Asian Journal of Civil Engineering最新文献_第2页

Numerical and experimental investigation on a novel seismic base-isolator made by the magnetic levitation technology

Asian Journal of Civil Engineering Pub Date : 2025-03-16 DOI: 10.1007/s42107-025-01286-y

Hamid Reza Hassani Ghoraba, Arash Akbari Hamed, Reza Mahboobi Esfanjani

{"title":"Numerical and experimental investigation on a novel seismic base-isolator made by the magnetic levitation technology","authors":"Hamid Reza Hassani Ghoraba, Arash Akbari Hamed, Reza Mahboobi Esfanjani","doi":"10.1007/s42107-025-01286-y","DOIUrl":"10.1007/s42107-025-01286-y","url":null,"abstract":"<div><p>The idea of reducing lateral stiffness to extend the natural period of structures is fundamental in using seismic base isolators in structural engineering. However, a perfect isolator with no horizontal stiffness is unrealistic due to the mechanical components in traditional isolators, such as rubber layers and springs. This research introduces the Maglev isolator, which uses magnetic levitation technology to explore a new way to achieve zero horizontal stiffness. To achieve this objective, finite element modeling was validated, leading to a system of two steel plates and ten coils, five on the upper plate and five on the lower, aligned to face each other. This configuration generated a repulsive force that suspended the system. The design’s stability was rigorously tested under static and dynamic loads in both time and frequency domains. After successful simulations in COMSOL, an active control mechanism was developed and evaluated in MATLAB to improve performance. Additionally, the seismic performance of a prototype was tested experimentally across two frequency ranges using a shaking table. The experimental results demonstrate that the isolated system achieves average reductions of 76% in absolute displacement and 73% in absolute acceleration compared to the input values. The Maglev isolator demonstrated remarkable efficacy at elevated frequencies, achieving a substantial decrease in both displacement (83% at 4 Hz versus 70% at 2 Hz) and acceleration (86% at 4 Hz compared to 60% at 2 Hz). This study confirms the novel base-isolator’s significant potential in reducing seismic energy transfer to buildings.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 4","pages":"1767 - 1786"},"PeriodicalIF":0.0,"publicationDate":"2025-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A hybrid OBL-NSGA-III/MOTLBO optimization approach for sustainable design of earth-air heat exchangers in building construction

Asian Journal of Civil Engineering Pub Date : 2025-03-15 DOI: 10.1007/s42107-025-01292-0

Akash Deep Yadav, Sujit Kumar Verma, Vikas Kumar Sharma

{"title":"A hybrid OBL-NSGA-III/MOTLBO optimization approach for sustainable design of earth-air heat exchangers in building construction","authors":"Akash Deep Yadav, Sujit Kumar Verma, Vikas Kumar Sharma","doi":"10.1007/s42107-025-01292-0","DOIUrl":"10.1007/s42107-025-01292-0","url":null,"abstract":"<div><p>This paper presents a novel hybrid optimization method combining the opposition-based learning non-dominated sorting genetic algorithm III (OBL-NSGA-III) and the multi-objective teaching–learning-based optimization (MOTLBO) method to optimize sustainable design of earth-air heat exchangers (EAHE) in construction. EAHE systems utilize stable underground temperatures to precondition air, offering an energy-efficient alternative to conventional HVAC systems. The hybrid methodology addresses multi-objective challenges, including minimizing lifecycle costs, carbon emissions, installation time, and pressure drop, while maximizing energy performance. The hybrid OBL-NSGA-III/MOTLBO approach integrates the global search capability of OBL-NSGA-III with the refinement potential of MOTLBO, ensuring enhanced convergence and solution diversity. The effectiveness of the model is demonstrated by a case study on a 150 m<sup>2</sup> residential building in Mathura, Uttar Pradesh, which achieved considerable reductions in carbon emissions and pressure drop, a 30% improvement in energy performance, and a 20% decrease in lifecycle costs when compared to existing systems. Sensitivity and trade-off analyses provide decision-makers with useful information by highlighting the interactions between design parameters like pipe length, diameter, and depth. This study promotes economical, energy-efficient, and ecologically conscious building methods, thereby establishing a reproducible foundation for optimising sustainable HVAC solutions and supporting global sustainability goals.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 4","pages":"1819 - 1835"},"PeriodicalIF":0.0,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698457","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

