Machine Learning Based Modelling Approach for Predicting the Mechanical Properties of Fibers Reinforced Polymer (FRP) Confined Concrete

Abstract

This study presents the application and comparison of soft computing techniques, such as,Gene Expression programming (GEP) and Multi Expression Programming (MEP) for modeling the compressive strength of carbon fiber-reinforced polymer (CFRP) confined concrete. The proposed soft computing models would be based on experimental results collected from previously published literature. The study will focus on ultimate strength of concrete material after confinement with CFRP composites. The study parameters will include diameter and height of the cylindrical specimen, elastic modulus of CFRP, unconfined concrete strength, and total thickness of CFRP layer. The validation of the proposed soft computing models will be done through drawing comparison with experimental results.Moreover, the results of proposed soft computing models and predictions will be verified through a parametric study and the accuracy will be compared with the existing models in the literature by an experimental versus theoretical comparison. Based on the results, evaluation and performance of proposed model will be assessed with other strength models proposed in the literature using the collected database.