In order to solve the problem of determining the distribution of different types of objects in system faults, a method to determine the distribution of objects was proposed. Firstly, the characteristics of the system fault evolution process and object distribution were discussed. Secondly, the method flow chart and implementation process were given. Finally, an example was analyzed. The example studied the basic data matrix composed of 6 factors and 50 objects, and the maximum training set cross-correlation was 0.8, the test set cross-correlation was 1, and the optimal object label distribution (object distribution) was obtained. Finally, the advantages and disadvantages of the method were described. The analysis shows that the database for studying the evolution process is the object set. Methods based on UKSR, combined with K-means and mutual information methods, a randomly distributed object label set is constructed, and the criteria for the optimal object label set are proposed. The optimal object label set is determined through a loop when the correlation between object labels and object data is the largest. The label value of objects in the set is the optimal object distribution. The method overcomes the problem of unsupervised learning and nonlinear mapping. It is concluded that the method can classify the measured objects in the system fault evolution process under unsupervised and nonlinear conditions, and the distribution of class labels of all objects with evolution time. The disadvantage is that it can only be used to study the system fault evolution process represented by two-dimensional.

To ensure the safe, high-quality, efficient, and environmentally friendly construction of future infrastructure projects, it is crucial to investigate the prevalent issues and characteristics of intelligent safety management and control practices in infrastructure projects. Firstly, the evolutionary process of intelligent safety management and control was comprehensively reviewed. It includes four distinct stages: intelligent identification and control of risk sources, data-driven identification and rectification of safety hazards, enhancement of intelligent safety management and control system, and comprehensive integration of intelligent management and control. On this basis, the successful experiences of different stages were summarized. Secondly, the challenges encountered in intelligent safety management and control were analyzed from the perspective of overall collaborative management, and its characteristics were analyzed from the perspective of "people, objects, environment, and management". Subsequently, starting from the three dimensions of safety management process, the whole life cycle of engineering construction, and the development level, the thoughts on intelligent management and control for infrastructure engineering safety were proposed, focusing on "reverence for safety, intelligent safety, inherent safety, digital intelligence, digital capability, and digital value". Finally, the future development path of intelligent safety management and control was envisioned. The results show that the safety management and control of infrastructure projects are transitioning from experience-based to data-driven approaches, while rapidly integrating new technologies, equipment, and processes. Intelligent safety management and control represents a significant extension of intelligent construction and management in infrastructure engineering. This is mainly evidenced by the transformation of safety management concepts, methods, and systems, as well as the value extraction from data assets. In the future, the intelligent management and control for infrastructure engineering safety will develop to comprehensive data fusion, knowledge-driven, virtual and real integration, human-machine collaboration, and full life-cycle control. At the same time, the importance of data privacy protection and standardised governance will become increasingly prominent.

In order to solve the problems of difficulty in quantifying the risk of airport runway incursion events, poor timeliness and low accuracy, and to enhance the capability of predicting runway incursion risks, a DBN model incorporating reinforcement learning for risk prediction was constructed. Firstly, causal inference theory was combined with grey relational analysis to analyze historical runway incursion events and identify the underlying risk factors. Secondly, Bayesian network(BN) theory was applied to explore the correlations among these factors and quantify these correlations using the Pearson linear correlation coefficient. This process helped in constructing a causation correlations network that effectively represented the propagation of risks associated with runway incursions. Then, the triangular fuzzy method and Hidden Markov Models (HMMs) were utilized to further refine and optimize the DBN parameter learning mechanism. Finally, the model's accuracy was validated using historical data. The results demonstrate that the proposed model's predictions of runway incursion risks closely align with the statistical values of historical data, achieving an accuracy rate of 84%, which represents a significant 10% improvement over Bayesian network predictions. Additionally, the use of mutual information to identify key nodes is found to effectively improve accuracy and discrimination compared to the degree value evaluation method.

