Method, system and equipment for identifying abnormal particulate matter concentration and medium

Abstract

The invention relates to a method, a system, equipment and a medium for identifying abnormal particulate matter concentration, and belongs to the technical field of atmospheric environment monitoring, and the method comprises the following steps: obtaining a first particulate matter concentration sequence and a second particulate matter concentration sequence of each station in a to-be-identified area in the same time period; calculating an association degree matrix according to the first particulate matter concentration sequence, and dividing the to-be-identified area into a plurality of blocks; setting the station with the highest first particulate matter concentration in each block as a first station, and calculating the relative deviation between the first particulate matter concentration of the first station and the average value of the first particulate matter concentrations of other stations in the block at the same moment; preliminarily judging whether the first particulate matter concentration of the first station is abnormal or not according to the relative deviation; and if the first particulate matter concentration is preliminarily judged to be abnormal, calculating a Pearson's correlation coefficient according to the first particulate matter concentration sequence and the second particulate matter concentration sequence of the first station, and finally judging whether the first particulate matter concentration of the first station is abnormal or not according to the Pearson's correlation coefficient.

Description

Technical Field

[0001] The present invention belongs to the technical field of atmospheric environment monitoring, and in particular relates to a method, system, device and medium for identifying abnormal particle concentration. Background Art

[0002] At present, atmospheric particulate matter has become the main factor of air pollution in my country. Monitoring data is the key basis for effectively formulating environmental policies and evaluating policies and accurately evaluating the effectiveness of policies. Therefore, it is crucial to ensure the authenticity and accuracy of atmospheric particulate matter monitoring data. However, in actual monitoring, abnormal particle concentration events may occur due to multiple complex factors, such as the invasion of particles such as catkins and sand into monitoring equipment or sampling systems, or the accumulation of dust due to the accumulation of time during the sampling process, which in turn causes the shedding of large particles. These seriously affect the accuracy of monitoring data and cannot truly reflect the air quality conditions. They must be discovered in a timely manner and the sampling system or monitoring equipment must be maintained.

[0003] At present, there is still a lack of effective methods for identifying abnormal atmospheric particulate matter data. Usually, it is determined manually or by setting a single concentration threshold, which has low timeliness and accuracy. Therefore, it is urgent to develop an efficient and intelligent method for identifying abnormal particle concentrations to accurately identify abnormal high-value events of particle concentrations triggered by multiple complex factors, so as to ensure timely implementation of manual maintenance measures and reduce the impact on the quality of monitoring data. Summary of the invention

[0004] In view of the above analysis, the embodiments of the present invention are intended to provide a method, system, device and medium for identifying abnormal particle concentration, so as to solve one or more of the above problems existing in the prior art. The purpose of the present invention is achieved as follows:

[0005] A first aspect of the present invention provides a method for identifying abnormal particle concentration, comprising:

[0006] Obtain a first particle concentration sequence and a second particle concentration sequence at the same time period for each station in the area to be identified;

[0007] Calculating a correlation matrix according to the first particle concentration sequence, and dividing the area to be identified into a plurality of blocks according to the correlation matrix;

[0008] The station with the highest first particle concentration in each block is set as the first station, and the relative deviation of the first particle concentration of the first station and the average first particle concentration of other stations in the block at the same time is calculated;

[0009] Preliminarily determine whether the first particle concentration at the first station is abnormal according to the relative deviation;

[0010] If it is preliminarily determined that the first particle concentration is abnormal, the Pearson correlation coefficient is calculated based on the first particle concentration sequence and the second particle concentration sequence of the first station, and whether the first particle concentration of the first station is abnormal is finally determined based on the Pearson correlation coefficient.

[0011] Furthermore, the first particle concentration and the second particle concentration are concentrations of different types of particles divided by particle size range.

[0012] Furthermore, the calculation of the correlation matrix based on the first particle matter concentration sequence includes: preprocessing the first particle matter concentration sequence of each station; calculating a difference sequence based on the first particle matter concentration sequences of two different stations in the same time period; calculating the correlation coefficients between all stations according to the difference sequence, and calculating the grey correlation degree according to the correlation coefficient; and calculating the correlation matrix according to the grey correlation degree.

