H. Naderpour - Assistant Professor, Department of Civil Engineering, Semnan University
A. Kheyroddin - Professor, Department of Civil Engineering, Semnan University
M. K. Sharbatdar - Assistant Professor, Department of Civil Engineering, Semnan University
G. Ghodrati Amiri - Professor, School of Civil Engineering, Iran University of Science and Technology

Shear strengthening of reinforced concrete (RC) beams using fiber-reinforced polymers (FRPs) has been studied intensively in the last decade, even if shear for simple RC beams is not actually fully understood. Three main configurations of FRP strengthening including side bonding, U-wrapping, and complete wrapping may be used for externally bonded reinforcement of RC beams. In the present study, the FRP contribution to the shear resistance of RC beams is predicted using available experimental data by applying artificial neural networks (ANNs). With known combinations of input and output data, the neural network can be trained to extract the underlying characteristics and relationships from the data.Then, when a separate set of input data is fed to the trained network, it will produce an approximate but reasonable output. Neural networks are highly nonlinear and can capture complex interactions among input/output variables in a system without any prior knowledge about the nature of these interactions. A database containing the results from more than 200 tests performed in different research institutions across the world was collected. Having parameters used as input nodes in ANN modeling such as beam dimensions, compressive strength of concrete, type of FRP fiber, ultimate tensile strength of FRP, angle of inclination of FRP fibers with respect to the horizontal axis and thickness of FRP, the target/outputnodes was shear contribution of FRP. The transfer functions were assumed to be Tan-sigmoid and Logsigmoid for hidden layers. The comparison of the new approaches with existing experimental data and available empirical models shows that the ANN model can accurately predict the shear contribution ofFRP.

FRP, Artificial Neural Network, Shear Resistance, RC Beam