In order to solve the problems of missed detection and false detection in the current remote sensing image small target detection task, a SMCA+CSC+shape-aware intersection over union loss(SIoU)-you only look once(SCS-YOLO) remote sensing image small target detection algorithm was proposed. Firstly, in response to the problem of small and clustered targets in remote sensing images, a spatial multi-scale convolutional attention module(SMCA) was constructed to improve the model’s feature extraction ability of spatial and channel information. Secondly, in order to solve the problem that the semantic information of small targets was easy to be lost during deep network transmission, the aggregation subpixel convolution module concentrated sub-pixel convolution(CSC) was designed, and the multi-scale aggregation feature extraction method was used to enhance the ability of the network to extract semantic information. Finally, the SIoU loss function was used to replace the complete intersection over union loss(CIoU) loss function in the original model, which accelerated the convergence speed of the network. The average of the average precision(mAP)of the SCS-YOLO model reaches 97% and 90.9% on the RSOD and NWPU VHR-10 datasets, respectively, which is 2.2% and 2.7% higher than that of the original model, which shows the effectiveness of the method in the small target detection task of remote sensing images.

Due to the complex underground environment, low lighting conditions, and the small size of hard hats, the detection results are not ideal. To address low-quality images in complex environments, an improved YOLOv7 for hard hat detection in low-quality images from underground coal mines was proposed. Firstly, addressing the limitation that image features were susceptible to noise interference under low-light conditions, a multi-scale MELAN module was introduced. By constructing a multi-scale attention mechanism, broader contextual information was captured, thereby enhancing feature extraction and effectively suppressing noise interference. Secondly, the OD-SMP module was constructed using soft pooling and full-dimensional dynamic convolution in the backbone network, which reduced information diffusion in feature mappings, retained more contextual information, and enhanced the detection capability for small targets. Finally, to address the varying quality of detection samples caused by the complex backgrounds and environments with different lighting and distances in underground coal mines, Wise-IoU was used as the loss function. Experimental results show that the average precision of the improved model is 94.9%, which is 13.5% higher than the original YOLOv7 model, demonstrating better detection performance.

Due to factors such as temperature, pressure, and production rate, integrity issues like annular leakage in gas well tubing frequently occur frequently. In order to study the influence of working conditions on the process of downhole oil pipe leakage, a high temperature and high pressure oil pipe leakage simulation model was established based on field parameters and compared with the existing mathematical model of small hole leakage. Based on the simulation model, the influence of flow field change, leakage aperture, casing pressure difference and leakage environment on the leakage process was analyzed. The results show that the changes of flow field mainly focus on the inside of the leak hole and the inlet and outlet of the leak hole. With the increase of the leak aperture, the leakage quantity, leakage velocity, pressure and density inside the leak hole increase. The greater the pressure difference between tubing and oil jacket annulus, the greater the leakage amount and leakage velocity, and the more drastic the change of pressure and density. The gas velocity and pressure in the upper part of the annular protective fluid are greater than that in the annular protective fluid section.

Modern air traffic management systems necessitate efficient and accurate identification and classification of hazard-related text data to ensure flight safety. Air traffic control hazard data encompasses information on potential factors, conditions, or events that may adversely impact aviation safety. Existing text classification methods face challenges due to the diversity of data categories and imbalances within classes. An enhanced ensemble model based on the Stacking framework, incorporating a dual-weighting mechanism was proposed for improved performance. A dual-protection strategy was implemented to categorize hazards and safety risks systematically. The methodology employed the term frequency-inverse document frequency(TF-IDF)algorithm to extract and vectorize features from preprocessed hazard texts. To address class imbalance, the synthetic minority over-sampling technique(SMOTE) and adaptive synthetic sampling approach(ADASYN)algorithms were utilized to generate synthetic samples for minority classes. The Stacking ensemble model was refined by dynamically weighting the F₁ scores derived from cross-validation of base learners and integrating a sensitivity assessment mechanism across the ensemble. Experimental results on the constructed dataset demonstrate that the ADASYN-enhanced ensemble model achieves notable improvements in precision, recall, and F₁ scores by 0.9%, 1.1%, and 1.0%, respectively, effectively mitigating overfitting in majority classes. The proposed algorithm significantly enhances the classification performance of imbalanced hazard text categories, contributing to the advancement of safety risk management in air traffic control.

To enhance heat transfer efficiency and improve thermal exchange performance, a composite enhanced thermal exchange technology was explored that combined annular internal fins with protruding units, aiming to create an innovative thermal exchange structure. Through numerical simulation methods, the flow and heat transfer characteristics of this structure were studied within the Reynolds number Re range is 8 000~20 000. The analysis results indicate that the layout of the protruding units and four parameters (depth, radius, spacing, and quantity) have a significant impact on thermal performance. The mechanism of enhanced heat transfer was explained using field synergy theory. Under optimal parameters, with a depth of 2 mm, a radius of a specific value, a spacing of 20 mm, and six protruding units, the best thermal exchange performance is achieved, with an overall heat transfer performance improvement of 4.71%~23.59% compared to internal finned tubes. Increasing depth, radius, and quantity, while decreasing spacing, enhances heat transfer but also increases resistance, limiting the growth of overall thermal performance. Field synergy analysis shows that the structure promotes strong secondary vortices, significantly enhancing the synergy effect between the velocity field and the temperature field.

