Soft computing for modeling punching shear of reinforced concrete flat slabs

This paper presents applying gene expression programming (GEP) approach for predicting the punching shear strength of normal and high strength reinforced concrete flat slabs. The GEP model was developed and verified using 58 case histories that involve measured punching shear strength. The modeling was carried out by dividing the data into two sets: a training set for model calibration, and a validation set for verifying the generalization capability of the model. It is shown that the model is able to learn with high accuracy the complex relationship between the punching shear and the factors affecting it and produces this knowledge in the form of a function. The results have demonstrated that the GEP model performs very well with coefficient of determination, mean, standard deviation and probability density at 50% equivalent to 0.98, 0.99, 0.10 and 0.99, respectively. Moreover, the GEP predicts punching shear strength more accurately than the traditional methods.