A kind of automatic monitoring system of ambient air quality

Abstract

The present invention discloses an automatic monitoring system for ambient air quality, which specifically relates to the field of environmental monitoring and is used to solve the problem of emission credibility of internal emission monitoring in enterprises. It is through combining the production situation of the enterprise and the wind direction factor to assist in analyzing the correlation between the monitoring site and the internal monitoring equipment data of the enterprise to identify potential equipment abnormality risks. First, the scale and intensity of the enterprise's production activities are evaluated. Secondly, the wind direction data is used to determine the monitoring sites that may be affected by the enterprise's emissions, so as to improve the pertinence of the monitoring. Then, the monitoring site and the internal monitoring equipment data of the enterprise are compared and analyzed to evaluate the working status and accuracy of the equipment. Finally, the comprehensive analysis results are used to evaluate the abnormal use of the monitoring equipment, timely discover and solve the problems of the monitoring equipment, ensure the accuracy and reliability of the emission monitoring data, prevent enterprises from evading environmental monitoring responsibilities, and safeguard the interests of the public environment and public health.

Description

Technical Field

[0001] The present invention relates to the field of environmental monitoring, and more specifically, to an automatic monitoring system and method for ambient air quality. Background Art

[0002] At present, many enterprises that are subject to key monitoring generally have monitoring equipment installed to monitor their emissions. However, some enterprises may fail to monitor due to reasons such as avoiding emissions or inaccurate monitoring equipment. Such a situation can easily distort the monitored emission data because the data obtained by the enterprise's internal monitoring equipment is not accurately monitored. On the contrary, the data obtained by social public monitoring sites may be mixed, making it difficult to clearly reflect the true situation of key monitored enterprises. This situation will lead to monitoring failure, the internal monitoring equipment of the enterprise cannot be effectively monitored, and the external monitoring sites will not be able to monitor the target enterprises in a targeted manner. Such inaccurate monitoring data may affect environmental protection and public health, and may provide enterprises with opportunities to evade monitoring responsibilities. Therefore, it is necessary to take measures to solve this problem to ensure the accuracy and reliability of monitoring data and maintain environmental quality and public interests.

[0003] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an automatic monitoring system and method for ambient air quality, which assists in analyzing the correlation between the monitoring site and the internal monitoring equipment data of the enterprise by combining the production situation of the enterprise and the wind direction factor, so as to identify potential equipment abnormality risks. First, the scale and intensity of the enterprise's production activities are evaluated. Secondly, the wind direction data is used to determine the monitoring sites that may be affected by the enterprise's emissions, so as to improve the targeted nature of the monitoring. Then, the monitoring site and the internal monitoring equipment data of the enterprise are compared and analyzed to evaluate the working status and accuracy of the equipment. Finally, the results of the comprehensive analysis are used to evaluate the abnormal use of the monitoring equipment, to promptly discover and resolve monitoring equipment problems, to ensure the accuracy and reliability of emission monitoring data, to prevent enterprises from evading environmental monitoring responsibilities, and to safeguard the interests of the public environment and public health, so as to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: an automatic monitoring system for ambient air quality, comprising a data collection module, a site identification module, a data association module and a trustworthy assessment module;

[0006] The data collection module evaluates the correspondence between the enterprise output data and the emission monitoring data through time alignment and data matching to find possible underreporting of environmental impacts or data recording problems, and passes the possible underreporting of environmental impacts or data recording problems to the site identification module;

[0007] The site identification module uses GIS technology and air diffusion models to quantitatively evaluate the sensitivity of monitoring sites to emission sources, sort the monitoring sites according to the size of the emission impact range, match the monitoring sites, and send the sorting information to the data association module;

[0008] The data association module maps the environmental data of the monitoring equipment and the top-ranked monitoring site to a high-dimensional feature space and compares the mean vectors of the two to reveal the similarities and differences in the distribution of environmental data between the enterprise's internal monitoring equipment and external monitoring sites, reflecting potential abnormalities, and sending environmental data analysis data to the trusted assessment module;

[0009] The trusted assessment module analyzes the credibility of enterprise emission data by building a probabilistic model to identify the general differences and overall monitoring differences in environmental data between monitoring sites and monitoring equipment.