Explicit content features of webpages are often unavailable due to distractions such as commercials, insufficient permissions, privacy protection, or deceptive disguises. To address the challenge of classifying webpages with severe content feature deficiency, a method combining graph embedding and extreme gradient boosting(XGBoost) was proposed. This method leveraged implicit relational features in webpage hyperlink networks for multi-classification. Firstly, a hyperlink network was constructed using relationships between webpages. Then, node features were extracted using graph embedding models, and statistical structural features such as clustering coefficients and PageRank values were concatenated to form dense feature vectors. Finally, ensemble learning models, including XGBoost, were trained to classify webpages for prediction. Experiments on a real Wikipedia dataset show that the Struct2Vec*+XGBoost approach achieves excellent classification results, with accuracy, precision, recall, and F₁-score metrics reaching 0.987 5, 0.965 9, 0.971 3, and 0.964 1, respectively. These results are superior to those of comparison models. The findings demonstrate the effectiveness of using implicit link-based features for webpage classification in scenarios with content feature deficiency.

In order to effectively evaluate and control the operational risks of unmanned aerial vehicle(UAV), based on the summary of various risk factors of UAV ground impact, the possible causes of UAV ground impact were analyzed, corresponding control measures were determined, and a safety barrier model combining risk analysis and control technology was established. It can clearly display the logical relationship between the causes of UAV operation safety, mitigation measures and accident consequences. Bow-tie (BT) model was mapped to Bayesian network (BN), each element of BT model was quantified, and the probability of unsafe events was calculated. The results show that the model can clearly show the risk control process and effectively reduce the operational risk of UAV. It provides an efficient and practical method for the operational risk assessment and control of UAV.

Shield tunnel construction impacts old buildings in urban areas. Extensive building deformation data was collected for Tianjin Metro Line 7’s shield tunnel passing beneath old buildings using automated measurement robots. Machine learning algorithms were applied to analyze the correlation between building instantaneous settlement and shield construction parameters such as average velocity, thrust, grouting volume, shield distance, and grouting pressure. A predictive model for building settlement was established. The results show that old buildings within -50~70 m are affected by shield construction. Differential settlement is significant, with noticeable differences on various facades. Grouting volume, thrust, and average velocity positively correlate with instantaneous settlement, with shield distance having the greatest impact. Reasonable construction parameters ensure building settlement and deformation remain within acceptable limits. The machine learning-based predictive model closely aligns with actual settlement curves, demonstrating robust predictive capabilities. This provides valuable insights for predicting and controlling surface settlement in future shield tunnel projects.

In order to alleviate the collision risk of non-intersecting runways simultaneous operation, it is necessary to apply a control strategy conforming to the operation characteristics. A collision risk assessment model was constructed by using event tree analysis and Monte Carlo method. Based on event tree analysis, the event to be solved was determined. The probability of related events was calculated by Monte Carlo method. By statistical and fitting the collision event data obtained by the experiment, the safety target level was standardized and the control strategy was put forward. Finally, taking the approach of 01L and the departure of 29R on the non-intersection runways of Daxing Airport as an example, the departure shielding window (0.41~7.39 km) was obtained. Using this strategy, the risk of aircraft collision can be controlled at an acceptable level. The proposed computational model of departure shielding window is of general applicability to the formulation of safe operation control strategies for non-intersecting converging runways.

Due to the unclear constitutive relationship between the structure and performance of styrene-butadiene-styrene block copolymer(SBS) modified asphalt, the current way to improve the performance of SBS modified asphalt is still to simply increase its SBS content. However, early pavement diseases are still frequent. To explore the effect of swelling degree of SBS on the rheological properties of modified asphalt and its internal mechanism without increasing SBS content. The microstructure of SBS modified asphalt was observed by fluorescence microscope. The conventional properties and rheological properties of SBS modified asphalt were analyzed by dynamic shear rheometer. The internal mechanism of the influence of SBS swelling degree on the performance of SBS modified asphalt was revealed by molecular dynamics. The results show that the fully swollen star-line blended SBS modified asphalt has a higher swelling area, and has obvious performance advantages in terms of conventional performance, rheological properties and anti-aging properties. Molecular simulation shows that the complete swelling of SBS makes the radial distribution function peak of SBS modified asphalt higher, which improves the interaction between SBS molecules and light components in SBS modified asphalt. On the basis of maintaining the original stable asphalt colloid structure, SBS styrene ends are interconnected to form π-π conjugate, which improves the toughness of SBS network.