Environment-friendly air quality intelligent detection method and system using Internet of Things technology
Patent Information
- Application Number
- CN202511910711.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-17
- Publication Date
- 2026-01-16
AI Technical Summary
Existing air quality detection technologies suffer from problems such as concentration distortion, ambiguous pollution source identification, and delayed warnings of secondary pollution. They fail to effectively combine the physical/chemical properties of air with Internet of Things (IoT) technology, resulting in insufficient detection accuracy and pollution source identification capabilities.
By deploying IoT sensing nodes in the monitoring area, the physical and chemical properties of air pollution sources are collected in real time. The concentration values are corrected using dynamic calibration algorithms. Combined with the fractal dimension and photolysis rate of particulate matter, pollution sources are identified and secondary pollution is assessed, thus achieving intelligent detection of air quality.
It enables precise source tracing and proactive early warning of air quality detection, improves detection accuracy and pollution source identification capabilities, and provides a scientific tool for precise pollution control.
Smart Images
Figure CN121347748A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent air quality detection technology, and in particular to an environmentally friendly intelligent air quality detection method and system utilizing Internet of Things (IoT) technology. Background Technology
[0002] With the acceleration of industrialization and urbanization, air pollution has become increasingly complex, involving not only primary pollutants but also secondary pollutants. As a result, traditional detection methods are no longer sufficient to meet the needs of precise pollution control.
[0003] The maturity of IoT technology has provided a new paradigm for air quality monitoring. Its core is to collect the physical / chemical properties of air in real time through distributed sensor nodes, and combine edge computing and cloud platform analysis to achieve an intelligent upgrade "from data to decision". However, the core defect of the existing technology is that it does not deeply couple the physical / chemical properties of air with IoT technology, resulting in significant shortcomings in detection accuracy, pollution source identification ability, and secondary pollution early warning effect. Specifically, the distortion of raw concentration data is not dynamically compensated, and pollution source identification relies on "a single concentration indicator" without utilizing the physical properties of particulate matter morphology, making it difficult to distinguish different sources with the same concentration. In addition, secondary pollution early warning also lacks chemical activity assessment and does not integrate photolysis rate and time factors, resulting in a lag in early warning. Summary of the Invention
[0004] The technical problem to be solved by this invention is that existing technologies have shortcomings such as concentration distortion, unclear source tracing, and delayed early warning. To address this, we propose an intelligent detection method and system for environmental air quality using Internet of Things (IoT) technology.
[0005] In a first aspect, one embodiment of the present invention provides an intelligent air quality detection method utilizing Internet of Things (IoT) technology, comprising the following steps: IoT sensing nodes are deployed in the monitoring area to collect physical and chemical parameters of air pollution sources in real time. The physical parameters include signal attenuation rate, response time, average daily effective illumination duration, and particulate fractal dimension of different pollution sources. The chemical parameters include photolysis rate under different pollution characteristics of different pollution sources. Based on the signal attenuation rate and response time, and by calculating the calibration coefficient through a dynamic calibration algorithm, the original concentration values collected by the IoT sensing layer are corrected to determine the pollution source concentration after calibration. Based on the calibrated pollution source concentration and particulate matter fractal dimension, pollution source identification indices for different pollution sources are obtained through a pollution source identification algorithm. Based on the pollution source identification index, and combined with the average daily effective sunshine duration and the photolysis rate under different pollution characteristics of different pollution sources, the secondary pollution generation potential value of the main pollution sources is determined by the secondary pollution assessment algorithm. Based on the secondary pollution generation potential value of the main pollution sources, the signal attenuation rate is corrected until the change rate of the signal attenuation rate after two consecutive corrections is less than the preset relative benchmark change rate. Based on the calibrated pollution source concentration, the pollution source identification index, and the secondary pollution generation potential value, combined with time series analysis, the intelligent air quality detection result is output.
