Calibration air pollutant monitoring equipment

An air pollutant concentration calibration model established using linear regression and machine learning algorithms solves the measurement error problem of ordinary air pollution monitoring equipment under different meteorological conditions, and achieves accurate air pollutant concentration calibration and measurement.

CN118888043APending Publication Date: 2024-11-01INST OF ENVIRONMENTAL & HEALTH-RELATED PROD SAFETY CHINESE CENT FOR DISEASE CONTROL & PREVENTION
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202410931996.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-12
Publication Date
2024-11-01

AI Technical Summary

Technical Problem

Existing conventional air pollution monitoring equipment is affected by environmental parameters such as temperature and humidity, resulting in large measurement errors. Traditional linear regression models cannot be accurately calibrated under different meteorological conditions, making it difficult to measure the concentration of common air pollutants.

Method used

An air pollutant concentration calibration model was established using linear regression and machine learning algorithms. The model was calibrated using ambient temperature and relative humidity data, and a random forest model was used to improve calibration accuracy.

Benefits of technology

It enables precise calibration under different meteorological conditions, improves the accuracy and reliability of air pollutant concentration measurement, and simplifies the calibration process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118888043A_ABST
    Figure CN118888043A_ABST
Patent Text Reader

Abstract

The invention provides a method for calibrating air pollutant monitoring equipment. The method comprises the following steps: step 1, acquiring a real-time air pollutant concentration reference value; step 2, acquiring a monitoring value of the to-be-calibrated air pollutant monitoring equipment; step 3, acquiring environment temperature data and relative humidity data; step 4, based on a linear regression method and a machine learning algorithm, according to the environment temperature data and the relative humidity data, establishing and training an air pollutant concentration calibration model; and 5, calibrating the air pollutant monitoring equipment to be calibrated by using the air pollutant concentration calibration model. The invention further comprises a device for calibrating the air pollutant monitoring equipment corresponding to the method for calibrating the air pollutant monitoring equipment. The invention provides the method and the device for calibrating the air pollutant monitoring equipment, which have the advantages of high efficiency and strong robustness and are used for calibrating the monitoring numerical value of the common air pollutant monitoring equipment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of air pollutant monitoring, and in particular relates to a method and a device for calibrating air pollutant monitoring equipment. Background Art

[0002] Ambient air pollutants have been proven to have adverse effects on human health from multiple perspectives. In order to better assess their impact on health, it is necessary to measure air pollution exposure concentrations more accurately. Previous environmental studies have shown that equipment with stable measurement performance and reliable accuracy is widely used in particulate matter monitoring and environmental health research, such as MicroPEM monitors, but fine measurement equipment is very expensive. Due to the high cost of this equipment, the application of fine measurement equipment in large-scale PM2.5 monitoring is extremely costly and difficult to implement.

[0003] In this context, common air pollution monitoring equipment came into being, which provides a revolutionary method for implementing air quality monitoring. The U.S. Environmental Protection Agency (USEPA) and European institutions have verified the advantages of applying common air monitoring technology and establishing common sensor monitoring networks based on population studies. These studies have shown that the spatial and temporal data resolution of common air pollution monitoring equipment has been greatly improved. However, the measurement results of common monitors, especially those based on light scattering, are easily affected by environmental parameters such as temperature and relative humidity, and the research on common monitors in the prior art has not yet involved the field of calibration, resulting in large errors in the measurement results of common air pollution monitoring equipment. Therefore, due to the limitations of accuracy and credibility, it is very difficult to achieve the measurement of common air pollutant concentrations in a large population.

[0004] In recent years, some studies have focused on the development and quality of common air pollutant monitors, but they mainly use traditional linear regression models to evaluate calibration performance. Several studies have investigated particulate matter sensors under laboratory conditions to evaluate the performance of the monitors and calibrate the monitoring concentrations of common sensors. However, the measurement principles of these monitors are not consistent, and the response factors of the monitors vary significantly under different meteorological conditions. In addition, according to epidemiological studies, environmental parameters, including ambient temperature and relative humidity, have a nonlinear relationship with particulate matter concentrations. Based on haze event observations, PM2.5 and PM10 concentrations show a curvilinear relationship under different temperatures and seasons (such as winter and spring), and temperature and relative humidity have also been shown to have a nonlinear correlation with particulate matter concentrations, indicating that these meteorological factors are nonlinearly related to the monitored concentrations. Therefore, the procedure based on the linear regression model may not be sufficient to calibrate the particulate matter concentrations under different meteorological conditions. The evaluation results using the traditional linear regression model have large errors and cannot achieve accurate calibration.

