Compressive strength of concrete cylindrical columns confined with fabric-reinforced cementitious matrix composites under monotonic loading: Application of machine learning techniques. (August 2022)

• Record Type: Journal Article
• Authors: Irandegani, Mohammad Ali; Zhang, Daxu; Shadabfar, Mahdi
• Is Part Of: Structures. Volume 42(2022)
• Page Start: 205
• Page End: 220
• Publication Date: 2022-08
• Subjects: Efabric elastic modulus (fiber) -- fcc compressive strength of the confined concrete -- fco unconfined concrete compressive strength -- ke stiffness efficiency -- ρfiber percentage of fiber -- ANN artificial neural network -- BR Bayesian Regularization -- CDF cumulative distribution function -- CPU central processing unit -- D column diameter -- FORM first-order reliability method -- FOSM first-order second moment -- FRCM fabric-reinforced cementitious matrix -- FRP fiber-reinforced polymer -- GA genetic algorithm -- GP genetic programming -- H column height -- LMA Levenberg-Marquardt algorithm -- MAE mean absolute error -- ML machine learning -- MSE mean squared error -- PBO polyparaphenylene benzobisoxazole -- RAM random access memory -- t temperature -- TLBO teaching–learning-based optimization; FRCM system -- Artificial Neural Network (ANN) -- Genetic Algorithm (GA)-based regression model -- Monte Carlo sampling; Structural engineering -- Periodicals; 624.1
• DOI: 10.1016/j.istruc.2022.05.111
• Languages: English
• ISSNs: 2352-0124

Abstract

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 f cc 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 f cc between 25 and 35 MPa. The maximum effect of temperature and unconfined concrete compressive strength, however, happens in the medium range of f cc between 35 and 45 MPa. Additionally, the percentage of fiber mostly affects the large range of fcc between 45 and 49 MPa.