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.

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 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.

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 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 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 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 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 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 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%.