<?xml version="1.0" encoding="utf-8"?>
    <rss version="2.0">
      <channel xmlns:content="http://purl.org/rss/1.0/modules/content/">
        <title>Frontiers in Built Environment | Structural Engineering and Design section | New and Recent Articles</title>
        <link>https://www.frontiersin.org/journals/built-environment/sections/structural-engineering-and-design</link>
        <description>RSS Feed for Structural Engineering and Design section in the Frontiers in Built Environment journal | New and Recent Articles</description>
        <language>en-us</language>
        <generator>Frontiers Feed Generator,version:1</generator>
        <pubDate>2026-08-17T03:54:51.854+00:00</pubDate>
        <ttl>60</ttl>
        <item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2026.1887640</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2026.1887640</link>
        <title><![CDATA[Influence of joint load-bearing behavior on the system-level response of reinforced-concrete truss-like beams: topology optimization basis]]></title>
        <pubdate>2026-08-14T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Iyad Ahmed</author><author>Thomas Mader</author><author>Peter Gappmaier</author><author>Mathias Hammerl</author><author>Sara Reichenbach</author><author>Matthias Neuner</author><author>Benjamin Kromoser</author>
        <description><![CDATA[Structural optimization can reduce material use and embodied carbon in reinforced concrete (RC) beams, but the removal of concrete creates truss-like load paths in which local joint behavior may strongly influence stiffness, force redistribution, and failure development. This study investigates the mechanical behavior of joints in reinforced concrete truss-like beams and evaluates how different joint geometries influence the transfer of moment, axial force, and shear between connected members. The research combines experimental testing, calibrated nonlinear finite element analysis (FEA), and isolated joint simulations. Two beam configurations, namely, Warren truss with 45° diagonals (W45) and Warren truss with verticals and 45° diagonals (W45-V), were tested under three-point bending and used to calibrate the numerical models. The calibrated FEA approach was then extended to four truss-like configurations: W45, Warren truss with 60° diagonals (W60), W45-V, and Pratt truss with 45° diagonals (P45). In addition, 66 isolated joint models were analyzed using unit rotation, axial displacement, and shear displacement to quantify moment, axial-force, and shear transfer between connected members. The results show that the investigated joints behave nonlinearly and asymmetrically, with clear stiffness changes after cracking. None of the joints behaves as an ideal hinge; instead, all configurations transfer moments, axial forces, and shear through semi-rigid joint action. W60 shows a stiffer and more direct force-transfer mechanism, W45-V provides improved redistribution through vertical members, and P45 exhibits the strongest directional dependence. Overall, member-only verification is insufficient, and simplified design should include semi-rigid joint behavior and local joint verification.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2026.1824242</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2026.1824242</link>
        <title><![CDATA[Time-of-flight-based guided-wave imaging for multi-damage localization in large plate structures with limited sensing paths]]></title>
        <pubdate>2026-07-10T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Changzhi Zhao</author><author>Mohammed Aslam</author><author>Do-Kyung Pyun</author><author>Jaesun Lee</author>
        <description><![CDATA[Guided-wave imaging is widely used for structural health monitoring and non-destructive evaluation of plate-like structures; however, many existing imaging methods require dense sensing networks and a large number of sensing paths, increasing data acquisition effort, storage requirements, and computational cost. This study proposes a time-of-flight-based guided-wave imaging framework for blind multi-damage localization in isotropic aluminum plates using a limited number of sensing paths. A pulse–echo sensing configuration with eight sensing paths is employed, and baseline-subtracted residual signals are processed using continuous wavelet transform to extract time-of-flight-related scattering features. An automated peak-selection pipeline, combining adaptive local-statistics thresholding, peak suppression, and distance-conditioned amplitude weighting, is introduced to identify reliable damage-reflection candidates without prior knowledge of the number or locations of damages. The selected features are then fused using a time-of-flight-based probabilistic imaging formulation to reconstruct damage index maps. Finite element simulations and plate experiments are conducted for one to three defects, including cases with a defect located outside the sensor-network region. Numerical results show relative localization errors of 1.95% for one defect, 1.19% and 5.92% for two defects, and 1.58%, 1.83%, and 0.96% for three defects. Experimental validation gives corresponding errors of 1.35%, 1.02% and 3.78%, and 1.48%, 4.27%, and 3.62%. The results demonstrate that blind multi-damage localization is feasible using only eight sensing paths when automated time-of-flight feature extraction and probabilistic fusion are combined. The proposed framework reduces sensing-path requirements while maintaining acceptable localization accuracy, although further validation is needed for very closely spaced damages and more complex operational conditions.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2026.1869657</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2026.1869657</link>
