Asian Journal of Civil Engineering最新文献_第3页

AI-driven prediction for compressive strength of lightweight ultra-high-performance fiber-reinforced cementitious composites: a hybrid ensemble model and novel SHAP-based equation 人工智能驱动的轻质超高性能纤维增强胶凝复合材料抗压强度预测：混合系综模型和基于shap的新型方程

Asian Journal of Civil Engineering Pub Date : 2026-07-02 DOI: 10.1007/s42107-026-01735-2

Thi-Ngoc-Han Vuong, Tan-Duy Phan

{"title":"AI-driven prediction for compressive strength of lightweight ultra-high-performance fiber-reinforced cementitious composites: a hybrid ensemble model and novel SHAP-based equation","authors":"Thi-Ngoc-Han Vuong, Tan-Duy Phan","doi":"10.1007/s42107-026-01735-2","DOIUrl":"10.1007/s42107-026-01735-2","url":null,"abstract":"<div><p>Lightweight ultra-high-performance fiber-reinforced cementitious composites (L-UHPFRC) have attracted increasing attention in modern construction due to their superior mechanical performance and reduced self-weight, making them highly suitable for long-span bridges and high-rise structures. However, accurately predicting their compressive strength (CS) remains challenging because of the complex nonlinear interactions among constituent materials. This study proposes an interpretable machine learning framework integrating a hybrid Random Forest–Whale Optimization Algorithm (RF–WOA) model for predicting the CS of L-UHPFRC. The proposed RF–WOA model demonstrated high predictive accuracy, achieving R<sup>2</sup> = 0.934, RMSE = 6.816, MAE = 4.698, and MAPE = 3.410% for the training dataset, while also exhibiting stable generalization performance with prediction-to-experiment ratios of (1.01, 0.05) and (0.99, 0.08) for the training and testing datasets, respectively. Furthermore, a novel SHAP-based explicit formulation was developed to capture the nonlinear relationships between input variables and CS while improving model transparency and engineering interpretability. Partial Dependence Plot (PDP) analyses further confirmed that the learned relationships are physically consistent with the underlying behavior of L-UHPFRC. The results demonstrate that the proposed framework provides a reliable, accurate, and interpretable tool for compressive strength prediction and mix design optimization of advanced lightweight cementitious composites, thereby supporting their broader practical implementation in sustainable and high-performance structural applications.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"27 9","pages":"4577 - 4597"},"PeriodicalIF":0.0,"publicationDate":"2026-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148807397","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

Effect on mechanical properties, durability and micro structure of high performance recycled aggregate concrete containing rice husk ash 稻壳灰对高性能再生骨料混凝土力学性能、耐久性和微观结构的影响

Asian Journal of Civil Engineering Pub Date : 2026-07-01 DOI: 10.1007/s42107-026-01741-4

Mahesh V. Tatikonda, Sudhir Patil

{"title":"Effect on mechanical properties, durability and micro structure of high performance recycled aggregate concrete containing rice husk ash","authors":"Mahesh V. Tatikonda, Sudhir Patil","doi":"10.1007/s42107-026-01741-4","DOIUrl":"10.1007/s42107-026-01741-4","url":null,"abstract":"<div><p>This study evaluates the mechanical and durability properties of recycled aggregate concrete using aggregates obtained from demolished structures. Experimental investigations were conducted in accordance with IS 383:2016 and IS 456:2000. Results indicate that recycled aggregate concrete demonstrates acceptable performance, supporting its use in selected structural and non-structural construction applications. In present study, the use of recycled aggregates from demolition waste and rice husk ash is used as a mineral admixture in producing high-performance concrete. The various tests are performed on the prepared concrete for mechanical properties. The tests were performed on the concrete prepared by replacing the normal aggregates by 0%, 30%, 60%, and 100% with recycled aggregates. The mineral admixture was kept at 10% after finalizing the optimum dosage, which was kept constant for all the mixes. The inclusion of 10% rice husk ash in high-performance concrete improves later-age compressive strength and durability due to pozzolanic action and slightly enhances tensile and flexural strength. Mix designs were prepared for grades of M-60, M-80, and M-100. The study revealed a 30% increase in all mechanical and durability properties of the prepared concrete when replacing normal concrete with recycled aggregates. From the tests, it can be suggested that 30% replacement of the natural aggregates by recycled aggregates obtained from the demolition waste can be used in making the high-performance concrete.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"27 10","pages":"4833 - 4851"},"PeriodicalIF":0.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148962065","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