[0010] In a preferred embodiment, the data collection module includes the following:

[0011] Use a unified time standard to synchronize the data source time and align the timestamps of output data and monitoring data;

[0012] The details are as follows:

[0013] For each time point, the time difference between the output data and the monitoring data is calculated, that is, the timestamp of the output data minus the timestamp of the monitoring data;

[0014] The formula for calculating the time difference is: ,in, is the time drift, is the timestamp of the output data, is the timestamp of the monitoring data;

[0015] Perform statistical analysis on all time differences and calculate the mean and standard deviation of the time differences;

[0016] Using the mean and standard deviation, determine the threshold range of abnormal time difference, and determine the threshold range of time difference: set the threshold range of time difference to the time difference of the mean plus or minus two times the standard deviation;

[0017] For each time point in the output data and monitoring data, check whether the corresponding time difference is within the range of abnormal time difference;

[0018] If the time difference exceeds the range of abnormal time difference, the timestamp of the output data or monitoring data will be corrected;

[0019] The formula for correcting the timestamp is: ,in, is the corrected timestamp, is the original timestamp, is the mean of the time differences.

[0020] In a preferred embodiment, a database query is used to perform a matching operation, and the output data and the monitoring data are matched according to the timestamp to ensure that each time point corresponds to the correct output and monitoring data;

[0021] Use SQL query language to match data in the database where the output data and monitoring data are located;

[0022] After obtaining the corresponding output and monitoring data at each time point, the data correspondence is calculated. The calculation formula is as follows: ;

[0023] in, is the data correspondence, is the sample size, It is the difference indicator between output data and monitoring data, that is, the Euclidean distance between the two;

[0024] The data correspondence is compared with the correspondence threshold. If the data correspondence is less than the correspondence threshold, it is necessary to be vigilant and generate a warning signal; conversely, if the data correspondence is not less than the correspondence threshold, a controllable signal is generated.

[0025] In a preferred embodiment, the site identification module includes the following contents:

[0026] If no controllable signal is obtained, obtain detailed information on emission sources from relevant departments;

[0027] Obtain geographical location information and monitoring data of monitoring sites from relevant agencies of environmental monitoring sites;

[0028] Use GIS software to load geographic information data of emission sources and monitoring sites and create spatial data layers; use GIS spatial analysis functions to calculate the spatial distance from emission sources to monitoring sites;

[0029] Based on the emission source as the dot and the rated distance as the radius, a circle is drawn to cover the park, and the monitoring stations in the park are counted. The degree of association between each monitoring station and the emission source is calculated. The calculation formula is as follows: ;

[0030] in, Indicates the scope of emission impact;

[0031] Determine the geographical location of the monitoring site and the emission source, and calculate the direction angle between the monitoring site and the emission source , is the wind direction angle;

[0032] Obtain environmental quality standards , and the maximum concentration near the emission source ;

[0033] Calculate the wind direction adjustment factor based on wind direction angle and wind speed ;

[0034] Calculate emission impact distance using air dispersion model ;

[0035] is the standard deviation in the horizontal direction, indicating the degree of dispersion of emissions in the horizontal direction; is the maximum concentration near the emission source, that is, the highest concentration value observed at the closest distance to the emission source; It is an environmental quality standard, also known as the threshold or limit of pollutant concentration;

[0036] According to the extent of emission impact, the monitoring sites are sorted from large to small to obtain a ranking table of monitoring sites.

[0037] In a preferred embodiment, the data association module includes the following contents:

[0038] Select the monitoring site ranked first in the monitoring site ranking, and collect gas composition data of the monitoring site and monitoring equipment;

[0039] Align various environmental monitoring data from monitoring sites and monitoring equipment according to time, and construct a multi-dimensional feature vector to represent the combination of various environmental data at each time point;

[0040] Feature mapping is performed on various environmental data of each monitoring site, and the Gaussian kernel function is used to map the data into a high-dimensional feature space. The calculation formula of the feature mapping function is: ;

[0041] in, is the environmental data vector, is the center of the Gaussian kernel, is the bandwidth parameter of the Gaussian kernel;

[0042] For monitoring sites and monitoring equipment, the mean vector of various environmental data in the feature space is calculated and the monitoring sites are marked as , comparing the monitoring equipment to ; Here, taking the monitoring site as an example, the mean vector is calculated, and the calculation formula is as follows: ;

[0043] in, Indicates monitoring site The mean vector of the environmental data in the feature space, It is a monitoring site The number of environmental data samples, It is a monitoring site No. Environmental data samples;

[0044] In the same way, the mean vector of the environmental data of the monitoring equipment in the feature space is calculated and obtained. ;

[0045] Using the mean calculation results, calculate the maximum mean difference between the monitoring sites and the monitoring devices: ;

[0046] in, represents the maximum mean difference between the monitoring site and the monitoring equipment, Represents the norm in the feature space.

