In order to discover fire accidents in chemical industrial parks in time and reduce accident losses，this study used CNN to establish a real-time fire detection system for chemical industrial parks. Based on CNN，the YOLOv5 algorithm was used to calculate chemical industrial park fire data sets and ordinary fire data sets. The loss value，recall rate，precision and mean average precision of the two data sets were compared. Among them，the loss value and recall rate of the chemical industrial park fire data set are slightly lower，but the precision and mean average precision were higher than that of an ordinary fire data set，which shows the feasibility of detecting fire. In addition，based on fire detection results，this study further designed the flame image recognition software system for the chemical industry park with the help of the PyQt5 program framework，realized the application of fire image and video recognition in the chemical park，and expanded the application scope of the method. The results show that the YOLOv5 target detection algorithm based on convolutional neural network can detect fires in chemical industrial parks in real-time. This detection method is portable，and the results are reliable，which can help improving the safety management level of the chemical industrial park.

In order to explore the similarities and differences，advantages and disadvantages between the definition of cause factors in LCM and the 24Model，a review of the definition of causes and results at various levels for both models was conducted. The definition content and its guidance role in safety practices，focusing on accident causation analysis，were compared. An empirical analysis was conducted using a coal mine gas explosion accident as an example to identify differences in the analysis results between the two models. The research shows that LCM is the first one-dimensional event sequence model that incorporates management factors into accident causation analysis. It provides clear definitions of cause factors at various levels and their logical relationships. However，LCM has issues with overlapping and repetitive definitions of causal factors and fails to reveal deeper accident cause factors such as guiding principles for safety work. 24Model，as a systematic accident causation model，predominantly defines various factors in terms of the organization. It describes the concepts of events，accidents，and safety，categorizing individual safety acts，safety capabilities，and organizational safety management systems，providing meanings and explanations. It explores organizational safety culture and reflects it with 32 elements. Both models' accident causation analysis methods are built on the definitions of cause factors at different levels and are applicable to their respective theoretical frameworks.

Mine tremors and rock bursts are hot，difficult，and bottleneck problems that need to be solved urgently in the mining field. In order to effectively control mine tremors and rock bursts，the definition and classification of mine tremors，the hypothesis of mine pressure and the prevention and control technologies of mine tremors and rock bursts were summarized. And the theory of roof-cutting and pressure-relief was reviewed. Then，its application in abandoned stope disposal and pressure unloading mining of medium-thick gold mines and gob-side entry retaining laneway of medium-thick and below coal mines were introduced，and its difference with 110 working method was compared. Based on this，the definition of mine tremors was given，and it was pointed out that the occurrence conditions of mine tremors are similar to those of rock bursts. Therefore，the controlled blasting and groove caving technology of a deep-buried hard roof plate was put forward for thick ore body mining. The summary shows that the technology of controlled blasting groove caving is still the main method to release and transfer high underground pressure in the prevention and control of mine tremors and rock bursts in the future，it can also simplify the "masonry beam" of deep-buried thick orebody into a spring rock beam bearing system.

In order to recognize the explosion suppression ability of potassium-containing fine water mist in the scenario of gas leakage in urban comprehensive pipeline corridors，the explosion suppression tests were carried out with additive-containing fine water mist located outside the methane-air explosion area by a self-made explosion experimental system. The effects of pure water and fine water mist of three potassium compounds，namely potassium oxalate，potassium carbonate and potassium chloride，on the overpressure and overfire range of 9.5% methane-air explosion were analyzed. The results indicate that the critical explosion suppression atomization concentration range of pure water mist outside the methane-air premixed area is 320-480g/m³. The overpressure decrease rate under potassium oxalate-containing conditions showed a trend of NormalCDF (Normal Cumulative Distribution Function) with increasing mass concentration，and the optimum suppression concentration is 10%. When the atomization concentration is 480 g/m ³，D₃₂ is 61.7 μm，the mass concentration of the compound is 10%，and the explosion suppression ability of water mist containing additives is greater than that of pure water mist. Among them，potassium oxalate has the strongest explosion suppression ability，followed by potassium carbonate and potassium chloride. The peak overpressure reduction rate is 2.32 times，1.88 times，and 1.53 times higher than that under pure water mist conditions，respectively. The range of overfire is reduced by 46.7%，40%，and 13.3%，respectively. Compared to potassium carbonate and potassium chloride，the potassium oxalate fine water mist outside the premixed area could absorb more heat and consume more active free radicals.

Pool fire caused by fuel leakage seriously threatens engine operation and aircraft safety. To deeply understand the complicated physical mechanisms of pool fire in engine fan cavities，temperature variation characteristics of double fuel pool fire were investigated. Firstly，the physical and numerical models of the CFM56-7B engine fan cavity were established based on the software FDS. Secondly，simulated temperature variations of single fuel pool fire were validated against measurements of the Trent 800 engine fan cavity，and then grid independence was analyzed. Finally，the fire development process and temperature variation characteristics of double fuel pools were analyzed within the fan cavity using several detectors and slices. The results indicated two phases for temperature variation of the double fuel-pool fire in the engine cavity，including an increment state and a quasi-steady state. Moreover，temperature variation magnitude was affected by distances between the detectors and the fuel pools. Fuel-pool fire flame propagation inclined to the left side of the fan cavity，causing an increment of fire temperature on the left side. Plume floating，flame fusion，fusion expansion，and full flame coalescences were observed in the axial direction of the cavity.

