Artificial intelligence techniques for prediction of the capacity of RC beams strengthened in shear with external FRP reinforcement

Abstract

The prediction of the shear capacity of reinforced concrete beams retrofitted in shear by means of externally bonded FRP is very complex as demonstrate the studies carried out up to date. As alternative to the conventional methods two approaches based on artificial intelligence are proposed for the first time. Firstly, the use of neural networks as a means of predicting shear capacity without the need of using complex models and, secondly, the use of genetic algorithms as a means of determining suitably how the shear mechanism works. Predictions obtained with both approaches are compared to experimental values.