Search Results (38)

This study proposes a novel deep learning framework for predicting the shear capacity of slender reinforced concrete (RC) beams without shear reinforcement. The proposed approach employs convolutional neural networks and autoencoders to transform structural data into image representations, reconstruct missing data, and predict shear capacity with high accuracy. Using a dataset of 964 experimental results covering a wide range of beam characteristics, the framework achieves remarkable predictive performance. The image-based methodology enables the model to capture spatial dependencies, while the autoencoder reconstructs incomplete data with a fidelity exceeding 95%. The framework is validated against conventional methods under different data masking levels (10%, 20%, 30%). For 10% masking, the proposed method achieves R² = 0.94, MAE = 0.05, and NSE = 0.93, significantly outperforming ACI 318 and Eurocode 2. Even with 30% masking, the framework maintains robust performance, with R² = 0.85 and NSE = 0.81. These results highlight the scalability and reliability of the model in handling incomplete datasets, as well as its potential to advance structural engineering practice by integrating machine learning techniques with traditional design methodologies. Full article

Openings are often introduced in continuous reinforced concrete (RC) deep beams to accommodate utility services, which can compromise their structural capacity. This paper presents a numerical investigation—via nonlinear finite element (FE) modeling—into the effects of post-construction rectangular openings in continuous high-strength concrete (HSC) deep beams. A previously tested two-span continuous HSC deep beam with rectangular openings was used for model validation and subsequently adopted in a parametric study, maintaining consistent beam and opening dimensions. The study focuses on the influence of opening location, both symmetric and asymmetric, at mid-depth within critical shear and flexural zones of the two-span continuous deep beam. Key parameters analyzed include load-carrying capacity, support reactions, initial and post-cracking stiffness, reinforcement stresses, and concrete stress distribution. Results indicate that mid-depth openings located in flexure-critical regions have minimal impact, causing only a 3–5% reduction in load-carrying capacity and negligible changes in stress behavior. However, when openings intersect the primary strut paths, reductions in capacity ranged from 17% to 53%, depending on the number and location of the openings (i.e., crossing external or internal struts). Furthermore, symmetric placement of openings was found to significantly mitigate performance degradation compared to asymmetric configurations. These findings provide design insights that enable safe incorporation of service openings without excessive material use, thereby promoting more sustainable and resource-efficient concrete construction. Full article

This study presents a strut-and-tie modeling (STM) framework for reinforced concrete (RC) deep beams strengthened with intraply hybrid composites (IRCs), integrating comprehensive experimental data from beams with three different span lengths (1.0 m, 1.5 m, and 2.0 m). Although the use of fiber-reinforced polymers (FRPs) for shear strengthening of RC members is well established, limited attention has been given to the development of STM formulations specifically adapted for hybrid composite systems. In this research, three distinct IRC configurations—Aramid–Carbon (AC), Glass–Aramid (GA), and Carbon–Glass (CG)—were applied as U-shaped jackets to RC beams without internal transverse reinforcement and tested under four-point bending. All experimental data were derived from the authors’ previous studies, ensuring methodological consistency and providing a robust empirical basis for model calibration. The proposed modified STM incorporates both the axial stiffness and effective strain capacity of IRCs into the tension tie formulation, while also accounting for the enhanced diagonal strut performance arising from composite confinement effects. Parametric evaluations were conducted to investigate the influence of the span-to-depth ratio (a/d), composite configuration, and failure mode on the internal force distribution and STM topology. Comparisons between the STM-predicted shear capacities and experimental results revealed excellent correlation, particularly for deep beams (a/d = 1.0), where IRCs substantially contributed to the shear transfer mechanism through active tensile engagement and confinement. To the best of the authors’ knowledge, this is the first study to formulate and validate a comprehensive STM specifically designed for RC deep beams strengthened with IRCs. The proposed approach provides a unified analytical framework for predicting shear strength and optimizing the design of composite-strengthened RC structures. Full article

Reinforced concrete (RC) deep beams constructed with low-strength concrete are susceptible to sudden splitting failures in the strut region due to shear–compression stresses. To mitigate this vulnerability, various strengthening techniques, including steel plates, fiber-reinforced polymer sheets, and cementitious composites, have been explored to confine the strut area. This study investigates the structural performance of RC deep beams with low-strength concrete, strengthened externally using an Engineered Cementitious Composite (ECC) layer. To ensure effective confinement and uniform shear distribution, shear reinforcement was provided at equal intervals with configurations of zero, one, and two vertical shear reinforcements. Four-point bending tests revealed that the ECC layer significantly enhanced the shear capacity, increasing load-carrying capacity by 51.6%, 54.7%, and 46.7% for beams with zero, one, and two shear reinforcements, respectively. Failure analysis through non-linear finite element modeling corroborated experimental observations, confirming shear–compression failure characterized by damage in the concrete struts. The strut-and-tie method, modified to incorporate the tensile strength of ECC and shear reinforcement actual stress values taken from the FE analysis, was used to predict the shear capacity. The predicted values were within 10% of the experimental results, underscoring the reliability of the analytical approach. Overall, this study demonstrates the effectiveness of ECC in improving shear performance and mitigating strut failure in RC deep beams made with low-strength concrete. Full article