[0013] Furthermore, dividing the area to be identified into a plurality of blocks according to the correlation matrix includes: drawing a grey correlation heat map according to the correlation matrix, and dividing the area to be identified into a plurality of blocks according to a range of the grey correlation.

[0014] Furthermore, the preliminarily judging whether the first particle concentration of the first station is abnormal based on the relative deviation includes: if the average first particle concentration of other stations in the block except the first station at the same time is greater than the first particle concentration threshold, and the relative deviation is greater than the first threshold, then preliminarily judging that the first particle concentration of the first station is abnormal.

[0015] Further, the calculating of the Pearson correlation coefficient based on the first particle concentration sequence and the second particle concentration sequence of the first station, and finally judging whether the first particle concentration of the first station is abnormal based on the Pearson correlation coefficient, include: if it is preliminarily judged that the first particle concentration of the first station is abnormal, intercepting a part of a specific historical period in the first particle concentration sequence and the second particle concentration sequence of the first station, and calculating the Pearson correlation coefficient; if the Pearson correlation coefficient is less than a second threshold value, finally judging that the first particle concentration of the first station is abnormal.

[0016] Furthermore, the method further includes: acquiring a new first particle concentration sequence and a new second particle concentration sequence at specific time intervals to update a correlation matrix and dynamically divide the area to be identified.

[0017] A second aspect of the present invention provides a system for identifying abnormal particle concentration, comprising:

[0018] An acquisition module, used to acquire a first particle concentration sequence and a second particle concentration sequence at the same time period at each station in the area to be identified;

[0019] A dynamic division module, used for calculating a correlation matrix according to the first particle concentration sequence, and dividing the area to be identified into a plurality of blocks according to the correlation matrix;

[0020] A deviation calculation module, used to set the station with the highest first particle concentration in each block as the first station, and calculate the relative deviation of the first particle concentration of the first station and the average first particle concentration of other stations in the block at the same time;

[0021] A preliminary judgment module, used for preliminarily judging whether the first particle concentration at the first station is abnormal according to the relative deviation;

[0022] The final judgment module is used to calculate the Pearson correlation coefficient according to the first particle concentration sequence and the second particle concentration sequence of the first station if the first particle concentration is initially judged to be abnormal, and finally judge whether the first particle concentration of the first station is abnormal according to the Pearson correlation coefficient.

[0023] According to a third aspect of the present invention, there is provided an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for identifying abnormal particle concentration described in any one of the embodiments is implemented.

[0024] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for identifying abnormal particle concentration described in any one of the embodiments.

[0025] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0026] The method for identifying abnormal particle concentration provided by the present invention divides the area to be identified into smaller blocks by calculating the correlation matrix, which is convenient for subsequent accurate identification and maintenance of abnormal sites, and then makes a preliminary judgment through relative deviation, and then further judges whether the particle concentration is abnormal by calculating the Pearson correlation coefficient, thereby improving the accuracy of identifying abnormal particle concentration. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of this specification. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0028] Figure 1 A flow chart of a method for identifying abnormal particle concentration provided in Example 1 of the present invention;

[0029] Figure 2 A schematic diagram of a grey correlation heat map provided in Example 1 of the present invention;

[0030] Figure 3 A schematic diagram of a system for identifying abnormal particle concentration provided in Example 2 of the present invention;

[0031] Figure 4 This is a schematic diagram of the electronic device architecture provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, 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 in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. It should be noted that, in the absence of conflict, the embodiments and features in the embodiments disclosed in this disclosure can be combined, separated, interchanged and / or rearranged with each other. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0033] Example 1

[0034] A specific embodiment of the present invention, as Figure 1-2 As shown, a method for identifying abnormal particle concentration is disclosed, comprising the following steps:

[0035] S1. Obtain a first particle concentration sequence and a second particle concentration sequence at the same time period for each station in the area to be identified.

[0036] In this embodiment, the first particle matter concentration and the second particle matter concentration are the concentrations of particles divided according to different particle size ranges. For example, PM2.5 (fine particulate matter, with a diameter not exceeding 2.5 microns) of each monitoring station in the area to be identified is the first particle matter concentration, and PM10 (inhalable particulate matter, with a diameter not exceeding 10 microns) is the second particle matter concentration. The first particle matter concentrations in hours with a time period of one month constitute a first particle matter concentration sequence, and similarly, the second particle concentrations constitute a second particle concentration sequence.

