Cluster calibration method and device of particulate matter sensor, terminal and storage medium

Abstract

The invention relates to the technical field of environment monitoring, in particular to a particle sensor cluster calibration method and device, a terminal and a storage medium. The method comprises the following steps: co-arranging a quality control micro-station and standard particulate matter monitoring equipment, and obtaining a quality control calibration coefficient of each channel of the quality control micro-station; placing the quality control micro-station and the plurality of common micro-stations in the same environment for particulate matter concentration acquisition to obtain reference signals and particulate matter concentration original data, and calculating a channel consistency index between each common micro-station and the quality control micro-station; determining a micro-station calibration coefficient of each channel of each common micro-station according to the channel consistency index and the quality control calibration coefficient; and calibrating the particulate matter concentration original data by adopting the micro-station calibration coefficient, and outputting the corrected particulate matter concentration value. According to the invention, the problems of low efficiency, high cost, poor cross-device parameter mobility and insufficient sensor channel specificity adaptation of a station-by-station calibration mode in the prior art can be solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of environmental monitoring, and in particular to a cluster calibration method and device for particulate matter sensors, a terminal and a storage medium. BACKGROUND

[0002] With the increasing demand for air quality monitoring, low-cost air quality micro stations have been widely used in air quality monitoring networks due to their flexibility and low cost, and have become an important supplement to traditional national standard monitoring equipment, helping to achieve more detailed and widely covered environmental air quality monitoring.

[0003] Currently, the calibration of low-cost air quality micro stations mainly uses the traditional station-by-station model training method, which requires comparing a single micro station with a standard monitoring device and establishing a calibration model for each device. In addition, some studies attempt to model the data collected by the micro station using machine learning algorithms to correct measurement errors.

[0004] However, the traditional station-by-station calibration method is time-consuming and inefficient, and cannot meet the demand for rapid deployment of large-scale micro stations. Although machine learning modeling has been explored, it still lacks a consistent calibration solution that can be efficiently applied to batch micro stations due to poor cross-device parameter transferability and insufficient adaptation to sensor channel specificity. SUMMARY

[0005] The embodiments of the present application provide a cluster calibration method, device, terminal and storage medium for particulate matter sensors to solve the problems of low efficiency and high cost of the existing station-by-station calibration method, as well as poor cross-device parameter transferability and insufficient adaptation to sensor channel specificity.

[0006] In a first aspect, the embodiments of the present application provide a cluster calibration method for particulate matter sensors, comprising: co-locating a quality control micro station with a standard particulate matter monitoring device to obtain quality control calibration coefficients for each channel of the quality control micro station; placing the quality control micro station and a plurality of ordinary micro stations in the same environment to collect particulate matter concentration data, obtaining a reference signal of the quality control micro station and particulate matter concentration raw data for each channel of each ordinary micro station; calculating a channel consistency index between each ordinary micro station and the quality control micro station based on the reference signal and the particulate matter concentration raw data; determining a micro station calibration coefficient for each channel of each ordinary micro station based on the channel consistency index and the quality control calibration coefficient; calibrating the particulate matter concentration raw data for the corresponding channel of the corresponding ordinary micro station using the micro station calibration coefficient, and outputting the corrected particulate matter concentration value.

[0007] In a possible implementation, the channel consistency index between each normal micro station and the quality control micro station is calculated according to the reference signal and the particulate matter concentration raw data, including: At least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient of the corresponding channel data of each normal micro station and the quality control micro station is calculated according to the reference signal and the particulate matter concentration raw data.

[0008] In a possible implementation, the micro station calibration coefficient of each channel of each normal micro station is determined according to the channel consistency index and the quality control calibration coefficient, including: It is detected whether at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets a preset condition; If at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets the preset condition, the product of the quality control calibration coefficient and a consistency calibration coefficient is determined as the micro station calibration coefficient of the corresponding channel of the current normal micro station, where the consistency calibration coefficient is a calibration coefficient obtained when the current normal micro station is calibrated against the quality control micro station. The micro station calibration coefficient of each channel of each normal micro station is determined according to the above method of determining the micro station calibration coefficient of the corresponding channel of the current normal micro station.

[0009] In a possible implementation, after it is detected whether at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets a preset condition, the method further includes: If at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets the preset condition, the quality control calibration coefficient is weighted, and the weighted quality control calibration coefficient is determined as the micro station calibration coefficient of the corresponding channel of the current normal micro station.