        <title><![CDATA[Comprehensive multi-objective optimization framework for sustainable urban flyover design: integrating radial basis function metamodeling and advanced optimization algorithms]]></title>
        <pubdate>2026-06-17T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Jaya Rajkumar Ramchandani</author><author>Suddhasheel Ghosh</author>
        <description><![CDATA[IntroductionUrban flyover infrastructure requires balancing structural efficiency, cost minimization, and environmental sustainability. Traditional deterministic methods fail to capture variability and reproducibility in large-scale civil projects.MethodsA comprehensive framework was developed integrating Radial Basis Function (RBF) surrogate modeling, sensitivity and uncertainty analysis, and comparative evaluation of nine optimization algorithms (NSGA-II, NSGA-III, DE, CMA-ES, GA, ES, SRES, Nelder-Mead, Pattern Search). The dataset included 47 flyover configurations across 12 Indian cities.ResultsThe RBF surrogate reduced computational effort by 95–98% while maintaining predictive accuracy (R2 > 0.95). Application to the Aurangabad interlinking flyover project achieved cost savings of 8–12%, environmental impact reductions of 15–25%, and material efficiency improvements of 20–30%. Soil bearing capacity and traffic volume accounted for 58% of cost variance.DiscussionThe integration of surrogate modeling and multi-algorithm optimization advances sustainable infrastructure design by providing robust, reproducible, and evidence-based solutions. This framework demonstrates practical relevance for balancing economic viability, structural adequacy, and environmental responsibility in urban flyover development.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2026.1853315</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2026.1853315</link>
        <title><![CDATA[Elastoplastic time-history analysis of prefabricated SRC frame structures in multi-floored grain warehouses]]></title>
        <pubdate>2026-06-04T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Qiang Li</author><author>Yonggang Ding</author><author>Guoqi Ren</author><author>Qikeng Xu</author><author>Zhenhua Xu</author>
        <description><![CDATA[The prefabricated steel-reinforced concrete (SRC) structure integrates the construction efficiency of prefabrication with the high-performance features of SRC materials, exhibiting great application potential in high-rise industrial buildings including Grain Warehouses subjected to lateral pressure and heavy loads. In order to evaluate the seismic performance of this structural system, this study takes a prefabricated SRC grain Warehouses in Guangzhou as the research object and then performs dynamic elastoplastic time-history analysis under rare earthquakes through the finite element software ABAQUS. The analysis concentrates on the seismic response, damage evolution, and energy dissipation mechanism of the structure, and shows the performance differences between this system and traditional reinforced concrete frame structures. The frequent earthquake level, which mainly considers serviceability under elastic conditions, is not investigated, and this study concentrates solely on rare earthquake excitation. The results suggest that under rare earthquake excitation, the maximum elastoplastic inter-story drift ratios in the X and Y directions are 1/248 and 1/266, respectively, both meeting the code limit of 1/100, suggesting excellent overall deformation capacity. When compared with traditional reinforced concrete structures, the prefabricated SRC grain Warehouses shows a smaller damage range in major components, revealing superior deformation capacity, energy dissipation mechanism, as well as overall seismic resilience. Moreover, the findings also offer a theoretical foundation for the seismic design as well as engineering use of prefabricated SRC structural systems.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2026.1829487</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2026.1829487</link>
        <title><![CDATA[Flexural and shear performance of concrete beams reinforced with macroscopic carbon nanotubes using finite element modelling]]></title>
        <pubdate>2026-05-26T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Deborah Wadzani Dauda</author><author>Ramesh Babu Chandran</author><author>Deepak Kumar Soni</author>
        <description><![CDATA[Carbon nanotubes (CNTs) are one among many materials that are used to reinforce concrete alongside steel bars. They are known for their exceptional mechanical properties which have been found to improve the mechanical performance and crack resistance of cementitious materials Although CNTs are usually incorporated into concrete as nano-fillers, fibres, or powders, this study aimed at using CNTs in a macroscopic form as bars to replace steel bars in reinforcing concrete. Numerical investigation on the flexural and shear performance of concrete beams reinforced with macroscopic CNT bars was carried out using Finite element method (FEM) in ANSYS 17.2. Six simply supported beams each of RCC and macroscopic CNTs comprising Concrete Grades 40, 60, 120, 200, 300, 400 making a total of twelve beams