Structural health monitoring (SHM) plays a crucial role in ensuring the safety of infrastructure in general, especially critical infrastructure such as bridges. SHM systems allow the real-time monitoring of structural conditions and early detection of abnormalities. This enables managers to make accurate decisions during the operation of the infrastructure. However, for various reasons, data from SHM systems may be interrupted or faulty, leading to serious consequences. This study proposes using a Convolutional Neural Network (CNN) combined with Gated Recurrent Units (GRUs) to recover lost data from accelerometer sensors in SHM systems. CNNs are adept at capturing spatial patterns in data, making them highly effective for recognizing localized features in sensor signals. At the same time, GRUs are designed to model sequential dependencies over time, making the combined architecture particularly suited for time-series data. A dataset collected from a real bridge structure will be used to validate the proposed method. Different cases of data loss are considered to demonstrate the feasibility and potential of the CNN-GRU approach. The results show that the CNN-GRU hybrid network effectively recovers data in both single-channel and multi-channel data loss scenarios.

Urban railway bridges are critical components of modern transportation networks. Dynamic loads and harsh environments put urban railway bridges at high risk of damage. Conventional vibration-based damage detection approaches often fail to provide sufficient accuracy and robustness under complex urban conditions. To address this limitation, this study introduces a hybrid deep learning framework that integrates a one-dimensional convolutional neural network (1D-CNN) and a recurrent neural network (RNN) for automatic damage detection using Linear Variable Differential Transformer (LVDT) displacement data. Start with the calibration of a finite element model (FEM) of the target bridge, achieved through updating the model parameters to align with field-acquired LVDT data, thereby establishing a robust and reliable baseline representation of the structure’s behaviour. Subsequently, a series of failure and damage scenarios is introduced within the FEM, and the associated dynamic displacement responses are generated to construct a comprehensive synthetic training dataset. These time-series responses serve as input for training a hybrid deep learning architecture, which integrates a one-dimensional convolutional neural network (1D-CNN) for automated feature extraction with a recurrent neural network (RNN) designed to capture the temporal dependencies inherent in the structural response data. Results show rapid convergence and minimal error in single-damage cases, and robust performance in multi-damage conditions on a dataset exceeding 5 million samples; the model attains a mean absolute error of ≈3.2% for damage severity and an average localisation error of <0.7 m. The findings highlight the effectiveness of combining numerical simulation with advanced data-driven approaches to provide a practical, data-efficient, and scalable solution for structural health monitoring in the urban railway context.

Field displacement measurements can support FE model updating, although the resulting model remains conditional on the available observations and modeling assumptions. This study proposes a hybrid Differential Evolution–Levenberg–Marquardt (DE–LM) framework for updating an FE model using train-induced displacement histories measured by linear variable differential transformers (LVDTs). A prestressed-concrete box-girder railway bridge was investigated, with the numerical model explicitly representing the box girder, sleepers, rails, and equivalent rail-fastening connections. Preliminary parameter screening was conducted to select three influential parameters: the box-girder elastic modulus and the effective vertical and lateral fastening stiffnesses. DE was employed to explore the bounded parameter space, after which LM refined the best global solution using local response sensitivities. Physical parameter bounds and regularisation were incorporated to limit non-unique and unrealistic solutions. Complete train passages were separated into calibration and independent validation datasets. The hybrid procedure reduced the initial objective value by approximately 90.5% and produced physically admissible parameter changes. For the independent validation dataset, the updated model achieved a mean normalized root mean square error of 2.17%, compared with 3.07% for DE-only, 4.94% for LM-only, and 7.46% for the initial model. The mean peak-displacement error was reduced to 0.70%. For the investigated case, the selected hybrid solution achieved lower validation errors than the reported DE-only and nominal-start LM solutions. The calibrated model provides a physics-based foundation for subsequent railway-bridge digital-twin development.