[0006] Preferably, the method for collecting the physical property parameters and the chemical property parameters is as follows: The signal attenuation rate and response time are collected by the sensor drift monitoring unit of the Internet of Things sensing layer, wherein the signal attenuation rate is determined by the degree of oxidation of electrochemical electrodes and the response time is determined by the step response experiment of laser particle size analyzer. The fractal dimension of the particles was acquired using a laser particle size analyzer and a scanning electron microscope. The fractal dimension of the particles was determined by a fractal geometry algorithm based on particle size distribution and microscopic morphology images. The average daily effective illumination duration with light intensity ≥300nm wavelength is collected using a light sensor; The photolysis rate of various pollutant characteristics was collected using a photochemical reactor.
[0007] Preferably, the specific steps of the dynamic calibration algorithm are as follows: Retrieve the initial attenuation rate and initial response time of the sensor when it left the factory, which are pre-stored in the cloud platform database; The drift factor of sensor performance is determined by the product of a first ratio of signal attenuation rate to initial attenuation rate and a second ratio of response time to initial response time. The gas sensor array in the Internet of Things sensing layer collects the raw concentration values of different pollution sources that need to be detected for air quality in real time. Based on the degree of influence of the drift factor on the original concentration values of different pollution sources, the calibrated pollution source concentrations of different pollution sources are determined.
[0008] Preferably, the specific steps of the pollution source identification algorithm are as follows: Retrieve the standard fractal dimensions of different pollution sources pre-existing in the cloud platform database; Based on the third ratio of the particulate matter fractal dimension to the standard fractal dimension, the degree of morphological matching of different pollution sources is determined; The pollution source identification index for different pollution sources is determined by multiplying the morphological matching degree with the calibrated pollution source concentration.
[0009] Preferably, the specific steps of the secondary pollution assessment algorithm are as follows: Retrieve the photolysis rates of different pollution sources corresponding to different pollution characteristics from the pre-existing cloud platform database; Based on the product of the photolysis rate, the pollution source identification index, and the average daily effective illumination duration, the potential value of secondary pollution generation under different pollution characteristics of different pollution sources is determined, and the maximum value of the potential value of secondary pollution generation under different pollution characteristics of different pollution sources is set as the potential value of secondary pollution generation of the main pollution source.
[0010] Preferably, based on the primary pollution source, the secondary pollution threshold concentration of the primary pollution source is retrieved, and when the secondary pollution generation potential value is greater than or equal to the secondary pollution threshold concentration, the following calculation for signal attenuation rate correction is performed: ; In the formula: s new EQ represents the corrected signal attenuation rate, s0 represents the initial attenuation rate of the sensor at the factory, and EQ represents the signal attenuation rate. i-j EQ represents the potential for secondary pollution generation from the i-th pollution source under the j-th pollution characteristic. i-j-0 Let s be the secondary pollution threshold concentration for the i-th pollution source and the j-th pollution characteristic, determined experimentally. base The increment of the base decay rate; Among them, i specifically refers to industrial dust pollution sources, vehicle exhaust pollution sources, and biomass combustion pollution sources, while j specifically refers to nitrogen dioxide pollution characteristics, sulfur dioxide pollution characteristics, and formaldehyde pollution characteristics.
[0011] Preferably, based on the corrected signal attenuation rate, the corrected signal attenuation rate is introduced into the dynamic calibration algorithm to replace the original signal attenuation rate for correction, until the rate of change of the signal attenuation rate after two consecutive corrections is less than a preset relative reference rate of change.
[0012] Secondly, embodiments of the present invention also provide an intelligent air quality detection system utilizing Internet of Things (IoT) technology, comprising: Sensing layer: Includes sensor drift monitoring unit, laser particle size analyzer, photochemical reactor, light sensor and gas sensor array, used to collect physical property parameters, chemical property parameters and raw concentration values; Network layer: Includes transmission module and edge computing gateway, used to transmit physical property parameters, chemical property parameters and raw concentration values collected by the sensing layer to the platform layer and execute dynamic calibration algorithm, pollution source identification algorithm and secondary pollution assessment algorithm; Platform layer: includes cloud servers and databases, wherein the cloud servers are configured with: Dynamic calibration module: used to perform calibration coefficients and calculate the concentration of pollution sources after calibration; Pollution source identification module: used to calculate the pollution source identification index for different pollution sources and match pollution sources; Secondary pollution assessment module: used to calculate and provide early warning of the potential for secondary pollution generation; Application layer: Includes a data visualization interface and an early warning command output unit, used to display the calibrated pollution source concentration, pollution source identification index, and secondary pollution generation potential value, as well as push pollution source control suggestions.