In order to clarify the research progress of intelligent risk management in coal mines, the research status of data-driven coal mine safety risk management models was comprehensively analyzed. The prediction methods and analysis models for coal mine safety risk assessment were also reviewed. Firstly, the intelligent risk management was defined, and the scope of analysis was determined by searching relevant literature. Then, the research status, existing problems and development trend of accident big data were reviewed from three aspects: data-driven analysis method, coal mine safety risk assessment model and coal mine big data prediction and early warning platform. The results show that the theory and application framework of data-driven risk analysis in the field of coal mine safety has been basically formed, but it still cannot meet the needs of risk assessment and emergency management. In the application of early warning platform, a unified and general basic framework of big data analysis platform for coal mine safety production has been formed, but its application and promotion in production practice are far from enough. In the future, it is necessary to construct the comprehensive risk assessment model to study the risk of coal mining, starting from improving data quality and integrating dynamic and static multi-source data. Besides, the application of data-driven analysis in production practice should also be strengthened. These works can promote the transformation of coal mine safety risk management mode from empiricism to data-driven, and realize the informatization and intelligence of coal mine safety risk management.

In order to accurately identify unsafe behaviors of personnel in complex industrial sites and reduce the occurrence of safety accidents, an improved YOLOv5 unsafe behavior detection model was proposed. Firstly, an attention mechanism was introduced in the backbone of YOLOv5 to enhance the sensitivity of convolutional networks to unsafe behavior features. Secondly, enriching the number of training samples through image geometric transformation and pixel-level processing enhanced the generalization ability of the detection model in different industrial environments. Then, the detection model was distilled, and the network structure parameters were optimized to accelerate the training of the mode. Finally, the model was trained and iterated 200 times to simulate three types of industrial sites: lifting slings, robot-automated production lines, and operating rooms. It detected whether personnel were wearing safety helmets, work clothes and working in safe areas, and determined the level of danger based on their behavior to ascertain whether they were working safely. The results show that the model can detect 12 types of unsafe behaviors of personnel in complex industrial environments, such as dim light, lighting, and occlusion. The accuracy on the unsafe behavior test set is 98.6%, the recall rate is 99.2%, and the average accuracy is 97.58%.

Frequent heavy rainfall events cause a dramatic increase in attached elevator scaffolding accidents. In order to improve construction safety and reduce the accident rate under heavy rainfall scenarios, an accident causation analysis model based on combination of IFRAM and BN was proposed. The model first qualitatively identified accident mechanisms and explored system functional resonance using IFRAM. Next, IFRAM was mapped to a BN quantitative analysis model, and the prior probabilities of each root node were computed using cloud optimization. Finally, taking the Xi'an "9.10" accident as an example, empirical research was conducted, and corresponding preventive measures were proposed. The results indicate that accidents are most likely to occur when the safety status is IV. The core causes of climbing accidents include workers violating regulations, failure to conduct mandatory supervision such as standing by and heavy rainfall. The combination of factors such as heavy rainfall environment and overloading of the frame after rain is the key to inducing frame climbing accidents.

In order to investigate the influence of internal and external factors on the safety state of the tailings dam, a method for analysing the safety state of the tailings dam based on heterogeneous hierarchical diagrams was proposed. Firstly, a hierarchical causal graph was constructed based on a priori knowledge to link key factors such as environment, seepage field and stress field with the safety status of tailing dams, and an evaluation index system was established by combining the attribute characteristics of heterogeneous nodes. Secondly, the cloud model and set-pair analysis theory were used to quantitatively calculate the potential logical relationship between the heterogeneous causal graph and the safety stability of the tailings dam. A dynamic interval calculation method for quantitative indicators and a safety status level calculation model were proposed to convert the fuzziness and uncertainty of complex and diverse evaluation indicators into quantitative expressions. Finally, a tailings dam in Luoyang was used as an example to verify the scientificity of the model.The results show that the model can quantitatively analyse the link between factors and states and identify the causes of negative changes in stacked dams. The conclusions of the model analysis can be used for the safety management of the dam-building process.