Effects of hollow glass microsphere and re-dispersible polymer powder dosage on properties of vitrified microbead-based thermal insulating putty 中空玻璃微球和可再分散聚合物粉用量对玻化微珠基保温腻子性能的影响

Asian Journal of Civil Engineering Pub Date : 2026-06-30 DOI: 10.1007/s42107-026-01742-3

Shuai Wang, Hao Peng, Zhishan Chen, Yunlong Zhao, Wanwan Fu, Yutao Chen, Longfei Li, Chuqi Huang

{"title":"Effects of hollow glass microsphere and re-dispersible polymer powder dosage on properties of vitrified microbead-based thermal insulating putty","authors":"Shuai Wang, Hao Peng, Zhishan Chen, Yunlong Zhao, Wanwan Fu, Yutao Chen, Longfei Li, Chuqi Huang","doi":"10.1007/s42107-026-01742-3","DOIUrl":"10.1007/s42107-026-01742-3","url":null,"abstract":"<div><p>Using one-factor-at-a-time (OFAT) tests, this study experimentally evaluates the effects of re-dispersible polymer powder (RDP) dosage and hollow glass microsphere (HGM) equal-volume replacement ratio on the properties of vitrified microbead (VMB)-based thermal insulating putty. Specimens with different RDP dosages and HGM replacement ratios were tested for consistency (workability), dry density, thermal conductivity, mechanical properties, water resistance, and microstructure. The results show that an RDP dosage of 3.0 wt% provides a favorable balance between mechanical performance and water resistance: compared with the control group, the 28-day compressive and flexural strengths increase by 11.0% and 35.0%, respectively, while water absorption decreases by 15.0%. When VMB is partially replaced by HGM at an equal-volume ratio of 10 vol%, the thermal conductivity decreases to 0.068 W/(m·K). SEM and FTIR analyses suggest that HGM may contribute to pore filling and possible secondary reactions, thereby improving the overall material performance. Based on the present OFAT results, a recommended mixture is proposed: 45 wt% VMB, 40 wt% fly ash as a cement replacement, 3 wt% RDP, 0.5 wt% cellulose ether, 0.3 wt% polypropylene fiber, and 10 vol% HGM as an equal-volume replacement of VMB. This mixture provides experimental support for the development of exterior-wall thermal insulating putty materials.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"27 10","pages":"4853 - 4865"},"PeriodicalIF":0.0,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148962100","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

Performance evaluation and machine learning modeling of geopolymer fly ash masonry bricks 地聚合物粉煤灰砌块性能评价与机器学习建模

Asian Journal of Civil Engineering Pub Date : 2026-06-30 DOI: 10.1007/s42107-026-01726-3

Mohd Zubair Mohd Ismail Shaikh, Ali B. M. Ali, Mustafa M. Aljumaily, Mukhtar Hamid Abed, Aseel Smerat, Kabul Khudaybergenov, Mohammed Kadhim Rahma

