Method, device and equipment for analyzing causes of atmospheric pollution and storage medium

Abstract

This invention relates to the field of environmental monitoring technology and discloses a method, apparatus, equipment, and storage medium for analyzing the causes of air pollution. The method includes receiving user instructions and determining a target area; acquiring real-time monitoring data of the target area and combining it with a historical database to generate a relevant dataset for the target area; performing data analysis on the relevant dataset based on transmission process, feature type, and feature source, and displaying the corresponding analysis results in chart form; filtering the analysis results for feature correlation to obtain relevant feature data, and generating predicted emission reduction information based on the relevant feature data; and combining the analysis results with the predicted emission reduction information to generate an air pollution cause analysis report for the target area. Because this invention combines real-time and historical data and outputs the analysis results in an intuitive chart form according to user selection criteria, users can conveniently and quickly obtain information on the causes of air pollution in the target area.

Description

Technical Field

[0001] This invention relates to the field of environmental monitoring technology, and in particular to a method, apparatus, equipment, and storage medium for analyzing the causes of air pollution. Background Technology

[0002] Currently, with the development of science and technology, air pollution problems are becoming increasingly prominent. Existing analyses of the causes of air pollution are mainly based on monitoring data from different stations. However, due to the numerous sources of relevant detection data from air quality stations, meteorological stations, and superstations, which are characterized by complex structures and long time spans, data analysis is computationally complex and time-consuming, failing to meet users' needs for timely, accurate, and intuitive access to information on the causes of air pollution in a particular region.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is related technology. Summary of the Invention

[0004] The main objective of this invention is to provide a method, apparatus, device, and storage medium for analyzing the causes of air pollution, aiming to solve the technical problem that when performing regional air pollution analysis tasks, the wide range and diverse types of data sources lead to complex analytical conclusions, making it difficult for users to quickly and accurately understand the causes of air pollution in the target area.

[0005] To achieve the above objectives, the present invention provides a method for analyzing the causes of air pollution, the method comprising the following steps:

[0006] Receive user instructions and determine the target area;

[0007] Real-time monitoring data of the target area is acquired and combined with historical databases to generate a relevant dataset for the target area;

[0008] Data analysis based on transmission process, feature type, and feature source is performed on the relevant datasets, and the corresponding analysis results are displayed in chart form.

[0009] The analysis results are filtered for feature correlation to obtain relevant feature data, and predicted emission reduction information is generated based on the relevant feature data.

[0010] The analysis results are combined with the predicted emission reduction information to generate an air pollution cause analysis report for the target area.

[0011] Optionally, the step of performing data analysis on the relevant datasets based on the transmission process, feature type, and feature source, and displaying the corresponding analysis results in chart form, includes:

[0012] In the relevant dataset, a preset algorithm is used to determine whether regional transmission occurs in the target area, and analysis results based on regional transmission are obtained.

[0013] The relevant datasets are classified according to the categories of characteristic pollutants to generate regional feature tables for the corresponding feature categories;

[0014] Extract VOC data from the relevant dataset and obtain the target VOC types; then match the source information of the target region based on the target VOC types.

[0015] The analysis results based on regional transmission, the regional feature set, and the source information are visualized.

[0016] Optionally, the step of extracting VOC data from the relevant dataset and obtaining the target VOC type, and matching the source information of the target region based on the target VOC type, includes:

[0017] Obtain the concentration data of VOC component factors and VOC-related factors in the relevant dataset, determine the correlation between each VOC-related factor and the VOC component factors, and generate a correlation table.

[0018] Select the VOC component factor located at a preset position in the correlation table as the target VOC factor;

[0019] The pollution sources in the target area are obtained by matching the target VOC factor, and the source information is obtained.

[0020] Optionally, the step of performing feature correlation screening on the analysis results to obtain relevant feature data, and generating predicted emission reduction information based on the relevant feature data, includes:

[0021] Based on a first preset time period, obtain VOC data within the first preset time period;

[0022] Extract the active VOC factor from the VOC data, and obtain predicted emission reduction information based on the active VOC factor and the target VOC factor.

[0023] Optionally, the step of using a preset algorithm to determine whether regional transmission exists in the target region within the relevant dataset, and obtaining analysis results based on regional transmission, includes:

[0024] Extract regional historical data from the relevant dataset to determine the background value range;

[0025] A preset algorithm is used to obtain the current reference mean based on real-time monitoring data, and the current reference mean is compared with the background value range;

[0026] Based on the comparison results, determine whether there is regional transmission phenomenon in the target area, and obtain the analysis results based on regional transmission.

[0027] Optionally, the step of classifying the relevant dataset according to the category of characteristic pollutants to generate a regional feature table set corresponding to the feature categories includes:

[0028] The relevant datasets are classified according to the characteristic pollutant categories to obtain routine monitoring data and VOC component data.

