SO2 emission tracing method and calculation equipment

Abstract

The embodiment of the present disclosure provides a SO2 emission tracing method and computing device. The SO2 emission tracing method includes: obtaining SO2 concentration monitoring data of multiple monitoring points within the target period and meteorological data within the control area; based on the SO2 concentration monitoring data and meteorological data, determining the diffusion path corresponding to each SO2 concentration monitoring data, and the SO2 concentration prediction data of the tracing point on the diffusion path; sorting the SO2 concentration prediction data corresponding to each tracing point according to the time mark to determine the SO2 concentration prediction sequence; based on the SO2 concentration prediction sequence of each tracing point and the proximity relationship of each tracing point, determining the predicted SO2 exceeding the standard discharge point. Based on the solution provided by the embodiment of the present disclosure, it is possible to more accurately screen and obtain the predicted SO2 exceeding the standard discharge points with higher credibility. Subsequently, it is also possible to conduct targeted investigations on the predicted SO2 exceeding the standard discharge points to determine the enterprises that exceed the standard discharge.

Description

Technical Field

[0001] The present disclosure relates to the technical field of atmospheric environment monitoring, and in particular to a SO2 emission tracing method and computing device. Background Art

[0002] Energy companies, petrochemical companies, and other enterprises generate gaseous pollutants such as SO2 during their production processes. To ensure air quality and prevent secondary disasters caused by excessive emissions of these pollutants, relevant laws, regulations, and administrative rules have strict regulations on the concentration and scale of pollutant emissions from polluting enterprises. These regulations require enterprises to install pollution treatment equipment when installing production equipment and to use this equipment during production to avoid excessive emissions of gaseous pollutants. However, due to the drive to proactively reduce production costs, aging equipment, and improper management and maintenance, these enterprises may still experience excessive pollutant emissions.

[0003] In order to strengthen the monitoring and management of corporate pollutant emissions and constrain corporate behavior, relevant technologies have considered tracing the source of pollutants based on atmospheric SO2 concentration monitoring data monitored by air quality monitoring stations. Specifically, when high-value SO2 concentration monitoring data is detected at air quality monitoring stations, relevant technologies are mostly based on local meteorological conditions to determine the tracing direction, and then patrol personnel will check the tracing points in the corresponding direction. However, the aforementioned method only checks the area near the target air quality station, and does not take into account the problem of high values in monitoring equipment caused by the diffusion of pollutants in a large area. The directionality and target of the tracing points are not strong, resulting in a huge workload for manual tracing but a low timeliness in discovering the source of pollution. Summary of the Invention

[0004] In order to solve the problem that existing pollution point tracing has weak directionality and targeting, the embodiments of the present disclosure provide a new SO2 emission tracing method and computing device.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for tracing the source of SO2 emissions, comprising:

[0006] Obtain SO2 concentration monitoring data from multiple monitoring points within a target period and meteorological data within a control area, wherein both the SO2 concentration monitoring data and the meteorological data have time stamps, and the control area includes traceability points;

[0007] Based on the SO2 concentration monitoring data and the meteorological data, reverse diffusion simulation is performed according to the pollutant diffusion mechanism to determine the diffusion path corresponding to each SO2 concentration monitoring data and the SO2 concentration prediction data of the traceability point on the diffusion path; each SO2 concentration prediction data also has a time stamp;

[0008] The SO2 concentration prediction data corresponding to each traceability point are sorted according to the time stamp to determine the SO2 concentration prediction sequence;

[0009] Based on the SO2 concentration prediction sequence of each tracing point and the proximity relationship of each tracing point, the predicted SO2 discharge points exceeding the standard are determined.

[0010] Optionally, the method further includes obtaining terrain feature data within the controlled area;

[0011] The reverse diffusion simulation is performed based on the SO2 concentration monitoring data and the meteorological data according to the pollutant diffusion mechanism to determine the diffusion path corresponding to each SO2 concentration monitoring data, including:

[0012] Based on the SO2 concentration monitoring data, the meteorological data and the terrain feature data, a reverse diffusion simulation is performed according to the pollutant diffusion mechanism to determine the diffusion path corresponding to each SO2 concentration monitoring data.

[0013] Optionally, the method further includes: obtaining a SO2 emission concentration monitoring sequence of the pollutant-discharging enterprise at each traceability point;

[0014] After determining and predicting the SO2 discharge point exceeding the standard, the method further includes:

[0015] Based on the SO2 emission concentration monitoring sequence of each pollutant-discharging enterprise and the SO2 concentration prediction sequence, the SO2 emission enterprises that are predicted to exceed the standard are determined.

[0016] Optionally, the step of determining and predicting SO2-exceeding emission enterprises based on the SO2 emission concentration monitoring sequence and the SO2 concentration prediction sequence of each emission enterprise includes:

[0017] Process the SO2 emission concentration monitoring sequence of each pollutant-discharging enterprise and determine the corresponding monitoring change trend; and process the SO2 concentration prediction sequence corresponding to the predicted SO2 exceeding emission points and determine the corresponding prediction change trend;

[0018] A target monitoring change trend that is at least partially identical to the predicted change trend is selected from the monitoring change trend, and the pollutant-discharging enterprise corresponding to the target monitoring change trend is used as the predicted SO2 excessive pollutant-discharging enterprise.

