A Method, Device, Medium and Equipment for Identifying Abnormal Data of PM2.5 Monitoring Equipment

Abstract

The invention relates to a method, device, medium and equipment for identifying abnormal data of a PM2.5 monitoring device, belonging to the technical field of atmospheric monitoring, and aims to solve the problem of low recognition accuracy in identifying abnormal data of PM2.5 monitoring station data in the prior art. The method includes: determining a set of relevant points based on the geographical location and historical data of a target PM2.5 micro-site; determining a first period and a second period according to the target hour; calculating a first correlation in the set of relevant points, and if the first correlation is greater than a first preset threshold, adding the corresponding surrounding PM2.5 micro-site to the comparison point set; obtaining a first eigenvalue according to the first correlation corresponding to each surrounding PM2.5 micro-site in the comparison point set; calculating a second correlation in the comparison point set, and obtaining a second eigenvalue according to each second correlation; if the difference between the first eigenvalue and the second eigenvalue is greater than a second preset threshold, calibrating the data of the target PM2.5 micro-site at the target hour as abnormal data.

Description

Technical Field

[0001] The present invention belongs to the technical field of atmospheric monitoring, and particularly relates to a method, device, medium and equipment for identifying abnormal data of a PM2.5 monitoring device. Background Art

[0002] The data review of the micro-station is used to identify abnormal data of the micro-station, and distinguish the increase in PM2.5 data caused by pollution source emissions and regional transmission in the normal environment from the abnormal PM2.5 data caused by factors such as equipment anomalies and human interference. Commonly, it can be divided into data-based anomaly judgment and anomaly status based on equipment status and parameters. Among them, the latter is based on the micro-station, micro-station equipment, surrounding cameras, and even the sensor status recorded during the manual operation and maintenance process. According to the monitoring situation and manual operation records, it is judged whether the micro-station equipment is normal (for example: camera monitoring, manual inspection finds that someone sprays water through a sprinkler around to cause abnormal data, or the equipment sensor detects a decrease in the intake air flow, and manual inspection finds that there is catkin blocking the air inlet, etc.). The former simply judges data anomalies based on the monitoring data of the micro-station equipment itself and some other monitoring data, and includes various implementation methods from simple threshold judgment to complex algorithms (for example: the difference in the hourly PM2.5 concentration measurement value between the micro-station and the surrounding micro-stations exceeds the threshold, or the micro-station data is lower than the absolute threshold and the humidity parameter is abnormally high).

[0003] In the conventional abnormal data identification and review, it is mainly based on the data information of the point hardware equipment (or other additional information), and the comparison of the data of the point with the data of the surrounding points to judge whether the data needs to be reviewed for anomalies. In many cases, such data-based anomaly identification methods cannot identify some relatively subtle data anomalies, or cannot accurately distinguish data anomalies from local pollution that actually exists.

[0004] Secondly, it is common sense that the PM2.5 concentration must be less than the PM10 concentration. Therefore, if the two are inverted at a single point, at least one of them must be abnormal. However, if some points in an area only monitor PM2.5 and some other points only monitor PM10, the relationship between the two cannot be identified as normal, and the prior art cannot use these data for anomaly identification either.

[0005] In summary, there is a problem of low identification accuracy in the prior art for identifying abnormal data of PM2.5 monitoring stations that needs to be solved. Summary of the Invention

[0006] In view of the above analysis, the embodiments of the present invention are to solve the problem of low identification accuracy in the prior art for identifying abnormal data of PM2.5 monitoring stations.

[0007] The present invention provides a method for identifying abnormal data of a PM2.5 monitoring device, including the following steps:

[0008] S1. Determine a set of relevant points based on the geographical location and historical data of the target PM2.5 microsite, where the set of relevant points includes several surrounding PM2.5 microsites;

[0009] S2. Calibrate the time of the data to be recognized as the target hour, and determine a first period and a second period according to the target hour. The first period includes X hours before the target hour, and the second period includes the target hour and X - 1 hours before the target hour;

[0010] S3. Calculate the first correlation between the historical data of each surrounding PM2.5 microsite in the set of relevant points during the first period and the historical data of the target PM2.5 microsite during the first period. If the first correlation is greater than a first preset threshold, add the corresponding surrounding PM2.5 microsite to the set of comparison points;

[0011] S4. Obtain a first eigenvalue according to the first correlation corresponding to each surrounding PM2.5 microsite in the set of comparison points;

[0012] S5. Calculate the second correlation between the historical data of each surrounding PM2.5 microsite in the set of comparison points during the second period and the historical data of the target PM2.5 microsite during the second period, and obtain a second eigenvalue according to each second correlation;

[0013] S6. If the difference between the first eigenvalue and the second eigenvalue is greater than a second preset threshold, calibrate the data of the target PM2.5 microsite at the target hour as abnormal data.