[0047] In a preferred embodiment, the trustworthy assessment module includes the following contents:

[0048] The maximum mean difference data between the monitoring sites and the monitoring equipment for a rated number of times per unit time is obtained, a difference data set is constructed, and a difference threshold is set to classify the maximum mean difference data into two categories: those greater than or equal to the threshold represent high differences, and those less than or equal to the threshold represent low differences;

[0049] Based on the probability model of difference data, the probability distribution of high difference and low difference is modeled to obtain the relative probability between the probability of high difference and low difference:

[0050] The probability that the maximum mean difference data falls within the high difference and low difference ranges is obtained each time;

[0051] Normalize the probabilities of all times to obtain a normalized probability distribution;

[0052] The relative probability between the final normalized probability distributions is used as the prevalence index.

[0053] In a preferred embodiment, the prevalence index and the maximum mean difference mean are compared with corresponding thresholds respectively. When both the prevalence index and the maximum mean difference mean are greater than the corresponding thresholds, an alarm is issued and the monitoring equipment located within the enterprise needs to be inspected.

[0054] The technical effects and advantages of the automatic monitoring system and method of ambient air quality of the present invention are as follows:

[0055] 1. The present invention ensures the temporal consistency of enterprise output data and monitoring data through time alignment and data matching, thereby accurately assessing environmental impacts. By unifying time standards and matching operations, potential environmental impact omissions or data recording problems can be effectively detected, which helps to improve the credibility and accuracy of monitoring data. This precise matching can timely discover the potential impact of production activities on the environment, so that necessary measures can be taken to protect the environment and public health, ensure the consistency and reliability between the production activities of enterprises and environmental monitoring, and provide strong support for subsequent decision-making.

[0056] 2. The present invention combines the enterprise's production situation and wind direction factors to assist in analyzing the correlation between the monitoring sites and the enterprise's internal monitoring equipment data to identify potential equipment abnormality risks. First, evaluate the scale and intensity of the enterprise's production activities. Secondly, use wind direction data to determine the monitoring sites that may be affected by the enterprise's emissions to improve the targeted nature of the monitoring. Then, compare and analyze the monitoring site data with the enterprise's internal monitoring equipment data to evaluate the working status and accuracy of the equipment. Finally, comprehensively analyze the results, evaluate the abnormal use of the monitoring equipment, promptly discover and resolve monitoring equipment problems, ensure the accuracy and reliability of emission monitoring data, prevent enterprises from evading environmental monitoring responsibilities, and safeguard the interests of the public environment and public health. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 The present invention is a schematic structural diagram of an automatic monitoring system for ambient air quality. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] Example 1

[0060] Figure 1 The present invention provides an automatic monitoring system for ambient air quality, comprising:

[0061] The data collection module evaluates the correspondence between the enterprise output data and the emission monitoring data through time alignment and data matching to find possible underreporting of environmental impacts or data recording problems, and passes the possible underreporting of environmental impacts or data recording problems to the site identification module;

[0062] The site identification module uses GIS technology and air diffusion models to quantitatively evaluate the sensitivity of monitoring sites to emission sources, sort the monitoring sites according to the size of the emission impact range, match the monitoring sites, and send the sorting information to the data association module;

[0063] The data association module maps the environmental data of the monitoring equipment and the top-ranked monitoring site to a high-dimensional feature space and compares the mean vectors of the two to reveal the similarities and differences in the distribution of environmental data between the enterprise's internal monitoring equipment and external monitoring sites, reflecting potential abnormalities, and sending environmental data analysis data to the trusted assessment module;

[0064] The trusted assessment module analyzes the credibility of enterprise emission data by building a probabilistic model to identify the general differences and overall monitoring differences in environmental data between monitoring sites and monitoring equipment.

[0065] The concept of enterprise emission monitoring includes two key factors: the enterprise's gross value added and wind direction. The level of production activity of an enterprise is usually related to its gross value added, so as production activities increase, emissions may increase accordingly. At the same time, considering that wind direction has an important impact on the spread of emissions, it is necessary to comprehensively consider the wind direction factor at the time when analyzing monitoring data.

[0066] First, by collecting data on the gross value-added of an enterprise, the scale and intensity of its production activities can be assessed. This assessment is an important prerequisite for enterprise emission monitoring, as emissions are usually directly related to production scale.

[0067] Secondly, considering the impact of wind direction on the spread of emissions, the selection of monitoring sites is crucial. By analyzing wind direction data, it is possible to determine which monitoring sites may be affected by corporate emissions. This approach helps to improve the targeting and effectiveness of monitoring, thereby better reflecting the actual situation of corporate emissions.

