Comprehensive atmospheric pollution source tracing method and terminal based on monitoring data

Abstract

The application provides an atmospheric pollution comprehensive source tracing method and terminal based on monitoring data, comprising the following steps: determining abnormal monitoring parameters and abnormal monitoring points according to normal value intervals corresponding to monitoring parameters; identifying the abnormal monitoring parameters to obtain an identification source type; determining the confidence of each type of monitoring source according to the identification source type; determining at least one suspected area and the area coefficient of each suspected area according to meteorological data of the abnormal monitoring points; determining the confidence of the pollution source according to the monitoring source type to which the pollution source belongs; determining the emission coefficient of the pollution source according to emission intensity data and geographical position information of the pollution source; determining the comprehensive contribution degree of the pollution source according to the area coefficient of the suspected area to which the pollution source belongs, the confidence of the pollution source and the emission coefficient of the pollution source; and sorting the comprehensive contribution degrees of all pollution sources in descending order to obtain a pollution source contribution list. The application can improve the atmospheric pollution source tracing accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of environmental monitoring, and particularly relates to an atmospheric pollution comprehensive tracing method based on monitoring data and a terminal. BACKGROUND

[0002] In recent years, with the development of atmospheric pollution prevention and control work, the environmental air quality has been significantly improved, and the heavy pollution process has been significantly reduced. The abnormal emission of the pollution source originally in a secondary position gradually highlights the influence on air quality, rises to a major problem, and becomes the focus of current environmental management. Only by tracing the abnormal pollution source in time and solving the problem can the environmental air quality be further improved. On the other hand, the monitoring of pollution sources has made great progress in recent years, whether in monitoring parameters, monitoring objects, monitoring means or monitoring timeliness, and has made significant breakthroughs. Comprehensive monitoring of various types of pollution sources has been basically achieved.

[0003] At present, the pollution problem is mainly traced by combining artificial analysis of monitoring data and on-site investigation. The tracing process requires a large amount of time. The application of various types of environmental monitoring data and pollution source monitoring data is still in a relatively primary stage, and is limited by the technical level, experience accumulation and work efficiency of human beings, which leads to the inability to discover pollution problems in time and quickly and accurately trace the pollution source.

[0004] Therefore, how to discover sudden pollution problems in time based on various types of environmental monitoring data, and quickly and accurately identify and trace abnormal pollution sources, has become a difficult problem to be solved in current environmental management. SUMMARY

[0005] Therefore, the present application provides an atmospheric pollution comprehensive tracing method based on monitoring data and a terminal, which can solve the problem of poor accuracy of pollution tracing in the prior art.

[0006] In a first aspect, an atmospheric pollution comprehensive tracing method based on monitoring data is provided by the embodiments of the present application. The method is applied to a target area, and the target area includes a plurality of monitoring points. The monitoring parameters of each monitoring point include a plurality of types. For any monitoring point, the method includes the following steps:

[0007] For each type of monitoring parameter, whether the monitoring parameter is an abnormal monitoring parameter is determined according to the normal value interval corresponding to the monitoring parameter. If there is an abnormal monitoring parameter in the monitoring point, the monitoring point is marked as an abnormal monitoring point.

[0008] The abnormal monitoring parameter is identified to obtain an identification source type corresponding to the monitoring point.

[0009] According to the identified source type, the confidence degree of each type of monitoring source is determined through a preset confidence degree relationship table, and for any identified source type, the confidence degree of each type of monitoring source corresponding to the identified source type is included in the confidence degree relationship table.

[0010] According to the meteorological data of the abnormal monitoring point, at least one suspected area is determined, and a region coefficient of each suspected area is determined.

[0011] For any pollution source in the at least one suspected area, the confidence degree of the pollution source is determined according to the type of monitoring source to which the pollution source belongs.

[0012] According to the emission intensity data of the pollution source and the geographic location information of the pollution source, the emission coefficient of the pollution source is determined.

[0013] According to the region coefficient of the suspected area to which the pollution source belongs, the confidence degree of the pollution source, and the emission coefficient of the pollution source, the comprehensive contribution degree of the pollution source is determined.

[0014] The comprehensive contribution degrees of all pollution sources in the at least one suspected area are sorted in descending order to obtain a pollution source contribution list.

[0015] In a second aspect, an embodiment of the present application provides a computer readable storage medium, the computer readable storage medium storing a computer program, and the computer program is executed by a processor to implement the steps of the method according to the first aspect or any possible implementation manner of the first aspect.

[0016] Compared with the prior art, the embodiment of the present application has the following beneficial effects:

[0017] The present application traces pollution sources through existing environmental monitoring data, obtains the confidence degree of the monitoring source to which the pollution source belongs based on the identified source, determines the suspected area and the region coefficient according to the meteorological data, determines the emission coefficient of the pollution source according to the emission intensity data of the pollution source and the geographic location information of the pollution source, and determines the comprehensive contribution degree of the pollution source according to the region coefficient of the suspected area to which the pollution source belongs, the confidence degree of the pollution source, and the emission coefficient of the pollution source. By sorting the contribution degrees, a pollution source contribution list is obtained, which is more consistent with the actual situation of pollution source tracing, and the monitoring data is updated in real time, there is no information lag, and the accuracy of pollution source tracing is further improved. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0019] Figure 1 is an implementation flowchart of a comprehensive atmospheric pollution tracing method based on monitoring data provided by the embodiments of the present application;

[0020] Figure 2 is a suspected area schematic diagram provided by the embodiments of the present application;

[0021] Figure 3 is another suspected area schematic diagram provided by the embodiments of the present application;

[0022] Figure 4 is a structural schematic diagram of a comprehensive atmospheric pollution tracing device based on monitoring data provided by the embodiments of the present application;

[0023] Figure 5 is a schematic diagram of a terminal provided by the embodiments of the present application. DETAILED DESCRIPTION

[0024] In the following description, specific details such as specific system structures, techniques, etc. are presented in order to thoroughly understand the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits and methods are omitted to avoid unnecessary details that hinder the description of the present application.

[0025] In order to make the objects, technical solutions and advantages of the present application clearer, the following will be described by specific embodiments in conjunction with the drawings.

[0026] The existing pollution tracing methods also include the latter trajectory method and the diffusion model method, etc. However, these methods either only refer to meteorological data, although the suspected area can be pointed out, but still face a large amount of investigation work, and the efficiency is low; or need to be based on pollution emission inventory data, and the inventory data is static data, and the timeliness is poor, so that the tracing result deviates greatly from the actual situation, and therefore, they are not suitable for real-time tracing for sudden problems. Therefore, the accuracy of pollution tracing is poor.

[0027] Based on this problem, the embodiments of the present application provide a comprehensive atmospheric pollution tracing method based on monitoring data, referring to Figure 1 which shows an implementation flowchart of a comprehensive atmospheric pollution tracing method based on monitoring data provided by the embodiments of the present application, and the details are as follows:

[0028] In step 101, for each type of monitoring parameter, whether the monitoring parameter is an abnormal monitoring parameter is determined according to a normal value interval corresponding to the monitoring parameter, and if there is an abnormal monitoring parameter at the monitoring point, the monitoring point is marked as an abnormal monitoring point.