[0013] The technical effects and advantages of this invention are as follows: This invention achieves a deep integration of air physical / chemical property measurement and dynamic calculation through Internet of Things (IoT) technology. First, it uses the attenuation and response of sensor signals to correct sensor physical drift, ensuring the authenticity of concentration data. Then, it uses the physical morphology fingerprint of particulate matter to identify pollution sources. Finally, it couples chemical activity and physical environmental parameters to assess the risk of secondary pollution. These three elements form a closed loop of "sensing-transmission-computation-application" through IoT, ultimately realizing an intelligent upgrade of environmental air quality detection from "passive monitoring" to "active early warning" and "precise source tracing," providing a scientific tool for precise pollution control. Attached Figure Description
[0014] Figure 1 This is a schematic diagram of the steps of the intelligent detection method for environmental air quality using Internet of Things (IoT) technology according to the present invention. Detailed Implementation
[0015] The present invention will now be described in further detail with reference to the accompanying drawings and preferred embodiments.
[0016] Reference Figure 1 As shown, the present invention provides a technical solution: an intelligent air quality detection method utilizing Internet of Things (IoT) technology, comprising the following steps: Step 1: Deploy IoT sensing nodes in the monitoring area and collect physical and chemical parameters of air pollution sources in real time. The physical parameters include signal attenuation rate, response time, average daily effective illumination duration, and particulate matter fractal dimension of different pollution sources. The chemical parameters include photolysis rate under different pollution characteristics of different pollution sources.
[0017] The methods for collecting physical and chemical property parameters are as follows: The signal attenuation rate and response time are collected by the sensor drift monitoring unit of the Internet of Things sensing layer. The signal attenuation rate is determined by the degree of oxidation of the electrochemical electrode, and the response time is determined by the step response experiment of the laser particle size analyzer. The fractal dimension of particulate matter was collected using a laser particle size analyzer and a scanning electron microscope. The fractal dimension of particulate matter was determined by a fractal geometric algorithm based on particle size distribution and microscopic morphology images. The average daily effective illumination duration with light intensity ≥300nm wavelength is collected using a light sensor; The photolysis rate of various pollutant characteristics was collected using a photochemical reactor.
[0018] Preferably, in one embodiment of this application, one minute is used as a data acquisition cycle. In practical applications, the implementer can adjust the acquisition frequency according to monitoring needs, and this application does not impose any restrictions.
[0019] It is understandable that each IoT sensing node outputs a complete set of physical and chemical property parameters in each acquisition cycle.
[0020] This completes the real-time collection of multi-dimensional parameters of air pollution sources.
[0021] Step 2: Based on the signal attenuation rate and response time, and by calculating the calibration coefficient through a dynamic calibration algorithm, the original concentration values collected by the IoT sensing layer are corrected to determine the pollution source concentration after calibration.
[0022] Preferably, in one embodiment of this application, the specific steps of the dynamic calibration algorithm are as follows: Retrieve the initial attenuation rate s0 and initial response time xt0 of the sensor when it left the factory, which are pre-stored in the cloud platform database; Based on the first ratio of signal attenuation rate s to initial attenuation rate s0 ; The second ratio of response time xt to initial response time xt0 ; Multiply the first ratio by the second ratio to determine the drift factor of the sensor performance; The specific formula for calculating the concentration of the pollution source after calibration is as follows: ; In the formula: PJ is the calibration coefficient, s is the current signal attenuation rate of the sensor, s0 is the initial attenuation rate of the sensor when it leaves the factory, xt is the current response time of the sensor, which is measured by the built-in timing module of the sensor, and xt0 is the initial response time of the sensor when it leaves the factory. The gas sensor array in the IoT sensing layer collects the raw concentration values N of different pollution sources that need to be monitored for air quality in real time. i-0 And based on the drift factor, the original concentration values N of different pollution sources i-0 To determine the extent of the impact and the calibrated concentrations of different pollution sources: N i =N i-0 ×PJ; Where: N i Let PJ be the concentration of the i-th pollution source after calibration, and N be the calibration coefficient. i-0 The original concentration value of the i-th pollution source is obtained by the sensor.
