Document Type : Research Papers
Department of Civil Engineering, Faculty of Technical and Engineering, University of Hormozgan, Bandar Abbas, Iran
Department of Civil Engineering, University of Hormozgan
Department of Civil Engineering, University of Birjand, Birjand, Iran
It is generally accepted that shear strength of reinforced concrete deep beams varies depending on the mechanical and geometrical parameters of the beam. Accurate estimation of shear strength is a substantial issue in engineering design. However, the prediction of shear strength in this type of beams is not very accurate. One of the relatively accurate methods of estimating shear strength is the use of artificial intelligence. In this study, the applicability of adaptive neuro-fuzzy inference system using meta-heuristic algorithms for predicting shear strength of reinforced concrete beams was examined and the results were compared with existing regulations. For this purpose, the parameters of concrete compressive strength, cross-section width, effective depth, beam length, shear span-to-depth beam ratio (a/d), as well as percentage of longitudinal and transverse reinforcement were selected as input, and shear strength of reinforced concrete deep beam as output parameter. Here, after the selection of appropriate input and outputs, K-fold validation method with k = 10 was used to train and test the algorithms. The results showed that the model of neural fuzzy inference system with differential evolutionary optimization algorithm with second root mean square error of 25.968 and correlation coefficient of 0.914 is more accurate than other methods.