Predictive compressive strength models for green concrete

Abstract

Purpose The purpose of this paper is to develop new predictive models using gene expression programming in order to estimate the compressive strength of green concrete, as accurate models that can predict the compressive strength of green concrete are still lacking. Design/methodology/approach To estimate the compressive strength of plain concrete, fly ash concrete, silica fume concrete and concrete with silica fume and fly ash, four predictive GEP models are developed. The GEP models are developed using a large and reliable database that is collected from the literature. The GEP models are validated using the collected experimental database. Findings The R2 is used to statistically evaluate the performance of the GEP models wherein the R2 values for the GEP models including all data are 85, 95, 80 and 95.3 percent for the models that predict the compressive strength of plain concrete, fly ash concrete, silica fume concrete and concrete with silica fume and fly ash, respectively. Originality/value The GEP models have high R2 values and low RMSE and MAE, which indicates that they are capable of predicting the compressive strength of green concrete with a reasonable accuracy.