Amidst the escalating demand for high-precision structural health monitoring in large-scale engineering applications, carbon fiber-reinforced polymer fiber Bragg grating (CFRP-FBG) sensors have emerged as a pivotal technology for fatigue life evaluation, owing to their exceptional sensitivity and intrinsic immunity to electromagnetic interference. A time-series predictive architecture based on long short-term memory (LSTM) networks is developed in this work to facilitate intelligent fatigue life assessment of structures subjected to complex cyclic loading by capturing and modeling critical spectral characteristics of CFRP-FBG sensors, specifically the side-mode suppression ratio and main-lobe peak-to-valley ratio. To enhance model robustness and generalization, Principal Component Analysis (PCA) was employed to isolate the most salient spectral features, followed by data preprocessing via normalization and model optimization through the integration of the Adam optimizer and Dropout regularization strategy. Relative to conventional Backpropagation (BP) neural networks, the LSTM model demonstrated a substantial improvement in predicting the side-mode suppression ratio, achieving a 61.62% reduction in mean squared error (MSE) and a 34.99% decrease in root mean squared error (RMSE), thereby markedly enhancing robustness to outliers and ensuring greater overall prediction stability. In predicting the peak-to-valley ratio, the model attained a notable 24.9% decrease in mean absolute error (MAE) and a 21.2% reduction in root mean squared error (RMSE), thereby substantially curtailing localized inaccuracies. The forecasted confidence intervals were correspondingly narrower and exhibited diminished fluctuation, highlighting the LSTM architecture’s enhanced proficiency in capturing nonlinear dynamics and modeling temporal dependencies. The proposed method manifests considerable practical engineering relevance and delivers resilient intelligent assistance for the seamless implementation of CFRP-FBG sensor technology in structural health monitoring and fatigue life prognostics. Full article

Fiber-reinforced polymer (FRP) bars have great potential to replace steel bars in the design of reinforced concrete (RC) beams since they have numerous advantages such as high tensile strength and good corrosion resistance. Therefore, many studies including experiments and numerical simulations have focused on the behavior of FRP RC beams. In this paper, a comprehensive overview of previous studies is conducted to provide a thorough understanding about the behavior, the design, and the limitations of FRP RC beams. Particularly, experimental studies on FRP RC beams are collected and reviewed. In addition, the numerical analysis of FRP beams including the finite element (FE) analysis, the discrete element (DE) analysis, and artificial intelligence/machine learning (AI/ML) is summarized. Moreover, the international standards for the design of FRP RC beams are presented and evaluated. Through the review of previous studies, 93 tested specimens are collected. They can be a great source of reference for other studies. In addition, it has been found that the studies on the continuous beams and deep beams reinforced with FRP bars are still limited. In addition, more studies using DE analysis and AI/ML to analyze the response of FRP RC beams under loading conditions should be conducted. Full article

Access to significant amounts of data is typically required to develop structural health monitoring (SHM) systems. In this study, a novel SHM approach was evaluated, with all training data collected solely from a validated finite element analysis (FEA) of a reinforced concrete (RC) beam and the structural health based on the tension side of a rebar under flexural loading. The developed SHM system was verified by four-point bending experiments on three RC beams cast in the dimensions of 4000 mm × 200 mm × 400 mm. Distributed optical fibre sensors (DOFS) were mounted on the concrete surface and on the bottom rebar to maximise sample points and investigate the reliability of the strain data. The FEA model was validated using a single beam and subsequently used to generate labelled SHM strain data by altering the dilation angle and rebar sizes. The generated strain data were then used to train an artificial neural network (ANN) classifier using deep learning (DL). Training and validation accuracy greater than 98.75% were recorded, and the model was trained to predict the tension state up to 90% of the steel yield limit. The developed model predicts the health condition with the input of strain data acquired from the concrete surface of reinforced concrete beams under various loading regimes. The model predictions were accurate for the experimental DOFS data acquired from the tested beams. Full article

