Prediction of shear strength of FRP-reinforced concrete flexural members without stirrups using artificial neural networks

Abstract

A theoretical model based on an artificial neural network (ANN) was presented for predicting shear strength of slender fiber reinforced polymer (FRP) reinforced concrete flexural members without stirrups. The model takes into account the effects of the effective depth, shear span-to-depth ratio, modulus of elasticity and ratio of the FRP flexural reinforcement and compressive concrete strength on shear strength. Comparisons between the predicted values and 106 test data showed that the developed ANN model resulted in improved statistical parameters with better accuracy than other existing equations. From the 2k experiment, the influence of parameters was identified in the order of effective depth, axial rigidity of FRP flexural reinforcement, shear span-to-depth ratio and compressive concrete strength. Using the ANN model and based on the results of the 2k experiment, predictive formulas for shear strength of slender FRP-reinforced concrete beam without stirrups were developed for practical applications. These formulas were able to predict the shear strength better than other existing equations.