Fiber Reinforced Polymer Bars Research Articles

Flexural performance of UHPC two-way slab reinforced with FRP bars

The flexural behaviors of ultra-high-performance concrete (UHPC) two-way square slabs reinforced with fiber-reinforced polymer (FRP) bars were studied experimentally. Flexural tests were conducted on eight specimens, varying in reinforcement type, reinforcement ratio and confinement condition in compressive zone. Test results showed that the bridging effects of steel fibers in UHPC can mitigate the brittle characteristics of slab experiencing punching shear failure. The failure modes of slabs shifted from tensile failure to compressive failure by increasing the tensile strength of bar, leading to an improvement on the flexural capacity and ductility. The ultimate capacity of the slab with a reinforcement ratio of 1.06 % was 15.8 % greater than that of the slab with a reinforcement ratio of 0.67 %. By incorporating a layer of basalt fiber-reinforced polymer (BFRP) grid in the compressive zone to confine UHPC, the bearing capacity and ductility index of the slab increased by 17.8 % and 56.7 %, respectively. Introducing an enhancement coefficient to account for the confinement effect induced by the BFRP grid, a method was developed for predicting the flexural capacity of FRP reinforced UHPC two-way slab subjected to a local load at the mid-span, and its prediction accuracy was well verified.

A New Practical Equation for the Shear Capacity of FRP-RC Slender Beams Assessment via Gene Expression Programming

Due to their advantageous mechanical and physical characteristics, fiber-reinforced polymer (FRP) bars have been used extensively in various structural elements in recent years. Numerous researchers examined the structural behaviour of such elements reinforced with FRP bars to forecast their capacity. Despite a large number of existing code provisions and proposed procedures based on the heuristic methods, a practical yet accurate equation for utilisation by the engineers who are dealing with structural retrofitting and analyzing is not available. Here, a gene expression programming (GEP) based simple algorithm is used in conjunction with an extensive database containing 481 stirrup-free experimental samples that were gathered from tests conducted in the lab. Next, using data from an additional programme, the GEP output is examined in order to produce a workable formula for determining the shear capacity of these members. Lastly, a comparison is done using the current equations. The outcomes show that, in comparison to the current ones, the suggested GEP equation along with the CSA S806-12 code provision yields more accurate values.

A New Avrami-Based Exponential Model for Predicting Fiber-Reinforced Polymer Bar Service Life: A Comparison with Existing Models Using a Large Database

The fiber-reinforced polymers (FRP) bar is a promising solution to problems caused by steel rebar corrosion in concrete. To assess the service life of the FRP bar based on accelerated test results, it is crucial to have a reliable model. Here, a modified exponential (MEP) model is proposed based on the Avrami equation. The Avrami equation provides a theoretical foundation for the empirical exponential (EP) model and does not a priori fix the power of the exposure time to one. A database containing 903 data points from 74 groups of test specimens is assembled to compare the reliability of the MEP model vis-a-vis the EP, single logarithmic, double logarithmic, and power function models. The combination of Root Mean Square Error (RMSE), the Mean Absolute Error (MAE), and the coefficient of determination (R2) criteria is proposed for assessing model reliability. It is shown that in certain cases the combined criteria, versus R2 alone, significantly increase the number of test groups meeting the acceptable performance limit. Observed test data aberrations are found to have minor influence on the results of the EP model, but they significantly influence the results of the other four models. The EP model generally predicts the lowest activation energy and the smallest strength retention for similar groups of bars, while the predicted values of the other four models exhibit a relatively small difference. The difference between the predicted strength retention values of the EP and MEP models shows an increasing trend with the increase of the absolute value of (1 − n), where n is the power of the exposure time in the MEP model.