Aluminium alloy (AA) bars have emerged in structural engineering applications mainly to reduce deterioration caused by corrosion. However, research on AA-reinforced concrete (RC) beams has been limited, despite RC beams reinforced with AA bars providing a study area with great potential. Therefore, this study mainly aims to investigate the behaviour of AA RC deep beams. The investigated parameters include concrete strength, tension reinforcement ratio, beam size, a/d ratio, and transverse reinforcement ratio, most of which have not yet been thoroughly studied. A finite element (FE) model was developed to obtain accurate predictions. The developed FE model predicted the actual load-bearing capacity with a mean value of 1.00. The findings indicated a clear trend in which shear force capacity increased from 124.1 to 181.4 kN with increasing concrete compressive strength from 20 to 40 MPa. A strong relationship between the reinforcement ratio and failure mode was obtained. The shear strength decreased from 2.95 to 2.1 MPa as the effective depth increased from 175 to 350 mm. An increase in transverse reinforcement ratio instigated an enhancement in shear force capacity. Finally, the applicability of the design models in the current literature was evaluated. The design formulations gave accurate predictions with an error of 3%. Full article

Using artificial neural networks (ANN), numerous models were developed for predicting the ultimate shear strength of reinforced concrete deep beams. Many experimental result databases from earlier research were carefully gathered for this study. Two hundred fifty-three findings from experiments were included in this database. The ultimate shear strength was the output parameter, while ten factors were determined as input parameters for the ANN model based on the completed literature research. The required model was constructed using a back propagation neural network. The model of the neural networks was determined using the trial-and-error method. It was discovered that, inside the range of the input boundaries considered, the ANN model could accurately estimate the ultimate shear strength of deep beams. The measured shear strength and the shear strength predicted by the ANN model have a high correlation coefficient of 0.97, indicating a strong relationship between the predicted and actual values. The results show that, given the range of input parameters, ANN offers an excellent agreement of interest as a practical technique for estimating the ultimate shear strength. A parametric investigation was performed using the trained neural network model to assess how the input parameters affected the shear strength capacity of deep beams. Full article

This study evaluates the performance of lightweight aggregate deep beams strengthened with low-cost glass fiber-reinforced polymer composite (Lo-G) wraps as an alternative to expensive synthetic fiber-reinforced polymers (FRPs). The investigation includes side-bonded and fully wrapped configurations of Lo-G wraps, alongside carbon FRP (CFRP) strips for comparison. The experimental results show that epoxy-based anchors provided significantly better resistance against de-bonding than mechanical anchors, improving beam performance. Strengthening with Lo-G wraps resulted in a peak capacity increase of 17.0% to 46.9% for side-bonded beams in Group 2, 10.5% to 41.4% for fully wrapped beams in the strip configuration in Group 3, and 15.4% to 42.7% for CFRP strips in Group 4. The ultimate deflection and dissipated energy were also improved, with dissipated energy increases of up to 264.6%, 322.3%, and 222.7% for side-bonded and fully wrapped Lo-G wraps and CFRP strips, respectively. The side-bonded configuration with two or three Lo-G wraps, supplemented by epoxy wraps, outperformed fully wrapped 250 mm strips in peak capacity, with peak capacity improvements of up to 46.9%. However, beams with mechanical anchors showed poor performance due to premature debonding. They rely on friction and expansion within the concrete to resist pull-out forces. If the surrounding concrete is not strong enough or if the anchor is not properly installed, it can lead to failure. Additionally, reducing strip spacing negatively impacted performance. Lo-G wraps showed an 8.5% higher peak capacity and 32.8% greater dissipated energy compared to CFRP strips. Despite these improvements, while Lo-G wraps are a cost-effective alternative, their long-term performance remains to be investigated. None of the existing models accurately predicted the shear strength contribution of Lo-G wraps, as the lower elastic modulus and tensile strength led to high deviations in prediction-to-experimental ratios, underscoring the need for new models to assess shear strength. Full article

The correlation analysis between current surface cracks of structures and external loads can provide important insights into determining the structural residual bearing capacity. The classical regression assessment method based on experimental data not only relies on costly structure experiments; it also lacks interpretability. Therefore, a novel load estimation method for RC beams, based on correlation analysis between detected crack images and strain contour plots calculated by FEM, is proposed. The distinct discrepancies between crack images and strain contour figures, coupled with the stochastic nature of actual crack distributions, pose considerable challenges for load estimation tasks. Therefore, a new correlation index model is initially introduced to quantify the correlation between the two types of images in the proposed method. Subsequently, a deep neural network (DNN) is trained as a FEM surrogate model to quickly predict the structural strain response by considering material uncertainties. Ultimately, the range of the optimal load level and its confidence interval are determined via statistical analysis of the load estimations under different random fields. The validation results of RC beams under four-point bending loads show that the proposed algorithm can quickly estimate load levels based on numerical simulation results, and the mean absolute percentage error (MAPE) for load estimation based solely on a single measured structural crack image is 20.68%. Full article

