Self-adaptive dynamic tracking atmospheric monitoring platform construction method for particulate matter and pollution gas

Abstract

The invention relates to the field of environmental monitoring, and discloses a particulate matter and pollution gas adaptive dynamic tracking atmospheric monitoring platform construction method, which comprises the following steps: S1, analyzing a monitoring area by adopting a geographic information system technology, comprehensively considering factors such as landform, population distribution, industrial layout and the like, and determining an initial monitoring node position; according to the method, the monitoring nodes are distributed and optimized, the positions and the number of the monitoring nodes are dynamically adjusted according to historical monitoring data and real-time feedback information through intelligent algorithms such as a particle swarm optimization algorithm, and the optimal coverage of the monitoring area is achieved. The positions and the number of the monitoring nodes can be dynamically adjusted according to the actual situation of the monitoring area through monitoring node layout optimization; the comprehensive coverage of the monitoring area is realized, and the representativeness of the monitoring data is improved.

Description

Technical Field

[0001] The present invention relates to the field of environmental monitoring technology, and in particular to a method for constructing an atmospheric monitoring platform for adaptive dynamic tracking of particulate matter and pollutant gases. Background Art

[0002] Particulate matter in the atmosphere refers to solid or liquid particles suspended in the atmosphere, such as PM2.5 (particles with an aerodynamic diameter ≤ 2.5 microns), PM10, dust, smoke, smog, aerosols, etc. These are the main indicators of air pollution.

[0003] Particulate matter is the product of precursors, which usually refer to gaseous pollutants such as sulfur dioxide, nitrogen oxides, volatile organic compounds, ammonia, etc. These gaseous pollutants (precursors) form secondary particulate matter through complex chemical reactions (such as oxidation, nucleation, condensation, and gas-particle conversion) in the atmosphere. For example, the following reactions occur:

[0004] SO2 (sulfur dioxide) + oxidant (such as OH radical) → H2SO4 (sulfuric acid) → sulfate particles (such as (NH4)2SO4)

[0005] NO x (Nitrogen oxides) + VOCs (volatile organic compounds) + light → O3 (ozone) + secondary organic aerosols

[0006] NH3 (ammonia) + HNO3 (nitric acid) or H2SO4 (sulfuric acid) → ammonium nitrate or ammonium sulfate particles.

[0007] With the rapid development of industrialization and urbanization, air pollution is becoming increasingly serious, posing a significant threat to human health and the ecological environment. Accurate, real-time monitoring of atmospheric particulate matter and pollutant concentrations and their dynamic changes is crucial for air pollution prevention and control and environmental quality improvement.

[0008] Existing atmospheric monitoring platforms have many shortcomings. On the one hand, the distribution of monitoring sites is often relatively fixed, making it difficult to fully cover different areas. This is especially true in areas with complex terrain or variable pollution sources, where monitoring data has significant limitations. On the other hand, most traditional monitoring equipment can only perform static monitoring and cannot adaptively track the dynamic changes of pollutants in the atmosphere, resulting in a significant reduction in the timeliness and accuracy of monitoring data. In addition, the data integration and collaborative working capabilities between different monitoring devices are poor, making it difficult to form a comprehensive and systematic atmospheric pollution monitoring system. Therefore, there is an urgent need for a method to construct an atmospheric monitoring platform that can adaptively and dynamically track particulate matter and pollutant gases and overcome the above-mentioned shortcomings.

[0009] Therefore, it is necessary to provide a method for constructing an atmospheric monitoring platform for adaptive dynamic tracking of particulate matter and pollutant gases to solve the above technical problems. Summary of the Invention

[0010] The purpose of the present invention is to provide a method for constructing an atmospheric monitoring platform for adaptive dynamic tracking of particulate matter and pollutant gases, so as to solve the existing problems in the above-mentioned background technology.

[0011] To achieve the above object, the present invention provides the following technical solutions:

[0012] A method for constructing an adaptive dynamic tracking atmospheric monitoring platform for particulate matter and pollutant gases includes the following steps:

[0013] S1. Analyze the monitoring area using geographic information system technology, comprehensively consider factors such as topography, population distribution, and industrial layout, and determine the location of the initial monitoring nodes;

[0014] It also uses intelligent algorithms such as particle swarm optimization to dynamically adjust the location and number of monitoring nodes based on historical monitoring data and real-time feedback information to achieve optimal coverage of the monitoring area;

[0015] S2. Select particulate matter monitoring equipment and pollutant gas monitoring equipment with different monitoring accuracy and response time based on the characteristics of the monitoring area and monitoring needs. Equip the monitoring equipment with an adaptive control module that automatically adjusts the monitoring equipment's sampling frequency, measurement range, and other parameters based on the real-time monitored pollutant concentration and change trends.

