Accurate prediction of long-term settlement under complex traffic loads remains a pivotal challenge for the safety and durability of transportation infrastructure. While explicit models for settlement calculation have been advanced to handle general three-dimensional stress states, a major practical hurdle lies in determining reliable model parameters. Parameter inversion offers a viable path to high-fidelity estimates, yet conventional inversion techniques often fall short in accuracy. Ensemble learning methods can improve data precision by synthesizing predictions from multiple intelligent models; however, commonly used soft voting strategies tend to overlook both systemic bias across base models and the distinct contribution of each predictor. To address this, this study proposes a Particle Swarm Optimization-Back Propagation Neural Network-Random Forest (PSO-BPNN-RF) inversion model that incorporates a refined soft voting method. Coupling this inversion model with a three-dimensional explicit settlement calculation framework for complex traffic loading enables high-precision parameter identification. The proposed approach is subsequently applied to parameter inversion for an explicit model of the Xiaoshan Airport taxiway, demonstrating strong generalization capability and superior accuracy.

This study developed an integrated numerical and data-driven framework for predicting the free-vibration characteristics of thin-walled curved box-girder bridges, a widely used yet mechanically complex structural form in modern bridge engineering. A computationally efficient one-dimensional thin-walled beam finite element method (FEM) was implemented in MATLAB, explicitly incorporating torsional, distortional, and warping effects, which are critical for accurately representing the dynamic behavior of curved girders. The proposed model was rigorously validated against detailed ANSYS shell-element simulations and published experimental data, demonstrating close agreement in both natural frequencies and corresponding mode shapes. A systematic parametric study was conducted to evaluate the influence of key design variables, including curvature radius, span length, boundary conditions, diaphragm layout, and cross-sectional geometry, on the first three modal frequencies. This process generated a comprehensive dataset, which then served as the basis for developing multivariate linear regression models. The resulting models yielded explicit predictive equations with excellent accuracy, with R² values exceeding 0.999 and root mean square error (RMSE) not greater than 0.31 Hz. The principal contribution of this work lies in its hybrid methodology, which effectively combines physics-based FEM with data-driven regression modeling. This dual approach not only deepens mechanistic insight but also delivers practical utility. The derived closed-form expressions offer engineers an efficient preliminary design tool, significantly reducing the dependency on computationally intensive finite element simulations during early design phases.

Young’s modulus is one of the geomechanical properties used in the design phase of different rock engineering applications. Difficulties in sample preparation and the high cost of experimental equipment lead researchers to perform studies on the estimation of Young’s modulus. However, previous studies on this topic are often limited in terms of rock type and/or number of data. Therefore, a comprehensive database covering a wide variety of rock types is needed for reliable estimation of Young’s modulus. To address this deficiency, a large database including Schmidt rebound value, uniaxial compressive strength, and porosity was compiled from the literature to derive equations and models for Young’s modulus estimation. Multivariate regression analysis and adaptive-neuro-fuzzy inference system (ANFIS) were used to predict Young’s modulus of rock materials. The reliability of the derived multivariate regression equations was verified using F- and t-tests, and the equations were found to be statistically reliable. The prediction pperformance of multivariate regression analysis and neuro-fuzzy models was compared using root mean square error (RMSE) and mean absolute percentage error (MAPE). The ANFIS models yielded considerably lower absolute prediction errors than the regression models. Thus, the neuro‑fuzzy method provided significantly higher prediction accuracy than the multivariate regression approach. The results indicated that the neuro-fuzzy model constructed in this study using the uniaxial compressive strength (σ_c), Schmidt rebound value (R), and porosity (n) as input parameters yielded the best predictions of E when compared to those predicted in some previous studies.

