An industrial park management method and device based on big data and a storage medium

Abstract

The application provides an industrial park management method and device based on big data and a storage medium, relates to the field of situation awareness of safety and emergency management, and solves the technical problems that it is difficult to set an escape route with a predictive danger avoiding function for staff when a dangerous event occurs in an industrial park, and it is difficult to identify short or non-fire smoke interference in danger identification; the method comprises the following steps: determining a processing signal of a monitoring point based on a fire area, a smoke concentration and a temperature; when the processing signal is signal one, determining a smoke diffusion path of the monitoring point based on target data; determining a blocking factor of each grid to each staff member according to the smoke diffusion path and a barrier, determining a passing coefficient of each line between the staff member position and the park exit based on the blocking factor, and selecting the most suitable line to arrange the staff member to escape based on the passing coefficient; and the application can improve the personnel safety guarantee of the industrial park after a dangerous event occurs.

Description

Technical Field

[0001] This application relates to the field of situational awareness in security and emergency management, and in particular to a big data-based industrial park management method, device and storage medium. Background Technology

[0002] Industrial parks, as vital carriers of industrial production, bring together a large number of enterprises, equipment, and personnel. Their management involves multiple aspects, including production operations, environmental protection, and safety supervision. With the expansion of industrial scale and the increasing complexity of technology, safety and emergency management have become paramount in industrial park management. Various safety hazards may exist within industrial parks, such as fires, explosions, and toxic gas leaks. Traditional safety management methods often rely on manual inspections and experience-based judgment, which are insufficient for comprehensive, real-time, and precise implementation.

[0003] Currently, most big data-based industrial park management methods struggle to establish predictive hazard avoidance escape routes for workers in the event of a dangerous incident. Often, these routes become ineffective as the environment deteriorates, increasing the safety risks caused by delays due to route changes. Furthermore, most big data-based industrial park management methods fail to identify transient or non-fire-related smoke disturbances during hazard identification. This can lead to large-scale evacuations and production disruptions in the event of small, harmless fires or smoke that are easily extinguished, increasing economic losses and panic.

[0004] Therefore, this invention discloses a big data-based industrial park management method, device, and storage medium to solve the above-mentioned technical problems. Summary of the Invention

[0005] This application provides a big data-based industrial park management method, device, and storage medium, which solves the technical problems of existing technologies in setting up a predictive hazard avoidance escape route for workers when a dangerous event occurs in an industrial park, and in identifying transient or non-fire smoke interference during hazard identification.

[0006] To achieve the above objectives, this application adopts the following technical solution: Firstly, a big data-based industrial park management method is provided, including: Acquire target data and personnel locations at various monitoring points in the industrial park; the target data includes the fire area, smoke concentration, temperature, wind speed, and wind direction at each monitoring point. The processing signal for monitoring points is determined based on the fire area, smoke concentration, and temperature. When the processing signal is signal one, the smoke diffusion path of the monitoring point is determined based on the target data; the blocking factor of each grid for each worker is determined according to the smoke diffusion path and the obstruction; the passage coefficient of each route between the personnel location and the park exit is determined based on the blocking factor; and the optimal route is selected to arrange the workers to escape based on the passage coefficient; among them, the obstruction includes walls, insurmountable equipment and fences. No operation is performed when all processed signals are signal two.

[0007] In conjunction with the first aspect mentioned above, one possible implementation involves acquiring target data and personnel locations at various monitoring points within the industrial park, including: The system uses personnel positioning devices to obtain the real-time location of staff, surveillance cameras to obtain video footage from each monitoring point, and video recognition to determine the fire area at each monitoring point. Based on the dynamic monitoring frequency, smoke concentration sensors are used to obtain the smoke concentration at each monitoring point, and temperature sensors are used to obtain the temperature at each monitoring point. Based on the dynamic monitoring frequency, wind speed and direction are obtained at each monitoring point using an anemometer. The monitoring points are located in flammable and explosive areas, and the dynamic monitoring frequency is determined based on time, regional importance factors, and processed signals.

[0008] In conjunction with the first aspect above, in one possible implementation, the dynamic monitoring frequency is obtained based on time, regional importance factors, and processed signals, including: B1: Determine if the industrial park has processed signal 1 within the previous n minutes of the current time; if yes, set the dynamic monitoring frequency of each monitoring point to the minimum value of the standard frequency range; if no, proceed to B2; where n is manually set, generally 300; the maximum and minimum values ​​of the standard frequency range are set according to the degree of danger of the industrial park, the higher the degree of danger of the industrial park, the smaller the maximum and minimum values; B2: Extract the current working and non-working hours set for the industrial park from the park's data repository, and obtain the number of emergency events during working hours (C1) and the number of emergency events during non-working hours (C2) in the current industrial park within the previous m days; where m is manually set, typically 180 days; emergency events include equipment overheating, fire, and smoke. B3: Extract the area where each monitoring point is located, extract the regional importance factor QZ of the current monitoring point from the park data repository according to the area, and determine the dynamic monitoring frequency DPi of the current monitoring point during working hours by calculation formula (1); where i is 1, it represents the relevant data during working hours, including the dynamic monitoring frequency DP1 and the number of emergency events C1; i is 2, it represents the relevant data during non-working hours, including the dynamic monitoring frequency DP2 and the number of emergency events C2. The calculation formula (1) is: ; In the formula, BP is the median value of the standard frequency range, which is generally taken as 20 seconds / time; BC is the standard number of emergency events, which is obtained based on the number of emergency events in the previous m days of industrial parks of the same type as the current industrial park; ZD is the maximum value of the standard frequency range, and ZX is the minimum value of the standard frequency range. To find the maximum value function, This is a function that takes the minimum value.

