Compressive Strength Prediction of Ferrochrome Slag Based Geopolymer Concretes Produced Under Different Curing Conditions by Using Prediction Methods

In this study, compressive strength (CS) values of ferrochrome slag (FS) based geopolymer concretes in different curing conditions were investigated. Ground FS was activated with the mixture sodium hydroxide and silicate. The silica modulus (Ms) concrete samples selected as 1.25, 1.50 1.75. Also, prepared by substituting 0%, 10% 20% fume (SF) replacement FS. Thus, 9 groups produced. CS determined on times (24, 48, 72 96 hours) temperatures (23, 40, 60, 80 100 °C). At same time, multilayer perceptron neural network (MLPNN), extreme learning machine (ELMNN) M5 model tree modeled for prediction samples, predict experimental results compared. According to experiment results, it that generally increased time increased, but addition SF, decreased. highest obtained sample containing 100% had 1.25 cured at °C 24-48-72 or hours. R2 MLPNN, ELMNN testing phase 0.956, 0.935 0.922, respectively. gave best result, root mean square error (RMSE) 0.723 normalized (NMRSE) 26.485 testing.