[0019] Optionally, the step of determining and predicting SO2-exceeding emission enterprises based on the SO2 emission concentration monitoring sequence and the SO2 concentration prediction sequence of each emission enterprise includes:

[0020] Based on the SO2 emission concentration monitoring series of each pollutant-discharging enterprise, a weighted summation of multiple weights is performed to obtain multiple combined concentration prediction series;

[0021] Processing each of the combined concentration prediction sequences to determine a corresponding combined change trend; and processing the SO2 concentration prediction sequence corresponding to the predicted SO2 exceeding discharge point to determine a corresponding predicted change trend;

[0022] Selecting a target combination change trend that is at least partially identical to the predicted change trend from the combination change trends, and determining the pollutant-discharging enterprise with the highest corresponding weight based on the target combination change trend;

[0023] The polluting enterprises with the highest weights are used as the predicted SO2 exceeding emission standards enterprises.

[0024] Optionally, before obtaining the SO2 concentration monitoring data of multiple monitoring points within the target period and the meteorological data within the control area, the method further includes:

[0025] Determine whether the SO2 concentration monitoring data at the first monitoring point at the first time triggers a high value alarm;

[0026] Determine whether to trigger a high-value alarm, and determine the target time period based on the first time point and a preset duration; the first monitoring point is at least one monitoring point among the multiple monitoring points.

[0027] Optionally, determining whether the SO2 concentration monitoring data at the first monitoring point at the first time point triggers a high value alarm includes:

[0028] In response to the SO2 concentration monitoring data at the first monitoring point at the first time point satisfying at least one of the following conditions, it is determined that a high value alarm is triggered:

[0029] The SO2 concentration monitoring data at the first monitoring point at the first time exceeds the set comparison threshold;

[0030] The ratio of the SO2 concentration monitoring data at the first monitoring point at the first time to the SO2 concentration monitoring data at the previous time is greater than a preset ratio, and the preset ratio is at least greater than 1;

[0031] The ranking of the SO2 concentration monitoring data of the first monitoring point at the first time point and the ranking of the SO2 concentration monitoring data at the previous time point are higher than the set change ranking;

[0032] The difference between the SO2 concentration monitoring data of the first monitoring point at the first time point and the average value of the SO2 concentration monitoring data of the adjacent points is greater than the set outlier threshold.

[0033] Optionally, after inspecting the predicted SO2 discharge points to determine that the discharge exceeds the standard, the method further includes:

[0034] The SO2 concentration monitoring data when the first monitoring point triggers a high value alarm is used as high value alarm triggering data.

[0035] Optionally, before obtaining the SO2 concentration monitoring data of multiple monitoring points within the target period and the meteorological data within the control area, the method further includes:

[0036] The historical SO2 concentration monitoring data of multiple target monitoring points are analyzed to determine the target time period.

[0037] In a second aspect, the present disclosure implements a computing device comprising a processor and a memory, wherein the memory is used to store a computer program; when the computer program is loaded by the processor, the processor executes the SO2 emission tracing method as described above.

[0038] The solution provided by the embodiment of the present disclosure utilizes the SO2 concentration monitoring data of multiple monitoring points and the meteorological data of the control area to perform reverse diffusion simulation, and after determining the SO2 concentration prediction data of each traceability point at different times, constructs the SO2 concentration prediction sequence of each traceability point. Based on the basic premise that pollutants are either diffused or discharged within the traceability point, through the SO2 concentration prediction sequence of each traceability point and the proximity relationship of the traceability point, according to the predetermined logical judgment rules, it is also possible to determine the predicted SO2 excessive discharge points. Based on the solution provided by the embodiment of the present disclosure, it is possible to more accurately screen and obtain the predicted SO2 excessive discharge points with a higher degree of credibility. Subsequently, it is also possible to conduct targeted investigations on the predicted SO2 excessive discharge points to identify the excessive discharge enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0040] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the prior art description. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative work, including

[0041] Figure 1 This is a flow chart of the SO2 emission tracing method provided by an embodiment of the present disclosure;

[0042] Figure 2 is a flow chart for determining enterprises that discharge pollutants exceeding standards in some embodiments of the present disclosure;

[0043] Figure 3 is a flow chart for determining enterprises that discharge pollutants exceeding standards in accordance with other embodiments of the present disclosure;

[0044] Figure 4 Schematic diagram of a SO2 emission tracing device provided in an embodiment of the present disclosure;

[0045] Figure 5 It is a structural diagram of a computing device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0046] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0047] As used herein, the term "including" and its variations are open-ended inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description. In this document, relational terms such as "first" and "second" are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0048] To address the problem that the tracing points determined by existing solutions are not very specific and targeted, resulting in a huge workload for tracing but a low timeliness in discovering pollution sources, the present disclosure provides a new SO2 emission tracing method. The tracing method provided in the present disclosure is executed by a computing device.

[0049] Figure 1 This is a flow chart of the SO2 emission tracing method provided by the embodiment of the present disclosure. Figure 1 As shown, the SO2 emission tracing method provided by the embodiment of the present disclosure includes S110-S140.

[0050] S110: Obtain SO2 concentration monitoring data of multiple monitoring points within the target period and meteorological data within the control area.

[0051] To trace the source of pollution, subsequent steps require reverse simulation analysis based on the data from monitoring points. This reverse simulation analysis requires a traceability basis, which means obtaining corresponding data within a time period as a foundation. Therefore, it is necessary to obtain traceability data within a certain period of time, that is, traceability data for the target period.

[0052] According to location theory, a point can only be determined by intersecting at least two lines. Accordingly, the source tracing process requires the identification of at least two paths. Cross-comparison of these paths is the only way to determine the location of the pollution source. To achieve this goal, the disclosed embodiments obtain SO₂ concentration monitoring data from multiple monitoring points to determine multiple source tracing paths (i.e., the diffusion paths mentioned later).