[0010] In a possible implementation, the method of determining the weighted quality control calibration coefficient is: The weight is determined based on the dynamic of at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient. The weighted calibration coefficient is determined according to wherein, represents the determined weighted calibration coefficient, represents the weight, represents the quality control calibration coefficient of the quality control micro station, represents the consistency calibration coefficient.

[0011] In a possible implementation, after detecting whether the at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets the preset condition, the method further includes: If none of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets the preset condition, the method further includes:

[0012] In a possible implementation, after detecting whether the at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets the preset condition, the method further includes: If at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient does not meet the preset condition, the method further includes:

[0013] In a second aspect, an embodiment of the present application provides a cluster calibration system of a particulate matter sensor, including: A quality control micro station configured to be co-located with a standard particulate matter monitoring device, and configured to obtain a quality control calibration coefficient of each channel; A plurality of ordinary micro stations configured to be co-located with the quality control micro station in the same environment to collect particulate matter concentration data of each channel; The quality control micro station is further configured to obtain a reference signal of each channel; A consistency analysis module configured to calculate a channel consistency index between each ordinary micro station and the quality control micro station according to the reference signal and the particulate matter concentration data; A calibration module configured to determine a micro station calibration coefficient of each channel of each ordinary micro station according to the channel consistency index and the quality control calibration coefficient; The plurality of ordinary micro stations are further configured to calibrate particulate matter concentration data of a corresponding channel of a corresponding ordinary micro station by using the micro station calibration coefficient, and output a corrected particulate matter concentration value.

[0014] In a third aspect, an embodiment of the present application provides a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements steps of a cluster calibration method of a particulate matter sensor when executing the computer program.

[0015] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the cluster calibration method of the particulate matter sensor according to the first aspect or any possible implementation manner of the first aspect.

[0016] The embodiment of the present application provides a particulate matter sensor cluster calibration method, device, terminal and storage medium. The quality control micro station and the standard particulate matter monitoring equipment are co-located, and quality control calibration coefficients of each channel of the quality control micro station are acquired. The quality control micro station and a plurality of ordinary micro stations are placed in the same environment to collect particulate matter concentration, and reference signals of the quality control micro station and particulate matter concentration original data of each channel of each ordinary micro station are obtained. According to the reference signals and the particulate matter concentration original data, a channel consistency index between each ordinary micro station and the quality control micro station is calculated. According to the channel consistency index and the quality control calibration coefficient, a micro station calibration coefficient of each channel of each ordinary micro station is determined. The micro station calibration coefficient is used to calibrate the particulate matter concentration original data of the corresponding channel of the corresponding ordinary micro station, and a corrected particulate matter concentration value is output. The embodiment of the present application can output the corrected particulate matter concentration value without manual modeling and training of each ordinary micro station, reduce the labor and computing power cost, build a regional level calibration anchor point through the quality control micro station, share and dynamically adapt the calibration coefficient, and realize the consistency calibration scheme of the batch of ordinary micro stations. The embodiment of the present application can complete the particulate matter concentration calibration without complex machine modeling, is more efficient and has lower complexity. BRIEF DESCRIPTION OF DRAWINGS In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0017] Figure 1 is the implementation flowchart of the particulate matter sensor cluster calibration method provided by the embodiment of the present application; Figure 2 is the flowchart of determining the micro station calibration coefficient of each channel of each ordinary micro station provided by the embodiment of the present application; Figure 3 is the structural schematic diagram of the particulate matter sensor cluster calibration system provided by the embodiment of the present application; Figure 4 is the schematic diagram of the terminal provided by the embodiment of the present application. DETAILED DESCRIPTION

[0018] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, technologies, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0019] In order to make the objects, technical solutions and advantages of the present application clearer, the following will be described by specific embodiments in conjunction with the accompanying drawings.

[0020] Figure 1 The implementation flowchart of the cluster calibration method of the particulate matter sensor provided by the embodiments of the present application is described in detail as follows. In step 101, the quality control micro station is co-located with the standard particulate matter monitoring device to obtain the quality control calibration coefficients of each channel of the quality control micro station.

[0021] In the particulate matter sensor calibration scenario, "co-located" means that the quality control micro station and the national standard particulate matter monitoring device (hereinafter referred to as "national standard device") are deployed under completely consistent environmental exposure conditions. Through close matching of physical positions and synchronous adaptation of environmental elements, it is ensured that the air samples collected by the two have high representativeness and comparability, thereby providing a basis for subsequent accurate acquisition of quality control calibration coefficients. The core goal is to eliminate the interference of environmental differences on monitoring data, so that the signal change of the quality control micro station can truly reflect the fluctuation characteristics of the particulate matter concentration measured by the national standard device.

