Local shelter site selection method, device, equipment, medium and product

Abstract

The invention provides a site selection method, device and equipment of an in-situ shelter, a medium and a product. According to one embodiment of the invention, the method comprises the following steps: evaluating the accident dynamic risk of the chemical industrial park according to the risk factors of the chemical industrial park; based on the accident dynamic risk, calculating accumulated exposure risks of the evacuees reaching different evacuation terminal points; and iteratively selecting an evacuation terminal point with the minimum accumulative exposure risk by using a genetic algorithm, and taking the evacuation terminal point as an in-situ shelter in the chemical industry park.

Description

Technical Field

[0001] This application relates to the field of public safety emergency management technology, and in particular to a method, apparatus, equipment, medium and product for selecting the location of an on-site shelter. Background Technology

[0002] Shelter-in-Place (SIP) is a widely accepted and adopted emergency response strategy after an emergency occurs. Shelter-in-Place refers to the act of seeking safety within an occupied building after an emergency has taken place.

[0003] Currently, the government and relevant organizations have issued guidelines or laws and regulations on on-site evacuation, guiding the public to adopt on-site evacuation emergency strategies rather than blindly fleeing or evacuating in the event of natural disasters such as earthquakes and floods, or accidents such as toxic gas leaks and nuclear accidents.

[0004] However, for those working in the chemical industry, even though the frequency, harm, and exposure to fire, explosion, and toxic hazards are far greater than those of the general public, on-site evacuation has not yet become a widely accepted and adopted emergency response strategy. How to plan the safest on-site evacuation sites in advance has become an urgent problem to be solved. Summary of the Invention

[0005] To overcome the problems existing in related technologies, this application provides a method, apparatus, equipment, medium and product for selecting the location of an on-site shelter.

[0006] According to a first aspect of any embodiment of this application, a method for selecting the location of an on-site shelter is provided, the method comprising:

[0007] Based on the risk factors of the chemical industrial park, assess the dynamic accident risks of the chemical industrial park;

[0008] Based on the aforementioned dynamic risks of the accident, the cumulative exposure risk of evacuees reaching different evacuation endpoints is calculated;

[0009] Using a genetic algorithm, the evacuation endpoint with the lowest cumulative exposure risk is iteratively selected as the on-site shelter within the chemical industrial park.

[0010] According to a second aspect of any embodiment of this application, a site selection device for an on-site shelter is provided, the device comprising:

[0011] The assessment module is used to assess the dynamic accident risks of the chemical industrial park based on the risk factors of the chemical industrial park;

[0012] The calculation module is used to calculate the cumulative exposure risk of evacuees reaching different evacuation endpoints based on the dynamic risk of the accident.

[0013] An iterative module is used to use a genetic algorithm to iteratively select the evacuation endpoint with the lowest cumulative exposure risk as the on-site shelter within the chemical industrial park.

[0014] According to a third aspect of any embodiment of this application, an electronic device is provided, comprising:

[0015] processor;

[0016] Memory used to store processor-executable instructions;

[0017] The processor executes the executable instructions to implement the method described in any embodiment of this application.

[0018] According to a fourth aspect of any embodiment of the present application, a computer-readable storage medium is provided having computer instructions stored thereon that, when executed by a processor, implement the method described in any of the embodiments of the present application described above.

[0019] According to a fifth aspect of any embodiment of this application, a computer program product is provided, having a computer program / instructions stored thereon, which, when executed by a processor, implement the method described in any of the embodiments of this application described above.

[0020] The technical solution provided in this application may include the following beneficial effects:

[0021] As can be seen from the above embodiments, by assessing the dynamic risks of accidents in chemical industrial parks based on risk factors, the rationality of subsequent on-site shelter selection can be improved. Based on the dynamic risks of accidents, the cumulative exposure risk of evacuees reaching different evacuation endpoints is calculated. Using a genetic algorithm, the evacuation endpoint with the minimum cumulative exposure risk is iteratively selected as the on-site shelter within the chemical industrial park. With the goal of minimizing the cumulative exposure risk to evacuees, the safest on-site shelter location within the chemical industrial park is selected, further ensuring the personal safety of evacuees.

[0022] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0023] The accompanying drawings, which are incorporated in and form part of this application, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0024] Figure 1 This is a flowchart illustrating a site selection method for an in-situ shelter according to an exemplary embodiment of this application;

[0025] Figure 2This is a schematic diagram illustrating an assessment of dynamic accident risk according to an exemplary embodiment of this application;

[0026] Figure 3 This is a flowchart illustrating another method for selecting the location of an in-situ shelter according to an exemplary embodiment of this application;

[0027] Figure 4 This is a schematic diagram of a chemical industrial park according to an exemplary embodiment of this application;

[0028] Figure 5 This is a schematic diagram illustrating a dynamic risk of an accident according to an exemplary embodiment of this application;

[0029] Figure 6 This is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of this application;

[0030] Figure 7 This is a block diagram illustrating a site selection device for an in-situ shelter according to an exemplary embodiment of this application. Detailed Implementation

[0031] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0032] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0033] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0034] Because actual chemical accidents are characterized by multiple hazard coupling and dynamic development, they exhibit extremely high uncertainty and unpredictability. Current methods for selecting sites for on-site shelters typically only involve static analysis of the impact of factors such as distance, journey, and feasibility on site selection, or choosing the optimal location from existing and alternative shelter facilities. These methods are unable to adaptively plan the safest on-site shelters.