[0029] The method provided by the embodiment of the application is applied to a target area, the target area includes a plurality of monitoring points, and the monitoring parameters of each monitoring point include a plurality of types. The method provided by the embodiment of the application is applied to each monitoring point respectively.

[0030] In the embodiment of the application, the target area can be a city, a city and its surrounding areas, or other types of areas, and the application is not limited thereto.

[0031] In the embodiment of the application, the monitoring points include, but are not limited to, all national, provincial, municipal and township air quality monitoring points arranged in a city. The obtained data includes geographical position information of each monitoring point, such as latitude and longitude, height information, etc.; monitoring time of each monitoring point, specifically to hours, such as hourly monitoring data. The plurality of types of monitoring parameters monitored by each monitoring point include, but are not limited to, PM 10 , PM 2.5 , SO2, NO2, CO, O3 and VOCs.

[0032] In an optional implementation, for each type of monitoring parameter, the normal value interval corresponding to the monitoring parameter can be pre-set according to an empirical value, or can be obtained by statistical analysis of historical data, and the embodiment of the application is not limited thereto.

[0033] In an optional implementation, the normal value interval is obtained by summarizing the data rule of the monitoring point in a recent period of time.

[0034] Optionally, for any type of monitoring parameter, the normal value interval corresponding to the monitoring parameter is determined according to the monitoring data of the monitoring parameter of the monitoring point in a first preset time period, wherein the first preset time period is a time period located before the current time, the normal value interval includes a first normal value interval, a second normal value interval and a third normal value interval, the first normal value interval is used to represent the change rate of the monitoring parameter at the current monitoring time and the last monitoring time in the normal state, the second normal value interval is used to represent the relative deviation of the monitoring value of the monitoring parameter of the monitoring point and other monitoring points in a control group in the normal state, the other monitoring points in the control group are all other monitoring points with a straight-line distance less than or equal to a first preset distance from the monitoring point, and the third normal value interval is used to represent the proportion of the monitoring concentration of the monitoring parameter in all monitoring parameters in the normal state.

[0035] After determining the first normal value interval, the second normal value interval and the point normal value interval, if the monitoring parameter meets the first discrimination condition and the second discrimination condition simultaneously, or the monitoring parameter meets the third discrimination condition, it is determined that the monitoring parameter is an abnormal monitoring parameter, wherein the first discrimination condition is that the change rate of the monitoring parameter at the current monitoring time and the last monitoring time exceeds the first normal value interval, the second discrimination condition is that the relative deviation of the monitoring value of the monitoring parameter at the monitoring point and the monitoring value of the monitoring parameter at other monitoring points in the control group exceeds the second normal value interval, and the third discrimination condition is that the proportion of the monitoring concentration of the monitoring parameter in all monitoring parameters exceeds the third normal value interval.

[0036] Optionally, the first preset time period is updated in a periodic cycle, wherein the periodic cycle can be every day or every week, and the first preset time period can be several weeks in the past to 3 months in the past. The specific value of the periodic cycle and the length of the first preset time period is not limited in the embodiments of the present application. For example, the length of the first preset time period is one month, and the first normal value interval, the second normal value interval and the third normal value interval are updated in a periodic cycle through the data of each month.

[0037] In a specific example, the first preset time period is 30 days in the past, and there are 24 monitoring time points per day. For a monitoring parameter, the first discrimination condition is that the change rate of the value of the monitoring parameter in the current hour compared with the last hour exceeds the first normal value interval; the second discrimination condition is that the relative deviation of the monitoring value of the monitoring parameter at the current monitoring point and the monitoring value of the monitoring parameter at other surrounding monitoring points exceeds the second normal value interval, and the third discrimination condition is that the proportion of the monitoring concentration of the monitoring parameter in the current hour in all monitoring parameters exceeds the third normal value interval.

[0038] In an optional implementation, the determination method of the first normal value interval is as follows:

[0039] For the monitoring value of the monitoring parameter at the monitoring point at n1 monitoring time points in the first preset time period, the change rate of the monitoring value at each adjacent two time points is calculated by the first preset formula to obtain n1-1 change rate values, the n1-1 change rate values are sorted from small to large to obtain a first sorting result, the values located in the first preset percentage of the first sorting result are obtained to determine a first threshold value, and the value interval less than or equal to the first threshold value is taken as the first normal value interval, wherein the first preset formula is

[0040]

[0041] wherein RC1 is used to represent the change rate of the monitoring value of the monitoring parameter at adjacent two time points, C t is used to represent the monitoring value of the monitoring parameter at t time.t-1 a monitoring value of the monitoring parameter at t-1.

[0042] In combination with the above specific examples, for any type of monitoring parameter, 720 monitoring values of the monitoring parameter of the monitoring point in the past 30 days are obtained, 719 values of RC1 are obtained through a first preset formula, the 719 values of RC1 are sorted in ascending order to obtain a first sorting result, the first preset percentage is 90%, a first threshold value is obtained according to the first 90% of the values in the first sorting result, and a value interval less than or equal to the first threshold value is taken as a first normal value interval.

[0043] In an optional implementation, a determination method of the second normal value interval is as follows:

[0044] The monitoring values of the monitoring parameter of the monitoring point and other monitoring points in the control group at n2 monitoring moments in a first preset time period are calculated through a second preset formula to obtain the relative deviations of the monitoring values of the monitoring parameter of the monitoring point and other monitoring points in the control group at each of the n2 monitoring moments, the obtained n2 values of the relative deviations are sorted in ascending order to obtain a second sorting result, values located in the front of the second preset percentage in the second sorting result are obtained, a second threshold value is determined, and a value interval less than or equal to the second threshold value is taken as a second normal value interval, wherein the second preset formula is

[0045]

[0046] RC2 is used to represent the relative deviation of the monitoring values of the monitoring parameter of the monitoring point and other monitoring points in the control group at the same monitoring moment, C i is used to represent the monitoring value of the monitoring parameter of the monitoring point at the monitoring moment, C J is used to represent the monitoring value of the monitoring parameter of the other monitoring point in the control group at the monitoring moment, and m is used to represent the number of the other monitoring points in the control group, is used to represent the average of the sum of the monitoring values of the monitoring parameter of all the other monitoring points in the control group at the monitoring moment.

[0047] In combination with the above specific examples, other monitoring points within a range of 3-5 km from the monitoring point are taken as a control group, i.e., the first preset distance is 3-5 km, 720 monitoring values of the monitoring point for the monitoring parameter in the past 30 days are obtained, and the monitoring values of each monitoring point in the control group for the corresponding 720 monitoring times of the monitoring parameter in the past 30 days are obtained. The values of 720 RC2 are obtained by the above-mentioned second preset formula, the 720 RC2 values are sorted from small to large to obtain a second sorting result, the second preset percentage is taken as 90%, the second threshold value is obtained according to the first 90% of the numerical values in the second sorting result, and the numerical value interval less than or equal to the second threshold value is taken as a second normal value interval.