In order to address the increasing risk of conflict caused by the difficulty in effectively predicting aircraft point source localization，a time series trajectory prediction model AM-LSTM based on AM and LSTM was constructed，to predict the instantaneous point source location of the aircraft in the airfield area in a short time in the future. On this basis，the contour was expanded according to the aircraft type and glide heading，the aircraft speed was used as the safety distance weight，and the ray method was used to realize the determination of the contour conflict. Urumqi Dewopu Airport was used as an example for validation，and the trained trajectory prediction model was utilized to predict aircraft taxiing trajectories in the airfield area and identified taxiing conflicts between aircraft profiles. The results show that the AM-LSTM prediction model can accurately predict the aircraft movement trajectory in the airfield area，and the average displacement error of the trajectory position prediction in the next 3 s is 1.05 m，and the accuracy of trajectory point position prediction can reach 94.37%. Therefore，it can accurately identify the risk of taxiing conflict on the basis of trajectory prediction，which is conducive to guaranteeing the safe operation of the airfield area.

In order to optimize the anti-explosion design of an underground unventilated kitchen，the finite element model of a house with an underground unventilated kitchen was established in FLACS software. Based on this model，the effect of gas cloud size，ignition position，shape of obstacle，position，and size of obstacle on gas explosion pressure was investigated. The extent of explosion damage to the unventilated kitchen structure was obtained according to simulation results. The results show that when the gas cloud size increases in the unventilated kitchen，the explosion damage to the building is more severe. The maximum pressure peak values are 41.9，19.5，and 3.25 kPa when ignition is in the kitchen，ventilation shaft，and living room. When an obstacle exists，a greater amount of pressure is generated. The peak pressure is much higher when the obstacle cross-section shape is square than when it is circular and rectangular. The closer the obstacle is to the ignition position，the more intense the pressure peak. With the increase in the obstacle section size，the peak pressure increases continuously. The greatest rise in peak pressure is near the elevator. Shock waves from gas explosions in unventilated kitchens have a greater impact on the floor space than in traditional kitchens.

In order to establish a scientific，accurate and normative urban safety risk management system，this paper makes some proposals based on the characteristics of urban safety risk. First，the urban safety risk was classified into four types according to the causal chain model which was established based on the definition and connotation of risk. Then，the characteristics of these four types of risk were analyzed considering the relevant static and dynamic urban characteristics. Last，the general and specific urban safety risk management proposals were made considering the current practice. This research shows that the characteristics of urban safety risk include accumulation of conventional risk，emergency of emerging risk，intensification of complex risk，and frequent occurrence of extreme risk. Some measures should be implemented to enhance the urban safety risk management system. The general framework of urban safety risk management should be established，and the specific risk assessment process and risk treatment measures should be implemented. Further，they should be integrated into the regular emergency management system of a city.

In order to effectively prevent and control fire accidents of hazardous chemical tanks during transportation，it is necessary to identify the type of tank fire quickly and correctly. The statistical data of domestic hazardous chemicals tanker fire accidents from 2013 to 2020 was analyzed with Python software. According to the characteristics of fire accidents，a regression model with multiple logistic regression theory was established. The three common fire types of hazardous chemicals tankers，namely，jet fire，pool fire and BLEVE(Boiled Liquid Evaporate Vapor Explosion)fire，were regarded as the categories of explained variables. Through the analysis of accident data，a total of 15 fire factors in five aspects，namely，space and road characteristics，time and meteorological characteristics，personnel factors，vehicle and equipment factors，and hazardous chemicals factors，were determined. A multiple logistic regression equation of fire probability of hazardous chemicals tankers was constructed，and the explicitness and accuracy of the equation were tested. The determined model was proved by examples. The probability of three types of fire in hazardous chemicals tankers was obtained. The accident prevention measures were proposed. The results show that it is the most likely a pool fire for a liquefied natural gas tanker，with a probability of 0.55. The second one is jet fire，and the last one is the boiling liquid expanding vapor explosion fire. To reduce the probability of pool fires，measures such as improving the mechanical strength of the container and reducing the collision strength could be adopted to prevent leakage holes of large size in the container. Measures such as slowing down the leakage rate，controlling the leakage range and efficient scientific fire extinguishing are adopted to decrease sequences of tank fire.

In order to help fire investigators determine the location of the fire origin，improve the chain of evidence in accident investigations and identify the cause of the fire quickly and accurately，the researches on fire origin determination based on fire traces were reviewed in present paper. First，fire traces were classified，including burn marks，smoke marks，collapse marks and electrical wiring marks，with emphasis on soot deposition traces. Then，multiple fire origin determination methods at home and abroad were reviewed and classified into three categories: determining the fire origin directly using experience，determining the fire origin using numerical reconstruction techniques，and determining the fire origin using machine learning algorithms. The advantages and limitations of each method were analyzed respectively. Finally，the future research tendency of fire origin determination technology was prospected. The results show that numerical simulation of soot deposition traces combined with machine learning for fire origin determination has a good perspective for application.