[0035] To address the aforementioned problems, this application proposes a method for selecting the location of in-situ shelters. The following embodiments are provided to further illustrate this application:

[0036] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for selecting the location of an in-situ shelter according to an exemplary embodiment of this application. This method for selecting the location of an in-situ shelter can be applied to a location selection system and may include the following steps:

[0037] Step 102: Assess the dynamic accident risks of the chemical industrial park based on the risk factors of the chemical industrial park.

[0038] In this step, the site selection system can receive risk factors of the chemical industrial park input by the user, construct possible accident scenarios based on the risk factors of the chemical industrial park, and use risk assessment technologies such as domino dynamic simulation algorithm, event tree analysis, and Bayesian network, combined with historical data and real-time monitoring data, to assess the dynamic risk of accidents in the chemical industrial park.

[0039] Risk factors are various factors that lead to or affect the consequences of an accident. Risk factors can include hazard information and environmental information. Hazard information can include the quantity, coordinates, stored substances, and quantity of hazard sources. Hazard sources are potential hazards that may cause personal injury, property damage, or environmental harm; for example, they could be hazardous chemical storage tanks.

[0040] Environmental information refers to the external environmental conditions that affect the occurrence and spread of accidents within chemical industrial parks. Environmental information can include wind speed, wind direction, humidity, and other information, as well as natural geographical features such as topography and vegetation cover.

[0041] Accident dynamic risk arises from the changes and interactions of various risk factors within a chemical industrial park, and represents the dynamic distribution of comprehensive accident risk. Accident dynamic risk is characterized by variability and uncertainty, and is assessed by considering the changes in risk factors over time, space, and quantity.

[0042] It is understood that the on-site shelter site selection method shown in this application embodiment is applied to chemical industrial parks, but it can also be applied to other related sites with chemical accident emergency management needs. This application embodiment does not limit this.

[0043] In one embodiment, please refer to Figure 2 , Figure 2 A schematic diagram illustrating the assessment of dynamic accident risk is shown. The dynamic risk assessment system 20 within the site selection system receives input data related to the chemical industrial park. This input data is used to construct a scenario for the chemical industrial park and may include: risk factors, equipment information, and simulation information. Risk factors may include: environmental information and hazard source information of the chemical industrial park.

[0044] The environmental information can include wind direction, wind speed, humidity, atmospheric stability, and temperature. Hazard source information can include type, quantity, and physicochemical properties. Equipment information refers to detailed information about facilities within the chemical industrial park, including coordinates, dimensions, quantity, weight, material, and pressure. Simulation information consists of parameters for assessing the dynamic risk of domino accidents, such as the number of iterations, simulation duration, and grid size.

[0045] The Dynamic Risk Assessment System 20 dynamically simulates domino accidents. Based on environmental and hazard information in the risk factors, it simulates random initial accidents and uses accident consequences, escalation probability, and damage analysis models to simulate the dynamic development of domino accidents in chemical industrial parks.

[0046] The dynamic risk assessment system 20 performs Monte Carlo simulations, using Monte Carlo simulation technology to repeat the simulation process of domino accidents, synthesizes the data of dynamic domino accident consequences, and generates the accident consequences of domino accidents.

[0047] The dynamic risk assessment system 20 performs statistical data analysis to analyze the consequences of domino accidents. It combines the event probability data of loss-of-containment (LOC) and the event tree model to calculate the probability of domino accidents.

[0048] The dynamic risk assessment system 20 statistically analyzes the consequences and probabilities of domino accidents to determine the risk distribution of dynamic comprehensive accidents. The system outputs and stores dynamic accident risks, dynamically displaying the changing dynamic risks over time, facilitating subsequent safety management planning.

[0049] The dynamic risk assessment system 20 can also use a geographic information system (GIS) to visualize the risk distribution of dynamic accident risks in a real chemical industrial park.

[0050] A domino effect is a chain reaction of accidents that trigger a series of other accidents. The consequences of an accident are the losses or impacts on people, property, and the environment after the accident occurs. The probability of an accident is the likelihood that a particular accident will occur within a certain timeframe.

[0051] Event probability data describes the likelihood of an event occurring, while event tree models are graphical tools used to describe the development path of an accident. Damage analysis models are based on statistics and data analysis and are used to assess the potential damage to people, property, and the environment caused by an accident. Event probability data, event tree models, and damage analysis models can be obtained through historical statistics, expert assessments, or simulation experiments.

[0052] As described above, by using a damage analysis model based on risk factors, a domino accident in a chemical industrial park is simulated. Monte Carlo simulation technology is used to generate the consequences of the domino accident. An event tree model is used to calculate the probability of the domino accident. Based on the consequences and the probability of the accident, the dynamic risk of the accident is determined. Since the development of domino accidents has extremely high uncertainty and unpredictability, it can simulate the characteristics of multi-hazard coupling and dynamic development in actual accidents, and realize a dynamic and quantitative assessment of the dynamic risk of accidents involving multiple hazards such as fire, explosion, and poison.

[0053] Step 104: Based on the dynamic risk of the accident, calculate the cumulative exposure risk of evacuees reaching different evacuation endpoints.

[0054] In this step, the site selection system uses path planning algorithms such as D* algorithm and Dijkstra algorithm to plan evacuation routes from evacuees in the chemical industrial park to different evacuation destinations based on spatial factors such as topography, road network, and obstacle distribution within the chemical industrial park.