were designed in accordance with ACI 318-19, simulated and analyzed under four-point bending. The results show that the CNT–reinforced beams in comparison to RCC beams had a higher load–carrying capacity which was up to 720 kN in difference and approximately 1.84 times that of RCC beams and this increased with higher concrete grades. From the load–deflection response, CNT–reinforced beams experienced enhanced deformation capacity at most concrete grades, ductility improved as much as 62.7%, while elastic stiffness was consistently higher than RCC beams at all grades, with improvements up to 14.4%. The flexural and shear performances as well outweighed that of RCC beams at most grades with flexural and shear capacities increasing from 496.84kNm to 912.15kNm and from 432.04kN to 793.18 kN respectively representing an improvement of 83.6%. However, when compared to the designed flexure and shear capacities, the CNT–reinforced beams performed better in flexure than shear. Failure in all RCC and macroscopic CNT–reinforced beams was governed by a combined flexure-shear action, but CNT beams had more distributed cracks indicating improved load redistribution before failure.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2026.1811594</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2026.1811594</link>
        <title><![CDATA[Comparative evaluation of supervised machine learning models in the non-destructive strength prediction of steel fiber reinforced concrete]]></title>
        <pubdate>2026-05-12T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>P. J. Shijin</author><author>R. Raghunandan Kumar</author><author>Robin Davis</author><author>Praveen Nagarajan</author><author>Sudha Das</author>
        <description><![CDATA[This study evaluates the performance of nine supervised machine learning (ML) techniques, namely, K-nearest neighbors (KNN), decision tree (DT), support vector regression (SVR), random forest (RF), gradient boosting (GB), AdaBoost (AB), extreme gradient boosting (XGBoost), light gradient boosting machine (LGBM), and categorical boosting (CatBoost)—on predicting the compressive and tensile strengths of steel fiber reinforced concrete (SFRC), thus providing a data-driven, non-destructive framework for assessing material performance. An extensive dataset is created by varying the fine-to-coarse aggregate ratio and steel fiber content in the range of 0%–2%. The models were evaluated using performance metrics such as coefficient of determination, R2, and mean squared error (MSE). The results indicate that XGBoost exhibited the best performance of all the compared ML models, as evident through its R2 value of 0.9926 for flexural strength, 0.9965 for split tensile, and 0.7837 for compressive strength prediction. These results illustrate that the nonlinear behavior of SFRC can be captured more effectively by AI-ML models and provide better and more accurate strength predictions, thereby supporting advanced non-destructive testing strategies and reducing reliance on extensive destructive testing. Through this study, ML models can be positioned within a structural health monitoring (SHM) context where the predicted parameters of strength can be used for maintenance planning, condition assessment, and damage detection. The outcomes of this study contribute to the enhancement of data-driven approaches for material characterization, thus helping incorporate ML models into real-world structural assessment frameworks.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2026.1798611</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2026.1798611</link>
        <title><![CDATA[Optimal placement of seismic barriers for enhancing the performance of steel moment-resisting frames against earthquakes]]></title>
        <pubdate>2026-04-10T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Masoomeh Asadzadeh Sardehaei</author><author>Mohammadreza Mashayekhi</author><author>Ataallah Sadeghi-Movahhed</author><author>Ali Majdi</author><author>Majid Movahedi Rad</author>
        <description><![CDATA[IntroductionDespite extensive research on vibration isolation systems for dissipating seismic waves, most studies have focused on the performance of seismic barriers against surface waves (e.g., those from train movement). Therefore, there has been limited investigation into how filled seismic barriers perform against earthquake forces originating from deep sources, or how different barrier configurations influence the seismic response of structures. This gap underscores the need to design and optimize vibration barriers to mitigate the effects of earthquake effects on structures and enhance structural safety in seismic zones. Therefore, the objective of this research is to evaluate the effectiveness of vibration barriers and identify the optimal model.MethodsTo achieve this goal, a 2D finite element model was used to simulate the propagation of seismic waves in a single-layer soil and investigate the effect of barriers on a five-story steel moment-resisting frame structure resting on a concrete foundation. A parametric study was conducted on 33 models (a base model without a barrier and 32 barrier models across six scenarios), covering variations in geometrical parameters (width, depth, distance), material types (concrete and geofoam), and barrier layouts.Results and DiscussionThe results showed that using two horizontal layers of geofoam under the foundation leads to optimal structural responses. Although the results indicated that geofoam barriers are superior for reducing superstructure responses, concrete barriers are more effective for controlling foundation acceleration.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2026.1756908</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2026.1756908</link>