In order to improve the perception level of fault water damage in coal mine, a fault water inrush stage sensing method based on fault activation evolution mechanism and key control factors was proposed. The evolution characteristics of working face floor and fault failure were studied through similar simulation tests of fault water inrush evolution process. The stage characteristics of monitoring parameters and the change of water inflow were revealed by taking the stress in the failure zone of floor, the stress in the fracture zone of fault and the water pressure in the water channel as the stage monitoring parameters. The key controlling factors of water inrush phase transformation were determined by grey correlation analysis method. Then, according to the fault water inrush analysis and research process, the fault water inrush stage perception method was proposed. The study determines that the numerical variation characteristics of monitoring parameters such as stress of floor failure zone, fault fracture zone and water pressure in water channel show obvious stage characteristics during fault activation water inrush. The order of grey correlation degree between control factors and water inflow is as follows: stress in floor failure zone > stress in fault fracture zone > water pressure in water channel, through identification of key control factors. Through the identification of key control factors, the perception of fault water inrush stage can be realized, and the perception method based on grey correlation analysis is feasible in principle.

In order to mitigate the impact of traffic accidents on the operation efficiency of freeways, and improve the throughput capacity of the accident area, based on real-time information via vehicle-to-vehicle and vehicle-to-road, a cooperative lane change guidance strategy in freeway traffic accident areas was proposed with the safety potential field theory. Firstly, in view of various traffic accidents in different lanes in two-lane or multi-lane traffic of one-way, the guidance area of collaborative lane change was divided into four areas: accident protection area, guidance transition area, collaborative lane change guidance area and free lane change area. The guidance threshold of lane change was determined to update vehicle status. Furthermore, the safety potential field of traffic accidents was established, and the corresponding guidance strategies of vehicle cooperative lane change were proposed according to different scenarios. The calculation methods of the safe distance for vehicle lane change and the latest lane change position were given. Finally, based on simulation of urban mobility (SUMO) software, the simulation results were verified in various scenarios. The results show that in the two-lane of one-way scenario, the optimization effect is most obvious when the vehicle cooperative guidance rate is at 75%. In the multi-lane of one-way scenario, the optimization effect is most obvious when the guidance rate is at 50%. Meanwhile, through comparative analysis, it is found that the average speed of vehicles passing through the accident section is increased by up to 6.3% and the maximum vehicle delay is reduced by 14.6% after adopting the lane change guidance strategy.

In order to monitor the health state of construction formwork support systems and prevent the risk of safety accidents caused by formwork collapses, a new intelligent monitoring method combining EMI and CNN for joints of formwork support systems was proposed. Firstly, based on the electromechanical coupling and sensing-driving characteristics of PZT, PZT-joint coupling model was built based on the electromechanical impedance sensing mechanism. Secondly, the original conductivity of PZT patch, coupled with the monitored structure, was used as a monitoring signature for identifying joint looseness based on the EMI technique. Thirdly, EMI-CNN model was built with the 801 original conductance signals of PZT over the sensitive frequency range as the inputs, and the nine degrees of joint looseness as the outputs. In total, the dataset consisted of 189 samples, 162 for training and 27 for testing. At last, taking an actual formwork support system joint from building site as an example, EMI-CNN model was verified and compared with EMI-BP model by the experiment. The research results show that EMI-CNN model reached convergence after 85 iterations. The prediction accuracy of the EMI-CNN model reached 100%, which is 29.63% better than EMI-BP model. This proposed method is distinguished by its real-time, accurate and non-destructive monitoring capabilities, providing an effective solution for health monitoring of joints in construction formwork support systems.

