Computer-Aided Civil and Infrastructure Engineering最新文献

The cover image is based on the Article A hybrid method for intercity transport mode identification based on mobility features and sequential relations mined from cellular signaling data by Fan Ding et al., https://doi.org/10.1111/mice.13229.

The cover image is based on the Article Automated quantification of crack length and width in asphalt pavements by Zhe Li et al., https://doi.org/10.1111/mice.13344.

Mobile sensing has emerged as an economically viable alternative to spatially dense stationary sensor networks, leveraging crowdsourced data from today's widespread population of smartphones. Recently, field experiments have demonstrated that using asynchronous crowdsourced mobile sensing data, bridge modal frequencies, and absolute mode shapes (the absolute value of mode shapes, i.e., mode shapes without phase information) can be estimated. However, time-synchronized data and improved system identification techniques are necessary to estimate frequencies, full mode shapes, and damping ratios within the same context. This paper presents a framework that uses only two time-synchronous mobile sensors to estimate a spatially dense frequency response matrix. Subsequently, this matrix can be integrated into existing system identification methods and structural health monitoring platforms, including the natural excitation technique eigensystem realization algorithm and frequency domain decomposition. The methodology was tested numerically and using a lab-scale experiment for long-span bridges. In the lab-scale experiment, synchronized smartphones atop carts traverse a model bridge. The resulting cross-spectrum was analyzed with two system identification methods, and the efficacy of the proposed framework was demonstrated, yielding high accuracy (modal assurance criterion values above 0.94) for the first six modes, including both vertical and torsional. This novel framework combines the monitoring scalability of mobile sensing with user familiarity with traditional system identification techniques.

Bolt loosening assessment is crucial to identify early warnings of structural degradation and prevent catastrophic events. This paper proposes an automatic bolt loosening assessment methodology. First, a novel end-to-end ensemble vision model, Bolt-FP-Net, is proposed to reason the locations of bolts and their hexagonal feature patterns concurrently. Second, an adaptive target-free perspective correction method is proposed to correct perspective distortion and enhance assessment accuracy. Finally, an iterative bolt loosening quantification is developed to estimate and refine the bolt loosening rotation. Experimental parametric studies indicated that the proposed Bolt-FP-Net can achieve excellent performance under different environmental conditions. Finally, a case study was conducted on steel bolt connections, which shows the proposed methodology can achieve high accuracy and real-time speed in bolt loosening assessment.

Surrogate-based traffic signal optimization (TSO) is a computationally efficient alternative to simulation-based TSO. By replacing the simulation-based objective function, a surrogate model can quickly identify solutions by searching for extreme points on its response surface. As a popular surrogate model, the ensemble of multiple diverse deep learning models can approximate complicated systems with a strong generalizability. However, existing ensemble methods barely focus on strengthening the prediction of extreme points, which we found can be realized by further diversifying base learners in the ensemble. The study proposes an adversarial diverse ensemble (ADE) method for online TSO with limited computational resources, comprising two stages: In the offline stage, base extractors are diversified with unlabeled data by a designed adversarial diversity training algorithm; in the online stage, base predictors are trained in parallel with limited labeled data, and the ensemble then serves as the surrogate model to search for solutions iteratively for TSO. First, it is demonstrated that the prediction accuracy on extreme points, and associated solution quality, can be constantly improved with base learners’ diversity enhanced by ADE. Case studies of TSO conducted on a four-intersection arterial further demonstrate the superior solution quality and computational efficiency of the ADE surrogate model in a wide range of traffic scenarios. Moreover, a large-scale online TSO experiment under dynamic traffic demand proves ADE's effectiveness in practical applications.

As conventional machine learning models often struggle with scarcity and structural variation of training data, this paper proposes a novel regression transfer learning framework called transferable tabular regressor (TransTabRegressor) to address this challenge. The TransTabRegressor integrates natural language processing (NLP) for feature encoding, transformer for enhanced feature representation, and deep learning (DL) for robust modeling, facilitating effective transfer learning across tabular datasets using reducing input parameters. By leveraging the NLP data processor, the framework embeds both parameter names and values, enabling it to recognize and adapt to different expressions of similar parameters. For instance, the bond strength of fiber-reinforced polymer (FRP) bars embedded in ultra-high-performance concrete (UHPC) is critical for ensuring the integrity of FRP-UHPC structures. While pullout tests are widely adopted for their simplicity to generate substantial data, beam tests provide a closer approximation to actual stress conditions but are more complex thus resulting in limited data size. As a verification, the framework is applied to predict the bond strength of FRP bars embedded in UHPC using limited beam test data. A pre-trained model is first established using 479 pieces of pullout test data. Subsequently, two transfer learning models are developed by fine-tuning on 115 pieces of beam test data, where 66 correspond to concrete splitting failure and 49 correspond to pullout failure. For comparative analysis, XGBoost and neural network models are directly trained on the beam test data. Evaluation results demonstrate that the transfer learning models achieve significantly improved prediction accuracy and generalization capability. This study significantly highlights the effectiveness of the proposed TransTabRegressor in handling data scarcity and variability in input parameters across various engineering applications.

Offshore earthquakes and subsequent tsunamis pose significant risks to many coastal populations worldwide. This paper introduces a data-driven machine learning model that synthesizes accurate 3D earthquake–tsunami fragility surfaces from randomly selected 2D fragility curves. The integration of physics-based simulations enhances the model's reliability for these specific hazards, making it a valuable tool for multi-hazard analysis in earthquake–tsunami contexts. Additionally, by shifting 2D fragility curves to represent retrofitted structural systems, the model can generate earthquake–tsunami fragility surfaces for community-level mitigation studies. While the model is demonstrated for earthquake–tsunami scenarios, its methodology architecture has the potential to contribute to other multi-hazard situations for the initial conditions in multi-hazard community resilience analysis.