An Artificial Network-Based Prediction of Key Reference Zones on Axial Stress–Strain Curves of FRP-Confined Concrete

The accurate prediction of reference points on the axial stress–axial strain relationship fiber-reinforced polymer (FRP)-confined concrete is vital to pre-design structures made with this system. This study uses an artificial neural network (ANN) for predicting hoop rupture (εh,rup) and transition zone, namely (εc1) stress (f’c1), stress–strain curves FRP-confined concrete. These are key parameters estimating a zone curves. In study, accompanied these parameters, ultimate condition including compressive strength strain, were predicted using comprehensive database. Various combinations input data ANN used increase accuracy predictions. A sensitivity analysis model validation assessment performed evaluate predictability developed models. At end, comparison between proposed models in existing design-oriented was presented. It shown that higher or comparable Additionally, predict f’c1 εc1 exhibit compared results indicate capture lateral confinement effect zones more robust performance