Preliminary Study on the Bending Behavior of Solid Timber Beams Reinforced with Basalt Fiber-Reinforced Polymer Bars

The purpose of this work is to test the effectiveness of strengthening timber structures by means of composite bars. This article presents the results of preliminary tests carried out on solid beams made of fir wood. The test specimens, which are classified as strength class C24, had dimensions of 7 × 17 × 330 cm. Beams were reinforced with 8 mm diameter basalt fiber-reinforced polymer (BFRP) bars. The bars were glued into grooved channels along the bottom surface. Epoxy resin was used as an adhesive. The strength tests were conducted in accordance with the requirements of EN 408+A1:2012. The four-point bending scheme was adopted. The tests were conducted in the following two series: unreinforced beams (A) and beams reinforced with composites (B). Five elements were tested in each series. The reinforcement resulted in an average increase in the bending moment value of 8.41%. The deflection value at failure increased by 19.77%. The work also includes an analysis of the failure mode and a ductility analysis. Further tests should be carried out using a higher reinforcement ratio. A higher reinforcement ratio should make the presented reinforcement configuration more effective.

Thin-layer Ultra-High-Strength Engineered Cementitious Composites (UHS-ECC) reinforced with small-diameter FRP bars for structural strengthening

This study proposed a novel strengthening system for reinforced concrete (RC) structures using a thin layer of Ultra-High-Strength Engineered Cementitious Composites (UHS-ECC) reinforced with small-diameter Fiber-Reinforced Polymer (FRP) bars. Experimental investigation, digital image correlation analysis, and numerical simulation were conducted to evaluate the flexural performance and failure mechanism of RC beams strengthened with 20-mm UHS-ECC layers and 3-mm FRP bars. It was found that the 20-mm UHS-ECC layer alone improved the load capacity of RC beams by 8.3 %, though with reduced deflection, whereas incorporating two 3-mm FRP bars increased load capacity by up to 40.4 %, without sacrificing deflection. Failure in all specimens was caused by concrete crushing; however, FRP-reinforced UHS-ECC layers mitigated early crack localization, significantly enhancing both strength and ductility. This study also revealed that cast-in-place FRP-reinforced UHS-ECC layers exhibited higher load capacity and could avoid ECC/concrete interfacial cracks compared to epoxy-bonded prefabricated layers. A three-dimensional finite element model was proposed for the strengthening system, and the flexural behavior was successfully predicted. It is revealed that the FRP-to-UHS-ECC bond had a marginal influence on performance, while the bond at the UHS-ECC-to-concrete interface significantly impacted flexural behavior. Remarkably, the small-diameter FRP bar achieved 75 % of its tensile strength at the ultimate stage. These findings underscore the potential of FRP-reinforced UHS-ECC layers as an effective solution for enhancing the mechanical and durability performance of RC structures.

Ductility assessment of GFRP reinforced concrete beams with a wedge-based mechanical model accounting for discrete fibers and confinement

Glass fiber-reinforced polymer (GFRP) bars for internal reinforcement for concrete have gained attention due to their non-corrosive properties, high resistance, and electromagnetic transparency. On the other hand, the brittle behavior and low modulus of elasticity of FRP bars limit their application and diffusion in the civil construction market. From this perspective, this work investigates the influence of three components on the increase of ductility of GFRP beams: i) discrete alkali-resistant glass fibers added to the concrete; ii) confinement of the concrete with GFRP stirrups; and iii) use of longitudinal reinforcement on the compression zone. An experimental program including four over-reinforced beams with different reinforcement configurations was conducted. The beams were tested in four-point bending configuration and the use of fibers, stirrups and compression reinforcement contributed to substantially increasing the beam ductility index. Finally, a concrete wedge model was developed to obtain equivalent stress-strain relationships for the concrete in compression. The model was successfully validated against experiments and proved to be a useful tool for rationally evaluating GFRP RC beams’ ductility.

