Plant gas pollution distribution prediction method and system, electronic device and storage medium

Abstract

The application discloses a kind of factory area gas pollution distribution prediction methods, comprising the following steps: S110 obtains the meteorological data of target area and the position and concentration data of multiple sampling points, establishes static distribution characteristic database, wherein, multiple sampling points include online monitoring point;S130 according to current monitoring state, filter out the most matched static distribution characteristic database;S140 establishes target area concentration control coefficient model, obtains dynamic distribution characteristic database;S150 based on the dynamic distribution characteristic database obtained, using spatial interpolation and visualization means form target area gas pollution distribution chart.The application also discloses a kind of factory area gas pollution distribution prediction system, electronic equipment and storage medium.The application is measured by multiple sampling points to establish static distribution characteristic database, combined with current monitoring state, constructs target area concentration control coefficient model, comprehensively considers two significant influencing factors of factory area meteorology and distance, realizes real-time accurate prediction of factory area level gas pollution distribution.

Description

Technical Field

[0001] This invention relates to the field of gas pollution monitoring technology, and in particular to a method, system, electronic device and storage medium for predicting the distribution of gas pollution in a factory area. Background Technology

[0002] Gaseous pollutants mainly include carbon monoxide (CO), sulfur dioxide (SO2), and nitrogen oxides (NOx). x The emissions of air pollutants include ozone (O3), PM2.5, PM10, and volatile organic compounds (VOCs) and toxic and harmful gases such as hydrogen sulfide and ammonia, which are of concern to petrochemical companies. These emissions pose a threat to the air environment and human health. With the promulgation of standards such as the "Comprehensive Treatment Plan for VOCs in Key Industries" and the "Technical Guidelines for the Construction of Environmental Risk Early Warning Systems for Toxic and Harmful Gases," petrochemical companies have added online monitoring equipment and are gradually building gas pollution monitoring networks to achieve online monitoring of pollutant concentrations at monitoring points. However, there are still no effective means to control pollution in areas where monitoring points are not deployed. For petrochemical companies, how to leverage existing grid-based monitoring network data to further predict the dynamic distribution of pollutants in the plant area is of significant importance for improving their leak monitoring capabilities. However, current pollution distribution prediction methods are mainly applicable to larger-scale areas such as cities and regions, and are not suitable for smaller plant areas with dense production enterprises and equipment.

[0003] The information disclosed in this background section is intended only to enhance the understanding of the overall background of the invention and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0004] One of the objectives of this invention is to provide a method, system, electronic device, and storage medium for predicting the distribution of gaseous pollution in industrial areas, thereby addressing the problem that existing technologies are not suitable for predicting pollution in industrial areas.

[0005] Another objective of this invention is to provide a method, system, electronic device, and storage medium for predicting the distribution of gas pollution in a factory area, thereby improving the accuracy of predicting the distribution of gas pollution in a factory area.

[0006] To achieve the above objectives, according to a first aspect of the present invention, the present invention provides a method for predicting the distribution of gaseous pollution in a factory area, comprising the steps of:

[0007] S110 acquires meteorological data of the target area and location and concentration data of multiple sampling points to establish a static distribution characteristic database, including multiple sampling points including online monitoring points;

[0008] S130 selects the most matching static distribution feature database based on the current monitoring status;

[0009] S140 establishes a concentration regulation coefficient model for the target area and obtains a dynamic distribution characteristic database;

[0010] Based on the obtained dynamic distribution feature database, S150 uses spatial interpolation and visualization methods to generate a gas pollution distribution map of the target area.

[0011] Furthermore, in the above technical solution, steps S130 to S150 are repeated at a set frequency to form a dynamically updated target area gas pollution distribution map.

[0012] Furthermore, in the above technical solution, multiple sampling points evenly cover the target area.

[0013] Furthermore, in the above technical solution, the current monitoring status includes the average wind direction, average wind speed, and average pollution concentration at a height of 10 meters upwind of the target area within a set time period.

[0014] Furthermore, in the above technical solution, the time period is set to the previous 1 to 6 hours. Furthermore, in the above technical solution, the average wind direction and average wind speed are calculated using the vector averaging method; the average pollution concentration is calculated using the arithmetic average method.

[0015] Furthermore, in the above technical solution, when the target area is closed or semi-closed, with flat terrain and few buildings obstructing the view, the static distribution feature database is a set of the coordinates of the sampling points and the concentration of the sampling points.

[0016] Furthermore, in the above technical solution, the steps for establishing a static distribution feature database include:

[0017] Based on the location and concentration data of multiple sampling points, a pollution distribution database for the target area is formed using spatial interpolation.

[0018] The target area is divided into a well-shaped grid, and the feature points are formed by combining the grid points and the online monitoring points.

[0019] Based on the pollution distribution database, the pollution concentration at each feature point is obtained, and a static distribution feature database static_net{x is established. s ,y s ,c s}, where x s y s c represents the coordinates of the feature point. s The pollution concentration at the characteristic point.

