Prediction of ultimate smear strength of reinforced-concrete deep beams using neural networks

This study explores the use of artificial neural networks in predicting the ultimate shear strength of reinforced-concrete deep beams. One hundred eleven experimental data collected from the literature cover the simple case of a simply supported beam with two point loads acting symmetrically with respect to the centerline of the span. The data are arranged in a format such that 10 input parameters cover the geometrical and material properties of the deep beam and the corresponding output value is the ultimate shear strength. Among the available methods in the literature, the American Concrete Institute, strut-and-tie, and Mau-Hsu methods were selected because of their accuracy and used to calculate the shear strength of each beam in the set. Later, an artificial neural network is developed using two different software programs and the ultimate shear strength of each beam is determined form these networks. It is found that the average ratio of actual and predicted shear strength was 0.99 for the neural network, 2.08 for the American Concrete Institute method, 0.85 for the strut-and-tie method, and 0.84 for the Mau-Hsu method. It is apparent that neural networks provide an efficient alternative method in predicting the shear strength capacity of reinforced-concrete deep beams where several equations exist, none of which produce an accurate result.