Prediction of mechanical properties of recycled aggregate concretes containing silica fume using artificial neural networks and fuzzy logic

Artificial neural networks and fuzzy logic have been widely used in many areas in civil engineering applications. In this study, the models in artificial neural networks and fuzzy logic systems for predicting compressive and splitting tensile strengths of recycled aggregate concretes containing silica fume have been developed at the age of 3, 7, 14, 28, 56 and 90 days. For purpose of constructing these models, experimental results for 210 specimens produced with 35 different mixture proportions were gathered from the literature. The data used in the artificial neural networks and fuzzy logic models are arranged in a format of eight input parameters that cover the age of specimen, cement, water, sand, aggregate, recycled aggregate, superplasticizer and silica fume. According to these input, in the artificial neural networks and fuzzy logic models are predicted the compressive and splitting tensile strengths values from mechanical properties of recycled aggregate concretes containing silica fume. In the models of the training and testing results have shown that artificial neural networks and fuzzy logic systems have strong potential for predicting 3, 7, 14, 28, 56 and 90 days compressive and splitting tensile strengths values of recycled aggregate concretes containing silica fume.