[0022] Optionally, at least one quality control micro station can be co-located with the standard particulate matter monitoring device in the present embodiment, so that the quality control calibration coefficients of at least one quality control micro station can be obtained, so as to subsequently use each quality control micro station as a reference anchor point to perform channel consistency analysis on multiple ordinary micro stations in the same area.

[0023] Optionally, the quality control calibration coefficients of the quality control micro station are obtained through a multiple linear regression model, and the multiple linear regression model uses the particulate matter concentration output by the national standard device as the dependent variable and the channel signals of the quality control micro station as the independent variable.

[0024] In step 102, the quality control micro station and multiple ordinary micro stations are placed in the same environment to collect particulate matter concentration, so as to obtain the reference signal of the quality control micro station and the particulate matter concentration original data of each channel of each ordinary micro station.

[0025] The ordinary micro station can be a low-cost multi-channel sensor, and the particle size of the particulate matter output by each channel thereof is different. The particulate matter concentration original data output by all channels can be collected.

[0026] Optionally, the channel of the sensor can be a 12-channel sensor, and for example, the multiple particle size channels can include 0.1 -0.3 , 0.3 -0.5 , 0.5 -1.0 , 1.0 -2.5 , 2.5 -4.0 , 4.0 -7.0 , 7.0 -8.0 , 8.0 -10.0 , 10.0 -15.0 , 15.0 -20.0 , 20.0 The 12 particle size channels above.

[0027] Optionally, the common microsite and the quality control microsite are placed in the same environment for signal collection, for example, the same environment can be obtained by dusting or outdoor natural diffusion.

[0028] Optionally, all the acquired particulate matter concentration raw data is preprocessed to obtain time-aligned, complete and correct particulate matter concentration data for subsequent consistency index calculation, microsite calibration coefficient determination, etc.

[0029] For example, time alignment, missing value filling and outlier removal can be performed.

[0030] Optionally, the particulate matter concentration data of the common microsite after preprocessing can be denoted as: ; The reference signal of the quality control microsite after preprocessing can be denoted as: ; Wherein, represents the data set of the th channel of the common microsite, represents the data set of the th channel of the quality control microsite, represents the th group of particulate matter concentration raw data in the th channel of the common microsite, represents the th group of reference signals in the th channel of the quality control microsite, , represents the number of data groups in the data set.

[0031] It should be noted that, for ease of description in the following text, the preprocessed particulate matter concentration data will also be described using the original particulate matter concentration data.

[0032] Step 103: Calculate the channel consistency index between each ordinary micro-station and the quality control micro-station based on the reference signal and the original particulate matter concentration data.

[0033] In one embodiment, based on the reference signal and raw particulate matter concentration data, a channel consistency index is calculated between each ordinary micro-station and the quality control micro-station, including: Based on the reference signal and raw particulate matter concentration data, at least one of the following is calculated for each ordinary microstation and the corresponding channel data of the quality control microstation: Pearson correlation coefficient, root mean square error, and coefficient of determination. This is to conduct a consistency score based on the calculated consistency index, providing a data basis for subsequently determining the microstation calibration coefficient of the ordinary microstation.

[0034] Optional, according to Calculate the Pearson correlation coefficient between the corresponding channel data of ordinary micro-stations and quality control micro-stations; in, express The mean, express The mean, This represents the Pearson correlation coefficient between the corresponding channel data of the microstation to be calibrated and the quality control microstation. Used to measure the linearity between channels, with values ​​ranging from [-1, 1]. The closer it is to ±1, the stronger the linearity between the corresponding channels.

[0035] Then calculate the root mean square error and coefficient of determination of the corresponding channel data of the microstation to be calibrated and the quality control microstation.

[0036] In As the independent variable, Using [variable name] as the dependent variable, fit a linear regression. Then, calculate the residuals. : ; The root mean square error (RMSE) is defined as follows: ; The coefficient of determination is defined as: .

[0037] Step 104: Determine the micro-station calibration coefficient for each channel of each ordinary micro-station based on the channel consistency index and the quality control calibration coefficient.

[0038] In an embodiment, referring to Figure 2 As shown, determining the micro-station calibration coefficient of each channel of each ordinary micro-station according to the channel consistency index and the quality control calibration coefficient can include: detecting whether at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets a preset condition; If at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets the preset condition, the product of the quality control calibration coefficient and the consistency calibration coefficient is determined as the micro-station calibration coefficient of the corresponding channel of the current ordinary micro-station, wherein the consistency calibration coefficient is the calibration coefficient obtained when the current ordinary micro-station is calibrated against the quality control micro-station consistency calibration; According to the above method of determining the micro-station calibration coefficient of the corresponding channel of the current ordinary micro-station, the micro-station calibration coefficient of each channel of each ordinary micro-station is determined.