The construction industry faces the challenge of decarbonization. Integrating manufacturing principles and Artificial Intelligence (AI) offers a promising pathway to reduce CO₂ emissions, specifically by integrating CO₂-emission variables into AI-driven production schedules. However, transparency to users is essential, as human users remain ultimately responsible for production outcomes. This requirement can be met through Explainable AI (XAI), which aims to provide transparency for end users. However, defining an appropriate XAI approach requires understanding problem- and industry-specific variables. Using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology, this study examines the state of the art in XAI literature to identify research gaps and formulate actionable recommendations. The study provides insights for developing an XAI approach to support the decarbonization of housing manufacturing explicitly. The key findings highlight the need for user-centric and industry-specific frameworks and the importance of clearly defining the XAI-AI relationship. Finally, this research synthesizes these findings into a roadmap to guide future research on XAI for the decarbonization of housing manufacturing.

This preliminary study introduces and evaluates a router-based multi-agent framework for automated foundation design calculations through intelligent task classification and expert selection. Three configurations were assessed: single-agent processing, multi-agent designer-checker architecture, and router-based expert selection, using baseline models including DeepSeek R1, ChatGPT 4 Turbo, Grok 3, and Gemini 2.5 Pro. Initial evaluation on 27 test cases with triple-trial execution shows promising performance: the router-based system achieved 95.00% for shallow foundations and 90.63% for pile design, representing improvements of 8.75 and 3.13 percentage points over standalone Grok 3, respectively, and outperforming conventional workflows by 10.0–43.75 percentage points. Grok 3 demonstrated superior standalone performance, indicating enhanced large language model (LLM) mathematical reasoning capabilities. The dual-tier classification framework successfully distinguished foundation types, enabling appropriate analytical approaches. While these preliminary results suggest router-based multi-agent systems as a promising approach for foundation design automation, the limited sample size necessitates comprehensive validation on larger, more diverse datasets before deployment recommendations. Safety–critical requirements necessitate continued human oversight in professional applications. This work provides a methodological foundation for future research in AI-assisted geotechnical engineering.

In response to the housing shortage in Canada, particularly in northern and remote communities, modular houses have emerged as a viable solution. These prefabricated structures offer speed, cost-efficiency, and flexibility. To enhance the durability and functionality of these modular homes, innovative construction techniques are being explored. A new bolted connection, utilizing high-strength long bolts, has been introduced for hollow structural sections (HSS), which can be designed using regression models trained by an experimentally validated finite element model (FEM). This study employs machine learning techniques, including neural networks, genetic regression, and decision trees, to detect the failure mode and predict the ultimate moment capacity of HSS moment connections under monotonic loading. A nonlinear validated FEM was developed using LS-DYNA software, and a matrix of 240 FEMs was generated to train and test the machine learning models, including a range of various design parameters such as the extended plate thickness, number of bolts, bolt arrangement, and bolt diameter. Five machine learning algorithms were used for classification and regression learning, with hyperparameter optimization applied to enhance their accuracy. Mathematical formulas for predicting the ultimate moment capacity were developed using genetic algorithm-based symbolic regression, trained on 70% of the matrix parameters. These formulas were then validated and tested with the remaining 30%, demonstrating high accuracy. Findings illustrate the efficiency of machine learning approaches for precisely predicting the ultimate capacity and failure patterns of bolted connections, highlighting their promise as reliable tools in design, complementing both experimental and analytical methods.

Accurate prediction of compressive strength is essential for improving the performance and durability of Engineered Cementitious Composites (ECC) in construction applications. Traditional methods often fall short in accounting for the complex interactions between material properties, such as fiber type, matrix composition, and curing conditions. To address this challenge, this study presents an advanced ensemble learning framework based on a dataset of 313 ECC samples characterized by 18 key features. The ensemble model integrates three base learners, namely Random Forest (RF), Gradient Boosting Decision Trees (GBDT), and Support Vector Regression (SVR), along with a meta-learner selected from ten candidate models. The proposed ensemble model demonstrates significantly higher prediction accuracy compared to conventional approaches. The results show that the ensemble model achieves a coefficient of determination (R²) of 0.896, a root mean square error (RMSE) of 5.734, and a mean absolute error (MAE) of 4.505, substantially outperforming individual models. Among the evaluated meta-learners, Lasso Regression was identified as the optimal choice. Its regularization capability effectively mitigated overfitting and enhanced generalization, leading to a notable improvement in the final predictive performance of the stacking framework. Furthermore, SHapley Additive exPlanations (SHAP) and Partial Dependence Plots (PDP) were employed for model interpretability and visualization. The analysis reveals that factors such as fiber elastic modulus, silica fume content, and fiber volume fraction significantly contribute to the enhancement of ECC compressive strength. This model provides practical insights for optimizing the design and application of ECC materials.