[0053] The SO2 concentration monitoring data is time-stamped, meaning the time it was acquired can be determined. This time stamp will serve as the basis for subsequent reverse diffusion simulation analysis.

[0054] A control zone is a pre-determined area where polluting enterprises are monitored for exceeding pollution standards. In practice, a control zone generally corresponds to the administrative area of an environmental regulator.

[0055] The control area includes traceability points. These are the locations of polluting enterprises. In real-world scenarios, these points could be industrial zones, high-tech development zones, and other locations within a region. While these points are treated as points, they still represent a region. For example, if the control area is a prefecture-level city, a traceability point could represent a 5km radius.

[0056] Acquiring meteorological data within the control area during the target time period involves obtaining meteorological data for the control area at each point in time within the target time period according to a predetermined time period. In practice, to ensure the accuracy of subsequent reverse diffusion simulations, the meteorological data within the control area should be as detailed as possible. For example, if the control area is a prefecture-level city, to ensure the accuracy of the simulation, the meteorological data should be at least county-level or township-level.

[0057] Because wind speed and direction directly affect the dispersion of pollutants, meteorological data must include at least wind speed and direction data. These data include not only wind speed and direction parallel to the ground, but also those in updrafts and downdrafts. Furthermore, in some cases, pollutants may settle or transform due to the action of water vapor in the air. Therefore, meteorological data may also include air humidity and water content data.

[0058] S120: Based on the SO2 concentration monitoring data and meteorological data, reverse diffusion simulation is performed according to the pollutant diffusion mechanism to determine the diffusion path corresponding to each SO2 concentration monitoring data, as well as the SO2 concentration prediction data of the traceability point on the diffusion path.

[0059] In the disclosed embodiment, each SO2 concentration prediction data also has a time stamp.

[0060] In reality, after being emitted by polluting enterprises, air pollutants diffuse according to specific diffusion mechanisms under the influence of external forces such as wind. The diffusion mechanisms of pollutants are well-defined through extensive historical experimental data and simulation experiments. For example, for some pollutants, the Lagrangian particle diffusion model can be used to characterize the diffusion mechanism. Once the diffusion mechanism and the diffusion dynamics (i.e., the wind speed and direction as represented by meteorological data) are known, the pollutant concentration at a downstream point can be determined based on the upstream pollutant concentration.

[0061] Accordingly, based on the SO2 concentration monitoring data at the downstream location (i.e., the target monitoring point) and the meteorological data within the control area, a reverse simulation based on the pollutant diffusion mechanism is performed, that is, a reverse diffusion simulation is performed to obtain a reverse diffusion path. If the traceability point is located on a certain diffusion path, the predicted SO2 concentration data at this traceability point at a certain point in time can be determined (here, it is referred to as SO2 concentration prediction data only from a prediction perspective and does not represent data for a future point in time).

[0062] Using the aforementioned method, multiple diffusion paths can be derived from SO2 concentration monitoring data acquired at the same monitoring point at different points in time during the target time period (these diffusion paths may be the same or different in spatial terms). Similarly, multiple diffusion paths can be derived from SO2 concentration monitoring data acquired at different monitoring points at the same point in time during the target time period (these diffusion paths may be the same in temporal terms, but their spatial dimensions may differ).

[0063] According to the aforementioned method, for a tracing point, SO2 concentration prediction data on multiple diffusion paths can be obtained, that is, there will be multiple SO2 concentration prediction data for a tracing point. It should be noted here that the aforementioned multiple SO2 concentration prediction data for a tracing point should be prediction data for different time points, that is, the multiple pollution source concentration prediction data for a tracing point have corresponding (different) time stamps. Of course, in some cases, due to problems such as inaccurate calculations and model simulations, some tracing points may have more than one SO2 concentration prediction data at a time point (that is, a time stamp). At this time, data processing can be used to exclude data with poor confidence, or several data can be weighted to obtain unique data for the corresponding tracing point at a time point.

[0064] S130: Sort the SO2 concentration prediction data corresponding to each tracing point according to the time stamp to determine the SO2 concentration prediction sequence.

[0065] Following the aforementioned method, SO2 concentration prediction data with different time stamps can be obtained for each traceability point. By sorting the corresponding SO2 concentration prediction data in chronological order, a SO2 concentration prediction sequence for each traceability point can be obtained. The SO2 concentration prediction sequence represents the change in pollutant concentration at the traceability point during the target time period.

[0066] S140: Based on the SO2 concentration prediction sequence of each tracing point and the proximity relationship of each tracing point, determine the predicted SO2 discharge point exceeding the standard.

[0067] Assuming here that no pollutants are produced in areas outside the control zone (of course, this assumption may not hold true; this is an ideal scenario), the pollutant concentrations detected at the monitoring point are due to pollutant emissions from polluting enterprises within the control zone. Polluting enterprises located within the area corresponding to the source traceability point will inevitably reflect their pollutant emissions in the SO2 concentration prediction series. If a polluting enterprise within a source traceability point exceeds its pollutant emissions within a short period of time, this will inevitably be reflected in the corresponding SO2 concentration prediction series.

[0068] Correspondingly, by comparing the SO2 concentration prediction sequences of each nearby tracing point, it can be found that the excessive pollutant concentration at certain tracing points at certain times is not caused by the diffusion of pollutants from surrounding tracing points. It is most likely caused by the excessive emissions of polluting enterprises within this tracing point. Accordingly, this tracing point can be regarded as an excessive pollution discharge point.