[0039] Optionally, referring to the determination criteria of the channel consistency index shown in Table 1.

[0040] Table 1

[0041] In Table 1, if the Pearson correlation coefficient is greater than or equal to a first preset value, it is determined that the consistency of the current channel between the current quality control micro-station and the ordinary micro-station is strong, showing a significant linear relationship, meeting the linear criterion.

[0042] Here, the first preset value is a value set according to requirements, and in this embodiment, the value of the first preset value is not limited, for example, the first preset value can be 0.8, 0.85, or 0.9, etc.

[0043] If the root mean square error is less than or equal to a second preset value, it is determined that the deviation of the particulate matter concentration corresponding to the current channel between the current quality control micro-station and the ordinary micro-station is not large. Wherein, the second preset value is a value set according to experience, and in this embodiment, the value of the second preset value is not limited, for example, the second preset value can be .

[0044] If the determination coefficient is greater than or equal to a third preset value, it is determined that the fitting effect of the particulate matter concentration corresponding to the current channel between the current quality control micro-station and the ordinary micro-station is good. Wherein, the third preset value is a value set according to experience, and in this embodiment, the value of the third preset value is not limited, for example, the third preset value can be 0.75, 0.8, etc.

[0045] Optionally, if at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets the preset condition, it means that the channel consistency of the current ordinary micro-station and the quality control micro-station is good, and the product of the quality control calibration coefficient and the consistency calibration coefficient can be determined as the micro-station calibration coefficient of the corresponding channel of the current ordinary micro-station. That is, according to determining a micro station calibration coefficient of a corresponding channel of the current common micro station; wherein, indicating the micro station calibration coefficient of the corresponding channel of the current common micro station, indicating a quality control calibration coefficient of the quality control micro station, indicating a consistency calibration coefficient obtained when the current common micro station is calibrated with the quality control micro station.

[0046] Optionally, the consistency calibration coefficient can be obtained by a multiple linear regression model, which uses the channel signal of the quality control micro station as the dependent variable and the channel signal of the common micro station as the independent variable.

[0047] For example, if the quality control calibration coefficient of the PM2.5 channel of the quality control micro station is 0.7, the Pearson correlation coefficient of the corresponding channel of the common micro station is 0.9, which meets the preset condition, and the consistency calibration coefficient obtained when the current common micro station is calibrated with the quality control micro station is 0.95, then 0.7*0.95=0.665 can be taken as the micro station calibration coefficient.

[0048] Optionally, in order to obtain a more accurate micro station calibration coefficient of the corresponding channel of the common micro station, the quality control calibration coefficient can be weighted.

[0049] Referring to Figure 2 After detecting whether at least one of the Pearson correlation coefficient, the root mean square error and the determination coefficient meets the preset condition, the method further comprises: If at least one of the Pearson correlation coefficient, the root mean square error and the determination coefficient meets the preset condition, the weighted quality control calibration coefficient is determined as the micro station calibration coefficient of the corresponding channel of the current common micro station after the quality control calibration coefficient is weighted.

[0050] It should be noted that if the Pearson correlation coefficient of the current channel of the current common micro station is between 0.8 and 0.85, it belongs to the edge standard channel, and a weight can be introduced to weight the quality control calibration coefficient.

[0051] In an embodiment, the method for determining the weighted quality control calibration coefficient can be: determining the weight based on the dynamic of at least one of the Pearson correlation coefficient, the root mean square error and the determination coefficient; determining the weighted calibration coefficient according to wherein, indicating the determined weighted calibration coefficient, i.e. the micro station calibration coefficient of the corresponding channel of the current common micro station, indicating the weight.

[0052] For example, the channel consistency state: the Pearson correlation coefficient of the synchronous comparison result of the PM2.5 channel of the current ordinary microstation and the quality control microstation is 0.83, which is in the "borderline compliance" interval 0.8-0.85, and meets the dynamic weighted reference condition.

[0053] The quality control calibration coefficient is obtained by co-location calibration with the national standard particulate matter monitoring equipment, and the multiple linear regression coefficient of the PM2.5 channel is 0.7, that is, the quality control calibration coefficient is 0.7; the consistency calibration coefficient obtained by the current ordinary microstation when calibrating the consistency of the quality control microstation is 0.5; The calculation rule of the weight is: based on the PCC dynamic setting, take , wherein, represents the weight, represents the Pearson correlation coefficient, and 0.7 is used to map to a reasonable weight range to avoid excessive dependence on a single source. Then .