[0020] Furthermore, in the above technical solution, the step of establishing a static distribution feature database also includes:

[0021] Spatial interpolation is performed on the established static distribution feature database to obtain the pollution distribution database, and the similarity between the restored pollution distribution database and the original pollution distribution database is calculated.

[0022] Set similarity thresholds M and N, where 0 < M < N < 1; and

[0023] The validity of the established static distribution feature database is determined based on similarity.

[0024] If M ≤ similarity ≤ N, then the established static distribution feature database is qualified;

[0025] If the similarity is less than M, then increase the grid density, re-divide the well-shaped grid, and establish a static distribution feature database; and

[0026] If the similarity is greater than N, then reduce the grid density, re-divide the grid into well-shaped grids, and establish a static distribution feature database.

[0027] Furthermore, in the above technical solution, the similarity thresholds are 0.7≤M≤0.75 and 0.8≤N≤0.85.

[0028] Furthermore, in the above technical solution, the meteorological data of the target area are the wind speed and wind direction at a height of 10 meters upwind of the target area, the average value of the meteorological data within the sampling period is the sampling meteorological conditions, and the sampling period is the time when all sampling points complete sampling.

[0029] Furthermore, in the above technical solution, multiple static distribution feature databases are established based on different sampling meteorological conditions. The current monitoring status is compared with the sampling meteorological conditions to select the most matching static distribution feature database, including:

[0030] The wind direction screening step involves calculating the wind direction difference (EW) between the average wind direction in the current monitoring state and the sampling meteorological conditions from multiple static distribution feature databases, and then screening for the minimum value, min_EW.

[0031] If there is only one static distribution feature database with EW≤(min_EW+W), then the static distribution feature database corresponding to the minimum wind direction difference value min_EW is determined as the best matching static distribution feature database, where W is a set angle value and W≤15°;

[0032] Otherwise, proceed to the wind speed screening step, calculate the wind speed difference ES between the average wind speed in the current monitoring state and the sampling meteorological conditions of multiple static distribution feature databases, and screen the minimum value min_ES. The static distribution feature database corresponding to the minimum wind speed difference min_ES is determined as the best matching static distribution feature database.

[0033] Furthermore, in the above technical solution, step S140 includes:

[0034] S141 Establish the concentration control coefficient model k for the i-th online monitoring point. i (x s ,y s ), k i The coordinates (x) of the i-th online monitoring point i y i The average wind direction θ and average wind speed s, and the pollution change intensity p, are currently being monitored. i Related, p i =c i / c i0 , where c i Let c be the average pollution concentration at the i-th online monitoring point in the current monitoring state. i0 The pollution concentration of the feature point corresponding to the i-th online monitoring point in the best-matching static distribution feature database;

[0035] S142 establishes a concentration regulation coefficient model for the target region:

[0036] Where N is the total number of online monitoring points;

[0037] S143 obtains the dynamic distribution feature database dynamic_net(x) s ,y s ,c d ), where c d =c s ·K(x s ,y s ).

[0038] Furthermore, in the above technical solution, the concentration control coefficient model k for the i-th online monitoring point... i (x s ,y s It conforms to the attenuation law of gas diffusion and satisfies:

[0039] When p i When k < 1, i ∈[p i ,1), when p i When k > 1, i ∈(1,p i ], when p i When k = 1, i =1;

[0040] When D i When k = 0, i =p i That is, there is no decay; when D iWhen =D0, k i =1, meaning complete decay; when D i When ∈(0,D0), as D i As k increases i Gradually changing from pollution intensity p i The decay is reduced to 1, where D0 is the distance to complete decay.

[0041]

[0042] Where d is the feature point (x s ,y s ) to the i-th online monitoring point (x i ,y i The distance, θ i The average wind direction θ and (x) in the current monitoring status s ,y s ) and (x i ,y i The acute angle between two points is the angle between the line segments; m represents a coefficient related to wind speed, 1≤m≤5, and the larger the average wind speed s in the current monitoring state, the larger m is.

[0043] Furthermore, in the above technical solution, D0 is related to the area size of the target region and the number of online monitoring points, and D0 is 100-500m.

[0044] Furthermore, in the above technical solution, if 0m / s≤s<1m / s, m=1; if 1m / s≤s<3m / s, m=2; if 3m / s≤s<5m / s, m=3; if 5m / s≤s<7m / s, m=4; if s≥7m / s, m=5.

[0045] According to a second aspect of the present invention, the present invention provides a gas pollution distribution prediction system for a factory area, comprising: a data acquisition unit for acquiring meteorological data of a target area and location and concentration data of multiple sampling points; a data processing unit for, based on the data acquired by the data acquisition unit, establishing a static distribution feature database, selecting the most matching static distribution feature database, establishing a concentration control coefficient model for the target area, and obtaining a dynamic distribution feature database; and, based on the obtained dynamic distribution feature database, forming a gas pollution distribution map of the target area using spatial interpolation and visualization methods.

[0046] Furthermore, in the above technical solution, the data acquisition unit includes mobile monitoring equipment and online monitoring stations.