[0029] Based on the conventional monitoring data, generate meteorological analysis maps, pollutant change characteristic maps, and station analysis maps for the target area;

[0030] Based on the second preset time period, a VOC component change trend table is generated according to the VOC component data.

[0031] Optionally, the step of acquiring real-time monitoring data of the target area and combining it with a historical database to generate a relevant dataset for the target area includes:

[0032] Based on a preset template, the real-time monitoring data of the target area is standardized with the historical database to obtain an initial dataset;

[0033] Data cleaning by anomaly screening of the initial dataset is performed to obtain the relevant dataset for the target region.

[0034] Furthermore, to achieve the above objectives, the present invention also proposes an air pollution cause analysis device, the device comprising:

[0035] The region determination module is used to receive user instructions and determine the target region;

[0036] The data management module is used to acquire real-time monitoring data of the target area and combine it with a historical database to generate a relevant dataset for the target area.

[0037] The chart display module is used to perform data analysis on the relevant datasets based on the transmission process, feature type, and feature source, and to display the corresponding analysis results in chart form.

[0038] The effect evaluation module is used to filter the feature correlation of the analysis results, obtain relevant feature data, and generate predicted emission reduction information based on the relevant feature data;

[0039] The cause report module is used to combine the analysis results with the predicted emission reduction information to generate an air pollution cause analysis report for the target area.

[0040] Furthermore, to achieve the above objectives, the present invention also proposes an air pollution cause analysis device, the device comprising: a memory, a processor, and an air pollution cause analysis program stored in the memory and executable on the processor, the air pollution cause analysis program being configured to implement the steps of the air pollution cause analysis method as described above.

[0041] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium storing an air pollution cause analysis program, which, when executed by a processor, implements the steps of the air pollution cause analysis method as described above.

[0042] This invention first receives user instructions to determine the target area; then, it acquires real-time monitoring data of the target area and combines it with a historical database to generate a relevant dataset for the target area; next, it performs data analysis on the relevant dataset based on transmission process, feature type, and feature source, and displays the corresponding analysis results in chart form; furthermore, it filters the analysis results for feature correlation to obtain relevant feature data, and generates predicted emission reduction information based on the relevant feature data; finally, it combines the analysis results with the predicted emission reduction information to generate an air pollution cause analysis report for the target area. Because this invention combines real-time and historical data as a dataset, it quickly outputs the required analytical statistics based on user selection criteria, displays them in an intuitive chart form, and provides a comprehensive regional analysis report. This improves the efficiency of data processing and statistics while enhancing data analysis capabilities, enabling users to conveniently and quickly obtain information on the causes of air pollution in the target area. Attached Figure Description

[0043] Figure 1 This is a schematic diagram of the structure of the atmospheric pollution cause analysis device for the hardware operating environment involved in the embodiments of the present invention;

[0044] Figure 2 This is a flowchart illustrating the first embodiment of the atmospheric pollution causation analysis method of the present invention;

[0045] Figure 3 This is a flowchart illustrating the second embodiment of the atmospheric pollution causation analysis method of the present invention;

[0046] Figure 4 This is a table showing the correlation between each VOC component factor and VOC-related factors in the second embodiment of the atmospheric pollution causation analysis method of the present invention;

[0047] Figure 5 This is a flowchart illustrating the third embodiment of the atmospheric pollution causation analysis method of the present invention;

[0048] Figure 6This is a schematic diagram of the atmospheric pollution causation analysis method based on regional transport, pollution characteristics, and pollution source categories in the third embodiment of the present invention.

[0049] Figure 7 This is a structural block diagram of the first embodiment of the atmospheric pollution cause analysis device of the present invention.

[0050] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0051] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0052] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of the air pollution cause analysis equipment in the hardware operating environment involved in the embodiments of the present invention.

[0053] like Figure 1 As shown, the air pollution cause analysis device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk storage device. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0054] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the equipment for analyzing the causes of air pollution, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0055] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and an air pollution cause analysis program.

[0056] exist Figure 1 In the air pollution cause analysis device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the air pollution cause analysis device of the present invention can be set in the air pollution cause analysis device, and the air pollution cause analysis device calls the air pollution cause analysis program stored in the memory 1005 through the processor 1001 and executes the air pollution cause analysis method provided in the embodiment of the present invention.

[0057] This invention provides a method for analyzing the causes of air pollution, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the atmospheric pollution causation analysis method of the present invention.

[0058] In this embodiment, the method for analyzing the causes of air pollution includes the following steps:

[0059] Step S10: Receive user instructions and determine the target area.

[0060] It should be noted that the executing entity of the method in this embodiment can be a computer service device with screen display, data processing, network communication, and program execution functions, such as a mobile phone, tablet computer, personal computer, air analyzer, air pollution detection device, etc., or other electronic devices that can achieve the same or similar functions and implement the air pollution cause analysis method. This embodiment does not limit this. Here, an air pollution cause analysis device (hereinafter referred to as the analysis device) is selected as an example to illustrate various embodiments of the air pollution cause analysis method of the present invention.

