Predicting the strength development of cements produced with different pozzolans by neural network and fuzzy logic

This study is based on the determination of optimum usage of pozzolans; as supplementary cementing material for blended cement production. Blended cements were produced with natural zeolite (clinoptilolite), Eskisehir trass, Nevsehir trass, fly ash and ground granulated blast furnace slag at 10, 20, 30, 35, 40 and 45% replacement ratios. Experimental results were also obtained by building models according to artificial neural network and fuzzy logic systems. It is concluded that the strength development of cement mortars containing different pozzolans can be obtained according to neural network and fuzzy logic model test results without any experimental study. (C) 2008 Elsevier Ltd. All rights reserved.