<!-- *** Custom HTML *** --> Dai, C.-Q.; Long, Y.-X.; Lv, Y.-L.; Hou, W.-Z., and Sui, H.-T., 2019. Water inrush mechanism and safety control in drilling and blasting construction of subsea tunnel. In: Gong, D.; Zhu, H., and Liu, R. (eds.), Selected Topics in Coastal Research: Engineering, Industry, Economy, and Sustainable Development. Journal of Coastal Research, Special Issue No. 94, pp. 218–222. Coconut Creek (Florida), ISSN 0749-0208. Based on the water inrush (WI) patterns of shallow buried tunnels, this paper elaborates on the WI mode and mechanism during the drilling and blasting of subsea tunnels in consideration of the characteristics of high-water pressure and complex geology of submarine tunnels. Then, through the main analysis for the deformation law of surrounding rock caused by drilling and blasting, it establishes the relationship between subsea/tunnel vault crown settlement and WI in construction under the construction conditions of unfavourable geological body, to obtain the two main failure modes of submarine tunnel: stratum cracking and partial separation failure. Besides, according to the characteristics of stratum deformation, the deformation displacement analysis of the roof and side walls of the tunnel was conducted to establish the safety control risk early warming mechanism on the basis of the risk control relationship between the measured values, early warning values, alarm values and limit control values of the stratum deformation. Finally, based on the core safety risk factors of the planning, design and construction stages of the subsea tunnel, the corresponding safety risk control measures were formulated.

Due to the similar features of different diseases and insufficient semantic information of small area diseases in the surface disease image of concrete bridges, the existing semantic segmentation models for identifying surface diseases in concrete bridges suffer from problems such as large number of parameters, insufficient feature extraction, and low segmentation accuracy. Therefore, this paper proposed a lightweight semantic segmentation method for concrete bridge surface diseases based on improved DeeplabV3+. Firstly, the lightweight improved MobileNetV3 was used as the backbone network to reduce the computational complexity of the model. Secondly, the CSF-ASPP (cross scale fusion atrous spatial pyramid pooling) module was designed to expand the receptive field, enable the model to capture more contextual information at different scales and improve its anti-interference ability. Finally, the focal loss function was used to solve the problem of sample imbalance. The experimental results show that the mean intersection over union (mIoU) and mean pixel accuracy (mPA) of the improved DeeplabV3 + reached 75.24% and 84.68%, respectively, which were 3.73% and 4.21% higher than those of DeeplabV3+. The segmentation accuracy for four diseases of spalling, exposed reinforcement rebar, efflorescence, and crack was better than that of DeeplabV3+, and it also achieved better segmentation results compared to other semantic segmentation models. The improved DeeplabV3 + model achieves a parameter size of 6.97 × 10⁶ and an inference speed of 52.64 FPS, demonstrating 90.33% reduction in parameters and 36.22 improvement in FPS compared to the DeeplabV3+. These advancements significantly enhance its suitability for real-time deployment on edge detection devices while maintaining high segmentation accuracy.

In order to study the instability mode of shield excavation face in soil-rock composite stratum and determine the ultimate support pressure of excavation face, this paper selects two typical soil-rock composite strata and uses three-dimensional finite element software to study the failure development process of shield excavation face. Based on the principle of limit equilibrium, a calculation model of limit support pressure for soil-rock composite stratum is proposed and applied to practical engineering. It is found that the shape of “unloading loosening zone” is mainly determined by the properties of upper soil and the properties of lower rock mainly determine the scope and shape of “sliding instability zone.” With the increase of soil proportion coefficient, the ultimate bearing capacity increases nonlinearly and the growth rate decreases gradually. At the same time, the influence of overlying Earth pressure and soil cohesion cannot be ignored.

