Machine Learning Approach for Prediction of Lateral Confinement Coefficient of CFRP-Wrapped RC Columns

Materials have a significant role in creating structures that are durable, valuable and possess symmetry engineering properties. Premium quality materials establish an exemplary environment for every situation. Among the composite constructions, carbon fiber reinforced polymer (CFRP) is one of best which provides symmetric superior strength stiffness to concrete structures. For structure be confining, region jeopardizes seismic loads axial force, specifically on columns, with limited proportion ties or stirrups implemented loftier ductility brittleness. The failure buckling columns CFRP has been studied by many researchers ongoing determine ways can retrofitted. This article symmetrically integrates two disciplines, computer application (machine learning). Technically, predicting lateral confinement coefficient (Ks) designs plays vital role. Therefore, machine learning models like genetic programming (GP), minimax probability regression (MPMR) deep neural networks (DNN) were utilized Ks value CFRP-wrapped RC columns. In order compute value, parameters such as column width, length, corner radius, thickness CFRP, compressive unconfined elastic modulus act stimulants. adopted 293 datasets square rectangular prediction Ks. developed models, GP MPMR provide encouraging performances higher R values 0.943 0.941; however, statistical indices proved model outperforms other better precision (R2 = 0.89) less errors (RMSE 0.056 NMBE 0.001). Based evaluation indices, rank analysis was carried out, secured more points ranked top.