An innovative approach for bond strength modeling in FRP strip-to-concrete joints using adaptive neuro-fuzzy inference system

In this study, a new computational approach for determination of the bond strength of fibre reinforced polymer (FRP) strip-to-concrete joints is presented based on adaptive neuro-fuzzy inference system (ANFIS). For this purpose, 150 experimental data were gathered from the literature. The number of 120 data was used to train the system, and the other 30 were applied to the test. Six parameters including the compressive strength of the concrete, width of the concrete prism, FRP thickness, FRP modulus of elasticity, FRP bond length and FRP width were utilized to determine the bond strength. The results of the proposed ANFIS show high accuracy in the model. A comparison study with other published equations was also done, and it was concluded that ANFIS had less error and also had better results in comparison with other existing methods. Finally, a sensitivity analysis was done to investigate the relative importance of each input parameter on the target.