Tunnel lining detection is an important element of quality management in tunnel construction and maintenance. Due to the variety of internal lining defects and unclear boundaries makes it challenging to identify these problems and train models effectively. Relying on manual detection or existing models, it is not possible to achieve fast and accurate defect detection. To address the above problems, A dataset consisted of 1 922 liner radar samples collected from Yunnan Tunnel B-scan was developed for training the model. A tunnel lining defect detection model YOLO-Tunnel based on YOLOv5 was proposed, which improved the model feature extraction ability, increased the receptive field, and improved the model localization ability by upgraded the Backbone and Neck. And further improved the model detection ability by selected the appropriate model size and balanced weight based on the dataset's scale and target size proportions. The results show that YOLO-Tunnel has better defect detection accuracy compared to YOLOv5s and also meets the real-time detection requirements, in which the precision, recall, and mAP are increased by 2.5, 9.0, and 8.1 percentage points, respectively, with the inference time increases by 2.7 ms to 21.8 ms. The research results provide a reference for further improving the performance of the detection of tunnel lining detection and the direction of optimization of the model reference.

In deep foundation pit engineering, the support form of “bored pile + internal support” is often used for foundation pit support, but the support effect of different support arrangements on the foundation pit is different. Relying on a foundation pit project in a fast-track reconstruction and expansion project in Changzhi City, ABAQUS was used to numerically simulate the whole process of excavation of different steel support layout schemes, and the influence of different internal support layout schemes on the settlement of the surface soil around the excavation of the foundation pit, the horizontal displacement of the supporting structure and the uplift of the bottom of the foundation pit were analyzed, and then the reliability of the model was verified by combining the field monitoring results. The results show that the numerical simulation results can accurately reflect the deformation law and characteristics of the foundation pit in the process of excavation and support. When the depth of the internal support arrangement is small, it has a good control effect on the maximum horizontal displacement of the supporting pile and the surface settlement outside the pit. When the depth of the internal support arrangement is large, the maximum uplift at the bottom of the pit has a certain control effect. Increasing the number of internal supports has different effects on reducing the maximum horizontal displacement of the supporting pile and the maximum uplift at the bottom of the pit.

To address limitations in the engineering application of neural network based maximum power point tracking(MPPT) algorithms, an improved lightweight neural network MPPT algorithm was proposed. The complexity and memory usage of the neural network were reduced through a knowledge distillation compression algorithm, and a lightweight model was obtained. The inherent theoretical error of model predictions was corrected using an optimized variable step-size perturb and observe method. In the initial stage, the neural network predicted the voltage range of the maximum power point. In the later stage, disturbance observation progressively refined this range until it converged at the maximum power point. A simulation model was developed in MATLAB/Simulink, and a physical model was constructed for comparative experiments. Results indicate that the proposed algorithm achieves higher tracking efficiency, improved ripple voltage suppression, and lower resource consumption rate in embedded devices.

In construction safety inspections, visual obstructions often lead to missing features, resulting in dangerous misjudgments. To improve the efficiency of risk identification in construction, a method for occluded feature inference based on amodal completion technology was proposed, using construction fence detection as a case study. First, a dataset of fence detection images with visual obstructions was created using image synthesis techniques. Then, a combination of YOLOv8 instance segmentation and the amodal segmenter based on boundary uncertainty estimation (ASBU) feature completion network was used to infer the visual features of the occluded parts of the fence. The completed features of the occluded construction fences can be applied to various construction safety monitoring tasks, such as closed-loop detection. The approach was validated using fence images from multiple construction sites, achieving precise feature completion for occluded fences (average intersection ratio mIoU>95.5%). The research results provide a framework for feature inference in occluded construction scenes, which enhances the efficiency of intelligent construction safety supervision.

To realize the efficient analysis of composite joints with novel side-plate reinforced connections, a macro model of beam-column-slab composite joint was proposed. The optimal realization method of the connection between floor and steel beam was determined. The accuracy and reliability of the macro model was verified. Furthermore, a beam-column joint frame model with traditional side-plate reinforced connections (TSP), a beam-column joint frame model with novel side-plate reinforced connections (FBSP), and a composite joint frame model with novel side-plate reinforced connections (CJ-FBSP) were established. Elastic-plastic time-history analysis was conducted on three frame models considering the joint performance. The top point lateral displacement, inter-story drift angle, plastic energy dissipation, and plastic hinge distribution of different frame models under seismic waves were obtained. The results show that the performance of TSP and FBSP joints can be well simulated according to the spring stiffness calculation method. At the same time, the connection method considering the shear slip and pull-out performance of studs can precisely simulate the mechanical performance of composite joints. The inter-story drift angle of the three joint frame models do not exceed the specification limit (1/50). The maximum inter-story drift angle of FBSP frame model is smaller than that of TSP frame model but larger than that of CJ-FBSP frame model, and the plastic energy dissipation capacity is the best. Due to the strengthening effect of the floor, the plastic hinge rate of CJ-FBSP frame model is the smallest but the plastic energy dissipation capacity is weak.