[0005] Based on the above, this application provides a technical solution to solve the above technical problems. Summary of the invention

[0006] Aiming at the scenario of common air pollution monitoring equipment in the prior art, the present invention provides a method for calibrating air pollutant monitoring equipment, comprising the following steps:

[0007] Step 1: Obtain real-time air pollutant concentration baseline values;

[0008] Step 2, obtaining the monitoring values ​​of the air pollutant monitoring equipment to be calibrated;

[0009] Step 3: Obtain ambient temperature data and relative humidity data;

[0010] Step 4: Based on the linear regression method and the machine learning algorithm, an air pollutant concentration calibration model is established and trained according to the ambient temperature data and the relative humidity data;

[0011] Step 5: Use the air pollutant concentration calibration model to calibrate the air pollutant monitoring device to be calibrated.

[0012] In a specific embodiment of the present invention, the machine learning algorithm is based on a random forest model.

[0013] In a specific embodiment of the present invention, the linear regression method is based on the formula Y=β1×X+β2×Temp+β3×RH+β0, wherein Y is the real-time air pollutant concentration reference value, X is the monitoring value of the air pollutant monitoring equipment to be calibrated, T is the ambient temperature data, RH is the relative humidity data, β1, β2, β3 are regression coefficients, and β0 is the regression intercept.

[0014] In a specific embodiment of the present invention, the number of variables and the decision tree corresponding to the maximum model R2 are selected as model parameters for random forest regression selection.

[0015] In a specific embodiment of the present invention, 90% of the data are randomly selected as a training data set, and the remaining 10% of the data are used as a test data set.

[0016] In a specific embodiment of the present invention, the method further includes: inputting the test data set into the air pollutant concentration calibration model, and evaluating the performance of the calibration model based on the results output by the calibration model.

[0017] In a specific embodiment of the present invention, it also includes: evaluating the performance of the calibration model by a cross-validation method.

[0018] In a specific embodiment of the present invention, the air pollutant concentration is PM2.5 concentration.

[0019] In a specific embodiment of the present invention, the step of obtaining the real-time air pollutant concentration baseline value includes:

[0020] The real-time air pollutant concentration data measured by three groups of MicroPEM monitors at the same time point and the same location are obtained, and the three groups of real-time air pollutant concentrations are averaged to obtain the average air pollutant concentration as the baseline value of the air pollutant concentration.

[0021] The present invention also provides a device for calibrating an air pollutant monitoring device, comprising the following modules:

[0022] A benchmark value acquisition module is used to obtain real-time air pollutant concentration benchmark values;

[0023] A monitoring module, used to obtain monitoring values ​​of the air pollutant monitoring equipment to be calibrated;

[0024] A parameter acquisition module is used to obtain ambient temperature data and relative humidity data;

[0025] A modeling module, based on a linear regression method and a machine learning algorithm, establishes and trains an air pollutant concentration calibration model according to the ambient temperature data and the relative humidity data;

[0026] The calibration module is used to calibrate the air pollutant monitoring device to be calibrated using the air pollutant concentration calibration model.

[0027] The present invention provides a method and device for calibrating air pollutant monitoring equipment, which establishes and trains an air pollutant concentration calibration model through a linear regression method and a machine learning model, and uses the air pollutant concentration calibration model to calibrate the test data of the air pollutant monitoring equipment. The calibration method proposed by the present invention is simple to calibrate and has a good calibration effect. It can be applied to the measurement of various air pollutant concentrations, so that various types of air pollutant monitoring equipment can be applied to air pollutant measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The preferred implementation scheme will be described below in a clear and understandable manner with reference to the accompanying drawings to further illustrate the above-mentioned characteristics, technical features, advantages and their implementation methods.