[0037] S2. Calculate a correlation matrix according to the first particle concentration sequence, and divide the area to be identified into multiple blocks according to the correlation matrix.

[0038] In this embodiment, step S2 specifically includes:

[0039] S201, preprocessing the first particle concentration sequence of each station;

[0040] Specifically, when monitoring particulate matter concentration at a monitoring station, erroneous or missing data may be generated due to equipment failure, human operational errors, data transmission errors, etc. Therefore, in order to improve data quality and ensure the accuracy and reliability of monitoring results, the data should be preliminarily processed. For example, the 3σ rule can be used to clean the first particulate matter concentration sequence, calculate the mean μ and standard deviation σ, and regard data outside the interval [μ-3σ,μ+3σ] as outliers. For outliers or missing values, the mean μ is used to replace or supplement them.

[0041] S202, calculating a difference sequence according to first particle concentration sequences of two different stations in the same period;

[0042] For example, X i and X j represents the first particulate matter concentration sequence after pretreatment at two different stations in the same period, and the difference sequence is expressed as:

[0043] Δij(k)=|X ik -X jk |, k = 1, 2, ... m;

[0044] Among them, X ik and X jk They respectively represent the first particle concentration values ​​monitored by two different stations at time k.

[0045] S203, calculating the correlation coefficients between all sites according to the difference sequence, and calculating the grey correlation degree according to the correlation coefficients;

[0046] Specifically, the correlation coefficient between site i and site j at time k is expressed as follows:

[0047]

[0048] Among them, ρ represents the resolution coefficient, which is set manually and usually set to 0.5;

[0049] X i and X j The grey relational degree is expressed as follows:

[0050]

[0051] Where m represents the maximum moment of the first particle concentration sequence and the second particle concentration sequence. When i=j, r ij =1.

[0052] S204, calculating a correlation matrix according to the grey correlation degree;

[0053] Specifically, the correlation matrix of the entire area to be identified is expressed as follows:

[0054]

[0055] S205 , drawing a grey correlation degree heat map according to the correlation degree matrix, and dividing the area to be identified into a plurality of blocks according to the range of the grey correlation degree.

[0056] For example, using a drawing tool to draw Figure 2 The grey correlation heat map shown in the figure can be divided into three blocks according to the actual situation. For example, the 12 sites can be divided into three blocks according to the three ranges of [-1, -0.3], (-0.3, 0.5], and (0.5, 1] ​​to facilitate the subsequent identification of anomalies.

[0057] S3. The station with the highest first particle concentration in each block is set as the first station, and the relative deviation of the first particle concentration of the first station and the average first particle concentration of other stations in the block at the same time is calculated.

[0058] Specifically, after multiple blocks are obtained in step S205, for each block, the station with the highest first particle concentration in the 1-m time period is found and set as the first station, and the moment with the highest first particle concentration is recorded. Then, the relative deviation between the first particle concentration of the first station at that moment and the average first particle concentration of other stations in the block at the same moment is calculated, which is expressed as follows:

[0059]

[0060] Among them, X a represents the first particle concentration at the first station, It represents the average value of the first particle concentration of other stations in the block at the same time except the first station; the relative deviation helps to quantify the degree of difference between a single station and the block as a whole.

[0061] S4. Preliminarily determine whether the first particle concentration at the first station is abnormal based on the relative deviation.

[0062] In this embodiment, step S4 specifically includes:

[0063] If the average first particle concentration of other sites in the block except the first site at the same time is greater than the first particle concentration threshold, and the relative deviation is greater than the first threshold, it is preliminarily determined that the first particle concentration of the first site is abnormal.

[0064] Specifically, the first particle concentration threshold can be adjusted according to actual conditions. When PM2.5 is used as the first particle concentration, the first particle concentration threshold should be set to 35 μg / m 3, the first threshold is set to 0.5, when When ε>0.5, it indicates that the first particle concentration at the first station in the block is higher than the first particle concentration at other stations, and the concentration should be preliminarily judged to be abnormal.

[0065] S5. If it is preliminarily determined that the first particle concentration is abnormal, calculate the Pearson correlation coefficient based on the first particle concentration sequence and the second particle concentration sequence of the first station, and finally determine whether the first particle concentration of the first station is abnormal based on the Pearson correlation coefficient.