[0061] It is understandable that the user command can be an operation command triggered by the user on the display interface of the current analysis device. On the display interface, the user can select the target area for which information on the causes of air pollution needs to be obtained and set the time range.

[0062] It should be understood that the target area can be selected based on provinces or cities divided by administrative regions, or it can be further located to a specific region based on the administrative division. This embodiment does not limit this.

[0063] Step S20: Obtain real-time monitoring data of the target area and combine it with the historical database to generate a relevant dataset of the target area.

[0064] It is understandable that the real-time monitoring data for the target area can be obtained from atmospheric monitoring data stations of different levels or different pollution categories, such as urban stations, meteorological stations, and super stations. These data from different sources can be correlated through the city, district, or county to which the stations belong, or directly through geographical location based on latitude and longitude, and then linked to the corresponding air quality stations in the target area. Monitoring data obtained from urban stations may include, but is not limited to, common air pollutants such as SO2, NO2, PM10, PM2.5, CO, and O3; monitoring data obtained from meteorological stations may include, but is not limited to, temperature, humidity, air pressure, wind speed, and wind direction; and monitoring data obtained from super stations may include volatile organic compound (VOC) composition data.

[0065] It should be noted that when obtaining real-time monitoring data from various sites, historical data from recent years can also be obtained. By combining real-time monitoring data with historical databases, a richer and more reliable dataset of relevant data for the target area can be obtained and stored in a data warehouse for direct retrieval when conducting regional analysis of other areas related to the current target area.

[0066] Furthermore, considering the diversity of data sources, the analysis of multi-source data is time-consuming. Therefore, the acquired multi-source data can be cleaned and standardized. Step S20 includes:

[0067] Step S201: Based on a preset template, standardize the real-time monitoring data of the target area with the historical database to obtain an initial dataset.

[0068] Understandably, this preset template can be a uniform table template. When importing multi-source data, the data is first standardized using this preset template, which can classify different data based on their source and type for further processing.

[0069] Step S202: Perform anomaly filtering and data cleaning on the initial dataset to obtain the relevant dataset for the target region.

[0070] It should be understood that after receiving the standardized initial dataset, the dataset can be sorted to remove duplicate data, abnormal data, and non-numeric data, thus achieving preliminary verification and quality control of the data, which facilitates further analysis and processing of the data.

[0071] Step S30: Perform data analysis on the relevant datasets based on the transmission process, feature type, and feature source, and display the corresponding analysis results in the form of charts.

[0072] It should be noted that analysis based on the transmission process can be an analysis of whether the pollution phenomenon in the target area is mainly due to regional transmission or local emissions; analysis based on the characteristics can be an analysis of different types of pollutants combined with time and climate characteristics; analysis based on the characteristics of the source can be a correlation analysis of pollution impact based on different types of pollutants, especially a correlation screening of VOCs components and matching them with corresponding pollution source industries.

[0073] Furthermore, considering that the analysis results obtained from different analyses of the dataset can be displayed in various forms, in order to facilitate users to obtain the analysis results more intuitively, step S30 includes:

[0074] Step S301: In the relevant dataset, a preset algorithm is used to determine whether there is a regional transmission phenomenon in the target area, and the analysis results based on regional transmission are obtained.

[0075] Understandably, data on specific pollutant types can be selected to determine whether regional transport exists in the target area, thereby determining whether pollution in the target area is mainly due to regional transport or local emissions. The pollutant types can be O3, xylene, SO2, etc., and a corresponding preset algorithm can be selected based on the selected pollutant types.

[0076] It should be noted that the preset algorithm can be the Texas Commission on Environmental Quality (TCEQ) method, the ozone background value method, and the characteristic pollutant method.

[0077] It should be understood that the TCEQ method is based on the background point measurement method. It can take the minimum value of the daily maximum eight-hour moving average of ozone related to O3 in the relevant dataset as the ozone transported from other regions, and the maximum average value of the daily maximum eight-hour moving average of ozone as the maximum ozone concentration in the region. The difference between the maximum and minimum values ​​of the daily maximum eight-hour moving average of ozone can obtain the local emission capacity of the current region, and thus determine whether the pollution in the target region is mainly due to regional transport or local emissions.

[0078] Understandably, the ozone background value method involves extracting historical ozone data from relevant datasets to calculate the ozone background value, comparing it with real-time monitored ozone data, and determining the contribution of regional transport and local emissions to pollution in the target area based on time. The characteristic pollutant ratio method can select hours or days as the smallest unit, statistically analyze the overall situation over a certain period, and set a standard ratio threshold to obtain the contribution of regional transport or local emissions to pollution in the target area. For example, if xylene or benzene is selected as the characteristic pollutant, then within a certain time period, if the xylene / benzene ratio is greater than 1.1, it can be considered that local emissions contribute significantly to pollution in the target area; if the xylene / benzene ratio is less than 1.1, it can be considered that regional transport contributes significantly to pollution in the target area.