[0047] According to a third aspect of the present invention, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform a plant area gas pollution distribution prediction method as described in any of the above technical solutions.

[0048] According to a fourth aspect of the present invention, the present invention provides a non-transitory computer-readable storage medium storing computer-executable instructions for causing a computer to execute a method for predicting the distribution of gas pollution in a factory area as described in any of the above-described technical solutions.

[0049] Compared with the prior art, the present invention has one or more of the following beneficial effects:

[0050] 1. This invention is applicable to the prediction of gaseous pollution distribution in industrial plants. Industrial plants are typically small in area, with densely packed production facilities and equipment, and wind direction significantly impacts pollution distribution. Emission sources within the plant are complex but their locations are clearly defined, and there are no mobile sources. Therefore, the pollution situation at the plant level is complex and variable, but the distribution characteristics are similar under the same meteorological conditions. This invention establishes a static distribution characteristic database through field measurements at multiple sampling points. It can also combine data from existing equipment such as online monitoring points and weather stations to select the most suitable static distribution characteristic database and construct a concentration control coefficient model for the target area. By comprehensively considering the two significant influencing factors of meteorology and distance within the plant area, it achieves real-time and accurate prediction of gaseous pollution distribution at the plant level.

[0051] 2. By setting the frequency as needed, the distribution of gaseous pollutants in the target area can be dynamically updated, which is beneficial for comprehensively displaying the pollution distribution level of enterprises and thus improving their pollution control level. It also facilitates the identification of heavily polluted areas, providing data support for refined pollution control and treatment.

[0052] 3. This invention can extract a static distribution feature database by dividing the grid, and the dynamic distribution feature database obtained by concentration control can more accurately reflect the actual pollution distribution.

[0053] 4. This invention can make full use of existing online monitoring resources in the plant area, such as online monitoring stations and weather stations. When establishing a static distribution characteristic database, only portable or mobile monitoring equipment is needed to sample multiple sampling points sequentially. The total number of monitoring devices is small, and the investment and maintenance costs are low, which is conducive to promotion and application in petrochemical enterprises.

[0054] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, and to make the above and other objects, technical features and advantages of the present invention easier to understand, one or more preferred embodiments are listed below and described in detail with reference to the accompanying drawings. Attached Figure Description

[0055] Figure 1 This is a flowchart of a method for predicting the distribution of gaseous pollution in a factory area according to an embodiment of the present invention.

[0056] Figure 2 k is according to one embodiment of the present invention i The decay curve, where p i >1.

[0057] Figure 3 k is according to one embodiment of the present invention i The decay curve, where p i <1.

[0058] Figure 4 This is a schematic diagram of the hardware structure of an electronic device for performing a method for predicting the distribution of gas pollution in a factory area according to an embodiment of the present invention. Detailed Implementation

[0059] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings, but it should be understood that the scope of protection of the present invention is not limited to the specific embodiments.

[0060] Unless otherwise expressly stated, throughout the specification and claims, the term "comprising" or its variations such as "including" or "comprises" shall be understood to include the stated elements or components without excluding other elements or other components.

[0061] In this document, for ease of description, spatial relative terms such as “below,” “under,” “down,” “above,” “above,” “up,” etc., are used to describe the relationship of one element or feature to another element or feature in the accompanying drawings. It should be understood that spatial relative terms are intended to encompass different orientations of an object in use or operation, in addition to those depicted in the figures. For example, if an object in the figure is flipped, an element described as “below” or “under” another element or feature would be oriented “above” that element or feature. Thus, the exemplary term “below” can encompass both the downward and upward orientations. An object may also have other orientations (rotated 90 degrees or other orientations), and the spatial relative terms used herein should be interpreted accordingly.

[0062] In this document, the terms "first," "second," etc., are used to distinguish two different elements or parts, and are not used to define specific positions or relative relationships. In other words, in some embodiments, the terms "first," "second," etc., can also be used interchangeably.

[0063] like Figure 1 As shown, the flow of the plant area gas pollution distribution prediction method according to a specific embodiment of the present invention is as follows:

[0064] S110 acquires meteorological data of the target area and location and concentration data of multiple sampling points to establish a static distribution characteristic database.

[0065] The sampling points include multiple online monitoring points, which can be existing online monitoring stations. These multiple sampling points evenly cover the target area. The location and concentration data of these multiple sampling points can be obtained using portable or mobile monitoring equipment; therefore, a relatively large number of sampling points can be deployed. It should be noted that sampling should be conducted when meteorological conditions are relatively stable, and the meteorological conditions used for sampling can be approximated by the average value over the sampling period.

[0066] Furthermore, in one or more exemplary embodiments of the present invention, the meteorological data for the target area can be the wind speed and direction at a height of 10 meters upwind of the target area. The average value of the meteorological data within the sampling period is the sampling meteorological condition, and the sampling period is the time required for all sampling points to complete the sampling. Therefore, sampling should be completed as quickly as possible when the meteorological conditions are relatively stable. Under different sampling meteorological conditions, data acquisition is completed for multiple sampling points in the target area, and multiple static distribution feature databases are established.