[0066] Specifically, after step S4 preliminarily determines that the first particle concentration at the first station is abnormal, in order to accurately identify whether it is abnormal, further judgment should be performed, including: if it is preliminarily determined that the first particle concentration at the first station is abnormal, intercepting a specific historical period of the first particle concentration sequence and the second particle concentration sequence of the first station, and calculating the Pearson correlation coefficient; if the Pearson correlation coefficient is less than the second threshold value, it is finally determined that the first particle concentration at the first station is abnormal.

[0067] For example, assuming that the first site has the highest first particle concentration at time q, the first particle concentration sequence and the second particle concentration sequence of the [q-5, q] time period are intercepted, and the Pearson correlation coefficient between the two is calculated as follows:

[0068]

[0069] Among them, X i Indicates the hourly value of the first particulate matter concentration, Y i Indicates the hourly value of the second particulate matter concentration, Represents X i The average value of Represents Y i The average value of

[0070] The Pearson correlation coefficient can reflect the degree of linear correlation between the first concentration sequence and the second concentration sequence. When the Pearson correlation coefficient is less than the second threshold, it means that the correlation between the first particle concentration and the second particle concentration at the first station in this time period is poor, and it is finally judged that the first particle concentration at the first station is indeed abnormal.

[0071] It should be noted that the second threshold is between 0 and 1, and is set to 0.7 in this embodiment, and can be adjusted according to actual conditions.

[0072] In some embodiments, the method for identifying abnormal particle concentration further includes: acquiring a new first particle concentration sequence and a new second particle concentration sequence at specific time intervals to update a correlation matrix and dynamically divide the area to be identified.

[0073] Exemplarily, the first particle concentration sequence and the second particle concentration sequence of each station in the area to be identified are re-obtained every month, the correlation matrix is ​​recalculated, the area to be identified is re-divided, and whether an abnormality occurs is re-determined to enhance the dynamics of the identification process.

[0074] In some embodiments, when step S5 finally determines that the first particle concentration of the first station is abnormal, it also includes forming an alarm work order, and pushing the alarm work order to the operation and maintenance personnel and relevant personnel of the monitoring station; the operation and maintenance personnel promptly go to the site to investigate, determine the cause and handle it in a timely manner until the alarm is lifted, and fill in the operation and maintenance work order for this alarm handling; the relevant personnel of the monitoring station promptly check whether the alarm is lifted and keep relevant records.

[0075] Compared with the prior art, the method for identifying abnormal particle matter concentration provided in this embodiment divides the area to be identified into smaller blocks by calculating the correlation matrix, which is convenient for subsequent accurate identification and maintenance of abnormal sites, and then makes a preliminary judgment through relative deviation, and then further judges whether the particle matter concentration is abnormal by calculating the Pearson correlation coefficient, thereby improving the accuracy of identifying abnormal particle matter concentration.

[0076] Example 2

[0077] This embodiment provides a system for identifying abnormal particle concentrations, such as Figure 3 As shown, including:

[0078] An acquisition module, used to acquire a first particle concentration sequence and a second particle concentration sequence at the same time period at each station in the area to be identified;

[0079] A dynamic division module, used for calculating a correlation matrix according to the first particle concentration sequence, and dividing the area to be identified into a plurality of blocks according to the correlation matrix;

[0080] A deviation calculation module, used to set the station with the highest first particle concentration in each block as the first station, and calculate the relative deviation of the first particle concentration of the first station and the average first particle concentration of other stations in the block at the same time;

[0081] A preliminary judgment module, used for preliminarily judging whether the first particle concentration at the first station is abnormal according to the relative deviation;

[0082] The final judgment module is used to calculate the Pearson correlation coefficient according to the first particle concentration sequence and the second particle concentration sequence of the first station if the first particle concentration is initially judged to be abnormal, and finally judge whether the first particle concentration of the first station is abnormal according to the Pearson correlation coefficient.

[0083] Example 3

[0084] This embodiment provides an electronic device, such as Figure 4 As shown, it includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the method for identifying abnormal particle concentration as described in any of the above embodiments is implemented.

[0085] Example 4

[0086] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for identifying abnormal particle concentration as described in any of the above embodiments is implemented.