[0054] The weighted calibration coefficient is .

[0055] It should be noted that in order to distinguish the above two cases, a judgment condition can be added, as shown in Figure 2 , after detecting whether at least one of the Pearson correlation coefficient, the root mean square error and the determination coefficient meets the preset condition, if at least one of the Pearson correlation coefficient, the root mean square error and the determination coefficient meets the preset condition, whether the Pearson correlation coefficient is in the borderline compliance interval is detected, if it is in the borderline compliance interval, the microstation calibration coefficient of the corresponding channel of the current ordinary microstation is determined by the weighted manner, otherwise the quality control calibration coefficient is directly taken as the microstation calibration coefficient of the corresponding channel of the current ordinary microstation.

[0056] Optionally, as shown in Figure 2 , after detecting whether at least one of the Pearson correlation coefficient, the root mean square error and the determination coefficient meets the preset condition, it can also include: If none of the Pearson correlation coefficient, the root mean square error and the determination coefficient meets the preset condition, the microstation calibration coefficient of the corresponding channel of the current ordinary microstation is determined to be 0.

[0057] For example, if the Pearson correlation coefficient for the PM2.5 channel is 0.75, the preset condition is not met. Therefore, the quality control calibration coefficient is rejected as the micro-station calibration coefficient for the corresponding channel of the current ordinary micro-station. That is, the micro-station calibration coefficient for the corresponding channel of the current ordinary micro-station is determined to be 0, and the PM2.5 channel is not used for particulate matter concentration calculation. Only the PM1 and PM10 compliance channels are used to calculate the total concentration. It should be noted that here, the PM1 and PM10 channels meet the standards. By rejecting channels with low consistency, the overall particulate matter concentration calculation results are avoided from being contaminated by errors from a single channel.

[0058] Optional, such as Figure 2 As shown, after detecting whether at least one of the Pearson correlation coefficient, root mean square error, and coefficient of determination meets the preset conditions, it may further include: If the Pearson correlation coefficient, root mean square error, and coefficient of determination do not meet the preset conditions, then the average ratio of the historical reference signal of the corresponding channel's quality control micro-station to the historical particulate matter concentration raw data of the ordinary micro-station will be determined as the micro-station calibration coefficient of the corresponding channel of the current ordinary micro-station.

[0059] To differentiate between the two processing methods where the Pearson correlation coefficient, root mean square error, and coefficient of determination all fail to meet the preset conditions, an additional detection step can be added: checking whether the number of times the preset conditions are not met exceeds the preset number. If the number of times the preset conditions are not met exceeds the preset number, indicating that the channel has been failing to meet the standard for a long time, local correction is triggered. This involves determining the average ratio of the historical reference signal of the corresponding channel's quality control micro-station to the historical particulate matter concentration raw data of the ordinary micro-station as the micro-station calibration coefficient for the corresponding channel of the current ordinary micro-station.

[0060] Example of local correction: For example, select the synchronous monitoring data of the ordinary micro-station and the quality control micro-station for the most recent 7 days, calculate the ratio of particulate matter concentration of the ordinary micro-station and the quality control micro-station in the same channel at the same time, and then calculate the average ratio of all time points. This average ratio is then used as the micro-station calibration coefficient of the corresponding channel of the current ordinary micro-station. That is, the particulate matter concentration value of the corresponding channel of the current ordinary micro-station is calculated using this average ratio.

[0061] Step 105: Use the micro-station calibration coefficient to calibrate the original particulate matter concentration data of the corresponding channel of the corresponding ordinary micro-station, and output the corrected particulate matter concentration value.

[0062] Optionally, based on the micro-station calibration coefficients for each channel of each ordinary micro-station obtained above, the raw particulate matter concentration data for the corresponding channel can be calibrated quickly, supporting batch deployment, offline calibration, and remote parameter updates.