[0014] In some embodiments, step S1 includes:

[0015] S11. Obtain the surrounding PM2.5 microsites within a radius of 5 - 20 kilometers centered on the target PM2.5 microsite as a first set of points;

[0016] S12. Calculate the third correlation between the historical data of each surrounding PM2.5 microsite in the first set of points during a third period and the historical data of the target PM2.5 microsite during the third period. If the third correlation is greater than a third preset threshold, add the corresponding surrounding PM2.5 microsite to the set of relevant points.

[0017] In some embodiments, the third period includes N days before the target hour, where N is greater than 30, and the value of X ranges from 10 to 48.

[0018] In some embodiments, the calculation formulas for the first correlation, the second correlation, and the third correlation can all be expressed as:

[0019]

[0020] where x mk represents the k-th historical data of the m-th surrounding PM2.5 micro-site in the relevant point set, comparison point set or first point set, and x ak is the k-th historical data of the target PM2.5 micro-site, p is the total number of historical data hours, is the average value of the historical data of the m-th surrounding PM2.5 micro-site, is the average value of the historical data of the target PM2.5 micro-site, and r represents the first correlation, second correlation or third correlation.

[0021] In some embodiments, the value of the first preset threshold ranges from 0.85 to 0.95, and the value of the second preset threshold ranges from 0.02 to 0.05.

[0022] In some embodiments, it further includes: S7. Judging the data abnormality of the target PM2.5 micro-site based on the correlation between the historical data of the PM10 micro-site around the target PM2.5 micro-site and the historical data of the target PM2.5 micro-site, including:

[0023] S71. Determine the PM10-related point set according to the geographical location and historical data of the target PM2.5 micro-site, and the PM10-related point set includes several surrounding PM10 micro-sites;

[0024] S72. Calculate the fourth correlation between the first-period historical data of each surrounding PM10 micro-site in the PM10-related point set and the first-period historical data of the target PM2.5 micro-site. If the fourth correlation is greater than the fourth preset threshold, add the corresponding surrounding PM10 micro-site to the PM10 comparison point set;

[0025] S73. Obtain the fourth eigenvalue according to the fourth correlation corresponding to each surrounding PM10 micro-site in the PM10 comparison point set;

[0026] S74. Calculate the fifth correlation between the second-period historical data of each surrounding PM10 micro-site in the comparison point set and the second-period historical data of the target PM2.5 micro-site, and obtain the fifth eigenvalue according to each fifth correlation;

[0027] S75. If the difference between the fourth eigenvalue and the fifth eigenvalue is greater than the fifth preset threshold, mark the data of the target PM2.5 micro-site at the target hour as abnormal data.

[0028] In some embodiments, step S71 includes:

[0029] S711. Obtain the surrounding PM10 micro-site positions within a radius of 5 - 20 kilometers centered on the target PM2.5 micro-site position as the second position set;

[0030] S712. Calculate the sixth correlation between the third-period historical data of each of the surrounding PM10 micro-site positions in the second position set and the third-period historical data of the target PM2.5 micro-site position. If the sixth correlation is greater than the sixth preset threshold, add the corresponding surrounding PM10 micro-site position to the PM10-related position set.