        <title><![CDATA[Beyond fragility: physics-driven neural surrogates for seismic resilience prediction of bridges]]></title>
        <pubdate>2026-03-30T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Jacob Atkins</author><author>Donya Hajializadeh</author><author>Waqas Iqbal</author><author>Farahnaz Soleimani</author>
        <description><![CDATA[Traditional fragility-based methods are rigorous, but they can be computationally intensive and difficult to scale to large bridge inventories, particularly when resilience assessments must propagate fragility outputs through functionality and recovery models for time-dependent decision support. This study presents a physics-driven neural surrogate framework that complements fragility-informed workflows by directly predicting a bridge-level seismic resilience index as a continuous system metric. Using pre-1971 concrete box-girder bridges as a case study, we generate a simulation-informed dataset from high-fidelity nonlinear time-history analyses in OpenSees, covering 1,600 bridge-ground motion scenarios. A multilayer perceptron (MLP) model is trained with systematic hyperparameter tuning over loss functions, optimizers, network depth, and regularization. The final MLP achieves over 97% prediction accuracy and outperforms baseline ensemble learning models. By learning directly from physics-based simulations, the proposed surrogate enables rapid and scalable resilience estimation, supporting retrofit prioritization, emergency planning, and resilience-informed design in seismically active regions.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2026.1753382</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2026.1753382</link>
        <title><![CDATA[Interpretable machine learning for predicting the bearing capacity of double shear-bolted connections: a data-driven evaluation]]></title>
        <pubdate>2026-02-17T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Soheila Kookalani</author><author>Hongchen Liu</author><author>Tirtharaj Dash</author><author>Alwyn Mathew</author><author>Ioannis Brilakis</author>
        <description><![CDATA[IntroductionAccurate prediction of the bearing capacity of double shear-bolted connections in structural steel is essential for ensuring safety and efficiency in structural design. This study explores the application of ten machine learning algorithms to enhance prediction accuracy while addressing the interpretability challenges often associated with such models.MethodsModels were tuned with 10-fold crossvalidation and assessed using RMSE, R2 and a20 accuracy index. A comprehensive sensitivity analysis evaluates the influence of input parameters, while advanced interpretability techniques, such as partial dependence plots, accumulated local effects, and Shapley additive explanations, are employed alongside parametric studies to elucidate the decision-making processes of the models.ResultsThese methods facilitate the identification of critical variables that influence bearing capacity predictions at both local and global scales.DiscussionThe study demonstrates that machine learning can be a trustworthy and data-driven complement to conventional mechanics-based approaches, when coupled with rigorous interpretability, advancing both safety and efficiency in steelconnection design. The findings highlight the potential of interpretable machine learning approaches to not only improve predictive precision but also provide actionable insights into complex model behaviours, ultimately advancing structural engineering practices and promoting data-driven design methodologies.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2025.1700908</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2025.1700908</link>
        <title><![CDATA[Numerical investigation of a novel steel connection for panelized modular houses]]></title>
        <pubdate>2026-01-05T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Mostafa Elhadary</author><author>Ahmed Bediwy</author><author>Ahmed Elshaer</author>
        <description><![CDATA[Indigenous communities in Canada, particularly those in remote areas, face a persistent shortage of adequate housing. Modular construction offers a potential solution, yet challenges related to transportation and lifting limit its widespread adoption. This study proposes an innovative steel bolted connection using hollow structural sections (HSS) to improve constructability and performance in modular housing. The connection was experimentally tested and validated using three-dimensional finite element models. A parametric study on one- and two-dimensional prototypes examined the influence of stiffeners, bolt arrangement, bolt number, and plate thickness on the connection’s structural performance. The results showed that the AR1.5 bolt arrangement increased capacity through early bolt bearing but reduced ultimate rotation by 50%, whereas the AR0.6 arrangement shifted failure to the column due to local buckling. Increasing plate thickness from 10 mm to 15 mm increased capacity by up to 7% and ductility by 11%, while increasing the number of bolts from six to ten improved capacity by up to 22%, depending on the arrangement. The addition of a 10-mm stiffener reduced ultimate rotation by approximately 60% due to local buckling. These findings highlight the critical role of bolt configuration and reinforcement techniques in optimizing both strength and deformation capacity, providing guidance for the design of efficient and durable modular housing connections.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2025.1724879</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2025.1724879</link>