Machine learning prediction method for the interface bond strength between fiber reinforced polymer bars and concrete based on multi-feature driven analysis

In severe service conditions, corrosion of reinforcement poses a significant challenge for concrete structures. Fiber reinforced polymer (FRP) materials, characterized by their low weight, high strength, and superior corrosion resistance, are effective in enhancing the durability of these structures. The interfacial bond performance between FRP bars and concrete is crucial for their synergistic action and is pivotal for the design and safety evaluation of FRP-reinforced concrete structures. This paper conducts a comprehensive analysis of factors including the material and mechanical properties of FRP bars, concrete mechanical properties, and bond length. Utilizing an exhaustive search strategy, it identifies the optimal characteristic parameters for assessing the bond strength between FRP bars and concrete. Subsequently, these parameters are integrated with four machine learning (ML) algorithms—DT, SVM, RF and XGB—to train the nonlinear mapping relationship between influencing factors and bond strength, proposing a unified and interpretable prediction method for the FRP bar-concrete interface bond strength. The model's predictive accuracy is then validated using a test dataset, and a comparative analysis is performed among the predictive models generated by the four ML algorithms, as well as against empirical calculation formulas. The findings indicate that the ML models offer superior predictive performance and accuracy over empirical formulas, with the XGB algorithm demonstrating the highest overall accuracy and best performance. Moreover, to address the black-box nature of ML algorithms, the SHAP method is employed to enhance the interpretability of the bond strength prediction process. The newly developed hybrid ML model holds promise as a novel approach for accurately assessing the bond strength at the FRP bar-concrete interface.

Natural language processing‐based deep transfer learning model across diverse tabular datasets for bond strength prediction of composite bars in concrete

AbstractAs conventional machine learning models often struggle with scarcity and structural variation of training data, this paper proposes a novel regression transfer learning framework called transferable tabular regressor (TransTabRegressor) to address this challenge. The TransTabRegressor integrates natural language processing (NLP) for feature encoding, transformer for enhanced feature representation, and deep learning (DL) for robust modeling, facilitating effective transfer learning across tabular datasets using reducing input parameters. By leveraging the NLP data processor, the framework embeds both parameter names and values, enabling it to recognize and adapt to different expressions of similar parameters. For instance, the bond strength of fiber‐reinforced polymer (FRP) bars embedded in ultra‐high‐performance concrete (UHPC) is critical for ensuring the integrity of FRP‐UHPC structures. While pullout tests are widely adopted for their simplicity to generate substantial data, beam tests provide a closer approximation to actual stress conditions but are more complex thus resulting in limited data size. As a verification, the framework is applied to predict the bond strength of FRP bars embedded in UHPC using limited beam test data. A pre‐trained model is first established using 479 pieces of pullout test data. Subsequently, two transfer learning models are developed by fine‐tuning on 115 pieces of beam test data, where 66 correspond to concrete splitting failure and 49 correspond to pullout failure. For comparative analysis, XGBoost and neural network models are directly trained on the beam test data. Evaluation results demonstrate that the transfer learning models achieve significantly improved prediction accuracy and generalization capability. This study significantly highlights the effectiveness of the proposed TransTabRegressor in handling data scarcity and variability in input parameters across various engineering applications.

Durability of Fiber-Reinforced Polymer (FRP) Bars: Progress, Innovations and Challenges Based on Bibliometric Analysis

This review systematically examines the literature on the Fiber-Reinforced Polymer (FRP) bars durability in concrete matrices using bibliometric analysis to understand progress, innovations, and challenges. The objective is to explore the durability of FRP bars, which are recognized for their strength-to-weight ratio, corrosion resistance, and non-conductivity, as a potential substitute to conventional steel reinforcement. Methods involved employing bibliometric tools such as Biblioshiny and VOSviewer to analyze trends, collaboration patterns, and the global distribution of publications. Findings reveal an increase in research activity over the past two decades, significant international collaboration, and leading contributions from key countries. Critical environmental factors like alkalinity, thermal conditions, and chemical aggressors affecting the interface of fiber-matrix mechanical properties were highlighted. Advances in predictive modeling for long-term behavior conditioned FRP bars are studied, steering future research towards improved durability and sustainable construction practices. This study contributes novelty by providing a comprehensive bibliometric perspective on FRP bar durability, identifying emerging trends, and suggesting areas for future suggested research to enhance the reliability and application of FRP bars in construction. Doi: 10.28991/CEJ-SP2024-010-09 Full Text: PDF