[0048] The third normal value interval determination method comprises:

[0049] The monitoring values of the monitoring point for the monitoring parameter at n3 monitoring times within the first preset time period are calculated by a third preset formula to obtain n3 proportion values of the monitoring concentration of the monitoring parameter at each monitoring time in all monitoring parameters, the n3 proportion values are sorted from small to large to obtain a third sorting result, the first third preset percentage of the numerical values in the third sorting result is obtained, a third threshold value is determined, and a numerical value interval less than or equal to the third threshold value is taken as a third normal value interval, wherein the third preset formula is

[0050]

[0051] wherein RC3(x) is used to represent the proportion value of the monitoring parameter x at a monitoring time, C x is used to represent the monitoring concentration value of the monitoring parameter x at the monitoring time, C xt is used to represent the preset standard concentration value of the monitoring parameter x, t is used to represent the total number of the monitoring parameter types in the monitoring point, C p is used to represent the monitoring concentration value of the monitoring parameter p at the monitoring time, C pt is used to represent the preset standard concentration value of the monitoring parameter p, wherein the monitoring parameter comprises t types, the monitoring parameter x is one of the t types of monitoring parameters, and the monitoring parameter p is any one of the t monitoring parameters.

[0052] In combination with the above specific examples, 720 monitoring values of the monitoring point for each type of monitoring parameter in the past 30 days are obtained, and the monitoring parameters are taken as PM 10 , PM 2.5 , SO2, NO2, CO, O3 and VOCs. 10 , PM 2.5 , SO2, NO2, CO, O3 and VOCs.

[0053] Table 1

[0054] Parameter PM 10 ]]> PM 2.5 ]]> SO2 NO2 CO O3 VOCs Standard value SV 70 μg / m 3 ]] 35 μg / m 3 ]] 60 μg / m 3 ]] 40 pg / m 3 ]] 4 mg / m 3 ]] 160 μg / m 3 ]] 500 ppb

[0055] The third preset formula is specifically expanded as:

[0056]

[0057] According to the third preset formula, 720 values of RC3 are obtained and sorted from small to large to obtain a third sorting result, a third preset percentage is 50%, and according to the first 50% of the values in the second sorting result, a third threshold is obtained, and a value interval less than or equal to the third threshold is taken as a third normal value interval.

[0058] After the first normal value interval, the second normal value interval and the point normal value interval are determined, if the monitoring parameter meets the first discrimination condition and the second discrimination condition at the same time, or the monitoring parameter meets the third discrimination condition, it is determined that the monitoring parameter is an abnormal monitoring parameter.

[0059] That is, as long as the third discrimination condition is met, the monitoring parameter is an abnormal monitoring parameter, or as long as the first discrimination condition and the second discrimination condition are met at the same time, the monitoring parameter is an abnormal monitoring parameter.

[0060] In step 102, the abnormal monitoring parameter is identified to obtain the identification source type corresponding to the monitoring point.

[0061] Optionally, the identification source type can be determined by experience, or the identification source type can be determined by an expert. The embodiment of the present application does not limit the method for determining the identification source type.

[0062] In the embodiment of the present application, the identification source type of the monitoring point can be determined by the technical method provided in the patent application number CN202010846058.3 and the patent name “A pollution source type automatic identification method based on machine learning”. The method uses a machine learning algorithm to combine environmental monitoring data to identify the occurrence of pollution problems and determine the pollution type.

[0063] The at least one identification source type corresponding to the monitoring point can also be identified by other existing algorithms. The embodiment of the present application does not limit this.

[0064] In step 103, according to the identification source type, the confidence degree of each type of monitoring source is determined through a preset confidence degree relationship table. For any identification source type, the confidence degree relationship table includes the confidence degree of each type of monitoring source corresponding to the identification source type.

[0065] In an optional implementation, the monitoring source type includes an industrial enterprise, a boiler, a catering, a construction site, a road, a residential area, a fire point, a motor vehicle exhaust, etc.

[0066] In the embodiments of the present application, the identification source types in the identification result include dust source, mobile source, coal-fired source, cooking fume source and industrial source. For example, Table 2 is a confidence relationship table of identification source and monitoring source obtained by combining application experience.

[0067] Table 2

[0068]

[0069] For example, the identification source type is dust source, and according to Table 2, the confidence of the monitoring source being an industrial enterprise is 0.4.

[0070] In step 104, at least one suspected area and an area coefficient of each suspected area are determined according to the meteorological data of the abnormal monitoring point.

[0071] In the embodiments of the present application, the meteorological data includes but is not limited to urban hourly meteorological data or meteorological monitoring point hourly meteorological data, and the meteorological data specifically includes but is not limited to wind direction, wind speed, temperature and humidity.

[0072] In some optional implementation manners, the propagation area is demarcated as the suspected area according to the wind speed data and wind direction data of a period of time before the monitoring point is marked as the abnormal monitoring point.

[0073] In the embodiments of the present application, optionally, the meteorological data of the abnormal monitoring point includes wind speed data and wind direction data of a second preset time period before a target time, and the target time is the time when the abnormal monitoring point appears the abnormal monitoring parameter.

[0074] In the following, a specific example is used for illustration. The target time is t time, the time length corresponding to the second preset time period is Δt, t time is the end time of the second preset time length, the wind speed and wind direction in the Δt time before the abnormal monitoring data appearance time t are counted, the suspected area where the abnormal pollution source is located is calculated, and the area coefficient s is obtained. The determination of the suspected area and the determination of the area coefficient of the suspected area are explained in combination with specific conditions:

[0075] In the first case, if the wind speed of the second preset time period is less than or equal to a first preset wind speed value, the at least one suspected area only includes one suspected area, and the area coefficient of the suspected area is a preset standard coefficient, wherein the suspected area is a circular area with the abnormal monitoring point as the center and the first propagation radius as the radius size, and the first propagation radius is a preset radius value.

[0076] For example, the first preset wind speed value is 0.2 m / s, the first propagation radius is a value of 1 km to 3 km, and when the wind speed v in the Δt time is less than or equal to 0.2 m / s, the suspected area S is a circular area with the abnormal monitoring point as the center and the propagation radius of 1 km to 3 km.

[0077] In the second case, if there is only one wind direction in the second preset time period, a second propagation radius is determined according to the wind speed data in the second preset time period and the length of the second preset time period, the at least one suspected area includes only one suspected area, and the area coefficient of the suspected area is a preset standard coefficient, wherein the suspected area is a sector area with the abnormal monitoring point as the center and the second propagation radius as the radius, the angle corresponding to the sector area is a preset angle, the preset angle is an acute angle, and the wind direction of the abnormal monitoring point in the second preset time period is coincident with the direction of the center line of the preset angle.

[0078] For example, when there is only one wind direction F (0° for north, 90° for east, 180° for south, and 270° for west), the suspected area S is a sector area with the abnormal monitoring point as the center and an included angle of F±22.5°, and the propagation distance is the second propagation radius r.

[0079] In an optional implementation, determining the second propagation radius according to the wind speed data in the second preset time period and the length of the second preset time period includes:

[0080] calculating the second propagation radius according to a fourth preset formula, the fourth preset formula being

[0081] r = ∫1 n v i *Δt i

[0082] wherein r is used to represent the second propagation radius, n is used to represent that there are n different sizes of wind speed in the second preset time period, v i is used to represent the size of the i-th wind speed, and Δt i is used to represent the duration of the i-th wind speed.

[0083] When there is only one suspected area, the area coefficient corresponding to the suspected area is a preset standard coefficient, for example, the preset standard coefficient is 1.