[0029] Figure 1 A schematic diagram of the steps of the method for air pollutant monitoring equipment proposed in Embodiment 1 of the present invention;

[0030] Figure 2 The particle concentration monitoring results of the Hike B3 and MicroPEM monitors in Example 1 of the present invention;

[0031] Figure 3 The performance test results of the method for the air pollutant monitoring device proposed in the first embodiment of the present invention;

[0032] Figure 4 The performance test results of the air pollutant monitoring device method proposed in the first embodiment of the present invention at low particle concentration;

[0033] Figure 5 This is a schematic diagram of the structure of the air pollutant monitoring device proposed in the second embodiment of the present invention. DETAILED DESCRIPTION

[0034] Various aspects of the present invention are described in further detail below.

[0035] Unless otherwise defined or indicated, all professional and scientific terms used herein have the same meanings as those familiar to those skilled in the art. In addition, any methods and materials similar or equivalent to those described herein can be applied to the present invention.

[0036] The following is an explanation of the terms.

[0037] Unless otherwise clearly specified and limited, the "or" mentioned in the present invention includes the relationship of "and". The "and" is equivalent to the Boolean logic operator "AND", the "or" is equivalent to the Boolean logic operator "OR", and "AND" is a subset of "OR".

[0038] It is to be understood that although the terms "first", "second", etc. may be used herein to describe different elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. Therefore, the first element may be referred to as the second element without departing from the teachings of the present invention.

[0039] In the present invention, the terms "comprising", "including" or "comprising" indicate that various components can be applied together in the mixture or composition of the present invention. Therefore, the term "consisting mainly of..." is included in the terms "comprising", "including" or "comprising".

[0040] Unless otherwise clearly specified and limited, the terms "connected", "connected" and "connection" in the present invention should be understood in a broad sense, for example, it can be a fixed connection, or it can be connected through an intermediary medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0041] For example, if an element (or component) is referred to as being on, coupled to, or connected to another element, the element may be directly formed on, coupled to, or connected to the other element, or there may be one or more intervening elements between them. In contrast, if the expressions "directly on," "directly coupled to," and "directly connected to" are used herein, then no intervening elements are indicated. Other words used to describe the relationship between elements should be similarly interpreted, such as "between" and "directly between," "attached" and "directly attached," "adjacent" and "directly adjacent," and the like.

[0042] It should also be noted that the words "front", "rear", "left", "right", "upper" and "lower" used in the following description refer to directions in the drawings. The words "inner" and "outer" used refer to directions toward or away from the geometric center of a particular component, respectively. It can be understood that these terms are used here to describe the relationship of one element, layer or region relative to another element, layer or region as shown in the drawings. In addition to the orientations described in the drawings, these terms should also include other orientations of the device.

[0043] Other aspects of the present invention will be apparent to those skilled in the art in view of the disclosure herein.

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the specific implementation methods of the present invention will be described below with reference to the accompanying drawings. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings and other implementation methods can be obtained based on these drawings without creative work.

[0045] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. The drawings only show the components related to the present application and are not drawn according to the number, shape and size of the components in actual implementation. The type, quantity and proportion of each component in actual implementation may be changed arbitrarily, and the component layout may also be more complicated. For example, the thickness of the components in the drawings may be exaggerated for the sake of clarity.

[0046] Embodiment 1

[0047] For the scenarios of common air pollution monitoring equipment in the prior art, see the attached Figure 1 The present invention provides a method for calibrating an air pollutant monitoring device, comprising the following steps:

[0048] Step 1: Obtain real-time air pollutant concentration baseline values;

[0049] Step 2, obtaining the monitoring values ​​of the air pollutant monitoring equipment to be calibrated;

[0050] Step 3: Obtain ambient temperature data and relative humidity data;

[0051] Step 4: Based on the linear regression method and the machine learning algorithm, an air pollutant concentration calibration model is established and trained according to the ambient temperature data and the relative humidity data;

[0052] Step 5: Use the air pollutant concentration calibration model to calibrate the air pollutant monitoring device to be calibrated.

[0053] In a preferred embodiment of the present invention, the step of obtaining the real-time air pollutant concentration baseline value includes:

[0054] The real-time air pollutant concentration data measured by three groups of MicroPEM monitors at the same time point and the same location are obtained, and the three groups of real-time air pollutant concentrations are averaged to obtain the average air pollutant concentration as the baseline value of the air pollutant concentration.