[0069] In specific implementations, the computing device can filter the SO2 concentration prediction sequences for each traceability point using a pre-set data threshold to identify high-value point segment sequences. After obtaining the high-value point segment sequences, the computing device searches for segment sequences corresponding to the time period of the adjacent traceability point based on the time period corresponding to the high-value point segment sequences. By comparing and logically reasoning the SO2 concentration prediction data in each of the aforementioned segment sequences, it can be determined that the high-value points are not caused by the diffusion of pollutants. These high-value points can then be used as predicted SO2 discharge points exceeding the standard.

[0070] In specific implementation, the computing equipment can compare the excessive pollution discharge data near the traceability point based on predetermined comparison logic rules (this comparison logic rule is determined based on the diffusion mechanism of pollutants under meteorological factors) and meteorological data to determine the predicted SO2 excessive pollution discharge point.

[0071] The SO2 emission source tracing method provided by the disclosed embodiments utilizes SO2 concentration monitoring data from multiple monitoring points and meteorological data from the control area to perform a reverse diffusion simulation. After determining the predicted SO2 concentration data for each traceability point at different times, a SO2 concentration prediction sequence for each traceability point is constructed. Based on the basic premise that pollutants are either diffused or emitted within the traceability point, the SO2 concentration prediction sequence for each traceability point and the proximity of the traceability points can be used to determine the predicted SO2 emission points exceeding the standard according to predetermined logical judgment rules.

[0072] Based on the SO2 emission source tracing method provided by the embodiments of the present disclosure, it is possible to more accurately screen and identify reliable predicted SO2 emission points exceeding the standard. Subsequently, targeted investigations can be conducted on these predicted SO2 emission points to identify the enterprises that exceed the standard.

[0073] The above scheme is to perform reverse diffusion simulation according to the pollutant diffusion mechanism based on the SO2 concentration monitoring data and meteorological data. It assumes that the control area is an ideal plane area or an approximately plane area, that is, it assumes that the control area is a plain area or a plateau area. However, in actual situations, the control area may not be the aforementioned ideal plane area or approximately plane area. The topographical features of the control area will affect the diffusion of pollutants. In addition, it may also affect the wind speed and wind direction of the local area (that is, it will affect the meteorological parameters). For this reason, in some embodiments, while executing the above S110, the computing device will also obtain the terrain feature data within the control area. Accordingly, when the terrain feature data within the control area is obtained, the above S120 is specifically: based on the SO2 concentration monitoring data, meteorological data and terrain feature data, a reverse diffusion simulation is performed according to the pollutant diffusion mechanism to determine the diffusion path corresponding to each SO2 concentration monitoring data.

[0074] In actual applications, identifying the predicted SO2 emission points that exceed the standard is not the goal; rather, screening the enterprises at these predicted SO2 emission points and predicting the SO2 emission points is the goal. To this end, after executing S140 , the enterprises within the predicted SO2 emission points must be screened to identify the predicted SO2 emission points.

[0075] In some embodiments of the present disclosure, a real-time online monitoring system is installed in the pollutant-discharging enterprise to monitor the concentration of pollutants discharged. Accordingly, after executing the aforementioned S140, the computing device may further execute the following S150.

[0076] S150: Based on the SO2 emission concentration monitoring sequence and SO2 concentration prediction sequence of each pollutant-discharging enterprise, determine the SO2 emission enterprises predicted to exceed the standard.

[0077] In specific implementation, after determining the SO2 emission concentration monitoring sequence and SO2 concentration prediction sequence of each pollutant-discharging enterprise, it is possible to determine which pollutant-discharging enterprises have a higher correlation between their emission concentration monitoring sequence and SO2 concentration prediction sequence by mutual comparison, and use the pollutant-discharging enterprises with higher correlation as the predicted SO2 exceeding emission standards enterprises.

[0078] FIG2 is a flowchart of determining enterprises that discharge pollutants exceeding the standard according to some embodiments of the present disclosure. As shown in FIG2 , in some embodiments of the present disclosure, a computing device may use the following steps S151-S154 to determine and predict enterprises that discharge SO2 pollutants exceeding the standard.

[0079] S151: Process the SO2 emission concentration monitoring sequence of each pollutant-discharging enterprise and determine the corresponding monitoring change trend.

[0080] In a specific implementation, the computing device can perform derivative operations on adjacent data in the SO2 emission concentration monitoring sequence of each pollutant-discharging enterprise to determine the first-order derivative and / or second-order derivative, and then sort the aforementioned first-order derivatives or sort the second-order derivatives by time stamp to determine the corresponding monitoring change trend. The first-order monitoring change trend constructed using the first-order derivative represents the rate of change of the pollutant emission concentration of the pollutant-discharging enterprise, and the second-order derivative represents the degree of change in the pollutant emission change rate of the pollutant-discharging enterprise.

[0081] S152: Process the SO2 concentration prediction sequence corresponding to the predicted SO2 exceeding emission point, and determine the corresponding prediction change trend.

[0082] The computing device may process the SO2 concentration prediction sequence using the aforementioned method for processing the SO2 exhaust concentration monitoring sequence to determine the corresponding predicted change trend.

[0083] In actual implementation, in order to simplify subsequent comparisons, the monitoring change trends determined in the previous text through first-order derivatives, second-order derivatives and other methods can be simply normalized to obtain normalized monitoring change trends and predicted change trends, and the normalized monitoring change trends and predicted change trends can be subsequently compared.