[0031] The present invention also provides a device for identifying abnormal data of a PM2.5 monitoring device, including:

[0032] A relevant position obtaining module, which determines a relevant position set based on the geographical location and historical data of the target PM2.5 micro-site position, and the relevant position set includes several surrounding PM2.5 micro-site positions;

[0033] A period selection module, which calibrates the time of the data to be identified as the target hour, and determines a first period and a second period according to the target hour. The first period includes X hours before the target hour, and the second period includes the target hour and X - 1 hours before the target hour;

[0034] A comparison position obtaining module, which calculates the first correlation between the first-period historical data of each of the surrounding PM2.5 micro-site positions in the relevant position set and the first-period historical data of the target PM2.5 micro-site position. If the first correlation is greater than the first preset threshold, add the corresponding surrounding PM2.5 micro-site position to the comparison position set;

[0035] A first feature obtaining module, which obtains a first feature value according to the first correlation corresponding to each of the surrounding PM2.5 micro-site positions in the comparison position set;

[0036] A second feature obtaining module, which calculates the second correlation between the second-period historical data of each of the surrounding PM2.5 micro-site positions in the comparison position set and the second-period historical data of the target PM2.5 micro-site position, and obtains a second feature value according to each of the second correlations;

[0037] An abnormality discrimination module, if the difference between the first feature value and the second feature value is greater than the second preset threshold, calibrate the data of the target PM2.5 micro-site position at the target hour as abnormal data.

[0038] The present invention also provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, it implements the PM2.5 monitoring device data anomaly recognition method described in any one of the above embodiments.

[0039] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the PM2.5 monitoring device data anomaly recognition method described in any one of the above embodiments.

[0040] The above embodiments of the present invention have at least the following beneficial effects:

[0041] 1. In the embodiment of the present invention, first, a relevant point set is determined through geographical location and historical data. Then, a first eigenvalue obtained based on the first correlation between the surrounding points and the target point in the first-cycle historical data including the target hour, and a second eigenvalue obtained based on the second correlation between the second-cycle historical data not including the target hour are used. According to the difference between the first eigenvalue and the second eigenvalue, it is possible to more accurately determine whether the data of the target point at the target hour is abnormal.

[0042] 2. The present invention can perform anomaly recognition on the data of the target PM2.5 microsite based on the historical data of the surrounding PM10 microsites and the historical data of the target PM2.5 microsite, and perform anomaly recognition based on multi-source data of multiple surrounding points to improve the recognition accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the embodiments of this specification. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0044] Figure 1 Schematic flowchart of the PM2.5 monitoring device data anomaly recognition method provided by the embodiment of the present invention;

[0045] Figure 2 Schematic architecture diagram of the PM2.5 monitoring device data anomaly recognition device provided by the present invention;

[0046] Figure 3 Schematic architecture diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. It should be noted that, without conflict, the implementation manners and features in the present disclosure can be combined with, separated from, interchanged with, and / or rearranged with each other. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0048] The terms used herein are for the purpose of describing particular embodiments and are not intended to be limiting. As used herein, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are also intended to include the plural forms. In addition, when the terms "comprise" and / or "include" and their variants are used in this specification, it is stated that there are the stated features, integers, steps, operations, components, assemblies, and / or groups thereof, but it does not exclude the existence or addition of one or more other features, integers, steps, operations, components, assemblies, and / or groups thereof. It should also be noted that, as used herein, the terms "substantially", "about", and other similar terms are used as approximate terms and not as degree terms, so they are used to explain the inherent deviations of measured values, calculated values, and / or provided values that those of ordinary skill in the art will recognize.

[0049] The present disclosure will be described below through several specific embodiments. To keep the following description of the embodiments of the present invention clear and concise, the detailed descriptions of known functions and known components are omitted in the present invention. Please refer to Figure 1 , the embodiments of the present invention provide a method for identifying abnormal data of a PM2.5 monitoring device, including the following steps:

[0050] S1. Determine a set of relevant points based on the geographical location and historical data of the target PM2.5 micro-site, and the set of relevant points includes several surrounding PM2.5 micro-sites;

[0051] S2. Calibrate the time of the data to be identified as the target hour, and determine a first period and a second period according to the target hour. The first period includes X hours before the target hour, and the second period includes the target hour and X - 1 hours before the target hour;

[0052] S3. Calculate the first correlation between the first-period historical data of each surrounding PM2.5 micro-site in the set of relevant points and the first-period historical data of the target PM2.5 micro-site. If the first correlation is greater than a first preset threshold, add the corresponding surrounding PM2.5 micro-site to the set of comparison points;

[0053] S4. Obtain a first eigenvalue according to the first correlation corresponding to each of the surrounding PM2.5 micro-site positions in the comparison point position set.