[0087] Computer readable storage media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. 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 technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0088] The professionals should further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians 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 the present invention.

[0089] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0090] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for identifying abnormal particle concentration, characterized in that: include: Obtain a first particle concentration sequence and a second particle concentration sequence at the same time period for each station in the area to be identified; Calculating a correlation matrix according to the first particle concentration sequence, and dividing the area to be identified into a plurality of blocks according to the correlation matrix; The station with the highest first particle concentration in each block is set as the first station, and the relative deviation of the first particle concentration of the first station and the average first particle concentration of other stations in the block at the same time is calculated; Preliminarily determine whether the first particle concentration at the first station is abnormal according to the relative deviation; If it is preliminarily determined that the first particle concentration is abnormal, the Pearson correlation coefficient is calculated based on the first particle concentration sequence and the second particle concentration sequence of the first station, and whether the first particle concentration of the first station is abnormal is finally determined based on the Pearson correlation coefficient.

2. The method for identifying abnormal particle concentration according to claim 1, characterized in that: The first particle concentration and the second particle concentration are concentrations of different types of particles divided by particle size range.

3. The method for identifying abnormal particle concentration according to claim 1, characterized in that: The calculating the correlation matrix according to the first particle concentration sequence includes: Preprocessing the first particle concentration sequence of each station; Calculate the difference sequence based on the first particle concentration sequence of two different stations in the same period; Calculate the correlation coefficients between all sites according to the difference sequence, and calculate the grey correlation degree according to the correlation coefficients; A correlation matrix is ​​calculated according to the grey correlation degree.

4. The method for identifying abnormal particle concentration according to claim 3, characterized in that: The step of dividing the area to be identified into a plurality of blocks according to the association matrix comprises: A grey correlation degree heat map is drawn according to the correlation degree matrix, and the area to be identified is divided into a plurality of blocks according to the range of the grey correlation degree.

5. The method for identifying abnormal particle concentration according to claim 1, characterized in that: The preliminarily determining whether the first particle concentration at the first station is abnormal according to the relative deviation includes: If the average first particle concentration of other sites in the block except the first site at the same time is greater than the first particle concentration threshold, and the relative deviation is greater than the first threshold, it is preliminarily determined that the first particle concentration of the first site is abnormal.

6. The method for identifying abnormal particle concentration according to claim 5, characterized in that: The calculating of the Pearson correlation coefficient according to the first particle concentration sequence and the second particle concentration sequence of the first station, and finally judging whether the first particle concentration of the first station is abnormal according to the Pearson correlation coefficient, comprises: If it is preliminarily determined that the first particle concentration at the first station is abnormal, the first particle concentration sequence and the second particle concentration sequence at the first station are intercepted for a specific historical period, and the Pearson correlation coefficient is calculated; If the Pearson correlation coefficient is less than the second threshold, it is ultimately determined that the first particle concentration at the first station is abnormal.

7. The method for identifying abnormal particle concentration according to any one of claims 1 to 6, characterized in that: Also includes: A new first particle concentration sequence and a new second particle concentration sequence are acquired at specific time intervals to update the correlation matrix and dynamically divide the area to be identified.

8. A system for identifying abnormal particle concentration, characterized in that: The system comprises: An acquisition module, used to acquire a first particle concentration sequence and a second particle concentration sequence at the same time period at each station in the area to be identified; A dynamic division module, used for calculating a correlation matrix according to the first particle concentration sequence, and dynamically dividing the area to be identified into a plurality of blocks according to the correlation matrix; A deviation calculation module, used to set the station with the highest first particle concentration in each block as the first station, and calculate the relative deviation of the first particle concentration of the first station and the average first particle concentration of other stations in the block at the same time; A preliminary judgment module, used for preliminarily judging whether the first particle concentration at the first station is abnormal according to the relative deviation; The final judgment module is used to calculate the Pearson correlation coefficient according to the first particle concentration sequence and the second particle concentration sequence of the first station if the first particle concentration is initially judged to be abnormal, and finally judge whether the first particle concentration of the first station is abnormal according to the Pearson correlation coefficient.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for identifying abnormal particle concentration according to any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the method for identifying abnormal particle concentration according to any one of claims 1 to 7 is implemented.

Images