How machine learning can transform the future of concrete

Asian Journal of Civil Engineering Pub Date : 2025-03-14 DOI: 10.1007/s42107-025-01281-3

Kaoutar Mouzoun, Azzeddine Bouyahyaoui, Hanane Moulay Abdelali, Toufik Cherradi, Khadija Baba, Ilham Masrour, Najib Zemed

{"title":"How machine learning can transform the future of concrete","authors":"Kaoutar Mouzoun, Azzeddine Bouyahyaoui, Hanane Moulay Abdelali, Toufik Cherradi, Khadija Baba, Ilham Masrour, Najib Zemed","doi":"10.1007/s42107-025-01281-3","DOIUrl":"10.1007/s42107-025-01281-3","url":null,"abstract":"<div><p>The concrete industry is confronted with persistent challenges, such as the need for extensive experimentation, time limitations, and high costs. Machine learning (ML) has become an extremely useful tool, providing diverse applications to tackle these challenges. This paper reviews the growing influence of ML on the concrete industry, highlighting its potential to revolutionize different aspects of concrete research and practical applications. The review explores the evolution of ML in this field, identifying key techniques, algorithms, and data sources commonly used in concrete related studies. It discusses the diverse applications of ML, including material characterization, mix design optimization, prediction of concrete properties, enhancement of nonlinear finite element analysis, crack detection, improvements in sustainability, and structural health monitoring. Additionally, the paper addresses challenges faced in the implementation of ML and offers recommendations to enhance its accuracy and effectiveness for concrete researchers, engineers, and practitioners.</p><h3>Graphical abstract</h3>\u0000<div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 4","pages":"1395 - 1411"},"PeriodicalIF":0.0,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Machine learning based prediction models for the compressive strength of high-volume fly ash concrete reinforced with silica fume

Asian Journal of Civil Engineering Pub Date : 2025-03-14 DOI: 10.1007/s42107-025-01277-z

Anish Kumar, Sameer Sen, Sanjeev Sinha

{"title":"Machine learning based prediction models for the compressive strength of high-volume fly ash concrete reinforced with silica fume","authors":"Anish Kumar, Sameer Sen, Sanjeev Sinha","doi":"10.1007/s42107-025-01277-z","DOIUrl":"10.1007/s42107-025-01277-z","url":null,"abstract":"<div><p>This study involves investigates the relationships between input parameters and compressive strength of concrete using a comprehensive dataset and advanced machine learning based modeling techniques. Compressive strength showed significant increases with curing time, particularly between 14 and 28 days, with optimal performance at 6–8% silica fume (SF) and moderate fly ash (FA) levels (30–50%). SVM-RBF, Random Forest, XGBoost based machine learning models along with non-parametric and linear regression models were developed in the current study. Among the models, XGBoost achieved the highest predictive performance (R<sup>2</sup>: 1.000 in training, 0.999 in testing), outperforming Random Forest and SVM-RBF in accuracy and robustness. Linear and non-parametric regressions exhibited higher errors, emphasizing the necessity of advanced approaches for complex data. Taylor diagrams for the models in training and testing phases also advocated the robustness of XGBoost model. Sensitivity analysis of the XGBoost model shows curing duration (76.844%) as the most critical factor Monotonicity analysis highlighted intricate nonlinear relationships, such as SF and coarse aggregate effects, which were overlooked by basic linear fittings. These findings demonstrate XGBoost’s capability to model complex dynamics, providing actionable insights into optimizing concrete mix design for enhanced compressive strength.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 4","pages":"1683 - 1701"},"PeriodicalIF":0.0,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Investigating the optimal CFRP wrapping orientation for enhanced torsional strength in RC beams

Asian Journal of Civil Engineering Pub Date : 2025-03-14 DOI: 10.1007/s42107-025-01264-4