In this study, the effectiveness was investigated of shear strengthening techniques in reinforced concrete (RC) deep beams incorporating stainless steel plates (SSPs). Four RC deep beams were tested under incremental static loading until failure to examine the proposed strengthening techniques. The key parameters considered in this study included the arrangement of the externally bonded SSPs. The experimental findings demonstrated that strengthening using SSPs led to substantial improvements in their performance compared to the unstrengthened control beam. The use of SSPs increased the ultimate shear capacity by 129 to 175% over the control specimen. Finite element models (FEMs) were developed to simulate the responses of the tested beams strengthened using SSPs. Parametric studies were then conducted using the validated FEM to investigate to identify the effects of the area of SSPs on the shear capacity of the beams. The parametric studies concluded that increasing the plate thickness resulted in the enhanced shear capacity of the deep beam specimens up to a critical point upon which the increases in the thickness have insignificant effects on the shear strength. The accuracy of the design equations given by European and American codes in predicting the shear strength of the deep beams is examined. Full article

Artificial intelligence (AI) has enabled several optimization techniques for structural design, including machine learning, evolutionary algorithms, as in the case of genetic algorithms, reinforced learning, deep learning, etc. Although the use of AI for weight optimization in steel and concrete buildings has been extensively studied in recent decades, multi-objective optimization for reinforced concrete (RC) and steel buildings remains challenging due to the difficulty in establishing independent objective functions and obtaining Pareto fronts. The well-known Non-Dominated Sorting Genetic Algorithm II (NSGA-II) is an efficient genetic algorithm approach for multi-objective optimization. In this work, the NSGA-II approach is considered for the multi-objective structural optimization of three-dimensional RC buildings subjected to earthquakes. For the objective of this study, two function objectives are considered: minimizing total cost and the probability of structural failure, which are obtained via several nonlinear seismic analyses of the RC buildings. Beams and columns’ cross-sectional dimensions are selected as design variables, and the Mexican Building Code (MBC) specifications are imposed as design constraints. Pareto fronts are obtained for two RC-framed buildings located in Mexico City (soft soil sites), which demonstrate the efficiency and accuracy of NSGA-II for structural optimization. Full article

Reinforced Concrete (RC) members in existing RC structures are susceptible to shear-critical due to their under-reinforced design. Thus, implementing a retrofitting technique is essential to eliminate the casualties that could arise from sudden and catastrophic collapses due to these members’ brittleness. Among other proposed techniques, using Carbon-Fiber Reinforced Polymers (C-FRP) ropes to increase the shear strength of RC structural elements has proved to be a promising reinforcement application. Moreover, an Electro-Mechanical Impedance (EMI-based) method using Lead Zirconate Titanate (PZT-enabled) was employed to assess the efficiency of the strengthening scheme. Initially, the proposed technique was applied to C-FRP rope under the subjection of pullout testing. Thus, a correlation of the rope’s tensile strength with the EMI responses of the PZT patch was achieved using the Root Mean Square Deviation (RMSD) metric index. Thereafter, the method was implemented to the experimentally acquired data of C-FRP ropes, used as shear reinforcement in a rectangular deep beam. The ropes were installed using the Embedded Through Section (ETS) scheme. Furthermore, an approach to evaluate the residual shear-bearing capacity based on the EMI responses acquired by being embedded in and bonded to the ropes’ PZTs was attempted, demonstrating promising results and good precision compared to the analytical prediction of the C-FRP ropes’ shear resistance contribution. Full article

To ensure the safety of buildings, accurate and robust prediction of a reinforced concrete deep beam’s shear capacity is necessary to avoid unpredictable accidents caused by brittle failure. However, the failure mechanism of reinforced concrete deep beams is very complicated, has not been fully elucidated, and cannot be accurately described by simple equations. To solve this issue, machine learning techniques have been utilized and corresponding prediction models have been developed. Nevertheless, these models can only provide deterministic prediction results of the scalar type, and the confidence level is uncertain. Thus, these prediction results cannot be used for the design and assessment of deep beams. Therefore, in this paper, a probabilistic prediction approach of the shear strength of reinforced concrete deep beams is proposed based on the natural gradient boosting algorithm trained on a collected database. A database of 267 deep beam experiments was utilized, with 14 key parameters identified as the inputs related to the beam geometry, material properties, and reinforcement details. The proposed NGBoost model was compared to empirical formulas from design codes and other machine learning methods. The results showed that the NGBoost model achieved higher accuracy in mean shear strength prediction, with an R² of 0.9045 and an RMSE of 38.8 kN, outperforming existing formulas by over 50%. Additionally, the NGBoost model provided probabilistic predictions of shear strength as probability density functions, enabling reliable confidence intervals. This demonstrated the capability of the data-driven NGBoost approach for robust shear strength evaluation of RC deep beams. Overall, the results illustrated that the proposed probabilistic prediction approach dramatically surpassed the current formulas adopted in design codes and machine learning models in both prediction accuracy and robustness. Full article