[0067] The establishment of a static distribution feature database can be carried out in different ways depending on the conditions of the factory area. For example, when the target area is closed or semi-closed, with flat terrain and few buildings blocking the view, the set of coordinates and concentrations of the sampling points can be directly used as the static distribution feature database.

[0068] For example, a static distribution feature database can also be established using a gridded approach, with the following steps:

[0069] Based on the location and concentration data of multiple sampling points, a pollution distribution database for the target area is formed using spatial interpolation.

[0070] The target area is divided into a well-shaped grid, and the feature points are formed by combining the grid points and the online monitoring points.

[0071] Based on the pollution distribution database, the pollution concentration at each feature point is obtained, and a static distribution feature database static_net{x is established. s ,y s ,c s}, where x s y s c represents the coordinates of the feature point. s The pollution concentration at the characteristic point.

[0072] Furthermore, to ensure that the grid partitioning reflects the actual distribution characteristics while minimizing data processing time and improving efficiency, and simultaneously reducing limitations on the flexibility of the dynamic distribution feature database, in one or more exemplary embodiments of the present invention, the step of establishing the static distribution feature database may further include a verification process:

[0073] Spatial interpolation is performed on the established static distribution feature database to obtain the pollution distribution database, and the similarity between the restored pollution distribution database and the original pollution distribution database is calculated.

[0074] Set similarity thresholds M and N, where 0 < M < N < 1; and

[0075] The validity of the established static distribution feature database is determined based on similarity.

[0076] If M ≤ similarity ≤ N, then the established static distribution feature database is qualified;

[0077] If the similarity is less than M, then increase the grid density, re-divide the well-shaped grid, and establish a static distribution feature database; and

[0078] If the similarity is greater than N, then reduce the grid density, re-divide the grid into well-shaped grids, and establish a static distribution feature database.

[0079] For example, the similarity threshold is M = 0.75 and N = 0.85. It should be understood that the present invention is not limited thereto. The range of the similarity threshold can be 0.7 ≤ M ≤ 0.75 and 0.8 ≤ N ≤ 0.85.

[0080] Based on the current monitoring status, S130 selects the most matching static distribution feature database.

[0081] The current monitoring status may include the average wind direction, average wind speed, and average pollution concentration at a height of 10 meters upwind of the target area within a set time period. For example, the set time period may be the previous 1 to 6 hours, but this invention is not limited thereto. Further, in one or more exemplary embodiments of this invention, the average wind direction and average wind speed are calculated using a vector average method; the average pollution concentration is calculated using an arithmetic average method.

[0082] By comparing the current monitoring status with the sampling meteorological conditions, the most matching static distribution feature database is selected, including:

[0083] The wind direction screening step involves calculating the wind direction difference (EW) between the average wind direction in the current monitoring state and the sampling meteorological conditions from multiple static distribution feature databases, and then screening for the minimum value, min_EW.

[0084] If there is only one static distribution feature database with EW≤(min_EW+W), then the static distribution feature database corresponding to the minimum wind direction difference value min_EW is determined as the best matching static distribution feature database, where W is a set angle value and W≤15°;

[0085] Otherwise, proceed to the wind speed screening step, calculate the wind speed difference ES between the average wind speed in the current monitoring state and the sampling meteorological conditions of multiple static distribution feature databases, and screen the minimum value min_ES. The static distribution feature database corresponding to the minimum wind speed difference min_ES is determined as the best matching static distribution feature database.

[0086] S140 establishes a concentration regulation coefficient model for the target area and obtains a dynamic distribution characteristic database.

[0087] S141 Establish the concentration control coefficient model k for the i-th online monitoring point. i (x s ,y s ), k i The coordinates (x) of the i-th online monitoring point i y i The average wind direction θ and average wind speed s, and the pollution change intensity p, are currently being monitored. i Related, p i =c i / c s , where c i Let c be the average pollution concentration at the i-th online monitoring point in the current monitoring state. i0 The pollution concentration of the feature point corresponding to the i-th online monitoring point in the best-matching static distribution feature database;

[0088] S142 establishes a concentration regulation coefficient model for the target region:

[0089] Where N is the total number of online monitoring points;

[0090] S143 obtains the dynamic distribution feature database dynamic_net(x) s ,y s ,c d ), where c d =c s ·K(x s ,y s ).

[0091] Furthermore, in one or more exemplary embodiments of the present invention, the concentration control coefficient model k of the i-th online monitoring point... i (x s ,y s It conforms to the attenuation law of gas diffusion and satisfies:

[0092] When p i When k < 1, i ∈[p i ,1), when p i When k > 1, i ∈(1,p i ], when p i When k = 1, i =1;

[0093] When D i When k = 0, i =p i That is, there is no decay when D i When =D0, k i =1, meaning complete decay, when D i When ∈(0,D0), as D i As k increases i Gradually changing from pollution intensity p i Change to 1, where D0 is the distance of complete attenuation.

