Aiming at the prominent problems of ignoring the unnatural connection relationship and interaction relationship between human bodies in two-person interaction recognition algorithm, a two-person interaction recognition network based on improved spatial temporal graph convolutional model was proposed. Firstly, the edge features of joint point data were aggregated by edge convolution to capture the unnatural connectivity relations inherent in the human body. Secondly, the interaction relationship graph between two people was constructed by using the improved relationship network. Furthermore, the branch of edge convolution and the interaction relationship graph were embedded into the spatial temporal graph convolutional network block, which were constructed as an edge-graph convolutional block and interaction relation graph convolutional block. Finally, an improved spatial temporal graph convolution algorithm was proposed to capture both the unnatural connection relationship and the interaction relationship, so as to realized the recognition of two-person interaction behavior. To verify the effectiveness of the network, it was tested on the international public large-scale standard dataset NTU RGB + D. The experimental results show that the network obtain a recognition accuracy of 97.77%, which is an improvement of 4. 28 percentage points compared to the baseline spatial temporal graph convolutional network. It improves the expressiveness of two-person interaction behavioral features, and achieves a better recognition effect than the existing state-of-the-art network models.

In order to address the issue of coordinate base inconsistency in the fusion display of road building information modeling (BIM) models and tilted reality models within existing large-scale 3D geographic information system (GIS) platforms, a high-precision matching method for geographic coordinates between road BIM models and tilted reality models was proposed. Taking into account the distribution characteristics of road bands and the requirements for road maintenance, the model was initially segmented. Subsequently, a spatial distance-weighted least-squares coordinate matching parameter fitting method was developed based on the distribution of characteristic points on the road pavement and asset facility model, with a focus on accurately joining edges of the road pavement in each segment. Real road data was selected for conducting experiments to validate this coordinate matching method. The method effectively resolves bias issues in matching between the road model and tilted reality model, achieving accuracy at millimeter level post-matching, thereby meeting digital maintenance needs as well as dynamic updating requirements for road traffic facilities.

Fault diagnosis of industrial motor bearings is crucial for equipment performance and lifespan. Traditional diagnostic methods aggregate data from multiple factories, leading to issues with data privacy and high annotation costs. To address these problems, a fault diagnosis strategy based on adaptive local collaboration (ALC) federated learning was proposed. In this approach, bearing data under different working conditions was stored across multiple clients, with a central server collaborating with each client to build a federated learning diagnostic model. An improved ResNet-18 network was used as the classifier, which was trained within the personalized federated learning framework. The ALC federated learning method enables each client to effectively integrate global and local models, extracting global information to optimize local training results. Experiments demonstrate that this method enhances fault diagnosis accuracy while protecting data privacy, showing higher fault classification precision compared to other methods, especially in multi-factory environments.

Synthetic aperture radar (SAR) target recognition method based on deep networks requires a large amount of training data, and in practical applications, it is extremely difficult for SAR imaging systems to obtain sufficient and evenly distributed target data. One way to solve the small sample problem in SAR target recognition, is to use electromagnetic simulation technology to generate a large amount of SAR simulation data. However, there are still significant differences between simulated images and measured SAR images, so using simulation data directly cannot bring significant performance improvement for target recognition. A simulation data optimization method based on SAR target characteristic constraints was proposed to address the above issues. On the basis of analyzing the characteristics of SAR targets, a texture structure cycle-consistent generative adversarial network (TS-CycleGAN) based on texture structure and cycle consistency was constructed, in which the structural similarity measure was used to constrain the generation process of CycleGAN. This method can reduce the difference between simulation data and measured data, and can improve the usability of simulation data. The experimental results on the SAR SAMPLE dataset show that, compared to other simulation data optimization methods, the proposed method achieves significant improvements in image quality evaluation and classification performance.

In order to select advanced technologies applicable to civil aircraft, technical characteristics from various fields were integrated to develop an evaluation framework. Five key evaluation dimensions were identified: technology competitiveness, technology readiness assessment, economic impact, engineering methods, and technology standards. From practical case studies, these dimensions were derived and used as the basis for an evaluation index system. A technology application perspective was adopted, utilizing a cloud model and a reverse cloud generator to determine indicator weights. This approach incorporated technical standards from different industries, airworthiness standards, and the entire life cycle of civil aircraft to create comprehensive evaluation guidelines. The results show that this approach effectively compares advanced technologies across different industries, differentiates similar technologies at various levels, and eliminates those that offer no benefit or are unsuitable for civil aircraft. This evaluation approach successfully selects advanced technologies with a high degree of compatibility with civil aircraft.

Given the practical application background of installing underground pipelines in coal mine tunnels and the actual environmental conditions underground, a jointed tunnel pipeline installation robot was designed. The detailed design of the robotic arm structure was completed, along with its 3D modeling. The kinematic model of the robot was established, and MATLAB was employed to verify the forward and inverse kinematics of the robotic arm. Based on the established kinematic model, a trajectory planning algorithm for the Cartesian space of the robotic arm was designed, and MATLAB and ADAMS software were used to verify the robotic arm through simulation experiments. The simulation demonstrates that the structural design of the robotic arm is reasonable, and the trajectory planning scheme for the robotic arm is feasible.