Structures are prone to damage. Identification and localization of damage at its initiation stage are extremely helpful for ensuring safety, economy, and operational benefits. A machine learning (ML) approach is helpful for this purpose, provided that high-quality and sufficient damage signals are available from a variety of locations across the structure. Such signals, generated at damage initiation, are frequently obtained using a non-destructive testing (NDT) technique, such as acoustic emission (AE), which employs the pencil lead break (PLB) method. However, PLB is not possible at inaccessible locations of the structure. Therefore, synthetic experimental signals are required for such locations. Accordingly, the present study aims to generate synthetic experimental signals from numerically simulated AE signals using an artificial neural network (ANN). Here, parameters from numerical signals serve as inputs, and the corresponding parameters of experimental signals are outputs. The most relevant signal parameters are determined using the Pearson correlation coefficient (PCC). The developed model is found to perform very well, achieving an accuracy of around 99%.

Landslides, as prevalent geohazards, exhibit complex and nonlinear evolutionary dynamics, frequently triggered by the coupled effects of reservoir water-level fluctuations and extreme precipitation. Such events are often characterized by abrupt, step-like deformation, posing significant challenges for accurate long-term displacement forecasting. To address the limitations of conventional models, including poor generalization, low robustness to chaotic disturbances, and insufficient capacity for nonlinear representation, we propose a hybrid deep learning framework termed GRU–TimeMixerKAN. This model synergistically integrates the sequential modeling capabilities of Gated Recurrent Units (GRU), the temporal-feature decoupling mechanism of TimeMixer, and the high-order nonlinear approximation power of the Kolmogorov–Arnold Network (KAN). Enhancements such as differencing-based detrending, sliding-window sampling, and automated hyperparameter optimization via Optuna are incorporated to further refine performance. The efficacy of the proposed model is evaluated using long-term displacement monitoring data from three reactivated reservoir landslides in the Three Gorges Reservoir Area (TGRA), with its performance benchmarked against nine state-of-the-art deep learning baselines. The results demonstrate that GRU–TimeMixerKAN consistently achieves the lowest Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), alongside competitive Symmetric Mean Absolute Percentage Error (sMAPE) and the highest Coefficient of Determination (R²). These findings underscore its superior capability in capturing displacement trends, responding to sudden changes, and generalizing robustly across diverse landslide cases. This study presents an effective and scalable methodology for advancing intelligent early warning and prediction systems for landslides.

Maintaining the structural integrity of reinforced concrete bridges necessitates the timely and accurate detection of surface defects. Conventional inspection methodologies remain labor-intensive, inherently subjective, and susceptible to human error, driving the need for automated assessment frameworks. This study introduces a multi-label defect classification model tailored for reinforced concrete bridge inspection, engineered to process imagery consistent with prevailing bridge inspection standards. The proposed framework is designed to simultaneously identify multiple co-occurring defects within a single image, addressing the practical reality of overlapping deterioration mechanisms. Leveraging the open-source Concrete Defect Bridge Image Dataset (CODEBRIM), three distinct ImageNet-pretrained deep neural network architectures were subjected to systematic hyperparameter optimization and fine-tuning to enhance classification performance across bridge-relevant defect categories. Beyond achieving high per-class accuracy, the optimized model attained a subset accuracy of 84.0% and a micro-averaged F1-score of 85.2% on a held-out test set, signifying robust recognition of overlapping distress conditions. Furthermore, evaluation on a synthetically generated dataset validated the model's generalization capacity under domain shift. The findings demonstrate that the proposed framework effectively supports automated defect documentation and holds significant potential for enhancing the objectivity and efficiency of bridge condition assessment protocols.