[0055] On the evacuation routes of evacuees to different evacuation destinations, the cumulative exposure risk borne by evacuees during the journey is calculated based on the dynamic risk of the accident assessed in step 102.

[0056] The evacuation endpoint is a candidate area for on-site shelter within the chemical industrial park, which can be an area continuously optimized and selected during the iterative process of a genetic algorithm. Cumulative exposure risk is the risk evacuees experience during their journey to different evacuation endpoints, used to assess the safety of different evacuation endpoints.

[0057] Step 106: Using a genetic algorithm, iteratively select the evacuation endpoint with the lowest cumulative exposure risk as the on-site shelter within the chemical industrial park.

[0058] In this step, the site selection system uses a genetic algorithm for iterative search. By evaluating the evolutionary iterative process of fitness, selection, crossover, and mutation, it seeks the evacuation endpoint with the lowest cumulative exposure risk.

[0059] During the iteration process, the selection of evacuation endpoints within the chemical industrial park is continuously optimized, thereby quickly converging to the evacuation endpoint with the lowest cumulative exposure risk, and using the evacuation endpoint with the lowest cumulative exposure risk as the on-site shelter within the chemical industrial park.

[0060] The on-site shelter location selection method in this embodiment improves the rationality of subsequent on-site shelter location selection by assessing the dynamic risk of accidents in the chemical industrial park based on the risk factors of the chemical industrial park. Based on the dynamic risk of accidents, the cumulative exposure risk of evacuees reaching different evacuation endpoints is calculated. Using a genetic algorithm, the evacuation endpoint with the minimum cumulative exposure risk is iteratively selected as the on-site shelter in the chemical industrial park. With the goal of minimizing the cumulative exposure risk to evacuees, the safest on-site shelter location in the chemical industrial park is selected to further ensure the personal safety of evacuees.

[0061] The foregoing embodiments described how, based on the dynamic risk of accidents in chemical industrial parks, the evacuation endpoint with the minimum cumulative exposure risk was iteratively selected to quickly determine the safest on-site shelter. The following embodiments will provide a more detailed explanation of the calculation process for cumulative exposure risk, and this method can be applied to any of the embodiments described above.

[0062] In one embodiment, the evacuation endpoint may include an iterative evacuation endpoint. The iterative evacuation endpoint is an evacuation endpoint that is continuously optimized and selected during the iterative process of the genetic algorithm. It can be the finally determined on-site shelter or an evacuation endpoint during the iterative process.

[0063] The site selection system constructs an equivalent distance criterion, which considers the cumulative accident risk borne by evacuees during their journey. Based on the accident consequences and probability of occurrence in the dynamic risk of accidents, the individual risk of each hazard source is calculated.

[0064] Individual risk is an accident risk indicator determined by the consequences and frequency of an accident. It can be the product of the accident consequences and the probability of an accident for each hazard.

[0065] Chemical industrial parks can include multiple hazard sources. For example, in the case of multi-hazard chemical accidents including fires, explosions, and toxic gas leaks, the site selection system sums the individual risks of multiple hazard sources at each time point to obtain a summation result. Along the evacuation path leading to the iterative evacuation endpoint, the summation result is integrated to generate the cumulative exposure risk at the iterative evacuation endpoint.

[0066] When calculating cumulative exposure risk, the location system can also consider other factors, such as the evacuation speed of evacuees, the availability of evacuation routes (whether they are blocked), and other obstacles during the evacuation process.

[0067] For example, the location system can calculate the cumulative exposure risk according to the following formula 1:

[0068]

[0069] Where CER represents the cumulative exposure risk, R represents the evacuation path of the evacuees to the endpoint of the iterative evacuation, and ρ i (t) represents the accident consequences of hazard source i at time point t. Let represent the probability of an accident occurring at time t for hazard source i, and n represent the number of hazard sources.

[0070] It is understood that the accident risk indicators shown in the embodiments of this application are individual risks. The cumulative exposure risk to different evacuation endpoints can also be calculated based on other accident risk indicators such as economic risk and social risk. The embodiments of this application do not limit this.

[0071] As described above, by calculating the individual risk of each hazard source based on the accident consequences and the probability of occurrence in the dynamic risk of accidents, the individual risks of multiple hazard sources at each time point are summed to obtain the summation result. The summation result is integrated along the evacuation path of the evacuees to the iterative evacuation endpoint to generate the cumulative exposure risk of the iterative evacuation endpoint. By comprehensively considering the accident consequences and the probability of occurrence of each hazard source, as well as the changing trend of individual risks over time, the cumulative exposure risk is made more accurate and reliable, further ensuring the safety of the subsequently selected on-site shelters.

[0072] In one embodiment, the evacuees may include multiple evacuees. These multiple evacuees are distributed across multiple evacuation starting points within the chemical industrial park. Each evacuation starting point is the location where evacuees begin their evacuation and refuge. These multiple evacuation starting points may be located in different areas of the chemical industrial park, and the number of evacuees distributed across each evacuation starting point is uneven.

[0073] When calculating cumulative exposure risk, the site selection system should consider evacuation paths from different evacuation starting points to the iterative evacuation endpoint. Based on the accident consequences and probability of occurrence in the dynamic risk of accidents, the individual risk of each hazard is calculated, and the individual risks of multiple hazard sources at each time point are summed to obtain the summation result.

