Predicting shear strength of RC slender beams with small web openings by artificial neural networks and regression analysis

In this study, the shear behavior of RC slender beams with small web openings was investigated. After an intensive review, only three prediction models were found in the literature. In the review study, 77 experimental shear test datasets of un-strengthened specimens were collected from the different articles of literature. Based on the collected dataset, two new prediction models were proposed using ANN and nonlinear regression analysis. The efficiency of the proposed models compared to the available models in the literature was assessed based on the collected experimental dataset using standard statistical metrics. Furthermore, a parametric analysis was conducted for further verification of the proposed and literature models. It was concluded that the results of the proposed models were found to be more consistent with experimental data than those of the models found in the literature.