[0079] Step S302: Classify the relevant dataset according to the category of characteristic pollutants to generate a regional feature table set corresponding to the feature categories.

[0080] Understandably, given the diverse sources and types of data in the dataset, different types of data can be analyzed from multiple dimensions, such as time, space, location, and climate, based on the essential characteristics of the pollutants corresponding to the data. This can generate various types of visualization charts, such as bar charts, tables, line charts, and even wind rose diagrams, to obtain a set of characteristic tables for the target region.

[0081] Step S303: Extract VOC data from the relevant dataset and obtain the target VOC type, and match the source information of the target region according to the target VOC type.

[0082] It is understandable that VOC data refers to data related to volatile organic compounds in relevant datasets. The target VOC types used to match pollutant sources can be determined by the correlation between each specific VOC component factor in the VOC data and other characteristic pollutants in the relevant datasets, such as ozone or nitrogen oxides, thereby matching the pollutant sources in the target area.

[0083] Understandably, a matching table between VOC types and pollutant sources can be pre-established. This table can contain mapping relationships between different VOC types and pollution source industries. The determination of these mapping relationships can be based on a summary of social experience values. For example, when the VOC type is formaldehyde, the corresponding pollution source industry for formaldehyde is the decoration industry.

[0084] Step S304: Visualize the analysis results based on regional transmission, the regional feature set, and the source information.

[0085] In practical implementation, the various types of analysis results obtained above can be indexed by tags such as transmission analysis, pollution characteristic analysis, and pollution source analysis. Under the corresponding tags, the analysis results based on regional transmission, the regional feature table, and the source information can be displayed respectively, so that users can obtain information on the causes of air pollution in the target area from multiple dimensions based on personalized selection.

[0086] Furthermore, to help users understand the changing trends of air pollution causes in a target area over a certain period of time, the daily air quality can be displayed in the form of an air calendar based on the user's pre-set time range. The display cells in the calendar, with the day as the smallest unit, can include the air quality level of the day, the type of air pollutant with the highest contribution, etc., so that users can intuitively understand the overall air pollution situation in the target area during the selected time period.

[0087] Furthermore, based on the generated air calendar and user-selected instructions, monitoring data from various stations in the relevant dataset can be extracted and combined with the Air Quality Index (AQI) levels to generate a ring chart of air quality level distribution, a ring chart of primary pollutants, a bar chart of changes in six common pollutants (SO2, NO2, PM10, PM2.5, CO, O3), and a bar chart of year-on-year changes for each station.

[0088] Step S40: Perform feature correlation screening on the analysis results to obtain relevant feature data, and generate predicted emission reduction information based on the relevant feature data.

[0089] It is understandable that when obtaining the multi-dimensional air pollution analysis data of the target area presented in different forms, the various pollutants constituting the air pollution of the target area can be correlated and screened to obtain the main pollutants of the target area that have a high contribution to the air pollution of the area. These may include the six common pollutants and the components of VOCs. The numerical data of the main characteristic pollutants of the target area can be obtained as the relevant characteristic data to determine the implementation effect of emission reduction measures for the main characteristic pollutants and generate predicted emission reduction information.

[0090] Step S50: Combine the analysis results with the predicted emission reduction information to generate an air pollution cause analysis report for the target area.

[0091] In practical implementation, the analysis equipment integrates the atmospheric pollution analysis data of the target area from the above-mentioned multi-dimensional perspectives with the implementation effect of the emission reduction measures currently adopted in the target area. It can obtain a detailed atmospheric pollution cause analysis report covering the analysis data and emission reduction information of the target area from various dimensions, and can also obtain a comprehensive analysis conclusion of the target area. The form of the comprehensive analysis conclusion can be, for example: In area A, during a selected time period, the main characteristic pollutant is ozone, and ozone exceeds the standard for a total of 4 days. Under the condition that the meteorological conditions do not change significantly, by precisely controlling the relevant pollution emission sources corresponding to the active species, when the emission reduction ratio is 100%, the ozone peak can theoretically be reduced for 4 days.

[0092] This embodiment first receives user instructions to determine the target area; then it acquires real-time monitoring data of the target area and combines it with a historical database to generate a relevant dataset for the target area; next, it performs data analysis on the relevant dataset based on transmission process, feature type, and feature source, and displays the corresponding analysis results in chart form; then, it filters the analysis results for feature correlation to obtain relevant feature data, and generates predicted emission reduction information based on the relevant feature data; finally, it combines the analysis results with the predicted emission reduction information to generate an air pollution cause analysis report for the target area. Because this embodiment combines real-time and historical data as a dataset, it quickly outputs the required analytical statistics based on user selection criteria, displays them in an intuitive chart form, and provides a comprehensive regional analysis report. This improves the efficiency of data processing and statistics while enhancing data analysis capabilities, enabling users to conveniently and quickly obtain information on the causes of air pollution in the target area.