[0016] S3, build a hybrid data transmission network based on wireless sensor networks and mobile networks to transmit monitoring data to the data processing center;

[0017] In the data processing center, big data processing technology and cloud computing platforms are used to store, analyze and process monitoring data in real time. Data mining algorithms and machine learning models are used to extract information such as the temporal and spatial distribution characteristics, change patterns and possible locations of pollution sources of pollutants.

[0018] S4. Develop an adaptive dynamic tracking algorithm based on the Kalman filter algorithm, etc., which dynamically adjusts the monitoring strategy of the monitoring platform according to the real-time changes of the monitoring data;

[0019] Combined with meteorological data, numerical simulation methods are used to predict the diffusion path of pollutants and optimize the dynamic tracking strategy of the monitoring platform.

[0020] As a further solution of the present invention, in the optimization of monitoring node layout, the density of monitoring nodes is increased in areas with dense pollution sources or areas with large changes in pollutant concentrations, and the number of nodes is appropriately reduced in areas with relatively stable pollution.

[0021] As a further solution of the present invention, the particulate matter monitoring equipment includes a laser scattering dust monitor, a beta-ray absorption particulate matter monitor, etc.; the polluted gas monitoring equipment includes a Fourier transform infrared spectrometer, an electrochemical gas sensor, etc.

[0022] As a further solution of the present invention, during the data transmission process, for monitoring nodes that are relatively close and have a small amount of data, WSN is used for data transmission; for nodes that are relatively far away or have a large amount of data, transmission is performed through a mobile network.

[0023] As a further solution of the present invention, when the adaptive dynamic tracking algorithm is running, when abnormal changes in pollutant concentration in a certain area are monitored, the algorithm automatically starts nearby backup monitoring equipment or adjusts the monitoring direction of existing monitoring equipment to focus on tracking and monitoring the area.

[0024] As a further solution of the present invention, when constructing an urban regional atmospheric monitoring platform, GIS technology is used to identify key areas such as urban centers, industrial areas, transportation hubs, and surrounding residential areas, parks, etc. as monitoring priorities, preliminarily determine the locations of monitoring nodes, and then adjust the node locations and number based on historical data and particle swarm optimization algorithm;

[0025] In heavily polluted areas, such as industrial zones and transportation hubs, select high-precision, fast-response monitoring equipment equipped with adaptive control modules. In relatively lightly polluted areas, such as residential areas, select low-cost, easy-to-maintain monitoring equipment.

[0026] Build wireless sensor networks and 4G networks to transmit data, and use cloud computing platforms to build big data processing systems to analyze data;

[0027] Adaptive dynamic tracking is performed using the Kalman filter algorithm combined with meteorological data.

[0028] As a further solution of the present invention, when constructing an industrial park atmospheric monitoring platform, geographic information analysis is performed on the industrial park, and the initial monitoring node locations are determined based on factory distribution and pollutant differences. The nodes are then adjusted using a particle swarm optimization algorithm based on factory production plans and historical emission data.

[0029] Select composite monitoring equipment with multiple monitoring functions and equipped with adaptive control modules to adjust the measurement range according to the factory's production cycle and emission characteristics;

[0030] Build high-speed wireless networks to transmit data, use distributed databases to store data, and use machine learning models to analyze data;

[0031] When the concentration of pollutants around the factory fluctuates abnormally, the adaptive dynamic tracking algorithm is activated, combining the meteorological conditions and terrain characteristics of the park to predict the spread of pollutants.

[0032] By optimizing the layout of monitoring nodes, the present invention can dynamically adjust the positions and numbers of monitoring nodes according to the actual conditions of the monitoring area, thereby achieving comprehensive coverage of the monitoring area and improving the representativeness of the monitoring data.

[0033] The selection and configuration of adaptive monitoring equipment enables the monitoring equipment to automatically adjust parameters according to the dynamic changes of pollutants, improving the accuracy and timeliness of monitoring data.

[0034] The constructed data transmission and processing system ensures the rapid transmission and efficient processing of monitoring data. Through big data analysis and machine learning models, it can deeply mine useful information from monitoring data, providing a scientific basis for air pollution prevention and control. The design of an adaptive dynamic tracking algorithm enables the monitoring platform to track the dynamic changes of pollutants in real time and adjust monitoring strategies in a timely manner, thus improving the monitoring platform's intelligence level and its ability to respond to sudden pollution incidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The present invention will be further described below with reference to the accompanying drawings and examples.

