Prediction of load-displacement curve of concrete reinforced by composite fibers (steel and polymeric) using artificial neural network

摘要

Within the framework of studies on FRC, series of tests were undertaken in the laboratory in order to bet-ter understand the behavior of FRC and composite fibers to characteristic loading. The results obtained in the tests vary according to the percentage of the fibers, the water content, the size of grains (grains size distribution) and percentage of composite fibers. Therefore, it is important to estimate the deformation of concrete corresponding to the applied load according to available data and in the case of lacking of enough experimental data. For this purpose, neural network technique was used to predict the load-dis-placement curve and also compressive strength of concrete based on mix proportions. At first, the results of experimental tests carried out in PWUT laboratory on fiber reinforced concrete specimens are pre-sented and then the missing experimental data and gaps in load-displacement curve trend are predicted by back-propagation method in neural network. It is worth mentioning that it can also be used to study the different types of fibers and also orientation of the fibers which will be presented in future works.