        <title><![CDATA[Evaluation of MobileNetV3-Large for crack classification across low- and high-resolution images]]></title>
        <pubdate>2025-12-10T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Liujie Chen</author><author>Haodong Yao</author><author>Ke Gan</author><author>Zanyu Huang</author><author>Jing Zhang</author><author>Ching-Tai Ng</author><author>Jiyang Fu</author>
        <description><![CDATA[IntroductionThis paper evaluates the robustness and generalization ability of five recently developed Convolutional Neural Networks (CNNs), Visual Geometry Group 16 (VGG16), Google Inception Net (GoogLeNet), Mobile Network version 3 Large (MobileNetV3-Large), Efficient Network B0 (EfficientNetB0) and Efficient Network version 2 Small (EfficientNetV2-S), on crack recognition and classification.MethodsThis study proposes a semantic segmentation based on VGG16- U-Net to address the issue of background noise in the images automatically and the transfer learning with fine-tuning is used to improve the performance of the CNNs in the bridge crack image dataset and building crack image dataset (transverse cracks, vertical cracks, oblique cracks and irregular cracks).ResultsThe results indicate that the MobileNetV3-Large has the best performance. For the low-resolution building crack image dataset, the accuracy of the crack recognition reaches 99.58% and the F1-score reaches 99.60%. The accuracy of the classification reaches 94.70% and the Macro-F1 reaches 94.71%. For the higher resolution bridge crack image dataset, the accuracy of the classification reaches 95.70% and the Macro-F1 reaches 95.67%.DiscussionThe results show that the MobileNetV3-Large has the best robustness and generalization ability with a small CNN size and the shortest training time.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2025.1692879</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2025.1692879</link>
        <title><![CDATA[Forecasting bond strength of various FRP bars with different surface characteristics in concrete using machine learning models]]></title>
        <pubdate>2025-11-10T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Ameer M. Salih</author><author>Aso A. Abdalla</author><author>Sardar R. Mohammad Ali</author><author>Tre A. Abdullah</author>
        <description><![CDATA[Fiber-reinforced polymer (FRP) bars are gaining prominence in civil infrastructure due to their high strength-to-weight ratio, corrosion resistance, and low thermal conductivity. The bond strength (BS) between FRP bars and concrete, which is influenced by surface treatments like sand-coating or ribbing, plays a critical role in ensuring structural performance and durability. This study aims to predict the bond strength of different FRP bar types and surface characteristics in concrete using machine learning models. A total of 416 datasets from standard pull-out tests were collected and statistically analyzed, considering variables such as bar type, surface treatment, concrete compressive strength, bar diameter, bonded length, concrete cover, and FRP bar tensile properties. Two machine learning models, Artificial Neural Networks (ANN) and Extreme Gradient Boosting (XGBoost) were developed for bond strength prediction. Model performance was evaluated using Root Mean Squared Error (RMSE), Correlation Coefficient (R), and Scatter Index (SI). XGBoost demonstrated superior performance with lower RMSE and SI, and higher R values in 5-fold cross-validation. Sensitivity analysis identified concrete compressive strength as the most significant input in bond strength prediction. Additionally, main effect plots and Analysis of Variance (ANOVA) tests were conducted to further investigate the relationships between variables. These findings contribute to a more accurate understanding of FRP bar-concrete interactions, facilitating the optimization of structural design.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2025.1693218</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2025.1693218</link>
        <title><![CDATA[Stacked ensemble and SHAP-based approach for predicting plastic rotational capacity in RC columns]]></title>
        <pubdate>2025-10-17T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Andrei-Odey Kadhim</author><author>Iolanda-Gabriela Craifaleanu</author><author>Eugen Lozincă</author>
