Structural Control & Health Monitoring最新文献

The management and maintenance of the aging bridges can benefit from an efficient and automatous bridge inspection process, such as crack detection and localization. This paper presents a robust and efficient approach for unmanned aerial vehicle (UAV)-based crack recognition and localization. An adapted YOLOX model is used in the proposed approach to improve accuracy and efficiency of crack recognition, and hence to enable real-time crack recognition from the captured UAV images at the edge-computing devices. In this way, non-crack images can be recognized in real-time during data acquisition and be filtered out to relieve the burden of subsequent data recording. In addition, a self-organizing positioning system based on ultra-wide-band (UWB) sensors is employed in the proposed system to enable real-time UAV positioning and crack localization in GNSS-denied areas such as spaces underneath the bridge deck. Experiment studies were carried out to investigate the impact of the quantities of employed UWB base stations on the UAV positioning accuracy. Finally, the proposed approach is tested on a self-developed UAV system and the effectiveness is validated through laboratory tests and real-world field tests.

With the development of computer and image processing technologies, computer vision (CV) has been attracting increasing attention in the field of civil engineering measurement and monitoring. Cables in slender structures have unique challenges for CV-based vibration measurement methods, such as low pixel proportion and sensitivity to environmental conditions. This study proposes a noncontact vibration measurement method based on a line tracking algorithm (LTA). The robustness and applicability of the proposed method under varying image resolutions, signal-to-noise ratios, and cable inclination angles were systematically evaluated through experimental test of a cable specimen. To validate the effectiveness of the proposed method for practical detection applications, a vibration test on a scaled cable-stayed bridge model was carried out. The numerical result indicates that the LTA provides high reliability and accuracy values of the cable force. The maximum errors of the first-order self-vibration frequency and cable force of the scaled cable-stayed bridge is 0.99% and 2%, respectively. The proposed method maintains strong stability across various conditions, which provides a reference for long-term structural health monitoring of cable-stayed bridges.

Fatigue failure is a common mode of deterioration for steel cables (e.g., 321 stainless steel) in cable-stayed bridges. In this case, given that the FeCoNiCrMn high-entropy alloy (HEA) coatings have been found to simultaneously improve the fatigue and corrosion resistance of 321 steel, the fatigue crack growth behavior of 321 steel coated with selective laser melting CoCrFeMnNi HEA was further studied in this work. The results indicate that the CoCrFeMnNi alloy coating is able to increase the fatigue crack growth resistance of 321 steel by 21.43% compared to the uncoated 321 steel, and this is because the initiation of crack is mitigated by the angular disparities between adjacent grains and an increased dislocation density in the coating. Furthermore, the acoustic emission (AE) technique was used to track fatigue damage and predict fatigue crack growth life. It was found that crack length could be effectively monitored and predicted using the count and energy parameter, suggesting material and stress ratio independence in the AE technique.

Recently, convolutional neural networks (CNNs) and hybrid networks, which integrate CNN with Transformer, have been widely employed in structuring crack detection, effectively addressing the challenges of high-precision crack identification in controlled scenes. However, scene generalization remains a significant challenge for existing networks, especially under limited dataset conditions. With the rapid development of foundation models (like ChatGPT), achieving scene generalization has become feasible. In this paper, by taking tunnel crack detection as the background, the CraSAM network is proposed, which incorporates a foundation model-based encoder and a prompt transfer learning module. Based on six datasets including tunnel, bridge, building, and pavement, the CraSAM is compared with 15 state-of-the-art models, including Unet, DeepLabv3+, SSSeg, and TransUNet. It exhibits superior generalization capability both on few-sample learned and unlearned conditions. This work will benefit to investigate of new ways for the utilization of the visual foundation model in various professional fields.

Modern industrial systems depend heavily on rotating machines, especially rolling element bearings (REBs), to facilitate operations. These components are prone to failure under harsh and variable operating conditions, leading to downtime and financial losses, which emphasizes the need for accurate REB fault diagnosis. Recently, interest has surged in using deep learning, particularly convolutional neural networks (CNNs), for bearing fault diagnosis. However, training CNN models requires extensive data and balanced bearing health states, which existing methods often assume. In addition, while practical scenarios encompass a diverse range of bearing fault conditions, current methods often focus on a limited range of scenarios. Hence, this paper proposes an enhanced method utilizing a one-dimensional deep CNN to ensure reliable operation, with its effectiveness evaluated on Case Western Reserve University (CWRU) rolling bearing datasets. The experimental results showed that the diagnostic accuracy reached 100% under 0∼3 hp working loads for 10 unbalanced health classes. Moreover, it attained 100% accuracy for high-class health states with 20, 30, and 40 classes, and when extended to 64 health classes, it reached a peak accuracy of 99.96%. Thus, the method achieved improved classification ability and stability by employing a straightforward model architecture, along with the integration of batch normalization and dropout operations. Comparative analysis with existing diagnostic methods further underscores the model superiority, particularly in scenarios involving unbalanced and high-class health states, thus emphasizing its effectiveness and robustness. These findings significantly advance the field of intelligent bearing fault diagnosis.