Numerical investigation on plastic hinge behavior of hybrid steel-FRP reinforced concrete columns

This paper presents a numerical study on the plastic hinge behavior and rotation capacity of concrete columns reinforced with a combination of steel bars and fiber-reinforced polymer (FRP) bars. A meso-scale numerical model, which considers the internal heterogeneity of concrete and bond behavior between concrete and longitudinal reinforcements, was developed and validated. The failure modes, lateral load-displacement responses, and the physical plastic hinge lengths of hybrid steel-FRP reinforced concrete (SFRC) columns were investigated and compared with those of conventional steel-reinforced concrete columns. The results indicated that the steel yielding zone and curvature localization zone of SFRC columns with FRP longitudinal bars were enlarged, due to the relatively low modulus of FRP bars. After that, a parametric analysis was performed to study the plastic hinge length of SFRC columns with respect to the nominal area ratio of FRP longitudinal bars, shear span-to-depth ratio, axial load ratio, and longitudinal reinforcement ratio. A new empirical model was proposed to predict the equivalent plastic hinge length, which was subsequently integrated into an analytical method for predicting the ultimate rotation. The comparison of predictions with simulation and test results demonstrated the accuracy of both the proposed empirical model and analytical method.

Effect of CFRP strip tie configurations on the behavior of GFRP reinforced concrete columns under different loading conditions

This study presents the results of an experimental program on the behavior of concrete specimens reinforced longitudinally with glass fiber-reinforced polymer (GFRP) bars and transversely with square, square-square, and square-circular (S, SS, and SC) configurations of carbon fiber-reinforced polymer strip (CS) ties under different loading conditions. Nine specimens were tested as columns under concentric and eccentric axial loads and three specimens were tested as beams under four-point bending. The experimental results demonstrated that specimens reinforced with the SC configuration of CS ties exhibited superior load-carrying capacity and deformability compared to specimens reinforced with the S or SS configurations when subjected to concentric and eccentric axial loads. Also, the contribution of GFRP bars in the maximum axial load sustained by specimens under concentric axial load is higher for specimens reinforced with SC configuration of CS ties than for specimens reinforced with S and SS configurations of the CS ties.

Reliability analysis and calibration for flexural design provisions of GFRP-RC beams

This study aims to conduct reliability assessment and calibration of the design provisions for flexural capacity in existing design codes for glass fiber reinforced polymer bar reinforced concrete (GFRP-RC) beams. Firstly, model uncertainties for three design codes including GB 50608-2020, ACI 440.1R-15 and CSA S806-12 were evaluated using the statistical analysis methods. Subsequently, the reliability analysis of flexural capacity in three design codes was investigated based on Monte Carlo Simulation (MCS) method, considering stochastic factors such as material properties, geometric parameters, model uncertainties and load effect combinations. Moreover, the influences of tensile strength of GFRP bar, the ratio of reinforcement ratio to balanced reinforcement ratio (ρf/ρfb) and the live-to-dead load effect ratio (θ) on reliability index were explored. Meanwhile, the calibration of GFRP material partial factor (γf) for GB code was performed with the target reliability index of 3.7, based on the least squares analysis. Finally, the flexural capacity provisions of GFRP-RC beams in the GB code was revised for improving the reliability index under a relatively low live-to-dead load effect ratio θ by re-calibrating parameter γf for GFRP bar tensile failure and introducing revision coefficient ξ for concrete compressive failure, achieving target reliability index over 3.7.

