The significant advantages of point cloud data are presented in domains such as architectural reverse modeling, 3D reconstruction, and construction progress monitoring. Vast amounts of data are typically involved in the collection of point clouds for architectural structures, with the point clouds of components like beams and columns being particularly crucial. The challenges faced by current semantic segmentation methods for 3D point clouds when processing large-scale data include insufficient extraction of local features and suboptimal recognition accuracy. An enhanced approach for the semantic segmentation of large-scale point clouds of key architectural components using the RandLA-Net deep learning network was proposed. In this regard, the robustness of segmentation results was improved by incorporating a coordinate attention module in the local spatial encoding section. Furthermore, an extended channel attention module has been developed to strengthen the model’s capability in feature discernment, and a focal loss function has been introduced to effectively train the network, while addressing class imbalance issues within architectural point cloud scenes. Consequently, the efficient processing of architectural structure point cloud data and the extraction of key components are enabled. The performance comparisons and analyses conducted through experiments demonstrate that the original RandLA-Net model is outperformed by our model in terms of overall accuracy and component extraction precision in semantic segmentation of large-scale point clouds, thereby confirming the enhanced performance and practical value of the proposed method.

Bonding with existing concrete is one of the important application situations of self-compacting concrete. With the aim of investigating the bonding characteristics between DSSC (desert sand self-compacting concrete) and other existing concrete, the bond-casting test, bonding interface splitting tensile strength and sand-filling method was used to determinate the failure mode and analyze the influence of concrete type and interface treatment method on the bonding characteristics between old and new concrete. Scanning electron microscope was used to photograph the micro-morphological characteristics of the bonding interface and determinate the distribution of gap width. The results show that the bonding performance is stronger when the linear grooving is consistent with the loading direction. Compared with linear groove cutting, the drilling interface is more efficient in interface efficiency and bonding strength. Low water-to-cement ratio reduces the bond interface gap. The effect of desert sand on the reduction of the bond interface gap is more significant with low water-to-cement ratio.

In order to enhance the output performance of axial flow helical turbine drilling tools, it is crucial to conduct research on the structure and hydraulic performance of the turbine. Firstly, an analytical computational model for the hydraulic characteristics of two types of helical turbines, namely constant thickness blade and variable thickness blade, was established using calculus principles. Secondly, the blade profile equation was constructed to analyze the influence of helix angle on the hydraulic performance of the turbine. Finally, based on the design example of an underground helical turbine generator, the output performance parameters of the two types of helical turbines and the impact of helix angle were analyzed. Furthermore, a mud pulse generator was manufactured based on the optimized analysis results of the helical turbine, and indoor experiments were conducted to study the impact of different displacements on the power generation performance. The research findings show as follows. Under given conditions, the variable thickness helical turbine exhibits significantly higher hydraulic performance compared to the helical turbine with constant blade thickness. The turbine output characteristics curve sharply decreases as the helix angle of the blade increases. However, the decrease in turbine output characteristics becomes insignificant when the helix angle exceeds a certain value (approximately 30°). With 7 blade counts and a helix angle of 38°, the underground turbine generator reaches a maximum power of 300 W with a load of 8 Ω. Through indoor testing, the power of the generator meets the requirements of underground tools. This research provides a reliable power source for underground intelligent drilling equipment.

The problem of scheduling and collaborative decision-making in airport metroplex or terminal areas can be significantly approached by obtaining accurate ETA (estimated time of arrival). Traditional methods are short of the ability to fine-tune the arrival metering nodes. The accurate quantitative estimation of large-volume and complex flight traffic situations is hard to achieved especially under the influence of highly dynamic environments in a medium to long term. An ETA correction method based on error feedback was proposed. Based on the aircraft performance parameters, an aircraft kinematics model was firstly constructed combined with route planning and meteorological data, which was used to give a preliminary ETA prediction through the calculation of 4D trajectory then. After that an error sequence would be constructed by comparing the difference between ATA (actual time of arrival) and the predicted results, with it the next error could be predicted using the error feedback model and the results obtained previously would be corrected. Finally, the arrival flights to a large hub airport were taken as examples to conduct a simulation, in which the rate of error within ±5 minutes that predicted 30 minutes in advance was chosen as the evaluation criteria. The simulation results show that the accuracy of ETA prediction can be improved by more than 25% in bad weather after corrected by the proposed method when compared with traditional means.

In order to improve the path planning ability and efficiency of AUV (autonomous underwater vehicle), an AUV path planning algorithm based on the community information transmission mechanism was proposed. Firstly, based on the community information transmission mechanism, the global short and long connection operators were designed to achieve the optimal search of the neighborhood of the planned path points and the probabilistic search outside the neighborhood. Then, the local short and long connection operators were designed, which implements the search for four boundary derived points of the path center point and the connections of feasible paths outside the derived points. Finally, the AUV path planning algorithm flow was completed. Six simulation and two seabed map simulation tests show that, compared with other algorithms, the algorithm has the advantages of strong planning ability, high planning efficiency, and smooth planning path.