[0093] refer to Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the atmospheric pollution causation analysis method of the present invention.

[0094] Based on the above embodiments, in order to conduct further analysis according to the source of pollution, step S303 includes:

[0095] Step S3031: Obtain the concentration data of VOC component factors and VOC-related factor concentration data in the relevant dataset, determine the correlation between each VOC-related factor and the VOC component factor, and generate a correlation table.

[0096] It is understandable that VOC component factors can include alkanes, alkenes, aromatic hydrocarbons, halogenated hydrocarbons, alkynes, natural sources, and others, while VOC-related factors can be ozone (O3) or nitrogen oxides (NO). x )wait.

[0097] Step S3032: Select the VOC component factor located at a preset position in the correlation table as the target VOC factor.

[0098] It should be noted that the factors of each VOC component and VOC-related factors (O3 and NO) can be obtained first. x The concentration data within the user-selected time period is grouped and the average concentration of each factor is calculated based on hourly data to determine the daily average concentration. Then, based on the above concentration data, the concentrations of each VOC component factor, O3, and NO are calculated separately. x The correlation R is used to screen out the highly correlated (|R|>0.5) components, obtain the correlation degree table, and further calculate the diurnal variation concentration difference of VOCs species for each VOC component factor.

[0099] It should be understood that, reference Figure 4 , Figure 4 This table shows the correlation between each VOC component factor and VOC-related factors. Figure 4 Table A shows the correlation between each VOC component factor and O3. Figure 4 In the text, B represents the specific VOC component factors and NO. x The correlation table was used to determine the VOC components that were highly correlated with ozone and nitrogen oxides. These were then selected to identify the active VOC species, i.e., the target VOC factors. See Table 1, which presents the target VOC factors in graphical form. Figure 4 The correlation is shown in Table 1, where the target VOC factors are propane, ethylene, n-butane, isobutane, ethane, toluene, propylene, and benzene.

[0100] Table 1 Target VOC Factors

[0101]

[0102] Step S3033: Match the pollution sources in the target area according to the target VOC factor to obtain source information.

[0103] It is understandable that the pollution source could be any industry that may cause air pollution, including but not limited to: motor vehicles, oil evaporation, petrochemicals, coal combustion, printing, and packaging industries.

[0104] In practice, after obtaining the target VOC factor, it can be matched with a pre-established matching table of VOC types and pollutant sources to determine the source industry corresponding to the target VOC factor and obtain source information.

[0105] Furthermore, upon obtaining the target VOC factor, i.e., the active VOC species, and the diurnal variation difference of the VOC species, the reduction concentration can be calculated based on the emission reduction ratio. Therefore, step S40 includes:

[0106] Step S401: Based on the first preset time period, obtain VOC data within the first preset time period.

[0107] It is understandable that the first preset time period can be the specific days in the time period selected and set by the user on the analysis device where the O3 concentration exceeds the standard, and the VOC data in the first time period can be the data corresponding to the above-mentioned VOC component factors and VOC related factors.

[0108] Step S402: Extract the active VOC factor from the VOC data, and obtain predicted emission reduction information based on the active VOC factor and the target VOC factor.

[0109] Understandably, after filtering out the data for specific days when O3 concentration exceeded the standard, it is possible to calculate the daily control time, active components, reduction amount, expected results, and other data, and make corresponding remarks on peak reduction or quality maintenance.

[0110] The method for calculating the control period is as follows: using historical data from the same period last year within the selected time range, calculate the hourly average for 24 hours, and calculate the change in each hour, i.e., the change in the current hour compared to the previous hour, (current hourly concentration - previous hourly concentration) * 100 / previous hourly concentration. Then, determine the hour when the hourly O3 value is greater than the hourly average and the hourly change is greater than the average change, and use this as the start time of the control. The moment when the radiation intensity begins to decrease, and the radiation intensity does not increase again in the subsequent moments of the day, is used as the end time of the control.

[0111] The screening method for active components, i.e., active VOC factors, can be as follows: Select a specific day in the analysis device display interface, and obtain the VOC component factors for that day and their correlation with VOC-related factors (O3, NO). X The correlation R value of the components is calculated, and the highly correlated component factors are filtered out and their intersection is taken as the active VOC factor. The results can also be displayed in the form of charts on the device display interface so that users can intuitively obtain the correlation between the factors.

[0112] The reduction amount can be ozone reduction, which is the difference in active components multiplied by the emission reduction ratio. The expected effect is the daily ozone concentration value minus the ozone reduction amount. The final note is to determine whether the expected effect is greater than 160 (the national secondary standard). If it is, it is considered peak reduction; otherwise, it is considered maintaining good quality.

