What question did this study set out to answer?

The aim is to develop a machine learning framework to predict volume expansion in cement pastes with additives.

February 14, 2026Open Access

Enhancing dimensional stability in cement pastes: a machine learning approach with metaheuristic-optimized categorical boosting

Puntos clave

The aim is to develop a machine learning framework to predict volume expansion in cement pastes with additives.
Developed a dataset of 170 samples from literature
Identified four input variables: Portland cement content, fly ash content, magnesium oxide, and curing age
Utilized a Categorical Boosting model optimized with metaheuristic algorithms
Demonstrated potential improvements in predicting volume expansion metrics
Showed effective use of machine learning for stability in cement formulations

Resumen

Abstract Low hydration activity and challenging management of delayed expansion restrict the application of fly ash (FA) F A and MgO MgO expansive additive (MEA) M E A in cement pastes. Very few research on machine learning techniques for volume expansion (V₄) V e in such systems have been conducted already. This study develops a machine learning framework to predict the volume expansion (V₄) V e of cement pastes incorporating fly ash (FA) F A and MgO MgO expansive additive (MEA) M E A, materials whose low hydration activity and delayed expansion complicate their practical use. A dataset of 170 samples compiled from published literature was utilized, comprising four input variables—Portland cement content (PC PC, %), fly ash content (FA FA, %), MgO MgO expansive additive (MEA MEA, %), and curing age (SA SA, days) —to predict the target variable, V₄ V e (%). A Categorical Boosting (CatBoost) C a t B o o s t model was optimized using two recent metaheuristic algorithms, the Starfish Optimization Algorithm (StOA) S t O A </jats

Me gusta

Guardar

Ver artículo completo