Accurately predicting bike-sharing flow is essential for optimizing the supply-demand balance of shared bikes and enhancing urban residents’ travel convenience. To address the issues of low prediction accuracy and insufficient capture of spatiotemporal characteristics in bike-sharing flow prediction, a hybrid convolutional-recurrent neural network (Conv3D-GRU) model was proposed. Using Chicago’s 2022 full-year bike-sharing data, experiments were conducted, and the results were compared with those of the 3D convolutional neural network (3D-CNN) model and the convolutional long short-term memory (ConvLSTM) model. The model performance was evaluated using root mean squared error (RMSE), mean absolute error (MAE), and the coefficient of determination (R²). Experimental results show that compared with the 3D-CNN and ConvLSTM models, Conv3D-GRU is improved by 3.25%, 4.90%, 1.14% and 11.94%, 13.70% and 2.46% on RMSE, MAE and R², respectively. This demonstrates that the Conv3D-GRU model has lower prediction errors and higher prediction accuracy, making it an effective and reliable approach for forecasting bike-sharing inflow and outflow.

In order to investigate the potential causative factors and mechanisms of accidents in the flight transit security system, and to further ensure the safety of civil aviation operation, based on the system theory and the gray correlation theory, and combining with the actual situation of the flight transit security operation process, the safety problems in the system were transformed into the control and feedback problems, and the safety control and feedback structure was mapped out. Using complex network theory to transform accident causation and its logical relationship, a directed weighted accident causation network model was constructed, the overall characteristics of the network and the connection of each node from different perspectives were quantitatively analyzed, such as the node degree, the network diameter and the average path length, etc., and then 16 important accident causation factors affecting the flight transit security system were selected. Through grey correlation analysis, the influence degree of each cause factor on the accident was judged, and the key cause factors that need to be prevented and controlled were finally determined. The results show that the personnel factor dominates the accidents in the flight crossing security system, and its sub-factors, such as speeding, insufficient number of personnel, error of towing personnel and illegal entry of personnel into the control area, are the key causal factors leading to the accidents.

Weld defects present within pipelines constitute a considerable threat for leakage and rupture accidents. To elevate the detection precision of these defects, X-ray inspection was employed as a means to identify and locate them with greater accuracy. However, the diverse types, small sizes, and complex backgrounds of weld defects posed challenges for accurate detection. To address the limitations of current deep learning-based models, such as inadequate adaptability to complex backgrounds and lighting variations, as well as poor performance in detecting small targets, an improved faster region convolutional neural networks(Faster R-CNN) network model was investigated. This model incorporated a channel attention mechanism into the backbone network, modified the residual block structure, and employed ROI Align to replace the traditional ROI Pooling. The results show that compared to the original algorithm, the improved Faster R-CNN model achieves significant improvements in mean average precision (mAP) and F₁, with respective increases of 15.82% and 16.44%. It is concluded that this improved model can meet the high-precision requirements for weld defect detection and holds significant theoretical importance as well as promising prospects for engineering applications.

Compared to image instance segmentation in general scenes, instance segmentation in complex stacked scenes is affected by complex situations such as severe occlusion and stacking of similar objects, making instance segmentation more difficult. To solve the problem of garbage instance segmentation in complex stacking scenarios, an instance segmentation algorithm combining YOLOv8 and two-layer feature network strategy was proposed. Firstly, the feature data was layered in the data preprocessing part, and the two-branch feature fusion was realized through the graph convolutions network (GCN), which reduces the influence of stacking on the features of the occluded objects, thus solving the instance segmentation problem under complex stack occlusion. At the same time, in order to solve the problem that similar objects are easily confused, a soft threshold non-maximum suppression algorithm and a new intersection ratio algorithm were integrated. Finally, according to the complexity of application scenarios and data sets, the feature extraction module of the backbone network was optimized, and the multi-scale attention mechanism was introduced in the backbone network, which effectively improves the detection performance of the model. In the experiment, examples of occlusive garbage classification were used to segment the dataset. The experimental results show that this method outperforms other methods in terms of average accuracy, average accuracy when the intersection to union ratio threshold is 0.5 (AP₅₀), and average accuracy when the intersection to union ratio is 0.5~0.95 (AP_50~95). Compared with the original YOLOv8 algorithm, the detection AP₅₀is increased by 7.9% and the segmentation AP₅₀ is increased by 5.4%, which has better detection and segmentation effects.

A numerical calculation model for airfoil dynamic stall numerical simulation was established by computational fluid dynamics method, and the influence of plunging motion on airfoil unsteady aerodynamic force was analyzed. The simulation results were compared to the pitching motion wind tunnel experimental data of NACA0012 airfoil, and the results of the model under mild stall and deep stall conditions were in good agreement with the experimental values, which verified the accuracy and feasibility of the numerical calculation model. The plunging motion of NACA23012 airfoil was equivalent to the pitching motion, the lift characteristics of airfoil under the two motion modes are very close, but the moment characteristics are obviously different. With the increase of amplitude of plunging motion and inflow Mach number, the difference of moment characteristics is further expanded. With the increase of amplitude of plunging motion, the damping effect of aerodynamic moment of pitching and plunging motions is obviously enhanced, with the increase of inflow Mach number, the damping effect is reduced, and the moment divergence occurs when the Mach number is 0.85.