In order to solve the problem of false alarms and missed alarms in pipeline gas leakage detection using a single sensor, timely warning and feedback of leakage status, a multi-source data fusion pipeline leakage detection method based on cross-attention was proposed. Firstly, the pre-trained ShuffleNetV2 model was used to extract spatial features from thermal imaging data. Then, a 1DCNN BiGRU model was constructed by combining a one-dimensional CNN (1DCNN) and a bidirectional gated recurrent unit (BiGRU) to extract temporal features from gas sensors. Finally, cross-attention was used to capture the spatiotemporal correlation of the data and obtain the feature representations of the two data sources. The residual method was used to connect the features and input them into the classification layer to obtain the recognition results. The results show that the constructed SCGA model has a gas recognition accuracy of 99.22%, and the loss value fluctuates between 0-0.04. Compared with support vector machines (SVM), 1DCNN, and BiGRU models that only use gas sensor data, the accuracy is improved by at least 4.12%. Compared with MobileNetV3, ShuffleNetV2, and ResNet18 models that only use thermal image sensor data, the accuracy is improved by at least 1.14%. Compared with the multi-source data fusion model SCG, which simply connects temporal and spatial features, the accuracy is improved by 1%. It was verified that the SCGA model has high accuracy.

In order to better analyze the stable sub-safety state and unstable sub-safety state existing in control sector operation, K-means algorithm was used to cluster three control sector operation stability evaluation indicators of excess-capacity ratio(ECR), retention degree and flight attitude mixing ratio so that the optimal classification of the operation stability of control sector was determined. The index threshold corresponding to each level was obtained by clustering analysis of a single index. Combined with the index weight calculated by the entropy weight method, the operational stability level of the control sector in each time period was obtained according to the principle of maximum membership degree. Then, the comprehensive evaluation model of control sector operation stability was constructed. The actual flight data of Xiamen No.01 sector was selected to more comprehensively analyze operation situation of control sector from the perspectives of stability and trend. The results show that the best effect is obtained when the control sector operation stability level is divided into three categories. The stability varies with time due to the influences of air traffic flow and control conditions, especially in the two time periods of 7: 30-9: 15 and 20: 00-21: 00, when the change of stability is most obvious. The controllers need to pay great attention to improving the safety of airspace operations.

To ensure the SOTIF of eVTOL vehicles in UAM and reduce the verification difficulty of artificial intelligence algorithms, an obstacle avoidance model was proposed based on RTA method. Firstly, SAC (soft actor-critic) algorithm improved by the artificial potential field method was used as the complex function of the eVTOL intelligent obstacle avoidance system. Then, dynamic response planning (DRP) was used as a backup function of the intelligent avionics system to mitigate SOTIF hazards. Moreover, monitoring and decision-making modules were adopted to obtain environmental conditions and develop an RTA architecture. Finally, the simulated obstacle avoidance performance was compared between the two systems using complex function and RTA. The results showed that both methods can achieve obstacle avoidance, but the traditional obstacle avoidance system using complex functions may impose SOTIF risk. The RAT architecture design increased safe flight time from 78.4% to 98.15%, with the total route length only increasing by 0.95%, reducing risks in operational scenarios while ensuring efficiency.

To mitigate the risks of leakage, fires and explosions in petrochemical equipment, focusing on a typical catalytic cracking unit, a novel early warning method for detecting abnormal states using probability distribution functions was introduced. Spline fitting principles were used to uncover the trends in operating parameters such as pressure, temperature and flow rate over time, and to extract characteristic parameters such as deviation rate and deviation amount. By employing the Weibull distribution, the failure probability distribution function of the equipment was determined. The extracted characteristic parameters were integrated with the failure function to construct a probabilistic distribution mathematical model incorporating these features. Based on this model, a comprehensive early warning process was developed, facilitating real-time risk assessment and anomaly detection during the catalytic cracking process. The findings demonstrate that this method can effectively predict anomalies under conditions of oscillation, step changes, and gradual trends in operating parameters. Compared to traditional instrument systems, this early warning method advances the warning time by 87 to 621 seconds, addressing the limitation of limited response time following single-threshold alarms in the conventional systems. Furthermore, a comparison of various data processing methods reveals that the early warning model based on spline fitting exhibits superior performance.