[0084] In an optional implementation, according to the statistics of the wind speed and the wind direction, the following cases are further included:

[0085] The third case: if there are multiple wind directions in the second preset time period, q1 wind directions closest to the target time are obtained, the duration and wind speed of each of the q1 wind directions are determined in turn, each of the q1 wind directions corresponds to a sub-time interval, q1 sub-time intervals are obtained, if the wind speed in each of the q1 sub-time intervals is less than or equal to the second preset wind speed value, q2 target sub-time intervals in which the wind speed is greater than the first preset wind speed are obtained in the q1 sub-time intervals, for any target sub-time interval, the propagation radius corresponding to the target sub-time interval is determined according to the wind speed data in the target sub-time interval and the time length of the target sub-time interval, wherein the second preset wind speed value is greater than the first preset wind speed value, q1 is a positive integer greater than or equal to 2, and 1≤q2≤q1;

[0086] The q2 target sub-time intervals are sorted in order from near to far to the target time, a fourth sorting result is obtained, and the suspected area corresponding to each target sub-time interval is obtained in turn according to the fourth sorting result, q2 suspected areas are obtained, wherein for any target sub-time interval, if the target sub-time interval is not located in the first position in the fourth sorting result, the suspected area corresponding to the target sub-time interval is determined based on the suspected area of the target sub-time interval located before the target sub-time interval, and at least one suspected area is q2 suspected areas, wherein the fourth sorting result includes the start time and the end time corresponding to each target sub-time interval;

[0087] According to the fourth sorting result, the region coefficient of the suspected area corresponding to the first target sub-time interval in the fourth sorting result is a preset standard coefficient, and the region coefficient of the suspected area corresponding to the first target sub-time interval in the fourth sorting result is greater than the region coefficient of the suspected area corresponding to the second target sub-time interval.

[0088] For example, take q1=3, when there are not less than 3 wind directions in the second preset time period, take the 3 wind directions closest to the target time, in order from near to far, the three sub-time intervals corresponding to the three wind directions are Δt1, Δt2 and Δt3, for example, there are north wind (F1=0.), northeast wind (F2=45.) and east wind (F3=90.) in order from near to far, the duration is Δt1, Δt2 and Δt3 respectively, and the corresponding wind speed is v1, v2 and v3. Wherein, v1, v2 and v3 represent a wind speed interval.

[0089] Based on the third case described above, different situations can be divided.

[0090] In the first case of the third case, the wind speed in each of the three sub-time intervals Δt1, Δt2 and Δt3 is greater than the first preset wind speed value and less than or equal to the second preset wind speed value, for example, the second preset wind speed value is 5 m / s.

[0091] The target sub-time interval is the three sub-time intervals Δt1, Δt2 and Δt3, and the corresponding suspected area and the area coefficient of each suspected area are determined, and a suspected area diagram is obtained, for example, as shown in FIG. 2B. Figure 2

[0092] In the Δt1 time, the suspected area S1 is a sector area with a propagation distance r1 and a central angle of 45°.

[0093] In the Δt2 time, the suspected area S2 is a maximum area with a propagation distance r2 and a central angle of 45°.

[0094] In the Δt3 time, the suspected area S3 is a maximum area with a propagation distance r3 and a central angle of 45°.

[0095] Wherein, r1, r2 and r3 are calculated according to the fourth preset formula.

[0096] The total suspected area S is the sum of S1, S2 and S3.

[0097] In the second case of the third case, the wind speed in each of the three sub-time intervals Δt1, Δt2 and Δt3 is less than or equal to the second preset wind speed value, for example, the second preset wind speed value is 5 m / s, and the wind speed in each of the three sub-time intervals is less than or equal to 5 m / s, but there is a sub-time interval whose wind speed is less than or equal to 0.2 m / s, and this sub-time interval does not participate in the calculation process of the suspected area. For example, in Δt2, v2 is less than 0.2 m / s, and the sub-time interval corresponding to Δt2 does not participate in the calculation, and the obtained suspected area is shown in FIG. 2C. Figure 3

[0098] In an optional implementation, if there is a time period in which the wind speed is greater than the second preset wind speed value in the time period corresponding to the q1 sub-time intervals, the starting time of the time period in which the wind speed is greater than the second preset wind speed value is marked as the starting time, and the method further comprises: removing the data before the starting time in the fourth sorting result to obtain a new fourth sorting result; determining at least one suspected area and the area coefficient of each suspected area based on the new fourth sorting result.

[0099] ​​In the third case, the third situation, Δt1, Δt2 and Δt3, the wind speed is greater than 5 m / s, then the wind speed greater than 5 m / s time t' and the data before the data is not considered, only to t-t' time, according to the above steps to calculate the suspected area.

[0100] In the fourth sorting result, the region coefficient of the suspected area corresponding to the previous target sub-time interval is greater than the region coefficient of the suspected area corresponding to the next target sub-time interval. For example, the obtained suspected area includes three suspected areas S1, S2 and S3 as shown in the figure, the region coefficient of S1 is a preset standard coefficient, for example, 1, the region coefficient of S2 is less than 1, for example, 0.5, and the region coefficient of S3 is less than 0.5, for example, 0.25. Figure 2

[0101] The region coefficient determination process of the suspected area based on the inventive concept is within the protection scope of the embodiments of the present application, and the embodiments of the present application do not limit the specific value of the region coefficient.

[0102] In step 105, for any pollution source in at least one suspected area, the confidence of the pollution source is determined according to the type of the monitoring source to which the pollution source belongs.

[0103] In the embodiments of the present application, the at least one suspected area refers to the total suspected area obtained by step 104.

[0104] According to the calibration range of the suspected area, according to the geographical position information of the pollution source, all pollution sources in the suspected area are obtained.

[0105] In the embodiments of the present application, the pollution source monitoring data includes organized monitoring data and unorganized monitoring data, wherein the organized monitoring includes industrial enterprises, boilers, catering, etc., and the unorganized monitoring data includes industrial enterprises, construction sites, roads, residential areas, etc. Monitoring data and fire point video monitoring data, motor vehicle exhaust telemetry data, etc.

[0106] Further, the organized monitoring data includes the source type, name, geographical position, pollutant parameter type, and hourly concentration and hourly emission amount of the monitoring object. The unorganized monitoring data includes the source type, name, geographical position, pollutant parameter type, and monitoring concentration data of the monitoring object.

[0107] Further, the monitoring source type includes industrial enterprises, boilers, catering, construction sites, roads, residential areas, fire points, motor vehicle exhausts, etc., the geographical position refers to longitude, latitude and height information, and the pollutant parameter type includes but is not limited to particulate matter, PM10, PM2.5, SO2, NOx, NO2, CO, O3 and VOCs. ​

[0108] For example, the identified source type obtained in step 102 is a coal-fired source, and for a pollution source in a suspected area, the pollution source is a restaurant, and the corresponding monitoring source type of the restaurant is catering. According to Table 2, the value of the confidence corresponding to the monitoring source being catering when the identified source type is a coal-fired source is R = 0.4. Therefore, the confidence of the pollution source is 0.4.

[0109] In step 106, the emission coefficient of the pollution source is determined according to the emission intensity data of the pollution source and the geographic location information of the pollution source.

