Data-driven shear strength prediction of steel fiber reinforced concrete beams using machine learning approach

Machine learning framework for predicting failure mode and shear capacity of ultra high performance concrete beams

The safety and stability of roadways is greatly influenced by the complex geological conditions present in the Sanmenxia Bauxite Mine, Henan Province, China. In this study, based on data from field survey, advanced detection methods, numerical studies, and monitoring studies, we have adopted the method of steel fiber-reinforced shotcrete to improve the excavation rate of roadways and guarantee the safety of the tunnel when it passes through unfavorable geological bodies, such as shale rocks and broken argillaceous limestone. Field surveys showed that the stability of roof rocks is the major problem faced by engineers; however, tunnel construction using cast-in-situ concrete, which is the method currently applied, costs too much time, resulting in an excavation rate that is too slow to meet the requirements of the Sanmenxia Bauxite Mine. Here, we propose an optimized scheme which, when combined with numerical simulations and data from advanced detection techniques and field monitoring surveys, can improve the efficiency of roadway roof support. During the implementation of the new scheme, the geological anomalies ahead of the working face were detected in advance. It is assumed that the supporting effect of the steel fiber-reinforced shotcrete is equivalent to that of the cast-in-situ concrete as long as a certain thickness is reached. Moreover, the steel fiber-reinforced shotcrete has better mechanical properties than cast-in-situ concrete and achieves a better combination effect with surrounding rock masses. Based on geological conditions and numerical results, the shotcrete should be thickest in the middle area along the roadway axis passing through the unfavorable geological bodies, and gradually become less thick from the middle to both ends. Field tests were carried out to verify the effectiveness of the scheme. The monitoring results show that the roadway passing through broken argillaceous limestone was stable after being supported by shotcrete (at least 80 mm); its thickness should reach at least about 120 mm when passing through shale rock mass. The results indicate that the use of steel fiber-reinforced shotcrete can considerably shorten the construction time compared with cast-in-situ concrete support. The scheme has proved to be a feasible, economical, and time-saving method for underground excavation in the Sanmenxia Bauxite Mine.

The stability and roof-support optimization of roadways passing through unfavorable geological bodies using advanced detection and monitoring methods, among others, in the Sanmenxia Bauxite Mine in China’s Henan Province

Adding steel fibers to concrete improves the capacity in tension-driven failure modes. An example is the shear capacity in steel fiber reinforced concrete (SFRC) beams with longitudinal reinforcement and without shear reinforcement. Since no mechanical models exist that can fully describe the behavior of SFRC beams without shear reinforcement failing in shear, a number of empirical equations have been suggested in the past. This paper compiles the existing empirical equations and code provisions for the prediction of the shear capacity of SFRC beams failing in shear as well as a database of 488 experiments reported in the literature. The experimental shear capacities from the database are then compared to the prediction equations. This comparison shows a large scatter on the ratio of experimental to predicted values. The practice of defining the tensile strength of SFRC based on different experiments internationally makes the comparison difficult. For design purposes, the code prediction methods based on the Eurocode shear expression provide reasonable results (with coefficients of variation on the ratio tested/predicted shear capacities of 27–29%). None of the currently available methods properly describe the behavior of SFRC beams failing in shear. As such, this work shows the need for studies that address the different shear-carrying mechanisms in SFRC and its crack kinematics.

/pdf/database-of-shear-experiments-on-steel-fiber-reinforced-3mvv224ipt.pdf

Database of Shear Experiments on Steel Fiber Reinforced Concrete Beams without Stirrups

Understanding shear behavior is crucial for the design of reinforced concrete beams and sustainability in construction and civil engineering. Although numerous studies have been proposed, predicting such behavior still needs further improvement. This study proposes a soft-computing tool to predict the ultimate shear capacities (USCs) of concrete beams reinforced with steel fiber, one of the most important factors in structural design. Two hybrid machine learning (ML) algorithms were created that combine neural networks (NNs) with two distinct optimization techniques (i.e., the Real-Coded Genetic Algorithm (RCGA) and the Firefly Algorithm (FFA)): the NN-RCGA and the NN-FFA. A database of 463 experimental data was gathered from reliable literature for the development of the models. After the construction, validation, and selection of the best model based on common statistical criteria, a comparison with the empirical equations available in the literature was carried out. Further, a sensitivity analysis was conducted to evaluate the importance of 16 inputs and reveal the dependency of structural parameters on the USC. The results showed that the NN-RCGA (R = 0.9771) was better than the NN-FFA and other analytical models (R = 0.5274–0.9075). The sensitivity analysis results showed that web width, effective depth, and a clear depth ratio were the most important parameters in modeling the shear capacity of steel fiber-reinforced concrete beams.

