Explosion event analysis and prediction method, device, equipment and medium

Abstract

The invention discloses an explosion event analysis and prediction method, device, equipment and medium, and relates to the technical field of accident auxiliary analysis, the method mainly comprises three aspects of source item analysis, diffusion prediction and hazard assessment, and can comprehensively analyze and guide the source item information, the diffusion condition and the emergency response scheme of an accident in time. A reference decision scheme is provided for a decision maker, emergency response can be timely made after an accident occurs, and personnel and property loss is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of accident auxiliary analysis, and in particular to an explosion event analysis and prediction method, device, equipment and medium. Background Art

[0002] Explosions occur frequently at present. When an explosion occurs, if it is not handled properly, it will cause immeasurable consequences.

[0003] The analysis of the possible impact of an explosion accident mainly includes three aspects: source analysis, diffusion prediction, and hazard assessment.

[0004] The source term of an explosion accident is an important basis for determining the accident level, evaluating the radiation consequences of the accident, and formulating emergency response measures. In the event of a serious explosion accident, the information on the source term may not be obtained in a timely and accurate manner, which will directly affect the evaluation of the accident consequences. In particular, it is an important basis for accident decision-making during the emergency response process.

[0005] After an explosion occurs, hazard assessment is not only related to individual outcomes but also to factors such as population, economy, and environment. Therefore, when judging the rationality of an emergency plan and the cost incurred, if only the quantitative relationship existing in the simple event itself is used as the judgment standard, it will not be conducive to decision makers setting an emergency plan with the lowest cost.

[0006] Therefore, how to provide an explosion event analysis and prediction method that can simultaneously achieve source analysis, diffusion prediction, and hazard assessment is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0007] In view of the above problems, the present invention provides an explosion event analysis and prediction method, device, equipment and medium for overcoming the above problems or at least partially solving the above problems.

[0008] The present invention provides the following solutions:

[0009] A method for analyzing and predicting explosion events, comprising:

[0010] Determining the event type, and calling the explosion accident source item analysis model corresponding to the event according to the event type, so as to analyze and determine the hazard source item of the event through the explosion accident source item analysis model;

[0011] Inputting the analysis results of the explosion accident source analysis model, meteorological information, and geographic parameters into the event development spatiotemporal dynamic model, so that the event development spatiotemporal dynamic model analyzes the diffusion of the released substances after the future target time period and outputs the concentration distribution of the released substances in the target time series;

[0012] Obtaining social situation data and resource data corresponding to the disposal plan to be evaluated, combining the analysis results of the spatiotemporal dynamic model of the event development, calling the hazard assessment model library to evaluate the injury situation of personnel, and generating a hazard assessment report corresponding to the disposal plan to be evaluated;

[0013] Obtain the disposal intentions of command organizations at all levels, combine them with the hazard assessment results output by the hazard assessment model, call the auxiliary decision-making model, analyze the disposal intentions and generate relevant plans or programs.

[0014] Preferably, the explosion accident source term analysis model at least includes a light impulse calculation module, a shock wave damage calculation module and a stable cloud computing module.

[0015] Preferably, the light impulse calculation module is used to calculate the light impulse and the influence of the terrain and objects on the light radiation by using the explosion equivalent, the explosion mode and the distance from the explosion center to obtain the light radiation damage characteristic value;

[0016] The shock wave damage calculation module is used to perform air shock wave overpressure calculation, ground explosion shock wave overpressure calculation, and dynamic pressure calculation using the explosion equivalent, the explosion mode, and the distance from the explosion center to obtain the shock wave damage characteristic value;

[0017] The stable cloud computing module is used to describe the stable cloud shape parameters and the sedimentation ash mass parameters, and is used to obtain the distribution of the stable cloud.

[0018] Preferably, the event development spatiotemporal dynamic model is used to determine the target regional scale mode in which the diffusion area is located, and the target regional scale mode includes any one of a first high-altitude global mode, a second high-altitude global mode, and a low-altitude scale mode;

[0019] According to the target regional scale model, the corresponding particle dynamics equation is called to calculate the average wind speed in the east direction within the time step required by the Lagrangian particle random walk model;

[0020] Utilizing the average wind speed in combination with the Lagrangian particle random walk model to calculate and obtain explosion event analysis and prediction results;

[0021] Calling a corresponding kernel function to simulate the spatial concentration distribution of particles according to the target area scale pattern;

[0022] The particle dynamics equation corresponding to the first high-altitude global model takes into account the influence of atmospheric drag and gravity and ignores the atmospheric turbulent wind field speed; the particle dynamics equation corresponding to the second high-altitude global model does not consider the influence of atmospheric drag, gravity and Brownian motion; the low-altitude scale model takes into account the influence of atmospheric drag, Brownian force and gravity and does not consider the effect of particles on gas flow;

[0023] The kernel function is used to calculate the spatial concentration distribution at the spatial coordinate point using a distribution function centered on the current coordinates of the particle.

[0024] Preferably, it is determined whether there is real-time monitoring data uploaded in the corresponding time series. If so, the monitoring data is used to perform data assimilation processing on the simulated prediction data generated by the diffusion model, so as to verify and correct the prediction data and update the output concentration distribution of the released substances.

[0025] Preferably: the hazard assessment model library includes at least a cost-effectiveness analysis model, a benefit analysis model and a multi-attribute utility analysis model;

[0026] The cost-effectiveness analysis model is used to calculate the cost paid by the minimum unit of the treatment plan to be evaluated, so as to determine whether the treatment plan to be evaluated is superior by judging the ratio of the increased protection cost to the reduction in collective dose;

[0027] The benefit analysis model is used to calculate the total net benefit of the treatment plan to be evaluated, so as to determine whether the treatment plan to be evaluated is optimal by judging the sum of the radiation protection cost and the radiation hazard cost;

[0028] The multi-attribute utility analysis model is used to calculate the total utility value of the treatment plan to be evaluated, so as to determine whether the treatment plan to be evaluated is excellent by judging the level of the total utility value.