[0036] Figure 1 This is a comparison chart of monitoring node layout optimization;

[0037] Figure 2 It is a dynamic comparison chart of pollutant concentration;

[0038] Figure 3 It is a scatter plot for the validation of pollution diffusion prediction. DETAILED DESCRIPTION

[0039] Example 1

[0040] Construction method of atmospheric monitoring platform for adaptive dynamic tracking of particulate matter and pollutant gases, construction of urban area atmospheric monitoring platform

[0041] Monitoring node layout:

[0042] Using GIS technology, a city area was analyzed, identifying key areas such as the city center, industrial zones, transportation hubs, and surrounding residential areas and parks as key monitoring areas. Based on factors such as topography and population distribution, the locations of 50 monitoring nodes were initially determined. The city covers an area of ​​approximately 1,000 square kilometers, with a population density of 20,000 people per square kilometer in the city center, 5,000 people per square kilometer in industrial zones, and 8,000 people per square kilometer in residential areas. By analyzing this data and taking into account topographical factors such as the direction of rivers and mountains, a preliminary layout of monitoring nodes was determined.

[0043] Air monitoring data from the city over the past year was collected and the location of monitoring nodes was optimized using a particle swarm optimization algorithm. Particulate matter concentrations in industrial areas exceeded national standards by an average of 20% over the past year, and nitrogen oxide concentrations near transportation hubs exceeded standards by an average of 15% during peak hours.

[0044] After multiple iterative calculations, it was finally decided to add 10 monitoring nodes in industrial areas and 5 monitoring nodes near transportation hubs. At the same time, 5 monitoring nodes were reduced in some relatively lightly polluted residential areas, achieving more reasonable coverage of urban areas.

[0045] After optimization, the representativeness of monitoring data has increased by 30%, and can more comprehensively reflect the pollution conditions in different areas of the city.

[0046] Monitoring equipment configuration:

[0047] In heavily polluted areas such as industrial zones and transportation hubs, high-precision and fast-response beta-ray absorption particulate matter monitors and Fourier transform infrared spectrometers are selected and equipped with adaptive control modules.

[0048] The accuracy of the β-ray absorption particle monitor can reach 0.1μg / m 3 , Fourier transform infrared spectrometer can detect a variety of pollutant gases with an accuracy of ppm level.

[0049] In relatively lightly polluted areas such as residential areas, low-cost and easy-to-maintain laser scattering dust monitors and electrochemical gas sensors are used. The accuracy of the laser scattering dust monitor is 1 μg / m 3 The detection accuracy of electrochemical gas sensors for common pollutant gases is at the ppb level.

[0050] When the monitoring equipment is put into operation, the adaptive control module automatically adjusts the sampling frequency according to the real-time monitored pollutant concentration. For example, in an industrial area, when the particulate matter concentration exceeds a certain threshold (such as 50μg / m 3 ), the sampling frequency was increased from every 10 minutes to every 5 minutes. This doubled the amount of data collected when pollution concentrations fluctuated dramatically, effectively improving the timeliness and accuracy of the data.

[0051] Data transmission and processing:

[0052] A wireless sensor network is constructed to connect closely spaced monitoring nodes, transmitting data via a gateway to a nearby data collection station. For more distant monitoring nodes, a 4G network is used to transmit data directly to a data processing center. In a wireless sensor network, data transmission rates can reach 1 Mbps, meeting the needs of transmitting small amounts of data over short distances. The average 4G network transmission rate is 50 Mbps, ensuring rapid transmission of large amounts of monitoring data over longer distances.

[0053] At the data processing center, a big data processing system was built using a cloud computing platform to store and analyze monitoring data in real time. Data mining algorithms were used to analyze daily and weekly variations in atmospheric pollutants in different areas of the city. For example, during the weekday morning rush hour (7:00-9:00 AM) in the city center, motor vehicle exhaust emissions cause nitrogen oxide concentrations to increase by 30%, while during weekends, concentrations only increase by 10%. In industrial areas, particulate matter concentrations drop by 40% during the weekday evening hours (10:00 PM-6:00 AM) due to reduced production at some factories. These patterns provide strong support for the development of pollution prevention and control measures.

[0054] Adaptive Dynamic Tracking:

[0055] The Kalman filter algorithm processes monitoring data. When it detects an abnormal increase in pollutant concentration in a specific area, the algorithm automatically activates nearby backup monitoring equipment and adjusts the monitoring direction of some equipment to focus on tracking and monitoring that area. In the past year, backup monitoring equipment was activated 20 times, effectively capturing 15 sudden pollution incidents.