To solve the problem that traditional safety design methods based on manual inspection were difficult to cope with the explosion of optional residence solutions caused by the large-scale integration of avionics systems, an avionics system partition model, task model and safety criticality level quantification model were constructed, and the comprehensive design optimization considering safety was modeled as an MDP problem. An optimization method of Soft Action-Critic (SAC) algorithm based on Actor-Critic framework was proposed. In order to obtain the correlation between the parameter selection and training results of SAC algorithm, the sensitivity of the algorithm parameters was studied. At the same time, to verify the superiority of the optimization method based on the SAC algorithm in optimizing the comprehensive design considering safety, optimization comparison experiments were carried out with the Deep Deterministic Policy Gradient (DDPG) algorithm and the traditional allocation algorithm as the objects. The results show that under the optimal parameter combination, the maximum reward after using convergence of SAC algorithm increases by nearly 8% compared with other parameter combinations, and the convergence time is shortened by nearly 16.6%. Compared with the DDPG algorithm and the traditional allocation algorithm, the optimization method based on SAC algorithm has improved approximately 62%, 7464%, 8370%, 2123% and 775% in terms of the maximum reward, cumulative constraint violation rate, partition balance risk effect, partition resource utilization and solution time

In order to improve the science and effectiveness of traceability and localization of hazardous gas leaks, determining the location and intensity of dangerous gas leaks is the key to emergency response to accidents. The Gaussian plume model was modified by analyzing the mass conservation law and improving the diffusion amplitude of the gas plume with an approximate Gaussian distribution. Additionally, a heuristic algorithm based on the principle of immunization—IA coupled with PSO—was proposed, and the PSO-IA algorithm was applied to source strength inversion. It is concluded that the modified Gaussian plume model has been verified by three classical algorithms (PS, GA and PSO), resulting in a prediction value error decreased by about 2%. PSO algorithm, which showed a better inversion effect, was selected for comparison with the PSO-IA algorithm. The PSO-IA algorithm has improved the effect of inverting source strength, with a localization error is 1.3 m, a source strength solving error of 0.8%, and a single computation time of less than 1 second. This enables fast and accurate positioning and estimation of source strength.

To address the complex scenarios of identifying danger zones in tower crane operations during construction, an early warning method of tower crane danger zone was proposed using computer vision technology. This method combined dynamic determination of tower crane danger zones with computer vision to detect personnel wearing situations of safety helmets and safety belt at the construction site and the inadvertent intrusion beneath the tower crane. Additionally, the YOLOv5 algorithm was adapted with attention models, and interactive window detection software was developed. Results indicate that the recognition accuracy of this model for human intrusion behavior and personal protective equipment exceeds 85%, demonstrating high precision. This method can be effectively applied in tower crane construction scenarios, optimizing fixed danger zone delineation to dynamic tower crane danger zones, and providing real-time monitoring of inadvertent personnel intrusion with warnings.

In order to improve the high-precision detection and early warning of crane safety operation and enhance the safety management ability of enterprises, focusing on the needs of unmanned industrial safety incident analysis and monitoring and early warning, an inspection robot that combines ground and air flight in hoisting scene was customized to intelligentize hoisting safety monitoring, pop-up image recording and safety alarm.A lifting dataset Cranes-Dataset (CRN-Dataset) containing 3 120 images was made, and DPIM algorithm was proposed to enhance the rapid detection ability of multi-scale objects.Based on corner detection and density-based spatial clustering of applications with noise and considering the safety attributes of the space distance between cranes and workers, the process of triggering alarms based on safety rules was developed to record real-time illegal operation image and popup alarm.The results show that, after actual deployment and verification, the DPIM algorithm significantly improves target identification ability compared with other traditional algorithms, and it is suitable for real-time calculation and data transmission of embedded edge intelligent analysis nodes to complete field deployment.

