Prediction of compressive strength of fiber-reinforced polymers-confined cylindrical concrete using artificial intelligence methods

Abstract

Compressive strength is the ability of materials to withstand loads without deformation or cracking. It is one of the most important criteria for evaluating the properties of concrete. The use of Fiber-Reinforced Polymers (FRP) to Strengthen concrete columns and as a supplement to improve some properties of concrete materials has received much attention in recent decades. Therefore, it is important to investigate and determine the compressive strength of confined concrete with FRP sheets. In this study, a comprehensive database containing 1066 specimens of concrete cylinders confined with FRP sheets has been collected. Then, using machine learning methods, the estimation and evaluation of the compressive strength of the mentioned specimens were discussed. The artificial neural network of multilayer perceptron (MLP) and support vector regression (SVR), fuzzy neural inference system (ANFIS), and its combination with particle swarm algorithm (PSO) and kriging interpolation method are the methods used in this study. Subsequently, these methods were compared with the models presented in previous studies. The results of this comparison show that the kriging interpolation method with a correlation coefficient of 0.985 in estimating compressive strength has the lowest error compared to other models.