[0009] In conjunction with the first aspect above, in one possible implementation, determining the processing signal of the monitoring point based on the fire area, smoke concentration, and temperature includes: D1: Sequentially extract the fire area HM of the monitoring points. When the fire area HM of the monitoring point is greater than 0, set the processing signal of the current monitoring point to signal one; when the fire area HM is not greater than 0, jump to D2. D2: Sequentially extract the smoke concentration YN and temperature WD of the monitoring point. When the smoke concentration YN is greater than the standard smoke threshold BYN, determine the reference factor CZ of the monitoring point based on the calculation formula (2). When the reference factor CZ is greater than the factor threshold, set the processing signal of the current monitoring point as signal one. When the reference factor CZ is not greater than the factor threshold, set the processing signal of the current monitoring point as signal two. The standard smoke threshold BYN and the factor threshold are both set based on experience. The processing signals include signal one and signal two. The calculation formula (2) is: ; In the formula, BW is the average historical temperature of the current monitoring point; and It is a proportional adjustment coefficient set based on experience, and , .

[0010] In conjunction with the first aspect mentioned above, one possible implementation involves determining the smoke diffusion path of monitoring points based on target data, including: Extract 3D models of industrial park buildings and equipment information of each piece of equipment from the park's data repository; the equipment information includes the appearance features and physical characteristics of the equipment. Equipment models are constructed based on the equipment information of each device, and simulation models are constructed based on the 3D model of the plant. The equipment models and simulation models are combined to generate a diffusion analysis model. The target data from each monitoring point is input into the diffusion analysis model to obtain the smoke diffusion path at each monitoring point.

[0011] In conjunction with the first aspect above, in one possible implementation, the blocking factor of each grid for each worker is determined based on the smoke diffusion path and the obstruction, including: E1: Divide the industrial park into several grids according to the standard area, and determine in turn whether there are any obstructions in the grids; if yes, set the blocking factor DZ of the grid to infinity; if no, jump to E2; where the standard area is manually set, it is generally set to 1 square meter. E2: Determine whether the grid is not in the smoke diffusion path of any monitoring point; if yes, mark the blocking factor DZ of the grid as 0; if no, extract the personnel positions sequentially, and determine the walking time ZC1 of the corresponding worker from the personnel position to the grid according to the standard speed; extract the position of the corresponding monitoring point, and obtain the distance between the grid and the corresponding monitoring point position. Based on the current wind speed and distance at the monitoring point Determine the duration ZC2 of smoke diffusion from the corresponding monitoring point to the grid; subtract ZC2 from the duration ZC1 to obtain the duration deviation value, and add the duration deviation value to the current time to obtain the smoke impact time point of the corresponding monitoring point affecting the current grid; if the smoke impact time point is not after the current time, extract the smoke concentration of the monitoring point at the smoke impact time point. If the time point of smoke impact is after the current time, the smoke concentration at the monitoring point at the time point of smoke impact is determined based on formula (3). , and jump to E3; where j is the number of the monitoring point corresponding to the smoke diffusion path of the grid, and the value range of j is [1, r], and r is the maximum value of the corresponding monitoring point number; the standard speed is the average speed of workers walking quickly in the current industrial park; E3: Extract the smoke concentration at the corresponding monitoring point at the time of smoke impact. The blocking factor DZ of the grid is determined by calculation formula (4); The calculation formula (3) is: ; In the formula, CPZ is the duration deviation value obtained by subtracting duration ZC2 from duration ZC1; This represents the smoke concentration change between the p nearest time points to the current time and the previous time point from the start time of the smoke at the current monitoring point; e is the number of each time point, and the value of e ranges from [1, p], where p is the maximum value of each time point number; The calculation formula (4) is: ; In the formula, The smoke accumulation impact coefficient, representing the effect of smoke concentration generated at monitoring point j on smoke accumulation in the grid, is obtained based on the changes in smoke concentration at monitoring point j in the smoke generated this time at various times prior to the current time. The value of is [1, 10]; BYN is the standard smoke concentration that affects the breathing of workers; This is determined based on the smoke concentration at monitoring point j at the current time; The wind speed recorded at the current time is the wind speed at monitoring point j; BFS is the standard wind speed set manually, which can be 2 m / s.

[0012] In conjunction with the first aspect mentioned above, one possible implementation involves determining the traffic coefficients of each route between a person's location and the park exit based on a blocking factor, including: Grids located within the standard range of monitoring points with processed signals of signal one, or grids with blocking factors greater than the standard blocking factor, are marked as impassable grids. The standard range is determined based on the smoke concentration of the nearest monitoring point with processed signals of signal one, and the standard range is proportional to the smoke concentration. The standard blocking factor is determined based on experiments on the blocking factor and safe passage for personnel. Obtain the grid data for each route from the personnel's location to the park exit, and sum the blocking factors corresponding to the grid data for each route to obtain the passage coefficient.

[0013] In conjunction with the first aspect mentioned above, one possible implementation involves selecting the optimal route for staff evacuation based on traffic flow coefficients, including: Extract the traffic coefficient of each route, sort the routes according to the traffic coefficient from small to large, mark the number of the route with the shortest route as the target number, mark the route corresponding to the target number and the route corresponding to the smaller target number as the expected route, and determine the suitability factor YZ of each expected route by calculation formula (5), mark the expected route with the smallest suitability factor YZ as the optimal route; guide the staff to escape the industrial park according to the optimal route by wearing a safety helmet; The calculation formula (5) is: ; In the formula, TL is the expected passage coefficient of the line, PTL is the average of the passage coefficients of each expected line, LC is the line length of the expected line, and PLC is the average of the line lengths of each expected line. and A proportional adjustment coefficient set to balance safety and speed, and .

[0014] Secondly, a big data-based industrial park management device is provided, comprising: a communication unit and a processing unit; the communication unit is used to acquire target data and personnel locations at various monitoring points in the industrial park; wherein, the target data includes the fire area, smoke concentration, temperature, wind speed, and wind direction at the monitoring points; The processing unit is used to determine the processing signal of the monitoring point based on the fire area, smoke concentration and temperature. When the processing signal is signal one, the smoke diffusion path of the monitoring point is determined based on the target data; the blocking factor of each grid for each worker is determined according to the smoke diffusion path and the obstruction; the passage coefficient of each route between the personnel location and the park exit is determined based on the blocking factor; and the optimal route is selected to arrange the workers to escape based on the passage coefficient; among them, the obstruction includes walls, insurmountable equipment and fences. No operation is performed when all processed signals are signal two.

