Application of Gene Expression Programming (GEP) for the Prediction of Compressive Strength of Geopolymer Concrete

For the production of geopolymer concrete (GPC), fly-ash (FA) like waste material has been effectively utilized by various researchers. In this paper, the soft computing techniques known as gene expression programming (GEP) are executed to deliver an empirical equation to estimate the compressive strength [Formula: see text] of GPC made by employing FA. To build a model, a consistent, extensive and reliable data base is compiled through a detailed review of the published research. The compiled data set is comprised of 298 [Formula: see text] experimental results. The utmost dominant parameters are counted as explanatory variables, in other words, the extra water added as percent FA ([Formula: see text]), the percentage of plasticizer ([Formula: see text]), the initial curing temperature ([Formula: see text]), the age of the specimen ([Formula: see text]), the curing duration ([Formula: see text]), the fine aggregate to total aggregate ratio ([Formula: see text]), the percentage of total aggregate by volume ([Formula: see text]), the percent SiO(2) solids to water ratio ([Formula: see text]) in sodium silicate (Na(2)SiO(3)) solution, the NaOH solution molarity ([Formula: see text]), the activator or alkali to FA ratio ([Formula: see text]), the sodium oxide (Na(2)O) to water ratio ([Formula: see text]) for preparing Na(2)SiO(3) solution, and the Na(2)SiO(3) to NaOH ratio ([Formula: see text]). A GEP empirical equation is proposed to estimate the [Formula: see text] of GPC made with FA. The accuracy, generalization, and prediction capability of the proposed model was evaluated by performing parametric analysis, applying statistical checks, and then compared with non-linear and linear regression equations.