Crack detection on bridges is an important part of assessing whether a bridge is safe for service. The methods using manual inspection and bridge-inspection vehicles have disadvantages, such as low efficiency and affecting road traffic. We have conducted an in-depth study of bridge-crack detection methods and have proposed a bridge crack identification algorithm for Unet, called the CBAM-Unet algorithm. CBAM (Convolutional Block Attention Module) is a lightweight convolutional attention module that combines a channel attention module (CAM) and a spatial attention module (SAM), which use an attention mechanism on a channel and spatially, respectively. CBAM takes into account the characteristics of bridge cracks. When the attention mechanism is used, the ability to express shallow feature information is enhanced, making the identified cracks more complete and accurate. Experimental results show that the algorithm can achieve an accuracy of 92.66% for crack identification. We used Gaussian fuzzy, Otsu and medial skeletonization algorithms to realise the post-processing of an image and obtain a medial skeleton map. A crack feature measurement algorithm based on the skeletonised image is proposed, which completes the measurement of the maximum width and length of the crack with errors of 1–6% and 1–8%, respectively, meeting the detection standard. The bridge crack feature extraction algorithm we present, CBAM-Unet, can effectively complete the crack-identification task, and the obtained image segmentation accuracy and parameter calculation meet the standards and requirements. This method greatly improves detection efficiency and accuracy, reduces detection costs and improves detection efficiency.

A bridge disease identification approach based on an enhanced YOLO v3 algorithm is suggested to increase the accuracy of apparent disease detection of concrete bridges under complex backgrounds. First, the YOLO v3 network structure is enhanced to better accommodate the dense distribution and large variation of disease scale characteristics, and the detection layer incorporates the squeeze and excitation (SE) networks attention mechanism module and spatial pyramid pooling module to strengthen the semantic feature extraction ability. Secondly, CIoU with better localization ability is selected as the loss function for training. Finally, the K-means algorithm is used for anchor frame clustering on the bridge surface disease defects dataset. 1363 datasets containing exposed reinforcement, spalling, and water erosion damage of bridges are produced, and network training is done after manual labelling and data improvement in order to test the efficacy of the algorithm described in this paper. According to the trial results, the YOLO v3 model has enhanced more than the original model in terms of precision rate, recall rate, Average Precision (AP), and other indicators. Its overall mean Average Precision (mAP) value has also grown by 5.5%. With the RTX2080Ti graphics card, the detection frame rate increases to 84 Frames Per Second, enabling more precise and real-time bridge illness detection.

Coal and oil shale are often mined and utilized together, and mixed dust is easily formed in these processes. In order to ensure safe production in these processes, the explosion characteristics of mixed dust were studied. Using a Godbert-Greenwold (G-G) Furnace experimental device, Hartmann tube experimental device, and 20 L explosion vessel, the oil shale and coal mixed dust ignition sensitivity experiment, flame propagation experiment, and explosion characteristics experiment were carried out. The minimum ignition temperature (MIT), minimum ignition energy (MIE), maximum explosion pressure (P_max), maximum rate of pressure rise ((dp/dt)_max), and explosibility index (K_St) parameters and the flame propagation behavior of the mixed dust were analyzed in detail. A scanning electron microscope (SEM) analysis of the coal and oil shale dust before and after the explosion was carried out to study the changes in the microscopic morphology of the dust particles. The results show that due to the oil shale having a high volatile content and low moisture content, in the mixture, the greater the percentage of oil shale, the more likely the dust cloud is to be ignited and the faster the explosion flame is propagated; the greater the percentage of oil shale, the greater the (dP/dt)_max and K_St will be and, under a high dust concentration, a greater P_max will be produced. During explosion, coal dust will experience particle pyrolysis and the gas phase combustion of the volatile matter, followed by solid phase combustion of coal char, whereas oil shale dust will only experience particle pyrolysis and the gas phase combustion of the volatile matter.

In order to propose a reliable method for assessing the safety condition for single-tower steel box girder Suspension bridges over the sea, a condition monitoring system is established by installing sensors on the bridge structure. The system is capable of gathering monitoring data that influence the safety status of the bridge. These include cable tension, load on the main tower and pylon, bearing displacement, wind direction, wind speed, and ambient temperature and humidity. Furthermore, an improved Analytic Hierarchy Process (AHP) algorithm is developed by integrating a hybrid triangular fuzzy number logic structure. This improvement, coupled with comprehensive fuzzy evaluation methods, improves the consistency, weight determination, and security evaluation capabilities of the AHP algorithm. Finally, taking the No.2 Channel Bridge as an example and based on the data collected by the health monitoring system, the application of the safety assessment method proposed in this paper provides favorable results in evaluating the overall safety status of the bridge in practical engineering applications. This provides a basis for management decisions by bridge maintenance departments. This project confirms that the research results can provide a reliable method for assessing the security status of relevant areas.

In this paper, the mechanical response mechanism and damage behavior of a railway tunnel lining structure under reverse fault dislocation were studied. The damage behavior of railway tunnel linings under reverse fault dislocation was validated by undertaking laboratory tests and three-dimensional numerical simulations, where Coulomb’s friction was used in the tangential direction of the interface. The failure damage, which increasingly accumulates with displacements, mainly concentrates in fault fracture neighborhoods 0.5 D to 1.5 D (D is the tunnel diameter) within the footwall. The maximum surrounding rock pressure and the maximum longitudinal strain develop in the tunnel near the hanging wall area. The damage begins as longitudinal cracking of the inverted arch. With the increase in dislocations, those cracks develop upward to the arch foot and the waist. Consequently, those oblique cracks separate lining segments, leading to abutment dislocation. The research results provide technical guidance and theoretical support for on-site construction and follow-up research, and they have important application value.

In response to the lack of relevant research on the health monitoring system and assessment of the structural safety status of a cable-stayed bridge across the sea, the real-time monitoring data was determined by the health monitoring system installed on the bridge structure. Strain and displacement data for the bridge structure were analyzed and processed. Based on operational research principles, a safety condition assessment of the Channel 1 Bridge was conducted using the Analytic Hierarchy Process (AHP). First, the reserve strength method is applied to determine the weight proportion of monitoring indicators such as strain and displacement. Secondly, the weight proportion of each monitoring indicator at different cross-sectional positions is determined. Then, the hierarchical division of the cable-stayed bridge structure is performed from the lowest layer, and the rating level of the Channel 1 Bridge structure is obtained using the variable weight synthesis method. This provides a basis for management decisions in the bridge maintenance department and serves as an example for future safety assessments of medium-span cable-stayed bridges over the sea.