[0113] In practice, the analysis equipment acquires VOC data on specific days when O3 concentration exceeds the standard, and calculates the reduction concentration based on active VOC factors, parameters such as control time and reduction amount, to obtain the expected effect. The expected effect is then compared with the national standard to further determine whether peak reduction or quality maintenance is necessary. Finally, the specific number of days with peak reduction and quality maintenance in the user-selected time period is counted to obtain predicted emission reduction information, which can show the control effect on different causes of air pollution in the target area.

[0114] This embodiment acquires VOC component concentration data and VOC-related factor concentration data from the relevant dataset, determines the correlation between each VOC-related factor and the VOC component factor, and generates a correlation table. It selects the VOC component factor located at a preset position in the correlation table as the target VOC factor. Based on the target VOC factor, it matches the pollution sources of the target area, obtains source information, and acquires VOC data within a first preset time period. It extracts reactive VOC factors from the VOC data and obtains predicted emission reduction information based on the reactive VOC factors and the target VOC factor. This enables analysis of the target area based on pollution sources and evaluation of the emission reduction effect of the target area based on specific VOC component factors within the pollution sources, allowing users to intuitively obtain air pollution information of the target area from multiple perspectives.

[0115] refer to Figure 5 , Figure 5 This is a flowchart illustrating the third embodiment of the atmospheric pollution causation analysis method of the present invention.

[0116] Based on the above embodiments, considering that specific pollutant data can be selected to determine whether regional transport exists in the target area, where O3 is a significantly representative pollutant, the ozone background value method can be specifically used to analyze the relevant dataset from the perspective of regional transport. Step S301 includes:

[0117] Step S3011: Extract regional historical data from the relevant dataset to determine the background value range.

[0118] Step S3012: Use a preset algorithm to obtain the current reference mean based on real-time monitoring data, and compare the current reference mean with the background value range.

[0119] Step S3013: Determine whether there is a regional transmission phenomenon in the target area based on the comparison results, and obtain the analysis results based on regional transmission.

[0120] In practice, the first step is to find the corresponding O3 background value range in the historical data of the region using the AQI data for the target day. Then, the average O3 background value for the target day is calculated as the current reference average. The current reference average is then compared with the background value range obtained above. If the current reference average is greater than the upper limit of the background value range, then there may be regional transmission in the target day.

[0121] Furthermore, considering the diverse sources and types of data in the dataset, different types of data can be hierarchically categorized based on the essential characteristics of the corresponding pollutants, so that users can obtain clearer, categorized analysis results. Step S302 includes:

[0122] Step S3021: Classify the relevant dataset according to the characteristic pollutant categories to obtain routine monitoring data and VOC component data.

[0123] Step S3022: Generate a meteorological analysis map, a pollutant change characteristic map, and a station analysis map for the target area based on the conventional monitoring data.

[0124] Step S3023: Based on the second preset time period, generate a VOC component change trend table according to the VOC component data.

[0125] It is understandable that the second preset time period can be a time period that the user sets on the display interface of the analysis device, or it can be a continuous time period that is automatically obtained based on the time range set by the user when initially selecting the target area for which information on the causes of air pollution.

[0126] Specifically, you can refer to Figure 6 , Figure 6 This is a flowchart illustrating the thought process for analyzing the causes of air pollution based on regional transport, pollution characteristics, and the types of pollution sources.

[0127] In regional transport analysis, the TCEQ method, ozone background value method, and characteristic pollutant ratio method can be used for judgment. Pollution characteristic analysis can be further divided into routine monitoring data analysis and super-station data analysis. Routine monitoring data analysis can be presented from the perspectives of meteorological analysis (displayed by wind rose diagrams and meteorological change diagrams), change characteristics (primary pollutant, good air quality rate analysis; concentration, daily change and year-on-year change diagrams of 6 routine pollutants), station analysis, and correlation analysis table of ozone and meteorological parameters. Super-station analysis can be presented from the perspectives of VOCs concentration composition and overall change, dominant species screening and daily change analysis. Pollution source analysis can be conducted from the perspectives of active VOCs component screening (SOA formation potential analysis, ozone formation potential analysis, correlation analysis of ozone with precursor VOCs and NO2 (screening highly correlated species - identifying active species - judging industry sources based on active species - emission reduction effect assessment)), characteristic pollutant ratio source tracing analysis, and ozone precursor remote sensing inversion, and can generate ozone VOCs and NO2, pollution rose diagrams.