[0054] S5. Calculate the second correlation between the second-period historical data of each of the surrounding PM2.5 micro-site positions in the comparison point position set and the second-period historical data of the target PM2.5 micro-site position, and obtain a second eigenvalue according to each of the second correlations.

[0055] S6. If the difference between the first eigenvalue and the second eigenvalue is greater than a second preset threshold, mark the data of the target PM2.5 micro-site position at the target hour as abnormal data.

[0056] It should be understood that the data of the target hour of the target point position is the object to be abnormally identified by the method provided by the present invention. The present invention can be used to identify the data of a certain hour in the historical data, or can adopt a real-time identification method. Then the target hour is the current hour. The following embodiments of the present invention are described by taking the identification of the data of the current hour as an example. That is to say, in this example, the current hour is equivalent to the target hour.

[0057] In some embodiments, step S1 includes:

[0058] S11. Obtain the surrounding PM2.5 micro-site positions within a radius of 5 - 20 kilometers centered on the target PM2.5 micro-site position as a first point position set.

[0059] Specifically, in some embodiments, for the target PM2.5 micro-site position a, all other PM2.5 micro-site positions within 10 km are taken as the first point position set A1.

[0060] S12. Calculate the third correlation between the third-period historical data of each of the surrounding PM2.5 micro-site positions in the first point position set and the third-period historical data of the target PM2.5 micro-site position. If the third correlation is greater than a third preset threshold, add the corresponding surrounding PM2.5 micro-site position to the relevant point position set.

[0061] Specifically, in an embodiment of the present invention, the points with a third correlation greater than 0.9 are taken to form the relevant point position set A2. That is to say, in this example, the third preset threshold is 0.9.

[0062] In some embodiments, the third period includes N days before the target hour, where N is greater than 30, and the value of X is 10 - 48.

[0063] Specifically, in some embodiments, when calculating the relevant point set, the historical data used is the data from 30 days to 395 days before the current hour (i.e., the data from the previous 1 month to the previous 1 year and 1 month), that is to say, the third period is from 30 days to 395 days before the current hour. It should be understood that the historical data for correlation calculation should be the audited hourly data, which can provide a more accurate data basis.

[0064] In some embodiments, the value of the first preset threshold ranges from 0.85 to 0.95, and the value of the second preset threshold ranges from 0.02 to 0.05.

[0065] In addition, for the determination of the first period and the second period, in one embodiment of the present invention, X is taken as 24. In other words, assuming the current hour is t0, the previous 1 hour is t1, and so on, the historical data of the previous 1 hour and the previous 23 hours (i.e., t1 - t24 historical data) is taken, and the correlation coefficient between the target point a and each point in the set A2 is calculated. Only the points in the calculation result r that are greater than 0.9 (the first preset threshold) are retained as the comparison point set A3, and the median of the correlation coefficients corresponding to these points is denoted as r mid(1-24) . It should be understood that r mid(1-24) is the first eigenvalue in the present invention. In some embodiments, the first eigenvalue and the second eigenvalue can be obtained by taking the median or average of the correlations in the target set, etc. Then the second correlation and the second eigenvalue are obtained using the data of the second period.

[0066] The second eigenvalue is obtained by taking the historical data of the current hour and the previous 23 hours (i.e., t0 - t23 historical data), calculating the correlation coefficient between the target point a and each point in the set A3, and taking the median r of the calculation result r mid(0-23) .

[0067] Calculate r mid(1-24) - r mid(0-23) , if the difference is greater than 0.03, the data of the target point for the current hour is abnormal. Here, the value of the second preset threshold is 0.03.

[0068] In some embodiments, the calculation formulas of the first correlation, the second correlation, and the third correlation can all be expressed as:

[0069]

[0070] where x mk represents the k-th historical data of the m-th surrounding PM2.5 micro-site in the relevant point set, the comparison point set, or the first point set, x ak is the k-th historical data of the target PM2.5 micro-site, p is the total number of historical data hours, is the average of historical data of the m-th surrounding PM2.5 micro-site is the average of historical data of the target PM2.5 micro-site, and r represents the first correlation, the second correlation or the third correlation.