{"title":"Performance evaluation and machine learning modeling of geopolymer fly ash masonry bricks","authors":"Mohd Zubair Mohd Ismail Shaikh, Ali B. M. Ali, Mustafa M. Aljumaily, Mukhtar Hamid Abed, Aseel Smerat, Kabul Khudaybergenov, Mohammed Kadhim Rahma","doi":"10.1007/s42107-026-01726-3","DOIUrl":"10.1007/s42107-026-01726-3","url":null,"abstract":"<div><p>The present study focuses on the development of sustainable unfired masonry bricks stabilized through geopolymerization of Class C and Class F fly ash using alkaline activators. The experimental program investigates the influence of alkali type (NaOH and KOH), molarity (6 M, 8 M, and 10 M), and curing temperature (ambient to 60 °C) on the mechanical and durability properties of geopolymer bricks. Engineering properties including dry and wet compressive strength, water absorption, efflorescence, and acid resistance were evaluated in accordance with relevant Indian Standards. The developed bricks achieved maximum dry compressive strengths of 21.83 MPa and 17.1 MPa for Class C and Class F fly ash respectively, with water absorption values well within codal limits. Acid resistance tests indicated less than 1% mass loss even at pH 2, demonstrating excellent durability. In addition to experimental evaluation, a machine learning framework was implemented to predict compressive strength using experimentally derived datasets comprising 210 samples. Input parameters included fly ash class, alkali type, molarity, activator ratio, curing temperature, and curing duration. Three supervised regression models—Random Forest (RF), Support Vector Regression (SVR), and Artificial Neural Network (ANN)—were developed and validated using fivefold cross-validation. Performance evaluation based on R<sup>2</sup>, RMSE, MAE, and MAPE demonstrated that the Random Forest model provided the highest predictive accuracy, followed by SVR and ANN. Feature importance analysis revealed that molarity and curing temperature were the most influential parameters governing compressive strength development. The integration of experimental investigation with machine learning prediction offers a reliable and efficient approach for optimizing geopolymer brick mix design and enhancing sustainable construction practices.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"27 9","pages":"4357 - 4384"},"PeriodicalIF":0.0,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148807540","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

Mechanics-aware machine learning for axial-capacity prediction of circular and rectangular concrete-filled steel tubular columns 圆形和矩形钢管混凝土柱轴向承载力预测的力学感知机器学习

Asian Journal of Civil Engineering Pub Date : 2026-06-25 DOI: 10.1007/s42107-026-01733-4

Arvind Dewangan, Nikita Jain, Aaqib Anwaar Butt, Neha Sharma, Rupesh Kumar Tipu, Sagar Paruthi, Vipin Kumar Verma

{"title":"Mechanics-aware machine learning for axial-capacity prediction of circular and rectangular concrete-filled steel tubular columns","authors":"Arvind Dewangan, Nikita Jain, Aaqib Anwaar Butt, Neha Sharma, Rupesh Kumar Tipu, Sagar Paruthi, Vipin Kumar Verma","doi":"10.1007/s42107-026-01733-4","DOIUrl":"10.1007/s42107-026-01733-4","url":null,"abstract":"<div><p>Accurate axial-capacity prediction of concrete-filled steel tubular (CFST) columns is challenging because the response depends on section shape, material strength, tube proportion, slenderness, and load eccentricity. This study evaluates a mechanics-aware machine-learning workflow for circular and rectangular CFST columns using a compiled experimental database of 2276 specimens. The workflow uses a normalized response, <span>(eta =P_{textrm{exp}}/P_0)</span>, to reduce gross-size dominance while retaining a direct link with structural mechanics. Benchmark learners, a stacked ensemble, design-code predictors, SHAP interpretation, split conformal intervals, and a desktop deployment prototype were assessed under grouped validation and a limited temporal holdout. The stacked model achieved <span>(hbox {RMSE}_eta =0.129)</span> and MAPE<span>(=12.72%)</span> under grouped cross-validation. On the 92-specimen temporal holdout, it achieved MAPE<span>(=8.80%)</span> and placed 93.48% of predictions within <span>(pm 20%)</span> of the experimental capacity. However, the holdout was small, recent large-scale circular specimens remained difficult, and conformal intervals showed lower-than-nominal temporal coverage. The results suggest that mechanics-aware machine learning can complement conventional CFST capacity assessment, but further external validation and improved uncertainty calibration are needed before routine design-level use.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"27 9","pages":"4527 - 4558"},"PeriodicalIF":0.0,"publicationDate":"2026-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148807279","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