[0029] Preferably: the auxiliary decision model includes a random forest auxiliary decision model and a reinforcement learning algorithm;

[0030] The random forest decision-making support model is used to make predictions based on the feature vectors. Each decision tree classifies the input feature vectors and provides a recommendation result. The recommendation results of all decision trees are voted or averaged to obtain a candidate disposal plan. The candidate disposal plan includes at least a candidate evacuation order and a candidate time and interval.

[0031] The reinforcement learning algorithm is used to determine that the random forest decision-making auxiliary model cannot clearly define the decision path or faces high-dimensional complexity problems, and then use high-dimensional data to optimize the candidate evacuation order and the candidate time and interval included in the candidate disposal plan to obtain a target disposal plan; the high-dimensional data at least includes a preset evacuation order, preset time and interval, speed, wind direction and traffic conditions.

[0032] An explosion event analysis and prediction device, used to execute the above-mentioned explosion event analysis and prediction method, comprising:

[0033] A source item simulation and analysis unit is used to determine the event type and call the explosion accident source item analysis model corresponding to the event according to the event type, so as to analyze and determine the hazard source item of the event through the explosion accident source item analysis model;

[0034] a diffusion prediction unit, configured to input the analysis results of the explosion accident source analysis model, meteorological information, and geographic parameters into a spatiotemporal dynamic model of event development, so that the spatiotemporal dynamic model of event development analyzes the diffusion of released substances after a future target time period and outputs the concentration distribution of the released substances in a target time series;

[0035] The hazard assessment unit is used to obtain social situation data and resource data corresponding to the disposal plan to be evaluated, combine the analysis results of the spatiotemporal dynamic model of the event development, call the hazard assessment model library to evaluate the injury situation of personnel, and generate a hazard assessment report corresponding to the disposal plan to be evaluated;

[0036] The auxiliary decision-making unit is used to obtain the disposal intentions of command organizations at all levels, combine the hazard assessment results output by the hazard assessment model, call the auxiliary decision-making model, analyze the disposal intentions and generate relevant plans or programs.

[0037] A device for analyzing and predicting explosion events, comprising a processor and a memory:

[0038] The memory is used to store program code and transmit the program code to the processor;

[0039] The processor is used to execute the above-mentioned explosion event analysis and prediction method according to the instructions in the program code.

[0040] A computer-readable storage medium is used to store program codes, and the program codes are used to execute the above-mentioned explosion event analysis and prediction method.

[0041] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0042] The embodiments of the present application provide a method, device, equipment and medium for analyzing and predicting explosion events, which mainly include three aspects: source analysis, diffusion prediction and hazard assessment. They can comprehensively and timely analyze and guide the source information, diffusion situation and emergency response plan of the accident, provide reference decision-making plans for decision makers, and facilitate timely emergency response after the accident occurs, thereby reducing casualties and property losses.

[0043] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be derived from these drawings without inventive effort.

[0045] Figure 1 This is a flow chart of a method for analyzing and predicting explosion events provided by an embodiment of the present invention;

[0046] Figure 2 This is a diagram illustrating an implementation framework of an explosion event analysis and prediction method provided by an embodiment of the present invention;

[0047] Figure 3 Schematic diagram of an explosion event analysis and prediction device provided by an embodiment of the present invention;

[0048] Figure 4 This is a schematic diagram of an explosion event analysis and prediction device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of the present invention.

[0050] See also Figure 1 , is a method for analyzing and predicting explosion events provided by an embodiment of the present invention, such as Figure 1 As shown, the method may include:

[0051] S101: Determine the event type, and call the explosion accident source term analysis model corresponding to the event according to the event type, so as to analyze and determine the hazard source term of the event through the explosion accident source term analysis model; in specific implementation, the accident source term analysis model includes at least a light impulse calculation module, a shock wave damage calculation module, and a stable cloud computing module. The light impulse calculation module is used to calculate the light impulse and the influence of terrain and landforms on light radiation using the explosion equivalent, the explosion mode, and the distance from the explosion center to obtain the light radiation damage characteristic value;

[0052] The shock wave damage calculation module is used to perform air shock wave overpressure calculation, ground explosion shock wave overpressure calculation, and dynamic pressure calculation using the explosion equivalent, the explosion mode, and the distance from the explosion center to obtain the shock wave damage characteristic value;

[0053] The stable cloud computing module is used to describe the stable cloud shape parameters and the sedimentation ash mass parameters, and is used to obtain the distribution of the stable cloud.

[0054] S102: Inputting the analysis results of the explosion accident source analysis model, meteorological information, and geographic parameters into the event development spatiotemporal dynamic model, so that the event development spatiotemporal dynamic model analyzes the diffusion of the released substances after the future target time period and outputs the concentration distribution of the released substances under the target time series; in specific implementation, the embodiment of the present application can provide the event development spatiotemporal dynamic model to determine the target regional scale mode in which the diffusion area is located, and the target regional scale mode includes any one of a first high-altitude global mode, a second high-altitude global mode, and a low-altitude scale mode;

[0055] According to the target regional scale model, the corresponding particle dynamics equation is called to calculate the average wind speed in the east direction within the time step required by the Lagrangian particle random walk model;

[0056] Utilizing the average wind speed in combination with the Lagrangian particle random walk model to calculate and obtain explosion event analysis and prediction results;

[0057] The corresponding kernel function is called according to the target area scale pattern to simulate the spatial concentration distribution of particles.

[0058] The particle dynamics equation corresponding to the first high-altitude global model takes into account the influence of atmospheric drag and gravity and ignores the atmospheric turbulent wind field speed; the particle dynamics equation corresponding to the second high-altitude global model does not consider the influence of atmospheric drag, gravity and Brownian motion; the low-altitude scale model takes into account the influence of atmospheric drag, Brownian force and gravity and does not consider the effect of particles on gas flow;

[0059] The kernel function is used to calculate the spatial concentration distribution at the spatial coordinate point using a distribution function centered on the current coordinates of the particle.