        <description><![CDATA[The accurate estimation of plastic rotational capacity in reinforced concrete (RC) elements is essential for performance-based seismic design and structural safety assessments. In this study, an extensive experimental database, comprising 258 rectangular and 151 circular RC column specimens, was compiled based on open data available and used to train machine learning models for predicting this parameter. Three algorithms, i.e. Support Vector Regression (SVR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost), were implemented and optimized using grid search within a nested cross-validation framework. The predictive performance was evaluated by averaging the coefficient of determination (R2) across five outer folds, while final accuracy was assessed on the test set using both R2, the Mean Absolute Error (MAE), the root mean squared error (RMSE), and the mean absolute percentage error (MAPE). Model interpretability was improved using SHAP (SHapley Additive exPlanations) analysis, which quantified the influence of input parameters on predictions. Finally, a stacking ensemble model was developed to integrate the strengths of the individual regressors. The proposed methodology demonstrates increased accuracy and robustness in predicting the plastic rotational capacity of both circular and rectangular RC columns, providing a valuable tool for seismic assessment and structural reliability analysis.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2025.1661712</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2025.1661712</link>
        <title><![CDATA[Wind tunnel testing to study turbulent wind field effect on wind load and wind-induced response of TV tower]]></title>
        <pubdate>2025-10-02T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Daqiao Xia</author><author>Cheng Pei</author>
        <description><![CDATA[For steel-constructed TV towers, complex aerodynamic profiles and low damping are typical characteristics—two attributes that render wind-induced response and wind load critical considerations in their design. Additionally, their wide distribution across diverse terrains exposes these structures to varied wind conditions, further complicating wind-resistant design efforts. To explore how wind field parameters affect wind load and wind-induced response, this study took a 240-m-high TV tower as the engineering background, simulated different turbulent wind fields in a wind tunnel, conducted force measurement tests using a high-frequency dynamic balance (with the model segmented into seven sections to improve accuracy), calculated via the equivalent static wind load (ESWL) method (considering the first three modes), and verified with the complete quadratic combination (CQC) method. Results within the tested range show that mean wind force decreases with increasing turbulence intensity, while the root mean square (RMS) of wind force increases correspondingly; conversely, the RMS of the tower’s wind-induced response decreases as turbulence intensity rises. These findings highlight the need to comprehensively consider mean and fluctuating wind effects and their impact on structural response in the wind-resistant design of steel TV towers.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2025.1672716</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2025.1672716</link>
        <title><![CDATA[Data-driven models for human–structure interaction based on MLP and NARX neural networks]]></title>
        <pubdate>2025-10-02T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Daniel Mena-Sanchez</author><author>Natividad Garcia-Troncoso</author><author>Wilfredo Alfonso</author><author>Albert R. Ortiz</author><author>Daniel Gomez</author>
        <description><![CDATA[Structural design often neglects the dynamic effects induced by human activities. Excessive vibrations in structures such as pedestrian bridges, grandstands, slabs, and stairways have highlighted the analysis as dynamic systems of humans interacting with structures. This phenomenon, commonly referred to as “human–structure interaction” (HSI), is investigated in this study using experimental records obtained from a cantilever steel frame specially constructed to represent a variety of structures susceptible to the HSI phenomenon. This study aims to develop and evaluate artificial neural network (ANN) models capable of representing subjects in the passive condition of HSI using only simple anthropometric parameters. Two models—Nonlinear Auto-Regressive with eXogenous input (NARX) and MultiLayer Perceptron (MLP) —are implemented and compared with a conventional Mass-Spring-Damper (MSD) model. The results show that the ANN models significantly outperform the MSD model, achieving lower Normalized Mean Square Error (NMSE) values both in time-response prediction (20.23% for NARX and 25.07% for MLP vs. 30.19% for MSD) and frequency-response prediction (16.00% for NARX and 17.05% for MLP vs. 26.01% for MSD). These findings demonstrate that the proposed ANN-based models can predict the dynamic response of individual subjects using only simple anthropometric parameters such as mass and height. This approach provides a practical and efficient tool for modeling HSI in civil engineering applications.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2025.1648231</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2025.1648231</link>
        <title><![CDATA[Comprehensive analysis of a single-story single-bay RC frame with varied reinforcement detailing]]></title>
        <pubdate>2025-08-26T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Ammar T. Al-Sayegh</author>