[0071] In some embodiments, it further includes: S7. Judging the data abnormality of the target PM2.5 micro-site based on the correlation between the historical data of the PM10 micro-sites around the target PM2.5 micro-site and the historical data of the target PM2.5 micro-site, including:

[0072] S71. Determining a PM10-related point set according to the geographical location and historical data of the target PM2.5 micro-site, where the PM10-related point set includes several surrounding PM10 micro-sites;

[0073] S72. Calculating the fourth correlation between the first-period historical data of each surrounding PM10 micro-site in the PM10-related point set and the first-period historical data of the target PM2.5 micro-site. If the fourth correlation is greater than the fourth preset threshold, add the corresponding surrounding PM10 micro-site to the PM10 comparison point set B3.

[0074] In some embodiments, the fourth preset threshold is between 0.6 and 0.8. In one embodiment, the value of the fourth preset threshold is 0.75.

[0075] Specifically, let the current hour be t0, the previous hour be t1, and so on. Take the historical data of the previous 1 hour and the previous 23 hours (i.e., the t1-t24 historical data), and calculate the correlation coefficient between the PM2.5 of the target point a and the PM10 of each point in the set B2. The calculation formula refers to the above-mentioned correlation coefficient calculation formula. Only keep the points in the calculation result r that are greater than 0.75 as the comparison point set B3.

[0076] S73. Obtaining a fourth eigenvalue according to the fourth correlation corresponding to each surrounding PM10 micro-site in the PM10 comparison point set.

[0077] Specifically, take the median r of the fourth correlation coefficients of these points bmid(1-24) as the fourth eigenvalue.

[0078] S74. Calculating the fifth correlation between the second-period historical data of each surrounding PM10 micro-site in the comparison point set and the second-period historical data of the target PM2.5 micro-site, and obtaining a fifth eigenvalue according to each fifth correlation;

[0079] Specifically, take the historical data of the current hour and the previous 23 hours (i.e., the historical data from t0 to t23), and calculate the correlation coefficient between the PM2.5 at the target point a and the PM10 at each point in set B3. The calculation formula is the same as in step 1. Take the median r of the calculation result r bmid(0-23) as the fifth eigenvalue.

[0080] In some embodiments, the fourth eigenvalue and the fifth eigenvalue can be obtained by taking the median or the average.

[0081] S75. If the difference between the fourth eigenvalue and the fifth eigenvalue is greater than the fifth preset threshold, then mark the data of the target PM2.5 micro-site at the target hour as abnormal data.

[0082] In some embodiments, the value of the fifth preset threshold ranges from 0.05 to 0.15.

[0083] Specifically, calculate r bmid(1-24) -r bmid(0-23) , if the difference is greater than 0.1, then the data of the target point at the current hour is abnormal. That is, in this embodiment, the value of the fifth preset threshold is 0.1.

[0084] In some embodiments, step S71 includes:

[0085] S711. Obtain the surrounding PM10 micro-sites within a radius of 5 to 20 kilometers centered on the target PM2.5 micro-site as the second point set.

[0086] Specifically, in an embodiment of the present invention, for the target PM2.5 micro-site a, take all other PM10 micro-sites within 10 km as the point set B1.

[0087] S712. Calculate the sixth correlation between the third-period historical data of each of the surrounding PM10 micro-sites in the second point set and the third-period historical data of the target PM2.5 micro-site. If the sixth correlation is greater than the sixth preset threshold, then add the corresponding surrounding PM10 micro-site to the PM10 relevant point set.

[0088] Specifically, in an embodiment of the present invention, the points with a sixth correlation greater than 0.75 form the PM10 relevant point set B2. That is to say, in this example, the sixth preset threshold is 0.75. The range of the third period can refer to the range of the above-mentioned third period.