[0060] Furthermore, it is determined whether there is real-time monitoring data uploaded under the corresponding time series. If so, the monitoring data is used to perform data assimilation processing on the simulated prediction data generated by the diffusion model, so as to verify and correct the prediction data and update the output concentration distribution of the released substances.

[0061] S103: Obtaining social situation data and resource data corresponding to the disposal plan to be evaluated, combining the analysis results of the spatiotemporal dynamic model of the event development, calling a hazard assessment model library to evaluate the injury situation of personnel, and generating a hazard assessment report corresponding to the disposal plan to be evaluated; in specific implementation, the embodiment of the present application can provide that the hazard assessment model library at least includes a cost-effectiveness analysis model, a benefit analysis model, and a multi-attribute utility analysis model;

[0062] The cost-effectiveness analysis model is used to calculate the cost paid by the minimum unit of the treatment plan to be evaluated, so as to determine whether the treatment plan to be evaluated is superior by judging the ratio of the increased protection cost to the reduction in collective dose;

[0063] The benefit analysis model is used to calculate the total net benefit of the treatment plan to be evaluated, so as to determine whether the treatment plan to be evaluated is optimal by judging the sum of the radiation protection cost and the radiation hazard cost;

[0064] The multi-attribute utility analysis model is used to calculate the total utility value of the treatment plan to be evaluated, so as to determine whether the treatment plan to be evaluated is excellent by judging the level of the total utility value.

[0065] S104: Obtain the disposal intentions of command organizations at all levels, combine the hazard assessment results output by the hazard assessment model, call the auxiliary decision-making model, analyze the disposal intentions and generate relevant plans or programs.

[0066] In specific implementation, the embodiment of the present application may provide that the auxiliary decision model includes a random forest auxiliary decision model and a reinforcement learning algorithm;

[0067] The random forest decision-making support model is used to make predictions based on the feature vectors. Each decision tree classifies the input feature vectors and provides a recommendation result. The recommendation results of all decision trees are voted or averaged to obtain a candidate disposal plan. The candidate disposal plan includes at least a candidate evacuation order and a candidate time and interval.

[0068] The reinforcement learning algorithm is used to determine that the random forest decision-making auxiliary model cannot clearly define the decision path or faces high-dimensional complexity problems, and then use high-dimensional data to optimize the candidate evacuation order and the candidate time and interval included in the candidate disposal plan to obtain a target disposal plan; the high-dimensional data at least includes a preset evacuation order, preset time and interval, speed, wind direction and traffic conditions.

[0069] The following is a detailed description of the explosion event analysis and prediction method provided by this application. Figure 2 shown.

[0070] First, the event type is determined through the system platform, and the source term model of the corresponding event is called to determine whether source term inversion is required. After that, the parameter configuration under the current event is completed. The source term model analyzes and determines the hazardous source term of this event (such as the type, quantity, and location information of the released substance).

[0071] The accident source analysis model at least includes a light impulse calculation module, a shock wave damage calculation module, and a stable cloud computing module;

[0072] The light impulse calculation module is configured to use the explosion equivalent, the explosion mode, and the distance from the explosion center to perform light impulse calculation and calculate the influence of terrain and objects on light radiation to obtain the light radiation damage characteristic value. In specific implementation, the embodiment of the present application can provide the light impulse calculation module to perform the following operations:

[0073] determining whether to consider attenuation caused by atmospheric absorption and scattering according to the distance from the explosion center;

[0074] If only geometric attenuation is considered and the attenuation caused by atmospheric absorption and scattering is ignored, and the explosion mode is determined to be airburst, the light impulse is calculated using the following formula:

[0075]

[0076] Where: f G represents the light equivalent coefficient; Q represents the explosion equivalent; r represents the distance from the explosion center;

[0077] If only geometric attenuation is considered and the attenuation caused by atmospheric absorption and scattering is ignored, and the explosion method is determined to be ground explosion, the light impulse is calculated using the following formula:

[0078]

[0079] Where: f d Represents the effective light impulse coefficient, h B Indicates higher than.

[0080] Considering the attenuation caused by atmospheric absorption and scattering, and determining that the explosion mode is airburst, the light impulse is calculated using the following formula:

[0081]

[0082] Where: τ represents the atmospheric transmittance;

[0083] Considering the attenuation caused by atmospheric absorption and scattering, and determining that the explosion method is ground explosion, the light impulse is calculated using the following formula:

[0084]

[0085] Furthermore, the atmospheric transmittance τ is expressed by the following formula:

[0086] τ=e -μr +0.23(μr) 1.6 e -0.65μr

[0087] Where: e -μr Indicates the transmittance of direct light; 0.23 (μr) 1.6 e -0.65μr represents the enhancement term of multiple scattering, and μ represents the average atmospheric attenuation coefficient.

[0088] The shock wave damage calculation module is used to perform air shock wave overpressure calculation, ground explosion shock wave overpressure calculation, and dynamic pressure calculation using the explosion equivalent, the explosion mode, and the distance from the explosion center to obtain the shock wave damage characteristic quantity; the shock wave calculation can be divided into two types: air shock wave and ground explosion shock wave. In specific implementation, the embodiment of the present application can provide that the air shock wave overpressure calculation is expressed by the following formula:

[0089]

[0090] The calculation of the ground explosion shock wave overpressure is expressed by the following formula:

[0091]

[0092] The dynamic pressure calculation is expressed by the following formula:

[0093]

[0094] The calculation of ground explosion shock wave overpressure is performed after the following judgment conditions are met:

[0095]

[0096] The stable cloud computing module is used to describe the stable cloud shape parameters and the sedimentation ash mass parameters, and is used to obtain the distribution of the stable cloud. In specific implementation, the embodiment of the present application can provide that the description of the stable cloud shape parameters includes:

[0097] According to the observation data, the height of the stable cloud cap is fitted, H B and top height H T It is expressed by the following formula:

[0098] H B =aQ b

[0099] H T =cQ d

[0100] Where Q represents the explosion equivalent, H B and H T The unit is meter, and its parameters are:

[0101] a=2228,b=0.3463; Q≤4.07kt

[0102] a=2661,b=0.2198; Q>4.07kt

[0103] c=3597,d=0.2553; Q<2.29kt

[0104] c=3170, d=0.4077; 2.29kt≤Q<19kt

[0105] c=6474,d=0.1650; Q≥19kt

[0106] Radius R of the stable cloud cap c The fitting formula is expressed as:

[0107] R C =exp[6.7553+0.32055ln Q+0.01137478(ln Q) 2 ].