[0068] Next, the monitoring data from the monitoring site is compared and analyzed with the data from the monitoring equipment within the enterprise. By comparing the correlation between the two, the working status and accuracy of the monitoring equipment within the enterprise can be evaluated. If there is a significant difference between the monitoring site data and the data from the enterprise's internal equipment, it may mean that the equipment is abnormal or faulty.

[0069] Finally, combined with the results of gross added value and wind direction analysis, the abnormal risk level of the monitoring equipment within the enterprise can be evaluated. This comprehensive analysis method helps to timely discover and resolve abnormal situations of monitoring equipment and ensure the accuracy and reliability of monitoring data.

[0070] In summary, by combining the enterprise's gross added value and wind direction factors, and assisting in analyzing the correlation between the data from the monitoring sites and the data from the enterprise's internal monitoring equipment, it can help identify the abnormal risk level of the enterprise's internal monitoring equipment, thereby improving the accuracy and reliability of emission monitoring.

[0071] The data collection module includes the following:

[0072] Use a unified time standard (such as UTC time) to synchronize the data source time to ensure that both output data and monitoring data have accurate timestamps for subsequent corresponding analysis;

[0073] The output data produced by an enterprise refers to various data related to the production activities of the enterprise, usually including but not limited to production quantity, output value, sales, etc. These data reflect the production situation and performance of the enterprise within a certain period of time. For example, in the manufacturing industry, output data may involve product quantity, quality, production efficiency, etc.; in the service industry, output data may involve the completion of service projects, customer satisfaction, etc. By monitoring and analyzing output data, enterprises can understand their own production efficiency and market demand, thereby guiding production planning, resource allocation and marketing strategies.

[0074] Time-align the timestamps of output data and monitoring data to allow comparison over the same time period.

[0075] The details are as follows:

[0076] For each time point, the time difference between the output data and the monitoring data is calculated, that is, the timestamp of the output data minus the timestamp of the monitoring data.

[0077] The formula for calculating the time difference is: ,in, is the time drift, is the timestamp of the output data, It is the timestamp of the monitoring data.

[0078] Perform statistical analysis on all time differences and calculate the mean and standard deviation of the time differences;

[0079] The threshold range of the abnormal time difference is determined by using the mean and the standard deviation. The threshold range of the time difference can be determined in the following manner: the threshold range of the time difference is set to the time difference of the mean plus or minus two times the standard deviation;

[0080] For each time point in the output data and monitoring data, check whether the corresponding time difference is within the range of abnormal time difference;

[0081] If the time difference exceeds the range of abnormal time difference, the timestamp of the output data or monitoring data will be corrected.

[0082] The formula for correcting the timestamp is: ,in, is the corrected timestamp, is the original timestamp, is the mean of the time differences.

[0083] Use database query to perform matching operations, match output data and monitoring data according to timestamps, and ensure that each time point corresponds to the correct output and monitoring data;

[0084] The SQL query language can be used to match data in the database where the output data and monitoring data are located.

[0085] Write SQL query statements, use timestamps as matching conditions, and jointly query output data and monitoring data to obtain data at corresponding time points.

[0086] Query statement example:

[0087] SELECTvalue.timestampASvalue_timestamp,value.dataASvalue_data,monitoring.timestampASmonitoring_timestamp,monitoring.dataASmonitoring_data

[0088] FROMvalue_tableASvalue

[0089] JOINmonitoring_tableASmonitoring

[0090] ONvalue.timestamp=monitoring.timestamp

[0091] Use data processing software (such as Python's pandas library, R language, etc.) to read output data and monitoring data files, and perform data matching processing.

[0092] Load the output data and monitoring data into a DataFrame, using timestamps as indexes to ensure that the timestamps of the two data sets correspond.

[0093] Through the merge operation (merge function or join operation), the two data frames are merged according to the timestamp to obtain the corresponding output and monitoring data at each time point.

[0094] Data processing software example (using Python's pandas library):

[0095] importpandas aspd

[0096] #Read output data and monitoring data files

[0097] value_data=pd.read_csv('value_data.csv')

[0098] monitoring_data=pd.read_csv('monitoring_data.csv')

[0099] #Set timestamp as index

[0100] value_data.set_index('timestamp',inplace=True)

[0101] monitoring_data.set_index('timestamp',inplace=True)

[0102] #Data merging operation

[0103] merged_data=pd.merge(value_data,monitoring_data,left_index=True,right_index=True,how='inner')

[0104] After obtaining the corresponding output and monitoring data at each time point, the data correspondence is calculated. The calculation formula is as follows: ;

[0105] in, is the data correspondence, is the sample size, It is the difference indicator between output data and monitoring data, that is, the Euclidean distance between the two.