[0074] Along the evacuation path from each evacuation starting point to the iterative evacuation endpoint, the summation result is integrated to generate the path exposure risk corresponding to each evacuation starting point. Here, path exposure risk is the cumulative accident risk borne by a single evacuee at each evacuation starting point on the evacuation path to the iterative evacuation endpoint.

[0075] Based on the number of evacuees and the path exposure risk at each evacuation starting point, the number of evacuees at each starting point is multiplied by the path exposure risk to obtain the total path exposure risk corresponding to each evacuation starting point. The total path exposure risks corresponding to each evacuation starting point are then summed to obtain the cumulative exposure risk of all evacuees reaching the iterative evacuation endpoint from different evacuation starting points.

[0076] The total path exposure risk is the cumulative total accident risk borne by multiple evacuees at each evacuation starting point along the evacuation path, taking into account the number of evacuees distributed at the evacuation starting point. It is used to assess the total risk level faced by all evacuees during the entire evacuation process.

[0077] For example, the location system can calculate the cumulative exposure risk according to the following formula 2:

[0078]

[0079] Where TCER represents the cumulative exposure risk, k represents the number of evacuation points, and m j R represents the number of people evacuated from the j-th evacuation starting point. j Let ρ represent the evacuation path from the j-th evacuation starting point to the iterative evacuation ending point. i (t) represents the accident consequences of hazard source i at time point t. Let represent the probability of an accident occurring at time t for hazard source i, and n represent the number of hazard sources.

[0080] As described above, by integrating the summation results along the evacuation path from each evacuation starting point to the iterative evacuation endpoint, the path exposure risk corresponding to each evacuation starting point is generated. The number of evacuees at each evacuation starting point is multiplied by the path exposure risk to obtain the total path exposure risk corresponding to each evacuation starting point. The total path exposure risks corresponding to each evacuation starting point are accumulated to obtain the cumulative exposure risk at the iterative evacuation endpoint. This method can accurately calculate the comprehensive risk generated by the distribution of personnel and dynamic risks at each evacuation starting point, and more comprehensively reflect the cumulative exposure risk borne by all evacuees distributed at different evacuation starting points, providing a reliable basis for subsequent site selection decisions.

[0081] In one embodiment, before calculating the cumulative exposure risk, the location system can plan an evacuation path from the evacuation starting point to the iterative evacuation endpoint in a path-free open chemical industrial park based on a path planning algorithm of the improved D* algorithm.

[0082] The location selection system can calculate the individual risk faced by evacuees at the next path point based on the accident consequences and the probability of accident occurrence in the dynamic risk of the accident, and take the individual risk faced by evacuees at the next path point as the actual cost.

[0083] The location selection system calculates the estimated exposure risk of evacuees from the current path point to the iterative evacuation endpoint based on the accident consequences and the probability of accident occurrence in the dynamic risk of the accident, and uses the estimated exposure risk as the estimated cost.

[0084] The location selection system constructs a heuristic function based on actual and estimated costs. Using this heuristic function, the system determines the evacuation path with the lowest risk for evacuees to reach the endpoint of the iterative evacuation.

[0085] Here, the next path point is the next location that the evacuee will reach during their journey towards the iterative evacuation endpoint. The current path point is the current location of the evacuee during their journey towards the iterative evacuation endpoint.

[0086] Actual cost reflects the actual harm an evacuee will suffer at the next waypoint, while estimated cost reflects the total risk an evacuee will face from the current waypoint to the iterative evacuation endpoint. Heuristic functions are used to assess the safety of different evacuation routes. Estimated exposure risk is the cumulative accident risk an evacuee faces along the evacuation route from the current waypoint to the iterative evacuation endpoint.

[0087] The estimated exposure risk can be calculated by summing the individual risks at each time point, and then integrating the sum along the evacuation path from the current path point to the endpoint of the iterative evacuation to obtain the estimated exposure risk.

[0088] As described above, by taking the individual risk faced by evacuees at the next path point as the actual cost, and based on the dynamic risk of the accident, taking the estimated exposure risk of evacuees from the current path point to the iterative evacuation endpoint as the estimated cost, a heuristic function that is closer to the actual situation is constructed based on the actual cost and the estimated cost. Using the heuristic function, the evacuation path corresponding to the iterative evacuation endpoint is determined. According to the dynamic distribution of the dynamic risk of the accident, the path can be planned in a free and open space, thereby generating a safer and more efficient evacuation path and further reducing the cumulative exposure risk during the evacuation process.

[0089] The foregoing embodiments described how to plan evacuation routes to different evacuation endpoints based on dynamic accident risks, and calculate the cumulative exposure risk borne by evacuees along the evacuation routes. The following embodiments will provide a more detailed explanation of the iterative site selection process for on-site shelters, and can be applied to any of the embodiments described above.

[0090] In one embodiment, the site selection system randomly generates a preset number of evacuation endpoints based on the regional scale and grid density of the chemical industrial park, forming the initial population of the genetic algorithm.

[0091] The fitness of individuals at different evacuation endpoints in the initial population is assessed using a fitness function and cumulative exposure risk. The fitness of an evacuation endpoint is inversely proportional to the cumulative exposure risk; the higher the cumulative exposure risk, the lower the fitness, and vice versa.

[0092] Using selection algorithms such as roulette wheel algorithm and tournament algorithm, based on the fitness of different evacuation endpoints, evacuation endpoints with high fitness are selected as parents to pass on their superior individual characteristics to offspring. Individual characteristics can be the coordinate location of the evacuation endpoint.

