Estimating the compressive strength of rectangular fiber reinforced polymer–confined columns using multilayer perceptron, radial basis function, and support vector regression methods

Recently, there has been a tendency to use machine learning (ML)–based methods, such as artificial neural networks (ANNs), for more accurate estimates. This paper investigates the effectiveness of three different machine learning methods including radial basis function neural network (RBNN), multi-layer perceptron (MLP), and support vector regression (SVR), for predicting the ultimate strength of square and rectangular columns confined by various FRP sheets. So far, in the previous study, several experiments have been conducted on concrete columns confined by fiber reinforced polymer (FRP) sheets with the results suggesting that the use of FRP sheets enhances the compressive strength of concrete columns effectively. Also, a wide range of experimental data (including 463 specimens) has been collected in this study for square and rectangular columns, confined by various FRP sheets. The comparison of ML-derived results with the experimental findings, which were in a very good agreement, demonstrated the ability of ML to estimate the compressive strength of concrete confined by FRP; the correlation coefficient (R2) for MLP, RBFNN, and SVR methods was equal to 0.97, 0.97, and 0.90, respectively. Similar accuracy was obtained by MLP and RBFNN, and they provided better estimates for determining the compressive strength of concrete confined by FRP. Also, the results showed that the difference between statistical indicators for training and testing specimens in the RBFNN method was greater than the MLP method, and this difference indicated the poor performance of RBFNN.

SEISMIC PERFORMANCE OF GFRP-RC RECTANGULAR COLUMNS: NUMERICAL STUDY

Composite materials like glass fiber-reinforced polymer (GFRP) is becoming widely acceptable to be used as a reinforcing material due to its high ultimate tensile strength-to-weight ratio and excellent resistance to corrosion. However, the seismic behavior of GFRP-reinforced concrete columns has not been fully investigated yet. This paper presents the results of a numerical analysis of full-size GFRP-RC rectangular columns under cyclic loading. The simulated column depicts the lower part of a building column between the foundation and the point of contra-flexure at the mid-height of the column. GFRP reinforcement properties and concrete modeling based on fracture energy have been incorporated in the numerical model. Experimental validation has been used to examine the accuracy of the constructed finite element models (FEMs) using a commercially available software. The validated FEM was used to perform a parametric study, considering several concrete strength values and axial load levels, to study its influence on the performance of the GFRP-reinforced concrete columns under cyclic loading. It was concluded that the hysteretic dissipation capacity deteriorates under high axial load level due to severe softening of the concrete. The FE results showed a substantial improvement of the lateral load-carrying capacities by increasing concrete compressive strength.

Punching shear behaviour of flat slabs with different reinforcement schemes: openings and rectangularity effects

PurposeThe main goal is to investigate the effect of size and location of opening and column size on the punching shear strength. Openings are often needed in order to install mechanical and electrical services. This process takes away part of the concrete volume which is responsible for resisting the shear forces and any unbalanced moment. Furthermore, the application of rectangular columns in flat slabs is commonly used in practice as they provide lateral stiffness to the building. They are also utilised in garages and multi-storey buildings where these elongated cross-sectional columns reduce the effective span length between adjacent columns.Design/methodology/approachThis research is a numerical-based investigation that is calibrated based on a thirteen previously tested and numerically calibrated slab specimens with no openings. A parametric study is conducted in this study to consider the effect of other parameters, which are the size and location of opening and the rectangularity ratio of column in order to evaluate their effect on the punching shear capacity. A total of 156 models are developed to study these factors. Additionally, the predicted shear carrying capacity of the simulated slabs is calculated using the ACI318–19 and Eurocode (EC2-04) equation.FindingsThe presence of openings reduced the punching shear capacity. The small opening's location and orientation have almost no effect except for one slab. For slabs of large openings, the presence of openings reduced the punching capacity. The punching capacity is higher when the openings are farther from the column. The numerically obtained results of slabs with rectangular columns show lower punching capacity compared to slabs of squared columns with the same length of the punching shear control perimeter. The punching capacity for all slabs is predicted by ACI318–19 and Eurocode (EC2-04) and it is found that Eurocode (EC2-04) provided a closer estimation.Originality/valueThe slabs considered for calibration were reinforced with four different punching shear reinforcement configurations, namely; ordinary closed rectangular stirrups, rectangular spiral stirrups, advanced rectangular spiral stirrups and circular spiral. Generally, there has been limited research on concrete flat slabs with openings in comparison with other subjects related to structural engineering (Guan, 2009) and no research on punching shear with openings of slabs reinforced with these reinforcement schemes. The available research focussed on the effects of openings on the flexural behaviour of reinforced concrete slabs includes Casadei et al. (2003), Banu et al. (2012) and Elsayed et al. (2009). In addition, experimental tests that examined slabs supported on rectangular columns are very limited.

Analysis for optimization of spiral reinforcement in pre-fabricated bridge columns

<p>Savings and optimization in the use of steel and concrete can significantly contribute to the reduction of CO2 emission and energy consumption, promoting a greener environment for the place we live. It has been shown that the use of multi-spiral reinforcement (MSR) in square or rectangular columns can significantly save the amount of steel for transverse reinforcement and yet can still achieve a higher structural performance than conventional tie reinforcement. The paper presents a validation of a numerical model for nonlinear analysis of novel multi-spiral reinforcement in prefabricated columns. The validated model will be used for the subsequent studies and optimization of the spiral reinforcement location, diameter and pitch. Selected arrangements of the multi-spiral reinforcements have been analysed to demonstrate their effectiveness in static and cyclic response.</p>