[0094]

[0095] Where d is the feature point (x s ,y s ) to the i-th online monitoring point (x i ,y i The distance, θ i The average wind direction θ and (x) in the current monitoring status s ,y s ) and (x i ,y i The acute angle between two points is the angle between the line segments; m represents a coefficient related to wind speed, 1≤m≤5, and the larger the average wind speed s in the current monitoring state, the larger m is.

[0096] For example, D0 is related to the area of ​​the target region and the number of online monitoring points, and D0 is generally 100-500m. For example, if 0m / s ≤ s < 1m / s, m ​​= 1; if 1m / s ≤ s < 3m / s, m ​​= 2; if 3m / s ≤ s < 5m / s, m ​​= 3; if 5m / s ≤ s < 7m / s, m ​​= 4; if s ≥ 7m / s, m ​​= 5.

[0097] For example, if the i-th online monitoring point has a meteorological monitoring station, that is, it can monitor and obtain the specific wind direction and wind speed data at that location in real time, then θ is calculated. i The average wind direction θ in the current monitoring state used when calculating coefficient m can preferably be replaced by the average wind direction of the monitoring point; the average wind speed s in the current monitoring state used when calculating coefficient m can preferably be replaced by the average wind speed of the monitoring point. If the height of the meteorological monitoring station at the monitoring point is not 10 meters, the wind speed value at a height of 10 meters can be obtained by converting it according to the formula.

[0098] For example, k can be determined using the following method. i With D i Relationship:

[0099] 1) Configure a point source gas leak, with the gas type being a typical gaseous pollutant in the target area, the leak source height being the emission height of a typical pollutant source in the target area, and the source strength being the normal emission rate of a typical pollutant source; for example, the gas selected is propylene, the leak source height is 10m, and the source strength is 50kg / h;

[0100] 2) Configure meteorological data as the common wind speed at the height of the leak source in the target area; for example, 5 m / s;

[0101] 3) Conduct leak simulations or tests to obtain gas leak diffusion data; with the wind direction as the x-axis and the origin at 2-10m downwind, record the maximum concentration value c on the vertical cross section at each x-position (x≥0);

[0102] 4) Using the maximum value of concentration c as 1000, proportionally reduce all concentrations of c to obtain ck; take the x-value at the position where ck = 1 as D0, and proportionally reduce / enlarge all x-values ​​to obtain D. x ; and establish [D x ,ck] correspond to the relation table f, where D x Equal intervals and D0≥D x ≥0, 1000≥ck≥1, that is, the correspondence table can be represented as ck=f(D x );

[0103] When p i When k > 1, i ∈(1,p i ], then k i With D i The numerical relationship is k i =1+[(p i -1)×f(D i [) / 1000];

[0104] When p i When k < 1, i ∈[p i ,1), then k iWith D i The numerical relationship is k i =1-[(1-p i )×f(D i () / 1000).

[0105] Based on the obtained dynamic distribution feature database, S150 uses spatial interpolation and visualization methods to generate a gas pollution distribution map of the target area.

[0106] Furthermore, in one or more exemplary embodiments of the present invention, steps S130 to S150 are repeated at a set frequency to form a dynamically updated target area gas pollution distribution map.

[0107] According to a specific embodiment of the present invention, a gas pollution distribution prediction system for a factory area includes: a data acquisition unit for acquiring meteorological data of a target area and location and concentration data of multiple sampling points; a data processing unit for establishing a static distribution feature database, selecting the most matching static distribution feature database, establishing a concentration control coefficient model for the target area, and obtaining a dynamic distribution feature database based on the data acquired by the data acquisition unit; and generating a gas pollution distribution map of the target area using spatial interpolation and visualization methods based on the obtained dynamic distribution feature database.

[0108] Furthermore, in one or more exemplary embodiments of the present invention, the data acquisition unit includes a mobile monitoring device and an online monitoring station.

[0109] The present invention’s method, system, electronic equipment and storage medium for predicting the distribution of gas pollution in a factory area are described in more detail below by way of specific embodiments. It should be understood that the embodiments are merely exemplary and the present invention is not limited thereto.

[0110] Example 1

[0111] This embodiment details the steps for selecting the most matching static distribution feature database based on the current monitoring status. In this embodiment, the target area includes 6 online monitoring points, and 8 static distribution feature databases have been established under different sampling meteorological conditions, as follows:

[0112] ① Static characteristic database A for wind direction 345° (northwest wind) and wind speed 2.5m / s;

[0113] ② Static characteristic database B with wind direction 330° (northwest) and wind speed 3m / s;

[0114] ③ Static characteristic database C for wind direction 320° (northwest wind) and wind speed 5m / s;

[0115] ④ Static characteristic database D for wind direction 90° (east) and wind speed 3m / s;

[0116] ⑤ Static characteristic database E with wind direction 120° (southeast) and wind speed 1m / s;

[0117] ⑥ Static characteristic database F with wind direction 130° (southeast) and wind speed 3m / s;

[0118] ⑦ Static characteristic database G with wind direction 170° (south wind) and wind speed 2m / s;

[0119] ⑧ Static characteristic database H with wind direction 190° (south wind) and wind speed 2m / s.