[0015] Thirdly, this application provides a storage medium, characterized in that it is used to store a computer program, which, when executed, implements a big data-based industrial park management method.

[0016] This application provides a method, device, and storage medium for industrial park management based on big data, with the following beneficial effects: 1. This invention acquires fire area, smoke concentration, temperature, wind speed, wind direction, and personnel location data at various monitoring points in an industrial park; determines the processing signal for each monitoring point based on the fire area, smoke concentration, and temperature; when a processing signal of signal one exists, determines the smoke diffusion path of the monitoring point based on the target data; determines the blocking factor of each grid for each worker based on the smoke diffusion path and obstructions; determines the passage coefficient of each route between the personnel location and the park exit based on the blocking factor; and selects the optimal route for workers to escape based on the passage coefficient. This invention solves the technical problems of existing technologies in setting up predictive hazard avoidance escape routes for workers during dangerous incidents in industrial parks, and in identifying transient or non-fire-related smoke interference during hazard identification. This invention can improve personnel safety in industrial parks after dangerous incidents.

[0017] 2. The blocking factor DZ established in this invention can dynamically adapt to changes in wind force, smoke diffusion boundary advancement, and concentration, thereby reflecting the changing trends of environmental risks in real time. This adaptive blocking factor allows route planning to accurately assess passage difficulty within seconds, avoiding escape route failure due to environmental deterioration. This invention integrates physical obstacles and gas hazards into a unified assessment system, dynamically adjusting the blocking factor based on changes in spatial location, time process, and environmental conditions, and can also predict the safety of a grid in advance, thus providing forward-looking protection for escape planning. This significantly improves the accuracy, timeliness, and feasibility of emergency route planning, minimizing the time personnel are exposed to harmful smoke and reducing safety risks caused by delays due to route changes.

[0018] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0019] Figure 1 A schematic diagram illustrating the steps of a big data-based industrial park management method provided in this application embodiment; Figure 2 A schematic diagram illustrating the steps for obtaining the blocking factor provided in this application embodiment; Figure 3 This is a schematic diagram of the structure of an industrial park management device based on big data, provided as an embodiment of this application. Detailed Implementation

[0020] In the description of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. The "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "multiple" means two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences.

[0021] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0022] like Figure 1 As shown in the embodiment of this application, an industrial park management method based on big data is provided, including: S1. Obtain target data and personnel locations at various monitoring points in the industrial park; among which, target data includes the fire area, smoke concentration, temperature, wind speed, and wind direction at the monitoring points; S2. Determine the processing signal of the monitoring point based on the fire area, smoke concentration and temperature; S3. When the processing signal is signal one, determine the smoke diffusion path of the monitoring point based on the target data; determine the blocking factor of each grid for each staff member based on the smoke diffusion path and the obstruction; determine the passage coefficient of each route between the staff member's location and the park exit based on the blocking factor; select the optimal route for staff member evacuation based on the passage coefficient; among which, the obstruction includes walls, insurmountable equipment and fences. No operation is performed when all processed signals are signal two.

[0023] In one possible implementation of this application embodiment, the above-mentioned S1 can be implemented by the following S101 and S102, which are described in detail below: S101. Obtain target data and personnel locations at various monitoring points in the industrial park, including: The system uses personnel positioning devices to obtain the real-time location of staff, surveillance cameras to obtain video footage from each monitoring point, and video recognition to determine the fire area at each monitoring point. Based on the dynamic monitoring frequency, smoke concentration sensors are used to obtain the smoke concentration at each monitoring point, and temperature sensors are used to obtain the temperature at each monitoring point. Based on the dynamic monitoring frequency, wind speed and direction are obtained at each monitoring point using an anemometer. The monitoring points are located in flammable and explosive areas, and the dynamic monitoring frequency is determined based on time, regional importance factors, and processed signals.

[0024] S102. The dynamic monitoring frequency is obtained based on time, regional key factors, and processed signals, including: B1: Determine if the industrial park has processed signal 1 within the previous n minutes of the current time; if yes, set the dynamic monitoring frequency of each monitoring point to the minimum value of the standard frequency range; if no, proceed to B2; where n is manually set, generally 300; the maximum and minimum values ​​of the standard frequency range are set according to the degree of danger of the industrial park, the higher the degree of danger of the industrial park, the smaller the maximum and minimum values; B2: Extract the current working and non-working hours set for the industrial park from the park's data repository, and obtain the number of emergency events during working hours (C1) and the number of emergency events during non-working hours (C2) in the current industrial park within the previous m days; where m is manually set, typically 180 days; emergency events include equipment overheating, fire, and smoke. B3: Extract the area where each monitoring point is located, extract the regional importance factor QZ of the current monitoring point from the park data repository according to the area, and determine the dynamic monitoring frequency DPi of the current monitoring point during working hours by calculation formula (1); where i is 1, it represents the relevant data during working hours, including the dynamic monitoring frequency DP1 and the number of emergency events C1; i is 2, it represents the relevant data during non-working hours, including the dynamic monitoring frequency DP2 and the number of emergency events C2. The calculation formula (1) is: ; In the formula, BP is the median value of the standard frequency range, which is generally taken as 20 seconds / time; BC is the standard number of emergency events, which is obtained based on the number of emergency events in the previous m days of industrial parks of the same type as the current industrial park; ZD is the maximum value of the standard frequency range, and ZX is the minimum value of the standard frequency range. To find the maximum value function, This is a function that takes the minimum value.

[0025] It is worth noting that the dynamic monitoring frequency set by this invention can optimize the utilization of monitoring resources and significantly improve response efficiency while ensuring monitoring security. Traditional fixed-frequency monitoring has two shortcomings: first, it generates a large amount of redundant data during periods of low risk and stable environment, consuming resources such as storage, computing, and network bandwidth; second, during periods of high risk or frequent abnormal events, insufficient frequency may lead to monitoring lag and delay in response. By setting a dynamic monitoring frequency, the system can comprehensively assess the current risk level by combining time factors, regional importance factors, historical emergency event data, and real-time signal processing status, thereby intelligently adjusting the data acquisition cycle of different monitoring points. For example, if signal 1 has been processed within the past n minutes, the system automatically switches to the minimum value of the standard frequency range to achieve extremely high-frequency monitoring and ensure fine-grained data capture under abnormal conditions; while in cases without emergency signals and with low historical event frequency, the monitoring frequency can be appropriately extended, thereby saving power consumption, reducing network pressure, and reducing maintenance burden.