Fazla Rabbi Anik, Sharmin Reza Chowdhury

{"title":"Investigating the optimal CFRP wrapping orientation for enhanced torsional strength in RC beams","authors":"Fazla Rabbi Anik, Sharmin Reza Chowdhury","doi":"10.1007/s42107-025-01264-4","DOIUrl":"10.1007/s42107-025-01264-4","url":null,"abstract":"<div><p>The aim of this study is to find the optimal wrapping orientation of Carbon Fiber Reinforced Polymer (CFRP) to increase the torsional strength of reinforced concrete (RC) beams under pure torsion. The use of CFRP materials to increase the flexural and shear strengths of RC beams is common, but its potential for torsional improvement is still less well-established. The behavior of RC beams reinforced with CFRP under pure torsion in different orientations is the main focus of this work. A control beam and three beams wrapped with CFRP in various orientations—fully wrapped, 90 ° vertical wrapped strips, and 45 ° inclined wrapped strips were modeled numerically. Each beam had same dimensions of 150 × 230 × 1500 mm. The ultimate torque, angle of twist, and cracking angle were measured for each beam. According to the results, CFRP considerably increased torsional strength in comparison to the control beam. The 90 ° vertical wrapped strip beam decreased the angle of twist by 66.33%, but the fully wrapped CFRP beam increased the ultimate torque by almost 75.28%. The 45 ° inclined wrapped strip beam showed an optimal performance compared to fully wrapped CFRP beam and 90 ° vertical wrapped strip beam by increasing the torque capacity by 23.85% and decreased the angle of twist by 32.65%. Analytical calculations and experimental work from the literature were used to validate these conclusions. ABAQUS software was used for the numerical investigation. This research underscores the potential of different CFRP wrapping orientations as a resilient solution for improving the torsional strength of RC beams, offering a valuable approach for enhancing the structural integrity and durability of reinforced concrete structures in torsion-prone environments.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 4","pages":"1511 - 1526"},"PeriodicalIF":0.0,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cruciform steel column: FEM simulation and experimental approach to evaluate the strength and buckling behaviour

Asian Journal of Civil Engineering Pub Date : 2025-03-13 DOI: 10.1007/s42107-025-01283-1

P. Arun Kumar, B. Anupriya

{"title":"Cruciform steel column: FEM simulation and experimental approach to evaluate the strength and buckling behaviour","authors":"P. Arun Kumar, B. Anupriya","doi":"10.1007/s42107-025-01283-1","DOIUrl":"10.1007/s42107-025-01283-1","url":null,"abstract":"<div><p>I-section is the most common structural member that is frequently utilized as a column element because of its serviceability and efficient load transfer. Due to its larger axial capacity and symmetrical geometry, the cruciform section is a potential substitute to the conventional column section. The two primary factors that determine a column’s capacity are the slenderness ratio and the second moment of inertia. The axial capacity of a column is effectively increased by symmetrical cruciform column sections, which have the identical second moment of inertia on both axes. In this work, the analytical examination utilising the FEM is contrasted with the experimental approach to carry out an extensive assessment for comparing Cruciform column sections with conventional steel sections. Analytical and experimental findings are compared with theoretical results to provide an adequate evaluation. The general performance and buckling properties of the column are evaluated in this study. Two unique cruciform column sections are reviewed and compared with the standard column section. In terms of performance, cruciform column sections outperform regular column sections. It is made evident that the flanged cruciform column section performs well when used in the place of heavier steel column sections, which lowers the overall sectional weight as well as the cost.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 4","pages":"1757 - 1765"},"PeriodicalIF":0.0,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predictive modeling of crumb rubber-modified mortar: insights from ANN, LR, RF, and M5P methods 碎屑橡胶改性砂浆的预测建模：ANN、LR、RF 和 M5P 方法的启示

Asian Journal of Civil Engineering Pub Date : 2025-03-10 DOI: 10.1007/s42107-025-01270-6

Parikshit Hurukadli, Bhupender Parashar, Bishnu Kant Shukla, Pushpendra Kumar Sharma, Parveen Sihag