To study the effect of anchor length on anchorage effect of weak rock masses in a deep tunnel, the indoor similar model tests were carried out on failure test of rock masses during the excavation opening. The variation characteristic on the failure, displacements and stress of the rock mass after excavation were analyzed comparatively under three conditions (without anchors, with short anchors and long anchors).In the loading test, the failure process of rock mass around the opening shows that the failure process of surrounding rock occurs first at the side wall, then the arch waist and the arch collapse. The surrounding rock in the arch roof after reinforcing rock bolts forms the effect of strengthening beam because of the reinforcement of rock bolts, which leads to the significant increase in the maximum settlement and failure load of the arch roof. The length of rock bolts need to pass through the plastic loosening zone of the arch roof. If the length of anchor rod is not enough to anchor the whole plastic loosening zone, there will be stratification between the anchored surrounding rock and the unanchored surrounding rock. Based on the theory of homogenization strength of rock mass, the short bolt mainly increases the effective support force of surrounding rock at shallow tunnel wall, thus improving the strength of surrounding rock, and the long bolt (cable) can regulate the stress in the elastic zone of deep surrounding rock. Therefore, the combination of the long bolt (cable) effectively regulates the stress state of surrounding rock.

With China’s Manufacturing 2025 Plan, the military industry to implement the unmanned production line, and AGV (automated guided vehicle) as a fully automated production line of the main logistics carrier, the scheduling of its strengths and weaknesses directly determines the capacity and efficiency of the entire production line. Due to the security requirements of military industrial places, wireless communication and other means cannot be used, and only point-to-point optical communication can be used, which also worsens the real-time communication of AGVs. Based on Plant Simulation software, a simulation system model was established, the real-time data interaction channel between the logistics simulation software and the field controller was opened, the synchronous operation of the simulation system and the reality was realized, and the seamless connection between the logistics simulation software and the field controller was completed, which effectively solves the difficult problem of poor real-time AGV scheduling caused by the lack of wireless power in the military industry. Experiments have proven that this method effectively simplifies the difficulty of writing the scheduling system and improves the overall real-time performance of the system by 0.058 seconds. Compared with the traditional method, the writing time is shortened by 9.7 times, and the debugging time is even shorter by 22 times. This study lays the foundation for the realization of full automation of military production lines and provides technical support for the use of pulsation production lines in hazardous places.

To explore the feasibility of using AI (artificial intelligence) three-dimensional motion analysis for analyzing the influencing factors on the distance of ski jumping and optimizing athletes’ technical movements, a study was conducted during the 2022 FIS Continental Cup Beijing event. Sixteen athletes’ take-off phase motions were captured within a fixed range using AI-based three-dimensional motion analysis system. This system automatically parsed the videos to obtain biomechanical parameters of the athletes’ take-off phase. By comparing the correlation coefficients and differences between manually processed data and AI-generated data of the three-dimensional coordinates of body joints over time, the validation of the equipment for ski jumping was conducted. The multiple correlation coefficient was found to be greater than 0.91, with an average difference value of less than 1.48 cm, indicating the reliability of the system. Furthermore, a comparison was made between the technical parameters of high-level foreign athletes and domestic athletes. Using t-tests and Pearson correlation coefficient analysis, the relationship between body posture parameters during the take-off phase and sports performance was examined. The results reveal correlations between take-off speed and angles of ankle and knee during the take-off phase, and between the final score and ankle angle during take-off, suggesting that Chinese athletes should focus on achieving full extension during take-off and timing their jumps appropriately to significantly enhance sports performance. Overall, the system demonstrated precise feedback for ski jumping technique analysis. Additionally, it enabled the acquisition of biomechanical parameters from world champion athletes to construct a champion model, providing valuable training references for Chinese athletes.

The anti-corrosion maintenance workload of railway fasteners and bolts in China is large, and the cost of manual lubrication operation is high, the efficiency is low, and the labor intensity is high, and there are problems such as operation safety risks and ballast pollution. In order to solve this series of problems, an automatic lubrication device based on PLC(programmable logic controller)control that can automatically lubricate fasteners and bolts on railway tracks was developed to realize the efficiency, intelligence and automation of the construction process. Optimize the design of the equipment’s traveling mechanism, lubrication system, fastener bolt identification and sensing device, control system, etc. The adjustable spraying structure was innovatively designed to realize the oil coating operation of different types of tracks, and the sensor device that can adapt to the change of the height and position of the rail fastener bolts was innovatively designed, so as to realize the accurate identification of the track fastener bolts with different height distribution. According to the characteristics of anti-rust grease, the quantitative atomization technology of the device was analyzed and optimized. Delta’s DVP ES2-24MR PLC is connected to an external actuator, which processes data through the PLC to control the corresponding sensors in real time, and uses compensation algorithms to achieve accurate control of the equipment oil coating operation. The experiment shows that the automatic lubrication device shortens a large number of construction periods, solves the pollution phenomena such as inaccurate lubrication, oil dripping and wire pulling of the existing mechanical lubricating machine, and the device can effectively guarantee the quality and safety of the lubrication operation, effectively improve the construction efficiency and reduce the construction cost.

Content Aiming at the problems of single convolution model, insufficient Receptive field and inaccurate feedback information of single discriminant network in current face image super-resolution reconstruction algorithm, an algorithm based on adaptive convolution and joint Loss function was designed. A generation adversarial network architecture was used by the model. On the generator side, adaptive convolution was used to construct dual path residual blocks and further form efficient residual groups. It can independently learn feature weights extracted under different receptive fields and supplement missing information from a single branch. The subpixel convolution layers were used to complete quadruple reconstruction of face images. In terms of discriminators, Vgg and U-net architecture networks were used as dual discriminant networks, and dual discriminant results were used to calculate adversarial losses. The losses, content losses, and perceptual losses form a joint loss function. Experiments on the Celeba dataset show that compared with RWSA, this algorithm improves PSNR by 1.166 dB, SSIM by 0.037, LPIPS by 0.033, and PI by 0.119, compared with other mainstream algorithms, it has advantages in image detail clarity.