[0026] Furthermore, introducing regional importance factors allows for more spatially differentiated adjustments to monitoring frequencies. Specifically, monitoring points in flammable and explosive areas or key production processes will be assigned higher dynamic monitoring frequencies under the same time and event conditions to reflect their higher safety management priority; while relatively safe areas can use lower frequencies, forming a differentiated and refined global monitoring strategy. The nested "minimum-maximum" structure of calculation formula (1) further ensures the rationality of the monitoring frequency boundary, ensuring that it neither exceeds the system's maximum monitoring capacity due to excessive risk nor falls below the minimum safe frequency due to excessively low risk, thereby maintaining the stability and safety of the monitoring system.

[0027] Overall, the introduction of dynamic monitoring frequency transforms the system from "static passive perception" to "dynamic intelligent perception." This not only enables rapid capture and response to abnormal states in terms of security protection, but also effectively reduces overall operating costs and equipment load, extends the lifespan of sensors and camera equipment, improves the real-time performance and accuracy of data analysis and decision-making, and achieves the dual goals of risk control and resource conservation.

[0028] It should be noted that the working and non-working hours set for the current industrial park are the overall working and non-working hours of the industrial park; for example: the working hours for A1 category employees are 7:00-14:00 on weekdays, the working hours for A2 category employees are 10:00-18:00 on weekdays, and the working hours for A3 category employees are 18:00-0:00 on weekdays; then the current working hours set for the industrial park are 7:00-0:00 on weekdays, and the non-working hours are 0:00-7:00 on weekdays.

[0029] It should be noted that the regional importance factor is set based on the importance of the region, and the regional importance factor is inversely proportional to the regional importance factor. For example, the importance of a high-risk region is level one, and the regional importance factor is 0.6; the importance of a dangerous region is level two, and the regional importance factor is 0.8; the importance of a general region is level three, and the regional importance factor is 1.

[0030] In one possible implementation of this application embodiment, the above-mentioned S2 can be implemented by the following S201, which will be described in detail below: S201. Based on fire area, smoke concentration, and temperature, determine the processed signals of monitoring points, including: D1: Sequentially extract the fire area HM of the monitoring points. When the fire area HM of the monitoring point is greater than 0, set the processing signal of the current monitoring point to signal one; when the fire area HM is not greater than 0, jump to D2. D2: Sequentially extract the smoke concentration YN and temperature WD of the monitoring point. When the smoke concentration YN is greater than the standard smoke threshold BYN, determine the reference factor CZ of the monitoring point based on the calculation formula (2). When the reference factor CZ is greater than the factor threshold, set the processing signal of the current monitoring point as signal one. When the reference factor CZ is not greater than the factor threshold, set the processing signal of the current monitoring point as signal two. The standard smoke threshold BYN and the factor threshold are both set based on experience. The processing signals include signal one and signal two. The calculation formula (2) is: ; In the formula, BW is the average historical temperature of the current monitoring point; and It is a proportional adjustment coefficient set based on experience, and , .

[0031] It is worth noting that this invention improves the accuracy, stability, and practicality of signal processing judgment through multi-dimensional fusion analysis of fire area, smoke concentration, and temperature, thereby achieving a more precise and scientific response strategy in monitoring fires or abnormal smoke in industrial parks. First, this invention does not simply rely on a single indicator to trigger the processing signal, but processes it according to a hierarchical judgment logic that prioritizes fire area and combines smoke concentration and temperature. When the fire area HM is greater than 0, it can be quickly identified as signal one, i.e., a high-priority emergency signal, so that an emergency response can be initiated without delay in the event of a real fire, ensuring that prevention and evacuation measures are taken as soon as possible. If no abnormality is detected in the fire area, the next step of subdivision analysis is entered by comparing the smoke concentration YN with the standard threshold BYN. At this time, the calculation of the reference factor CZ is introduced to link the nonlinear change characteristics of smoke concentration with the dynamic change of temperature. In the calculation formula (2) Through exponential transformation, the extent to which smoke concentration exceeds the standard threshold can be amplified, while suppressing growth fluctuations at extremely high concentrations, avoiding over-amplification of outliers and reducing misjudgments. By comparing the temperature with historical averages, an S-shaped nonlinear function is used to smooth the transition of temperature effects, making the improvement in the reference factor more significant at higher temperatures. This aligns closely with practical experience, as truly dangerous smoke is often accompanied by a significant temperature rise, effectively distinguishing between transient and non-fire-related smoke interference. , The setting of the proportional adjustment coefficient ensures that smoke factors dominate the overall judgment, while temperature serves as an important auxiliary factor, thus forming a weighted assessment model that better meets actual safety requirements. The greatest advantage of this method is that, on the one hand, it significantly reduces false alarms caused by a single abnormal smoke concentration, avoiding unnecessary large-scale evacuations and production interruptions, and minimizing economic losses and panic; on the other hand, it can still stably and rapidly generate a signal in the event of a real fire or high risk, ensuring the safety of personnel and equipment in the park. This invention provides an intelligent judgment framework that balances "rapid response" and "false alarm control" for signal generation, possessing significant practical value and potential for continuous optimization in actual park safety management.

[0032] It should be noted that, When YN is greater than BYN, it is a non-linear curve that rises in value, and the growth rate decreases as the value of YN-BYN increases.

[0033] It should be noted that, Through The transformed result is a nonlinear function with values ​​ranging from 0 to 1, and its value varies with... It increases as it increases.

