In this study, an artificial intelligence tool called gene expression programming (GEP) has been successfully applied to develop an empirical model that can predict the shear strength of steel fiber reinforced concrete beams. The proposed genetic model incorporates all the influencing parameters such as the geometric properties of the beam, the concrete compressive strength, the shear span-to-depth ratio, and the mechanical and material properties of steel fiber. Existing empirical models ignore the tensile strength of steel fibers, which exercise a strong influence on the crack propagation of concrete matrix, thereby affecting the beam shear strength. To overcome this limitation, an improved and robust empirical model is proposed herein that incorporates the fiber tensile strength along with the other influencing factors. For this purpose, an extensive experimental database subjected to four-point loading is constructed comprising results of 488 tests drawn from the literature. The data are divided based on different shapes (hooked or straight fiber) and the tensile strength of steel fiber. The empirical model is developed using this experimental database and statistically compared with previously established empirical equations. This comparison indicates that the proposed model shows significant improvement in predicting the shear strength of steel fiber reinforced concrete beams, thus substantiating the important role of fiber tensile strength.

The flanged, barbell, and rectangular squat reinforced concrete (RC) walls are broadly used in low-rise commercial and highway under and overpasses. The shear strength of squat walls is the major design consideration because of their smaller aspect ratio. Most of the current design codes or available published literature provide separate sets of shear capacity equations for flanged, barbell, and rectangular walls. Also, a substantial scatter exists in the predicted shear capacity due to a large discrepancy in the test data. Thus, this study aims to develop a single gene expression programming (GEP) expression that can be used for predicting the shear strength of these three cross-sectional shapes based on a dataset of 646 experiments. A total of thirteen influencing parameters are identified to contrive this efficient empirical compared to several shear capacity equations. Owing to the larger database, the proposed model shows better performance based on the database analysis results and compared with 9 available empirical models.

Extensive numerical and analytical studies exist that focus on the scours around bridge piers with different cross-sections. However, studies addressing the scour around bridge piles are rather limited and not conclusive. Therefore, the most efficient cross-section reducing the local scour around a pile group is experimentally examined herein. Accordingly, comparative scouring of three different shapes, namely, circular, rectangular and lenticular, is investigated by installing a cohesion-less bedding material around scaled bridge piles immersed in clear water. It is also shown that the available pier scour predictive models grossly underestimate the depth of pile scour holes. For example, the pier predictive models underestimate the pile scours hole by more than 50% in the case of square and circular cross-sections. It also transpires from the experimental investigation that the scour hole depth around the square shape pile is significant, around the circular pile is moderate and around the lenticular pile is minimal.

Predictive models were developed to effectively estimate the RC exterior joint’s shear strength using gene expression programming (GEP). Two separate models are proposed for the exterior joints: the first with shear reinforcement and the second without shear reinforcement. Experimental results of the relevant input parameters using 253 tests were extracted from the literature to carry out a knowledge analysis of GEP. The database was further divided into two portions: 152 exterior joint experiments with joint transverse reinforcements and 101 unreinforced joint specimens. Moreover, the effects of different material and geometric factors (usually ignored in the available models) were incorporated into the proposed models. These factors are beam and column geometries, concrete and steel material properties, longitudinal and shear reinforcements, and column axial loads. Statistical analysis and comparisons with previously proposed analytical and empirical models indicate a high degree of accuracy of the proposed models, rendering them ideal for practical application.

For structures and load-bearing beams under extreme impact loading, the prediction of the transmitted peak impact force is the most challenging task. Available numerical and soft computing-based methods for finding peak impact force are not very accurate. Therefore, a simple and user-friendly predictive model is constructed from a database containing 126 impact force experiments of the simply supported RC beams. The proposed model is developed using gene expression programming (GEP) that includes the effect of the impact velocity and the impactor weight. Also identified are other influencing factors that have been overlooked in the existing soft computing models, such as concrete compressive strength, the shear span to depth ratio, and the tensile reinforcement quantity and strength. This allows the proposed model to overcome several inconsistencies and difficulties residing in the existing models. A statistical study has been conducted to examine the adequacy of the proposed model compared to existing models. Additionally, a numerical confirmation of the empirical model of the peak impact force is obtained by reference to 3D finite element simulation in ABAQUS. Finally, the proposed model is employed to predict the dynamic shear force and bending moment diagrams, thus rendering it ideal for practical application.