An Investigation into Strength Prediction of Columns Strengthened with CFRP Using Artificial Neural Networks

Abstract

This study presents an investigation into the strength prediction of columns strengthened with Carbon Fiber Reinforced Polymer (CFRP) using Artificial Neural Networks (ANNs). The research aims to develop a reliable predictive model for estimating the ultimate load-carrying capacity of CFRP-strengthened columns by considering key influencing parameters. A dataset comprising numerical results was used to train and validate the ANN model. The selected input parameters included column length, column diameter, steel tube thickness, concrete compressive strength, steel yield strength, CFRP ultimate tensile strength, CFRP thickness, and the number of CFRP layers. The ultimate axial strength served as the output parameter. The developed ANN model demonstrated high accuracy in predicting the column strength, capturing the nonlinear relationships among the variables effectively. The results confirm that artificial neural networks can serve as a powerful tool for structural strength prediction, reducing the need for extensive experimental testing and offering valuable insights for engineering design and assessment.