[0110] In some optional implementations, the greater the emission intensity, the greater the emission coefficient, and the closer the distance to the abnormal monitoring point, the greater the emission coefficient. In some optional implementations, the emission intensity data of the pollution source and the geographic location information of the pollution source are used to assign the emission coefficient of the pollution source. Alternatively, a list of empirical values can be set to establish a unique mapping relationship list of the emission coefficient, the distance to the abnormal monitoring point, and the emission intensity, and the emission coefficient is determined through the list.

[0111] In an optional implementation, the embodiment of the present application further provides a method for determining an emission coefficient, comprising:

[0112] determining at least one type of basic data for characterizing the emission intensity of the pollution source.

[0113] For each type of basic data, the normalized emission intensity value of the type of basic data, the class intensity weight of the pollution source for the type of basic data, and the emission change weight are sequentially calculated, wherein the class intensity weight is used to represent the ratio of the sum of the average emission volume of the monitoring source to which the pollution source belongs in the target area within a preset reference time and the average emission volume of each type of monitoring source of the same identified source, and the emission change weight is used to represent the change amount of the emission intensity of the type of basic data at the target time and the previous time, wherein the class intensity weights of the same type of monitoring source in the target area are the same.

[0114] For example, the identified source is a dust source, and according to Table 2 above, the monitoring sources corresponding to the confidence of the dust source not being 0 include industrial enterprises, construction sites, roads, residential areas, and fire points. The average values of the emission volumes of each type of monitoring source in the target area are sequentially calculated to obtain the average value of the emission volumes of all industrial enterprises in the target area A, the average value of the emission volumes of all construction sites B, the average value of the emission volumes of all roads C, the average value of the emission volumes of all residential areas D, and the average value of the emission volumes of all fire points E. The sum of the emission volumes of all types of monitoring sources A + B + C + D + E is calculated. For a pollution source in the target area, if the monitoring source label corresponding to the pollution source is an industrial enterprise, the class intensity weight of the pollution source is equal to A / (A + B + C + D + E).

[0115] According to the geographical position information of the pollution source, an enhanced weight of the pollution source is obtained, if the straight-line distance between the pollution source and the calibrated monitoring point is less than or equal to a second preset distance, the enhanced weight of the pollution source is a first enhanced weight, otherwise the enhanced weight of the pollution source is a second enhanced weight, wherein the calibrated monitoring point is a monitoring point with a calibrated monitoring parameter, the calibrated monitoring parameter meets at least one of the first, second and third discrimination conditions, and the first enhanced weight is greater than the second enhanced weight.

[0116] According to the normalized emission intensity value of each type of basic data, the class intensity weight and the emission change weight of at least one type of basic data, and the enhanced weight of the pollution source, the emission coefficient of the pollution source is calculated.

[0117] Firstly, at least one type of basic data used to represent the emission intensity of the pollution source is determined: the basic data used by different pollution sources is different.

[0118] The pollution source with the unorganized emission monitoring point of the construction site, the road, the residential area, the motor vehicle exhaust, etc. adopts the real-time monitoring concentration data to represent the emission intensity.

[0119] The industrial enterprise, the catering, the boiler, etc. may have both the organized emission monitoring and the unorganized emission monitoring point, wherein the actual emission amount or the real-time monitoring concentration is used to represent the emission intensity of the organized emission, and the real-time monitoring concentration data is used to represent the emission intensity of the unorganized emission.

[0120] The fire point adopts the video monitoring data to represent the emission intensity.

[0121] Secondly, for each type of basic data, the normalized emission intensity value of the type of basic data, the class intensity weight and the emission change weight of the pollution source to the type of basic data are calculated in turn.

[0122] In the first sub-step of the second step, the normalized processing of the emission intensity of the pollution source

[0123] The monitoring data of various pollution sources is mapped into the range of 0-1 to make it dimensionless and establish comparability. The normalization calculation formula is as follows:

[0124]

[0125] Wherein, q i is the emission intensity of the pollution source i, q min is the minimum value of the emission intensity of the pollution source in the region, q max is the maximum value of the emission intensity of the pollution source, q i ′ is the normalized emission intensity of the pollution source i.

[0126] When the pollution source uses a single data to represent the emission intensity, the data can be normalized; when the pollution source uses two or more types of data to represent the emission intensity, the different types of data are normalized respectively.

[0127] The second sub-step of the second step is to obtain the class intensity weight QW of the pollution source for the type of basic data

[0128] The class intensity weight QW is used to represent the difference in emission volume between different pollution source types.

[0129] According to the relative ratio of the average single source emission of each type of pollution source in the benchmark time jurisdiction, the class intensity weight QW is calculated.

[0130] The third sub-step of the second step is to calculate the emission change weight CW of the pollution source for the type of basic data

[0131] The emission change weight CW is used to represent the change in the emission of the pollution source. When the emission or the monitoring concentration is reduced or flat, CW is 1; when the emission or the monitoring concentration is increased,

[0132]

[0133] Wherein, q t is the emission intensity of the pollution source at time t, q t-1 is the emission intensity of the pollution source at time t-1.

[0134] For a certain pollution source, the emission change weight is the maximum value of the emission change weights of various pollutants.

[0135] The third step is to obtain the intensification weight of the pollution source according to the geographical position information of the pollution source

[0136] For example, the monitoring point position of the monitoring parameter meeting any one of the first, second and third discrimination conditions is taken as a calibration monitoring point position, the second preset distance is a distance value of 1km to 2km, the intensification weight of the pollution source within the second preset distance range around the calibration monitoring point position is the first intensification weight, otherwise it is the second intensification weight, for example, the first intensification weight is 2, and the second intensification weight is 1.

[0137] In an optional implementation, for a pollution source represented by only one type of basic data, the emission coefficient of the pollution source is calculated according to the normalized emission intensity value of each type of basic data in at least one type of basic data, the class intensity weight and the emission change weight, and the intensification weight of the pollution source, which includes:

[0138] The emission coefficient of the pollution source is calculated according to the fifth preset formula, and the fifth preset formula is

[0139] e i = q' i * QWi i * CWi i * SWi i

[0140] wherein e i represents an emission coefficient of the pollution source i, the pollution source i being a pollution source whose emission intensity is represented by only one type of basic data; q i ' represents a normalized emission intensity value of the type of basic data in the pollution source i, QW i represents a class intensity weight of the type of basic data in the pollution source i, CW i represents an emission variation weight of the type of basic data in the pollution source i, SW i represents a strengthening weight of the pollution source i;

[0141] For a pollution source whose emission intensity is represented by two types of basic data, the emission coefficient of the pollution source is calculated according to the normalized emission intensity value, the class intensity weight and the emission variation weight of each type of basic data in at least one type of basic data, and the strengthening weight of the pollution source, including:

[0142] The emission coefficient of the pollution source is calculated according to a sixth preset formula, the sixth preset formula being

[0143] e j = (q' m * QWi m * CWi m + q' n * QWi n * CWi n ) * SWi j

[0144] wherein the two types of basic data are organized emission monitoring data and unorganized emission monitoring data, e j represents an emission coefficient of the pollution source j, the pollution source j being a pollution source whose emission intensity is represented by two types of basic data; q' m represents a normalized emission intensity value of the organized emission monitoring data in the pollution source j, QW m represents a class intensity weight of the organized emission monitoring data in the pollution source j, CW m represents an emission variation weight of the organized emission monitoring data in the pollution source j; q' n represents a normalized emission intensity value of the unorganized emission monitoring data in the pollution source j, QW n represents a class intensity weight of the unorganized emission monitoring data in the pollution source j, CW nan emission variation weight for representing unorganized emission monitoring data in the pollution source j, SW j an intensification weight for representing the pollution source j.