[0108] The explosion accident source term analysis model provided in the embodiment of the present application establishes a relatively complete explosion accident source term analysis model, which can simulate the distribution of light radiation (light impulse), shock waves and stable clouds after the accident, and provide a basis for evaluating and simulating the propagation, impact and prevention of the accident. Through a comprehensive and complete analysis and simulation of the explosion accident, source term parameters such as light radiation, shock waves and radioactive smoke clouds can be obtained, so that decision makers can set corresponding protective measures according to the various source term parameters obtained, and provide a scientific basis for emergency response, pollution control and public protection after the accident. Compared with the traditional single source term simulation, this method can obtain rich and diverse source term data with one model, reducing the model setting cost and the time cost required for calculation.

[0109] The analytical results of the source model and information such as meteorological and geographical parameters are input into the spatiotemporal dynamic model of event development through the system platform to analyze the diffusion situation in the next 8 hours, 24 hours or a specified time, and output the concentration distribution of released substances under a specific time series.

[0110] The spatiotemporal dynamic model of event development provided in the embodiment of the present application is applicable to the simulation of the evolution and diffusion of hazard levels in different regional scale scenarios (the first high-altitude global model is 200km×200km, the second high-altitude global model is 100km×100km, and the low-altitude mesoscale model is 50km×50km and 5km×5km).

[0111] The average motion part is provided by the model's own wind field diagnostic mode or the external weather forecast mode, and the fluctuation part is represented by the sum of the correlation part (the influence of the fluctuation at the previous moment on the fluctuation at the next moment) and the random part (using random processes to simulate the randomness of turbulent pulsations).

[0112] Compared to other diffusion models, the Lagrangian particle random walk model offers a simpler computational approach. By simply modifying the wind speed fluctuation properties, the model can be adapted to diffusion calculations at various scales. For regional-scale models (200 km × 200 km, 100 km × 100 km), atmospheric turbulence is negligible. Here, the movement of pollutants in the atmosphere primarily occurs through transport. Removing or significantly reducing the wind speed fluctuation factor during simulations can adapt to these environments. For local-scale models (50 km × 50 km, 5 km × 5 km), atmospheric turbulence is intense, disrupting the stratified structure and causing more random movement of pollutants. Therefore, increasing the wind speed fluctuation factor during simulations is necessary to accommodate these environments.

[0113] When simulating particle diffusion at different regional scales, the corresponding particle dynamics equation can be determined according to the type of regional scale where the particles are located. Specifically:

[0114] 1. For simulations on a 200km×200km regional scale

[0115] Considering the low overall particle concentration, ignoring the effect of particles on gas flow, particle motion is mainly affected by atmospheric drag and gravity. At this time, ignoring the atmospheric turbulence wind field velocity u can be used in, is the average wind speed within the time step Δt.

[0116] The particle dynamics equation is as follows:

[0117]

[0118] Among them, u p 、x p is the velocity and position of the particle; a D is the drag acceleration, a G is the acceleration due to gravity.

[0119] In order to solve the problem of large errors in concentration statistics caused by insufficient sampling number of Lagrangian particle model, the kernel function calculation method is used to calculate the concentration on the ground. The concentration distribution is:

[0120]

[0121] Among them C ij (t) represents the ground average concentration of the (i, j)th grid at time t, Q k (t) represents the source intensity of the kth particle at time t, and the kernel function f(xx k ,yy k ) represents the normalized mass distribution of the kth particle. In this model, Gaussian distribution is used, S ij Represents the area of the (i,j)th grid.

[0122] 2. Simulation of a 100km×100km regional scale

[0123] At this scale, the particle size is small, the evaluation area is large, and the time step is long. The effects of atmospheric drag, gravity, and Brownian motion are not considered. The particle dynamics equation is as follows:

[0124]

[0125] Where u is the wind speed; it satisfies the following formula:

[0126]

[0127] in, is the average wind speed within the time step Δt, u′ is the fluctuation of wind speed (also known as turbulent energy velocity), which satisfies:

[0128] u′(t)=u′(t-Δt)R(Δt)+u″

[0129] Among them, the Lagrangian coupling coefficient R(Δt)=exp(-Δt / T L ), random fluctuation u″ satisfies Gaussian distribution, with mean 0 and variance

[0130] In this scale mode, the kernel function calculation method is used to calculate the concentration on the ground, and the kernel function calculation method is used to calculate the concentration in the air at the ground level. The concentration distribution is:

[0131]

[0132] Among them, C ij (t) represents the average ground-layer air concentration of the (i, j)th grid at time t, Q k (t) represents the source intensity of the kth particle at time t, and the kernel function f(xx k ,yy k ,zz k ) represents the normalized mass distribution of the kth particle, and Gaussian distribution is used in this model, V ij Represents the (i,j)th grid volume of the ground layer.

[0133] 3. For simulations on a 50km×50km or 5km×5km regional scale

[0134] At this scale, the particle concentration is low, and the effect of particles on gas flow is not considered. Particle motion is mainly affected by atmospheric drag, Brownian force, and gravity. Therefore, the particle dynamics equation is as follows:

[0135]

[0136] Among them, u p 、x p is the velocity and position of the particle; a D is the drag acceleration, a B is the Brownian force acceleration, a G is the acceleration due to gravity.

