نوع مقاله : علمی - پژوهشی
موضوعات
عنوان مقاله English
نویسندگان English
Reinforced concrete structures are widely used in civil infrastructure due to their favorable load-bearing properties, high compressive strength, and economical construction. However, the shear performance of these structures has always been a major concern in their design and operation. One of the common methods for strengthening reinforced concrete members is the use of fiber-reinforced polymers (FRP). Reinforcing bars made of FRP are widely utilized due to their numerous advantages compared to steel reinforcement. However, studies conducted on FRP-reinforced concrete beams have primarily focused on their longitudinal behavior, and their shear strength has not been comprehensively investigated. The primary aim of this research is to propose a model based on Artificial Neural Networks (ANN) for predicting the shear strength of FRP-reinforced concrete beams. For this purpose, a database of 177 FRP-reinforced concrete beams was compiled from the results of existing studies. The proposed model provides a high-accuracy prediction of the shear strength of these beams. Additionally, to evaluate the performance of the proposed model, residual analysis and comparisons of the outputs of the Adaptive Neuro-Fuzzy Inference System (ANFIS) and the Artificial Neural Network (ANN) were conducted. The results demonstrated that the ANN model exhibits superior accuracy. The proposed model can serve as an efficient tool for calculating the shear strength of FRP-reinforced concrete beams. Consequently, within the parameter ranges defined in this study, there will be no need for costly and time-consuming experimental studies.
کلیدواژهها English
