Modeling of Compressive Strength of Geopolymers by a Hybrid ANFIS-ICA Approach

Abstract

A hybrid adaptive neuro-fuzzy interfacial systems–imperialist competitive algorithm (ANFIS-ICA) was presented to determine the effect of concentration of alkali solution, alkali binder to alkali solution weight ratio, alkali activator to ordinary portland cement (OPC) weight ratio, oven curing temperature, and age of curing on the compressive strength of OPC-based geopolymers. Optimization of the type and number of membership functions was carried out by ICA while the training, testin,g and validating of the collected data sets was conducted by ANFIS. The obtained results indicated that the proposed ANFIS-ICA model is capable to predict the compressive strength of geopolymeric specimens well and suitably determine the effect of each parameter on this property. A parametric study is presented to show the effect of each parameter predicted by the model on compressive strength of the specimens.