[0063] The embodiment of the present application provides a kind of cluster calibration method of particulate matter sensor, by being co-located with standard particulate matter monitoring equipment, the quality control micro station is obtained Quality control calibration coefficient of each channel of micro station;Quality control micro station and multiple ordinary micro stations are placed in the same environment to carry out particulate matter concentration collection, the reference signal of quality control micro station and the particulate matter concentration original data of each channel of each ordinary micro station are obtained;According to reference signal and particulate matter concentration original data, the channel consistency index between each ordinary micro station and quality control micro station is calculated;According to channel consistency index and quality control calibration coefficient, the micro station calibration coefficient of each channel of each ordinary micro station is determined;The particulate matter concentration original data of corresponding channel of corresponding ordinary micro station is calibrated using micro station calibration coefficient, and the corrected particulate matter concentration value is output.The embodiment of the present application can output the corrected particulate matter concentration value without artificial modeling and training for each ordinary micro station, reduce the labor and computing power expenditure, by quality control micro station Construction regional level calibration anchor point, calibration coefficient sharing and dynamic adaptation are carried out, and the consistency calibration scheme of batch ordinary micro station is realized.The embodiment of the present application can complete particulate matter concentration calibration without complex machine modeling, and is more efficient and less complex.

[0064] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0065] The following is the device embodiment of the present application, and for the details not described in detail, reference can be made to the corresponding method embodiments described above.

[0066] Figure 3 The structure of the cluster calibration system of the particulate matter sensor provided by the embodiment of the present application is shown, only the part related to the embodiment of the present application is shown for convenience of description, and the details are described as follows: As Figure 3 shown, a cluster calibration system of particulate matter sensor includes: quality control micro station 31, ordinary micro station 32, consistency analysis module 33 and calibration module 34; Quality control micro station 31 is used for co-locating with standard particulate matter monitoring equipment, and obtaining quality control calibration coefficient of each channel; Multiple ordinary micro stations 32 are placed in the same environment with quality control micro station to carry out particulate matter concentration collection, and obtain particulate matter concentration original data of each channel; Quality control micro station 31 is also used to obtain reference signal of each channel; Consistency analysis module 33 is used for calculating channel consistency index between each ordinary micro station and quality control micro station according to reference signal and particulate matter concentration original data; The calibration module 34 is configured to determine the micro station calibration coefficient of each channel of each ordinary micro station according to the channel consistency index and the quality control calibration coefficient. The plurality of ordinary micro stations 32 are further configured to calibrate the particulate matter concentration raw data of the corresponding channel of the corresponding ordinary micro station by using the micro station calibration coefficient, and output the corrected particulate matter concentration value.

[0067] In a possible implementation, when the consistency analysis module 33 calculates the channel consistency index between each ordinary micro station and the quality control micro station according to the reference signal and the particulate matter concentration raw data, the consistency analysis module 33 is configured to: calculate at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient of the corresponding channel data between each ordinary micro station and the quality control micro station according to the reference signal and the particulate matter concentration raw data.

[0068] In a possible implementation, when the calibration module 34 determines the micro station calibration coefficient of each channel of each ordinary micro station according to the channel consistency index and the quality control calibration coefficient, the calibration module 34 is configured to: detect whether at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets a preset condition; if at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets the preset condition, determine the product of the quality control calibration coefficient and a consistency calibration coefficient as the micro station calibration coefficient of the corresponding channel of the current ordinary micro station, wherein the consistency calibration coefficient is a calibration coefficient obtained when the current ordinary micro station is calibrated against the quality control micro station; determine the micro station calibration coefficient of each channel of each ordinary micro station according to the above method of determining the micro station calibration coefficient of the corresponding channel of the current ordinary micro station.

[0069] In a possible implementation, after the calibration module 34 detects whether at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets the preset condition, the calibration module 34 is further configured to: if at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets the preset condition, determine the weighted quality control calibration coefficient as the micro station calibration coefficient of the corresponding channel of the current ordinary micro station after performing a weighting process on the quality control calibration coefficient.

[0070] In a possible implementation, when the calibration module 34 determines the weighted quality control calibration coefficient, the calibration module 34 is configured to: determine the weight based on the dynamics of at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient; determine the weighted calibration coefficient according to wherein, represents the determined weighted calibration coefficient, represents the weight, a quality control calibration coefficient of the quality control microsite, a consistency calibration coefficient.

[0071] In a possible implementation, after the calibration module 34 detects whether at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets the preset condition, the calibration module 34 is further configured to: If none of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets the preset condition, the calibration module 34 determines that the microsite calibration coefficient of the corresponding channel of the current ordinary microsite is 0.

[0072] In a possible implementation, after the calibration module 34 detects whether at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient meets the preset condition, the calibration module 34 is further configured to: If at least one of the Pearson correlation coefficient, the root mean square error, and the determination coefficient does not meet the preset condition, the calibration module 34 determines, as the microsite calibration coefficient of the corresponding channel of the current ordinary microsite, a mean value of a ratio of the historical reference signal of the quality control microsite to the historical particulate matter concentration original data of the ordinary microsite.