[0093] Simulated binary crossover and linear crossover algorithms are used to simulate the parent generation, preventing the population from getting trapped in local optima too early. Multinomial mutation and uniform mutation algorithms are then used to give offspring a chance to find other optimal solutions, generating new offspring based on the parent generation to form a new population.

[0094] The fitness, selection, crossover, and mutation of new evacuation endpoints in offspring are iteratively evaluated until preset cutoff conditions such as fitness threshold and least squares method are met, resulting in the evacuation endpoint with the minimum cumulative exposure risk.

[0095] As described above, by utilizing the fitness function and cumulative exposure risk, the fitness of different evacuation endpoints is evaluated. Based on the fitness of different evacuation endpoints, the evacuation endpoint with high fitness is selected as the parent. Using crossover and mutation algorithms, offspring are generated based on the parent. The evacuation endpoints in the offspring are iteratively evaluated, selected, crossovered, and mutated until a preset cutoff condition is met, resulting in the evacuation endpoint with the minimum cumulative exposure risk. By utilizing the global search capability of the genetic algorithm, the evacuation endpoint with the minimum cumulative exposure risk can be quickly screened from a large number of possible solutions, reducing the complexity of on-site refuge site selection while ensuring the accuracy of on-site refuge site selection.

[0096] In one embodiment, the location selection system can construct a fitness function based on the maximum cumulative exposure risk of different evacuation endpoints and the cumulative exposure risk of different evacuation endpoints. The fitness function ensures that evacuation endpoints with lower cumulative exposure risk have higher fitness, thus making them more likely to be retained and used to generate the next generation during the selection process of the genetic algorithm. Through iterative optimization, the evacuation endpoint with the minimum cumulative exposure risk can eventually be found.

[0097] For example, the location system can calculate fitness according to the following formula 3:

[0098] fitness(i) = max p TCER-TCER(i) Formula 3

[0099] Where TCER(i) represents the cumulative exposure risk at evacuation endpoint i, max p TCER represents the maximum cumulative exposure risk at different evacuation endpoints in the current population p.

[0100] As mentioned above, by constructing a fitness function based on the maximum value of the cumulative exposure risk of different evacuation endpoints and the cumulative exposure risk of different evacuation endpoints, the fitness function uses the maximum value and the cumulative exposure risk of each evacuation endpoint as evaluation indicators, which can quickly and intuitively reflect the safety of each candidate evacuation endpoint.

[0101] To further explain the site selection process for shelter-in-place facilities, Figure 3 , Figure 3 A flowchart illustrating another method for selecting the location of in-situ shelters is shown. This method may include the following steps:

[0102] Step 302: Assess the dynamic risk of accidents based on the risk factors of the chemical industrial park.

[0103] In this step, the site selection system collects relevant information such as environmental information, hazard source information, equipment information, storage tank information, and personnel information of the chemical industrial park.

[0104] Please see Figure 4 , Figure 4 A schematic diagram of a chemical industrial park is shown. For example, this chemical industrial park is located in the southeast corner of an island, bordered by the sea on two sides and mountains to the north. The park contains nearly 200 hazardous chemical storage tanks, which store various hazardous chemicals that could potentially cause fires, explosions, or leaks of toxic substances. The park also includes office areas, residential areas, and other areas where people congregate; these areas serve as evacuation points for emergency shelters.

[0105] The site selection system can assess the dynamic accident risk of a chemical industrial park based on input data such as hazard source information, environmental information, and simulation data. For example, the input data for the dynamic risk assessment system 20 can be shown in Table 1:

[0106] Table 1 Input data for Dynamic Risk Assessment System 20

[0107]

[0108] Among them, the center coordinates can be... Figure 4 The origin is located at the top left corner.

[0109] The Dynamic Risk Assessment System 20, based on risk factors such as hazard source information and environmental information, combined with simulation information such as iteration count, simulation duration, and grid size, uses a damage analysis model to simulate domino accidents in chemical industrial parks. By statistically analyzing the consequences and probability of domino accidents, the system determines the dynamic risk of accidents in the chemical industrial park.

[0110] Please see Figure 5 , Figure 5 A schematic diagram of dynamic accident risk is shown. Figure 5 The display shows the risk distribution of the dynamic risk of the accident 300 seconds after the accident occurred, output by the dynamic risk assessment system 20.

[0111] Step 304: Randomly select a set of evacuation endpoints as the initial population.

[0112] In this step, the site selection system collects relevant information such as environmental information, hazardous source information, equipment information, storage tank information, and personnel information of the chemical industrial park to construct a scenario of the chemical industrial park.

[0113] The site selection system encodes the regional coordinates according to the grid scale. The genetic algorithm can be implemented using MATLAB computing tools that calculate real-number encoded coordinates. The real-number coordinates of the site selected for on-site refuge do not need to be specially encoded. Based on the regional scale and grid density of the chemical industrial park, a preset number of coordinate locations are randomly selected as a group of evacuation endpoints as the initial population.

[0114] Step 306: Using heuristic functions, plan evacuation paths for evacuees to reach different evacuation endpoints in the initial population.

[0115] In this step, the location selection system takes the individual risk faced by the evacuee at the next path point as the actual cost, and the estimated exposure risk of the evacuee from the current path point to the iterative evacuation endpoint as the estimated cost.