[0089] The present invention also provides a device for identifying abnormal data of PM2.5 monitoring equipment, as Figure 2 shown, including:

[0090] A relevant point acquisition module determines a set of relevant points based on the geographical location and historical data of the target PM2.5 micro-site. The set of relevant points includes several surrounding PM2.5 micro-sites;

[0091] A period selection module calibrates the time of the data to be recognized as the target hour, and determines a first period and a second period according to the target hour. The first period includes X hours before the target hour, and the second period includes the target hour and X - 1 hours before the target hour;

[0092] A comparison point acquisition module calculates a first correlation between the historical data of the first period of each surrounding PM2.5 micro-site in the set of relevant points and the historical data of the first period of the target PM2.5 micro-site. If the first correlation is greater than a first preset threshold, the corresponding surrounding PM2.5 micro-site is added to the comparison point set;

[0093] A first feature acquisition module obtains a first feature value according to the first correlation corresponding to each surrounding PM2.5 micro-site in the comparison point set;

[0094] A second feature acquisition module calculates a second correlation between the historical data of the second period of each surrounding PM2.5 micro-site in the comparison point set and the historical data of the second period of the target PM2.5 micro-site, and obtains a second feature value according to each second correlation;

[0095] An anomaly discrimination module, if the difference between the first feature value and the second feature value is greater than a second preset threshold, calibrates the data of the target PM2.5 micro-site at the target hour as abnormal data.

[0096] The present invention also provides an electronic device, as Figure 3 shown, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, it implements the PM2.5 monitoring device data anomaly recognition method described in any one of the above embodiments.

[0097] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the PM2.5 monitoring device data anomaly recognition method described in any one of the above embodiments.

[0098] A computer-readable storage medium includes both permanent and non-permanent, removable and non-removable media and can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0099] Those skilled in the art should also be further aware that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of function in the above description. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0100] The steps of the methods or algorithms described in connection with the embodiments disclosed herein can be implemented in hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the art.

[0101] The specific embodiments described above have further elaborated on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying abnormal data of PM2.5 monitoring equipment, characterized in that: The following steps are involved: S1. Determine a set of related points based on the geographical location and historical data of the target PM2.5 micro-site, wherein the set of related points includes several surrounding PM2.5 micro-sites; S2. Mark the time of the data to be identified as the target hour, and determine the first period and the second period according to the target hour, wherein the first period includes X hours before the target hour, and the second period includes the target hour and X-1 hours before the target hour; S3, calculating the first correlation between the first period historical data of each surrounding PM2.5 micro-site in the related point set and the first period historical data of the target PM2.5 micro-site, and if the first correlation is greater than a first preset threshold, adding the corresponding surrounding PM2.5 micro-site to the comparison point set; S4. Obtain a first eigenvalue according to the first correlation corresponding to each of the surrounding PM2.5 micro-site locations in the comparison point set; the first eigenvalue includes the median or average of a plurality of first correlations; S5, calculating the second correlation between the second period historical data of each peripheral PM2.5 micro-site in the comparison point set and the second period historical data of the target PM2.5 micro-site, and obtaining a second eigenvalue according to each of the second correlations; the second eigenvalue includes the median or average of several second correlations; S6. If the difference between the first characteristic value and the second characteristic value is greater than a second preset threshold, the data of the target PM2.5 micro-site at the target hour is marked as abnormal data; Step S1 includes: S11, taking the target PM2.5 micro-site location as the center and the surrounding PM2.5 micro-site locations within a radius of 5 to 20 kilometers as the first point location set; S12. Calculate the third correlation between the third period historical data of each of the surrounding PM2.5 micro-sites in the first point set and the third period historical data of the target PM2.5 micro-site; if the third correlation is greater than a third preset threshold, add the corresponding surrounding PM2.5 micro-site to the relevant point set.

2. The method for identifying abnormal data of PM2.5 monitoring equipment according to claim 1, characterized in that: The third period includes N days before the target hour, where N is greater than 30 and the value of X is 10-48.

3. The method for identifying abnormal data of PM2.5 monitoring equipment according to claim 1, characterized in that: The calculation formulas of the first correlation, the second correlation and the third correlation can all be expressed as: Among them, x mk represents the kth historical data of the mth peripheral PM2.5 micro-site in the relevant point set, the comparison point set or the first point set, x ak is the kth historical data of the target PM2.5 micro-site, p is the total number of hours of historical data, is the historical data average of the mth surrounding PM2.5 micro-station, is the historical data mean of the target PM2.5 micro-site, and r represents the first correlation, the second correlation or the third correlation.