[0023] Understandably, the signal attenuation rate *s* reflects a decrease in sensor sensitivity (e.g., the detection signal weakens after the electrochemical electrode is corroded), and the response time *xt* reflects the sensor's reaction speed to concentration changes (e.g., particulate matter adhering to the optical lens causes signal delay). In terms of the drift factor (… When the value is greater than 1, it directly reflects sensor performance degradation (increased signal attenuation rate s or increased response time xt), requiring calibration compensation. This is achieved by adjusting the drift factor ( When ≈1, it can directly reflect the stability of the sensor's performance, and there is no need to significantly correct the calibration coefficient. This is achieved by subtracting the drift factor from 1. The calibration coefficient PJ obtained after this process reflects the degree of performance degradation of the sensor due to aging or environmental factors. This coefficient is used to adjust the original concentration value N. i-0 Dynamic compensation is performed to improve data accuracy, and then the concentration N of the i-th pollution source is calibrated. i Reflecting the corrected "true environmental concentration," after compensation by the calibration factor PJ, the calibrated concentration N of the i-th pollution source is... i It is closer to the true value.
[0024] At this point, the calibrated concentration values for each pollution source are obtained.
[0025] Step 3: Based on the calibrated pollution source concentration and particulate matter fractal dimension, obtain the pollution source identification index for different pollution sources through a pollution source identification algorithm.
[0026] Preferably, in one embodiment of this application, the specific steps of the pollution source identification algorithm are as follows: Retrieve the standard fractal dimension D corresponding to different pollution sources from the pre-existing cloud platform database. i-0 ; The third ratio based on the fractal dimension of particulate matter and the standard fractal dimension To determine the degree of morphological matching among different pollution sources; Based on the degree of morphological matching, the calibrated pollution source concentration N i The product of these factors determines the pollution source identification index for different pollution sources. The specific formula for calculating the pollution source identification index is as follows: ; In the formula: WY i Let D be the index for identifying the i-th pollution source. i Let D be the fractal dimension of the i-th pollution source particulate matter measured by multi-angle laser scattering method. i-0 Let be the standard fractal dimension of the i-th source.
[0027] Understandable It can reflect the degree of morphological matching between current particulate matter and the target pollution source, such as D. i-0 =2.2, Di =2.3, similarity = 2.2 / 2.3≈0.96, indicating a high degree of morphological similarity. The obtained pollution source identification index WY is 2.3. i The larger the value, the greater the contribution of the pollution source to the current pollution (e.g., industrial source WY). i =85 μg / m³, traffic source WY i =102 μg / m³, indicating that traffic sources contribute more. Step 3 of this embodiment identifies major pollution sources (such as industrial dust, vehicle exhaust, and biomass combustion) from a "morphological fingerprint" perspective, solving the problem of "different sources with the same concentration." Therefore, the i-th pollution source identification index WY... i By combining concentration and particulate matter morphology characteristics, it can effectively distinguish different pollution sources and improve the accuracy of source tracing.
[0028] At this point, the identification index of each pollution source is obtained.
[0029] Step 4: Based on the pollution source identification index, and combined with the average daily effective sunshine duration and the photolysis rate under different pollution characteristics of different pollution sources, the secondary pollution generation potential value of the main pollution sources is determined by the secondary pollution assessment algorithm.