[0084] S153: Compare the monitored change trend and the predicted change trend to determine whether there is a target monitored change trend that is at least partially identical to the predicted change trend; if so, execute S154.

[0085] S154: The polluting enterprises corresponding to the target monitoring change trend are used as the predicted SO2 exceeding emission standards enterprises.

[0086] When comparing the monitored and predicted trends, a segment of the predicted trend sequence can be extracted and compared with the corresponding time period data in the monitored trend. Alternatively, a sliding window method can be used to compare the segment with the monitored trend sequence to determine whether there is a segment in the monitored trend sequence that is identical or similar to the aforementioned segment. If such a segment is found, the corresponding monitored trend sequence is determined as the target monitored trend sequence, and the pollutant-discharging enterprise corresponding to the target monitored trend is identified as the enterprise predicted to exceed the SO2 standard.

[0087] By using the aforementioned steps S151-S154 to calculate the monitored and predicted trends, the impact of non-changing pollutant emissions on the data is eliminated, making it easier to identify and predict enterprises that exceed SO2 emission standards. In practice, the aforementioned method can more accurately identify enterprises that exceed emission standards when there is only one enterprise at a location with excessive emission standards, or when the emission trends of multiple enterprises are consistent.

[0088] Figure 3 This is a flow chart of determining enterprises that discharge pollutants exceeding the standards in accordance with other embodiments of the present disclosure. Figure 3 As shown, in some embodiments of the present disclosure, the computing device may use the following S155-S159 to determine and predict the SO2 pollution-exceeding enterprises.

[0089] S155: Based on the SO2 emission concentration monitoring sequence of each pollutant-discharging enterprise, a weighted summation of multiple weights is performed to obtain multiple combined concentration prediction sequences.

[0090] In practice, it's possible that multiple pollutants are located at a site with excessive discharge standards, and their emissions may fluctuate randomly, without any correlation between them. Therefore, the aforementioned method cannot accurately predict the SO2-exceeding pollutant based on the SO2 concentration monitoring series for each pollutant. Furthermore, the amount of pollutants discharged per unit time may vary from pollutant to pollutant, which could affect the prediction of SO2-exceeding pollutants.

[0091] To solve this problem, the embodiment of the present disclosure considers that the SO2 emission concentration monitoring series of each polluting enterprise can be processed by weighted summation of multiple weights to obtain multiple combined concentration prediction sequences. The weight coefficients used in the aforementioned weighted summation can be determined based on empirical data such as the production characteristics of each enterprise and the amount of pollution discharged by each enterprise, or they can be determined by mining historical data using machine learning methods. By setting reasonable weight coefficients, or setting a large number of weight coefficient combinations, some or a certain combined concentration sequence obtained may characterize the changes in pollution concentration at the pollution discharge points exceeding the standard caused by pollution discharge by multiple enterprises.

[0092] S156: Process each combined concentration prediction sequence to determine the corresponding combined change trend; and process the SO2 concentration prediction sequence corresponding to the predicted SO2 exceeding discharge point to determine the corresponding prediction change trend.

[0093] The execution process of S156 is the same as that of S151-S152 above, and will not be repeated here. For details, please refer to the above description.

[0094] S157: Select a target monitoring change trend that is at least partially identical to the predicted change trend from the combined change trend, and determine the corresponding ranked enterprise with the highest weight based on the target monitoring change trend.

[0095] S158: The pollutant-emitting enterprises with the highest weights are used as the predicted SO2 pollutant-emitting enterprises exceeding the standard.

[0096] When comparing the combined monitoring trend with the predicted trend, a segment of the trend sequence can be extracted from the predicted trend and compared with the corresponding time period data in the combined trend. Alternatively, a sliding window method can be used to compare the segment with the combined trend to determine whether the combined trend contains a segment that is identical or similar to the aforementioned trend sequence. If such a segment is found, the corresponding combined trend is determined as the target combined trend. Because the trends of polluting enterprises with higher weights in the target combined trend have a greater impact on the combined trend, they are more likely to be exceeding the standard and are therefore used as the predicted SO2 exceeding standard enterprises.

[0097] By adopting the aforementioned S151-S154 or S155-S158, even if the SO2 emission concentration monitoring sequence of the pollutant-emitting enterprise is inaccurate or falsified, it is possible to determine and predict the SO2 exceeding the standard pollutant-emitting enterprise through data reasoning.

[0098] The aforementioned solution does not restrict the target time period. In practical applications, following this approach may result in a significant waste of computing resources, and the resulting predicted SO2 discharge points and polluting enterprises exceeding the standard are of little practical application. Therefore, in some embodiments, the following steps S160-S170 may be performed before executing S110.

[0099] S160: Determine whether the SO2 concentration monitoring data at the first monitoring point at the first time point triggers a high value alarm.

[0100] In a specific implementation, the computing device can communicate with the monitoring equipment at each monitoring point and receive SO2 concentration monitoring data from each monitoring point in real time. After receiving the SO2 concentration monitoring data, the computing device will determine whether the SO2 concentration monitoring data triggers a high-level alarm based on the high-level alarm rules of the corresponding monitoring device. In the disclosed embodiment, if a high-level alarm is triggered based on the SO2 concentration monitoring data at a particular monitoring point, the corresponding monitoring point will be designated as the first monitoring point.

[0101] In a specific implementation, the computing device may determine whether the pollutant concentration at the first monitoring point triggers a high value alarm using the following method.