[0120] If the average wind direction is 80° and the average wind speed is 2 m / s in the current monitoring state, the current monitoring state is compared with the different sampling meteorological conditions mentioned above. In the wind direction screening step, the static distribution feature database D has a minimum wind direction difference of min_EW = 10°, and there is no other static distribution feature database with EW ≤ (min_EW + W). Therefore, the static distribution feature database D is determined to be the best matching static distribution feature database.

[0121] If the average wind direction is 125° and the average wind speed is 1.3 m / s in the current monitoring state, the current monitoring state is compared with the different sampling meteorological conditions mentioned above. In the wind direction screening step, the static distribution feature databases E and F have the same wind direction difference of 5°, which is the minimum value. Moving to the wind speed screening step, the static feature database E has the minimum wind speed difference value min_ES. Therefore, the static distribution feature database E is determined to be the best-matching static distribution feature database.

[0122] Example 2

[0123] This embodiment specifically illustrates when p i When >1, the concentration control coefficient model k for the i-th online monitoring point i (x s ,y s ). k i (x s ,y s It should conform to the attenuation law of gas diffusion, and k i ∈(1,p i ], that is, the attenuation range is p i Up to 1.

[0124] When a feature point is exactly at the position of the i-th online monitoring point, i.e., D i =0, then k i =p i That is, there is no attenuation; when a feature point is far enough away from the i-th online monitoring point, i.e., D i When D ≥ 0, k i=1, meaning complete decay; as D i As k increases i Gradually from p i The decay rate decreases to 1, and the decay curve is as follows: Figure 2 As shown.

[0125]

[0126] Where d is the feature point (x s ,y s ) to the i-th online monitoring point (x i ,y i The distance,

[0127] θ i The average wind direction θ and (x) in the current monitoring status s y s ) and (x i y i The angle between two points is the acute angle of the line segment; m represents a coefficient related to wind speed, 1≤m≤5, and the larger the average wind speed s in the current monitoring state, the larger m is. In this embodiment, the average wind speed in the current monitoring state is 1.5m / s, so m=2.

[0128] Example 3

[0129] This embodiment specifically illustrates when 0 < p i When <1, the concentration control coefficient model k of the i-th online monitoring point i (x s ,y s ). k i (x s ,y s It should conform to the attenuation law of gas diffusion, and k i ∈[p i [,1], that is, the attenuation range is from 1 to p i .

[0130] When a feature point is exactly at the position of the i-th online monitoring point, i.e., D i =0, then k i =p i That is, there is no attenuation; when a feature point is far enough away from the i-th online monitoring point, i.e., D i When D ≥ 0, k i =1, meaning complete decay; as D i As k increases i Gradually from p i Increasing to 1, the decay curve is as follows: Figure 3 As shown. In this embodiment, the average wind speed in the current monitoring state is 1.5 m / s, so m = 2.

[0131] Example 4

[0132] This embodiment specifically illustrates when p i When = 1, the concentration control coefficient model k of the i-th online monitoring point i =1. The total number of online monitoring points is N, and the concentration control coefficient model for the target area is: When the value is 1, the dynamic distribution feature database is equal to the static distribution feature database, i.e., dynamic_net(x) = 1. s ,y s ,c d )=static_net{x s ,y s ,c s}

[0133] Example 5

[0134] This embodiment specifically illustrates the concentration control coefficient model for the i-th online monitoring point, where θ... i And the calculation of m. If the i-th online monitoring point does not have a meteorological monitoring station, first obtain the average wind direction θ in the current monitoring state as the wind direction state of the monitoring point location, and then use the average wind direction θ and (x s ,y s ) and (x i ,y i The acute angle between two points is θ. i ;

[0135] Obtain the average wind speed s in the current monitoring state as the wind speed state at the monitoring point location. If 0 m / s ≤ s < 1 m / s, m ​​= 1; if 1 m / s ≤ s < 3 m / s, m ​​= 2; if 3 m / s ≤ s < 5 m / s, m ​​= 3; if 5 m / s ≤ s < 7 m / s, m ​​= 4; if s ≥ 7 m / s, m ​​= 5.

[0136] Example 6

[0137] This embodiment specifically illustrates the concentration control coefficient model for the i-th online monitoring point, where θ... i And the calculation of m: If the i-th online monitoring point has a meteorological monitoring station, it can monitor and obtain the specific wind direction and wind speed data at that location in real time; firstly, all wind direction monitoring data within a set time period of the meteorological monitoring station are statistically analyzed, and the average wind direction θ is calculated using the vector averaging method; θ i For the average wind direction θ and (x s ,y s ) and (x i ,y i The acute angle between two points formed by a line segment.

[0138] That is, if the average wind direction at a height of 10 meters upwind of the target area and the average wind direction at the i-th online monitoring point are both known, it is preferable to use the average wind direction at the i-th online monitoring point to calculate θ. i .