This paper proposes a novel hybrid-driven digital twin (DT) framework for time-variant reliability assessment of civil structures, which mainly consists of four modules, including physics model construction, data-driven model calibration, failure probability calculation, and time-variant reliability prediction. In the first module, a DT model of a specific structure is constructed to simulate structural dynamic responses. Then, an improved unscented Kalman filter (IUKF) algorithm is performed to continuously calibrate the parameters of DT model. Subsequently, in module 3, the subset simulation (SS) approach is employed to calculate failure probability of structures subjected to various model parameter samples, and the generated input–output samples are further applied for metamodel training. A Kriging metamodeling is used to construct the correlation between model parameters and structural failure probability. Once the metamodel is well trained, the time-variant reliability assessment of structures can be continuously achieved in module 4. Numerical simulations on a Bouc–Wen model are conducted to validate the feasibility and accuracy of the proposed approach. Furthermore, a scaled column shake table structure is further employed to verify the effectiveness of the proposed approach. Both numerical and experimental results have shown that the proposed approach is capable of conducting time-variant reliability assessment of civil structures.

This paper presents a novel unsupervised method for structural damage diagnosis, which transforms the problem of structural damage diagnosis into the problem of identifying anomalous data in monitoring data. The method establishes the sensor interrelationships based on the graph structure, optimizes the hyperparameters of the graph neural network (GNN) model, and realizes the structural response prediction. By calculating the discrepancy between the predicted response and the monitoring data, the method identifies the anomalies to facilitate the identification and localization of structural damage. The efficiency of the proposed method for bolt loosening detection was evaluated through the analysis of acceleration data collected from a vibrating grandstand simulator and strain data from a wind tunnel test of a scaled tower model. The experimental results indicated that the established connections can provide a preliminary indication of the relative importance of the sensors, which may also be regarded as a metric for each node in the structure. The proposed method is effective in the detection and localization of minor damage in infrastructure structures.

Structural temperature field significantly affects structural responses, such as displacements and stresses, of a long-span suspension bridge. An accurate and effective analysis of structural temperature field is therefore important. This study proposes a digital twin-empowered analysis of structural temperature field of a long-span suspension bridge. The real bridge and its surrounding environment are regarded as a physical entity. The information, such as ambient temperature and structural temperature, collected by the structural health monitoring system at the locations of sensors is taken as the data collected from the physical entity. A 3D finite element model of the bridge is then constructed as a virtual entity for heat transfer analysis with solar radiation, wind speed, and other environmental conditions included. The data collected from the physical entity are then mapped to the virtual entity through a particle swarm optimization algorithm to update uncertain parameters in the thermal boundary and convert the virtual entity to a digital twin. The established digital twin is finally used to find and predict the structural temperature field of the entire bridge. The results demonstrate that the digital twin-empowered heat transfer analysis is feasible and able to provide more accurate prediction of the structural temperature field of the entire bridge.

In the realm of structural health monitoring (SHM) of bridge structures, the accurate reconstruction of girder-end displacement (GED) is crucial for identifying potential structural damage and ensuring the monitoring system’s reliability. A novel fine-grained spatial (FGS) attention mechanism, combined with efficient channel attention (ECA), has been proposed to effectively utilize multisource monitoring data. This hybrid attention mechanism has been integrated into an arithmetic optimization algorithm–bidirectional long short-term memory (AOA–BiLSTM) framework for reconstructing GED using non-GED data, including deflection, temperature, strain, and traffic data. Data are organized into a two-dimensional array based on sensor types and spatial locations to capture interchannel and intrachannel correlations. ECA captures local correlations among different sensor types, while the proposed FGS enhances model interpretability by focusing on local dependencies within each sensor type. Huber loss is employed for robust performance, and AOA techniques are used for efficient hyperparameter optimization. Validation with real-world data from a cable-stayed bridge demonstrates the necessity and efficacy of considering multidimensional information correlations in response reconstruction for SHM applications. This work lays a theoretical foundation for improving safety assessments, anomaly detection, data recovery, and virtual sensing in bridge structures.

Metro networks have been extensively developed in large cities to satisfy traffic demands. Adjacent to subways, there has been an increasing construction of fixed-base, base-isolated, and interstory-isolated buildings on metro depots. Notably, metro-induced environmental vibrations have led to vibrations in buildings, thus affecting human health and the regular operation of sensitive equipment. Numerical simulations are considered a valuable method for assessing building vibrations. However, research on a generalized numerical simulation strategy for simulating the metro-induced vibrations of the abovementioned three types of buildings remains rare. Hence, this study recommends a generalized numerical simulation strategy and validates it through the comparison between the results of shaking table tests. The acceleration time histories of floor, distributions of the acceleration at different positions on the slab and along the height of the building, and one-third octave band vertical acceleration levels were accurately simulated for the three structures. Meanwhile, the simulation accuracies of three types of damping models were discussed. The relative differences between the simulated and experimental maximum acceleration amplification coefficients and one-third octave band vertical acceleration levels were both less than 4.2%. Furthermore, the influences of the mesh sizes of the elements for the slabs and the parameters of the Rayleigh damping model on the simulated results were investigated. The recommended simulation strategy can contribute to further investigation of the metro-induced vertical vibration assessment of different types of structures.