        <description><![CDATA[This study examines various reinforcement detailing approaches in Single-Story-Single-Bay (SSSB) reinforced concrete (RC) frames using the design tool SAP 2000 and nonlinear finite element analysis (NLFEA) with ABAQUS. A finite element model of the SSSB was developed in ABAQUS, adjusted based on experimental data from prior tests. The Concrete Damaged Plasticity (CDP) model simulated the behavior of concrete, while steel reinforcement bars were modelled as bilinear elastoplastic materials. After calibration, the peak lateral load and displacement values from the FEA models closely matched experimental results. The Control Model (CM) served as a basis for new models: (i) Half Diameter of Stirrups in the Beam (HDB), (ii) Half Diameter of Stirrups in both Beam and Columns (HDBC), and (iii) Double Spacing of Stirrups in Beam and Columns (DSBC). This analysis evaluated the effect of key design parameters, specifically the transverse reinforcement ratio (ρt), on SSSB’s load-carrying capacity. Results showed HDB had a 10.2% increase in lateral load compared to CM, while HDBC and DSBC demonstrated decreases of 15.8% and 15.5%, respectively, relative to experimental values.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2025.1612575</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2025.1612575</link>
        <title><![CDATA[Responsible AI in structural engineering: a framework for ethical use]]></title>
        <pubdate>2025-07-11T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Vagelis Plevris</author><author>Haidar Hosamo</author>
        <description><![CDATA[The integration of Artificial Intelligence (AI) into structural engineering holds great promise for advancing analysis, design, and maintenance. However, it also raises critical ethical and governance challenges—including bias, lack of transparency, accountability gaps, and equity concerns—which are particularly significant in a discipline where public safety is paramount. This study addresses these issues through eight fictional but realistic case studies that illustrate plausible ethical dilemmas, such as algorithmic bias in predictive models and tensions between AI-generated recommendations and human engineering judgment. In response, the study proposes a structured framework for responsible AI implementation, organized into three key domains: (i) Technical Foundations (focusing on bias mitigation, robust validation, and explainability); (ii) Operational and Governance Considerations (emphasizing industry standards and human-in-the-loop oversight); and (iii) Professional and Societal Responsibilities (advocating for equity, accessibility, and ethical awareness among engineers). The framework offers actionable guidance for engineers, policymakers, and researchers seeking to align AI adoption with ethical principles and regulatory standards. Beyond offering practical tools, the study explores broader theoretical and institutional implications of AI, including risks associated with model drift, the need for lifecycle oversight, and the importance of cultural and geographic adaptability. It also outlines future challenges and opportunities, such as incorporating AI ethics into engineering education and considering the ethical impact of emerging technologies like quantum computing and digital twins. Rather than offering prescriptive answers, the study aims to initiate an essential dialogue on the evolving role of AI in structural engineering, equipping stakeholders to manage its benefits and risks while upholding trust, fairness, and public safety.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2025.1618329</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2025.1618329</link>
        <title><![CDATA[Comparative study of NLFE models for simulating settlement-induced damage in masonry façades: macro- and simplified micro-models]]></title>
        <pubdate>2025-06-09T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Alfonso Prosperi</author><author>Michele Longo</author><author>Paul A. Korswagen</author><author>Giorgia Giardina</author><author>Jan G. Rots</author>
        <description><![CDATA[Damage assessment for masonry structures subjected to settlement is crucial for ensuring structural safety, guiding repairs, and preserving the built environment. Non-linear finite element modelling offers an effective approach for this purpose, though balancing model complexity, computational cost, and predictive reliability remains a key challenge. This study addresses the absence of a systematic comparison between macro- and simplified micro-modelling strategies for such analyses, clarifying their respective strengths, limitations, and sensitivity to key parameters. The performance and accuracy of semi-coupled NLFEM models are compared in simulating the response of a 1/10th scaled masonry façade under settlement, available from prior research. The two approaches considered are: simplified micro-modelling, where bricks are represented as expanded blocks with non-linear interfaces for mortar joints and their contact edges, and macro-modelling, where masonry is homogenised into an equivalent orthotropic composite material. The macro-models employ two well-established constitutive models, the Total Strain Rotating Crack Model (TSRCM) and the Engineering Masonry Model (EMM), to capture the non-linear cracking behaviour of masonry. Sensitivity analyses assess the influence of base interface models and the interface’s tangential stiffness. The results show how the selection of the modelling approach depends on the analysis objective: The macro-model with the Engineering Masonry Model best predicts damage severity, deviating by only 10% from the experiment, further improved by calibrating the minimum head-joint tensile strength. While all models yield similar predictions for vertical displacements of the façade, the TSRCM better captures overall and horizontal displacements, whereas the simplified micro-model more accurately represents the crack pattern. The EMM-based macro-models are the most computationally efficient, with TSRCM requiring 1.5 times the CPU time of EMM, and the micro-model requiring twice as much. The analysis also shows that the TSRCM-based macro-model is more sensitive to variations in the type of base interface models and base interface tangential stiffness, convergence criteria, incremental-iterative procedure, and analysis settings, whereas the EMM macro-model and the simplified micro-model are less affected. By identifying the strengths and limitations of each modelling approach, this study supports informed modelling choices for a more reliable assessment of settlement damage, contributing to the effective protection of existing masonry structures.