{"title":"Predictive modeling of crumb rubber-modified mortar: insights from ANN, LR, RF, and M5P methods","authors":"Parikshit Hurukadli, Bhupender Parashar, Bishnu Kant Shukla, Pushpendra Kumar Sharma, Parveen Sihag","doi":"10.1007/s42107-025-01270-6","DOIUrl":"10.1007/s42107-025-01270-6","url":null,"abstract":"<div><p>This study investigates the feasibility of using crumb rubber as a partial sand replacement in cement mortar, aiming to address environmental challenges associated with tire waste while contributing to sustainable construction practices. The experimental phase involved preparing cement mortar samples with varying percentages of crumb rubber and analyzing the resulting compressive strength. Crumb rubber substitution at levels of up to 7.5% in a 1:5 to 1:6 mix proportion resulted in practical compressive strengths between 2–6 MPa, suitable for certain applications in construction. The compressive strength reduction associated with increased crumb rubber was offset by improved durability characteristics, including enhanced ductility and energy absorption. To model and predict compressive strength effectively, four machine learning approaches—Artificial Neural Network (ANN), Random Forest (RF), Linear Regression (LR), and M5P tree—were implemented. The ANN model emerged as the most effective with respect to testing data, with performance metrics including Coefficient of Correlation (CC) values of 0.9998, Nash–Sutcliffe Efficiency (NSE) values 0.9959, least Root Mean Squared Error (RMSE) of 0.2125, least Scattering Index (SI) of 0.041 and least Mean Absolute Error (MAE) of 0.1693. Sensitivity analysis further highlighted crumb rubber percentage as a critical factor influencing compressive strength, underscoring the potential for targeted optimization. The findings suggest that incorporating crumb rubber in mortar can balance sustainability goals with material performance, especially when paired with advanced predictive modeling. Future work is recommended to optimize formulations by varying water-cement ratios or introducing plasticizers to enhance the strength of rubber-modified mortar. This research highlights a promising pathway for reusing waste materials in construction, contributing to both environmental and structural engineering fields.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 4","pages":"1621 - 1633"},"PeriodicalIF":0.0,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Machine learning algorithms on self-healing concrete 自愈混凝土的机器学习算法

Asian Journal of Civil Engineering Pub Date : 2025-03-10 DOI: 10.1007/s42107-025-01272-4

Shrikant M. Harle

{"title":"Machine learning algorithms on self-healing concrete","authors":"Shrikant M. Harle","doi":"10.1007/s42107-025-01272-4","DOIUrl":"10.1007/s42107-025-01272-4","url":null,"abstract":"<div><p>Self-healing concrete (SHC) has emerged as a groundbreaking material in sustainable construction, addressing critical challenges such as crack formation and durability limitations in traditional concrete. Recent research highlights the use of advanced techniques, including bacterial and fungal agents, machine learning (ML) models, and innovative material compositions, to enhance the performance and self-healing capabilities of SHC. Studies have focused on leveraging bacteria-induced calcium carbonate precipitation, particularly using organisms like <i>Bacillus subtilis</i> and <i>Trichoderma reesei</i>, to autonomously seal cracks and improve compressive strength. Machine learning techniques such as Adaptive Boosting (AB), Gradient Boosting (GB), and Random Forest (RF) have been employed to optimize crack repair rate predictions and material design, with models achieving exceptional accuracy metrics (e.g., R² > 0.98). Visualization tools like heatmaps and radar charts reveal insights into aggregate balance, strength recovery, and model performance across evaluation criteria. Despite these advancements, the adoption of SHC faces challenges, including standardization of methods, cost constraints, and scalability for large-scale applications. This review provides a comprehensive understanding of SHC’s potential, emphasizing its role in creating durable, efficient, and environmentally friendly materials for modern infrastructure.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 4","pages":"1381 - 1394"},"PeriodicalIF":0.0,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimized high-performance concrete using Styrene–Butadiene Rubber and hybrid fibers: enhancing fresh, mechanical, durability, and microstructural properties for sustainable construction 使用苯乙烯-丁二烯橡胶和混合纤维优化高性能混凝土：提高新鲜度、机械性能、耐久性和微结构性能，实现可持续建筑