[0034] It should be noted that this invention primarily focuses on planning the safe evacuation of people after a fire or abnormal smoke in an industrial park. Therefore, before calculating the reference factor in step D2, only the fire area HM and smoke concentration YN were determined, without considering temperature WD. Although temperature WD was not determined, it was incorporated into the subsequent calculation of the reference factor CZ. This is because abnormally high temperatures are required to produce smoke. If smoke is not accompanied by a rise in temperature, it may dissipate on its own, minimizing the harm to the industrial park and its workers. In such cases, it is not advisable to guide a large-scale evacuation to avoid panic. Therefore, from a practical perspective, this invention, by incorporating temperature analysis, can more accurately calculate the reference factor CZ used to issue processing signals.

[0035] It should be noted that, and It is a proportional adjustment coefficient set based on experience. Because: The multiplier is the relevant data for smoke concentration YN, and The multiplier is the temperature WD data; since temperature is only used as an auxiliary data to correct the reference factor CZ in the calculation of the reference factor CZ, the main calculation of the reference factor CZ is still based on the smoke concentration YN. Therefore, the proportional adjustment coefficient set for the smoke concentration YN data in this invention is greater than the proportional adjustment coefficient for the temperature WD data.

[0036] In one possible implementation of this application embodiment, the above-mentioned S3 can be implemented by the following S301, S302, S303 and S304, which are described in detail below: S301. Determine the smoke diffusion path of the monitoring point based on the target data, including: Extract 3D models of industrial park buildings and equipment information of each piece of equipment from the park's data repository; the equipment information includes the appearance features and physical characteristics of the equipment. Equipment models are constructed based on the equipment information of each device, and simulation models are constructed based on the 3D model of the plant. The equipment models and simulation models are combined to generate a diffusion analysis model. The target data from each monitoring point is input into the diffusion analysis model to obtain the smoke diffusion path at each monitoring point.

[0037] It should be noted that the appearance features of the equipment include its size and shape, while the physical features include the material of the equipment and the thickness of the fireproof coating.

[0038] It should be noted that in planning the smoke diffusion path, the wind direction can also be used as the diffusion direction of the smoke. The diffusion length of the smoke is obtained by multiplying the wind force by the blowing coefficient. In the diffusion direction, the grids that are less than the diffusion length from the monitoring point are used as diffusion grids, and the diffusion grids are combined into the smoke diffusion path. The blowing coefficient is obtained based on the smoke concentration. The higher the smoke concentration, the smaller the blowing coefficient.

[0039] It should be noted that the diffusion analysis model can be pre-built or built in real time. When pre-built, upon receiving signal one, the target data is input into the three-dimensional digital twin model of the current industrial park to obtain the smoke diffusion path. When built in real time, upon receiving signal one, the diffusion analysis model is first built, and then the target data is input into the three-dimensional digital twin model of the current industrial park to obtain the smoke diffusion path.

[0040] like Figure 2 As shown in S302, the blocking factor of each grid for each worker is determined based on the smoke diffusion path and obstructions, including: E1: Divide the industrial park into several grids according to the standard area, and determine in turn whether there are any obstructions in the grids; if yes, set the blocking factor DZ of the grid to infinity; if no, jump to E2; where the standard area is manually set, it is generally set to 1 square meter. E2: Determine whether the grid is not in the smoke diffusion path of any monitoring point; if yes, mark the blocking factor DZ of the grid as 0; if no, extract the personnel positions sequentially, and determine the walking time ZC1 of the corresponding worker from the personnel position to the grid according to the standard speed; extract the position of the corresponding monitoring point, and obtain the distance between the grid and the corresponding monitoring point position. Based on the current wind speed and distance at the monitoring point Determine the duration ZC2 of smoke diffusion from the corresponding monitoring point to the grid; subtract ZC2 from the duration ZC1 to obtain the duration deviation value, and add the duration deviation value to the current time to obtain the smoke impact time point of the corresponding monitoring point affecting the current grid; if the smoke impact time point is not after the current time, extract the smoke concentration of the monitoring point at the smoke impact time point. If the time point of smoke impact is after the current time, the smoke concentration at the monitoring point at the time point of smoke impact is determined based on formula (3). , and jump to E3; where j is the number of the monitoring point corresponding to the smoke diffusion path of the grid, and the value range of j is [1, r], and r is the maximum value of the corresponding monitoring point number; the standard speed is the average speed of workers walking quickly in the current industrial park; E3: Extract the smoke concentration at the corresponding monitoring point at the time of smoke impact. The blocking factor DZ of the grid is determined by calculation formula (4); The calculation formula (3) is: ; In the formula, CPZ is the duration deviation value obtained by subtracting duration ZC2 from duration ZC1; This represents the smoke concentration change between the p nearest time points to the current time and the previous time point from the start time of the smoke at the current monitoring point; e is the number of each time point, and the value of e ranges from [1, p], where p is the maximum value of each time point number; The calculation formula (4) is: ; In the formula, The smoke accumulation impact coefficient, representing the effect of smoke concentration generated at monitoring point j on smoke accumulation in the grid, is obtained based on the changes in smoke concentration at monitoring point j in the smoke generated this time at various times prior to the current time. The value of is [1, 10]; BYN is the standard smoke concentration that affects the breathing of workers; This is determined based on the smoke concentration at monitoring point j at the current time; The wind speed recorded at the current time is the wind speed at monitoring point j; BFS is the standard wind speed set manually, which can be 2 m / s.

