Compressive strength of concrete cylindrical columns confined with fabric-reinforced cementitious matrix composites under monotonic loading: Application of machine learning techniques

Abstract

The reinforcement of concrete columns with fabric reinforced cementitious matrix (FRCM) is one of the most challenging issues in the construction of concrete structures, as there is still an absence of a promising model to assess their performance. This is because the behavior of such elements is complex and accompanied by a high margin of uncertainty. To address this issue, this study compiles a large dataset of the performance of FRCM-reinforced concrete columns under monotonic load. The obtained dataset is then used to train an artificial neural network (ANN) as a promising method for predicting the compressive strength of concrete columns with acceptable accuracy. Afterward, using a genetic algorithm (GA)-based regression model, a simplified formula is developed as an explicit model for predicting the compressive strength of FRCM-confined concrete columns. Additionally, a reliability model is established and solved by the Monte Carlo sampling method to capture the uncertainty and provide the results probabilistically. The results indicate that with the increase of fcc, the probability of exceedance is sharply reduced, so that the failure probability of fcc greater than 68 MPa falls below 2%. Moreover, a reliability sensitivity analysis is performed to measure the effects of input parameters on the resulting exceedance probability. The results reveal that the greatest impact of column diameter and height falls within the small range of fcc between 25 and 35 MPa. The maximum effect of temperature and unconfined concrete compressive strength, however, happens in the medium range of fcc between 35 and 45 MPa. Additionally, the percentage of fiber mostly affects the large range of fcc between 45 and 49 MPa.