An Artificial Neural Network Prediction Model of GFRP Residual Tensile Strength

Abstract

This study uses an Artificial Neural Network (ANN) to examine the constitutive relationships of the Glass Fiber Reinforced Polymer (GFRP) residual tensile strength at elevated temperatures. The objective is to develop an effective model and establish fire performance criteria for concrete structures in fire scenarios. Multilayer networks that employ reactive error distribution approaches can determine the residual tensile strength of GFRP using six input parameters, in contrast to previous mathematical models that utilized one or two inputs while disregarding the others. Multilayered networks employing reactive error distribution technology assign weights to each variable influencing the residual tensile strength of GFRP. Temperature exerted the most significant influence at 100%, while sample dimensions had a minimal impact at 17.9%. In addition, the mathematical model closest to the proposed was the Bazli model, because the latter depends on two variables (thickness and temperature). The ANN accurately predicted the residual tensile strength of GFRP at elevated temperatures, achieving a correlation coefficient of 97.3% and a determination coefficient of 94.3%.