Aiming at the problem of time-consuming and labor-intensive routing path design in the cable layout design of complex electromechanical products, an automatic routing technology for complex electromechanical product cables based on multi rules particle swarm algorithm was proposed. Firstly, the cable routing environment of electromechanical products was analyzed, and the routing path was abstracted into a sequence of points to complete the definition of cable routing space. Through pose transformation, the problem of difficult interference detection between wiring paths and parts in electromechanical products was solved. In order to make full use of the wiring space, the particle multiple rules were introduced into the particle swarm optimization algorithm. By using particle number, multi-scale collision detection, adjacent waypoint replacement method and fourth-order quasi-uniform B-spline curve method, the problem that the routing environment is complicated and the optimal solution cannot be obtained was solved, and the searching ability, solving speed and routing quality of the algorithm were improved. Through simulation analysis and comparison with other algorithms, the superiority of the algorithm is proved. The example proves that the proposed method can search feasible paths efficiently during routing. The generated routing paths do not interfere with parts in three-dimensional space, and there are no mutation points in the path fairing, which provides a new idea for the automatic routing of complex electromechanical products.

The Permian Wutonggou Formation in Dixi area of Junggar Basin has huge potential for oil and gas exploration. Based on the latest seismic data, combined with thin section data, drilling and logging data, rock physical properties and physical parameters, using seismic forward modeling, wave impedance attributes and waveform clustering attributes, the basic characteristics of the reservoir were characterized, the seismic waveform identification method of the upper and lower sand groups in the first member of Wutonggou Formation was clarified, the thickness distribution law of the upper and lower sand groups was described, and the sedimentary facies development characteristics of the upper and lower sand groups were clarified. The results display that the sandstone of Wutonggou Formation is mainly lithic sandstone and feldspar lithic sandstone, which belongs to low porosity and low permeability reservoir. The seismic waveform characteristics of sand bodies are significantly affected by seismic resolution, sand body thickness, mudstone interlayer thickness, sand body superposition relationship and underlying lithology. The sand body distribution regular pattern based on the interpretation of the sand body waveform characteristics of the forward model is highly consistent with the average wave impedance attribute distribution regular pattern. The study area develops delta front underwater distributary channel microfacies, estuary dam microfacies, underwater tributary bay microfacies and sheet sand microfacies. There are great differences in the development characteristics of sedimentary facies between the upper and lower sand groups.

In September 5, 2022, a M6.8 earthquake occurred in Luding County Sichuan Province. Quite a lot of store-front type buildings damaged or collapsed. Five representative buildings representing both positive and negative aspects were selected to analyze the earthquake damage mechanism through theoretical basis and model experiment. The results show that the earthquake damage is mainly concentrated in the bottom layer, which is composed of concrete column and masonry wall. The masonry wall with no lateral openings restrains the transverse and torsional deformation of the structure, and the floor only transports along the longitudinal direction, and the seismic shear force shared by each member is proportional to its longitudinal lateral stiffness. The rigid and brittle members with large stiffness will appear “internal force condensation”, and then reach “deformation saturation”, and lose the load-bearing capacity in the way of brittle failure, and the gravity of the upper layers will be borne by the transverse wall. If the earthquake does not stop at this time, the transverse wall will lose the role of “buttress” in the direction of exit plane, and the whole structure will collapse along the longitudinal contact with the ground. On the contrary, if the structure of the bottom layer avoids large differences in stiffness, it can significantly improve the seismic resistance.

Aiming at the problems of anti-noise, anti-high resistance and complex threshold setting of traditional pole selection methods, a fault selection method of flexible DC distribution line based on Res-BiLSTM network was proposed. Firstly, the original fault signal was subjected to complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and then the reconstructed signal was obtained by using the correlation coefficient and Shannon entropy for reconstruction. Secondly, the Res-BiLSTM network model was constructed for the pole selection. In order to improve the network accuracy and the convergence speed, the channel attention module was introduced into the split-attention network. The reconstructed signal features were extracted using the convolutional bidirectional long short-term memory and the improved split-attention network at the same time. The extracted features were fused using the attention feature fusion module, and the fused features are classified. Finally, PSCAD/EMTDC was employed to construct the model and to verify the proposed methodology. The simulation results show that the proposed pole selection method is highly accurate, anti-interference, and independent of fault distance.

With its advantages in cooling efficiency and cost, the cold channel closed system is more and more used in the construction of new data centers. However, the closed channel system will turn the originally open channels between data center cabinets into narrow spaces with restricted ventilation. When the main combustibles in the data center catch fire, the accumulated hot smoke and gas in the closed channel cannot be timely discharged, seriously threatening the safety of data center equipment and personnel. At present, there is a paucity of experimental data and theoretical basis for the fire hazard of cables commonly used in data centres. Pyrosim software was used to establish a full-size physical model of the data center room in the cold closed channel, and fire dynamics simulator(FDS) software was used to establish a full-size fire model to simulate different fire source locations, so as to analyze the changes of fire parameters such as smoke spread rate, visibility and temperature distribution. The results show that when a fire occurs under the floor (maximum heat release rate reaches 2 000 kW), the smoke would fill the whole machine room more quickly due to the influence of the special air conditioning airflow and floor than the cabinet fire. The visibility at the safety exit measuring point reached 0 m, 60 s earlier than the fire at the inside of the cabinet. At the same time, affected by the air conditioning airflow and perforated tiles, the temperature at the inside of the cabinet quickly reaches the critical value where the fire hazard is much greater. The results could provide important theoretical support for the fire protection system design of the cold channel of closed data center.