Computational Hybrid Machine Learning Based Prediction of Shear Capacity for Steel Fiber Reinforced Concrete Beams

Replacement of existing unreinforced masonry (URM) walls, commonly used as a non-structural member in apartments, with new reinforced concrete (RC) components has been used as a reliable method when remodeling is carried out. However, special care needs to be taken when URM walls are removed not to waste construction time and materials. Therefore, retrofitting existing URM walls can be deemed a better solution rather than replacing URM walls with RC ones. Using shotcrete is one of retrofitting techniques of URM walls. However, using normal shotcrete cannot improve adequate ductility and may cause brittle failure at a wall frame or slab connection. Therefore, new materials, such as engineered cementitious composite (ECC) and ultra-high performance concrete (UHPC) have emerged to resolve the problem of normal shotcrete by increasing ductility and toughness of retrofitting materials. In this study, sprayed ECC was used to increase both strength and ductility of existing URM walls. The results of two retrofitted URM walls under lateral quasi-static loading were compared to non-retrofitted one. One strengthened wall, retrofitted masonry wall (RTM)-ECC, was just sprayed and anchored to a wall base. Another strengthened wall, RTM-ECC-WM, was the same as RTM-ECC except for addition of wire mesh. The retrofitted specimens showed significant increase of strength, ductility, and energy dissipation capacity in comparison with the control one. In addition, RTM-ECC-WM indicated higher strength degradation due to the load transferring effect of wire mesh than RTM-ECC.

Lateral Resistance of Unreinforced Masonry Walls Strengthened With Engineered Cementitious Composite

Experimental study on the cyclic behavior of steel fiber reinforced high strength concrete columns and evaluation of shear strength

High-strength concrete is widely used in construction field. The growth has been possible as a result of recent developments in material technology and a demand for high-strength concrete. High-strength concrete has different mechanical properties from normal-strength, as many researches mentioned about. However, the existing equations and procedures for prediction of ultra-high strength concrete are based on tests using normal-strength concrete, yet. In this study, experiments on ultra-high-strength steel fiber reinforced concrete beams with 2% volume fraction of steel fiber and 200MPa of compressive strength have been conducted. Test was conducted by two point loading with 2,000kN actuator for slender test specimen which have varied shear-span to depth ratio. Using test results with several assumptions, an empirical equation for flexural strength and shear strength of ultra-high-strength steel fiber reinforced concrete beams have been proposed.

Flexural and Shear Capacity Evaluation of Reinforced Ultra-high Strength Concrete Members with Steel Rebars

Evaluation of punching shear strength of voided slabs considering the effect of the ratio b0/d

In this research, flexural performance was evaluated using macro-synthetic fiber-reinforced concrete (MFRC) in structural deck plates. Material tests were performed to evaluate the mechanical properties of the MFRC, and the flexural strength evaluation was conducted in two experiments, positive and negative moment tests. In the material test results, compressive strength and modulus of elasticity of the MFRC were increased compared with normal concrete. Flexural tensile tests showed that, after achieving maximum strength, the deck plates had sufficient residual strength until fracture. Structural tests showed that flexural strength and cracking load of all specimens increased according to macro synthetic fiber dosage. According to the experimental results, we proposed a flexural strength model of a steel deck plate containing macro synthetic fiber. The model showed greater accuracy than the current standard compared with the experimental results. In addition, since it was confirmed that the MFRC steel decks had greater flexural stiffness until yielding, it will be necessary to quantitatively evaluate the effect of MFRC on the effective flexural stiffness of steel decking in future studies.

Baek Il Bae

Papers

Lateral Resistance of Unreinforced Masonry Walls Strengthened With Engineered Cementitious Composite

Experimental study on the cyclic behavior of steel fiber reinforced high strength concrete columns and evaluation of shear strength

Flexural and Shear Capacity Evaluation of Reinforced Ultra-high Strength Concrete Members with Steel Rebars

Evaluation of punching shear strength of voided slabs considering the effect of the ratio b0/d

Flexural Strength of Composite Deck Slab with Macro Synthetic Fiber Reinforced Concrete