[0055] Preferably, the air pollutant monitoring device to be calibrated is a Hike B3 industrial air quality monitor. The Hike B3 device is mainly used to measure indoor air quality and establish a pollution monitoring system. It can record concentration values ​​through wireless transmission.

[0056] More specifically, this embodiment uses 16 Hike B3 monitors with a sampling frequency of 10 minutes. TM The 3.2A version of the monitor individual exposure sampler was used as a standard control to exclude the possible influence of outliers. The sampling frequency of the MicroPEM monitor was 10 seconds, and the monitoring data of one of the MicroPEM monitors was used as a blank control.

[0057] The experimental equipment is concentrated in 30m 2 The Hike B3 instrument was used in indoor conditions. Since cigarette smoke accounts for a large proportion of indoor air pollution and can be used as a test suspended particulate matter for instrument calibration, in this embodiment, cigarette smoke is used to simulate urban indoor particulate pollutants.

[0058] After the instrument was running stably, a cigarette was lit in the laboratory compartment. The MicroPEM monitor was equipped with a polytetrafluoroethylene filter, which had an important influence on the real-time concentration of the calibrated particles. The humidity in the laboratory compartment was regulated by a humidifier. The temperature and relative humidity of the laboratory compartment were recorded using a Hike B3 device. In order to ensure uniform airflow, all instruments were placed in the middle of the experimental compartment. In general, each experiment took 5-6 hours to complete. After lighting the cigarette, it took 0.5-1 hour to obtain stable measurement data.

[0059] In this example, the concentration of particulate matter was within the detection limit of the MicroPEM monitor and the Hike B3 device, preferably excluding the average concentration above 500 μg / m 3 Monitoring data from the MicroPEM monitor.

[0060] In a preferred embodiment of the present invention, the air pollutant concentration is PM2.5 concentration.

[0061] In a preferred embodiment of the present invention, before obtaining the real-time air pollutant concentration baseline value in step 1, the process further includes:

[0062] The real-time data of the MicroPEM monitor was corrected to a zero drift value, and the abnormal data caused by instrument defects was deleted. The monitoring data of the real-time MicroPEM monitor was calibrated according to the cleaned film weighing data as a standard control PM2.5 concentration value.

[0063] In a preferred embodiment of the present invention, after obtaining the monitoring value of the air pollutant monitoring device to be calibrated in step 2, the method further includes:

[0064] According to the monitoring time, the real-time air pollutant concentration baseline value is matched with the monitoring value of the air pollutant monitoring equipment to be calibrated.

[0065] Specifically, since the sampling frequency of the Hike B3 PM2.5 monitor is 10 minutes, while the sampling frequency of the MicroPEM monitor is 10 seconds, the real-time data of the Hike B3 monitor will not change instantly when the PM2.5 concentration changes rapidly. In order to avoid data fluctuations and obtain more accurate data, it is necessary to delete the data collected in the first 15 minutes after lighting the cigarette. The corrected real-time data of the MicroPEM monitor is processed according to the time point of the real-time data of the Hike B3 PM2.5 monitor, and then matched with the real-time data of the Hike B3 PM2.5 monitor.

[0066] According to the scheme of this embodiment, the experimental monitoring data and environmental parameters are shown in Table 1. The PM2.5 concentration of the Hike device is higher than that of the MicroPEM monitor. The ambient temperature is in the range of 16.2 to 31.0°C and the relative humidity is in the range of 5.8 to 79.3%. The particle concentration of the Hike B3 and MicroPEM monitor is shown in the attached figure. Figure 2 As shown in the figure, the horizontal axis is the ordinal number arranged in ascending order according to the standard control concentration, and the vertical axis is the PM2.5 concentration, with the concentration unit being μg / m 3 , Figure 2 The red dots in the graph represent the average concentration of the MicroPEM monitor, and the black dots represent the average concentration of the Hike monitor. It can be seen that the monitoring data of the Hike B3 monitor is slightly higher than that of the MicroPEM monitor.

[0067]

[0068] Table 1

[0069] In a preferred embodiment of the present invention, the machine learning algorithm is based on a random forest model.

