In order to investigate the influence of porous materials on the explosion propagation characteristics of LPG in vent pipes，experiments were conducted on a self-built gas explosion test platform. The inhibitory effect of silicon carbide materials with different thicknesses and porosities on the flame propagation characteristics and explosion overpressure in the vent pipe was investigated. The results show that porous materials can effectively prevent the propagation of LPG explosion flame. With the increase of porosity and thickness，the propagation distance，propagation speed and intensity of LPG flame are reduced，and the porosity has a greater effect on the fire resistance than the thickness. The installation of porous materials also reduces the maximum explosion overpressure. When LPG is not ignited behind the installation location，increasing the porosity and thickness of porous materials，the maximum explosion overpressure in front of the material (PT1，PT2) increases，and that behind the material (PT3) is close to the static film-breaking pressure. The firestopping effect of material porosity and thickness shows that increasing the porosity of the material for firestopping should be prioritized when the strength of the material is up to standard in engineering applications.

In order to improve the performance of small target detection in infrared imaging and the ability of low altitude airspace supervision，an infrared small target detection network based on multi-scale attention feature enhancement fusion was proposed. Firstly，Resnet34 was used to extract the multi-scale features of infrared images. Secondly，the multi-scale spatial attention feature enhancement module(MFEM) was used to improve the ability of feature extraction. Then，in the step-by-step up sampling process，the dual channel attention feature fusion module(DFFM) was used to fuse the semantic information and detail information to better protect the characteristics of infrared small targets. Finally，taking the video sequence detection of ground/air infrared dim small aircraft target as an example，the real scene test was carried out by comparing with other methods. The results show that compared with existing methods，the proposed method improves the scores of intersection over union(IoU)，F-measure and false negative rate(FNR)，and can accurately locate the target and generate good segmentation results. The DFFM can simultaneously use multi-scale context information and spatial attention mechanism to highlight infiared small targets. The DFFM assigns weights to sets of different channel features，thereby obtaining the most appropriate feature map for feature fusion and improving the detection performance.

To address the low prediction performance of drilling risks in unknown formations during oil and gas development，a drilling risk assessment approach based on grey adjacent well information was proposed. Firstly，a three-parameter interval grey number was proposed to present formation information. Secondly，the depth adjustment and weighted interpolation methods were used to develop a target well gray wellbore information matrix based on adjacent well information. Subsequently，a three-parameter grey safety drilling fluid density window was proposed. Then，a risk assessment model including overflow，well leakage，collapse，and adhesion was developed based on generalized strength-interference theory. Finally，a case study was performed on five wells in an oil field in western China. The results indicated that introduced concept of wellbore information matrix and optimization parameter description of depth adjustment and weighted interpolation effectively presented the profile of the target well's wellbore information. The grey safe drilling fluid density window developed by three-parameter interval grey numbers and wellbore information matrix significantly reduced uncertainty in drilling risk assessment. The evaluation results from drilling risk assessment model based on generalized strength-interference theory agreed well with that in real situations，providing reliable fundamental knowledge for drilling risk assessment.

In order to study the reasons for the deterioration of the anchor performance caused by groundwater variation，a series of physical model tests were employed to explore the anchorage enhancement of the expanded anchor in the anti-floating process. Firstly，a single pull-out test was carried out through the indoor model test，and the change of bearing capacity of multi-bell-shaped expanded anchor under different buried depths during the pull-out process was obtained. Secondly，according to the ultimate uplift bearing capacity obtained from the single pull-out test，the cyclic test was carried out to explore the evolution mechanism of the bearing performance of the multi-bell-shaped expanded anchor under different cyclic amplitudes，cyclic times and cyclic frequencies. Finally，the image particle velocity method (PIV) was used to analyze the deformation mechanism of the surrounding soil，and the variation characteristics of the surrounding soil displacement under single pulling-out and cyclic loading were obtained. The test results show that the axial load-displacement curve of the bell-shaped expansion anchor can be roughly divided into three stages: elasticity，vibration and failure. With the increase of buried depth，the ultimate bearing capacity and soil displacement of the anchor increase. Under the action of cyclic loadings，the increase of the cyclic load ratio，the number of cycles and the cycle frequency will weaken the bearing capacity of the anchors.

In order to solve the problem that the pressure drop signals caused by compressor suction or upstream block valve cut-off conditions leaded to incorrect shut-off of the block valve，and the problem that the block valve failure due to insignificant pipeline pressure drop caused by small hole leakage，a simulation model was established. Taking a typical gas transmission trunk line as the research object，300 sets of pressure drop signals under three different working conditions，namely compressor suction，emergency cut-off of the block valve and pipeline leakage，were obtained. The pressure drop rate of the pressure drop signal was calculated by point-to-point detection method. Singular value decomposition(SVD) method was used to extract the characteristics of the pressure drop rate signal，and the min-max normalization method was used to normalize the characteristic values of the pressure drop rate signal. SVM method was used to identify the characteristic value signals of different pressure drop rates，and the corresponding working conditions were obtained. To solve the problem that the unreasonable setting of kernel function parameters and penalty factors in the SVM model affected the accuracy of algorithm recognition，TLBO algorithm was used to optimize the kernel function parameters and penalty factors，and a TLBO-SVM model for intelligent identification of gas pipeline leakage signals was established. The model was applied to classify and identify 300 groups of simulated pressure drop rate signals in three working conditions. The results show that the recognition accuracy of the model is 92.22% for three kinds of pressure drop rate signals under different working conditions. The identification accuracy is 96.67% for small hole leakage with a leakage diameter of 50-125 mm and a pressure drop rate range of 0.01-0.07 MPa/min. For the actual leakage pressure drop rate signal of a main pipeline，the accuracy of TLBO-SVM is 100%.

