Abstract
Annually, the thermal coal industries produce billion tons of fly-ash (FA) as a waste by-product. Which has been proficiently used for the manufacture of FA based geopolymer concrete (FGC). To accelerate the usage of FA in building industry, an innovative machine learning techniques namely gene expression programming (GEP) and multi expression programming (MEP) are employed for forecasting the compressive strength of FGC. The comprehensive database is constructed comprising of 311 compressive strength results. The obtained equations relate the compressive strength of FGC with eight most effective parameters i.e., curing regime (T), time for curing (t) in hours, age of samples (A) in days, percentage of total aggregate by volume (% Ag), molarity of sodium hydroxide (NaOH) solution (M), silica (SiO2) solids percentage in sodium silicate (Na2SiO3) solution (%S), superplasticizer (%P) and extra water (%EW) as percent FA. The accurateness and predictive capacity of both GEP and MEP model is assessed via statistical checks, external validation criteria suggested by different researcher and then compared with linear regression (LR) and non-linear regression (NLR) models. In comparison with MEP equation, the GEP equation has lesser statistical error and higher correlation coefficient. Also, the GEP equation is short and it would be easy to use in the field. So, the GEP model is further utilized for sensitivity and parametric study. This research will increase the re-usage of hazardous FA in the development of green concrete that would leads to environmental safety and monetarist reliefs.