[0145] In step 107, a comprehensive contribution degree of the pollution source is determined according to the area coefficient of the suspected area to which the pollution source belongs, the confidence of the pollution source and the emission coefficient of the pollution source.

[0146] In the embodiment of the present application, the comprehensive contribution degree z of each pollution source is determined by comprehensively considering the confidence of the monitoring source type to which the pollution source belongs, the area coefficient of the suspected area in which the pollution source is located and the emission coefficient of the pollution source. For example, if a certain air quality monitoring point is increased in a certain monitoring parameter, the suspected area S is determined through step 104; for the seven monitoring source types in S, the confidence R of each type of monitoring source is obtained according to the identification source type identified by the result of step 103, and if there is more than one type of identification source, the confidence of the corresponding monitoring source type is added; each pollution source obtains its own area coefficient s according to the different areas in S; the emission coefficient e is obtained according to the emission intensity and the geographical location; and the comprehensive contribution degree z is calculated as follows:

[0147] z = R * s * e

[0148] In step 108, the comprehensive contribution degrees of all pollution sources in at least one suspected area are sorted in descending order to obtain a pollution source contribution list.

[0149] The comprehensive contribution degrees of all pollution sources in the suspected area are calculated according to the calculation formula, and the pollution source contribution list is formed according to the contribution degree.

[0150] The pollution source contribution list result is automatically updated with the change of time and monitoring data, and the main contribution source of abnormal pollution problem can be found in real time, which supports the rapid elimination of abnormal emission problem and improves the environmental air quality.

[0151] The present application traces the pollution source through the existing environmental monitoring data, obtains the confidence of the monitoring source to which the pollution source belongs based on the identification source, determines the suspected area and the area coefficient according to the meteorological data, determines the emission coefficient of the pollution source according to the emission intensity data of the pollution source and the geographical location information of the pollution source, and determines the comprehensive contribution degree of the pollution source according to the area coefficient of the suspected area to which the pollution source belongs, the confidence of the pollution source and the emission coefficient of the pollution source. The pollution source contribution list is obtained by sorting the contribution degree, which is more in line with the actual situation of pollution source tracing, and the monitoring data is updated in real time, there is no information lag, and the accuracy of pollution source tracing is further improved.

[0152] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the application.

[0153] The following is an apparatus embodiment of the application. For details not described in detail, reference can be made to the corresponding method embodiments described above.

[0154] Figure 4 The structure schematic diagram of the atmospheric pollution comprehensive source tracing apparatus based on monitoring data provided by the embodiment of the application is shown. For the convenience of description, only the part related to the embodiment of the application is shown, and the details are described as follows:

[0155] As shown in Figure 4 The atmospheric pollution comprehensive source tracing apparatus 4 based on monitoring data includes a first determination module 41, an identification module 42, a second determination module 43, a third determination module 44, a fourth determination module 45, a fifth determination module 46, a sixth determination module 47, and a contribution list acquisition module 48;

[0156] The first determination module 41 is configured to determine, for each type of monitoring parameter, whether the monitoring parameter is an abnormal monitoring parameter according to the normal value interval corresponding to the monitoring parameter, and mark the monitoring point as an abnormal monitoring point if there is an abnormal monitoring parameter at the monitoring point;

[0157] The identification module 42 is configured to identify the abnormal monitoring parameter to obtain the identification source type corresponding to the monitoring point;

[0158] The second determination module 43 is configured to determine the confidence degree of each type of monitoring source according to the identification source type and through a pre-set confidence degree relationship table. For any identification source type, the confidence degree relationship table includes the confidence degree of each type of monitoring source corresponding to the identification source type;

[0159] The third determination module 44 is configured to determine at least one suspected area and the area coefficient of each suspected area according to the meteorological data of the abnormal monitoring point;

[0160] The fourth determination module 45 is configured to determine the confidence degree of any pollution source in the at least one suspected area according to the monitoring source type to which the pollution source belongs;

[0161] The fifth determination module 46 is configured to determine the emission coefficient of the pollution source according to the emission intensity data of the pollution source and the geographic location information of the pollution source;

[0162] The sixth determination module 47 is configured to determine the comprehensive contribution degree of the pollution source according to the area coefficient of the suspected area to which the pollution source belongs, the confidence degree of the pollution source, and the emission coefficient of the pollution source;

[0163] The contribution list acquisition module 48 is configured to sort comprehensive contribution degrees of all pollution sources in the at least one suspected area in descending order to obtain a pollution source contribution list.

[0164] The present application traces pollution sources by using existing environmental monitoring data, obtains the confidence degree of a monitoring source to which a pollution source belongs based on source identification, determines a suspected area and a region coefficient according to meteorological data, determines the emission coefficient of the pollution source according to the emission intensity data of the pollution source and the geographic location information of the pollution source, and determines the comprehensive contribution degree of the pollution source according to the region coefficient of the suspected area to which the pollution source belongs, the confidence degree of the pollution source and the emission coefficient of the pollution source. The pollution source contribution list is obtained by sorting the contribution degrees, which is more in line with the actual situation of pollution source tracing, and the monitoring data is updated in real time, so that there is no information lag, and the accuracy of pollution source tracing is further improved.

[0165] The device for tracing comprehensive atmospheric pollution based on monitoring data provided in the embodiment can be used to execute the method for tracing comprehensive atmospheric pollution based on monitoring data, and has similar implementation principles and technical effects. Details are not described herein.

[0166] Figure 5 is a schematic diagram of a terminal provided in an embodiment of the present application. As shown in Figure 5 , the terminal 5 in this embodiment includes a processor 50, a memory 51, and a computer program 52 stored in the memory 51 and executable on the processor 50. The processor 50 implements the steps in each of the above method embodiments for tracing comprehensive atmospheric pollution based on monitoring data when executing the computer program 52, such as Figure 1 steps 101 to 108. Alternatively, the processor 50 implements the functions of each module / unit in each of the above device embodiments when executing the computer program 52, such as Figure 4 the functions of the modules 41 to 48.

[0167] For example, the computer program 52 can be divided into one or more modules / units, one or more of which are stored in the memory 51 and executed by the processor 50 to complete the present application. One or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program 52 in the terminal 5.

[0168] The terminal 5 can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing devices. The terminal 5 can include, but is not limited to, the processor 50 and the memory 51. Those skilled in the art can understand Figure 5The terminal 5 is merely an example and does not limit the terminal 5, which can include more or less components than shown, or combine some components, or have different components, such as the terminal can also include an input / output device, a network access device, a bus, etc.

[0169] The processor 50 can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0170] The memory 51 can be an internal storage unit of the terminal 5, such as a hard disk or a memory of the terminal 5. The memory 51 can also be an external storage device of the terminal 5, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 5. Further, the memory 51 can include both the internal storage unit and the external storage device of the terminal 5. The memory 51 is used to store computer programs and other programs and data required by the terminal. The memory 51 can also be used to temporarily store data that has been output or will be output.

