Artificial neural networks (ANNs) are an emerging field of research and have proven to have significant potential for use in structural engineering. In previous literature, many studies successfully utilized ANNs to analyze the structures under different loading conditions and verified the accuracy of the approach. Several studies investigated the use of ANNs to analyze the shear behavior of reinforced concrete (RC) members. However, few studies have focused on the potential use of an ANN for analysis of the torsional behavior of an RC member. Torsion is a complex problem and modeling the torsional fracture mechanism using the traditional analytical approach is problematic. Recent studies show that the nonlinear behavior of RC members under torsion can be modeled using ANNs. This paper presents a comprehensive analytical and parametric study of the torsional response of RC beams using ANNs. The ANN model was trained and validated against an experimental database of 159 RC beams reported in the literature. The results were compared with the predictions of design codes. The results show that ANNs can effectively model the torsional behavior of RC beams. The parametric study presented in this paper provides greater insight into the torsional resistance mechanism of RC beams and its characteristic parameters.

The current design codes i.e. AISC 360-16, CSA-S16-19, EC-04 etc. provide empirical relationships to estimate the capacity of shear connectors which were developed based on pushout tests of headed studs and channels connectors in exposed type sections. Therefore, these equations may result inaccurate predictions for strength of connectors in infilled-type sections. This study presents a detailed experimental study investigating the performance of angle connectors in composite sections. The testing program consisted two series of pushout tests. A total of 36 specimens were tested, considering the influence of several important parameters i.e. the length (L_c), height (h_c), and web-thickness (t_w) of angle connector, length of the weld (w) and the direction of shear connector (forward/backward) etc. The tests results demonstrated that with increasing connector height h_s, and thickness, the maximum load P_max and slip δu were increased. The connector direction didn't change much the load-slip behavior. The prediction accuracy of the existing shear capacity models was evaluated by comparing the predictions with experimental results. The current equations were noticed to be highly inconsistent in predicting the shear capacity of angle connectors, especially in case of infilled type sections. When the entire length of connector was taken as the effective length, the models overestimated the shear capacity. While in case when the welding length was taken as effective length in calculations, the models underestimated the shear strength of angle connectors.

Energy dissipation of columns in the post-yielding range of deformation plays a significant role in preventing the total collapse of reinforced-concrete (RC) structures. However, such plastic deformations cause elongation in plastic hinge regions of RC columns if the axial force ratio is low. This study investigated the elongation behaviour of RC columns by testing five groups of 20 specimens subjected to three different loading patterns. Experimental results showed that the longitudinal axial strain of RC columns was quite different from that of RC beams because of the presence of axial force. The longitudinal axial strain of RC columns reduced with increasing axial force. Axial strain was also a function of loading pattern and lateral reinforcement ratio. Based on these observations, an analytical model was developed to predict the axial strain behaviour of RC columns. The proposed model includes four path types: a loading region, an unloading region, a slip region and a repeated loading region. The model was verified against 32 test results, including specimens tested in this study and reported in the literature. The longitudinal axial strain predicted using the proposed model agreed reasonably well with the experimental axial strains results.