[0106] The degree of correspondence between output data and monitoring data refers to the degree of association or matching between the two. Specifically, it refers to the temporal correspondence between output data and monitoring data, that is, whether the output data and monitoring data have similar trends, changes or values ​​at the same time point.

[0107] For example, if the output data at a certain point in time show that the intensity of production activities is high, and the monitoring data simultaneously show that the concentration of air pollutants is high, then the two data have a high degree of correspondence at that point in time.

[0108] Output data refers to the production data of enterprises, including production quantity, output, sales and other data related to production activities. Monitoring data refers to environmental monitoring data, such as air quality monitoring data, water quality monitoring data, etc., which are used to measure the pollution level or quality of the surrounding environment.

[0109] For example, suppose there is a steel plant whose production data (output data) includes daily steel production, sales, etc. At the same time, the steel plant has also installed air quality monitoring equipment to monitor the concentration of pollutants such as particulate matter (such as PM2.5) and sulfur dioxide (SO2) in the surrounding air.

[0110] Steel plant production data (output data) and air quality monitoring data (monitoring data) can be used to analyze the impact of steel production activities on the surrounding environment. By comparing daily steel production with the concentration of particulate matter and sulfur dioxide in the air, the impact of steel production activities on air quality can be assessed. In this case, the degree of correspondence between output data and monitoring data refers to the degree of correlation between steel production and air pollutant concentrations.

[0111] Compare the data correspondence with the correspondence degree threshold. If the data correspondence is less than the correspondence degree threshold, it indicates that there are differences or inconsistencies between production activities and environmental monitoring, and there may be omissions in environmental impacts or problems with data recording. This requires vigilance and generates an early warning signal. On the contrary, if the data correspondence is not less than the correspondence degree threshold, it indicates that the correlation between production activities and environmental monitoring is high, and it is not easy to have omissions in environmental impacts or problems with data recording. Therefore, a controllable signal is generated.

[0112] The present invention ensures the temporal consistency of enterprise output data and monitoring data through time alignment and data matching, thereby accurately assessing environmental impacts. By unifying time standards and matching operations, potential environmental impact omissions or data recording problems can be effectively detected, which helps to improve the credibility and accuracy of monitoring data. This precise matching can timely discover the potential impact of production activities on the environment, so that necessary measures can be taken to protect the environment and public health, ensure the consistency and reliability between the production activities of enterprises and environmental monitoring, and provide strong support for subsequent decision-making.

[0113] The site identification module includes the following:

[0114] If no controllable signal is obtained, obtain detailed information on the emission source from relevant departments, including emission type (such as chimneys, wastewater discharge outlets, etc.), emission volume (emission volume per unit time), emission components (such as sulfur dioxide, nitrogen oxides, etc.), etc.

[0115] Obtain the geographical location information and monitoring data of the monitoring sites, such as air quality, from the environmental monitoring site database or relevant agencies;

[0116] Use GIS software to load geographic information data of emission sources and monitoring sites and create spatial data layers; use GIS spatial analysis functions to calculate the spatial distance from emission sources to monitoring sites;

[0117] Based on the emission source as the dot and the rated distance as the radius, a circle is drawn to cover the park, and the monitoring stations in the park are counted. The degree of association between each monitoring station and the emission source is calculated. The calculation formula is as follows: ;

[0118] in, Indicates the scope of emission impact;

[0119] Determine the geographical location of the monitoring site and the emission source, and calculate the direction angle between the monitoring site and the emission source , is the wind direction angle;

[0120] Obtain environmental quality standards , and the maximum concentration near the emission source ;

[0121] Calculate the wind direction adjustment factor based on wind direction angle and wind speed ;

[0122] Calculate emission impact distance using air dispersion model ;

[0123] It is the standard deviation in the horizontal direction, which indicates the diffusion degree of emissions in the horizontal direction. Specifically, it indicates the width of the emission concentration distribution, that is, the diffusion range of pollutants released by the emission source in the horizontal direction;

[0124] It is the maximum concentration near the emission source, that is, the highest concentration value observed at the closest distance to the emission source. This value usually appears in the area near the emission source, and the concentration gradually decreases as the distance from the emission source increases. Near the emission source, the concentration will reach the maximum value because the pollutants have not spread to far places after being released.

[0125] It is an environmental quality standard, also known as the threshold or limit of pollutant concentration. This threshold is formulated in accordance with relevant national or regional laws, regulations, standards or guiding documents to guide and supervise the concentration limit of specific pollutants in the atmospheric environment.

[0126] The emission impact range is used to assess the extent to which a monitoring site is affected by an emission source. This value reflects the distribution of pollutant concentrations in the environment surrounding the monitoring site, that is, the extent to which pollutants released by the emission source affect the air quality near the monitoring site.