In order to reduce the risk of logistics drones to the ground after failure or collision in the air, a model for logistics drones to the ground risk assessment was constructed, focusing on the risk analysis of drone failure and crash. Firstly, in the drone failure and crash risk model, the possible failure of drones in different flight stages was discussed in detail, including vertical fall and horizontal fall, as well as the casualties and economic losses that these falls may cause to ground personnel. Secondly, the collision and crash risk model was analyzed the dynamic behavior of drones after a collision in the air and its impact on ground safety, including collision momentum-energy conservation and collision consequence assessment. Finally, a comprehensive three-dimensional risk assessment matrix was constructed, combining the possibility of accidents, the number of deaths on the ground and the economic losses to evaluate the risk level in different scenarios. The case analysis shows that the number of deaths on the ground is within the order of 10^-6, and the risk level in different regions is obtained. It can be seen that this method provides important risk assessment tools and data support for logistics drone operators and relevant policy makers.

The accumulated water in the cavity behind the tunnel lining in cold regions may freeze under low-temperature conditions, resulting in local frost heave pressure. Assuming that the cavity behind the tunnel lining was a semi-elliptical space, the interaction between the surrounding rock, ice body, and lining during the frost heave process was simplified as springs in series, and an analytical solution for the local frost heave pressure in the semi-elliptical water-accumulated space was proposed. A three-dimensional numerical model was developed to verify the effectiveness of the analytical solution. Further, the relationships between local water-accumulated frost heave pressure and surrounding rock grade, lining stiffness, water-accumulated depth, and frost heave level were studied, and the influences of frost heave position on the mechanical characteristics of lining structure were analyzed. The results show that the local water-accumulated frost heave pressure of the cold region tunnel is negatively correlated with the surrounding rock grade and positively correlated with the lining stiffness, water-accumulated depth, and frost heave level. The influence degree of various factors on frost heave pressure is as follows: water-accumulated depth > lining stiffness > surrounding rock grade > frost heave level. The impact of water-accumulated frost heave on the lining structure mainly occurs in the contact area between the ice body and the lining, leading to the convergence of the tunnel towards the inner side. The principal stress of the lining is maximum when the water-accumulated space is located at the inverted arch, and the principal stress of the lining is minimum when it is located at the arch foot. Under the action of local frost heave, there is a sudden change in the bending moment and axial force of the lining structure, manifested as the bending moment increase and axial force decrease of the lining under tension on the air side, as well as the bending moment decrease and axial force decrease of the lining under tension on the surrounding rock side. The stiffness differences in different zones of the lining lead to different impacts of frost heave pressure on structure safety. The influence degree of frost heave position on structure safety is as follows: vault > inverted arch > arch shoulder > arch foot > wall foot.

In order to study a non-destructive testing method for concrete beam stress, a ultrasonic tail stress identification algorithm coda wave-deep residual shrinkage network (C-DRSN) based on deep residual shrinkage network(DRSN) was proposed. According to the high-dimensional characteristics of the tail wave signal vector, the interference of signal noise to the measurement stress accuracy was reduced by introducing residual contraction block, using soft threshold function and attention mechanism, and the adaptive recognition and extraction of stress features in the signal were realized, and the recognition accuracy was improved. The characteristics were visually analyzed, and the mapping relationship between the tail wave sign and the stress was established. In order to verify the model's ability of stress recognition, ultrasonic tail wave signals of concrete I-beams under three-point bending and eccentric compression loads were collected respectively. The results show that the recognition rate can reach 99% under both loading modes, indicating that the proposed method is feasible in the stress recognition of concrete beams, and the accuracy of the proposed method is higher than that of the tail wave interference method.

In order to better address incidents of online violence resulting from uncontrolled public opinion in the era of self-media, network platforms are involved in decision-making during the early stages of online violence opinion formation. This can effectively prevent the formation of online violence opinions. Firstly, based on the inducement behaviors of online violence and considering the internal self-purification effects among platforms, self-media, and netizens, the costs and benefits of their autonomous behaviors during the initial stages of online violence opinion formation were defined. Next, a “platform-self-media-netizen” three-party evolutionary game model was constructed, and the behaviors of each subject and their evolutionary stable strategies were analyzed. Finally, numerical simulation experiments were conducted using MATLAB to verify the accuracy of the model and evolutionary results. To further reveal the factors influencing the cooperation among these parties, the impact of their initial cooperation willingness and related parameters on the system was explored. Simulation results show that a strong regulatory strategy adopted by network platforms, with clear guidance, can effectively enhance the cooperation willingness of self-media and netizens, effectively curbing the formation of online violence opinions.

The novel electro-hydraulic composite intelligent completion system primarily involves downhole flow control technology and multi-parameter detection technology and so on. Based on the principles of mechanical structure design, the structural design of the core component of the electro-hydraulic composite intelligent completion flow control valve was conducted, namely the throttle valve sleeve. Finite element analysis was utilized to numerically simulate and study the mechanical performance and fluid flow characteristics of the throttle valve sleeve. The the flow field characteristics under various openings, water cut rates, displacements, and working conditions were analyzed by this method. The results indicate that the downhole temperature and pressure conditions have little effect on the flow control performance of the throttle valve sleeve. The performance is stable and meets the design requirements under high temperature and high pressure (125 ℃, 50 MPa). With different openings, the pressure difference gradually increases as the flow rate increases. At a constant flow rate, the pressure difference decreases with the increase of the opening. When the flow rate and opening are constant, the pressure difference gets greater when water cut becomes larger. When the flow rate and water content are constant, the greater the control series of the throttle valve sleeve, the smaller the pressure difference. The research results can provide theoretical guidance for the structural design of intelligent completion flow control valve.