4. The method for identifying abnormal data of PM2.5 monitoring equipment according to claim 1, characterized in that: The value of the first preset threshold is between 0.85 and 0.95, and the value of the second preset threshold is between 0.02 and 0.

05.

5. The method for identifying abnormal data of PM2.5 monitoring equipment according to claim 1, characterized in that: Also includes: S7, based on the correlation between the historical data of the PM10 micro-sites around the target PM2.5 micro-site and the historical data of the target PM2.5 micro-site, determining the data abnormality of the target PM2.5 micro-site, including: S71, determining a PM10 related point set according to the geographical location and historical data of the target PM2.5 micro-site, wherein the PM10 related point set includes a number of surrounding PM10 micro-sites; S72, calculating the fourth correlation between the first cycle historical data of each peripheral PM10 micro-site in the PM10 related point set and the first cycle historical data of the target PM2.5 micro-site, and if the fourth correlation is greater than a fourth preset threshold, adding the corresponding peripheral PM10 micro-site to the PM10 comparison point set; S73, obtaining a fourth eigenvalue according to the fourth correlation corresponding to each of the peripheral PM10 micro-site locations in the PM10 comparison point set; S74, calculating the fifth correlation between the second period historical data of each peripheral PM10 micro-site in the comparison point set and the second period historical data of the target PM2.5 micro-site, and obtaining a fifth eigenvalue according to each of the fifth correlations; S75. If the difference between the fourth eigenvalue and the fifth eigenvalue is greater than the fifth preset threshold, the data of the target PM2.5 micro-station at the target hour is calibrated as abnormal data.

6. The method for identifying abnormal data of PM2.5 monitoring equipment according to claim 5, characterized in that: Step S71 includes: S711, taking the target PM2.5 micro-site as the center and the surrounding PM10 micro-sites within a radius of 5 to 20 kilometers as the second point set; S712. Calculate the sixth correlation between the third-period historical data of each of the surrounding PM10 micro-sites in the second point set and the third-period historical data of the target PM2.5 micro-site. If the sixth correlation is greater than the sixth preset threshold, add the corresponding surrounding PM10 micro-site to the PM10-related point set.

7. A device for identifying abnormal data of PM2.5 monitoring equipment, characterized in that: include: A related point acquisition module determines a related point set based on the geographical location and historical data of the target PM2.5 micro-site, wherein the related point set includes several surrounding PM2.5 micro-sites; The cycle selection module marks the time of the data to be identified as the target hour, and determines the first cycle and the second cycle according to the target hour, wherein the first cycle includes X hours before the target hour, and the second cycle includes the target hour and X-1 hours before the target hour; A comparison point acquisition module calculates a first correlation between the first period historical data of each surrounding PM2.5 micro-site in the relevant point set and the first period historical data of the target PM2.5 micro-site, and if the first correlation is greater than a first preset threshold, the corresponding surrounding PM2.5 micro-site is added to the comparison point set; A first feature acquisition module, which acquires a first feature value according to a first correlation corresponding to each of the surrounding PM2.5 micro-site locations in the comparison point set; the first feature value includes a median or an average value of a plurality of first correlations; A second feature acquisition module calculates the second correlation between the second period historical data of each peripheral PM2.5 micro-site in the comparison point set and the second period historical data of the target PM2.5 micro-site, and obtains a second feature value according to each of the second correlations; the second feature value includes the median or average of several second correlations; an abnormality identification module, if the difference between the first characteristic value and the second characteristic value is greater than a second preset threshold, marking the data of the target PM2.5 micro-site at the target hour as abnormal data; The relevant point acquisition modules include: S11, taking the target PM2.5 micro-site location as the center and the surrounding PM2.5 micro-site locations within a radius of 5 to 20 kilometers as the first point location set; S12. Calculate the third correlation between the third period historical data of each of the surrounding PM2.5 micro-sites in the first point set and the third period historical data of the target PM2.5 micro-site; if the third correlation is greater than a third preset threshold, add the corresponding surrounding PM2.5 micro-site to the relevant point set.

8. An electronic device, characterized in that: It includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the PM2.5 monitoring equipment data anomaly identification method as described in any one of claims 1-6 is implemented.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method for identifying abnormal data of PM2.5 monitoring equipment as described in any one of claims 1-6 is implemented.

Images