Performance evaluation and parametric optimization of advanced mechanical rebar couplers as an alternative to conventional lap splicing 替代传统搭接的新型机械螺纹钢连接件的性能评价与参数优化

Asian Journal of Civil Engineering Pub Date : 2026-06-25 DOI: 10.1007/s42107-026-01729-0

Atul S. Kurzekar, Sanjivkumar Harinkhede, Payal Pendharkar

{"title":"Performance evaluation and parametric optimization of advanced mechanical rebar couplers as an alternative to conventional lap splicing","authors":"Atul S. Kurzekar, Sanjivkumar Harinkhede, Payal Pendharkar","doi":"10.1007/s42107-026-01729-0","DOIUrl":"10.1007/s42107-026-01729-0","url":null,"abstract":"<div><p>Reinforcing bar splices are an important part of reinforced concrete construction. Conventional lap splicing is widely used, but it often creates reinforcement congestion, increases steel consumption, and makes concreting and bar placement difficult. To overcome these problems, this study developed and evaluated an optimized mechanical rebar coupler as an alternative to conventional lap splices. The proposed coupler was analysed using finite element modelling in ANSYS under different tensile loading conditions. Coupler lengths of 80 mm, 100 mm, 120 mm, and 150 mm were studied for 12 mm, 16 mm, and 20 mm diameter reinforcing bars. The behaviour of the coupler was evaluated in terms of equivalent stress, elongation, elastic strain, and tensile strength based on the provisions of ACI 318, IS 16,172, IS 1786, and IS 456. The results showed that increasing the coupler length reduced stress concentration and elastic strain while keeping deformation within allowable limits. Finite element analysis under a tensile load of 10,000 N showed that the stress in the 12 mm reinforcement bar reduced from about 221 MPa for the 80 mm coupler to nearly 200 MPa for the 150 mm coupler. This shows that longer couplers helped distribute the stress more evenly. Experimental tensile testing of the developed coupler specimens gave ultimate tensile strengths of 563.48 MPa, 641.34 MPa, and 643.39 MPa for the 12 mm, 16 mm, and 20 mm reinforcement bars, respectively.These values were about 25%, 32%, and 34% higher than welded splice specimens and much higher than conventional lap splices. The developed coupler also showed better stress distribution, stable deformation behaviour, and reduced reinforcement congestion. Overall, the study shows that the proposed mechanical rebar coupler can be used as an efficient and practical alternative to conventional lap splicing in reinforced concrete construction.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"27 9","pages":"4431 - 4462"},"PeriodicalIF":0.0,"publicationDate":"2026-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148807286","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

Multi response optimization of basalt fiber reinforced high performance concrete incorporating GGBS and silica fume using response surface methodology 基于响应面法的玄武岩纤维增强含GGBS和硅灰高性能混凝土的多响应优化

Asian Journal of Civil Engineering Pub Date : 2026-06-25 DOI: 10.1007/s42107-026-01737-0

P. A. Sudam, U. R. Darla, M. K. R. Gaddam, G. Himala Kumari, P. V. R. Narendra, M. Sai Babu, C. V. Bharathi, Tejeswara Rao Maganti

