Recent development in data processing systems had directed study and research of engineering towards the creation of intelligent systems to evolve models for a wide range of engineering problems. In this respect, several modeling techniques have been created to simulate various civil engineering systems. This study aims to review the studies on support vector machines (SVM) in structural engineering and investigate the usability of this machine learning based approach by providing three case studies focusing on structural engineering problems. Firstly, the concept of SVM is explained and then, the recent studies on the application of SVM in structural engineering are summarized and discussed. Next, we performed three case studies using the experimental studies provided. Applicability of SVM in structural engineering is confirmed by these case studies. The results showed that SVM is superior to various other learning techniques considering the generalization capability of produced model.

Reliability-based modeling of punching shear capacity of FRP-reinforced two-way slabs reliability;fiber reinforced polymer;RC slab;punching shear;structural safety;Monte Carlo simulation; This paper deals with the reliability analysis of design formulations derived for predicting the punching shear capacity of FRP-reinforced two-way slabs. Firstly, a new design code formulation was derived by means of gene expression programming. This formulation differs from the existing ones as the slab length (L) was introduced in the equation. Next, the proposed formulation was tested for its generalization capability by a parametric study. Then, the stochastic analyses of derived and existing formulations were performed by Monte Carlo simulation. Finally, the reliability analyses of these equations were carried out based on the results of stochastic analysis and the ultimate state function of ASCE-7 and ACI-318 (2011). The results indicate that the prediction performance of new formulation is significantly higher as compared to available design equations and its reliability index is within acceptable limits.

The study aimed to explore the possibility of strengthening RC corbels with many strengthening techniques. The research analyzed the RC corbels behavior under a wide range of variables. The theoretical study consisted of twelve models reinforced with GFRP bars with strengthening by steel plate. Finite element analysis with ANSYS APDL was used to verify five specimens. This research deals with a static nonlinear FE simulation to investigate the behavior of RC Corbels reinforced internally and externally. The verification with experimental work demonstrated a satisfactory agreement in the load-displacement relationship, ultimate load and displacement, and failure mode. The parametric study was implemented which included strengthening the four concrete corbels externally and four corbels internally by a steel plate in many configurations while the remaining three were modeled with varied compressive strength (30, 40, and 50) MPa. The external strengthening included the placing of steel plate externally around the corbel in a U-shaped form and partial strengthening by strips and bottom plate. The models with internal strengthening involved placing the steel plate internally instead of stirrups. The results discovered that the strengthening provided enrichments in the stiffness, ductility, and energy absorption by 37 %, 4 %, and 26 %. In addition, in the case of full external strengthening more than internal retrofitting, there is a maximum improvement in the cracking and ultimate load carrying capacity. The external strengthening was better than internal one due to the confinement effect of the concrete. The stress distribution and crack pattern were affected by the strengthening techniques and more cracks appeared in the corbels with external steel plates.

This research investigated and compared the structural behavior of reinforced concrete straight beams and beams made with out-of-plane parts. This study focused on the influence of the location and number of out-of-plane parts, as well as encasing the beams with a steel section, on the ultimate strength, deflection, and rotation in addition to the ductility, energy absorption, and failure mode. A total of nine beams were modelized numerically, divided into three series. The first one included one straight beam, while the remaining two series included four beams each made with out-of-plane parts with and without steel sections. The beams with out-of-plane parts connected the two, three, four, and five concrete segments. The outcomes revealed that the beams made with out-of-plane parts showed less strength than straight beams, which increased the connected segments and reduced the ultimate strength capacity. The regular beam’s linearity was dissimilar to the zigzag beams, which showed a linearity of 32% and was reduced to 22%, 20%, 19.67%, and 16% for beam out-of-plane parts made with two, three, four, and five segments, respectively. Forming a zigzag in the plane of the beams reduced the cracking load, but the decrement depended on the number of parts, which led to more reduction in the yielding load. Concerning the deflection and deformations, the concrete straight beams failed in flexure, with maximum deflection occurring at the midspan of the beam, which was different for beams without plane parts, which showed a combined shear-torsional failure for which the maximum deformation occurred at the midspan with inclination of connected parts on the interior perpendicular axis. Encasing the beams’ out-of-plane parts with steel sections enhanced the structural behavior. The ductility and energy absorption of the out-of-plane parts beams were less than the straight ones, but encasing the beams with a steel section improved the ductility and energy absorption twice.