[0102] (1) The SO2 concentration monitoring data at the first monitoring point at the first time exceeds the set comparison threshold. In specific implementation, the comparison threshold can be reasonably set according to national standards, industry standards or local standards of the control area. For example, if the SO2 concentration in a certain place reaches 150 micrograms per cubic meter, it is determined that a high value alarm is triggered.

[0103] (2) The ratio of the SO2 concentration monitoring data at the first monitoring point at the first time point to the SO2 concentration monitoring data at the previous time point is greater than a preset ratio, and the preset ratio is at least greater than 1. In actual situations, the SO2 concentration monitoring data in a certain area will remain within a certain numerical range, and there will be no sudden increase. If a sudden increase occurs, it is most likely caused by excessive emissions. Based on this, the embodiment of the present disclosure can set an abnormal sudden increase multiple greater than 1. If the ratio of the SO2 concentration monitoring data collected at the first time point to the average value of the SO2 concentration monitoring data in the previous period is greater than the abnormal sudden increase multiple, a high value alarm is triggered. In some applications, the abnormal sudden increase multiple is set at 1.5.

[0104] (3) The ranking of the SO2 concentration monitoring data of the first monitoring point at the first moment is higher than the ranking of the SO2 concentration monitoring data at the previous moment by a set change ranking. The ranking mentioned here refers to the ranking of the SO2 concentration monitoring data of the monitoring points within the monitoring area. Under normal circumstances, the SO2 concentration monitoring data of each monitoring point is basically stable, and the corresponding ranking will not change. However, if the ranking of the SO2 concentration monitoring data of the first monitoring point suddenly rises by several places (that is, the ranking deteriorates), the SO2 concentration monitoring data of the first monitoring point is likely to be abnormal. Accordingly, a high value alarm can be triggered. For example, in some embodiments, if the pollution discharge ranking of the SO2 concentration monitoring data of the first monitoring point deteriorates by five places, a high value alarm is triggered.

[0105] (4) The difference between the SO2 concentration monitoring data of the first monitoring point at the first time point and the average value of the SO2 concentration monitoring data of the adjacent points is greater than the set outlier threshold.

[0106] Under certain environmental conditions, the SO2 concentration data from various monitoring points is distributed within a region, conforming to a normal or specific distribution. However, if the SO2 concentration data from a first monitoring station is significantly higher than that from other monitoring stations—specifically, if the SO2 concentration data from the first monitoring station is significantly higher than the average SO2 concentration data for all other monitoring stations, thus significantly exceeding the set outlier threshold—then the SO2 concentration data from the first monitoring station can be considered abnormal, triggering a high-value alert.

[0107] S170: Determine whether to trigger a high-value alarm, and determine a target time period based on the first time point and a preset duration.

[0108] After determining that a high value alarm is triggered, the first time point and the predetermined preset duration can be used to determine the target period. Specifically, the first time point can be used as the end time point or the middle time point of the target period, and the target period can be determined based on the preset duration.

[0109] In some other embodiments, the computing device does not determine the target time period according to the aforementioned method, but instead determines the target time period by analyzing historical data and performing a high-value analysis on the historical SO2 concentration monitoring data of multiple target monitoring points. For example, some polluting enterprises may have obvious time characteristics when exceeding the pollution discharge standard, such as possibly exceeding the pollution discharge standard during the midnight period. By analyzing the historical SO2 concentration monitoring data of multiple target monitoring points, the time pattern of the occurrence of high-value data is found, and the target time period is determined. For example, if it is found that certain monitoring points have high-value pollutant data for a long time at night between 20:00 and 23:00, the target time period can be determined to be 20:00-23:00.

[0110] As mentioned previously, it's necessary to obtain SO2 concentration data from monitoring points or pollutant discharge concentration data from polluting enterprises. In practical applications, after receiving this data, the computing device will clean and preprocess it, eliminating invalid data caused by the monitoring equipment itself, maintenance operations, or environmental factors to ensure data availability. In specific implementations, consideration should be given to excluding zero and negative values, out-of-range data, continuous and constant data (which is likely falsified), and abnormally high-increase data (specifically, this can be achieved using second-order differencing to eliminate data with significantly excessive second-order rate of change).

[0111] The process of using this method to identify excessive discharge points and predict SO2-exceeding enterprises generates a large amount of data, including both abnormally high-value and normal data. This data can be collated to form a database of typical high-value values for subsequent data analysis. High-value screening rules can then be optimized based on the data analysis characteristics of this database. Furthermore, this data can be used to construct high-value identification and source tracing reports, providing recommendations to administrative departments for pollution control.

[0112] In addition to providing the aforementioned SO2 emission tracing method, the embodiment of the present disclosure also provides a SO2 emission tracing device. Figure 4 Schematic diagram of the SO2 emission tracing device provided by the embodiment of the present disclosure. Figure 4 As shown, the SO2 emission source tracing device 400 includes a data acquisition unit 401, a numerical analysis unit 402, a sequence construction unit 403 and a screening unit 404.

[0113] The data acquisition unit 401 is used to obtain SO2 concentration monitoring data of multiple monitoring points within the target period and meteorological data within the control area. The SO2 concentration monitoring data and meteorological data both have time stamps, and the control area includes traceability points.

[0114] The numerical analysis unit 402 is used to perform reverse diffusion simulation based on the SO2 concentration monitoring data and meteorological data according to the pollutant diffusion mechanism, determine the diffusion path corresponding to each SO2 concentration monitoring data, and the SO2 concentration prediction data of the traceability point on the diffusion path; each SO2 concentration prediction data also has a time mark.