[0171] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to complete all or part of the above described functions. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit, and the integrated unit can be realized in the form of hardware or in the form of software. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the unit and module in the system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0172] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in a certain embodiment can be referred to the relevant description of other embodiments.

[0173] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or in combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0174] In the embodiments provided by the present application, it should be understood that the disclosed apparatus / terminal and method can be implemented in other ways. For example, the apparatus / terminal embodiments described above are merely schematic, for example, the division of modules or units is merely a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0175] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0176] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0177] The integrated modules / units, if implemented in the form of software functional units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of each of the above-mentioned atmospheric pollution comprehensive source tracing methods based on monitoring data can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0178] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. An atmospheric pollution integrated source apportionment method based on monitoring data, characterized in that, The method is applied to a target region, the target region including a plurality of monitoring points, each monitoring point having a plurality of types of monitoring parameters, and for any monitoring point, the method includes: For each type of monitoring parameter, determining whether the monitoring parameter is an abnormal monitoring parameter according to a normal value interval corresponding to the monitoring parameter, and if there is an abnormal monitoring parameter for the monitoring point, marking the monitoring point as an abnormal monitoring point; Identifying the abnormal monitoring parameter to obtain an identification source type corresponding to the monitoring point; According to the identification source type, determining the confidence degree of each type of monitoring source through a pre-set confidence degree relationship table, for any identification source type, the confidence degree relationship table including the confidence degree of each type of monitoring source corresponding to the identification source type; the identification source type including dust source, moving source, coal-fired source, cooking oil fume source and industrial source; the monitoring source including industrial enterprise, boiler, catering, construction site, road, residential area, fire point and motor vehicle exhaust; According to the meteorological data of the abnormal monitoring point, determining at least one suspected area and a region coefficient of each suspected area; For any pollution source in the at least one suspected area, determining the confidence degree of the pollution source according to the monitoring source type to which the pollution source belongs; According to the emission intensity data of the pollution source and the geographical location information of the pollution source, determining the emission coefficient of the pollution source; According to the region coefficient of the suspected area to which the pollution source belongs, the confidence degree of the pollution source and the emission coefficient of the pollution source, determining the comprehensive contribution degree of the pollution source; The comprehensive contribution degrees of all pollution sources in the at least one suspected area are sorted in descending order to obtain a pollution source contribution list.

2. The method of claim 1, wherein, Before the method further includes: For any type of monitoring parameter, determining the normal value interval corresponding to the monitoring parameter according to the monitoring data of the monitoring parameter of the monitoring point in a first preset time period, wherein the first preset time period is a time period located before the current time, and the normal value interval includes a first normal value interval, a second normal value interval and a third normal value interval, the first normal value interval is used to represent the change rate of the monitoring parameter at the current monitoring time and the last monitoring time in the normal state, the second normal value interval is used to represent the relative deviation of the monitoring value of the monitoring parameter of the monitoring point and other monitoring points in a control group in the normal state, the other monitoring points in the control group are all other monitoring points with a straight-line distance from the monitoring point less than or equal to a first preset distance, and the third normal value interval is used to represent the proportion of the monitoring concentration of the monitoring parameter in all monitoring parameters in the normal state; The method further includes: For each type of monitoring parameter, determining whether the monitoring parameter is an abnormal monitoring parameter according to a normal value interval corresponding to the monitoring parameter, and if there is an abnormal monitoring parameter for the monitoring point, marking the monitoring point as an abnormal monitoring point; If the monitoring parameter meets the first discrimination condition and the second discrimination condition at the same time, or the monitoring parameter meets the third discrimination condition, it is determined that the monitoring parameter is an abnormal monitoring parameter, wherein the first discrimination condition is that a change rate of the monitoring parameter at a current monitoring time and a previous monitoring time exceeds the first normal value interval, the second discrimination condition is that a relative deviation of the monitoring point and monitoring values of the monitoring parameter of other monitoring points in a control group exceeds a second normal value interval, and the third discrimination condition is that a proportion of a monitoring concentration of the monitoring parameter in all monitoring parameters exceeds the third normal value interval.

3. The method of claim 2, wherein, The determination method of the first normal value interval comprises: For the monitoring point within the first preset time period The monitored value of the parameter at each monitoring time point is used to calculate the rate of change between every two adjacent monitoring times using a first preset formula, thus obtaining... -1 is the value of the rate of change, for the The values ​​of the rate of change of -1 are sorted from smallest to largest to obtain a first sorting result. The values ​​within the first preset percentage of the first sorting result are then determined, and a first threshold is defined. The range of values ​​less than or equal to the first threshold is taken as the first normal value range. The first preset formula is: wherein, for representing the rate of change of the monitoring parameter monitoring value at two adjacent time points, for representing the monitoring value of the monitoring parameter at time point, for representing the monitoring value of the monitoring parameter at time point; The determination method of the second normal value interval comprises: For this monitoring point and other monitoring points within the same control group, within the first preset time period The monitored values ​​of the monitored parameter at each monitoring time are calculated sequentially using the second preset formula. The relative deviation of the monitored parameter value at each monitoring point within a monitoring time period from that of other monitoring points in the control group is used to obtain... The relative deviation values ​​are sorted from smallest to largest to obtain a second sorting result. The values ​​within the top second preset percentage of the second sorting result are then used to determine a second threshold. The range of values ​​less than or equal to the second threshold is defined as the second normal value range. The second preset formula is: wherein, for representing the relative deviation of the monitoring value of the monitoring parameter of the monitoring point from the monitoring values of the monitoring parameter of other monitoring points in the control group at the same monitoring moment, for representing the monitoring value of the monitoring parameter of the monitoring point at the monitoring moment, C j for representing the monitoring value of the monitoring parameter of other monitoring points in the control group at the monitoring moment, for representing the number of other monitoring points in the control group, for representing the average of the sum of the monitoring values of the monitoring parameter of all other monitoring points in the control group at the monitoring moment. The determination method of the third normal value interval comprises: The monitoring value of the monitoring parameter at each of the monitoring time points in the first preset time period is calculated by a third preset formula The monitoring value of the monitoring parameter at each of the monitoring time points in the first preset time period is calculated by a third preset formula The proportion of the monitoring concentration of the monitoring parameter at each of the monitoring time points in all monitoring parameters is obtained The proportion of the monitoring concentration of the monitoring parameter at each of the monitoring time points in all monitoring parameters is obtained The third sorting result is obtained by sorting the proportion values from small to large, the value located in the front third preset percentage of the third sorting result is obtained, the third threshold value is determined, and the value interval less than or equal to the third threshold value is taken as the third normal value interval, wherein the third preset formula is wherein, for indicating the monitoring parameter the proportion value at a monitoring time, for indicating the monitoring parameter the monitoring concentration value at a monitoring time, for indicating the monitoring parameter the preset standard concentration value, for indicating the total number of the monitoring parameter types in the monitoring point, for indicating the monitoring parameter the monitoring concentration value at a monitoring time, for indicating the monitoring parameter the preset standard concentration value.