An innovative strategy for improving ductility of seawater sea-sand engineered cementitious composites beam reinforced with GFRP bar

Seawater sea-sand engineered cementitious composites (SS-ECC) members with glass fiber reinforced polymer (GFRP) bars have inferior ductility due to the brittle nature of GFRP bars. In the current research, an enlarged head anchorage system (EHAS) was recommended to improve the ductility of GFRP bars reinforced SS-ECC beams. To explore the bond characteristics between SS-ECC and GFRP bars with EHAS, a total of 39 specimens were tested by pull-out loading. The influences of enlarged head shape, stirrup spacing and SS-ECC’s strength grade on the bond characteristics were experimentally investigated. GFRP longitudinal bars in specimens with EHAS presented rupture failure rather than anchorage failure. EHAS could effectively realize the slip hardening of GFRP bars in low strength SS-ECC, and ensure the reliable bond of GFRP bars in high strength SS-ECC. Additionally, the failure mechanism of specimens under pull-out loading was explored by finite element analysis (FEA). The pull-out resistance was mainly provided by EHAS in force transition stage and slip hardening stage. The influences of fiber reinforced polymer (FRP) bar type on the bond performance were investigated by FEA. EHAS could realize the slip-hardening behaviors of aramid, basalt and carbon FRP bars in normal strength SS-ECC. More importantly, to verify the effectiveness of the proposed ductility enhancement strategy, SS-ECC beams reinforced with GFRP bars were tested by four-point bending. These beams with different enlarged head shapes possessed excellent ductility and strong ultimate deformation capacity. It was recommended that low strength SS-ECC and GFRP bars with EHAS were jointly utilized to enhance the ductile performance of the beams.

The impact of using prestressed CFRP bars on the development of flexural strength

Abstract The load-carrying capacity and ductility of conventional steel reinforcement may be greatly increased by using ordinary and prestressed carbon fiber-reinforced polymer (CFRP) bars, resulting in reinforced concrete structures with greater sturdiness. This research investigates the flexural behavior of CFRP-prestressed beams with bonded tendons as opposed to conventional steel-prestressed beams. This article examines a less explored topic that often fails because post-tensioned beams with unbonded CFRP tendons are crushed by concrete. The linear-elastic behavior of CFRP accounts for much of the experimentally observed considerable variations in flexural characteristics between CFRP and steel-prestressed beams. Compared to unbonded CFRP specimens, bonded CFRP specimens are much stronger. Our knowledge of CFRP reinforcement in concrete infrastructure is advanced by this work, which highlights the need for better design techniques to increase strength and ductility. It is recommended that CFRP bars be bonded with epoxy resin to restrict fast energy dissipation and avoid concrete failure. As a result, CFRP-reinforced concrete beams will react less linearly and more ductilely. CFRP may improve prestressed concrete beam performance and lifespan in a number of scenarios, as shown by comparative research with traditional steel reinforcement. Six 1,800–mm-long RC beams with a 200 × 300 mm cross-section were examined and divided into three groups, analyzing important loading phases (i.e., cracked, ultimate, and mid-span deflection) using CFRP bars as prestressed tendons to replace the bottom steel rebars. The load-carrying capabilities and ductility of CFRP-reinforced beams were much greater than those of the reference beam. A single beam using normal CFRP bars for reinforcement showed a 21.2 mm mid-span deflection and an ultimate load of 157.2 kN, with a 57.7-kN fractured load. Another beam with normal CFRP bars also showed enhanced performance, with a mid-span deflection of 21.2 mm, an ultimate load of 160.6 kN, and a cracking load of 57.5 kN.