[0041] It is worth noting that this invention, by introducing a dynamic calculation mechanism for the blocking factor, integrates multi-source information such as the spatial division of the industrial park, obstacle distribution, smoke diffusion paths, wind field influence, personnel location, and smoke concentration changes, thereby providing accurate and real-time risk assessment basis for safe escape route planning. First, gridding can refine the entire park to a resolution of 1 square meter, providing sufficiently fine granularity in determining safe passage areas and effectively reflecting local environmental differences. When a grid cell contains an obstacle, its blocking factor DZ is set to infinity, essentially determining that the area is impassable, thus ensuring that physically impassable areas are never mistakenly selected when generating escape routes. Second, for grid cells without any obstacles or smoke diffusion paths, DZ is marked as 0, ensuring that no artificial increase in escape resistance occurs within safe areas. This dynamic differentiation avoids a "one-size-fits-all" approach to safe zone division, improving the flexibility of route planning. When a grid is located in the smoke diffusion path, the system will combine the difference between the arrival time of personnel and the arrival time of smoke to predict the smoke concentration at the corresponding moment. If the smoke has not yet arrived, the future concentration will be predicted using equation (3) to ensure that the escape route can avoid areas that will be threatened by smoke in advance, even if it is used for movement in the short term. Next, by using the multi-monitoring point weighted cumulative effect of equation (4), the superposition effect of smoke from different sources on the same grid can be comprehensively considered, and by... The strength of the cumulative effect of parameter adjustment significantly increases the blocking factor of grids affected by smoke over extended periods, thereby raising the priority of escape routes avoiding this area. Simultaneously, factors such as wind speed, distance, and the ratio of smoke concentration to standard smoke concentration introduced into the formula ensure that the blocking factor DZ is not a static value but dynamically adapts to changes in wind speed, smoke diffusion boundary advancement, and concentration, thus reflecting real-time trends in environmental risk. This adaptively changing blocking factor allows route planning to accurately assess passage difficulty within seconds, preventing escape routes from failing due to environmental degradation.

[0042] Overall, the advantages of this invention are: first, it integrates physical obstacles and gas hazards into a unified assessment system; second, the blocking factor design can be dynamically adjusted according to changes in spatial location, time process, and environmental conditions; and third, it can predict the safety of a grid even in the future, thus providing forward-looking protection for escape planning. This significantly improves the accuracy, timeliness, and feasibility of emergency route planning, minimizes the time personnel are exposed to harmful fumes, and reduces the safety risks caused by delays due to route changes.

[0043] It should be noted that the industrial park is planned into several grids according to the standard area, which is based on the ground; the ground includes roads, stair surfaces, floor surfaces of each floor, and other areas that workers can pass through.

[0044] It should be noted that if a grid is located within the smoke diffusion path of a monitoring point, it may be located within the smoke diffusion paths of multiple monitoring points. Therefore, the distance between the grid and the monitoring points corresponding to the smoke diffusion paths varies. There may be multiple.

[0045] It should be noted that the specific steps for determining the walking time ZC1 of the corresponding worker from the personnel position to the grid according to the standard speed are as follows: Obtain the shortest path between the personnel location and the grid, and identify whether there is a monitoring point with a processing signal of signal one within the standard range of each grid in the shortest path; if yes, mark the grid as impassable, and re-obtain the shortest path between the personnel location and the grid until there is no monitoring point with a processing signal of signal one within the standard range of each grid in the obtained shortest path, then stop the operation; otherwise, do not perform any operation; wherein, the standard range is obtained based on the smoke concentration of the monitoring point closest to the grid that has a processing signal of signal one, and the standard range is proportional to the smoke concentration; The walking time ZC1 from the worker's location to the grid is obtained by dividing the length of the shortest path by the standard speed.

[0046] It should be noted that the distance between the grid and the corresponding monitoring point is obtained. Based on the current wind speed and distance at the monitoring point The specific steps for determining the time ZC2 for smoke to diffuse from the corresponding monitoring point to the grid are as follows: Obtain the distance of smoke diffusion between the grid and the corresponding monitoring point location. The distance the smoke spreads Divide by the wind speed to obtain the time ZC2 for the smoke to spread from the corresponding monitoring point to the grid; where, the distance of smoke spread is... It is obtained based on the smoke diffusion path between the monitoring point and the grid.

[0047] It should be noted that the duration deviation value obtained by subtracting duration ZC2 from duration ZC1 can be positive, negative, or zero. Therefore, the time point of smoke impact may be before or after the current time. For ease of understanding later, the standard walking speed of the staff is set to the same value as the wind speed at the current monitoring point. When the duration deviation is positive, it indicates that duration ZC1 is greater than duration ZC2. If the standard speed and wind speed are the same, it proves that at the current time, the distance between the worker and the grid is greater than the distance between the monitoring point and the grid. When the worker reaches the grid, the smoke that affects the grid is generated when the worker runs to a position where the distance between the worker and the grid is distance two. Therefore, the time point when the worker runs to a position where the distance between the worker and the grid is distance two is marked as the smoke impact time point. Thus, the smoke impact time point is located after the current time. The smoke impact time point is the current time plus the duration deviation value, and the duration deviation value is positive at this time. When the duration deviation is zero, it means that duration ZC1 is equal to duration ZC2. If the standard speed and wind speed are the same, it proves that at the current time, the distance between the worker and the grid is equal to the distance between the monitoring point and the grid. Therefore, the smoke generated at the current time arrives at the grid at the same time as the worker. Thus, the time point of smoke impact is the current time. The time point of smoke impact is the current time plus the duration deviation value, and the duration deviation value is zero at this time. When the duration deviation value is negative, it indicates that duration ZC1 is less than duration ZC2. If the standard speed and wind speed are the same, it proves that at the current time, the distance between the worker and the grid is less than the distance between the monitoring point and the grid. Therefore, when the worker arrives at the grid, the smoke affecting the grid was generated before the current time and arrived at the grid position at the same time as the worker. Therefore, the time point of smoke impact is before the current time. The time point of smoke impact is the current time plus the duration deviation value, and the duration deviation value is negative at this time.

[0048] S303. Determine the traffic coefficients for each route between personnel locations and park exits based on blocking factors, including: Grids located within the standard range of monitoring points with processed signals of signal one, or grids with blocking factors greater than the standard blocking factor, are marked as impassable grids. The standard range is determined based on the smoke concentration of the nearest monitoring point with processed signals of signal one, and the standard range is proportional to the smoke concentration. The standard blocking factor is determined based on experiments on the blocking factor and safe passage for personnel. Obtain the grid data for each route from the personnel's location to the park exit, and sum the blocking factors corresponding to the grid data for each route to obtain the passage coefficient.

