Shear design procedure for reinforced normal and high-strength concrete beams using artificial neural networks. Part II: beams with stirrups

In order to re-evaluate the current shear procedures of different codes of practice for normal-strength and high-strength beams with web reinforcement an extensive research study was performed. An Artificial Neural Network was developed to predict the shear strength of reinforced beams failing on diagonal tension failure and, based on its results, a parametric study was carried out to study the influence of each parameter affecting the shear strength of beams with web reinforcement. Some important influences are highlighted, for example the non-linear relationship between the amount of stirrups and the shear strength. Finally, new design expressions are proposed, taking into account the observed behaviour for the design of high-strength and normal-strength reinforced concrete beams with shear reinforcement. The new expressions correlate much better with the empirical tests than EC-2 or ACI procedures.