Asian Journal of Civil Engineering最新文献

The dynamic analysis of tall buildings has been studied in the literature, ignoring rotational inertia and the local shear deformation mechanism. Using both the continuous method and the transfer matrix method, this paper presents an analytical and numerical solution for the free vibration analysis of tall buildings modeled as Double-Beam systems Timoshenko type. The continuous model used accounts for all types of bending and shear behavior, both global and local, and directly introduces the rotational inertia of the walls. This results from the parallel coupling of two Timoshenko beams, considering three kinematic fields. The derivation of equilibrium equations, constitutive laws, and boundary conditions is obtained through an energetic approach applying Hamilton’s principle. The proposed analytical solution addresses the particular case of tall buildings with uniform properties subjected to a uniformly distributed load along their height. The proposed numerical method allows solving the general case of tall buildings with variable properties and arbitrary load patterns. It is observed that the new local shear deformation mechanism has a greater influence on the result's accuracy compared to rotational inertia. Numerical applications validate the proposed methods and demonstrate acceptable accuracy, suggesting their use by both the academic community and practicing engineers. Furthermore, the formulation of the proposed analytical and numerical methods can be easily extrapolated to various applications in mechanical, naval, and aerospace engineering, requiring only the recalculation of equivalent stiffnesses for each specific case.

Building Information Modeling (BIM) fills the gaps of traditional methods, reducing design errors in road infrastructure projects. Its application aims to strengthen collaboration and facilitate the exchange of data between different stakeholders, which is a major asset in the management and optimization of road projects. During the preliminary design phase, choosing the best alternative is a crucial step, as it directly influences the quality and sustainability of the final infrastructure. The literature review revealed that existing methods were mainly based on the use of two-dimensional cartographic documents, thus limiting the visualization and analysis of the different possible options. This article proposes an innovative approach highlighting the use of INFRAWORKS, a 3D tool for projecting different alternatives in a realistic environment. The main objective of this research is to determine the optimal road alignment according to carefully selected criteria, for the renewal of a road section vulnerable to flooding, connecting the city of Sidi Belattar to the RN 90, located on the left bank of the Chellif, in Algeria. In order to structure and solve the problem of selecting alternatives, the analysis of multi-criteria decision support methods (MCDM) was adopted, combining two complementary methods: TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution), used to rank the alternatives, and ELECTRE III (Elimination and Choice Translating Reality), allowing prioritize them according to their relevance. The results of the ranking of the alternatives were consistent, recommending the Second Alternative as the optimal solution to replace the vulnerable section of the existing alignment. Ultimately, this approach constitutes a significant advance by integrating BIM and MCDA, thus illustrating an innovative approach to improve the planning and design of road infrastructures from their early stages of development.

This study investigates the potential of utilizing textile sludge and glass powder as sustainable materials in the production of environmentally friendly concrete paving blocks. The research aimed to evaluate the feasibility of incorporating varying percentages of textile sludge (0%, 10%, 20%, 30%, and 40% by weight of fine aggregate) and glass powder (0%, 5%, 10%, 15%, and 20% by weight of cement) into the concrete mix, analyzing its effects on the mechanical properties, workability, and durability of the paving blocks. The prepared mix samples were subjected to comprehensive testing, including compressive strength, flexural strength, tensile splitting strength, water absorption, and abrasion resistance, conforming to relevant standards. Results indicated that the addition of textile sludge and glass powder improved the workability of the concrete mix, with optimal mechanical performance achieved at a composite mix of 20% textile sludge and 15% glass powder. This formulation resulted in a compressive strength of 44.34 MPa after 28 days, meeting the standards for high-performance paving blocks. To enhance predictive capability and optimize mix design, a machine learning-based performance model was developed using the XGBoost regression algorithm. The model demonstrated high predictive accuracy (R² >0.95) across multiple target variables, including compressive, flexural, and tensile strength, as well as water absorption. This data-driven approach enabled rapid performance estimation of concrete mixes based on TS and GP content, reducing reliance on exhaustive laboratory experimentation and promoting intelligent, resource-efficient design decisions. Moreover, the incorporation of these industrial by-products significantly reduced the environmental impact of concrete production by minimizing carbon emissions and enhancing recyclability compared to traditional concrete blocks. Overall, the findings underscore the viability of transforming waste materials into high-performance, eco-friendly construction components. This work contributes to sustainable construction practices and effective industrial waste management. Future research should explore long-term durability, environmental life cycle assessments, and real-time ML-integrated decision support systems for broader adoption.