[0049] S304. Based on traffic flow coefficients, select the optimal route for staff evacuation, including: Extract the traffic coefficient of each route, sort the routes according to the traffic coefficient from small to large, mark the number of the route with the shortest route as the target number, mark the route corresponding to the target number and the route corresponding to the smaller target number as the expected route, and determine the suitability factor YZ of each expected route by calculation formula (5), mark the expected route with the smallest suitability factor YZ as the optimal route; guide the staff to escape the industrial park according to the optimal route by wearing a safety helmet; The calculation formula (5) is: ; In the formula, TL is the expected passage coefficient of the line, PTL is the average of the passage coefficients of each expected line, LC is the line length of the expected line, and PLC is the average of the line lengths of each expected line. and A proportional adjustment coefficient set to balance safety and speed, and .

[0050] It should be noted that, and This is a proportional adjustment coefficient set to balance safety and speed; if safety is the primary consideration, then... If the priority is escape speed, then .

[0051] The above primarily describes the solutions of the embodiments of this application from the perspective of device implementation. It is understood that each device, such as a big data-based industrial park management device, includes at least one of the hardware structures and software modules corresponding to the execution of each function in order to achieve the above-mentioned functions. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0052] This application embodiment can divide a big data-based industrial park management device into functional units based on the above method example. For example, each function can be divided into separate functional units, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0053] When using integrated units, Figure 3 The diagram shows a possible structure of an industrial park management device (referred to as communication device 30) based on big data involved in the above embodiments. The communication device 30 includes a processing unit 301 and a communication unit 302, and may also include a storage unit 303. Figure 3 The structural diagram shown can be used to illustrate the structure of an industrial park management device based on big data involved in the above embodiments.

[0054] when Figure 3 The schematic diagram shown illustrates the structure of an industrial park management device based on big data involved in the above embodiments. The processing unit 301 is used to control and manage the operation of the industrial park management device based on big data. The communication unit 302 is used for the industrial park management device based on big data to communicate with other devices. The storage medium (referred to as storage unit 303) is used to store the program code and data of the industrial park management device based on big data.

[0055] For example, communication unit 302 is used to acquire target data and personnel locations at various monitoring points in the industrial park; wherein, the target data includes the fire area, smoke concentration, temperature, wind speed and wind direction at the monitoring points; Processing unit 301 is used to determine the processing signal of the monitoring point based on the fire area, smoke concentration and temperature; When the processing signal is signal one, the smoke diffusion path of the monitoring point is determined based on the target data; the blocking factor of each grid for each worker is determined according to the smoke diffusion path and the obstruction; the passage coefficient of each route between the personnel location and the park exit is determined based on the blocking factor; and the optimal route is selected to arrange the workers to escape based on the passage coefficient; among them, the obstruction includes walls, insurmountable equipment and fences. No operation is performed when all processed signals are signal two.

[0056] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0057] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely illustrative descriptions of the application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

[0058] Some of the data in the above calculation formula are obtained by removing dimensions and taking their numerical values. The calculation formula is the closest to the real situation obtained by software simulation of a large amount of collected data. The preset parameters and preset thresholds in the calculation formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

Claims

1. A big data-based industrial park management method, characterized in that, include: Acquire target data and personnel locations at various monitoring points in the industrial park; the target data includes the fire area, smoke concentration, temperature, wind speed, and wind direction at each monitoring point. The processing signal for monitoring points is determined based on the fire area, smoke concentration, and temperature. When the processing signal is signal one, the smoke diffusion path of the monitoring point is determined based on the target data; the blocking factor of each grid for each worker is determined according to the smoke diffusion path and the obstruction; the passage coefficient of each route between the personnel location and the park exit is determined based on the blocking factor; and the optimal route is selected to arrange the workers to escape based on the passage coefficient; among them, the obstruction includes walls, insurmountable equipment and fences. No operation is performed when all processed signals are signal two.

2. The industrial park management method based on big data according to claim 1, characterized in that, The acquisition of target data and personnel locations at various monitoring points in the industrial park includes: The system uses personnel positioning devices to obtain the real-time location of staff, surveillance cameras to obtain video from each monitoring point, and video recognition to obtain the fire area at each monitoring point. Based on the dynamic monitoring frequency, the system uses smoke concentration sensors to obtain the smoke concentration at each monitoring point, temperature sensors to obtain the temperature at each monitoring point, and wind speed and direction at each monitoring point to obtain the wind speed and direction at each monitoring point. The dynamic monitoring frequency is obtained based on time, regional importance factors, and processed signals.

3. The industrial park management method based on big data according to claim 2, characterized in that, The dynamic monitoring frequency is obtained based on time, regional importance factors, and processed signals, including: B1: Determine whether the industrial park has processed signal 1 within the previous n minutes of the current time; if yes, set the dynamic monitoring frequency of each monitoring point to the minimum value of the standard frequency range; if no, jump to B2; where the maximum and minimum values ​​of the standard frequency range are set according to the degree of danger of the industrial park. B2: Extract the current working and non-working hours set for the industrial park from the park's data repository, and obtain the number of emergency events during working hours (C1) and the number of emergency events during non-working hours (C2) in the industrial park within the previous m days; among which, emergency events include equipment overheating, fire, and smoke. B3: Extract the area where each monitoring point is located, extract the regional importance factor QZ of the current monitoring point from the park data repository according to the area, and determine the dynamic monitoring frequency DPi of the current monitoring point during working hours by calculation formula (1); where i is 1, it represents the relevant data during working hours, including the dynamic monitoring frequency DP1 and the number of emergency events C1; i is 2, it represents the relevant data during non-working hours, including the dynamic monitoring frequency DP2 and the number of emergency events C2. The calculation formula (1) is: ； In the formula, BP is the median value of the standard frequency range; BC is the standard number of emergency events, which is obtained based on the number of emergency events in the previous m days of industrial parks of the same type as the current industrial park; ZD is the maximum value of the standard frequency range, and ZX is the minimum value of the standard frequency range. To find the maximum value function, This is a function that takes the minimum value.