In order to address the challenges of urban traffic congestion and safety, an ACLR model was proposed. By integrating ConvLSTM, attention mechanisms, and residual structures, the ACLR model effectively enhanced the extraction of spatio-temporal traffic features.The time, space and other characteristics of taxi traffic were processed respectively, and the influence of regional point of interest(POI) data on taxi traffic was mined. Additionally, a specialized learning component was incorporated to capture the impact of external factors and point-of-interest density on traffic flow. Using taxi trajectory data from Beijing, the ACLR model demonstrates superior prediction accuracy compared to other models such as the autoregressive integrated moving average (ARIMA) model, long short-term memory (LSTM), deep spatio-temporal residual networks (ST-ResNet), convolutional neural network(CNN)-ResNet-LSTM (CRL), and attentive crowd flow machines (ACFM) in urban traffic flow forecasting,which is helpful to improve the prediction performance of the model without POI density or considering POI density. The predicted value of the ACLA model is basically consistent with the real value, and it can also be in good agreement with the real value during peak hours, which effectively improves the ability to extract traffic temporal and spatial characteristics, reduces the prediction error, and optimizes the traffic flow prediction performance.

To solve the intelligent detection problem of fire lane occupancy warning, a lightweight early warning approach based on YOLOv7 was proposed by introducing the principles of area intrusion. Firstly, a research framework for detecting fire lane area intrusions was devised, utilizing the YOLOv7 model. This was accompanied by the compilation of an image dataset that encompassed fire lanes and vehicle detection, sourced from both field investigations and open datasets. Subsequently, the spatial pyramid pooling's multi-stage partial convolution was substituted with a receptive field block module, and the SimAM attention model was incorporated to enhance the network's capability in multi-scale feature extraction and fusion. Furthermore, the Slim-Neck architecture was implemented to minimize the model's computational requirements and parameter count. The interactive interface was then designed and implemented using PyQt5. The algorithm was subsequently validated in a community located in Xi'an, Shaanxi Province. The results show that the accuracy of the model to identify fire lanes and vehicles is over 80%. Compared with the original model, the improved model reduces the number of parameters by 20.5%, the floating-point calculation by 11.3%, and the detection speed by 42.4% to 48.6 f/s. This promotes the development of intelligent detection technology for fire lane occupancy.

In order to accelerate the speed and efficiency of autonomous systems testing, the method of generating a scene database for unmanned driving in campus environments was proposed. Firstly, the simulation test scenarios in complex campus environment were analyzed, and the campus scenes were simplified as a combination of road network structure, ground properties, interacting members and environmental factors. Secondly, the method of generating the scene database based on importance indicators was proposed to solve the boundedness of the campus scenario database. Then, the complexity indicators and interest probability indicators were used to describe the importance indicators of scenarios. The fuzzy analytic hierarchy process(FAHP) was used to evaluate the complexity of the scenario. The interest probability of the scenario was calculated by combining the kernel density estimation method and the interested weight calculation method. Next, the parameter space was segmented to obtain the set of similar scenarios, and the scenario sets were sorted according to test priority and importance indicators. The filtered scenarios were gradually added to the test scenario database, and the scenario database with test sequences was generated. Finally, the test evaluations based on the real-world campus scenario database were conducted to verify the effectiveness of the scenario database generation method proposed in this paper. The results show that the campus test scenes can be effectively described using four scene elements and the tree structure. The method proposed in this paper can generate a campus test scene library with high test efficiency, high coverage, conformity to natural probability, and interest interval, which is helpful to improve the efficiency of unmanned simulation test in complex campus environment.

To alleviate the contradiction between limited traffic police resources and the untimely handling of road traffic accidents, a traffic police resource optimization allocation approach was proposed based on a queuing theory model under a grid management mode of roads. Firstly, license plate recognition data obtained from the city's road network bayonet system was used to extract historical travel trajectories of vehicles and develop a similarity model between road segments. Secondly, the spectral clustering algorithm was adopted to cluster the road segments and form a set with the highest association between the segments, serving as the result of the road network division. Then, for the real-time traffic accidents within the grid, a queuing theory model was further proposed to calculate the minimum number of police officers required for each grid, along with an optimized allocation scheme for police resources. Finally, the proposed method was validated in Yinzhou District of Ningbo City. The results showed that the proposed optimization method for police allocation reduced the number of police officers by 18.18% and patrol mileage by 10.87% compared to the traditional method of dispatching police officers as soon as an accident occurs. Furthermore, the proposed method increased the accident handling response speed by 10.68%, demonstrating excellent optimization performance.