[0116] Based on actual and estimated costs, a heuristic function is constructed. Using this heuristic function, evacuation paths are planned for evacuees to reach different evacuation endpoints in the initial population.

[0117] Step 308: Based on the dynamic risk of the accident, calculate the cumulative exposure risk borne by evacuees along the evacuation routes at different evacuation endpoints.

[0118] In this step, the site selection system calculates the individual risk of each hazard source based on the accident consequences and the probability of accident occurrence in the dynamic risk of accidents, and sums the individual risks of multiple hazard sources at each time point to obtain the summation result.

[0119] For each iterative evacuation endpoint in different evacuation endpoints, the summation result is integrated along the evacuation path from each evacuation starting point to the iterative evacuation endpoint to generate the path exposure risk borne by a single evacuee at each evacuation starting point.

[0120] Multiply the number of evacuees at each evacuation starting point by the path exposure risk to obtain the total path exposure risk borne by multiple evacuees at each evacuation starting point.

[0121] The total path exposure risk corresponding to each evacuation starting point is summed to obtain the cumulative exposure risk borne by all evacuees during their journey from different evacuation starting points to the iterative evacuation endpoint.

[0122] Continue with Figure 4 Taking the chemical industrial park shown as an example, this park includes evacuation points 1, 2, 3, 4, and 5. Each evacuation point is located in a different location within the park, and multiple evacuees gather at each point. The distribution of evacuees within the chemical industrial park is shown in Table 2.

[0123] Table 2. Distribution of evacuees within the chemical industrial park

[0124] Evacuation starting point coordinate Number of people evacuated Evacuation speed (m / s) 1 (600,250) 5 5 2 (1050,70) 10 5 3 (1540,460) 6 5 4 (1680,700) 2 5 5 (810,840) 4 5

[0125] The site selection system calculates the total path exposure risk borne by multiple evacuees at each evacuation starting point 1, 2, 3, 4 and 5 in the chemical industrial park, based on the coordinates, number of evacuees and evacuation speed. The total path exposure risk corresponding to each evacuation starting point is accumulated to obtain the cumulative exposure risk borne by all evacuees during their journey from the five evacuation starting points to the iterative evacuation endpoint.

[0126] Step 310: Construct a fitness function based on cumulative exposure risk.

[0127] In this step, the location selection system calculates the cumulative exposure risk based on the dynamic risk of the accident and the evacuation route. Then, based on the maximum value of the cumulative exposure risk at different evacuation endpoints and the cumulative exposure risk at different evacuation endpoints, it constructs a fitness function.

[0128] Step 312: Assess fitness at different evacuation endpoints.

[0129] In this step, the location system uses a fitness function to evaluate the fitness of each evacuation endpoint, which can determine the cumulative exposure risk corresponding to each evacuation endpoint.

[0130] Step 314: Select the parent generation based on the fitness of different evacuation endpoints.

[0131] In this step, the location selection system selects the evacuation endpoint with high fitness as the parent based on the fitness of different evacuation endpoints.

[0132] Step 316: Perform crossover and mutation on the parent generation to obtain the offspring generation.

[0133] In this step, the location selection system uses crossover and mutation algorithms to perform crossover and mutation on the parent generation, increasing the diversity of solutions and obtaining newly generated offspring.

[0134] Step 318: Calculate the fitness of the evacuation endpoint in the offspring.

[0135] In this step, the location system uses a fitness function to calculate the fitness of the new evacuation endpoint in the offspring.

[0136] Step 320: Determine whether the cutoff condition is met.

[0137] In this step, the location system compares the fitness of the evacuation endpoint in the offspring with the preset cutoff conditions to determine whether the cutoff conditions are met.

[0138] If the cutoff condition is not met, proceed to step 322;

[0139] If the cutoff condition is met, proceed to step 324.

[0140] Step 322: Determine whether the maximum number of generations has been reached.

[0141] In this step, the location system determines whether the number of iterations has reached the maximum number of generations. The number of iterations is the number of times the process of evolution from the initial population to a new generation is repeated through genetic operations such as selection, crossover, and mutation. The maximum number of generations is the maximum threshold for the number of iterations.

[0142] If the maximum number of generations has not been reached, perform iterative optimization and execute step 314;

[0143] If the maximum number of generations is reached, proceed to step 324.

[0144] Step 324: Determine the evacuation endpoint with the lowest cumulative exposure risk.

[0145] In this step, the site selection system stops iterative optimization, determines the evacuation endpoint with the lowest cumulative exposure risk, and uses this evacuation endpoint as an on-site shelter.

[0146] Continue with Figure 4 Taking the chemical industrial park shown as an example, the parameters, algorithm, and cutoff conditions of the genetic algorithm are shown in Table 3:

[0147] Table 3. Parameters, Algorithm, and Cutoff Conditions for Genetic Algorithms

[0148]

[0149] The crossover rate is 0.8, meaning there is an 80% probability of crossover occurring during the iteration process. The mutation rate is 0.1, meaning there is a 10% probability of mutation occurring during the iteration process.

[0150] The site selection system randomly selects 50 evacuation endpoints within the chemical industrial park as the initial population. A tournament selection algorithm is used to choose evacuation endpoints with high fitness as parents. Simulated binary crossover and polynomial mutation algorithms are then used to perform crossover and mutation on the parents to obtain offspring, and the fitness of the evacuation endpoints in the offspring is calculated.