[0137] Where u is the wind speed; it satisfies the following formula:

[0138]

[0139] in, is the average wind speed within the time step Δt, u′ is the fluctuation of wind speed (also known as turbulent energy velocity), which satisfies:

[0140] u′(t)=u′(t-Δt)R(Δt)+u″

[0141] Among them, the Lagrangian coupling coefficient R(Δt)=exp(-Δt / T L ), random fluctuation u″ satisfies Gaussian distribution, with mean 0 and variance

[0142] In this scale mode, the kernel function calculation method is used to calculate the concentration on the ground, and the kernel function calculation method is used to calculate the concentration in the air at the ground level. The concentration distribution is:

[0143]

[0144] Among them, C ij (t) represents the average ground-layer air concentration of the (i, j)th grid at time t, Q k (t) represents the source intensity of the kth particle at time t, and the kernel function f(xx k ,yy k ,zz k ) represents the normalized mass distribution of the kth particle, and Gaussian distribution is used in this model, V ij Represents the (i,j)th grid volume of the ground layer.

[0145] This application provides two kernel function equations for different scale models, employing a kernel function approach to address concentration fluctuations. The kernel function approach treats the mass of each simulated particle not as a single point (delta function), but as a distribution function (such as a Gaussian function) centered on the particle's current coordinates. Using this approach to calculate concentration at spatial coordinate points significantly reduces concentration field fluctuations.

[0146] The calculation is complete when it reaches a certain level of accuracy. Without this (kernel function) method, sampling and calculation would have required 20,000 calculations. Now, convergence is achieved with 2,000 calculations. Previously, one point was sampled, but now each sample represents n samples, representing the sampling of a cluster of particles. This achieves acceleration. Sampling can be done in this way at every scale. Think of the atmosphere as many air particles, and count where each particle will be at each moment in the future. Each particle count count counts as one sample. Each sample performs the aforementioned diffusion calculation.

[0147] At the same time, it is determined whether the system platform has real-time monitoring data uploaded in the corresponding time series. If so, the monitoring data is used to verify and correct the analysis results, that is, data assimilation processing, and the output concentration distribution of the released substances is updated. At the same time, with the help of the visualization function of the system platform, the prediction results are visualized.

[0148] The research on the prediction and assessment of radiation hazard areas using data assimilation technology mainly includes the following aspects: (1) selecting an appropriate diffusion model to reflect the real physical process as accurately as possible while considering costs and benefits; (2) rationally arranging or selecting observation points in the observed area, pre-processing the observation positions before the assimilation begins, or cleaning and screening the assimilated data in order to obtain the observation data that is most coordinated with the assimilation system; (3) selecting an appropriate assimilation algorithm and writing it using programming software to make it coordinated with the diffusion model.

[0149] Data assimilation involves two processes: prediction and update. The prediction process initializes the model based on the state value at time t, continuously integrating forward to guide new observations into the input, and predicting the model state value at time t+1. The update process weights the observed value at time t+1 and the model state prediction value to obtain the optimal estimate of the current state, where the weight is determined by the error between the two. The model is reinitialized based on the current state value at time t+1, and the prediction and update steps are repeated to complete the prediction and update of the state for all observations. Currently, the most mature algorithms are mainly based on the Kalman filter series.

[0150] The main process of radionuclide data assimilation is as follows:

[0151] (1) Data simulation.

[0152] Based on the existing source information (user input) as input conditions, a diffusion model based on numerical simulation is used to generate high-resolution simulation prediction data.

[0153] (2) Real-time data acquisition and preprocessing.

[0154] Use sensor networks or mobile monitoring equipment to conduct continuous and high-frequency observations of key on-site parameters (such as concentration, wind direction, wind speed, etc.) to obtain the latest and most accurate real-time monitoring data.

[0155] Real-time data preprocessing: Cleans, calibrates, and standardizes the collected real-time monitoring data. This includes removing outliers, eliminating systematic errors, and ensuring data consistency and integrity.

[0156] (3) Construction of assimilation framework.

[0157] Model selection: Choose an appropriate assimilation method (such as Kalman filtering, ensemble Kalman filtering, or particle filtering) based on the data type and assimilation requirements. Different algorithms have different applicable scenarios and technical characteristics, so you need to make a reasonable choice based on the specific problem.

[0158] Window setting: Set a reasonable assimilation time period or frequency. This is not only related to the timeliness of data updates, but also involves the trade-off between model parameter adjustment and data matching.

[0159] (4) Assimilation implementation.

[0160] Data matching: Accurately match real-time monitoring data with the data at corresponding times and locations in simulated forecast data to ensure temporal and spatial consistency.

[0161] Assimilation calculation: Use the selected assimilation method (such as Kalman filtering) to update and optimize the simulation results. By introducing observation information, correct or adjust model parameters, initial conditions, or other state variables to improve simulation accuracy.

[0162] (5) Result evaluation and feedback.

[0163] Verification analysis: Compare and analyze the assimilated numerical simulation results with the real-time monitoring data to evaluate the accuracy and reliability of the assimilation effect.

[0164] Optimization and adjustment: Based on the verification results, further optimize the model parameters or algorithm strategies to improve assimilation accuracy and prediction capabilities.

[0165] (6) Results presentation.

[0166] Result display: The optimized simulation results are combined with GIS for visualization, which helps decision makers to quickly understand the on-site situation.

[0167] Relevant social data and resource (personnel, materials, etc.) data are input through the system platform, combined with the analysis results of the spatiotemporal dynamic model of event development, and the hazard assessment model is called to evaluate the injury situation of personnel and generate a hazard assessment report.

[0168] Hazard assessments are not only related to individual outcomes but also to demographic, economic, and environmental factors. Therefore, all consequences must be assessed through a cost analysis process to determine the comprehensive cost of each outcome. The primary challenge in cost analysis is quantifying political and environmental factors. The hazard assessment model presented in this application employs fuzzy mathematics to establish cost indicators and cost indicator equivalence assessment methods, thereby quantifying fuzzy factors. This allows the development of a mathematical model for cost utilization analysis, enabling analysis of action plans.

[0169] Three countermeasure optimization methods are adopted for hazard analysis, namely cost-effectiveness analysis, cost-benefit analysis and multi-attribute utility analysis.

[0170] a. Cost-effectiveness analysis.