{"title":"Multi response optimization of basalt fiber reinforced high performance concrete incorporating GGBS and silica fume using response surface methodology","authors":"P. A. Sudam, U. R. Darla, M. K. R. Gaddam, G. Himala Kumari, P. V. R. Narendra, M. Sai Babu, C. V. Bharathi, Tejeswara Rao Maganti","doi":"10.1007/s42107-026-01737-0","DOIUrl":"10.1007/s42107-026-01737-0","url":null,"abstract":"<div><p>The increasing demand for high-performance and durable concretes has led to the exploration of mineral admixtures and fibers as sustainable alternatives to conventional cement-based systems. This study focuses on optimizing the mechanical and impact properties of basalt fiber–reinforced high-performance concrete incorporating ground granulated blast-furnace slag (GGBS) and silica fume (SF) using Response Surface Methodology (RSM). A Box–Behnken Design (BBD) was adopted with three factors GGBS (0–40%), SF (0–20%), and basalt fiber (0–0.6%) to analyze their individual and interactive effects on compressive, splitting tensile, flexural strengths, and impact energy. The 28-day strengths reached 74.58 MPa (compressive), 7.54 MPa (tensile), and 11.80 MPa (flexural), while impact energy improved to 11.65 kN-m. RSM contour analysis revealed strong nonlinear interactions, with the optimum range of 25 to 35% GGBS, 10 to 15% SF, and 0.4 to 0.5% fiber achieving superior performance. ANOVA confirmed model adequacy (R² = 0.95 to 0.98) with low variability and non-significant lack-of-fit. Multi-response optimization using the desirability approach (0.926) identified 21.22% GGBS, 14.14% SF, and 0.4549% fiber as the best combination, predicting 72.45 MPa compressive strength and 10.32 kN-m impact energy. The findings highlight that RSM-based design provides an efficient pathway for developing sustainable, high-performance concrete with reduced cement usage and enhanced strength–ductility balance.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"27 9","pages":"4615 - 4645"},"PeriodicalIF":0.0,"publicationDate":"2026-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148807280","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 novel GA-GBM based model to construct CPT-SPT relationship 基于GA-GBM的CPT-SPT关系构建模型

Asian Journal of Civil Engineering Pub Date : 2026-06-25 DOI: 10.1007/s42107-026-01731-6

Shuai Fang, Haoqing Xu, Nan Zhang, Xinpeng Lv, Shi He

{"title":"A novel GA-GBM based model to construct CPT-SPT relationship","authors":"Shuai Fang, Haoqing Xu, Nan Zhang, Xinpeng Lv, Shi He","doi":"10.1007/s42107-026-01731-6","DOIUrl":"10.1007/s42107-026-01731-6","url":null,"abstract":"<div><p>Numerous relationships between Cone Penetration Test (CPT) and Standard Penetration Test (SPT) have been developed which consist of empirical formulas, statistical models, and machine learning models. However, these models often suffer from low prediction accuracy and limited generalizability when converting CPT data to SPT <i>N</i> or SPT <i>N</i><sub><i>60</i></sub>. In this study, a GA-GBM based model was developed to construct the CPT-SPT relationship in order to address the aforementioned issues. The raw database was segmented by intervals of soil behavior type index (<i>I</i><sub><i>c</i></sub>) using the GA, and the BP method was then employed to identify and eliminate outliers within each <i>I</i><sub><i>c</i></sub> interval. The preprocessed dataset was analyzed using the GBM technique with the results returned to the GA to iteratively adjust boundaries of each <i>I</i><sub><i>c</i></sub> interval (i.e. Method A) or obtain an optimal number of <i>I</i><sub><i>c</i></sub> interval (i.e. Method B) that optimizes the predictive performance of the proposed model. As compared to other widely used models reported in literature, the accuracy of predicted SPT <i>N</i><sub><i>60</i></sub> from CPT data was significantly improved with an R² of 0.80 and an RMSE of only 5.80. For the new dataset, R<sup>2</sup> of 0.73 was obtained by the proposed model which is much higher than other models. It is demonstrated the proposed GA-GBM model exhibits strong generalization capability and can predict SPT <i>N</i><sub><i>60</i></sub> more accurately. Overall, the proposed model offers new insights into the relationship between CPT and SPT.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"27 9","pages":"4497 - 4513"},"PeriodicalIF":0.0,"publicationDate":"2026-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148807616","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

Flexural behavior of coir reinforced ferrocement panel for roofing 屋面用加筋钢板的弯曲性能

Asian Journal of Civil Engineering Pub Date : 2026-06-25 DOI: 10.1007/s42107-026-01732-5

