Asian Journal of Civil Engineering最新文献

Generation of waste tire increases with end-of its life. This scenario made the researchers to explore the feasibility of reusing and recycling the waste tire as an alternative material. Recent literatures mainly focus on the engineering properties of used tires alone or their behaviour when mixed with soil. To understand the research towards reuse/recycle of waste tire, a bibliometric study has been carried out to report a comprehensive and detailed bibliometric network mapping and evaluation of research progress connected to the utilization of used tires in geotechnical application. For the last two decades, it has been systematically documented through the Dimensions database. To understand the influence of publications, affiliations, journals, countries, authors, and keywords etc.in this field of research, the statistical analysis has been carried out. By using a bibliometric mapping tool, the evolving pattern of authors’ research themes and collaboration structures were examined. This bibliometric study findings revealed that there have been a significant number of publications and influence of authors to this studied topic in the recent two decades, as well as an increase in authors’ collaboration. Moreover, the objective is extended to explore the use of waste tire as geo-material to its use in geo-engineering practices.

The proliferation of Artificial Intelligence (AI) in Structural Health Monitoring (SHM) has catalyzed a paradigm shift from traditional, feature-based damage detection to end-to-end, data-driven methodologies. While Deep Learning (DL) models, particularly Convolutional Neural Networks (CNNs), have demonstrated remarkable efficacy, the advent of Transformer architectures presents a new frontier with unparalleled capabilities for sequence modeling. However, a direct comparative analysis of these architectures on a standardized experimental benchmark, coupled with a deep investigation into their decision-making processes, remains a critical research gap. This study addresses this void by conducting a comprehensive investigation using a publicly available experimental dataset from a six-storey laboratory shear building. We develop, train, and evaluate two distinct DL models: a lightweight one-dimensional CNN (Fast CNN) and a state-of-the-art Transformer-based model (Fast Transformer). Both models are tasked with directly classifying the structural state (undamaged vs. damaged) from raw accelerometer time-series data. Performance evaluation based on standard metrics reveals that both models achieve exceptional accuracy, with the Fast CNN reaching 99.44% and the Fast Transformer reaching 98.87% on validation datasets. This work’s core contribution lies in applying Explainable AI (XAI) techniques, including Integrated Gradients and saliency mapping, to deconstruct these models’ “black box” nature. Our analysis reveals a non-intuitive yet consistent finding: both the CNN and the Transformer primarily focus on the vibration signature of the base sensor (Sensor 1) to detect damage located at the fourth storey. This suggests the models have learned to identify damage through their influence on the structure’s global dynamic response as reflected at their boundary conditions. Furthermore, XAI reveals distinct operational strategies: the CNN acts as a highly localized feature detector, whereas the Transformer leverages its self-attention mechanism to weigh a broader spatiotemporal context. This paper provides a rigorous benchmark for modern DL architectures in vibration-based SHM and tells a technical story of how interpretable AI can uncover novel, physically meaningful damage detection strategies, enhancing trust and guiding future development of intelligent monitoring systems.

This study investigates the effects of incorporating fly ash (FA) and silica fume (SF) into concrete and evaluates the predictive accuracy of machine learning models such as Backpropagation Neural Network (BPNN), Random Forest Regressor (RFR), and Gradient Boosting Regressor (GBR), on compressive strength. Optimal performance was achieved with 50–60% FA and 8–10% SF, reaching strengths above 76 MPa at 90 days, while 100% FA with 10% SF reached 71.13 MPa at 90 days versus 27.6 MPa at 14 days. Among all models, GBR showed the best accuracy (R² = 0.996, MSE = 0.578, MAPE = 0.941%), with SHAP and Partial Dependence analyses confirming curing time as the most influential factor, followed by %SF and %FA. Perturbation analysis confirmed GBR’s robustness to input variation, and monotonicity analysis revealed a strong positive trend between curing time and strength (Spearman correlation = 0.9245), confirming GBR’s suitability for strength prediction and mix optimization.

