Modeling for Shear Strength of FRP-Reinforced Concrete Members by Generalized Regression Neural Network

Generalized Regression Neural Networks (GRNNs) can be used for regression analysis where the behaviors are non-linear. This paper presents the shear capacity predictions of concrete members reinforced with fiber reinforced polymer (FRP) bars using GRNN. The members are reinforced in the long direction only and there was no diagonal reinforcement. A total of 196 test results are utilized training and testing of the GRNN model. The outcomes of train and test dataset are compared with the test results. From the comparison, GRNN is found to be an effective tool for the estimation of shear capacity of FRP reinforced concrete elements with no transverse reinforcement.