A genetic programming predictive model for parametric study of factors affecting strength of geopolymers

In this paper, the effect of different factors including mixture proportions and curing conditions on compressive strength of fly ash-based geopolymers was studied. Several parameters were used to construct a predictive model based on genetic programming, which deliver the compressive strength of specimens with reasonable accuracy. A parametric study was carried on to evaluate the effect of each individual parameter on strength of geopolymers. The results obtained by the model showed that changing the percentage of aggregates in the standard range and age of curing are ineffective on compressive strength of the considered geopolymer. On the other hand, increasing the percentage of fly ash, curing temperature and liquid to ash weight ratio were shown to assist compressive strength to improve. Another important parameter namely, sodium silicate to alkali hydroxide weight ratio had an optimum value of 2.5 to deliver the highest strength. All of model predictions were in accordance to the experimental results and those available in the literature for many types of fly ashbased geopolymers. It was concluded that Sarawak fly ash can be suitably used to synthesize geopolymers when the producing factors are precisely determined.