[0127] A larger emission impact range means that the monitoring site is more widely affected by the emission source, and the monitored pollutant concentration may be higher. This may mean that the area where the monitoring site is located is more seriously polluted and corresponding measures need to be taken to protect the environment and human health.

[0128] On the contrary, the smaller the emission impact range, the smaller the emission source impact range of the monitoring station, and the monitored pollutant concentration may be lower. This indicates that the area where the monitoring station is located is relatively less polluted and the environmental quality may be relatively good.

[0129] According to the extent of emission impact, the monitoring sites are sorted from large to small to obtain a ranking table of monitoring sites.

[0130] The data association module includes the following:

[0131] The monitoring site ranked first in the monitoring site ranking is selected, and the gas composition data of the monitoring site and monitoring equipment are collected to ensure that the corresponding time and space of the data are consistent.

[0132] Align various environmental monitoring data from monitoring sites and monitoring equipment according to time, and construct a multi-dimensional feature vector to represent the combination of various environmental data at each time point;

[0133] Feature mapping is performed on various environmental data of each monitoring site, and the Gaussian kernel function is used to map the data into a high-dimensional feature space. The calculation formula of the feature mapping function is: ;

[0134] in, is the environmental data vector, is the center of the Gaussian kernel, is the bandwidth parameter of the Gaussian kernel;

[0135] For monitoring sites and monitoring equipment, the mean vector of various environmental data in the feature space is calculated and the monitoring sites are marked as , comparing the monitoring equipment to ; Here, taking the monitoring site as an example, the mean vector is calculated, and the calculation formula is as follows: ;

[0136] in, Indicates monitoring site The mean vector of the environmental data in the feature space, It is a monitoring site The number of environmental data samples, It is a monitoring site No. Environmental data samples;

[0137] In the same way, the mean vector of the environmental data of the monitoring equipment in the feature space is calculated and obtained. ;

[0138] Using the mean calculation results, calculate the maximum mean difference between the monitoring sites and the monitoring devices: ;

[0139] in, represents the maximum mean difference between the monitoring site and the monitoring equipment, Represents the norm in the feature space.

[0140] The maximum mean difference is used to evaluate and calculate the degree of difference in the distribution of environmental data between monitoring sites and monitoring equipment. The monitoring equipment is located inside the enterprise, and the monitoring sites are selected monitoring sites in the society. The maximum mean difference between the two is analyzed to represent and reflect the overall difference of the environmental data of the monitoring sites.

[0141] When the maximum mean difference is large, it means that the distribution of environmental data between the monitoring site and the monitoring equipment is quite different, that is, the environmental conditions at the two locations are quite different. This may indicate that the environmental data monitored by the monitoring site within the enterprise is quite different from that of the monitoring sites in other parts of the society, and the monitoring equipment within the enterprise may be abnormal, which needs to be paid attention to.

[0142] When the maximum mean difference is small, it means that the distribution difference of environmental data between monitoring sites and monitoring equipment is small, that is, the environmental conditions of the two locations are relatively similar. This may indicate that the environmental data monitored by the monitoring equipment inside the enterprise is slightly different from that of monitoring sites in other parts of the society, and the environmental status of the enterprise is relatively consistent with the surrounding environment, which can reflect that the monitoring facilities inside the enterprise are normal.

[0143] The Trust Assessment Module includes the following:

[0144] The maximum mean difference data between the monitoring sites and the monitoring equipment for a rated number of times per unit time is obtained, a difference data set is constructed, and a difference threshold is set to classify the maximum mean difference data into two categories: those greater than or equal to the threshold represent high differences, and those less than or equal to the threshold represent low differences;

[0145] Based on the probability model of difference data, the probability distribution of high difference and low difference is modeled to obtain the relative probability between the probability of high difference and low difference:

[0146] The probability that the maximum mean difference data falls within the high difference and low difference ranges is obtained each time;

[0147] Normalize the probabilities of all times to obtain a normalized probability distribution;

[0148] The relative probability between the final normalized probability distributions is used as the prevalence index.

[0149] The universality index is used to indicate the universality of the differences in environmental monitoring data between monitoring sites. Specifically, it measures the universality of the maximum mean differences between monitoring sites and monitoring equipment in multiple measurements, that is, the universality of the distribution differences of monitoring data as a whole.

[0150] - When the universality index is larger, it means that the degree of difference in environmental monitoring data of monitoring sites and monitoring equipment is generally larger, that is, there are large differences between data at different time points. This may indicate that the environmental conditions of monitoring sites and monitoring equipment vary greatly in different time periods or under different circumstances.