Asian Journal of Civil Engineering Pub Date : 2025-03-10 DOI: 10.1007/s42107-025-01271-5

Anirudh Sharma, Ram Vilas Meena

{"title":"Optimized high-performance concrete using Styrene–Butadiene Rubber and hybrid fibers: enhancing fresh, mechanical, durability, and microstructural properties for sustainable construction","authors":"Anirudh Sharma, Ram Vilas Meena","doi":"10.1007/s42107-025-01271-5","DOIUrl":"10.1007/s42107-025-01271-5","url":null,"abstract":"<div><p>Building on our previous research, which identified 3% Styrene–Butadiene Rubber (SBR) and 10% silica fume replacement by cement as optimal for High-Performance Concrete (HPC), this study investigates the combined effects of SBR and hybrid fibers (50% glass fibers and 50% polypropylene fibers) at varying proportions (0.25–2%) on the fresh, mechanical, durability, and microstructural properties of HPC. The mix design adhered to IS 10262:2009, with testing conducted as per IS 516:1959 standards. Results indicate that adding SBR improves workability, while hybrid fibers enhance tensile and flexural strength through crack-bridging mechanisms. The optimal composition, with 3% SBR and 1% hybrid fibers, achieved a 20% increase in compressive strength compared to the control. Durability studies demonstrated reduced permeability, improved freeze–thaw resistance, and better chemical attack resistance. Microstructural analysis via SEM, TGA, and XRD revealed a dense interfacial transition zone (ITZ), reduced porosity, and higher C–S–H content, contributing to superior mechanical and durability properties. This comprehensive study establishes the benefits of SBR and hybrid fibers in producing sustainable and high-performing concrete, aligning with IS code recommendations. The findings provide a robust framework for enhancing concrete performance in diverse construction applications.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 4","pages":"1635 - 1654"},"PeriodicalIF":0.0,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bayesian-optimized tree-based models for predicting the shear strength of U-shaped externally bonded FRP-strengthened RC beams

Asian Journal of Civil Engineering Pub Date : 2025-03-06 DOI: 10.1007/s42107-024-01258-8

Redouane Rebouh, Ali Benzaamia, Mohamed Ghrici

{"title":"Bayesian-optimized tree-based models for predicting the shear strength of U-shaped externally bonded FRP-strengthened RC beams","authors":"Redouane Rebouh, Ali Benzaamia, Mohamed Ghrici","doi":"10.1007/s42107-024-01258-8","DOIUrl":"10.1007/s42107-024-01258-8","url":null,"abstract":"<div><p>The rehabilitation of aging concrete infrastructure using externally bonded fiber-reinforced polymer (EB-FRP) systems has emerged as a crucial solution in civil engineering. Yet, accurate prediction of their shear-strengthening contribution remains challenging due to complex failure mechanisms and behavioral uncertainties. This study investigates the application of Tree-based machine learning models for predicting the shear strength contribution of U-shaped EB-FRP systems in reinforced concrete beams. Three distinct approaches—Decision Tree, Random Forest, and CatBoost—were developed and evaluated using a refined database of 189 experimental specimens, encompassing diverse beam configurations and strengthening parameters. The methodology incorporates Bayesian optimization through the Optuna framework for systematic hyperparameter tuning, ensuring optimal model performance. The CatBoost model demonstrated superior predictive capabilities, maintaining exceptional consistency across training (R<sup>2</sup> = 0.92, VAF = 92.55%) and testing phases (R<sup>2</sup> = 0.90, VAF = 89.91%), significantly outperforming Decision Tree and Random Forest models. Comparative analysis against current design guidelines (ACI 440.2R-17, fib Bulletin 90, and TR-55) revealed substantial improvements in prediction accuracy, with the CatBoost model reducing mean absolute error by approximately 65% compared to code provisions. The results highlight the potential of advanced machine learning techniques in capturing the complex nonlinear relationships governing FRP shear contribution, offering a reliable tool for preliminary design and validation of strengthening systems. This study contributes to the growing integration of data-driven approaches in structural engineering practice, particularly in the context of FRP-strengthening applications.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 4","pages":"1465 - 1478"},"PeriodicalIF":0.0,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0