[0151] If the evacuation endpoint with the highest fitness remains unchanged within 10 generations, then the cutoff condition of the optimal solution remaining unchanged within 10 generations is met, and the evacuation endpoint with the highest fitness is determined as the in-situ shelter. If the cutoff condition is not met and the maximum number of generations is reached, then the evacuation endpoint with the highest fitness is determined as the in-situ shelter. If the cutoff condition is not met and the maximum number of generations is not reached, fitness, selection, crossover, and mutation are iteratively evaluated.

[0152] Please continue reading. Figure 5 In five repeated on-site shelter selection processes, the site selection system consistently output the same shelter location (1050m, 730m). Furthermore, the genetic algorithm used by the site selection system exhibits good convergence efficiency, reaching the cutoff condition within 20 generations in all five repeated site selection processes.

[0153] Figure 5 The locations of evacuation starting points are marked with squares, and the locations of on-site shelters determined by the site selection system are marked with red stars. The evacuation routes from each evacuation starting point to the on-site shelter are also shown. The on-site shelter is adjacent to evacuation starting point 2, demonstrating the importance of population density at the evacuation starting point in the site selection considerations for on-site shelters.

[0154] Figure 6 This is a schematic diagram illustrating the structure of an electronic device according to an exemplary embodiment of this application. The electronic device may be, for example, a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, personal digital assistant, server, smart home appliance, in-vehicle system, etc. (Reference) Figure 6 At the hardware level, the electronic device includes a processor 602, an internal bus 604, a network interface 606, memory 608, and non-volatile memory 610, and may also include other hardware required for business operations. The processor 602 reads the corresponding computer program from the non-volatile memory 610 into the memory 608 and then runs it, forming a location selection device for the on-site shelter at the logical level. Of course, in addition to the software implementation, this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to individual logic units, but can also be hardware or logic devices.

[0155] Figure 7 This is a block diagram illustrating a site selection device for an in-situ shelter according to an exemplary embodiment of this application. (Refer to...) Figure 7The device may include: an evaluation module 702, a calculation module 704, and an iteration module 706, wherein:

[0156] The assessment module 702 is used to assess the dynamic accident risk of the chemical industrial park based on the risk factors of the chemical industrial park;

[0157] The calculation module 704 is used to calculate the cumulative exposure risk of evacuees reaching different evacuation endpoints based on the dynamic risk of the accident.

[0158] The iterative module 706 is used to use a genetic algorithm to iteratively select the evacuation endpoint with the lowest cumulative exposure risk as the on-site shelter within the chemical industrial park.

[0159] In one example, the assessment module 702, when used to assess the dynamic accident risk of a chemical industrial park based on risk factors, includes: simulating a domino accident in the chemical industrial park using a damage analysis model based on the risk factors; generating the accident consequences of the domino accident using Monte Carlo simulation technology; calculating the accident probability of the domino accident using an event tree model; and determining the dynamic accident risk based on the accident consequences and the accident probability.

[0160] In one example, the evacuation endpoint includes an iterative evacuation endpoint, and the chemical industrial park includes multiple hazard sources. The calculation module 704, when used to calculate the cumulative exposure risk of evacuees reaching different evacuation endpoints based on the accident dynamic risk, includes: calculating the individual risk of each hazard source based on the accident consequences and accident occurrence probability in the accident dynamic risk; summing the individual risks of the multiple hazard sources at each time point to obtain a summation result; and integrating the summation result along the evacuation path of the evacuees to the iterative evacuation endpoint to generate the cumulative exposure risk of the iterative evacuation endpoint.

[0161] In one example, the evacuees include multiple evacuees distributed across multiple evacuation starting points within the chemical industrial park; the calculation module 704 is further configured to integrate the summation result along the evacuation path from each evacuation starting point to the iterative evacuation endpoint to generate the path exposure risk corresponding to each evacuation starting point; multiply the number of evacuees at each evacuation starting point by the path exposure risk to obtain the total path exposure risk corresponding to each evacuation starting point; and accumulate the total path exposure risks corresponding to each evacuation starting point to obtain the cumulative exposure risk at the iterative evacuation endpoint.

[0162] In one example, the iterative module 706, when using a genetic algorithm to iteratively select the evacuation endpoint with the lowest cumulative exposure risk as an in-situ shelter within the chemical industrial park, includes: evaluating the fitness of different evacuation endpoints using a fitness function and the cumulative exposure risk; selecting the evacuation endpoint with high fitness as the parent based on the fitness of the different evacuation endpoints; generating offspring based on the parent using crossover and mutation algorithms; and iteratively evaluating, selecting, crossovering, and mutating the evacuation endpoints in the offspring until a preset cutoff condition is met to obtain the evacuation endpoint with the lowest cumulative exposure risk.

[0163] In one example, the iterative module 706, before calculating the fitness of the different evacuation endpoints using the fitness function and the cumulative exposure risk, further includes: constructing the fitness function based on the maximum value of the cumulative exposure risk of the different evacuation endpoints and the cumulative exposure risk of the different evacuation endpoints.

[0164] In one example, before calculating the individual risk of each hazard source based on the accident consequences and probability of occurrence in the dynamic accident risk, the calculation module 704 further includes: taking the individual risk faced by the evacuee at the next path point as the actual cost; the next path point is the next position the evacuee will reach during the journey to the iterative evacuation endpoint; taking the estimated exposure risk of the evacuee from the current path point to the iterative evacuation endpoint as the estimated cost based on the dynamic accident risk; the current path point is the current position of the evacuee during the journey; constructing a heuristic function based on the actual cost and the estimated cost; and using the heuristic function to determine the evacuation path corresponding to the iterative evacuation endpoint.