[0151] - When the universality index is smaller, it means that the difference in environmental monitoring data of monitoring sites and monitoring equipment is generally smaller, that is, there is a smaller difference between data at different time points. This may indicate that the environmental conditions of monitoring sites and monitoring equipment change more consistently in different time periods or under different circumstances.

[0152] The prevalence index and the mean of the maximum mean difference are compared with the corresponding thresholds respectively. When both the prevalence index and the mean of the maximum mean difference are greater than the corresponding thresholds, an alarm is issued and the monitoring equipment located inside the enterprise needs to be checked.

[0153] This alarm mechanism is set up to promptly detect possible abnormalities or manipulation of monitoring equipment within the enterprise. If the environmental data monitored by the external monitoring site for a long time is significantly different from the data of the monitoring equipment within the enterprise, and this difference persists in multiple measurements, and the universality index and the maximum mean difference mean both exceed the corresponding threshold, then it may indicate that the monitoring equipment within the enterprise has been interfered with or deliberately blocked, resulting in inaccurate or invalid monitoring data.

[0154] Therefore, sounding the alarm and inspecting the monitoring equipment within the enterprise can help promptly discover and resolve problems with the monitoring equipment, ensure the effectiveness and accuracy of environmental monitoring, and also help prevent companies from using improper means to evade environmental monitoring responsibilities and safeguard the interests of the public environment and public health.

[0155] The present invention assists in analyzing the correlation between the monitoring sites and the internal monitoring equipment data of the enterprise by combining the enterprise production situation and wind direction factors to identify potential equipment abnormality risks. First, evaluate the scale and intensity of the enterprise's production activities. Secondly, use wind direction data to determine the monitoring sites that may be affected by the enterprise's emissions to improve the targeted nature of monitoring. Then, compare and analyze the monitoring site data with the enterprise's internal monitoring equipment data to evaluate the working status and accuracy of the equipment. Finally, comprehensively analyze the results, evaluate the abnormal use of the monitoring equipment, promptly discover and resolve monitoring equipment problems, ensure the accuracy and reliability of emission monitoring data, prevent enterprises from evading environmental monitoring responsibilities, and safeguard the interests of the public environment and public health.