In order to solve the problems that some operating conditions could not be automatically identified and the accuracy of abnormal operating condition recognition was low in the process of monitoring the production and operation of multi-product pipeline system，the intelligent operating condition recognition method was applied to construct a multi-product pipeline operating condition recognition model with real-time monitoring capability. First，logic rule discrimination methods and event logs in the multi-product pipeline system were used to supplement the data labels. Second，the data were segmented according to the start and end time of the operating conditions，and the subsequence of different operating conditions were extracted by using the sliding window. Third，the features of subsequence were extracted to construct the model for operating condition recognition of multi-product pipelines，and the recognition effects of six classification models，namely，random forest (RF)，adaptive boosting (AdaBoost)，support vector machine (SVM)，time series forest (TSF)，random interval spectral forest (RISF) and sequence learner (SEQL)，were compared and analyzed. Finally，a real multi-product pipeline was used as an example for model validation. The results show that the TSF model has the highest recognition accuracy for the four operating conditions of valve switching，valve internal leakage，pigging and sling pump，and is more suitable for the recognition of short-term operating conditions. In contrast，the recognition precision of the AdaBoost model has a higher probability of including the true value in the 95% confidence interval.

In order to explore the mechanism of rock burst induced by the instability of coal rock combinations under different dip angles，a particle discrete element program was used to conduct uniaxial compression tests on five sets of coal and rock combination models with different dip angles: 0，15，30，45 and 60°. The research results indicate that coal is the main cause of instability and failure in coal-rock combinations. When the dip angle of the coal-rock combination increased from 0° to 30° and from 30° to 60°，the uniaxial compressive strength of the coal-rock combination decreased by 2.01% and 9.59%，and the number of microscopic cracks decreased by 22.9% and 4.0%，respectively. The appearance time of the acoustic emission signal is advanced，indicating that the increase in dip angle led to a decrease in the uniaxial compressive strength of the coal-rock combination，and the instability failure time is advanced，but the degree of failure is reduced. In the early stage of uniaxial loading，the movement of coal and rock particles at the interface of different dip angle combinations led to an expansion trend at the interface. The dip angle affected the movement of coal and rock particles near the interface，leading to a gradual transition of the failure area of the combination from the coal body to the coal-rock interface. When the cracks in the coal body extend to the coal-rock interface，the interface slip effect generated by the high dip angle coal-rock combination causes its failure mode to change from compression shear failure to slip failure，with a 30° dip angle as the boundary.

In order to reveal the effect of water content on the tensile and compressive mechanical properties of coal samples，coal samples from the No.22 seam of the Hanjiawa coal mine were selected. Brazilian disc splitting tests，uniaxial compression tests，and triaxial compression tests were conducted on coal samples with different moisture contents and confining pressures to explore the mechanical characteristics of water containing coal samples. The results show that the strength and elastic modulus of coal samples decreases exponentially with increasing water content. When the coal samples reach saturation，the strength and elastic modulus decrease by 48.3% and 37.6% respectively. With the increase in water content，the plasticity of coal samples is enhanced，and the samples are prone to breakage. Under triaxial compression，the peak value of failure and the strength of coal samples increase with the increase of confining pressure. However，the strength of water-bearing coal samples under different confining pressures is obviously lower than that of dry coal samples. The water content has little effect on the internal friction angle of coal samples but has a significant effect on the cohesive force of coal samples.

In order to address the increasingly serious cloud-native container security threats arising from large-scale cloud migration of systems，the ISM method merging IPFS，DEMATEL，and method were proposed to identify the key tactical factors influencing cloud-native container security threats and their hierarchical logical relationships from the security intruder perspective. The findings of this research are as follows: the centrality and causality of the persistence and privilege escalation tactical phases are high，positioning them at the core of the entire cloud-native security threat landscape. Security attacks during these two phases require high-priority attention. Threat attacks during the execution and persistence tactical phases constitute essential factors in cloud-native container security. The threats during the initial access，credential theft，and lateral movement tactical phases have the most direct impact on cloud-native container security. In comparison with traditional and triangular fuzzy sets improved DEMATEL-ISM，our proposed method has better performance in identifying container security-related critical factors.

To enhance the driving safety and achieve correct decision planning for autonomous vehicles，a safe driving trajectory prediction method based on EKF-GRU was proposed. By combining learning-based methods with physics-based approaches，the prediction accuracy was improved and the rationality of the predicted trajectories was enhanced. In the first step of this method，a prediction network was constructed based on GRU to predict the longitudinal acceleration and yaw angular velocity of vehicles by extracting historical trajectory features. In the second step，an EKF state estimator was built based on the nonlinear vehicle kinematics to generate the vehicle's future limited-time trajectory，incorporating the observations obtained previously. The trajectory prediction method was validated on the NGSIM I-80 and US-101 multi-vehicle trajectory datasets. Experimental results demonstrate that the final distance errors (FDE)，root mean square errors (RMSE)，and average distance errors (ADE) of the predicted trajectories generated by traditional physics-based methods are 6.48，7.69 and 3.03 meters，respectively. In contrast，trajectories predicted using EKF-GRU exhibit higher accuracy，and the corresponding values are 5.45，6.67 and 2.56 meters，respectively. This represents improvements of 15.90%，13.26% and 15.51%.