling accuracy by further incorporating out-of-range data and features for future research.