Evaluation of glass fiber-reinforced polymer bars for application in sections of reinforced concrete

In order to evaluate the effectiveness and acceptability of glass fiber reinforced polymer (GFRP) bars as a substitute for conventional steel reinforcement, this study looks into their use in reinforced concrete sections. To assess the mechanical qualities of GFRP bars, the research includes mix design, casting, and extensive testing, such as flexural and tensile tests. Furthermore, a comprehensive study of GFRP-integrated reinforced concrete building sections is carried out, looking at factors like primary stresses, bending stresses, shear stresses, and deflection. Additionally, using ANSYS software, a comparative study of beam-column junctions using GFRP and RCC sections is conducted to evaluate structural performance under various loading circumstances. The results demonstrate how GFRP bars can improve building projects' structural integrity, toughness, and sustainability

Tension stiffening and cracking behaviors in glass fiber reinforced polymer bar enhanced precast recycled aggregate concrete specimen

Glass fiber reinforced polymer (GFRP) bar-enhanced precast recycled aggregate concrete (PRAC) elements combine PRAC’s environmental benefits with GFRP’s corrosion resistance, making them ideal for coastal urban infrastructure. However, in-depth research on the tensile stiffness and cracking behaviors of this composite is lacking. The significant mechanical differences between GFRP bars (low modulus, high strength) and PRAC, as compared to traditional materials, raise safety concerns for widespread use. This study investigates the short-term load capacity, deformation and cracking characteristics of GFRP bar-reinforced PRAC tensile specimens through tests and analyses. The tests examine how variables like water-to-binder ratio, coarse aggregate type, recycled aggregate (RA) content and mixing methods affect the specimens' mechanical responses. Theoretical analyses, using existing equations and a partial interaction model, clarify stress-strain relationships and crack propagation under applied loads, revealing: (a) As RA content increases, PRAC shows a moderate decrease in workability and mechanical performance. The strength variability in PRAC generally falls between that of natural aggregate concrete (NAC) and conventional recycled aggregate concrete (CRAC) using RAs from construction and demolition waste, being closer to NAC. Additionally, the strength conversion relation seen in NAC applies similarly to PRAC. (b) During tension at both ends of the specimen, PRAC's resistance decreases by 24.3 % compared to NAC but is still 20.3 % higher than CRAC. (c) The number of cracks in the PRAC specimen decreases with higher RA content and basalt fibers, while the ratio of stabilized load to cracking load increases. (d) The CEB-FIP standard offers more accurate predictions of the specimen’s composite stress-strain relation, while the Chinese code excels in predicting crack width. The partial interaction model effectively predicts the specimen’s load, deformation and crack characteristics by accounting for the behaviors and bonding of both PRAC and GFRP bars.

Shear capacity of slender FRP-RC beams utilizing a hybrid ANN with the firefly optimizer

The popularity of fiber-reinforced polymer (FRP) bars as a structural element has soared due to their advantageous mechanical and physical properties. Despite an abundance of code requirements and heuristic equations, engineers specializing in structural retrofitting and analysis often struggle to utilize a suitable yet precise equation. This study introduces a novel approach by presenting a firefly optimization algorithm (FOA) combined with an artificial neural network (ANN)—termed as FOA-ANN—as an advanced hybrid machine learning model. The primary objective is to predict the shear capacity of slender FRP reinforced concrete (FRP-RC) beams without stirrup. An extensive experimental database of slender FRP-RC beams without stirrup was compiled. Leveraging this database and the proposed hybrid method, a simple yet accurate closed-form equation for determining the shear capacity of slender FRP-RC beams without stirrup was formulated. Additionally, a selection of pre-existing equations was provided for comparison of accuracy. Results indicate that the suggested FOA-ANN equation offers a more accurate alternative, outperforming equations derived from CSA S806-12 and AASHTO LRFD. The FOA-ANN hybrid technique proves to be highly effective in predicting the shear capacity of slender FRP-RC beams without stirrup.