[0115] The sequence construction unit 403 is used to sort the SO2 concentration prediction data corresponding to each tracing point according to the time identifier to determine the SO2 concentration prediction sequence.

[0116] The screening unit 404 is used to determine the predicted SO2 discharge points exceeding the standard based on the SO2 concentration prediction sequence of each tracing point and the proximity relationship of each tracing point.

[0117] In some instances, data acquisition unit 401 also acquires terrain data within the control area. Accordingly, numerical analysis unit 402 performs reverse diffusion simulation based on the SO2 concentration monitoring data, meteorological data, and terrain data according to the pollutant diffusion mechanism to determine the diffusion path corresponding to each SO2 concentration monitoring data.

[0118] In some embodiments, the data acquisition unit 401 also acquires the SO2 emission concentration monitoring sequence of the pollutant-discharging enterprises at each traceability point. Accordingly, the screening unit 404 determines the enterprises predicted to exceed the SO2 emission standard based on the SO2 emission concentration monitoring sequence and SO2 concentration prediction sequence of each pollutant-discharging enterprise.

[0119] In some embodiments, the screening unit 404 processes the SO2 emission concentration monitoring sequence of each pollutant-discharging enterprise to determine the corresponding monitoring change trend; and processes the SO2 concentration prediction sequence corresponding to the predicted SO2 exceeding emission point to determine the corresponding prediction change trend; selects a target monitoring change trend that is at least partially identical to the prediction change trend from the monitoring change trend, and uses the pollutant-discharging enterprise corresponding to the target monitoring change trend as the predicted SO2 exceeding emission enterprise.

[0120] In some embodiments, the screening unit 404 performs a weighted summation of multiple weights based on the SO2 emission concentration monitoring sequence of each pollutant discharge enterprise to obtain multiple combined concentration prediction sequences; processes each combined concentration prediction sequence to determine the corresponding combined change trend; and processes the SO2 concentration prediction sequence corresponding to the predicted SO2 exceeding the standard emission point to determine the corresponding predicted change trend; selects a target combined change trend that is at least partially identical to the predicted change trend from the combined change trend, and determines the corresponding pollutant discharge enterprise with a higher weight based on the target combined change trend; and uses the pollutant discharge enterprise with a higher weight as the predicted SO2 exceeding the standard emission enterprise.

[0121] In some embodiments, before obtaining the SO2 concentration monitoring data of multiple monitoring points within the target time period and the meteorological data within the control area, the data acquisition unit 401 determines whether the SO2 concentration monitoring data of the first monitoring point at the first time point triggers a high value alarm; determines whether the high value alarm is triggered, and determines the target time period based on the first time point and the preset time length; the first monitoring point is at least one monitoring point among the multiple monitoring points.

[0122] In some embodiments, the data acquisition unit 401 determines that a high value alarm is triggered in response to the SO2 concentration monitoring data of the first monitoring point at the first time point meeting at least one of the following conditions: the SO2 concentration monitoring data of the first monitoring point at the first time point exceeds a set comparison threshold; the ratio of the SO2 concentration monitoring data of the first monitoring point at the first time point to the SO2 concentration monitoring data at the previous time point is greater than a preset ratio, and the preset ratio is at least greater than 1; the ranking position of the SO2 concentration monitoring data of the first monitoring point at the first time point is higher than the ranking position of the SO2 concentration monitoring data at the previous time point by a set change position; the difference between the SO2 concentration monitoring data of the first monitoring point at the first time point and the average value of the SO2 concentration monitoring data of the adjacent points is greater than a set outlier threshold.

[0123] In some embodiments, after inspecting the predicted SO2 discharge point to determine that it exceeds the discharge standard, the method further includes: using the SO2 concentration monitoring data when the first monitoring point triggers a high-value alarm as high-value alarm triggering data.

[0124] In some embodiments, before acquiring the SO2 concentration monitoring data of multiple monitoring points within the target period and the meteorological data within the control area, the data acquisition unit 401 analyzes the historical SO2 concentration monitoring data of the multiple target monitoring points to determine the target period.

[0125] The embodiment of the present disclosure also provides a computing device for implementing the aforementioned method. Figure 5 This is a schematic diagram of the structure of the computing device provided by the embodiment of the present disclosure. Figure 5 , which shows a structural diagram of a computing device 500 suitable for implementing the embodiments of the present disclosure. Figure 5 The computing device shown is only an example and should not bring any limitation to the functionality and scope of use of the embodiments of the present disclosure.

[0126] like Figure 5 As shown, computing device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. RAM 503 also stores various programs and data required for the operation of computing device 500. Processing device 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to bus 504.

[0127] Typically, the following devices may be connected to the I / O interface 505: an input device 505 including, for example, a touch screen, a touchpad, a camera, a microphone, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the computing device 500 to communicate with other devices wirelessly or by wire to exchange data. Figure 5 The computing device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0128] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0129] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable storage medium, a computer-readable signal medium, or any combination of the above two.

[0130] Computer-readable storage media may be, for example, but not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0131] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, embodying computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wire, optical cable, RF (radio frequency), or any suitable combination thereof.

[0132] In some embodiments, the client and computing devices may communicate using any currently known or later developed network protocol, such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or later developed network.

[0133] The computer-readable medium may be included in the computing device, or may exist independently without being incorporated into the computing device.

