Prediction of compressive strength fiber-reinforced geopolymer concrete (FRGC) using gene expression programming (GEP)

Abstract

This paper examines the rapidly evolving fiber-reinforced geopolymer composites (FRGC), focusing on the material and geometrical properties of construction fibers and the mechanisms involved in fiber-binder interaction at different curing conditions to determine the compressive strength. To eliminate expensive and time-consuming experimental techniques, soft computing techniques, i.e., gene expression programming (GEP), were used to develop an empirical equation for the prediction of compressive strength (fc′) of FRGC. The database consists of 393 experimental datasets to determine the (fc′) with several curing days to train the GEP models. The mixtures contain the most influential parameters such as fly ash (FA), silica fume (SF), metakaolin (MK), ground granulated blast furnace slag (GGBS), aggregate (AG), sodium hydroxide (SH), sodium metasilicate (SM), alkaline activator (AAK), binder (B), superplasticizer (SP), water (W), curing age (CA), length (L), diameter (D), aspect ratio (AR), density (ρ), tensile strength (ft′), and fiber (F) to determine the fc′. The database is separated into two parts, 70% is used for training, and 30% is for testing. Several linking functions, chromosomes, head size, and genes have been undertaken to determine the optimal results. Expression trees (ETs) are developed and presented in the discussion section, and create the empirical equation from it. Determining the performance of the best model, MSE, RMSE, and R2 are calculated for the FRGC mixture to confirm the GEP models under various situations. Additionally, sensitivity analysis (SA) is also introduced to see the FRGC of each input parameter’s contribution to the prediction of fc′.