As a widely distributed and abundant clean energy source, geothermal energy may lead to inefficient resource utilization and a series of ecological environmental issues when improperly developed. The typical geothermal distribution area in Linqing, Liaocheng City, Shandong Province was selects as the research object. Based on detailed geothermal geological survey data, the construction of a "multi-well coordination system" geothermal heating model was explored and the feasibility analysis with operational benefit was conducted. The results demonstrate that the proposed coordinated multi-well geothermal heating mode can reduce geothermal resource extraction by 41.46% while maintaining equivalent heating coverage and quality standards, significantly enhancing maximum utilization efficiency of geothermal resources. The system simultaneously achieves geothermal tailwater reinjection with favorable economic returns. The static investment payback period approximates 3 years, and the total revenue over 20 heating seasons reaches 25.742 million yuan. Through zoning division implementation in key operational areas, this model effectively addresses challenges including dense well distribution, uneven development patterns, and difficulties in reinjection well construction. The findings provide technical references and application demonstrations for geothermal heating development in other regions.

In order to accurately calculate the hydrodynamic parameters of the slope rill at any point during the erosion process, and to avoid errors caused by using the average flow rate to calculate the hydrodynamic parameters in the traditional method. Based on the variability and complexity of the development process of slope rills, as well as the characteristics of water sand two-phase flow, the Euler-Euler two-phase flow model was used to calculate and analyze the morphological evolution characteristics and erosion mechanisms of slope rills at different stages of expansion erosion. The results show that the Euler-Euler two-phase flow model can accurately describe the morphology evolution process of slope rill in expanded erosion. Based on the morphology evolution characteristics of slope rill at different stages of expanded erosion, the expanded erosion of slope rill is divided into the period when the rill sidewall is slightly spreading and eroding (the early stage), the period when the expanded erosion become severe with a significant increase in the number and area of amalgamated arcs (the middle stage), and the period when the expanded erosion basically ceased and the rill morphology stabilized (the late stage). The influential factors of slope gradient, initial flow rate, and preset rill width on the Darcy-Weisbach resistance coefficient, Reynolds number, and real-time flow rate are significant. Optimal characterization parameters for different stages of slope rill development, such as erosion arc length and hydraulic radius, are proposed, aiding in determining the specific period of slope rill development and predicting the development trend of rill morphology through changes in these parameters. The research results provide a theoretical basis for soil erosion control measures and are of great significance for soil and water conservation.

As a critical unconventional oil and gas resource within the global energy framework, heavy oil has garnered significant attention for its development efficiency. Although steam flooding technology has improved the efficiency of heavy oil production, the phenomenon of steam breakthrough negatively impacts thermal efficiency and reservoir development. Traditional prediction methods have shown inadequate precision and delayed response when dealing with long-term oilfield time series data. Data from 13 steam flooding well groups in the Shengli oilfield heavy oil block were utilized. An innovative approach was adopted, using the instantaneous temperature ratio between production and injection wells as an indicator of steam breakthrough time. Pearson correlation coefficient analysis was employed to select key factors related to steam breakthrough time. Based on these factors, a deep learning model built on the Transformer architecture was developed, achieving accurate predictions of the instantaneous temperature ratio. The predictions closely aligned with oilfield observation data, demonstrating higher prediction accuracy and stability compared to traditional long short-term memory (LSTM) models. The research results not only provide a new perspective for the precise prediction of steam breakthrough time in heavy oil reservoirs but also further validate the extensive potential of deep learning technology in oilfield development applications, supporting the construction of intelligent oilfield management and decision support systems.

The blowout preventer (BOP) is a key well control equipment, in which the shear ram BOP is the last line of defense against blowout accidents. Therefore, its shear performance under extreme working conditions is crucial for the safety of drilling operations. A super shear ram BOP was taken as the research object, and the numerical analysis was carried out by using the dynamics module. The simulation results were compared with experimental and theoretical values to verify the accuracy and applicability of the model. In order to investigate the influence of extreme working conditions on the shear capacity of the ram BOP, the shearing performance of the drill pipe joints was evaluated under high pressure working conditions, eccentric working conditions and moving conditions. The response surface method was applied to develop a shear force prediction model under extreme working conditions. Based on the prediction model and the actual shearing capacity provided by the ram BOP, the shearing failure scenarios under extreme working conditions were determined. The results show that the relative errors between the theoretical values and the simulation results are less than 3%. In the shearing process, the larger the axial tension and compression load, the more unfavorable the shearing. While the certain deviation distance is conducive to the shearing. The research results can provide technical guidance for preventing the shearing failure of ram BOP.