C. R. Dhamini, K. Madhavi, S. M. Basutkar, M. V. Renukadevi

{"title":"Flexural behavior of coir reinforced ferrocement panel for roofing","authors":"C. R. Dhamini, K. Madhavi, S. M. Basutkar, M. V. Renukadevi","doi":"10.1007/s42107-026-01732-5","DOIUrl":"10.1007/s42107-026-01732-5","url":null,"abstract":"<div><p>This article investigates the flexural performance of ferrocement panel (FP) reinforced with natural fiber coir (CR) mesh and a hybrid of coir and GI weld (CG) mesh as a substitute to conventional metallic mesh (GI). Six combinations of panel were explored by casting slab panels with dimensions of 1000 mm x 450 mm x 50 mm varying mortar strength and fiber volume fraction. The results indicated the Load carrying capacity of FP made with two layers of CR mesh and CG mesh were comparable when the mortar strength was varied from 22.54 to 26.80 MPa. The ductility index (DI) and toughness index (TI) of CG based FPs was higher than CR based FP by 43 to 108% and 28 to 55% respectively. Improved performance of FP was observed when CG was used as reinforcement. The influence of mortar strength, fiber volume fraction, and aspect ratio of panel on flexural strength of FP was evaluated by identifying a factor <span>(:Phi)</span>. Linear and regression prediction models were developed for estimation of flexural strength. The models depicted a coefficient of determination ranging from 0.84 to 0.90 with a variation in FS being less than 10%.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"27 9","pages":"4515 - 4526"},"PeriodicalIF":0.0,"publicationDate":"2026-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148807278","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

Stochastic and interpretable hybrid machine learning framework for predicting mechanical properties of steel fiber reinforced concrete 预测钢纤维混凝土力学性能的随机可解释混合机器学习框架

Asian Journal of Civil Engineering Pub Date : 2026-06-25 DOI: 10.1007/s42107-026-01725-4

Tran H. T Le, Anh-Thang Le, Dongkyu Lee

{"title":"Stochastic and interpretable hybrid machine learning framework for predicting mechanical properties of steel fiber reinforced concrete","authors":"Tran H. T Le, Anh-Thang Le, Dongkyu Lee","doi":"10.1007/s42107-026-01725-4","DOIUrl":"10.1007/s42107-026-01725-4","url":null,"abstract":"<div><p>Steel fiber reinforced concrete (SFRC) exhibits complex mechanical behavior because its strength depends on matrix composition, fiber geometry, and fiber–matrix interaction, making accurate and interpretable prediction challenging. This study develops an interpretable and uncertainty-aware hybrid machine learning (ML) framework to predict SFRC mechanical properties. Six algorithms, including Adaptive Boosting, Extreme Gradient Boosting, Extremely Randomized Trees, Random Forest, CatBoost, and Neural Networks, were benchmarked with Tree-structured Parzen Estimator (TPE) optimization to improve generalization. Among the evaluated models, CatBoost–TPE achieved the best testing performance, with R² values of 0.901, 0.803, and 0.851 for compressive, tensile, and flexural strengths, respectively, while reducing RMSE and MAE by 8–29%. To move beyond deterministic prediction, Sobol-based stochastic global sensitivity analysis (SGSA) was integrated with SHAP feature attribution to evaluate parameter influence and uncertainty propagation. Results show that binder–water variability mainly governs compressive behavior, whereas stochastic perturbations in the fiber–matrix subsystem have stronger effects on tensile and flexural responses. The optimized framework is further deployed as a web-based decision-support tool to support preliminary SFRC strength prediction and data-driven mix-design exploration within the applicability domain of the trained model. This approach may support preliminary quality control and reduce trial-and-error laboratory testing within the studied data range.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"27 9","pages":"4335 - 4356"},"PeriodicalIF":0.0,"publicationDate":"2026-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148807284","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