[0139] Similarly, the value of the average wind speed screening coefficient m of the i-th online monitoring point is preferred. If the height of the meteorological station of the i-th online monitoring point is not 10 meters, it is converted to the wind speed at a height of 10 meters according to the formula.

[0140] Example 7

[0141] This embodiment provides a non-transitory (non-volatile) computer storage medium that stores computer-executable instructions that can execute the methods in any of the above method embodiments and achieve the same technical effect.

[0142] Example 8

[0143] This embodiment provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, which, when executed by a computer, cause the computer to perform the methods described above and achieve the same technical effects.

[0144] Example 9

[0145] Figure 4 This is a schematic diagram of the hardware structure of the electronic device for executing the plant area gas pollution distribution prediction method in this embodiment. The device includes one or more processors 610 and a memory 620. Taking one processor 610 as an example, the device may also include an input device 630 and an output device 640.

[0146] The processor 610, memory 620, input device 630, and output device 640 can be connected via a bus or other means. Figure 4 Taking the example of a connection between China and Israel via a bus.

[0147] The memory 620, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules. The processor 610 executes various functional applications and data processing of the electronic device by running the non-transitory software programs, instructions, and modules stored in the memory 620, thereby implementing the processing method of the above-described method embodiments.

[0148] The memory 620 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; the data storage area may store data, etc. Furthermore, the memory 620 may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 620 may optionally include memory remotely located relative to the processor 610, and these remote memories may be connected to the processing device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0149] Input device 630 can receive input digital or character information and generate signal input. Output device 640 may include display devices such as a display screen.

[0150] One or more modules are stored in memory 620 and, when executed by one or more processors 610, execute:

[0151] S110 acquires meteorological data of the target area and location and concentration data of multiple sampling points to establish a static distribution characteristic database, including multiple sampling points including online monitoring points;

[0152] S130 selects the most matching static distribution feature database based on the current monitoring status;

[0153] S140 establishes a concentration regulation coefficient model for the target area and obtains a dynamic distribution characteristic database;

[0154] Based on the obtained dynamic distribution feature database, S150 uses spatial interpolation and visualization methods to generate a gas pollution distribution map of the target area.

[0155] The above-described product can execute the methods provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the methods. Technical details not described in detail in this embodiment can be found in the methods provided in other embodiments of the present invention.

[0156] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0157] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general-purpose hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0158] The foregoing description of specific exemplary embodiments of the present invention is for illustrative and explanatory purposes. These descriptions are not intended to limit the invention to the precise forms disclosed, and it will be apparent that many changes and variations can be made in accordance with the foregoing teachings. The exemplary embodiments were chosen and described in order to explain the specific principles of the invention and its practical application, thereby enabling those skilled in the art to implement and utilize various different exemplary embodiments of the invention, as well as various different choices and variations. Any simple modifications, equivalent changes, and alterations made to the foregoing exemplary embodiments should fall within the scope of protection of the present invention.

Claims

1. A method for predicting the distribution of gaseous pollution in a factory area, characterized in that, Including the following steps: S110 acquires meteorological data of the target area and location and concentration data of multiple sampling points to establish a static distribution feature database, wherein the multiple sampling points include online monitoring points; the steps of establishing the static distribution feature database include: based on the location and concentration data of multiple sampling points, forming a pollution distribution database of the target area using spatial interpolation; dividing the target area into a well-shaped grid, and taking the combination of grid points and online monitoring points to form feature points; obtaining the pollution concentration of each feature point according to the pollution distribution database, and establishing the static distribution feature database. ,in , The coordinates of the feature point, The pollution concentration at the characteristic point; S130 obtains the current monitoring status and filters out the most matching static distribution feature database; specifically, multiple static distribution feature databases are established according to different sampling meteorological conditions, and the current monitoring status is compared with the sampling meteorological conditions to filter out the most matching static distribution feature database. S140 establishes a concentration regulation coefficient model for the target area and obtains a dynamic distribution characteristic database; step S140 specifically includes: S141 establishing a concentration regulation coefficient model for the i-th online monitoring point. , Coordinates of the i-th online monitoring point ( , ), average wind direction in the current monitoring status and average wind speed and the intensity of pollution changes Related, ,in Let be the average pollution concentration at the i-th online monitoring point in the current monitoring state. S142 establishes the concentration regulation coefficient model for the target area, corresponding to the characteristic point of the i-th online monitoring point in the best-matching static distribution characteristic database. ,in The total number of online monitoring points; S143 obtains the dynamic distribution characteristic database. ,in ; Based on the obtained dynamic distribution feature database, S150 uses spatial interpolation and visualization methods to generate a gas pollution distribution map of the target area.

2. The method for predicting the distribution of gas pollution in a factory area according to claim 1, characterized in that, Repeat steps S130 to S150 at a set frequency to generate a dynamically updated gas pollution distribution map of the target area.

3. The method for predicting the distribution of gas pollution in a factory area according to claim 1, characterized in that, The multiple sampling points evenly cover the target area.