[0171] To assess the impact of various consequences, the minimum unit cost of each option is calculated, namely the cost-effectiveness ratio ΔX / ΔS, where ΔX is the increased cost of implementing a protection option compared to the previous option, and ΔS is the corresponding reduction in collective dose. The option with the smaller cost-effectiveness ratio is considered the better option. This analysis method only considers the two most basic factors: protection cost and collective dose.

[0172] This method is simple and easy to implement, and does not require a predetermined α value (the monetary cost equivalent to the collective dose per person·Sv, which is stipulated by law by the competent authorities). This method also has some shortcomings, for example, it only produces a better solution, not necessarily the optimal solution, and it cannot determine the optimal protection level.

[0173] b. Interest analysis.

[0174] The cost-benefit analysis method is a method that directly reflects the optimization concept. Its main feature is that it can identify the solution with the maximum total net benefit, namely:

[0175] B=V-(P+X+Y)=maximum

[0176] In the formula, B is the total net benefit, V is the gross benefit, P is all production costs excluding costs related to radiation protection, X is the cost of protection required to achieve the corresponding level of protection, and Y is the radiation hazard cost associated with that level of protection. If V and P are assumed to be unrelated to radiation protection, then to maximize B, the sum of X + Y must be minimized. In other words, the core of cost-benefit analysis is to find the protection plan that minimizes the sum of the radiation protection cost and the radiation hazard cost—the optimal protection plan.

[0177] In practical applications, two methods can be used to calculate the radiation hazard cost Y. One method only considers the collective dose without considering the distribution of individual doses. The corresponding cost-benefit analysis method of this calculation method is called the simple cost-benefit analysis method; the other calculation method considers both the collective dose and the distribution of individual doses, which is called the extended cost-benefit analysis method.

[0178] The radiation hazard cost Y is:

[0179] Y=αS

[0180] Where α is the monetary cost of unit collective dose radiation exposure, yuan / person·Sv; S is the collective dose, person·Sv.

[0181] The difference between the extended cost-benefit analysis method and the simple cost-benefit analysis method is that the analysis not only considers the protection cost and collective dose, but also considers other factors related to radiation protection, such as the distribution of individual doses, different types of population groups, and possible adverse effects of protective measures.

[0182] Taking the impact of individual doses as an example, the distribution of individual doses is often uneven. Larger doses can lead to greater harm, so even at a greater cost, efforts should be made to reduce these larger individual doses. Specifically, when calculating the cost of radiation hazards, the term β, reflecting the distribution of individual doses, is added to the above formula. Y is then calculated as follows:

[0183]

[0184] Where S j represents the collective dose of the jth group of workers, which is the number of people in the group N j and average dose H j The product of j is the additional cost of collective dose given to group j, for different levels of individual dose, β j The greater the individual dose, the greater the j The larger the value, the greater the risk. The cost-benefit analysis method can determine the optimal level of protection and the path to achieving it. This method can be considered a relatively direct reflection of the basic concept of radiation protection optimization.

[0185] c. Multi-attribute utility analysis.

[0186] Multi-attribute utility analysis is a widely used countermeasures method. Its outstanding feature is that it can quantify factors that are difficult to quantify with monetary values, thereby making quantitative judgments on issues that can usually only be analyzed qualitatively, making countermeasures more scientific.

[0187] In the multi-attribute utility analysis method, the utility function is first determined for each factor to be considered, then the corresponding utility value of each plan is calculated, and finally the total utility values of each plan are compared. The plan with a higher total utility value is the best.

[0188] After obtaining the partial utility value of each factor, we weighted them and sum them up to calculate the total utility value of each plan according to the following formula:

[0189]

[0190] Where U represents the total utility value of the i-th option, u ij represents the partial utility of the i-th plan for factor j; w j represents the weight factor assigned to factor j (j = 1, 2, ..., n), which is normalized, i.e. ∑wj =1.

[0191] This approach may be very attractive for solving high-level strategic problems, but it can be difficult to implement in practice because it requires the precise formulation of utility functions (which are often nonlinear) and the evaluation and assignment of weighting factors.

[0192] The disposal intentions of command organizations at all levels are input through the system platform, combined with the hazard assessment results output by the hazard assessment model, and the auxiliary decision-making model library is called to analyze and generate relevant plans or programs.

[0193] The intelligent decision-making support model provided in the embodiment of the present application includes a random forest decision-making support model and reinforcement learning. The two parts are introduced in detail below.

[0194] Reinforcement learning (PPO) is a machine learning technique that trains software to make decisions to achieve optimal outcomes. It mimics the trial-and-error learning process humans use to achieve their goals. Software actions that contribute to the goal are reinforced, while actions that deviate from the goal are ignored.

[0195] The main advantage of combining the random forest and PPO algorithms lies in their respective characteristics and complementary nature. The random forest model has a relatively simple structure, a clear decision path, and is easy to understand and interpret. It can quickly perform preliminary screening and provide initial evacuation plans based on predefined rules and conditions, making it suitable for most common situations. It also has low computational cost and can quickly produce results when dealing with simpler problems with clear rules. The PPO algorithm excels in handling high-dimensional data and complex nonlinear decision-making problems. It can make optimized decisions in dynamic and complex environments. Through continuous learning and optimization, it adapts to changing environments and conditions, improving the system's decision-making capabilities. Through trajectory sampling and cumulative reward calculation, it optimizes decision-making strategies, making the generated evacuation plans more reasonable and effective overall.

[0196] In some cases, the random forest model may not be able to effectively handle complex environmental data and environmental changes, resulting in an unclear decision path or difficulty handling high-dimensional data and nonlinear relationships. In this case, the Proximal Political Optimization (PPO) algorithm will be called to provide optimized decisions.

[0197] When a random forest model encounters a dilemma where it can't clearly define a decision path, it's usually due to conflicting information or high uncertainty in the input data. In these situations, the random forest model can't provide a clear decision solution. The PPO algorithm, however, uses a policy network to generate a new decision-making strategy that can handle dynamic and uncertain environments.