[0156] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0157] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0158] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0159] In the several embodiments provided in the present application, it should be understood that the disclosed systems and devices can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0160] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0161] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0162] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0163] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0164] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An automatic monitoring system for ambient air quality, characterized in that: It includes data collection module, site identification module, data association module and trustworthy assessment module; The data collection module evaluates the correspondence between the enterprise's output data and monitoring data through time alignment and data matching. The output data is the enterprise's production data, and the monitoring data is the environmental monitoring data obtained by the enterprise's internal monitoring equipment, so as to find possible environmental impact omissions or data recording problems, and pass the possible environmental impact omissions or data recording problems to the site identification module; The data collection module includes the following: Use a unified time standard to synchronize the data source time and align the timestamps of output data and monitoring data; The details are as follows: For each time point, the time difference between the output data and the monitoring data is calculated, that is, the timestamp of the output data minus the timestamp of the monitoring data; The formula for calculating the time difference is: ,in, is the time drift, is the timestamp of the output data, is the timestamp of the monitoring data; Perform statistical analysis on all time differences and calculate the mean and standard deviation of the time differences; Using the mean and standard deviation, determine the threshold range of abnormal time difference, and determine the threshold range of time difference: set the threshold range of time difference to the time difference of the mean plus or minus two times the standard deviation; For each time point in the output data and monitoring data, check whether the corresponding time difference is within the range of abnormal time difference; If the time difference exceeds the range of abnormal time difference, the timestamp of the output data or monitoring data will be corrected; The formula for correcting the timestamp is: ,in, is the corrected timestamp, is the original timestamp, is the mean of the time differences; Use database query to perform matching operations, match output data and monitoring data according to timestamps, and ensure that each time point corresponds to the correct output and monitoring data; Use SQL query language to match data in the database where the output data and monitoring data are located; After obtaining the corresponding output and monitoring data at each time point, the data correspondence is calculated. The calculation formula is as follows: ; in, is the data correspondence, is the sample size, It is the difference indicator between output data and monitoring data, that is, the Euclidean distance between the two; Compare the data correspondence with the correspondence threshold. If the data correspondence is less than the correspondence threshold, it is necessary to be vigilant and generate a warning signal; on the contrary, if the data correspondence is not less than the correspondence threshold, a controllable signal is generated; The site identification module uses GIS technology and air diffusion models to quantitatively evaluate the sensitivity of external monitoring sites to emission sources, and sorts the external monitoring sites according to the size of the emission impact range, matches the external monitoring sites, and sends the sorting situation to the data association module; The site identification module includes the following: If no controllable signal is obtained, obtain detailed information on emission sources from relevant departments; Obtain geographic location information and monitoring data of external monitoring sites; Use GIS software to load geographic information data of emission sources and external monitoring sites and create spatial data layers; use GIS spatial analysis functions to calculate the spatial distance from emission sources to external monitoring sites; Based on the emission source as the dot and the rated distance as the radius, a circle is drawn to cover the park, and the external monitoring stations in the park are counted. The degree of association between each external monitoring station and the emission source is calculated. The calculation formula is as follows: ; in, Indicates the scope of emission impact; Determine the geographic location of external monitoring sites and emission sources, and calculate the direction angle between the external monitoring sites and emission sources , is the wind direction angle; Obtain environmental quality standards , and the maximum concentration near the emission source ; Calculate the wind direction adjustment factor based on the direction angle and wind direction angle ; Calculate emission impact distance using air dispersion model ; is the standard deviation in the horizontal direction, indicating the degree of dispersion of emissions in the horizontal direction; is the maximum concentration near the emission source, that is, the highest concentration value observed at the closest distance to the emission source; It is an environmental quality standard, also known as the threshold or limit of pollutant concentration; According to the extent of emission impact, the external monitoring sites are sorted from large to small to obtain a ranking table of monitoring sites; The data association module maps the environmental data of the enterprise's internal monitoring equipment and the external monitoring site ranked first into a high-dimensional feature space, and compares the mean vectors of the two, revealing the similarities and differences in the distribution of environmental data between the enterprise's internal monitoring equipment and the external monitoring site, reflecting potential abnormalities, and sending the environmental data analysis data to the trusted assessment module; The data association module includes the following: Select the external monitoring site that ranks first in the external monitoring site ranking, and collect gas composition data from the external monitoring site and the enterprise's internal monitoring equipment; Align various environmental monitoring data from external monitoring sites and internal monitoring equipment of enterprises according to time, and construct a multi-dimensional feature vector to represent the combination of various environmental data at each time point; Feature mapping is performed on various environmental data of each external monitoring site, and the Gaussian kernel function is used to map the data into a high-dimensional feature space. The calculation formula of the feature mapping function is: ; in, is the environmental data vector, is the center of the Gaussian kernel, is the bandwidth parameter of the Gaussian kernel; For external monitoring sites and internal monitoring equipment of enterprises, the mean vector of various environmental data in the feature space is calculated, and the external monitoring sites are marked as , marking the enterprise's internal monitoring equipment as ; Calculate the mean vector of the environmental data of the external monitoring site in the feature space. The calculation formula is as follows: ; in, Indicates external monitoring site The mean vector of the environmental data in the feature space, Is an external monitoring site The number of environmental data samples, Is an external monitoring site No. Environmental data samples; In the same way, the mean vector of the environmental data of the enterprise's internal monitoring equipment in the feature space is calculated and obtained. ; Using the mean calculation results, calculate the maximum mean difference between the external monitoring sites and the enterprise's internal monitoring equipment: ; in, represents the maximum mean difference between external monitoring sites and internal monitoring equipment of the enterprise, Represents the norm in the feature space; The trusted assessment module constructs a probabilistic model to identify the general differences and overall monitoring differences in environmental data between external monitoring sites and internal enterprise monitoring equipment, and analyzes the credibility of enterprise emission data.

2. The automatic monitoring system for ambient air quality according to claim 1, characterized in that: The Trusted Assessment Module includes the following: The maximum mean difference data between the rated number of external monitoring sites and the enterprise's internal monitoring equipment is obtained per unit time, a difference data set is constructed, and a difference threshold is set to classify the maximum mean difference data into two categories: those greater than or equal to the threshold represent high differences, and those less than or equal to the threshold represent low differences; Based on the probability model of difference data, the probability distribution of high difference and low difference is modeled to obtain the relative probability between the probability of high difference and low difference: The probability that the maximum mean difference data falls within the high difference and low difference ranges is obtained each time; Normalize the probabilities of all times to obtain a normalized probability distribution; The relative probability between the final normalized probability distributions is used as the prevalence index.

3. The automatic monitoring system for ambient air quality according to claim 2, characterized in that: The prevalence index and the mean of the maximum mean difference are compared with the corresponding thresholds respectively. When the prevalence index and the mean of the maximum mean difference are both greater than the corresponding thresholds, an alarm is issued and the monitoring equipment located inside the enterprise needs to be checked.

Images