[0030] Preferably, in one embodiment of this application, the specific steps of the secondary pollution assessment algorithm are as follows: Retrieve the photolysis rate k corresponding to different pollution characteristics of different pollution sources from the pre-existing cloud platform database. j ; Based on the photolysis rate k j Pollution Source Identification Index WY i The product of the average daily effective sunshine duration t is used to determine the potential value of secondary pollution generation under different pollution characteristics of different pollution sources.
[0031] Preferably, in one embodiment of this application, for each pollution source and its combination of pollution characteristics, the following is calculated: EQ i-j =WY i ×k j ×t; Where: EQ i-j Let k be the potential value for secondary pollution generation under the j-th pollution characteristic of the i-th pollution source. j Let t be the photolysis rate of the j-th pollution characteristic, and t be the cumulative daily effective illumination duration measured by the photosensitive sensor.
[0032] Get all EQ i-j The maximum value in the range is taken as the potential value for secondary pollution generation from the main pollution source.
[0033] It is understandable that the photolysis rate k of the j-th pollution characteristic jThe photolysis rate k of the j-th pollution characteristic can reflect the photochemical activity of pollutants. j Larger molecules are more easily decomposed under light, such as formaldehyde. k = 1 × 10 - 6 s -1 This indicates that formaldehyde is more likely to cause secondary pollution, and the calculated EQ... i-j The larger the EQ value, the greater the amount of secondary pollutants generated by the pollution source per unit time (e.g., vehicle exhaust P=361μg / m³, industrial dust P=204μg / m³, indicating that vehicle exhaust is more likely to cause O3 exceedances). This allows for the distinction between "primary pollution" and "secondary pollution risk," providing a priority basis for environmental law enforcement—the EQ value. i-j Prioritize the control of major pollution sources (such as biomass burning and vehicle exhaust), and provide early warnings for secondary pollution events (such as summer photochemical smog). In summary, EQ i-j This reflects the potential ability of pollutants to undergo photochemical reactions and generate secondary pollutants under light conditions.
[0034] Thus, the potential value for secondary pollution generation from the main pollution sources was obtained.
[0035] Step 5: Based on the secondary pollution generation potential value of the main pollution sources, the signal attenuation rate is corrected until the change rate of the signal attenuation rate after two consecutive corrections is less than the preset relative benchmark change rate. Based on the calibrated pollution source concentration, pollution source identification index and secondary pollution generation potential value, combined with time series analysis, the intelligent air quality detection results are output.
[0036] Preferably, in one embodiment of this application, the secondary pollution generation potential value (EQ) of the main pollution source is determined. i-j Is it greater than or equal to its corresponding secondary pollution threshold concentration EQ? i-j-0 If the conditions are met, the signal attenuation rate is corrected using the following formula: ; In the formula: s new EQ represents the corrected signal attenuation rate, s0 represents the initial attenuation rate of the sensor at the factory, and EQ represents the signal attenuation rate. i-j EQ represents the potential for secondary pollution generation from the i-th pollution source under the j-th pollution characteristic. i-j-0 Let s be the secondary pollution threshold concentration for the i-th pollution source and the j-th pollution characteristic, determined experimentally. base The increment of the base decay rate; Among them, i specifically refers to industrial dust pollution sources, vehicle exhaust pollution sources, and biomass combustion pollution sources, while j specifically refers to nitrogen dioxide pollution characteristics, sulfur dioxide pollution characteristics, and formaldehyde pollution characteristics.
[0037] The corrected signal attenuation rate snew Substitute the results back into the dynamic calibration algorithm of step 2, and iterate until the rate of change of signal attenuation after two consecutive corrections is less than the preset relative reference rate of change.
[0038] Finally, the calibrated pollution source concentration, pollution source identification index, and secondary pollution generation potential value are input into the time series analysis model. Combined with historical data trends, the model outputs intelligent air quality detection results, which are then visualized and pushed out as early warnings at the application layer. Furthermore, the calibrated pollution source concentration, pollution source identification index, and secondary pollution generation potential value can be combined with the time series observation form of line graphs to observe the changing trends of "primary pollution" and "secondary pollution risk" of each pollution source, and timely air quality early warning intervention measures can be taken based on the changing trends.