[0198] Furthermore, when the input data is high-dimensional and contains complex nonlinear relationships between variables, the random forest model may not be able to adequately model and generate reasonable decisions. For example, when on-site information includes multiple sources of danger, complex wind direction and speed variations, and diverse traffic conditions, the random forest model struggles to process this high-dimensional data and generate effective evacuation plans. In such cases, the PPO algorithm continuously optimizes its decision-making strategy through trajectory sampling and cumulative reward calculation. This effectively handles high-dimensional data and complex nonlinear relationships, generating more reasonable and effective evacuation plans.

[0199] It can be understood that the final determined target disposal plan can be directly displayed to the decision maker for the decision maker to analyze and judge on his own to achieve the purpose of assisting decision-making. In actual applications, in order to deduce the feasibility of the formed target disposal plan, the embodiment of the present application can also provide a task simulation deduction model to simulate and deduce the target disposal plan to evaluate the feasibility and effectiveness of the target disposal plan.

[0200] In summary, the explosion event analysis and prediction method provided by this application mainly includes three aspects: source analysis, diffusion prediction, and hazard assessment. It can comprehensively and timely analyze and guide the source information, diffusion situation, and emergency response plan of the accident event, and provide decision makers with reference decision plans, which is conducive to timely emergency response after the accident occurs and reduce the loss of life and property.

[0201] See also Figure 3 , the embodiment of the present application can also provide an explosion event analysis and prediction device, such as Figure 3 As shown, the device for executing the above-mentioned explosion event analysis and prediction method may include:

[0202] The source item simulation analysis unit 301 is used to determine the event type and call the explosion accident source item analysis model corresponding to the event according to the event type, so as to analyze and determine the hazard source item of the event through the explosion accident source item analysis model;

[0203] The diffusion prediction unit 302 is configured to input the analysis results of the explosion accident source analysis model, meteorological information, and geographic parameters into the event development spatiotemporal dynamic model, so that the event development spatiotemporal dynamic model can analyze the diffusion of the released substances after the target time period in the future and output the concentration distribution of the released substances in the target time series.

[0204] The hazard assessment unit 303 is used to obtain social situation data and resource data corresponding to the treatment plan to be evaluated, combine the analysis results of the spatiotemporal dynamic model of the event development, call the hazard assessment model library to evaluate the injury situation of the personnel, and generate a hazard assessment report corresponding to the treatment plan to be evaluated;

[0205] The auxiliary decision-making unit 304 is used to obtain the disposal intentions of command organizations at all levels, combine the hazard assessment results output by the hazard assessment model, call the auxiliary decision-making model, analyze and obtain the disposal intentions and generate relevant plans or programs.

[0206] The present application also provides an explosion event analysis and prediction device, which includes a processor and a memory.

[0207] The memory is used to store program code and transmit the program code to the processor;

[0208] The processor is used to execute the steps of the above-mentioned explosion event analysis and prediction method according to the instructions in the program code.

[0209] like Figure 4 As shown, an explosion event analysis and prediction device provided by an embodiment of the present application may include: a processor 10, a memory 11, a communication interface 12, and a communication bus 13. The processor 10, the memory 11, and the communication interface 12 communicate with each other via the communication bus 13.

[0210] In the embodiment of the present application, the processor 10 may be a central processing unit (CPU), a graphics processing unit (GPU), an application-specific integrated circuit, a digital signal processor, a field programmable gate array, or other programmable logic devices.

[0211] The processor 10 may call a program stored in the memory 11 . Specifically, the processor 10 may execute operations in an embodiment of the explosion event analysis and prediction method.

[0212] The memory 11 is used to store one or more programs. The program may include program code, and the program code includes computer operating instructions. In the embodiment of the present application, the memory 11 stores at least a program for implementing the following functions:

[0213] Determining the event type, and calling the explosion accident source item analysis model corresponding to the event according to the event type, so as to analyze and determine the hazard source item of the event through the explosion accident source item analysis model;

[0214] Inputting the analysis results of the explosion accident source analysis model, meteorological information, and geographic parameters into the event development spatiotemporal dynamic model, so that the event development spatiotemporal dynamic model analyzes the diffusion of the released substances after the future target time period and outputs the concentration distribution of the released substances in the target time series;

[0215] Obtaining social situation data and resource data corresponding to the disposal plan to be evaluated, combining the analysis results of the spatiotemporal dynamic model of the event development, calling the hazard assessment model library to evaluate the injury situation of personnel, and generating a hazard assessment report corresponding to the disposal plan to be evaluated;

[0216] Obtain the disposal intentions of command organizations at all levels, combine them with the hazard assessment results output by the hazard assessment model, call the auxiliary decision-making model, analyze the disposal intentions and generate relevant plans or programs.

[0217] In one possible implementation, the memory 11 may include a program storage area and a data storage area, wherein the program storage area can store an operating system and application programs required for at least one function (such as a file creation function, a data reading and writing function), etc.; the data storage area can store data created during use, such as initialization data, etc.

[0218] In addition, the memory 11 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device or other volatile solid-state storage device.

[0219] The communication interface 12 may be an interface of a communication model, used for connecting to other devices or systems.

[0220] Of course, it needs to be explained that Figure 4 The structure shown does not constitute a limitation on the explosion event analysis and prediction device in the embodiment of the present application. In actual application, the explosion event analysis and prediction device may include Figure 4 More or fewer components than shown, or combinations of certain components.

[0221] The embodiment of the present application may also provide a computer-readable storage medium, wherein the computer-readable storage medium is used to store program code, and the program code is used to execute the steps of the above-mentioned explosion event analysis and prediction method.

[0222] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0223] Through the description of the above embodiments, it can be seen that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or certain parts of the embodiments of the present application.

[0224] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple. For relevant parts, refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without expending creative work.

[0225] The above description is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention are included in the scope of protection of the present invention.

