Reliability analysis of strength models for short-concrete columns under concentric loading with FRP rebars through Artificial Neural Network

Over the last decade, the utilization of fiber-reinforced polymers (FRP) has been increased due to their versatile properties in concrete columns as a replacement of steel bars and their contribution to the axial load-carrying capacity of short concrete columns (SCC). Different researchers proposed equations to understand the load-carrying capacity of FRP rebars in SCC at the ultimate limit state (ULS). However, the current design practices have their reservation on the use (or taking the contribution) of FRP bars as the main vertical reinforcement in SCC. The present study aims to provide reliability analysis of all well-known physical models (for predicting the effect of FRP in SCC under concentric loading at ULS) through Artificial Neural Network (ANN) models (which do not base on mechanics) and new proposed equation (having a constant parameter to incorporate the lateral confinement effect). For this purpose, a database of 108 samples of SCC with FRP bars under concentric loading only, with detailed information (i.e., cross-section A(g), length of column L, Elastic Modulus of FRP E-f, compressive strength of concrete f(c) (MPa), longitudinal reinforcement ratio rho(l) (%), transverse reinforcement ratio rho(t) (%), and the ultimate axial load P-exp (kN), is collected from previous studies. The predicted axial load values (P-pred) from the ANN model (R = 0.94 and RMSE = 0.32) and proposed equation (R = 0.94 and RMSE = 0.32) exhibited closer results to the experimental values (P-exp)as compared to counterpart physical models. Comparative studies of ratio P-exp/P-pred against the critical parameters exhibited better accuracy of the ANN model and proposed equation as compared to counterpart physical models.

Automated summary

The utilization of fiber-reinforced polymers (FRP) in concrete columns has increased over the past decade, with researchers proposing equations to understand their load-carrying capacity. However, there are reservations in current design practices regarding the use of FRP bars as main reinforcement in columns. A study using Artificial Neural Network models and a new proposed equation aims to provide reliability analysis of physical models in predicting the effect of FRP in columns under concentric loading at the ultimate limit state. Results show that the ANN model and proposed equation yield closer results to experimental values compared to counterpart physical models.