What question did this study set out to answer?

The central aim is to develop a machine learning framework to predict the compressive strength of recycled aggregate self-compacting concrete.

March 5, 2026Open Access

Machine Learning-Based Prediction of Compressive Strength in Recycled Aggregate Self-Compacting Concrete: An Ensemble Modeling Approach with SHAP Interpretability Analysis

Puntos clave

The central aim is to develop a machine learning framework to predict the compressive strength of recycled aggregate self-compacting concrete.
Established a database with 301 experimental specimens and 18 input variables.
Utilized four advanced ensemble modeling approaches including LightGBM and CatBoost.
Applied SHAP analysis for interpretability of influence on compressive strength.
Performed rigorous residual analysis to validate model assumptions.
The stacking ensemble model achieved R2 = 0.963, RMSE = 3.321 MPa, and MAE = 2.506 MPa.
Identified specimen age as the most influential predictor of compressive strength.
Confirmed valid predictive capabilities of the model across various concrete compositions.

Resumen

The incorporation of recycled concrete aggregates (RCAs) into self-compacting concrete (SCC) represents a critical sustainable construction strategy addressing both construction waste management and natural resource conservation. However, predicting the compressive strength of recycled aggregate self-compacting concrete (RASCC) remains challenging due to complex nonlinear interactions among mixture parameters. This study develops a robust predictive framework using ensemble machine learning algorithms to accurately estimate RASCC compressive strength across diverse mixture compositions. A comprehensive database comprising 301 experimental specimens with 18 input variables—including curing age, binder components, water-to-binder ratio, recycled aggregate properties, and supplementary cementitious materials—was systematically analyzed. Four advanced modeling approaches were evaluated: Light Gradient Boosting Machine (LightGBM), Categorical Boosting (CatBoost), Stacked Generalization with Ridge regression meta-learner, and Voting ensemble with Non-Negative Least Squares optimization. The Stacking ensemble model demonstrated superior predictive performance on the independent test set, with R2 = 0.963, RMSE = 3.321 MPa, and MAE = 2.506 MPa. Rigorous residual analysis confirmed model validity through satisfaction of normality, homoscedasticity, and independence assumptions. SHAP interpretability analysis identified specimen age as the dominant predictor, followed by recycled aggregate density and water-to-binder ratio, while elucidating the complex nonlinear contributions of supplementary cementitious materials including fly ash and ground granulated blast furnace slag. The developed framework demonstrates practical applicability for predicting RASCC compressive strength across conventional to high-performance grades, facilitating sustainable mix design optimization while maintaining structural performance requirements, and advancing circular economy principles through confident integration of recycled aggregates in SCC applications.

Leer artículo completoexternamente

Me gusta

Guardar

Ver artículo completo