Claims

1. A method for analyzing and predicting explosion events, characterized in that: include: Determining the event type, and calling the explosion accident source item analysis model corresponding to the event according to the event type, so as to analyze and determine the hazard source item of the event through the explosion accident source item analysis model; Inputting the analysis results of the explosion accident source analysis model, meteorological information, and geographic parameters into the event development spatiotemporal dynamic model, so that the event development spatiotemporal dynamic model analyzes the diffusion of the released substances after the future target time period and outputs the concentration distribution of the released substances in the target time series; Obtaining social situation data and resource data corresponding to the disposal plan to be evaluated, combining the analysis results of the spatiotemporal dynamic model of the event development, calling the hazard assessment model library to evaluate the injury situation of personnel, and generating a hazard assessment report corresponding to the disposal plan to be evaluated; Obtain the disposal intentions of command organizations at all levels, combine them with the hazard assessment results output by the hazard assessment model, call the auxiliary decision-making model, analyze the disposal intentions and generate relevant plans or programs.

2. The explosion event analysis and prediction method according to claim 1, wherein: The explosion accident source term analysis model at least includes a light impulse calculation module, a shock wave damage calculation module and a stable cloud computing module.

3. The explosion event analysis and prediction method according to claim 2, wherein: The light impulse calculation module is used to calculate the light impulse and the influence of terrain and objects on light radiation by using the explosion equivalent, explosion mode and distance from the explosion center to obtain the light radiation damage characteristic value; The shock wave damage calculation module is used to perform air shock wave overpressure calculation, ground explosion shock wave overpressure calculation, and dynamic pressure calculation using the explosion equivalent, the explosion mode, and the distance from the explosion center to obtain the shock wave damage characteristic value; The stable cloud computing module is used to describe the stable cloud shape parameters and the sedimentation ash mass parameters, and is used to obtain the distribution of the stable cloud.

4. The explosion event analysis and prediction method according to claim 1, wherein: The event development spatiotemporal dynamic model is used to determine the target regional scale mode in which the diffusion area is located, and the target regional scale mode includes any one of a first high-altitude global mode, a second high-altitude global mode, and a low-altitude scale mode; According to the target regional scale model, the corresponding particle dynamics equation is called to calculate the average wind speed in the east direction within the time step required by the Lagrangian particle random walk model; Utilizing the average wind speed in combination with the Lagrangian particle random walk model to calculate and obtain explosion event analysis and prediction results; Calling a corresponding kernel function to simulate the spatial concentration distribution of particles according to the target area scale pattern; The particle dynamics equation corresponding to the first high-altitude global model takes into account the influence of atmospheric drag and gravity and ignores the atmospheric turbulent wind field speed; the particle dynamics equation corresponding to the second high-altitude global model does not consider the influence of atmospheric drag, gravity and Brownian motion; the low-altitude scale model takes into account the influence of atmospheric drag, Brownian force and gravity and does not consider the effect of particles on gas flow; The kernel function is used to calculate the spatial concentration distribution at the spatial coordinate point using a distribution function centered on the current coordinates of the particle.

5. The explosion event analysis and prediction method according to claim 1, wherein: Determine whether there is real-time monitoring data uploaded under the corresponding time series. If so, use the monitoring data to perform data assimilation processing on the simulation prediction data generated by the diffusion model to verify and correct the prediction data and update the output concentration distribution of the released substances.

6. The explosion event analysis and prediction method according to claim 1, wherein: The hazard assessment model library at least includes a cost-effectiveness analysis model, a benefit analysis model, and a multi-attribute utility analysis model; The cost-effectiveness analysis model is used to calculate the cost paid by the minimum unit of the treatment plan to be evaluated, so as to determine whether the treatment plan to be evaluated is superior by judging the ratio of the increased protection cost to the reduction in collective dose; The benefit analysis model is used to calculate the total net benefit of the treatment plan to be evaluated, so as to determine whether the treatment plan to be evaluated is optimal by judging the sum of the radiation protection cost and the radiation hazard cost; The multi-attribute utility analysis model is used to calculate the total utility value of the treatment plan to be evaluated, so as to determine whether the treatment plan to be evaluated is excellent by judging the level of the total utility value.

7. The explosion event analysis and prediction method according to claim 1, wherein: The auxiliary decision model includes a random forest auxiliary decision model and a reinforcement learning algorithm; The random forest decision-making support model is used to make predictions based on the feature vectors. Each decision tree classifies the input feature vectors and gives a recommendation result. The recommended results of all decision trees are voted or averaged to obtain a candidate disposal solution. The selected disposal plan at least includes a selected evacuation order and a selected time and interval; The reinforcement learning algorithm is used to determine that the random forest decision-making auxiliary model cannot clearly define the decision path or faces high-dimensional complexity problems, and then use high-dimensional data to optimize the candidate evacuation order and the candidate time and interval included in the candidate disposal plan to obtain a target disposal plan; the high-dimensional data at least includes a preset evacuation order, preset time and interval, speed, wind direction and traffic conditions.

8. An explosion event analysis and prediction device, characterized in that: The device is used to execute the explosion event analysis and prediction method according to any one of claims 1 to 7, comprising: A source item simulation and analysis unit is used to determine the event type and call the explosion accident source item analysis model corresponding to the event according to the event type, so as to analyze and determine the hazard source item of the event through the explosion accident source item analysis model; a diffusion prediction unit, configured to input the analysis results of the explosion accident source analysis model, meteorological information, and geographic parameters into a spatiotemporal dynamic model of event development, so that the spatiotemporal dynamic model of event development analyzes the diffusion of released substances after a future target time period and outputs the concentration distribution of the released substances in a target time series; The hazard assessment unit is used to obtain social situation data and resource data corresponding to the disposal plan to be evaluated, combine the analysis results of the spatiotemporal dynamic model of the event development, call the hazard assessment model library to evaluate the injury situation of personnel, and generate a hazard assessment report corresponding to the disposal plan to be evaluated; The auxiliary decision-making unit is used to obtain the disposal intentions of command organizations at all levels, combine the hazard assessment results output by the hazard assessment model, call the auxiliary decision-making model, analyze the disposal intentions and generate relevant plans or programs.

9. An explosion event analysis and prediction device, characterized in that: The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the explosion event analysis and prediction method according to any one of claims 1 to 7 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store program code, and the program code is used to execute the explosion event analysis and prediction method according to any one of claims 1 to 7.

Images