4. The method according to any one of claims 1 to 3, characterized in that, The meteorological data of the abnormal monitoring point comprises wind speed data and wind direction data of a second preset time period before a target time, the target time is a time when the abnormal monitoring parameter of the abnormal monitoring point appears, and the determination of at least one suspected area and a region coefficient of each suspected area according to the meteorological data of the abnormal monitoring point comprises: If the wind speed of the second preset time period is less than or equal to a first preset wind speed value, the at least one suspected area only comprises one suspected area, and the region coefficient of the suspected area is a preset standard coefficient, wherein the suspected area is a circular area with the abnormal monitoring point as the center and a first propagation radius as the radius, and the first propagation radius is a preset radius value. If there is only one wind direction in the second preset time period, a second propagation radius is determined according to the wind speed data in the second preset time period and a time length of the second preset time period, the at least one suspected area only comprises one suspected area, and the region coefficient of the suspected area is a preset standard coefficient, wherein the suspected area is a sector area with the abnormal monitoring point as the center and the second propagation radius as the radius, an angle corresponding to the sector area is a preset angle, the preset angle is an acute angle, and a wind direction of the abnormal monitoring point in the second preset time period is coincident with a direction of a center line of the preset angle.

5. The method of claim 4, wherein, The method further comprises: If there are multiple wind directions within the second preset time period, then the wind direction closest to the target time is obtained. Wind direction, determine the following in sequence The duration and wind speed of each wind direction in the given wind direction, the Each wind direction corresponds to a sub-time interval, resulting in... Each sub-time interval, if the aforementioned Within each sub-time interval, the wind speed remains consistently less than or equal to the second preset wind speed value. The wind speed value within a specific time interval is greater than the first preset wind speed. For each target sub-time interval, the propagation radius corresponding to that sub-time interval is determined based on the wind speed data within that sub-time interval and the duration of that sub-time interval. The second preset wind speed value is greater than the first preset wind speed value. A positive integer greater than or equal to 2, 1 ≤ ≤ ; According to the order from near to far to the target moment, the target sub-time intervals are sorted to obtain a fourth sorting result, and a suspected area corresponding to each target sub-time interval is obtained in sequence according to the fourth sorting result to obtain a suspected area. Wherein, for any target sub-time interval, if the target sub-time interval is not located at the first position in the fourth sorting result, the suspected area corresponding to the target sub-time interval is determined based on the suspected area of the target sub-time interval located before the target sub-time interval, and the at least one suspected area is the suspected area. Wherein, the fourth sorting result includes the start moment and the end moment corresponding to each target sub-time interval.​ According to the fourth sorting result, a region coefficient of a suspected area corresponding to a first target sub-time interval in the fourth sorting result is the preset standard coefficient, and a region coefficient of a suspected area corresponding to a previous target sub-time interval is greater than a region coefficient of a suspected area corresponding to a next target sub-time interval in adjacent two target sub-time intervals in the fourth sorting result.

6. The method of claim 5, wherein, If there is a time period in which the wind speed is greater than the second preset wind speed value in the time period corresponding to the one sub-time interval, the starting time in which the wind speed is greater than the second preset wind speed value in the time period corresponding to the one sub-time interval is marked as the starting time, and the method further comprises: In the fourth sorting result, data located before the starting time is removed to obtain a new fourth sorting result. Based on the new fourth sorting result, at least one suspected area and a region coefficient of each suspected area are determined.

7. The method of claim 4, wherein, The determination of the second propagation radius according to the wind speed data in the second preset time period and the time length of the second preset time period comprises: The second propagation radius is calculated according to a fourth preset formula, and the fourth preset formula is wherein, for representing the second propagation radius, for representing the second preset time period, a wind speed of a different size, for representing the first size of a wind speed, for representing the first duration of a wind speed.

8. The method of claim 2 or 3, wherein, The determining the emission coefficient of the pollution source according to the emission intensity data of the pollution source and the geographical position information of the pollution source comprises: determining at least one type of basic data for representing the emission intensity of the pollution source; for each type of basic data, sequentially calculating a normalized emission intensity value of the type of basic data, a class intensity weight of the pollution source for the type of basic data, and an emission change weight, wherein the class intensity weight is used to represent a ratio of a sum value of an average emission volume of a monitoring source to which the pollution source belongs in the target region and an average emission volume of each type of monitoring source of the same identified source in a preset reference time, and the emission change weight is used to represent a change amount of the emission intensity of the type of basic data at a target time and a previous time; the target time is a time when the abnormal monitoring parameter of the abnormal monitoring point appears; obtaining a strengthening weight of the pollution source according to the geographical position information of the pollution source, if a straight-line distance between the pollution source and a calibration monitoring point is less than or equal to a second preset distance, the strengthening weight of the pollution source is a first strengthening weight, otherwise the strengthening weight of the pollution source is a second strengthening weight, wherein the calibration monitoring point is a monitoring point with a calibration monitoring parameter, and the calibration monitoring parameter meets at least one of the first, second and third discrimination conditions; the first strengthening weight is greater than the second strengthening weight; calculating the emission coefficient of the pollution source according to the normalized emission intensity value, the class intensity weight and the emission change weight of each type of basic data in the at least one type of basic data, and the strengthening weight of the pollution source.

9. The method of claim 8, wherein, For the pollution source represented by only one type of basic data, the calculating the emission coefficient of the pollution source according to the normalized emission intensity value, the class intensity weight and the emission change weight of each type of basic data in the at least one type of basic data, and the strengthening weight of the pollution source comprises: calculating the emission coefficient of the pollution source according to a fifth preset formula, the fifth preset formula is wherein, an emission factor for representing a pollution source, i a pollution source, i is a pollution source characterized by emission intensity using only one type of base data; a normalized emission intensity value for representing the type of base data in the pollution source, i a class intensity weight for representing the type of base data in the pollution source, an emission variation weight for representing the type of base data in the pollution source, i a reinforcement weight for representing the pollution source, a reinforcement weight for representing the pollution source, i a reinforcement weight for representing the pollution source, a reinforcement weight for representing the pollution source, i a reinforcement weight for representing the pollution source, For the pollution source represented by two types of basic data, the calculating the emission coefficient of the pollution source according to the normalized emission intensity value, the class intensity weight and the emission change weight of each type of basic data in the at least one type of basic data, and the strengthening weight of the pollution source comprises: calculating the emission coefficient of the pollution source according to a sixth preset formula, the sixth preset formula is The two types of basic data are organized emissions monitoring data and fugitive emissions monitoring data. Used to indicate pollution sources j Emission coefficient, pollution source j To characterize pollution sources by emission intensity using two types of basic data; Used to indicate pollution sources j The normalized emission intensity values ​​from organized emission monitoring data. Used to indicate pollution sources j The class intensity weights of the organized emissions monitoring data are as follows: Used to indicate pollution sources j Weighting of emission changes in organized emission monitoring data; Used to indicate pollution sources j Normalized emission intensity values ​​from fugitive emission monitoring data. Used to indicate pollution sources j Class intensity weights for unorganized emission monitoring data in China Used to indicate pollution sources j Weighting of emission changes in fugitive emission monitoring data. Used to indicate pollution sources j The weighting of the enhancement.

10. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the steps of the method of any one of claims 1 to 9. The processor executes the computer program to realize the steps of the method of any one of claims 1 to 9.

Images