Structural Control and Health Monitoring

In the realm of structural health monitoring (SHM), understanding the expected behavior of a structure is vital for the timely identification of anomalous activities. Existing methods often model only the physical quantities of monitoring data, neglecting the corresponding temporal information. To address this, this paper presents an innovative deep learning framework that synergistically combines a BiLSTM model, fortified by a temporal pattern attention (TPA) mechanism, with time-encoded temperature and traffic-induced deflection-temporal patterns. The arithmetic optimization algorithm (AOA) is employed for optimal hyperparameter tuning, and incremental learning was implemented to enable real-time updates of the model. Based on the proposed framework, an anomaly detection method was subsequently developed. This method is bidirectional: it uses quantile loss to provide expected ranges for structural behavior, identifying isolated anomalies, while the windowed normalized mutual information (WNMI) based on multivariate kernel density estimation (MKDE) helps detect trend variability caused by decreases in structural stiffness. This framework and the anomaly detection method were validated using data from an operational cable-stayed bridge. The results demonstrate that the method effectively predicts structural behavior and detects anomalies, highlighting the critical role of temporal information in SHM.

Traditional manual inspection technology has the problems of high risk, low efficiency, and being time-consuming in bridge safety management. The unmanned aerial vehicle (UAV)-based detection technology is widely used in bridge structure safety monitoring. However, the existing deep learning-based concrete crack identification method has great limitations in dealing with complex background and tiny cracks in bridge structures. To address these problems, this study designs a crack pixel-level high-performance segmentation model for bridge concrete cracks that is suitable for UAV detection scenarios using machine vision (MV) and deep learning (DL) algorithms. First, considering the high requirements for the computing performance of the MV-based model for UAV-based detection, the ResNet-18-based lightweight convolutional neural network is used to represent the traditional large-scale backbone network of the pyramid scene parsing network (PSPNet) to develop a high-performance crack automatic identification model. Then, considering that bridge concrete cracks have the characteristics of subtle shapes and complex backgrounds, the spatial position self-attention module is inserted into the PSPNet to improve its detection accuracy. A concrete bridge is used for the case study, and a dataset of cracks in bridge concrete structures collected by UAVs is constructed and used for model training. The experimental results show that the loss function of the developed method in the training process results in a smooth decline, and the developed algorithm achieves the evaluation indicators of 0.9008 precision, 0.8750 recall, 0.8820 accuracy, and 0.9012 IOU on the bridge concrete crack dataset, which are significantly higher than other state-of-the-art baseline methods. In addition, four common UAV bridge detection scenarios, including low light, complex crack forms, high background roughness, and complex background scenes, are used to further test the crack detection ability of the developed crack identification model. The experimental results show that the proposed crack identification method can effectively overcome interference and real-size pixel-level segmentation of crack morphology. In addition, it also achieved a detection efficiency of 35.04 FPS, which shows that the real-time detection ability of the method has good applicability in the UAV detection scene.

This paper introduces a novel and comprehensive model for the analysis of dam deformation trends, integrating the variational mode decomposition (VMD) method, fractal theory, and the whale optimization algorithm (WOA) to refine the deep extreme learning machine (DELM) model. This integration allows for a meticulous denoising process through VMD, effectively isolating pertinent signal characteristics from noise and measurement interference. Following this, fractal theory is utilized to conduct an in-depth qualitative analysis of the denoised data, capturing intricate patterns within the deformation trends. The model further evolves with the application of WOA to optimize the DELM model, thereby facilitating an integrated approach that merges qualitative insights with quantitative analysis. The efficacy of this advanced model is demonstrated through a case study, highlighting its capability to deliver accurate and reliable predictions that are in harmony with practical engineering scenarios. This research not only offers a robust framework for analyzing dam deformation trends but also sets a new standard in the field, providing a new solution for assessing structural integrity in hydrological engineering.

The detection of ballastless track surface (BTS) defects is a prerequisite for ensuring the safe operation of high-speed railways. Traditional convolutional neural networks fail to fully exploit contextual information and lack global pixel representations. The extensive stacking of convolutions leads deep learning models to play a black-box detection role, lacking interpretability. Due to the current lack of sufficient high-quality surface data for ballastless tracks, it is a severe constraint on the accurate identification of the substructure state in high-speed railways. This paper proposes an intelligent detection method for BTS defects named TrackNet based on self-attention and transfer learning. The method enhances the fusion ability of global features of BTS defects using multihead self-attention. The model’s dependence on extensive defect data is reduced by transferring knowledge from large-scale publicly available datasets. Experimental results demonstrate that compared to advanced Swin Transformer model results, the TrackNet model achieves improvements in average accuracy and F1-score by 5.15% and 5.16%, respectively, on limited test data. The TrackNet model visualizes the decision regions of the model in identifying BTS defects, revealing the black-box recognition mechanism of deep learning models. This research performs engineering applications and provides valuable insights for the multiclass recognition of BTS defects in high-speed railways.

The multiple intersecting stiffeners on the chemical milling stiffened panel (CMSP) limit the application of active health monitoring methods on it. An imaging algorithm based on electromechanical impedance (EMI) and probability-weighting is proposed to achieve quantitative evaluation and localization of the damage on CMSP. The proposed algorithm compensates for the difference in sensor performance with coefficients and there is no need to determine the key parameters of the algorithm through prior experiments. In the paper, the applicability of ultrasonic guided wave (GW) and EMI on CMSP was first studied through the finite element method. Based on EMI and the mean absolute percentage deviation (MAPD), the selected damage indicator (DI), a probability-weighted damage imaging algorithm are proposed and experimentally verified. The results indicate that due to the reflection and attenuation effects of stiffeners on GW, the signal characteristics of damage scattering waves are contaminated, making it difficult to quantitatively characterize the damage from GW signals through DIs. MAPD is positively correlated with the damage degree and has consistency in characterizing the signal of different PZTs under the same working condition. The feasibility and accuracy of the proposed algorithm are verified through experiments which show a strong engineering application capability.

Rapid and accurate structural damage assessment after an earthquake is important for efficient emergency management. The widespread application of surveillance cameras provides a new possibility for improving the efficiency of assessment. However, it is still challenging to directly assess the structural seismic damage based on videos captured by indoor surveillance cameras during earthquakes. In this study, we elaborate on the concept of estimating the structural natural frequency based on the relative pixel displacement of inter-stories. Furthermore, we propose a strategy for post-earthquake structural damage assessment that integrates the computer vision and time-frequency analysis. This approach aims to navigate the difficulties inherent in earthquake damage assessment and improve emergency responses. The relative pixel displacement between the camera and the fixed features on the floor is extracted from videos by using the Harris corner detection and Kanade–Lucas–Tomasi algorithms. The structural natural frequency is estimated using the synchroextracting transform-enhanced empirical wavelet transform. The natural frequency shift-related seismic damage index is defined and calculated for damage assessment. A shake table experiment of a small-scale steel model is conducted to verify the accuracy and feasibility of the approach, and the practicality of the proposed approach is further verified by utilizing the data from a full-scale reinforced concrete benchmark model experiment. The results demonstrate that the approach can accurately and efficiently evaluate the structural damage after an earthquake based on the video captured by surveillance cameras during the earthquake. The error of the acquired damage index is less than 0.1. We will apply more advanced algorithms in the future to alleviate this problem.