[0039] This completes the entire process of air quality detection, from data collection to intelligent analysis.
[0040] Based on the same inventive concept as the above method, embodiments of the present invention also provide an intelligent air quality detection system utilizing Internet of Things (IoT) technology, comprising: Sensing layer: Includes sensor drift monitoring unit, laser particle size analyzer, photochemical reactor, light sensor and gas sensor array, used to collect physical property parameters, chemical property parameters and raw concentration values; Network layer: Includes transmission module and edge computing gateway, used to transmit physical property parameters, chemical property parameters and raw concentration values collected by the sensing layer to the platform layer and execute dynamic calibration algorithm, pollution source identification algorithm and secondary pollution assessment algorithm; Platform layer: Includes cloud servers and databases. Cloud server configuration includes: Dynamic calibration module: used to perform calibration coefficients and calculate the concentration of pollution sources after calibration; Pollution source identification module: used to calculate the pollution source identification index for different pollution sources and match pollution sources; Secondary pollution assessment module: used to calculate and provide early warning of the potential for secondary pollution generation; Application layer: Includes a data visualization interface and an early warning command output unit, used to display the calibrated pollution source concentration, pollution source identification index, and secondary pollution generation potential value, as well as push pollution source control suggestions.
[0041] Thus, the method and system of this embodiment have achieved full-process intelligentization from sensing, transmission, calculation to early warning.
[0042] It should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should also be within the scope of protection of this invention.
Claims
1. An environmental air quality intelligent detection method using Internet of Things technology, characterized in that, The method comprises the following steps: deploying an Internet of Things sensing node in a monitoring area and collecting physical property parameters and chemical property parameters of air pollution sources in real time, wherein the physical property parameters include signal attenuation rate, response time, daily average effective illumination time, and particle fractal dimension of different pollution sources, and the chemical property parameters include photolysis rate under different pollution characteristics of different pollution sources; based on the signal attenuation rate and the response time, and through a dynamic calibration algorithm, a calibration coefficient is calculated to correct the original concentration value collected by the Internet of Things sensing layer, and the concentration of the pollution source after calibration is determined; based on the concentration of the pollution source after calibration and the particle fractal dimension, and through a pollution source identification algorithm, a pollution source identification index of different pollution sources is obtained; based on the pollution source identification index, combined with the daily average effective illumination time and the photolysis rate under different pollution characteristics corresponding to different pollution sources, a secondary pollution generation potential value of the main pollution source is determined through a secondary pollution evaluation algorithm; based on the secondary pollution generation potential value of the main pollution source, the signal attenuation rate is corrected until the change rate of the signal attenuation rate of the last two corrections is less than a preset relative reference change rate, and according to the concentration of the pollution source after calibration, the pollution source identification index, and the secondary pollution generation potential value, combined with time series analysis, an intelligent air quality detection result is output. 2.The environmental protection air quality intelligent detection method using the Internet of Things technology according to claim 1, characterized in that, The collection method of the physical property parameters and the chemical property parameters is: the signal attenuation rate and the response time are collected by a sensor drift monitoring unit of the Internet of Things sensing layer, wherein the signal attenuation rate is determined by the degree of electrochemical electrode oxidation, and the response time is determined by a laser particle size instrument step response experiment; the particle fractal dimension is collected by a laser particle size instrument and a scanning electron microscope, and the particle fractal dimension is determined by a fractal geometry algorithm of particle size distribution and microscopic morphology image; the daily average effective illumination time of illumination intensity greater than or equal to 300 nm wavelength is collected by an illumination sensor; the photolysis rate of each pollution characteristic is collected by a photochemical reaction instrument. 