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2025.1565348</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2025.1565348</link>
        <title><![CDATA[Research on a risk assessment model for dense urban cable channels based on fuzzy mathematics]]></title>
        <pubdate>2025-04-23T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Yongjie Nie</author><author>Daoyuan Chen</author><author>Shuai Zheng</author><author>Xiaowei Xu</author><author>Xilian Wang</author><author>Zhensheng Wu</author>
        <description><![CDATA[With the acceleration of urbanization, the safe and stable operation of dense urban cable channels is of great importance to the guarantee of urban power and communication systems. Cable channels face many sources of risk that bring great challenges to urban power supplies. Most existing risk assessment methods are based on accurate mathematical models, which require clear and deterministic boundaries of assessment indicators. These methods have difficulty in dealing with the fuzziness and uncertainty of cable channel risk factors, such as the challenge of determining the degree of aging of cable insulation or the degree of influence of external environmental factors that cannot be simply quantified. This paper presents a risk assessment model of a dense urban cable passage based on fuzzy mathematics. The model combines a membership function with a fuzzy comprehensive evaluation method to analyze and classify the risk factors of a dense urban cable passage. Eight risk factors were identified, including external damage, facility defects, and non-standard cable laying, and the importance of each factor was evaluated by constructing a membership matrix based on historical data and expert scoring methods. A typical dense cable trench and cable tunnel in actual operation in a region of China Southern Power Grid are analyzed, and the risk level is calculated by MATLAB 2021a programming. The results show that the model can effectively assess the level of risk and clearly show the impact of individual risk factors on the overall risk. For example, in the cable trench risk assessment, the model accurately identifies that external damage and cable overheating risk factors lead to moderate risk, and the remaining six factors are low risk. In the cable tunnel assessment, the corresponding risk level of each risk factor is also accurately determined. This indicates that the evaluation method based on fuzzy mathematics can not only quantify the uncertainty of risk factors but also improve the rationality of the evaluation results and provide a scientific decision basis for the safety management and maintenance of cable channels. The model has significant advantages over traditional evaluation methods.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/fbuil.2025.1561429</guid>
        <link>https://www.frontiersin.org/articles/10.3389/fbuil.2025.1561429</link>
        <title><![CDATA[Geometric characterization of locally corroded surfaces in steel bridge girders]]></title>
        <pubdate>2025-04-16T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Tao Zhang</author><author>Michael Vaccaro</author><author>Arash Zaghi</author><author>Amvrossios Bagtzoglou</author>
        <description><![CDATA[The aging of steel bridge girders is often compounded by corrosion at girder ends due to leaking deck joints. With 6.8% of U.S. bridges in poor condition, there is an urgent need for accurate yet efficient methods to assess the residual load-bearing capacity of corroded girders. Traditional assessment methods often represent corrosion as uniform section loss or rely on simplified surface representations, compromising the accuracy of the residual capacity estimation. To address these limitations, this paper proposes a novel approach for characterizing the geometry of locally corroded steel surfaces by decomposing the corroded region into high-frequency (fine surface textures) and low-frequency (global shape) components using multilevel Lanczos filters. Validated using 3D scans collected from a 57-year-old in-service bridge, our case study shows that each high-frequency component can be modeled as a stationary random field using a Hole-Gaussian autocorrelation function, with correlation lengths inversely proportional to the cutoff frequencies of the Lanczos filters. The low-frequency component is accurately characterized by a bivariate Lagrange polynomial fitted via a 4 × 4 coefficient matrix, with average volume errors of less than 1% and normalized root mean square errors under 10% for most surfaces. The technique results in a manage set of parameters that can be used to investigate the effects of corrosion damage on the behavior of corroded steel members.]]></description>
      </item>
      </channel>
    </rss>