A Neuro-Fuzzy Model for Punching Shear Prediction of Slab-Column Connections Reinforced with FRP

Document Type : Regular Article


Faculty of Civil Engineering, Semnan University, Semnan, Iran


In this article, one of the robust systems of soft computing namely adaptive neuro-fuzzy inference system (ANFIS) is used to estimate the punching shear capacity of the concrete column-slab connections reinforced with FRP. For this purpose, a collection of experimental tests was used to train and test the ANFIS model. Five parameters including the area section of the column, Young’s modulus of the FRP bars, the effective flexural depth of the slab, FRP reinforcement ratio and also the compressive strength of concrete are used as inputs of the neuro-fuzzy system to estimate the considered output. The whole structure of the ANFIS also presented in mathematical steps. The obtained results of the created model of this paper indicated that the proposed ANFIS structure with a suitable accuracy could be used as a predictive model to determine the punching shear capacity of the considered elements. Also, the formulated model of the ANFIS in this paper can easily apply for codes and other researches.


Google Scholar


Main Subjects