[0165] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0166] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0167] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions, such as a memory including instructions, is also provided, which can be executed by a processor of an on-site shelter location device to implement the method as described in any of the above embodiments.

[0168] The non-transitory computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc., and this application does not limit it.

[0169] In an exemplary embodiment, a computer program product including a computer program / instruction is also provided, which can be executed by a processor of an on-site shelter location device to implement the method described in any of the above embodiments.

[0170] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0171] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention filed herein. This application is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and alterations can be made without departing from its scope. The scope of this application is limited only by the appended claims.

[0172] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for selecting the location of an on-site shelter, characterized in that, The method includes: Based on the risk factors of the chemical industrial park, assess the dynamic accident risks of the chemical industrial park; Based on the aforementioned dynamic risks of the accident, the cumulative exposure risk of evacuees reaching different evacuation endpoints is calculated; Using a genetic algorithm, the evacuation endpoint with the lowest cumulative exposure risk is iteratively selected as the on-site shelter within the chemical industrial park.

2. The method according to claim 1, characterized in that, The assessment of the dynamic accident risk of the chemical industrial park based on its risk factors includes: Based on the aforementioned risk factors, a damage analysis model was used to simulate a domino accident in the chemical industrial park. The consequences of the domino accident were generated using Monte Carlo simulation technology. The probability of the domino event is calculated using an event tree model. Based on the consequences of the accident and the probability of the accident occurring, the dynamic risk of the accident is determined.

3. The method according to claim 1, characterized in that, The evacuation endpoint includes: an iterative evacuation endpoint; the chemical industrial park includes: multiple hazardous sources. The calculation of the cumulative exposure risk of evacuees reaching different evacuation endpoints based on the dynamic risk of the accident includes: Based on the accident consequences and the probability of accident occurrence in the aforementioned dynamic risk of accidents, the individual risk of each hazard source is calculated; The individual risks of the multiple hazards at each time point are summed to obtain the summation result; Along the evacuation path from the evacuee to the iterative evacuation endpoint, the summation result is integrated to generate the cumulative exposure risk at the iterative evacuation endpoint.

4. The method according to claim 3, characterized in that, The evacuees include multiple evacuees, which are distributed at multiple evacuation points within the chemical industrial park. The method further includes: Integrate the summation result along the evacuation path from each evacuation starting point to the iterative evacuation endpoint to generate the path exposure risk corresponding to each evacuation starting point; Multiply the number of evacuees at each evacuation starting point by the path exposure risk to obtain the total path exposure risk corresponding to each evacuation starting point; The total path exposure risk corresponding to each evacuation starting point is accumulated to obtain the cumulative exposure risk of the iterative evacuation endpoint.

5. The method according to claim 1, characterized in that, The process of using a genetic algorithm to iteratively select the evacuation endpoint with the lowest cumulative exposure risk as the on-site shelter within the chemical industrial park includes: The fitness of the different evacuation endpoints is evaluated using the fitness function and the cumulative exposure risk. Based on the fitness of the different evacuation endpoints, the evacuation endpoint with the higher fitness is selected as the parent. Using crossover and mutation algorithms, offspring are generated based on the parent generation; The evacuation endpoints in the offspring are iteratively evaluated, selected, crossed over, and mutated until a preset cutoff condition is met, thus obtaining the evacuation endpoint with the minimum cumulative exposure risk.

6. The method according to claim 5, characterized in that, Before calculating the fitness of the different evacuation endpoints using the fitness function and the cumulative exposure risk, the method further includes: The fitness function is constructed based on the maximum cumulative exposure risk of the different evacuation endpoints and the cumulative exposure risk of the different evacuation endpoints.

7. The method according to claim 3, characterized in that, Before calculating the individual risk of each hazard source based on the accident consequences and probability of occurrence in the dynamic risk of the accident, the method further includes: The individual risks faced by the evacuees at the next waypoint are taken as the actual cost; the next waypoint is the next location that the evacuees will reach during their journey to the iterative evacuation endpoint. Based on the aforementioned dynamic risks of the accident, the estimated exposure risk of the evacuee from the current path point to the iterative evacuation endpoint is used as the estimated cost; the current path point is the current location of the evacuee during the journey. Based on the actual cost and the estimated cost, a heuristic function is constructed; Using the heuristic function, the evacuation path corresponding to the endpoint of the iterative evacuation is determined.

8. A site selection device for an on-site shelter, characterized in that, The device includes: The assessment module is used to assess the dynamic accident risks of the chemical industrial park based on the risk factors of the chemical industrial park; The calculation module is used to calculate the cumulative exposure risk of evacuees reaching different evacuation endpoints based on the dynamic risk of the accident. An iterative module is used to use a genetic algorithm to iteratively select the evacuation endpoint with the lowest cumulative exposure risk as the on-site shelter within the chemical industrial park.

9. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor implements the method as described in any one of claims 1-7 by executing the executable instructions.

10. A computer-readable storage medium storing computer instructions thereon, characterized in that, When executed by the processor, this instruction implements the method as described in any one of claims 1-7.

11. A computer program product having a computer program / instructions stored thereon, characterized in that, When the computer program / instruction is executed by the processor, it implements the method as described in any one of claims 1-7.

Images