The shift toward sustainable building and energy conservation necessitates intelligent, data-driven strategies for selecting construction materials. This study presents a metaheuristic-driven framework for optimizing sustainable material selection in energy-conscious infrastructure projects. Drawing from the Open Materials Database, the framework applies ten nature-inspired metaheuristic algorithms—such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Grey Wolf Optimizer (GWO)—to solve a complex multi-objective problem: minimizing cost, embodied carbon, and environmental impact, while maximizing mechanical performance, durability, and recyclability. Results show the effectiveness of PSO and GWO in achieving good constraint satisfaction and convergence, while other algorithms provide various Pareto-optimal trade-offs. Visualization tools, such as radar charts and dynamic building material recommendation maps, allow for the flexibility and transparency of decisions. Low-carbon residential scenario illustration shows the applicability of the framework to a range of sustainability endpoints. The paper emphasizes the application of AI and machine learning in engineering to develop more sustainable and energy-efficient infrastructure. Future research entails integration with real-time decisions systems, Building Information Modeling (BIM), and uncertainty modeling to support practical application and resilience.

The axial performance of Cold-Formed Steel (CFS) back-to-back built-up columns was investigated through a combination of experimental testing, finite element (FE) modelling, and machine learning (ML) techniques. Six column specimens with varying web depths and flange widths were tested under axial compression. The results were validated using FE simulations developed in ANSYS. To enhance the dataset for ML modelling, a parametric study involving 60 column configurations was conducted. Predictive models, including linear regression and artificial neural networks (ANN), were employed to estimate axial deformation. The linear regression model produced a predictive equation of y = 0.9803x + 0.0115, with a high coefficient of determination (R² = 0.9907), indicating excellent predictive accuracy. Correlation analysis identified column length and yield strength as the most influential parameters. Evaluation metrics, including Mean Squared Error (MSE), Mean Absolute Error (MAE), Mean Absolute Relative Error (MARE), and Mean Squared Relative Error (MSRE), yielded average values of 0.000058, 0.005779, 0.012620, and 0.000275, respectively. The integrated framework—combining physical testing, validated FE modelling, and data-driven ML prediction—offers a robust and efficient approach for the structural assessment and design optimisation of CFS built-up columns in lightweight steel construction.

The precise estimation of the shear strength of reinforced concrete (RC) beams constructed with recycled aggregate concrete (RAC) is essential for the secure and sustainable design of structural components. The utilization of construction and demolition waste (CDW) to produce recycled aggregate concrete (RAC) is an attractive approach from both an environmental and budgetary perspective. However, this study proposes a single and novel hybrid machine learning framework to predict the shear strength of RAC beams using a dataset compiled from published experimental studies and validated numerical models. Ensemble learning techniques such as Support Vector Regression (SVR), Gradient Boosted Regression Trees (GBRT), CatBoost, Decision Tree (DT), and Bagging Regressor (BR) were developed to train models using six input features: 28-day compressive strength of concrete (fc), the percentage of recycled coarse aggregate (RCA), the effective depth of the beam cross-section (d), the width of the beam cross-section (b), the percentage of longitudinal reinforcement (rhow), the shear span to effective depth ratio (a/d) and output parameter is the shear strength of the specimen (V_test). Furthermore, evaluating model performance, we used R², RMSE, MAPE, and MAE metrics on a robust database that was divided into training (70%) and testing (30%) phases. Results show that the hybrid models outperform standalone algorithms, with the hybrid GBRT model combination achieving the highest prediction accuracy throughout both stages using R² (0.869, 0.998), RMSE, MAE, and MAPE (20.033, 12.753, and 15.598%), respectively. Additionally, Shapley Additive Explanations (SHAP) analysis was employed to determine significant input characteristics and clarify how they affect the Beam Shear Strength Prediction. The presence of the width of the beam cross-section and the shear span to effective depth ratio contributes the highest positive influence to the outcome. This study demonstrates that hybrid ML approaches can reliably capture nonlinear interactions among RAC beam variables, offering a powerful alternative to empirical formulas. Moreover, a Graphical User Interface (GUI) was developed to enable designers to effectively and economically forecast beam shear strength, and the experimental findings substantially impact the construction industry by facilitating a more accurate and reliable implementation of RAC.

