Accurate and efficient assessment of structural damage in shield tunnels is essential for ensuring the safety and reliability of transportation systems. Cracks in tunnel linings are common, necessitating regular structural integrity assessments to ensure safety. Traditional modeling of such damage is often complex and time-consuming. Therefore, the objective of this study is to automate the entire process from detecting tunnel damage in images to conducting numerical analyses for shield tunnels, thereby enabling rapid assessment of structural integrity. We propose a segment-based method that updates a finite element (FE) model of shield tunnels to reflect geometric changes due to cracks, utilizing computer vision (CV) techniques and geometric analyses. Firstly, the Segment Anything Model, along with CV techniques, is used to identify the shapes and sizes of tunnel components from full and partial tunnel segment images. Then, a Dual VMamba U-Net (DVMamba-UNet) is proposed to identify cracks and provide detailed crack information, i.e., crack masks. Finally, geometric analysis is employed to develop algorithms that automatically transform coordinates and select elements within FE models, facilitating the update of geometric changes. Residual capability assessments of updated FE models are used to evaluate the structural damage and the tunnel segment condition. Two case studies are conducted to verify the effectiveness of the proposed approach and algorithms. The results show that the proposed method allows for automatic updates to the FE tunnel model based on damage detected in images through CV techniques and geometric analyses. Additionally, updated FE tunnel models representing different damage levels are developed and analyzed using numerical simulations. This approach not only proves effective in evaluating structural damage in shield tunnels but also offers potential as a data processing and model updating modules within future Digital Twin frameworks for tunnel infrastructure.

Accurate synchronization of distributed sensor measurements is essential for reliable vibration-based structural health monitoring (SHM). Wireless Internet of Things (IoT) systems, while attractive for large-scale SHM deployments, inevitably introduce unknown time lags arising from clock drift and communication delays. Conventional frequency-domain (FD) estimators and feature-based machine-learning (ML) models struggle to handle such asynchronous measurements, especially when delays are smaller than the sampling interval. To address these limitations, this paper proposed a learning-based synchronization framework that integrates a time-lag convolutional neural network with attention (TLCA) to directly estimate continuous-valued time lags from raw vibration signals, together with a resampling-based alignment strategy to correct non-integer delays. The proposed framework was validated using both simulated structural responses and field data from a wireless SHM system deployed on the Jindo Bridge. By directly learning time relationships from raw vibration signal pairs, TLCA achieves sub-millisecond accuracy and consistently outperforms conventional frequency-domain and feature-based learning methods, with about an order-of-magnitude improvement in precision. It also maintained strong robustness under increased noise and modal coupling. With efficient data-level alignment and low computational complexity of the overall framework, it can enable accurate and real-time synchronization for practical IoT-based SHM applications.

Wheel flats (WF) are a common defect in railway systems, posing risks to operational safety, passenger comfort, and the longevity of infrastructure. Existing detection methods face significant challenges, including sparse labeled data, high noise interference, and limited adaptability to complex operational conditions. To address these issues, this study introduces a semi-supervised learning workflow integrating multi-sensor data from Distributed Acoustic Sensing (DAS) and accelerometers, with a novel Graph Vector-Quantization Variational AutoEncoder (GVQVAE) as the core component. The model combines time-frequency analysis for feature extraction, a graph-based architecture for data fusion, and a vector quantization mechanism to effectively leverage both labeled and unlabeled data. Experimental results from an operational subway system demonstrate the model’s robustness and high accuracy, with an average detection accuracy of 97.08%. These findings highlight the potential of the proposed DAS-accelerometer fusion and GVQVAE model as an effective, scalable solution for enhancing WF detection in modern railway systems.

The edge recognition of mechanical faults using deep learning models requires the deployment and operation of neural networks, which consume a large amount of memory. However, edge devices have limited memory. To address the problem, a neural network micromemory control strategy is proposed. This strategy addresses the memory resource constraints through process quantization and byte indexing while maintaining the model structure and accuracy. First, the neural network parameters with Gaussian and uniform distributions are tested and corrected to achieve process quantization. Then, a parameter memory control is implemented to achieve low-memory deployment and runtime. Subsequently, a bytes indexing is proposed for parameter location reading, enabling low-memory process inversed quantization. Finally, temporary variables is computed through micro memory overlay. This memory control method using process quantization and bytes indexing not only allows for ultra-low memory deployment and operation of neural networks but also improves test accuracy. It achieves over 97% test accuracy and an edge computation speed of over 200 KB/s with a maximum of 3.89 KB of runtime memory.

Monitoring the health of vehicle-track system using deep learning and distributed fiber optic sensing presents a significant challenge due to the vast volume of real-time data and the difficulty of directly assessing the system’s condition. This often results in a severe imbalance in the distribution of extreme samples within the dataset, as large-scale signal collection typically lacks manual labeling. Consequently, supervised deep learning models face limitations due to insufficient labeled training data, while unsupervised deep learning models struggle with contamination from ambiguous samples whose health status remains unclear, hindering the development of robust and accurate models. To address this challenge, we propose SemAnoDiffusion, a semi-supervised model based on blur diffusion and an enhanced contrastive loss training approach. SemAnoDiffusion leverages a small set of labeled data alongside a large amount of unlabeled samples to accurately differentiate between anomalous data, normal data, and ambiguous samples that fall between these categories. In a case study of a metro system in Singapore, Distributed Acoustic Sensing and accelerometer arrays were used to collect track vibration responses as trains passed, with wheel flats occurring in a small subset of the trains. SemAnoDiffusion achieved 100% accuracy in classifying manually labeled normal and anomalous samples and effectively identified semi-damaged samples with unclear damage levels from the labeled data, successfully detecting all trains with wheel flats.

Transportation infrastructure constitutes a significant part of civil infrastructure, such as bridges, tunnels, and roads, enormously promoting economic development. Transportation infrastructure is subjected to a high volume of traffic, damage, and component deterioration, as well as disaster events during the service period. Monitoring and management of the transportation infrastructure is always a critical task. Recently, digital twin (DT) is an emerging topic for transportation infrastructure management, with the advancement of artificial intelligence, Internet of Things, big data, and other smart technologies. Herein, DT aims to build a virtual counterpart of the physical infrastructure that is continually updated with its performance, maintenance, and health status. However, research in DT for transportation infrastructure mainly focused on infrastructure management (e.g., traffic state prediction and passenger flow assessment) and ignored the health status of the infrastructure itself. Challenges and associated opportunities exist in the adoption of DT for transportation infrastructure, such as balancing model fidelity and computation efficiency. Thus, it is necessary to investigate the key enabling technologies of DT in transportation infrastructure and provide a comprehensive reference for ongoing and future research. In this paper, a systematic investigation to identify the development of DTs for transportation infrastructure is presented. The paper starts by explaining the definition of DT and highlighting the various characteristics of DT. Next, the key enabling technologies and applications of DT for transportation infrastructure are discussed. Finally, based on the current development status of DT, challenges and open research are discussed along with their potential solutions.