[0128] This embodiment determines the background value range by extracting regional historical data from the relevant dataset; it uses a preset algorithm to obtain the current reference mean based on real-time monitoring data, and compares the current reference mean with the background value range; based on the comparison result, it determines whether regional transport exists in the target area, obtaining analysis results based on regional transport, which can accurately determine whether air pollution in the target area is mainly caused by regional transport or local emissions. Furthermore, it classifies the relevant dataset according to characteristic pollutant categories to obtain routine monitoring data and VOC component data; it generates meteorological analysis maps, pollutant change characteristic maps, and station analysis maps for the target area based on the routine monitoring data; and it generates a VOC component change trend table based on the VOC component data within a second preset time period. This allows for the aggregation and correlation of different types of data, enabling analysis from different dimensions. While achieving multi-source data integration, it also facilitates users in obtaining information on the causes of air pollution in the target area more conveniently and quickly.

[0129] In addition, to achieve the above objectives, the present invention also proposes a storage medium storing an air pollution cause analysis program, which, when executed by a processor, implements the steps of the air pollution cause analysis method as described above.

[0130] Since this storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, which will not be repeated here.

[0131] refer to Figure 7 , Figure 7 This is a structural block diagram of the first embodiment of the atmospheric pollution cause analysis device of the present invention.

[0132] like Figure 7 As shown, the air pollution cause analysis device proposed in this embodiment of the invention includes:

[0133] The region determination module 701 is used to receive user instructions and determine the target region;

[0134] The data management module 702 is used to acquire real-time monitoring data of the target area and combine it with a historical database to generate a relevant dataset of the target area.

[0135] The chart display module 703 is used to perform data analysis on the relevant datasets based on the transmission process, feature type and feature source, and display the corresponding analysis results in chart form;

[0136] The effect evaluation module 704 is used to perform feature correlation screening on the analysis results, obtain relevant feature data, and generate predicted emission reduction information based on the relevant feature data.

[0137] The cause report module 705 is used to combine the analysis results with the predicted emission reduction information to generate an air pollution cause analysis report for the target area.

[0138] This embodiment first receives user instructions to determine the target area; then it acquires real-time monitoring data of the target area and combines it with a historical database to generate a relevant dataset for the target area; next, it performs data analysis on the relevant dataset based on transmission process, feature type, and feature source, and displays the corresponding analysis results in chart form; then, it filters the analysis results for feature correlation to obtain relevant feature data, and generates predicted emission reduction information based on the relevant feature data; finally, it combines the analysis results with the predicted emission reduction information to generate an air pollution cause analysis report for the target area. Because this embodiment combines real-time and historical data as a dataset, it quickly outputs the required analytical statistics based on user selection criteria, displays them in an intuitive chart form, and provides a comprehensive regional analysis report. This improves the efficiency of data processing and statistics while enhancing data analysis capabilities, enabling users to conveniently and quickly obtain information on the causes of air pollution in the target area.

[0139] Based on the first embodiment of the air pollution cause analysis device of the present invention, a second embodiment of the air pollution cause analysis device of the present invention is proposed.

[0140] In this embodiment, the chart display module 703 is used to determine whether regional transport exists in the target area in the relevant dataset using a preset algorithm, and obtain analysis results based on regional transport; classify the relevant dataset according to the characteristic pollutant category to generate a regional feature table corresponding to the characteristic category; extract VOC data from the relevant dataset to obtain the target VOC category, and obtain the source information of the target area according to the target VOC category; and visualize the analysis results based on regional transport, the regional feature table, and the source information.

[0141] Furthermore, the chart display module 703 is also used to acquire VOC component factor concentration data and VOC related factor concentration data in the relevant dataset, and determine the correlation between each VOC related factor and VOC component factor to generate a correlation degree table; select the VOC component factor located at a preset position in the correlation degree table as the target VOC factor; and match the pollution source of the target area according to the target VOC factor to obtain source information.

[0142] The effect evaluation module 704 is used to acquire VOC data within the first preset time period; extract the active VOC factor from the VOC data; and obtain predicted emission reduction information based on the active VOC factor and the target VOC factor.

[0143] Furthermore, the chart display module 703 is also used to extract regional historical data from the relevant dataset to determine the background value range; use a preset algorithm to obtain the current reference mean based on real-time monitoring data, compare the current reference mean with the background value range; determine whether there is a regional transmission phenomenon in the target area based on the comparison result, and obtain the analysis result based on regional transmission.

[0144] Furthermore, the chart display module 703 is also used to classify the relevant dataset according to the characteristic pollutant category to obtain routine monitoring data and VOC component data; generate a meteorological analysis map, a pollutant change characteristic map and a station analysis map of the target area based on the routine monitoring data; and generate a VOC component change trend table based on the VOC component data according to the second preset time period.

[0145] The data management module 702 is used to standardize the real-time monitoring data of the target area with the historical database based on a preset template to obtain an initial dataset; and to perform anomaly screening and data cleaning on the initial dataset to obtain a relevant dataset of the target area.

[0146] Other embodiments or specific implementations of the atmospheric pollution cause analysis device of the present invention can be referred to the above-described method embodiments, and will not be repeated here.