Evaluation of the long-term performance and durability of basalt fiber reinforced polymer bars in concrete structures

To simulate the internal corrosion process of basalt fiber reinforced polymer (BFRP) bars in an alkaline environment of concrete, a diffusion based model was employed and modified in this study according to Fickian diffusion and diffusion coefficients at 25 ℃, 40 ℃, and 55 ℃ obtained from existing studies. Thus, the long-term corrosion medium concentration diagram, degraded depth, and strength retention of BFRP bars in the concrete environment at any ambient temperature can be predicted. Durability tests of BFRP bars in an alkaline solution at 60 ℃ were conducted to verify that the diffusion based model’s predictions were accurate. Moreover, long-term bonding tests between BFRP bars and concrete were conducted. The results indicate that the predicted results of the degraded depth and strength degradation of BFRP bars corresponded well to the experimental data. Morphology analysis by scanning electron microscopy (SEM) indicates that the alkaline solution intrusion caused the resin matrix to deteriorate, the fibers and the resin to debond, and the reaction between OH- and SiO2 in the fibers to occur, which in turn caused the tensile and bonding strengths of FRP bars to degrade. Moreover, after 63 days of corrosion at 55 ℃, the degraded depth exceeded 7 times that of 25 ℃ and 2 times that of 40 ℃, which implies that the ambient temperature had an obvious influence on the deterioration of BFRPs. The degradation rate was extremely slow at room temperature and rapidly accelerated with the rise in temperature.

Enhancing the Flexural Capacity of Deteriorated Low-Strength Prestressed Concrete Beam Using Near-Surface Mounted Post-Tensioned Carbon Fiber-Reinforced Polymer Bar

This study aimed to address the critical issue of age deterioration in prestressed concrete (PSC) structures by investigating the strengthening of aged PSC structures using a near-surface mounted (NSM) post-tensioned carbon fiber-reinforced polymer (CFRP). A total of nine PSC beams, each with a length of 6.5 m, were fabricated for a four-point bending test. Various experimental parameters were taken into account, including the strengthening method, compressive strength of concrete in the PSC beam, and the prestressing force of the PSC beam. The results indicated that the NSM post-tensioned CFRP strengthening system proved more efficient when compared to the NSM non-post-tensioned CFRP strengthening system. The flexural capacity of the NSM post-tensioned CFRP strengthening system, under the deteriorated low-strength PSC beam, increased by up to 30.9% compared to the PSC reference beam. Additionally, the experimental results were compared to a finite-element analysis, and a parametric study was conducted to examine the material properties of the PSC beam. Consequently, the NSM post-tensioned CFRP strengthening system is expected to be an effective solution for addressing the issue of deteriorated low-strength PSC structures.

Predicting shear strength of fiber-reinforced concrete beams reinforced with longitudinal FRP bars with machine learning techniques

ABSTRACT This study investigates the shear strength prediction of Fibre-Reinforced Concrete (FRC) beams reinforced with Fibre-Reinforced Polymer (FRP) bars and without stirrups through the application of Machine Learning (ML) techniques. The utilisation of FRP bars, particularly Glass Fibre-Reinforced Polymer (GFRP) and Basalt Fibre-Reinforced Polymer (BFRP) bars, has emerged as a promising alternative to traditional steel reinforcement due to their superior mechanical properties and corrosion resistance. Moreover, the incorporation of macro- and micro-discrete fibres into concrete compositions enhances both shear and flexural behaviour while reducing crack propagation induced by tensile stresses. The primary objective of this research is to develop accurate predictive models for the shear capacity of FRP-reinforced concrete beams, considering various influential parameters. Six different ML techniques, namely Multiple Linear Regression (MLR), Gaussian Process Regression (GPR), k-Nearest Neighbors (KNN), Support Vector Machines (SVMs), Artificial Neural Networks (ANNs) and Random Forest Regression (RFR), are employed to analyse the complex interactions between input variables, such as fibre type, bar diameter, concrete compressive strength, beam dimensions and the resulting shear strength. By leveraging these computational approaches, we aim to overcome the limitations of conventional analytical methods and provide robust predictions for structural design and optimisation.