Computer vision-based structural deformation monitoring techniques were studied in a large number of applications in the field of structural health monitoring (SHM). Numerous laboratory tests and short-term field applications contributed to the formation of the basic framework of computer vision deformation monitoring systems towards developing long-term stable monitoring in field environments. The major contribution of this paper was to analyze the influence mechanism of the measuring accuracy of computer vision deformation monitoring systems from two perspectives, the physical impact, and target tracking algorithm impact, and provide the existing solutions. Physical impact included the hardware impact and the environmental impact, while the target tracking algorithm impact included image preprocessing, measurement efficiency and accuracy. The applicability and limitations of computer vision monitoring algorithms were summarized.

Deep-learning- and unmanned aerial vehicle (UAV)-based methods facilitate structural crack detection for tall structures. However, contemporary datasets are generally established using images taken with handheld or vehicle-mounted cameras. Thus, these images might be different from those taken by UAVs in terms of resolution and lighting conditions. Considering the difficulty and complexity of establishing a crack image dataset, making full use of the current datasets can help reduce the shortage of UAV-based crack image datasets. Therefore, the performance evaluation of existing crack image datasets in training deep neural networks (DNNs) for crack detection in UAV images is essential. In this study, four DNNs were trained with different architectures based on a publicly available dataset and tested using a small UAV-based crack image dataset with 648 +pixel-wise annotated images. These DNNs were first tested using the four indices of precision, recall, mIoU, and F1, and image tests were also conducted for intuitive comparison. Moreover, a field experiment was carried out to verify the performance of the trained DNNs in detecting cracks from raw UAV structural images. The results indicate that the existing dataset can be useful to train DNNs for crack detection from UAV images; the TransUNet achieved the best performance in detecting all kinds of structural cracks.

Landslides not only cause great economic and human life losses but also seriously affect the safe operation of infrastructure such as highways. Rainfall is an important condition for inducing landslides, especially when a fault and weak interlayer exist on the slope, which can easily transform into a landslide and cause instability under the action of rainfall. To explore the effects of a soft interlayer, a fault, and extreme rainfall on slope stability, this paper takes the landslide on the right side of the G104 Jinglan Line in Shengzhou City, Shaoxing City, Zhejiang Province, China, as an example. The cause, failure mechanism, and characteristics of the landslide are analyzed through field investigation and borehole exploration in the landslide area. The slope is simulated by numerical analysis, and the stability of the landslide under natural conditions and extreme rainstorm conditions is calculated using the strength reduction method. The stability of the slope before and after treatment is compared, and the effectiveness of the treatment measures is verified by combining the field monitoring data. At the same time, the complex geological structure and rainfall are considered to have been the main factors leading to the G104 landslide. Near the fault, the weak interlayer of the landslide was easily disturbed, the deformation trend of the deep displacement was consistent with rainfall, and the axial force of the anti-slide piles at the weak interlayer was correspondingly large. For a wedge rock slope, “excavation unloading” and “prestressed anchor + prestressed anchor cable + anti-slide pile” are effective treatments. This paper reveals the effects of a weak interlayer, a fault, and strong rainfall on a rocky high slope, providing predictions of instability modes and time evolution patterns for similar complex geological slopes under rainfall infiltration conditions and providing references for their treatment measures.

In the application of a bridge weigh-in-motion (WIM) system, the collected data may be temporarily or permanently lost due to sensor failure or system transmission failure. The high data loss rate weakens the distribution characteristics of the collected data and the ability of the monitoring system to conduct assessments on bridge condition. A deep learning-based model, or generative adversarial network (GAN), is proposed to reconstruct the missing data in the bridge WIM systems. The proposed GAN in this study can model the collected dataset and predict the missing data. Firstly, the data from stable measurements before the data loss are provided, and then the generator is trained to extract the retained features from the dataset and the data lost in the process are collected by using only the responses of the remaining functional sensors. The discriminator feeds back the recognition results to the generator in order to improve its reconstruction accuracy. In the model training, two loss functions, generation loss and confrontation loss, are used, and the general outline and potential distribution characteristics of the signal are well processed by the model. Finally, by applying the engineering data of the Hangzhou Jiangdong Bridge to the GAN model, this paper verifies the effectiveness of the proposed method. The results show that the final reconstructed dataset is in good agreement with the actual dataset in terms of total vehicle weight and axle weight. Furthermore, the approximate contour and potential distribution characteristics of the original dataset are reproduced. It is suggested that the proposed method can be used in real-life applications. This research can provide a promising method for the data reconstruction of bridge monitoring systems.

The persistence of pothole maintenance represents an enduring challenge. Past studies have largely concentrated on the materials and techniques used for remediation, with a lack of attention given to the pothole interface. This paper employed epoxy asphalt rubber (EAR-10) as the repair material, exploring the impact of coupled temperature-dynamic loading on the mechanical response of the interface. Finite element modelling (FEM), adopting the viscoelastic characteristics of EAR-10, was deployed to investigate the mechanical response of the interface under three temperature service conditions high, medium, and low when a dynamic load traversed the pothole. The stress variations in the interface at various inclinations and thicknesses of the repair blocks were also studied. In addition, the comparative analysis of high-temperature rut resistance for powdered rubber composite-modified asphalt and SBS modified asphalt was conducted via the multiple stress examination in terms of its high-temperature resilience, resistance to moisture-induced damage, and fatigue life by employing the asphalt mixture rutting test, low-temperature bending test on small beams, and the water immersion Marshall stability test, respectively. The repair efficacy of EAR-10 was appraised through post-repair water immersion rutting tests and bending tests on composite structural small beams. The results indicated that incorporating coupled temperature-dynamic loading led to a considerable increase in stress, particularly under low-temperature service conditions. An inclination angle of 30 degrees was found to be optimal for the interface. The research methodology presented here is pertinent to guiding the pothole repair in the steel bridge pavement, ensuring the strength and durability of the interface rivals that of newly constructed layers.

Thousands of multi-span, simply supported beam bridges with short or medium spans have been built in China. They often suffer from problems of cracks in the link slabs over piers, and the deterioration and damage of deck expansion joints at abutments. To address these problems, one approach is to retrofit them by converting the simply supported box beams into continuous structures over the piers and jointless bridges over the abutments. This paper discusses the design methodology and details for retrofitting the Jinpu Bridge in Zhangzhou, Fujian, China, from a simply supported bridge into a semi-integral bridge, in which semi-fixed dowel joints are used to connect the superstructure and the substructure, including piers and abutments. Simultaneously, the finite element software is used to calculate the internal forces and displacements of the structure. The analysis reveals an 11.1% reduction in the maximum positive moment at the midspan of the main beam in the semi-integral bridge compared to the simply supported bridge. However, the shear forces at the interior pier increase by 6.4%. According to the response spectrum analysis, the maximum longitudinal displacement of the semi-integral bridge’s main beam is 11.6 mm, reduced by 80.1% compared to the simply supported bridge under a dead load and earthquake effects. The maximum bending moment and shear force on the pier of the semi-integral bridge are 984.7 kN·m and 312.6 kN, respectively, both below their ultimate bearing capacities. The maximum displacement at the top of the pier is 7.7 mm, which is below the allowable 52.4 mm displacement. The calculated results conform to the design requirements specified by the code.