[0134] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the tester computer, partially on the tester computer, as a stand-alone software package, partially on the tester computer and partially on a remote computer, or entirely on a remote computer or computing device. In cases involving a remote computer, the remote computer may be connected to the tester computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0135] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0136] The units involved in the embodiments described in the present disclosure may be implemented in software or in hardware. The name of a unit does not, in some cases, limit the unit itself. The functions described above in this document may be at least partially performed by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0137] The foregoing are merely specific embodiments of the present disclosure, intended to enable those skilled in the art to understand and implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure is not to be limited to the embodiments described herein, but is to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for tracing the source of SO2 emissions, characterized in that: include: Obtain SO2 concentration monitoring data from multiple monitoring points within the target period and meteorological data within the control area, as well as SO2 emission concentration monitoring sequences for pollutant-discharging enterprises within each traceability point; the SO2 concentration monitoring data and meteorological data are both time-stamped, and the control area includes the traceability point; Based on the SO2 concentration monitoring data and the meteorological data, reverse diffusion simulation is performed according to the pollutant diffusion mechanism to determine the diffusion path corresponding to each SO2 concentration monitoring data and the SO2 concentration prediction data of the traceability point on the diffusion path; each SO2 concentration prediction data also has a time stamp; The SO2 concentration prediction data corresponding to each traceability point are sorted according to the time stamp to determine the SO2 concentration prediction sequence; Based on the SO2 concentration prediction sequence of each tracing point and the proximity relationship of each tracing point, the predicted SO2 discharge point exceeding the standard is determined; Determining enterprises predicted to discharge SO2 exceeding the standard based on the SO2 emission concentration monitoring sequences of each pollutant-discharging enterprise and the SO2 concentration prediction sequence, including: performing a weighted summation of multiple weights based on the SO2 emission concentration monitoring sequences of each pollutant-discharging enterprise to obtain multiple combined concentration prediction sequences; processing each of the combined concentration prediction sequences to determine a corresponding combined change trend; and processing the SO2 concentration prediction sequences corresponding to the predicted SO2 emission points exceeding the standard to determine a corresponding predicted change trend; A target combination change trend that is at least partially identical to the predicted change trend is selected from the combination change trend, and the corresponding pollutant-emitting enterprises with the highest weights are determined based on the target combination change trend; the pollutant-emitting enterprises with the highest weights are used as the predicted SO2 exceeding standard pollutant-emitting enterprises.

2. The method according to claim 1, characterized in that The method further includes obtaining terrain feature data within the controlled area; The reverse diffusion simulation is performed based on the SO2 concentration monitoring data and the meteorological data according to the pollutant diffusion mechanism to determine the diffusion path corresponding to each SO2 concentration monitoring data, including: Based on the SO2 concentration monitoring data, the meteorological data and the terrain feature data, a reverse diffusion simulation is performed according to the pollutant diffusion mechanism to determine the diffusion path corresponding to each SO2 concentration monitoring data.

3. The method according to claim 1 or 2, characterized in that The step of determining and predicting SO2-exceeding pollutant-discharging enterprises based on the SO2 concentration monitoring sequence of each pollutant-discharging enterprise and the SO2 concentration prediction sequence includes: Process the SO2 emission concentration monitoring sequence of each pollutant-discharging enterprise and determine the corresponding monitoring change trend; and process the SO2 concentration prediction sequence corresponding to the predicted SO2 exceeding emission points and determine the corresponding prediction change trend; A target monitoring change trend that is at least partially identical to the predicted change trend is selected from the monitoring change trend, and the pollutant-discharging enterprise corresponding to the target monitoring change trend is used as the predicted SO2 excessive pollutant-discharging enterprise.

4. The method according to claim 1 or 2, characterized in that Before obtaining SO2 concentration monitoring data of multiple monitoring points within the target period and meteorological data within the control area, the method further includes: Determine whether the SO2 concentration monitoring data at the first monitoring point at the first time triggers a high value alarm; Determine whether to trigger a high-value alarm, and determine the target time period based on the first time point and a preset duration; the first monitoring point is at least one monitoring point among the multiple monitoring points.

5. The method according to claim 4, characterized in that The determining whether the SO2 concentration monitoring data at the first monitoring point at the first time triggers a high value alarm includes: In response to the SO2 concentration monitoring data at the first monitoring point at the first time point satisfying at least one of the following conditions, it is determined that a high value alarm is triggered: The SO2 concentration monitoring data at the first monitoring point at the first time exceeds the set comparison threshold; The ratio of the SO2 concentration monitoring data at the first monitoring point at the first time to the SO2 concentration monitoring data at the previous time is greater than a preset ratio, and the preset ratio is at least greater than 1; The ranking of the SO2 concentration monitoring data of the first monitoring point at the first time point and the ranking of the SO2 concentration monitoring data at the previous time point are higher than the set change ranking; The difference between the SO2 concentration monitoring data of the first monitoring point at the first time point and the average value of the SO2 concentration monitoring data of the adjacent points is greater than the set outlier threshold.

6. The method according to claim 5, characterized in that After inspecting the predicted SO2 discharge exceeding the standard and confirming that the discharge exceeds the standard, the method further includes: The SO2 concentration monitoring data when the first monitoring point triggers a high value alarm is used as high value alarm triggering data.

7. The method according to claim 1 or 2, characterized in that: Before obtaining SO2 concentration monitoring data of multiple monitoring points within the target period and meteorological data within the control area, the method further includes: The historical SO2 concentration monitoring data of multiple target monitoring points are analyzed to determine the target time period.

8. A computing device, characterized in that It includes a processor and a memory, the memory is used to store a computer program; when the computer program is loaded by the processor, the processor executes the SO2 emission tracing method as described in any one of claims 1 to 7.

Images