[0073] The above embodiment provides a cluster calibration system of a particulate matter sensor. The quality control microsite is co-located with a standard particulate matter monitoring device to obtain a quality control calibration coefficient of each channel. The plurality of ordinary microsites are placed in the same environment as the quality control microsite to collect particulate matter concentration original data of each channel. The quality control microsite is further configured to obtain a reference signal of each channel. The consistency analysis module is configured to calculate a channel consistency index between each ordinary microsite and the quality control microsite according to the reference signal and the particulate matter concentration original data. The calibration module is configured to determine a microsite calibration coefficient of each channel of each ordinary microsite according to the channel consistency index and the quality control calibration coefficient. The plurality of ordinary microsites are further configured to calibrate the particulate matter concentration original data of the corresponding channel of the corresponding ordinary microsite by using the microsite calibration coefficient, and output a corrected particulate matter concentration value. The embodiment of the present application can output a corrected particulate matter concentration value without manual modeling and training of each ordinary microsite, thereby reducing the labor and computing power cost. The embodiment of the present application builds a regional level calibration anchor point through the quality control microsite, and performs calibration coefficient sharing and dynamic adaptation to realize a consistency calibration scheme for a batch of ordinary microsites. Moreover, the embodiment of the present application can complete particulate matter concentration calibration without complex machine modeling, and is more efficient and less complex.

[0074] Figure 4 is a schematic diagram of a terminal provided by the embodiment of the present application. As shown in Figure 4As shown, the terminal 4 of this embodiment comprises a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. The processor 40 implements the steps in the above-described cluster calibration method embodiments of the particulate matter sensor when executing the computer program 42, for example Figure 1 As shown, the steps 101 to 105. Alternatively, the processor 40 implements the functions of the modules / units in the above-described apparatus embodiments when executing the computer program 42, for example Figure 3 As shown, the functions of the modules / units.

[0075] By way of example, the computer program 42 can be segmented into one or more modules / units, one or more of which are stored in the memory 41 and executed by the processor 40 to complete the present application. One or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program 42 in the terminal 4. For example, the computer program 42 can be segmented into Figure 3 As shown, the modules / units.

[0076] The terminal 4 can include, but is not limited to, the processor 40 and the memory 41. Those skilled in the art can understand that Figure 4 The terminal 4 is merely an example and does not constitute a limitation on the terminal 4, which can include more or fewer components than shown, or combine some components, or different components, for example, the terminal can also include an input / output device, a network access device, a bus, etc.

[0077] The processor 40 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0078] The memory 41 can be an internal storage unit of the terminal 4, such as a hard disk or a memory of the terminal 4. The memory 41 can also be an external storage device of the terminal 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, or the like equipped on the terminal 4. Further, the memory 41 can also include both the internal storage unit and the external storage device of the terminal 4. The memory 41 is used to store computer programs and other programs and data required by the terminal. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0079] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit, and the integrated unit can be realized in the form of hardware or software. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0080] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0081] Those of ordinary skill in the art can appreciate that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed 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 to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0082] In the embodiments of the present application, it should be understood that the disclosed apparatus / terminal and method can be implemented in other manners. For example, the apparatus / terminal embodiments described above are merely schematic, and the division of the modules or units is merely logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0083] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0084] In addition, each functional unit in the various embodiments of the present application can be integrated into a processing unit, or each unit can be a physically independent unit, or two or more units can be integrated into a unit. The integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0085] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, all or part of the flow of the above-mentioned embodiment method can also be implemented by a computer program instructing related hardware to complete, and the computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of the above-mentioned various particle sensor cluster calibration method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0086] The above-described embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A cluster calibration method for a particulate matter sensor, characterized in that, include: The quality control microstation was placed together with the standard particulate matter monitoring equipment, and the quality control calibration coefficients of each channel of the quality control microstation were obtained. The quality control microstation and multiple ordinary microstations were placed in the same environment to collect particulate matter concentration data, thereby obtaining the reference signal of the quality control microstation and the raw particulate matter concentration data of each channel of each ordinary microstation. Based on the reference signal and the raw particulate matter concentration data, calculate the channel consistency index between each ordinary micro-station and the quality control micro-station; Based on the channel consistency index and the quality control calibration coefficient, determine the micro-station calibration coefficient for each channel of each ordinary micro-station; The micro-station calibration coefficient is used to calibrate the original particulate matter concentration data of the corresponding channel of the corresponding ordinary micro-station, and the corrected particulate matter concentration value is output.

