Prediction of FRP-concrete ultimate bond strength using Artificial Neural Network

The ultimate bond strength between Fiber Reinforced Polymers (FRP) and concrete is one of the most important elements in the performance of the strengthened beam and its failure mode and failure mechanism. In this investigation an Artificial Neural Network (ANN) model has been developed to predict the ultimate bond strength (P_u) between FRP and concrete based on several factors that influence it. These factors, which were used as input to the ANN, include concrete prism width (b_c), concrete compressive strength (f_cu), concrete tensile strength (f_t) as well as the FRP thickness (t_f), width (bf), tensile strength (f_f), elastic modulus (E_f) and the bond length (L) between FRP and concrete. The ANN predicted ultimate strength loads were compared with experimental values. It is concluded that the ultimate bond strength predicted by the ANN model are reasonably accurate compared to the experimental values and the accuracy can be further improved by using sufficient data generated by similar standardized tests. Based on the developed model, a parametric study can be carried out to investigate the influence of several parameters on the ultimate bond-strength between FRP and concrete and on the behaviour of bond slip compared to existing models.