Structural Health Monitoring (SHM) of bridges plays a pivotal role in sustaining infrastructure reliability and public safety. However, conventional vibration-based approaches encounter significant challenges such as susceptibility to environmental variability and heavy dependence on baseline data, which limit their effectiveness in complex operational environments. This systematic review aims to critically evaluate recent advancements in vibration-based SHM methodologies, with a focus on the integration of Artificial Intelligence (AI) and Machine Learning (ML) techniques from 2014 to 2025. A systematic literature review was conducted using Scopus as the primary database, guided by the PRISMA framework, encompassing 51 peer-reviewed journal articles published between 2014 and 2025. The findings highlight significant methodological advancements, including the application of supervised neural networks, unsupervised learning algorithms such as autoencoders, hybrid AI models integrating physics-informed neural networks (PINNs), and Bayesian approaches for uncertainty quantification. AI-driven methods demonstrated enhanced accuracy, robustness, and scalability, addressing critical limitations of conventional SHM systems. However, challenges persist, particularly in terms of computational complexity, the requirement for large labelled datasets, generalization across bridge types, and limited field-based validation. This study underscores the potential of hybrid AI approaches and identifies several research gaps. Future directions include enhanced field-based validations, integration of optimal sensor placement techniques, development of interpretable models, and predictive maintenance strategies incorporating Remaining Useful Life (RUL) estimation.

The urgent need to find sustainable alternatives to Portland cement, which emits substantial CO₂ during production, has driven research toward exploring environmentally friendly materials. Ground granulated blast furnace slag (GGBFS) and fly ash geopolymer concrete (FA-GPC) have emerged as promising alternatives due to their potential to reduce CO₂ emissions and address industrial waste disposal issues. This research paper focuses on enhancing the accuracy of predicting the compressive strength of GPC containing FA and GGBFS through efficient machine learning models: Random Forest (RF) and Decision Tree (DT). The study conducts comprehensive laboratory investigations, gathering numerous samples, and using statistical measurements such as RMSE, MAE, and R-value to evaluate the models' performance. Sensitivity analysis is performed to identify key factors influencing geopolymer concrete strength, enabling informed decisions for concrete mix design optimization. The results indicate that the decision tree model generally outperforms the random forest model in accuracy and explaining data variance, particularly with smaller datasets. However, the choice between models should consider specific requirements and dataset sizes of the problem at hand for real-world applications in the construction industry. The evaluation metrics for two regression models, RF and DT, trained on different ratios of training and testing data (70:30 and 50:50), were compared. For the 70:30 ratio, the DT model outperformed the RF model with lower error metrics (RMSE, MSE, MAE) and a higher R-squared value (R²). Similarly, for the 50:50 ratio, the DT model showed better performance than the RF model. The Decision Tree models demonstrated particularly exceptional performance on the testing data, especially with D1 achieving a perfect fit with an R2 value of 1.0.

Ensuring seismic resilience in reinforced concrete (RC) structures while maintaining construction efficiency and cost-effectiveness is a key challenge in structural engineering. This study introduces a Genetic Algorithm (GA)-based optimization framework to enhance both seismic performance and construction feasibility of RC buildings. The framework incorporates updated Algerian seismic regulations (RPA 2024) and current economic constraints. A MATLAB-SAP2000 system was developed, with MATLAB managing the optimization process and SAP2000 performing structural analysis. This integrated approach was applied to RC buildings of varying complexities (five, eight, and ten-story structures), optimizing beam and column dimensions as well as reinforcement areas, all while respecting practical construction constraints and architectural demands. Results show that the GA-based method significantly reduces construction costs and material usage without compromising seismic safety. Controlled displacements and drift ratios confirm the method’s effectiveness, demonstrating that Genetic Algorithms offer a practical and efficient tool for designing resilient, cost-effective, and constructible RC structures in seismic regions.

The increasing demand for concrete in the construction industry has significantly depleted natural resources, particularly cement and aggregates, leading to ecological degradation and increased carbon emissions. Addressing these challenges, this study investigates the potential of utilizing micro silica (MS) and ceramic tile waste (CTW) as partial replacements for cement and coarse aggregates, respectively, in OPC 43-grade concrete. The primary objective is to enhance concrete sustainability without compromising its mechanical performance. Concrete mixes were prepared with varying replacement levels: MS at 5% and 10%, and CTW at 20% and 40%. Standardized tests were conducted to evaluate compressive, split tensile, and flexural strengths at 7 and 28 days. The highest strength performance was recorded in the mix with 5% MS and 20% CTW (S5C20), which showed improvements of 10.14% in compressive strength, 11.41% in split tensile strength, and 5.58% in flexural strength compared to the control mix. EDS analysis confirmed enhanced microstructural densification due to pozzolanic activity and mechanical interlock effects. To support experimental findings, optimization models were applied using Response Surface Methodology (RSM), Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), and Fuzzy Logic, with RSM achieving the highest prediction accuracy (desirability score of 0.961). The study concludes that a combined substitution of 5% MS and 20% CTW yields the most balanced enhancement in strength and sustainability. Excessive replacement, especially at 40% CTW, results in marginal strength loss due to reduced workability and aggregate brittleness. This work highlights the dual benefit of waste valorization and structural reliability, promoting circular construction practices. Recommendations include long-term durability assessment, life cycle analysis, and pilot implementation in real construction projects to validate performance under field conditions.