[0070] Preferably, the linear regression method is based on the formula Y=β1×X+β2×Temp+β3×RH+β0, wherein Y is the real-time air pollutant concentration reference value, X is the monitoring value of the air pollutant monitoring equipment to be calibrated, T is the ambient temperature data, RH is the relative humidity data, β1, β2, β3 are regression coefficients, and β0 is the regression intercept.

[0071] Among them, the multivariate linear regression model is used to establish the relationship between the above multiple independent variables and the dependent variable, and β1, β2, β3, and β0 are estimated by the least squares estimation method to minimize the residual sum of squares.

[0072] More specifically, the number of variables (mtry) and decision trees (ntree) corresponding to the maximum model R2 were selected as model parameters for random forest regression selection.

[0073] In a preferred embodiment of the present invention, 90% of the data are randomly selected as a training data set, and the remaining 10% of the data are used as a test data set.

[0074] Preferably, the test data set is input into the air pollutant concentration calibration model, and the performance of the calibration model is evaluated based on the results output by the calibration model.

[0075] More specifically, the performance of the calibration model was evaluated by cross-validation. The performance test results of the calibration model are shown in the attached figure. Figure 3 As shown, attached Figure 3 (a) shows the performance test fitting results of the traditional linear regression model. Figure 3(b) Performance test fitting results of the air pollutant concentration calibration model. The observed values ​​and linear regression calibration values ​​in this embodiment are relatively scattered, and the confidence interval is greater than 95%. The random forest model calibration values ​​and observed values ​​are more concentrated near the regression line of y=0.99x+0.05. The R-squared value and slope are important parameters for measuring model performance. The R-squared value (R 2 =0.98) is higher than the traditional linear regression model value (R 2 =0.87), it can be seen that the calibration model of the present invention has better fitting performance than the traditional linear regression model.

[0076] At low particle concentrations, the linear regression model had a slope of 1.07, R 2 =0.87. When the test data set is applied to the air pollutant concentration calibration model proposed in this embodiment, the slope and R 2 They are 1.01 and 0.99 respectively. The analysis results are shown in the attached Figure 4 As shown, attached Figure 4 (a) shows the performance test fitting results of the traditional linear regression model. Figure 4 (b) Performance test fitting results of the air pollutant concentration calibration model.

[0077] It can be seen that in low particulate matter concentration scenarios, the performance of the method for calibrating air pollutant monitoring equipment proposed in this embodiment is still better, reflecting the strong robustness of the air pollutant concentration calibration model in multiple scenarios.

[0078] This embodiment provides a method for calibrating an air pollutant monitoring device, establishing and training an air pollutant concentration calibration model through a linear regression method and a machine learning model, and using the air pollutant concentration calibration model to calibrate test data of the air pollutant monitoring device. The calibration method proposed by the present invention is simple to calibrate and has a good calibration effect. It can be applied to the measurement of various air pollutant concentrations, so that various types of air pollutant monitoring devices can be applied to air pollutant measurement.

[0079] Embodiment 2

[0080] See attached Figure 5 , is a schematic diagram of a structure of a device for calibrating an air pollutant monitoring device according to another specific embodiment of the present invention. The device for calibrating an air pollutant monitoring device comprises the following modules:

[0081] A benchmark value acquisition module is used to obtain real-time air pollutant concentration benchmark values;

[0082] A monitoring module, used to obtain monitoring values ​​of the air pollutant monitoring equipment to be calibrated;

[0083] A parameter acquisition module is used to obtain ambient temperature data and relative humidity data;

[0084] A modeling module, based on a linear regression method and a machine learning algorithm, establishes and trains an air pollutant concentration calibration model according to the ambient temperature data and the relative humidity data;

[0085] The calibration module is used to calibrate the air pollutant monitoring device using the air pollutant concentration calibration model.

[0086] In summary, the present invention has achieved the following effects:

[0087] The present invention provides a method and device for calibrating air pollutant monitoring equipment, which establishes and trains an air pollutant concentration calibration model through a linear regression method and a machine learning model, and uses the air pollutant concentration calibration model to calibrate the test data of the air pollutant monitoring equipment. The calibration method proposed by the present invention is simple to calibrate and has a good calibration effect. It can be applied to the measurement of various air pollutant concentrations, so that all types of air pollutant monitoring equipment can be applied to air pollutant measurement. .