[0147] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0148] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0149] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0150] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for analyzing the causes of air pollution, characterized in that, The method includes: Receive user instructions and determine the target area; Real-time monitoring data of the target area is acquired and combined with historical databases to generate a relevant dataset for the target area; Data analysis based on transmission process, feature type, and feature source is performed on the relevant datasets, and the corresponding analysis results are displayed in chart form. The analysis results are filtered for feature correlation to obtain relevant feature data, and predicted emission reduction information is generated based on the relevant feature data. The analysis results are combined with the predicted emission reduction information to generate an air pollution cause analysis report for the target area; The process of performing data analysis on the relevant datasets based on transmission process, feature type, and feature source, and displaying the corresponding analysis results in chart form, includes: In the relevant dataset, a preset algorithm is used to determine whether regional transmission occurs in the target area, and analysis results based on regional transmission are obtained. The relevant datasets are classified according to the categories of characteristic pollutants to generate regional feature tables for the corresponding feature categories; Extract VOC data from the relevant dataset and obtain the target VOC types; then match the source information of the target region based on the target VOC types. The analysis results based on regional transmission, the regional feature set, and the source information are visualized.

2. The method for analyzing the causes of air pollution as described in claim 1, characterized in that, The process of extracting VOC data from the relevant dataset and obtaining the target VOC type, and matching the source information of the target region based on the target VOC type, includes: Obtain the concentration data of VOC component factors and VOC-related factors in the relevant dataset, determine the correlation between each VOC-related factor and the VOC component factors, and generate a correlation table. Select the VOC component factor located at a preset position in the correlation table as the target VOC factor; The pollution sources in the target area are obtained by matching the target VOC factor, and the source information is obtained.

3. The method for analyzing the causes of air pollution as described in claim 2, characterized in that, The step of filtering the analysis results for feature correlation to obtain relevant feature data, and generating predicted emission reduction information based on the relevant feature data, includes: Based on a first preset time period, obtain VOC data within the first preset time period; Extract the active VOC factor from the VOC data, and obtain predicted emission reduction information based on the active VOC factor and the target VOC factor.

4. The method for analyzing the causes of air pollution as described in claim 1, characterized in that, The step involves using a preset algorithm to determine whether regional transmission occurs in the target region within the relevant dataset, and obtaining analysis results based on regional transmission, including: Extract regional historical data from the relevant dataset to determine the background value range; A preset algorithm is used to obtain the current reference mean based on real-time monitoring data, and the current reference mean is compared with the background value range; Based on the comparison results, determine whether there is regional transmission phenomenon in the target area, and obtain the analysis results based on regional transmission.

5. The method for analyzing the causes of air pollution as described in claim 1, characterized in that, The step of classifying the relevant dataset according to the category of characteristic pollutants to generate a regional feature table set corresponding to the feature categories includes: The relevant datasets are classified according to the characteristic pollutant categories to obtain routine monitoring data and VOC component data. Based on the conventional monitoring data, generate meteorological analysis maps, pollutant change characteristic maps, and station analysis maps for the target area; Based on the second preset time period, a VOC component change trend table is generated according to the VOC component data.

6. The method for analyzing the causes of air pollution as described in claim 1, characterized in that, The process of acquiring real-time monitoring data of the target area and combining it with a historical database to generate a relevant dataset for the target area includes: Based on a preset template, the real-time monitoring data of the target area is standardized with the historical database to obtain an initial dataset; Data cleaning by anomaly screening of the initial dataset is performed to obtain the relevant dataset for the target region.

7. An air pollution cause analysis device, characterized in that, The device includes: The region determination module is used to receive user instructions and determine the target region; The data management module is used to acquire real-time monitoring data of the target area and combine it with a historical database to generate a relevant dataset for the target area. The chart display module is used to perform data analysis on the relevant datasets based on the transmission process, feature type, and feature source, and to display the corresponding analysis results in chart form. The effect evaluation module is used to filter the feature correlation of the analysis results, obtain relevant feature data, and generate predicted emission reduction information based on the relevant feature data; The cause report module is used to combine the analysis results with the predicted emission reduction information to generate an air pollution cause analysis report for the target area; The chart display module is further configured to: use a preset algorithm to determine whether regional transport exists in the target region within the relevant dataset, and obtain analysis results based on regional transport; classify the relevant dataset according to the category of characteristic pollutants, and generate a regional feature table corresponding to the characteristic category; extract VOC data from the relevant dataset and obtain the target VOC category, and match the source information of the target region according to the target VOC category; and visualize the analysis results based on regional transport, the regional feature table, and the source information.

8. An air pollution cause analysis device, characterized in that, The device includes: a memory, a processor, and an air pollution causation analysis program stored in the memory and executable on the processor, the air pollution causation analysis program being configured to implement the steps of the air pollution causation analysis method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores an air pollution cause analysis program, which, when executed by a processor, implements the steps of the air pollution cause analysis method as described in any one of claims 1 to 6.

Images