To solve the crowd congestion problems caused by a large number of phubbers in enclosed one-way long passages in public spaces such as the subway, an intervention model was proposed to calculate the intervention critical value. Experiments were performed to analyze the behavioral characteristics of phubbers and normal pedestrians in enclosed one-way long corridors. Then, different distribution functions were used to propose a small-scale behavioral model. Furthermore, a large-scale congestion intervention decision-making model was proposed based on the proportion of phubbers and crowd density. Finally, the critical value curve between passenger density and the proportion of phubbers was validated against a one-way long passage in a Beijing subway station. The results indicated that behavioral characteristics of phubbers presented as slow following, while normal pedestrians tended to speed up and overtake whenever possible. The simulations calculated the critical value curve between the passenger's density and the phubber's proportion. If the calculated value was lower than the critical curve, it was a low-risk area without any intervention strategies. Otherwise, intervention strategies were required to avoid serious congestion.

Aiming at the problem of UAV aerial photography parameters relying on manual experience when collecting image of 3D real scene reconstruction at traffic accident sites, which led to large model measurement errors and low precision, an automatic calculation method of key parameters of UAV aerial photography was proposed. First, the key parameters of aerial photography used by single-lens UAV for images acquisition of traffic accident site were altitude, gimbal angle and shooting interval angle. The numerical relationships of the key parameters with the imaging range, imaging accuracy and overlap rate were analyzed. Then, the aerial photography key parameters computation model was constructed. The key input parameters were the given accident site, UAV technical parameters, image aspect ratio and overlap requirements. On the premise that the accident site was in the effective imaging range and there was no imaging blind zone, the UAV photography parameters were automatically calculated with the goal of improving the accuracy and presentation effect of the image utilization rate model. Finally, combined with case application, the UAV aerial photography parameters calculated by this method were applied to complete the image acquisition at the accident sites, and the constructed 3D real scene model could clearly and completely present the overview of the accident site, with an average measurement error of 1.72%, and a measurement accuracy of 3.54 cm. Compared with the manual empirical method, the average error of the method was reduced by 47.56%, and the accuracy was improved by 48.40%. The study shows that this method can realize the automatic quantitative calculation of aerial photography parameters for 3D real scene reconstruction of traffic accident sites, construct the model with centimeter-level error, and improve the parameterization and automation of UAV aerial photography.

To enhance the fire emergency evacuation capability of hospital buildings in fire, a device was designed for timely emergency evacuation and safe escape. UBmap, AHP, and FAST were integrated into the overall design framework to investigate users' needs and relevant product design elements for emergency evacuation devices. The UBmap incorporated the escape behavior of patients during the fire based on the characteristics of hospital buildings, and constructed a behavior journey map to predict and extract needs at each stage. AHP/FAST aggregation methods were then used to rank these needs according to their importance, converting them into primary and secondary functions for analysis and resolution. This determined the accuracy of the product design orientation and functional logic, and finally completed the design scheme. The theoretical model based on UBmap/AHP/FAST was applied to the design and development of fire evacuation device in hospital buildings. The design's overall strength and feasibility were further verified and validated using finite element analysis in ANSYS Workbench software. The results show that the integration of different systematic product analysis, design, and simulation testing methods reduces weak points and uncertainties in the design process. This approach makes the design more systematic and scientific, and achieves the goals of reducing production costs, enhancing safety and efficiency, and improving disaster prevention and mitigation.