4. The method for predicting the distribution of gas pollution in a factory area according to claim 1, characterized in that, The current monitoring status includes the average wind direction, average wind speed, and average pollution concentration at a height of 10 meters upwind of the target area within a set time period.

5. The method for predicting the distribution of gaseous pollution in a factory area according to claim 4, characterized in that, The set time period is the previous 1 to 6 hours; the average wind direction and average wind speed are calculated using the vector average method; the average pollution concentration is calculated using the arithmetic average method.

6. The method for predicting the distribution of gas pollution in a factory area according to claim 4, characterized in that, When the target area is closed or semi-closed, with flat terrain and few buildings, the static distribution feature database is a set of the coordinates of the sampling points and the concentration of the sampling points.

7. The method for predicting the distribution of gaseous pollution in a factory area according to claim 1, characterized in that, The steps for establishing a static distribution feature database also include: Spatial interpolation is performed on the established static distribution feature database to obtain the pollution distribution database, and the similarity between the restored pollution distribution database and the original pollution distribution database is calculated. Set similarity thresholds M and N, where 0 < M < N < 1; and The validity of the established static distribution feature database is determined based on similarity. If M ≤ similarity ≤ N, then the established static distribution feature database is qualified; If the similarity is less than M, then increase the grid density, re-divide the well-shaped grid, and establish a static distribution feature database; and If the similarity is greater than N, then reduce the grid density, re-divide the grid into well-shaped grids, and establish a static distribution feature database.

8. The method for predicting the distribution of gas pollution in a factory area according to claim 7, characterized in that, The similarity thresholds are 0.7≤M≤0.75 and 0.8≤N≤0.

85.

9. The method for predicting the distribution of gaseous pollution in a factory area according to claim 1, characterized in that, The meteorological data for the target area are the wind speed and direction at a height of 10 meters upwind of the target area. The average value of the meteorological data within the sampling period is the sampling meteorological condition. The sampling period is the time it takes for all sampling points to complete the sampling.

10. The method for predicting the distribution of gas pollution in a factory area according to claim 9, characterized in that, The database of static distribution features selected to find the best match includes: The wind direction screening step involves calculating the wind direction difference (EW) between the average wind direction in the current monitoring state and the sampling meteorological conditions from multiple static distribution feature databases, and then screening for the minimum value, min_EW. If there is only one static distribution feature database with EW≤(min_EW+W), then the static distribution feature database corresponding to the minimum wind direction difference value min_EW is determined as the best matching static distribution feature database, where W is a set angle value and W≤15°; Otherwise, proceed to the wind speed screening step, calculate the wind speed difference ES between the average wind speed in the current monitoring state and the sampling meteorological conditions of multiple static distribution feature databases, and screen the minimum value min_ES. The static distribution feature database corresponding to the minimum wind speed difference min_ES is determined as the best matching static distribution feature database.

11. The method for predicting the distribution of gaseous pollution in a factory area according to claim 10, characterized in that, The concentration control coefficient model of the i-th online monitoring point It conforms to the attenuation law of gas diffusion and satisfies: when When <1, ,when When >1, ,when When =1, =1; when hour, That is, there is no decay; when hour, That is, complete decay; when At that time, with The increase, Gradually changing from pollution intensity Decay to 1, where, For the distance of complete attenuation, , in, For feature points ( , ) to the Online monitoring points ( , The distance, ; The average wind direction under current monitoring conditions. and( , )and( , The acute angle between two points and the line segments between them; This represents a coefficient related to wind speed. And the average wind speed in the current monitoring status The larger, The larger.

12. The method for predicting the distribution of gas pollution in a factory area according to claim 11, characterized in that, It is related to the size of the target area and the number of online monitoring points. The range is 100~500m.

13. The method for predicting the distribution of gas pollution in a factory area according to claim 11, characterized in that, If 0m / s≤ <1m / s, =1; if 1m / s≤ <3m / s, =2; if 3m / s≤ <5m / s, =3, if 5m / s≤ <7m / s, =4, if ≥7m / s, =5.

14. A gas pollution distribution prediction system for a factory area, characterized in that, The method described in any one of claims 1 to 13 includes: The data acquisition unit is used to acquire meteorological data of the target area and location and concentration data of multiple sampling points; The data processing unit is used to establish a static distribution feature database, select the most matching static distribution feature database, establish a target area concentration control coefficient model, and obtain a dynamic distribution feature database based on the data acquired by the data acquisition unit; and to form a gas pollution distribution map of the target area using spatial interpolation and visualization methods based on the obtained dynamic distribution feature database.

15. The plant area gas pollution distribution prediction system according to claim 14, characterized in that, The data acquisition unit includes mobile monitoring equipment and online monitoring stations.

16. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, causes the at least one processor to perform the plant area gas pollution distribution prediction method as described in any one of claims 1 to 13.

17. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer-executable instructions for causing the computer to execute the plant area gas pollution distribution prediction method as described in any one of claims 1 to 13.

Images