Artificial neural networks for the prediction of shear capacity of steel plate strengthened RC beams

This paper presents the development of multilayer feedforward artificial neural network models for predicting the ultimate shear capacity of RC beams strengthened with web bonded steel plates. Two models are constructed using the data obtained from FEM model previously developed and validated by the authors. It is found that the neural network models predict the shear capacities of beams quite accurately. The model with dimension less parameters is found to be slightly less accurate than the ordinary model. Moreover, the neural network models predict the shear capacities of beams more accurately than the formula proposed by the authors in a previous study. Limited parametric Studies show that the network models capture the underlying shear behavior of RC beams with web-bonded steel plates quite accurately. (C) 2004 Elsevier Ltd. All rights reserved.