出版社：Niğde Üniversitesi Mühendislik Fakültesi Dekanlığı
摘要：In the present study, the gene expression programming (GEP) technique is used for predicting the splitting tensile strength ( f sts ) values of steel fiber reinforced concretes containing silica fume at different days. The experimental results of 186 specimens produced with 126 different mixtures were obtained from the different literatures for the purpose of constituting the model in the GEP technique. In the sets of the model, the age of specimen, the amounts of concrete mixtures and the properties of steel fibers were entered as the inputs variables, while the f sts were used as the output variable in the model. According to these input variables, the f sts values of steel fiber reinforced concretes containing silica fume at different days are in accordance with the experimental results in the model. The results of the training, testing and validation of models compared with the experimental results have shown that GEP technique has strong potential for predicting the f sts values of concretes containing silica fume at different days. The statistical parameters expressed with the R-squared (R 2 ), the mean absolute percentage error (MAPE) and the root mean square error (RMSE) clearly show the applicability of GEP model. Keywords: Steel fiber, silica fume, concrete, splitting tensile strength