Most of the tunnel projects are related to the national economy and people’s livelihood, and their operational safety is of paramount importance. Tunnel safety accidents or hidden safety hazards often start from subtleties. Therefore, the identification of tunnel cracks is a key part of tunnel safety control. The development of computer vision technology has made it possible for the automatic detection of tunnel cracks. Aiming at the problem of low recognition accuracy of existing crack recognition algorithms, this paper uses an improved homomorphic filtering algorithm to dehaze and clear the collected images according to the characteristics of tunnel images and uses an adaptive median filter to denoise the grayscaled image. The extended difference of Gaussian function is used for edge extraction, and the morphological opening and closing operations are used to remove noise. The breakpoints of the binary image are connected after removing the noise to make the image more in line with the actual situation. Aiming at the identification of tunnel crack types, the block index is proposed and used to distinguish linear cracks and network cracks. Using the histogram-like method to distinguish linear cracks in different directions can well solve the mixed crack situation in an image. Compared with the traditional method, the recognition rate of the new algorithm is increased to 94.5%, which is much higher than the traditional crack recognition algorithm. The average processing time of an image is 5.2 s which is moderate, and the crack type discrimination accuracy is more than 92%. In general, the new algorithm has good prospects for theoretical promotion and high engineering application value.

In the excavation process of a drilling and blasting tunnel, it takes multiple blasting excavations to form, so it is inevitable to produce multiple blasting impact loads, which will cause certain vibration damage to the surrounding rock-support structure. To solve this problem, based on the attenuation formula of blasting vibration wave and considering the cumulative effect of short footage blasting load, the radial displacement formula of surrounding rock particles is derived, and the analytical solution of vibration velocity field is obtained by using the method of separating variables. Then, taking Cuobuling station of Qingdao Metro as the engineering background, the finite element software is used to simulate the tunnel excavation process under the action of short footage multiple blasting. The vibration damage impact of multiple blasting loads on the surrounding rock-supporting structure is analyzed from the accumulated displacement value and vibration velocity cumulative value of the excavation tunnel. The results show that the damage accumulation effect is produced in the surrounding rock of each section during the blasting construction, among which the accumulation is the largest at the arch bottom. With the increase of blasting times, the damage of the surrounding rock is still accumulating gradually. Compared with the first blasting, the peak value of vibration velocity of the second blasting increased by 114%, and with the increase of blasting times, the variation trend of maximum vibration velocity of the measuring point showed an upward trend, but the subsequent vibration acceleration decreased. Under the condition of grade V surrounding rock, when the thickness of the concrete spray layer is 350 mm, the maximum displacement cumulative value of each measuring point in profile 1-1 is reduced by about 50.4% compared with that without support. According to the displacement nephogram of the concrete spray layer, the displacement of the concrete spray layer accumulates after three times of blasting, which affects the stability of the supporting structure. Finally, an example analysis is carried out and compared with the analytical model results to verify the accuracy of the mechanical model.

China is gradually transitioning from the "tunnel construction exploration era" to the "tunnel high-quality construction and operation era", and the maintenance demand of highway tunnels has increased sharply. Therefore, there is an urgent need for an evaluation method to evaluate the service reliability of highway tunnels, so as to provide reference for tunnel maintenance personnel to carry out maintenance work. Taking highway tunnels as the research object, this paper extracts three parameters, including length, maximum width and fractal dimension, from the binary image of highway tunnel lining cracks. The standard for dividing the length of the highway tunnel section is 500m as the tunnel section, and a section disease sample space including multiple highway tunnels is constructed. The EM clustering algorithm was used to determine the number of graded grades of disease, and the relative Euclidean distance was used as the evaluation index to divide the safety grade of the tunnel into five grades: normal, degraded, inferior, deteriorated and hazardous. The partial least squares method is used to establish the lining service reliability evaluation formula and verify the residual of each sample point in the sample space. The smaller the average value of the residual, the better fitting effect of the established evaluation formula. The service reliability evaluation method proposed in this paper is applied to engineering practice and compared with the expert scoring method and the national standard method, which proves that the evaluation method in this paper has the advantages of strong visibility, simple evaluation method, and is conducive to engineering practice.