Diseño del refuerzo a cortante de estructuras de hormigón a base de materiales compuestos aplicando redes neuronales artificiales

Shear strengthening design with FRP for concrete structures using artificial neural networks

In the last years composite materials are emerging as an alternative technique to traditional materials and techniques to increase the load-carrying capacity of existing concrete structures due to their advantageous properties. Because of this increasing interest, different guidelines about the strengthening of concrete structures with FRP systems are emanating in different countries and continents. However, most research in this area has been undertaken to study flexural behaviour and little study has been focused on shear strengthening. This is mainly due to that shear failure is a complex mechanism even for simple RC elements and, furthermore, the mechanism becomes more complex when external shear reinforcement is added. Because of it, the proposed practical design methods change enough when evaluating the contribution of the external shear reinforcement. Most of proposed expressions are based on a regression analysis from experimental data corresponding to specific configurations which makes very difficult to capture the real interrelation among the involved parameters. To avoid this, an artificial neural network has been developed to predict the shear strength of concrete beams reinforced with this method from previous tests. Furthermore, a parametric study has been carried out to determine the influence of some beam and external reinforcement parameters on the shear strength with the purpose of reaching more reliable designs.