To reduce traffic accidents caused by autonomous vehicles and improve the efficiency of vehicle safety testing in simulation environments, an autonomous driving collision test scenario construction method was proposed based on deep reinforcement learning. Firstly, the vehicle's driving process was mapped to a Markov decision process by setting the state, action, and reward functions. Then, the agent was trained to complete the vehicle collision task and generate the collision test scenarios based on the built simulation platform (CARLA-DRL). Finally, 500 random collision simulation tests were conducted to analyze the collision success rate, collision time, and collision energy based on the relative distance between the agent and the autonomous vehicle. The results indicated that the agent generated collision trajectories that conformed to vehicle dynamics and could construct refined and multi-type collision test scenarios. The average collision success rate between the agent and the autonomous vehicle was 62.20%, the average collision time was 127.25 s, and the average collision energy value was 175.98 kJ. The proposed method can construct high-frequency, high-efficient, and high-risk autonomous driving vehicle collision test scenarios, increasing the probability of occasional high-risk scenarios in simulation scenarios and enhancing the efficiency of safety testing for autonomous vehicle collision incidents.

To improve the efficiency of disaster response, the "Hebei rainstorm" and "Heilongjiang rainstorm" were adopted as illustrative cross-regional research cases, and text-image-audio multimodal data were collected from short videos. In the face of massive unstructured data, deep learning technology was employed to realize the extraction of multimodal emotional features, cross-modal integration and intelligent sentiment classification in short videos. By comprehensively using spatial and temporal big data, the multimodal emotional characteristics of short video of rainstorm disaster were deeply mined and analyzed in the spatial and temporal dimension. The results indicate that the model's accuracy exceeds 85%, efficiently fulfilling the objectives set for short video analysis. From the temporal perspective, the emotional fluctuations of netizens broadly align with the cycle of rainstorm disasters, providing a basis for assessing disaster severity and public opinion trends. Furthermore, the intervention of media and government entities plays a significant role in shaping the emotional evolution surrounding rainstorm disasters. In terms of spatial dimensions, negative emotions exhibit a "low-high-low" trend as disasters shift locations, and the resonance and diffusion of these emotions display distinct regional characteristics. Therefore, it is imperative to prioritize public opinion guidance in disaster-stricken areas, as well as in some eastern regions of China and non-disaster areas experiencing similar phenomena.

An open-pit mine landslide identification method was proposed based on object-oriented annotation datasets and the Res-U-Net model to realize accurate identification and early warning of open-pit mile landslide disasters. Firstly, the mine landslide image data in the study area were obtained by UAV aerial survey. Secondly, the multi-scale-spectral segmentation method and threshold separation principle were applied to divide and classify the open-pit mine landslide data, and the landslide dataset was developed based on the object-oriented method. Then, the U-Net network was used as the infrastructure to propose a landslide identification semantic segmentation model based on Res-U-Net by integrating the residual module into each convolutional layer. Finally, the datasets constructed by different methods were used to identify landslides, and the Res-U-Net model was compared with the widely used semantic segmentation models, Fully Convolutional Networks (FCN), and U-net. The results indicated that the landslide data set based on object-oriented annotation had better landslide identification performance when compared to the traditional manual annotation dataset, resulting in improvements in identification accuracy, recall rate, F₁ score, and kappa coefficient of more than 12%. The landslide identification accuracy of the Res-U-Net model was more than 0.8, realizing the accurate landslide open-pit mine disaster identification.

In order to assist earthquake rescue personnel in enhancing disaster response speed and adapting to diverse search and rescue needs, an intelligent management method for earthquake rescue equipment information based on a knowledge graph was proposed. Through the top-down knowledge graph construction method, earthquake rescue knowledge was first obtained from various information sources to serve as the basis for knowledge modeling. Next, a rule-based method was used to extract search and rescue knowledge, which was then integrated based on cosine similarity. The integrated knowledge was stored in the form of Resource Description Framework (RDF) triples. Subsequently, the open-source graph database Neo4j was employed to organize the triples into a visualized knowledge graph. Finally, a question-and-answer system was built based on the knowledge graph, allowing users to query the knowledge on the graph using natural language. The results indicate that the knowledge graph includes five categories of entities and relationships: disasters, secondary disasters, environmental factors, rescue needs, and rescue equipment. It facilitates quick matching of equipment based on rescue needs. The knowledge graph-based method can effectively manage and schedule rescue equipment information, improving the efficiency of the preparation phase of rescue operations.