While several studies have previously explored the prediction of compressive strength in geopolymer concrete, many suffer from limitations in feature selection, model generalizability, and prediction accuracy. This invention aims to enhance the prediction process by employing advanced machine learning algorithms capable of capturing complex, non-linear relationships between mix design parameters and compressive strength outcomes. To realize this objective, a dataset consisting of 276 geopolymer concrete mixes and their corresponding 28-day compressive strength values was compiled. Input features were selected based on two key criteria: their proven relevance in prior literature and their statistical significance in model performance. Multiple regression models—including Linear Regression, Decision Tree, Random Forest, Gradient Boosting, XGBoost, and NGBoost—were implemented and evaluated. Through trial-and-error, optimal hyperparameters such as the number of training epochs and k-fold values for cross-validation were determined. Model performance was assessed using standard evaluation metrics (R, RMSE, MAE, MSE), and further validated via score-based analysis. The model’s adaptability was tested using an independent secondary dataset. The results confirm that the NGBoost model achieved the most accurate predictions among all tested models, outperforming traditional approaches in both accuracy and consistency. This invention offers a scalable and reliable solution for predicting compressive strength, significantly reducing the need for physical trial mixes and enabling efficient, data-driven mix design in geopolymer concrete applications.

The incorporation of deep learning (DL) methodologies such as Neural Networks, Convolutional Neural Networks (CNNs), and CNNs-based hybrid AI systems, has tremendously shifted the paradigm in the field of structural retrofitting. This review analyses the architectural frameworks, practical implementations, and the structural safety measures undertaken using DL models aimed at improving the performance and cost efficiency in retrofitting techniques. Additional focus areas include damage identification, performance assessment of treated structures, and retrofitting design optimisation. The review critically assesses the data sufficiency, model training steps, and validation processes within the scope of civil engineering to deploy DL driven models. Clearly, further work is warranted with respect to sparsity of data, the ‘black box’ nature of the models, high computational costs, and absence of uniform benchmark criteria. Interdisciplinary approaches—combining civil engineering, data science, and legal policy—are essential to mitigate these challenges and fully exploit AI-enhanced capabilities for retrofitting. This paper will serve as a single point of reference for anyone intending to research or practically implement intelligent, adaptable, and safety-oriented retrofitting strategies.

Nowadays, architectural requirements affect structural design investigations. On the other hand, the pounding effect is one of the crucial effects between two adjacent high-rise buildings under seismic load. Because shear walls experience higher stresses at their ends, end shear walls alleviate these stresses and enhance the effect of shear walls in high-rise buildings. This study aimed to evaluate the impact of end shear walls on the seismic pounding between two adjacent 20-story reinforced concrete buildings subjected to seven far-field seismic records by nonlinear time history analysis. Also, the distance between the two buildings is considered zero. The inclusion of end shear walls was found to significantly reduce seismic pounding effects. Specifically, notable reductions were observed in average pounding displacements and rotational accelerations in the horizontal (X) direction. Average pounding drifts in the X-direction decreased by up to 26%, while average pounding accelerations in the X-direction were reduced by up to 9%. Similarly, pounding accelerations in the vertical (Z) direction and vertical pounding rotations were also substantially reduced. These findings highlight the effectiveness of end shear walls in mitigating seismic pounding and improving the overall seismic performance of adjacent reinforced concrete high-rise buildings subjected to far-fault ground motions.

This research reports a laboratory study on the optimal levels of vitrified Polish waste (VPW) and ground granulated blast furnace slag (GGBS) as partial substitutes for cement to examine the strength properties of concrete. Ordinary Portland cement was partially substituted with 5%, 10%, 15%, and 20% mixtures of vitrified polish waste and ground granulated blast-furnace slag (GGBFS). The water-to-cementitious materials ratio was consistently set at 0.38 for all mixtures. The concrete’s strength qualities were assessed using compressive testing, strength testing, splitting tensile strength testing, and flexural strength testing. The compression strength test was executed at 7 and 28 days of curing, while the split tensile strength and flexural strength tests were conducted on M30, M35, and M40 grade concrete. The mix proportions for M30, M35, and M40 are 1:1.615:3.427, 1:1.50:3.25, and 1:1.40:3.15, respectively. The test findings demonstrated that the compressive strength, split tensile strength, and flexural strength of concrete mixtures incorporating GGBFS and VPW enhance with the increasing proportions of GGBS and VPW. A multilayer perceptron (MLP) neural network was used to evaluate concrete strength, and the predicted results were very similar to the actual measurements. The findings demonstrate that an optimal level of 15% GGBFS and VPW relative to the total binder content yields no further enhancement in compressive strength, split tensile strength, or flexural strength with additional GGBFS and VPW.