3.The environmental protection air quality intelligent detection method using the Internet of Things technology according to claim 2, characterized in that, The specific steps of the dynamic calibration algorithm are: the initial attenuation rate and the initial response time of the sensor at the time of factory shipment are retrieved from the pre-existing cloud platform database; the drift factor of the sensor performance is determined based on the product of the first ratio of the signal attenuation rate to the initial attenuation rate and the second ratio of the response time to the initial response time; the original concentration value of different pollution sources requiring air quality detection is collected in real time by a gas sensor array of the Internet of Things sensing layer; the concentration of the pollution source after calibration of different pollution sources is determined based on the influence degree of the drift factor on the original concentration value. 4.The environmental protection air quality intelligent detection method using the Internet of Things technology according to claim 3, characterized in that, The specific steps of the pollution source identification algorithm are: the standard fractal dimension corresponding to different pollution sources is retrieved from the pre-existing cloud platform database; the morphological matching degree of different pollution sources is determined based on the third ratio of the particle fractal dimension to the standard fractal dimension; the pollution source identification index of different pollution sources is determined based on the product of the morphological matching degree and the concentration of the pollution source after calibration. 5.The environmental protection air quality intelligent detection method using the Internet of Things technology according to claim 4, characterized in that, The specific steps of the secondary pollution evaluation algorithm are: the photolysis rate corresponding to different pollution characteristics of different pollution sources is retrieved from the pre-existing cloud platform database; Determine the secondary pollution generation potential value of different pollution sources under different pollution characteristics based on the product of the photolysis rate, the pollution source identification index, and the daily average effective light duration, and set the maximum value of the secondary pollution generation potential value of different pollution sources under different pollution characteristics as the secondary pollution generation potential value of the main pollution source. 6.The environmental-protection air quality intelligent detection method using the Internet of Things technology according to claim 5, characterized in that, Based on the main pollution source, retrieve the secondary pollution threshold concentration of the main pollution source, and when the secondary pollution generation potential value is greater than or equal to the secondary pollution threshold concentration, perform the following calculation of signal attenuation rate correction: ； wherein: s new s0 is the initial decay rate of the sensor at the time of manufacture, EQ i-j sij is the secondary pollution generation potential value of the ith pollution source under the jth pollution characteristic, EQ i-j-0 sij is the secondary pollution threshold concentration of the ith pollution source under the jth pollution characteristic determined by experiment, s base is the base decay rate increment; Where i is specifically industrial dust pollution source, automobile exhaust pollution source, and biomass combustion pollution source, and j is specifically nitrogen dioxide pollution characteristic, sulfur dioxide pollution characteristic, and formaldehyde pollution characteristic. 7.The environmental-protection air quality intelligent detection method using the Internet of Things technology according to claim 6, characterized in that, Based on the corrected signal attenuation rate, introduce the corrected signal attenuation rate into the dynamic calibration algorithm to replace the signal attenuation rate for correction until the change rate of the signal attenuation rate of the last two corrections is less than the preset relative reference change rate.
8. An environmental air quality intelligent detection system for performing the environmental air quality intelligent detection method using Internet of Things technology according to any one of claims 1-7, characterized in that, Comprise: The perception layer includes a sensor drift monitoring unit, a laser particle size analyzer, a photochemical reaction instrument, an illumination sensor, and a gas sensor array, which are used to collect physical property parameters, chemical property parameters, and original concentration values; The network layer includes a transmission module and an edge computing gateway, which are used to transmit the physical property parameters, chemical property parameters, and original concentration values collected by the perception layer to the platform layer and execute the dynamic calibration algorithm, the pollution source identification algorithm, and the secondary pollution evaluation algorithm; The platform layer includes a cloud server and a database, and the cloud server is configured with: The dynamic calibration module is used to calculate the calibration coefficient and the calibrated pollution source concentration; The pollution source identification module is used to calculate the pollution source identification index of different pollution sources and match the pollution sources; The secondary pollution evaluation module is used to calculate the secondary pollution generation potential value and issue a warning; The application layer includes a data visualization interface and a warning instruction output unit, which are used to display the calibrated pollution source concentration, the pollution source identification index, and the secondary pollution generation potential value and push pollution source control suggestions.