Prediction of the Shear Strength of Concrete T-Beams Using Artificial Neural Networks Model

Abstract

This paper presents an application of artificial neural network (ANN) to develop a model for predicting the shear strength of T-beams. The required data has been taken from literature. Statistical tools like mean, standard deviation (SD), correlation coefficients (R) and mean absolute error (MAE) are adopted to verify the ANN model against the experimental results obtained from the literature and with the existing empirical codes. The produced ANN model is utilized to carry out a parametric analysis to study the impact of the multiple parameters on the shear strength of T-beams. The parameters were shear span to depth ratios, effective depth, shear reinforcement, flange thickness, compressive strength of concrete, longitudinal steel ratio, flange width and web width. The outcomes of the parametric study show excellent trend agreement with the experimental database which emphasizes the statistical results. The overall analysis shows that the ANN model is more accurate than the guideline equations with respect to the experimental results and can be applied satisfactorily within the range of parameters covered in this study.