This study investigates the optimal design of counterfort retaining walls through the application of a Differential Evolution (DE) algorithm. A typical counterfort retaining wall comprises four fundamental components: stem, toe, heel, and counterfort. By treating the dimensions of these elements and the associated reinforcements as design variables, the optimal design process identifies the most cost-effective dimensions while adhering to the various constraints. The DE algorithm, a population-based optimization technique similar to Genetic Algorithms, distinguishes itself through its unique methodologies for crossover, mutation, and population updating. The construction cost of a retaining wall primarily encompasses the expenses for concrete, reinforcement steel, and formwork. In this study, the wall geometry was optimized using the DE algorithm, with the optimization framework implemented in MATLAB software. The computed results were compared with the recommended values for different wall heights. To ascertain the optimal combination of feasible design variables, objective functions were employed, contingent on the design variable values. This investigation utilized 12 design variables and 12 design constraints to optimize the objective function. Counterforts are incorporated to enhance the stability of the main wall, with a minimum thickness defined to ensure compliance with the specified lower limit values. Furthermore, the objective function was formulated for wall heights of 6, 7, 8, 9, and 10 m above ground level using the DE algorithm. The results demonstrate that the optimization of counterfort retaining walls can significantly reduce construction costs.

Anchor bolts of the column base are important in ensuring the stability and safety of pre-engineered steel frames. The reliability of anchor bolts is influenced by various random factors, including geometric dimensions, material properties, loads, and particularly the corrosion status. This study aims to evaluate the reliability of steel column anchor bolts in marine environments where metal corrosion is a dominant factor. A deterministic model for calculating the safety condition of anchor bolts is built and then developed into a stochastic model by considering geometric dimensions, material properties, loads, and corrosion status as random variables. The safety probability (reliability) of the anchor bolts is evaluated through Latin hypercube sampling and Monte Carlo simulation. The research results indicate that the safety probability of anchor bolts in a marine atmospheric environment tends to decrease over time. Specifically, for Model 1, the safety probability decreases from 94.26% after 10 years, 87.96% after 15 years, 63.66% after 25 years, and only 6.78% after 50 years. Model 2 exhibits a slower decline, with the safety probability decreasing from 96.2% after 10 years to 92.4% after 15 years, 80.46% after 25 years, and 33.25% after 50 years. Meanwhile, Model 3 shows a higher probability of maintaining safety, with a likelihood of decreasing from 96.82% after 10 years, 94.11% after 15 years, 86.29% after 25 years, and 52.14% after 50 years. Although the structure met the safety requirements according to the initial model, the results of the random analysis showed that the risk of damage increased due to the influence of random variables, especially metal corrosion in the marine environment.

Concrete, as the most extensively used construction material, contributes significantly to environmental degradation due to the high consumption of natural resources and carbon dioxide emissions. To foster sustainable development, this study investigates the incorporation of alternative materials Fly Ash and Rice Husk Ash as partial replacements for cement in M25 grade concrete. The research evaluates both the compressive strength and workability of these modified mixes. Furthermore, machine learning techniques, including XGBoost, Random Forest, and Support Vector Machine (SVM), were employed to predict the compressive strength based on experimental data. A user-friendly prediction system was developed to enable analysis by selecting either Fly Ash or Rice Husk Ash as the replacement material. Among the models used, XGBoost outperformed the others in terms of predictive accuracy, achieving the highest (hbox {R}^{2}) score and lowest error metrics. The results indicate that these alternative materials can enhance concrete properties at specific replacement levels, and that machine learning models, particularly XGBoost, offer accurate and efficient predictions. This study underscores the potential of integrating sustainable materials with data-driven modeling for eco-friendly and performance-optimized concrete mix designs.