4. The industrial park management method based on big data according to claim 1, characterized in that, The processed signals used to determine the monitoring points based on fire area, smoke concentration, and temperature include: D1: Sequentially extract the fire area HM of the monitoring points. When the fire area HM of the monitoring point is greater than 0, set the processing signal of the current monitoring point to signal one; when the fire area HM is not greater than 0, jump to D2. D2: Sequentially extract the smoke concentration YN and temperature WD of the monitoring point. When the smoke concentration YN is greater than the standard smoke threshold BYN, determine the reference factor CZ of the monitoring point based on the calculation formula (2). When the reference factor CZ is greater than the factor threshold, set the processing signal of the current monitoring point as signal one. When the reference factor CZ is not greater than the factor threshold, set the processing signal of the current monitoring point as signal two. The processing signal includes signal one and signal two. The calculation formula (2) is: ； In the formula, BW is the average historical temperature of the current monitoring point; and It is a proportional adjustment coefficient, and , .

5. The industrial park management method based on big data according to claim 1, characterized in that, The process of determining the smoke diffusion path at monitoring points based on target data includes: Extract 3D models of industrial park buildings and equipment information of each piece of equipment from the park's data repository; the equipment information includes the appearance features and physical characteristics of the equipment. Equipment models are constructed based on the equipment information of each device, and simulation models are constructed based on the 3D model of the plant. The equipment models and simulation models are combined to generate a diffusion analysis model. The target data from each monitoring point is input into the diffusion analysis model to obtain the smoke diffusion path at each monitoring point.

6. The industrial park management method based on big data according to claim 1, characterized in that, The process of determining the blocking factor of each grid for each worker based on the smoke diffusion path and obstructions includes: E1: Divide the industrial park into several grids according to the standard area, and determine in turn whether there are any obstructions in the grids; if yes, set the blocking factor DZ of the grid to infinity; if no, jump to E2; E2: Determine whether the grid is not in the smoke diffusion path of any monitoring point; if yes, mark the blocking factor DZ of the grid as 0; if no, extract the personnel positions sequentially, and determine the walking time ZC1 of the corresponding worker from the personnel position to the grid according to the standard speed; extract the position of the corresponding monitoring point, and obtain the distance between the grid and the corresponding monitoring point position. Based on the current wind speed and distance at the monitoring point Determine the duration ZC2 of smoke diffusion from the corresponding monitoring point to the grid; subtract ZC2 from the duration ZC1 to obtain the duration deviation value, and add the duration deviation value to the current time to obtain the smoke impact time point of the corresponding monitoring point affecting the current grid; if the smoke impact time point is not after the current time, extract the smoke concentration of the monitoring point at the smoke impact time point. If the time point of smoke impact is after the current time, the smoke concentration at the monitoring point at the time point of smoke impact is determined based on formula (3). , and jump to E3; where j is the number of the monitoring point corresponding to the smoke diffusion path of the grid, and the value range of j is [1, r], and r is the maximum value of the corresponding monitoring point number; the standard speed is the average speed of workers walking quickly in the current industrial park; E3: Extract the smoke concentration at the corresponding monitoring point at the time of smoke impact. The blocking factor DZ of the grid is determined by calculation formula (4); The calculation formula (3) is: ； In the formula, CPZ is the duration deviation value obtained by subtracting duration ZC2 from duration ZC1; This represents the smoke concentration change between the p nearest time points to the current time and the previous time point from the start time of the smoke at the current monitoring point; e is the number of each time point, and the value of e ranges from [1, p], where p is the maximum value of each time point number; The calculation formula (4) is: ； In the formula, Let be the smoke accumulation impact coefficient, representing the effect of smoke concentration generated at monitoring point j on smoke accumulation in the grid. The value of is [1, 10]; BYN is the standard smoke concentration that affects the breathing of workers; This is determined based on the smoke concentration at monitoring point j at the current time; This represents the wind speed recorded at monitoring point j at the current time.

7. The industrial park management method based on big data according to claim 1, characterized in that, The determination of the traffic coefficients for each route between personnel location and park exit based on the blocking factor includes: Grids located within the standard range of monitoring points where the processed signal is signal one, or grids with a blocking factor greater than the standard blocking factor, are marked as impassable grids. Obtain the grid data for each route from the personnel's location to the park exit, and sum the blocking factors corresponding to the grid data for each route to obtain the passage coefficient.

8. The industrial park management method based on big data according to claim 1, characterized in that, The method of selecting the optimal route for staff evacuation based on traffic coefficients includes: Extract the traffic coefficient of each route, sort the routes according to the traffic coefficient from small to large, mark the number of the route with the shortest route as the target number, mark the route corresponding to the target number and the route corresponding to the smaller target number as the expected route, and determine the suitability factor YZ of each expected route by calculation formula (5), mark the expected route with the smallest suitability factor YZ as the optimal route; guide the staff to escape the industrial park according to the optimal route by wearing a safety helmet; The calculation formula (5) is: ； In the formula, TL is the expected passage coefficient of the line, PTL is the average of the passage coefficients of each expected line, LC is the line length of the expected line, and PLC is the average of the line lengths of each expected line. and A proportional adjustment coefficient set to balance safety and speed, and .

9. A big data-based industrial park management device, used to operate the big data-based industrial park management method according to any one of claims 1 to 8, characterized in that, include: Communication unit and processing unit; The communication unit is used to acquire target data and personnel locations at various monitoring points in the industrial park; the target data includes the fire area, smoke concentration, temperature, wind speed, and wind direction at the monitoring points. The processing unit is used to determine the processing signal of the monitoring point based on the fire area, smoke concentration and temperature. When the processing signal is signal one, the smoke diffusion path of the monitoring point is determined based on the target data; the blocking factor of each grid for each worker is determined according to the smoke diffusion path and the obstruction; the passage coefficient of each route between the personnel location and the park exit is determined based on the blocking factor; and the optimal route is selected to arrange the workers to escape based on the passage coefficient; among them, the obstruction includes walls, insurmountable equipment and fences. No operation is performed when all processed signals are signal two.

10. A storage medium, characterized in that, Used to store computer programs, which, when executed, implement the big data-based industrial park management method according to any one of claims 1 to 8.

Images