2. The cluster calibration method for particulate matter sensors according to claim 1, characterized in that, Based on the reference signal and the raw particulate matter concentration data, calculate the channel consistency index between each ordinary micro-station and the quality control micro-station, including: Based on the reference signal and the original particulate matter concentration data, calculate at least one of the following: Pearson correlation coefficient, root mean square error, and coefficient of determination for the corresponding channel data of each ordinary microstation and the quality control microstation.

3. The cluster calibration method for particulate matter sensors according to claim 2, characterized in that, Based on the channel consistency index and the quality control calibration coefficient, determine the micro-station calibration coefficient for each channel of each ordinary micro-station, including: Detect whether at least one of the Pearson correlation coefficient, the root mean square error, and the coefficient of determination meets a preset condition; If at least one of the Pearson correlation coefficient, the root mean square error, and the coefficient of determination meets a preset condition, the product of the quality control calibration coefficient and the consistency calibration coefficient is determined as the micro-station calibration coefficient of the corresponding channel of the current ordinary micro-station, wherein the consistency calibration coefficient is the calibration coefficient obtained when the current ordinary micro-station is benchmarked against the quality control micro-station for consistency calibration; Based on the above method for determining the micro-station calibration coefficient of the corresponding channel of the current ordinary micro-station, the micro-station calibration coefficient of each channel of each ordinary micro-station is determined.

4. The cluster calibration method for particulate matter sensors according to claim 3, characterized in that, After detecting whether at least one of the Pearson correlation coefficient, the root mean square error, and the coefficient of determination meets a preset condition, the method further includes: If at least one of the Pearson correlation coefficient, the root mean square error, and the coefficient of determination meets a preset condition, the weighted quality control calibration coefficient is then determined as the micro-station calibration coefficient for the corresponding channel of the current ordinary micro-station after weighting the quality control calibration coefficient.

5. The cluster calibration method for particulate matter sensors according to claim 4, characterized in that, The method for determining the weighted quality control calibration coefficient is as follows: The weights are determined based on the dynamics of at least one of the Pearson correlation coefficient, the root mean square error, and the coefficient of determination. according to Determine the weighted calibration coefficients; where, This represents the determined weighted calibration coefficients. Indicates weight, This represents the quality control calibration coefficient of the quality control micro-station. This represents the consistency calibration coefficient.

6. The cluster calibration method for particulate matter sensors according to claim 3, characterized in that, After detecting whether at least one of the Pearson correlation coefficient, the root mean square error, and the coefficient of determination meets a preset condition, the method further includes: If the Pearson correlation coefficient, the root mean square error, and the coefficient of determination do not meet the preset conditions, then the micro-station calibration coefficient of the corresponding channel of the current ordinary micro-station is determined to be 0.

7. The cluster calibration method for particulate matter sensors according to claim 6, characterized in that, After detecting whether at least one of the Pearson correlation coefficient, the root mean square error, and the coefficient of determination meets a preset condition, the method further includes: If at least one of the Pearson correlation coefficient, the root mean square error, and the coefficient of determination does not meet the preset condition, then the average ratio of the historical reference signal of the quality control micro-station of the corresponding channel to the historical particulate matter concentration raw data of the ordinary micro-station is determined as the micro-station calibration coefficient of the corresponding channel of the current ordinary micro-station.

8. A cluster calibration system for a particulate matter sensor, characterized in that, include: The quality control micro-station is used in conjunction with standard particulate matter monitoring equipment to obtain the quality control calibration coefficients for each channel; Multiple ordinary micro-stations were placed in the same environment as the quality control micro-station to collect particulate matter concentration data, and the raw particulate matter concentration data of each channel were obtained. The quality control microstation is also used to obtain reference signals for each channel; The consistency analysis module is used to calculate the channel consistency index between each ordinary micro-station and the quality control micro-station based on the reference signal and the original particulate matter concentration data; The calibration module is used to determine the micro-station calibration coefficient for each channel of each ordinary micro-station based on the channel consistency index and the quality control calibration coefficient; The plurality of ordinary micro-stations are also used to calibrate the original particulate matter concentration data of the corresponding channel of the corresponding ordinary micro-station using the micro-station calibration coefficient, and output the corrected particulate matter concentration value.

9. A terminal, comprising a memory and a processor, the memory for storing a computer program, the processor for calling and running the computer program stored in the memory, characterized in that, When the processor executes the computer program, it implements the steps of the cluster calibration method for particulate matter sensors as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the cluster calibration method for particulate matter sensors as described in any one of claims 1 to 7.

Images