[0088] Based on this application, it should be understood by those skilled in the art that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number and aspect described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.

[0089] Those skilled in the art know that, in addition to realizing the system and its various devices, modules, and units provided by the present invention in a purely computer-readable program code, it is entirely possible to realize the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for realizing various functions can also be regarded as structures within the hardware component; the devices, modules, and units for realizing various functions can also be regarded as both software modules for realizing the method and structures within the hardware component.

[0090] It should be noted that the above embodiments can be freely combined as needed. The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention.

[0091] All documents mentioned in the present invention are cited as references in this application, just as each document is cited as reference separately. In addition, it should be understood that after reading the above content of the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms also fall within the scope defined by the claims attached to this application.

Claims

1. A method for calibrating an air pollutant monitoring device, characterized in that: The following steps are involved: Step 1: Obtain real-time air pollutant concentration baseline values; Step 2, obtaining the monitoring value of the air pollutant monitoring device to be calibrated; Step 3: Obtain ambient temperature data and relative humidity data; Step 4: Based on the linear regression method and the machine learning algorithm, an air pollutant concentration calibration model is established and trained according to the ambient temperature data and the relative humidity data; Step 5: Use the air pollutant concentration calibration model to calibrate the air pollutant monitoring device to be calibrated.

2. The method for calibrating an air pollutant monitoring device according to claim 1, characterized in that: The machine learning algorithm is based on a random forest model.

3. The method of calibrating an air pollutant monitoring device according to claim 2, characterized in that: The linear regression method is based on the formula Y=β1×X+β2×Temp+β3×RH+β0, Among them, Y is the real-time air pollutant concentration benchmark value, X is the monitoring value of the air pollutant monitoring equipment to be calibrated, T is the ambient temperature data, RH is the relative humidity data, β1, β2, β3 are regression coefficients, and β0 is the regression intercept.

4. The method of calibrating an air pollutant monitoring device according to claim 3, characterized in that: The number of variables and decision trees corresponding to the maximum model R2 were selected as model parameters for random forest regression selection.

5. The method of calibrating an air pollutant monitoring device according to claim 1, characterized in that: 90% of the data are randomly selected as the training data set, and the remaining 10% of the data are used as the test data set.

6. The method of calibrating an air pollutant monitoring device according to claim 5, characterized in that: Also includes: The test data set is input into the air pollutant concentration calibration model, and the performance of the calibration model is evaluated according to the results output by the calibration model.

7. The method of calibrating an air pollutant monitoring device according to claim 5, characterized in that: Also includes: The performance of the calibration model was evaluated by cross-validation.

8. The method of calibrating an air pollutant monitoring device according to claim 1, characterized in that: The air pollutant concentration is PM2.5 concentration.

9. The method of calibrating an air pollutant monitoring device according to claim 1, characterized in that: The steps for obtaining the real-time air pollutant concentration baseline value include: The real-time air pollutant concentration data measured by three groups of MicroPEM monitors at the same time point and the same location are obtained, and the three groups of real-time air pollutant concentrations are averaged to obtain the average air pollutant concentration as the baseline value of the air pollutant concentration.

10. A device for calibrating an air pollutant monitoring device, characterized in that: Includes the following modules: A benchmark value acquisition module is used to obtain real-time air pollutant concentration benchmark values; A monitoring module, used to obtain monitoring values ​​of the air pollutant monitoring equipment to be calibrated; A parameter acquisition module is used to obtain ambient temperature data and relative humidity data; A modeling module, based on a linear regression method and a machine learning algorithm, establishes and trains an air pollutant concentration calibration model according to the ambient temperature data and the relative humidity data; The calibration module is used to calibrate the air pollutant monitoring device to be calibrated using the air pollutant concentration calibration model.

Citation Information

Patent Citations

  • Artificial intelligence based hydraulic fracturing system monitoring and control

    CA3148496A1

  • Dynamic calibration method capable of eliminating influence of chemical components in particulate matters and monitoring instrument

    CN107884322A

  • Atmospheric pollution factor concentration space-time distribution prediction method and system

    CN110263479A

  • Livestock Internet of Things collected body temperature calibration method

    CN112560336A

  • Evolutionary ensemble learning-based atmospheric pollutant concentration space-time prediction method

    CN114578457A