[0056] Combined with real-time meteorological data provided by the meteorological department, numerical simulation methods are used to predict the diffusion paths of pollutants. For example, if pollutants emitted by a pollution source are predicted to spread to surrounding residential areas due to wind direction, the monitoring platform's monitoring strategy is promptly adjusted, and monitoring equipment is added near the residential area in advance to ensure accurate monitoring of the pollutant's spread. Statistics show that this prediction and adjustment strategy has achieved an accuracy rate of 85% in predicting the diffusion path of pollutants, effectively improving the monitoring platform's ability to respond to pollution spread.

[0057] Example 2: Construction of an Industrial Park Atmospheric Monitoring Platform

[0058] Monitoring node layout:

[0059] A detailed geographic analysis of an industrial park was conducted. Taking into account the distribution of different factories within the park and the differences in pollutant types and concentrations, 30 monitoring node locations were initially identified. The industrial park covers an area of ​​150 square kilometers and houses 100 factories across various sectors, including chemical, machinery manufacturing, and electronics. Chemical companies are primarily located in the northern part of the park, machinery manufacturing is concentrated in the eastern part, and electronics companies are located in the southern part.

[0060] Based on the production plans and historical pollution emission data of each factory within the park, a particle swarm optimization algorithm was used to optimize the location of monitoring nodes. Over the past year, chemical companies emitted an average of 50 tons of sulfur dioxide per month, machinery manufacturers emitted 30 tons of particulate matter, and electronics companies emitted 20 tons of volatile organic compounds. Ultimately, eight monitoring nodes were added around some high-polluting factories, while three were removed from the relatively less polluted areas on the edge of the park. After optimization, monitoring coverage of high-pollution areas increased from 60% to 80%.

[0061] Monitoring equipment configuration:

[0062] In view of the various polluting gases and particulate matter that may be generated in the industrial park, a composite monitoring device with multiple monitoring functions was selected and equipped with an adaptive control module. For example, a multi-parameter monitor that can simultaneously monitor pollutants such as sulfur dioxide, nitrogen oxides, and particulate matter was selected. Its detection accuracy for sulfur dioxide can reach 0.5ppm, nitrogen oxides 1ppm, and particulate matter 0.5μg / m 3 .

[0063] The adaptive control module automatically adjusts the monitoring equipment's measurement range based on the factory's production cycle and pollutant emission characteristics. During periods of high-volume production, such as peak season for chemical companies, sulfur dioxide emissions can instantly increase fivefold. During these periods, the measurement range automatically expands from 0-10ppm to 0-50ppm to ensure accurate detection of high pollutant concentrations. This adaptive adjustment improves data efficiency by 40% during periods of fluctuating factory production.

[0064] Data transmission and processing:

[0065] A high-speed wireless network was established within the industrial park to ensure rapid transmission of monitoring data to the park's data processing center. The high-speed wireless network maintains a stable transmission rate of over 10 Mbps. The data processing center uses a distributed database to store monitoring data and analyzes it using machine learning models to identify emission patterns and patterns across different factories. For example, this analysis revealed that chemical companies experience a 20% increase in volatile organic compound emissions during high temperatures, while machinery manufacturers experience a 15% reduction in particulate matter emissions during equipment maintenance cycles.

[0066] Adaptive Dynamic Tracking:

[0067] When abnormal fluctuations in pollutant concentrations are detected around a factory, the adaptive dynamic tracking algorithm immediately activates, adjusting the sampling frequency and monitoring direction of nearby monitoring equipment to track the factory's pollution emissions in real time. In the past six months, the algorithm has been activated 30 times and accurately tracked 25 abnormal factory emissions events.

[0068] Numerical simulation methods were used to predict the spread of pollutants, combining the park's meteorological conditions and topographical characteristics. This provided accurate information support for pollution prevention and control and emergency response within the park. The dominant wind direction in the park during summer is southeasterly, with mountains blocking the way to the west. Numerical simulations accurately predicted that pollutants would disperse northeastern to the park under the influence of southeasterly winds and accumulate in a localized area due to the mountain ranges. This provided critical information for the timely evacuation of personnel and the implementation of prevention and control measures, effectively reducing the scope and severity of the pollution.

Claims

1. A method for constructing an adaptive dynamic tracking atmospheric monitoring platform for particulate matter and pollutant gases, characterized in that: The following steps are involved: S1. Analyze the monitoring area using geographic information system technology, comprehensively consider factors such as topography, population distribution, and industrial layout, and determine the location of the initial monitoring nodes; It also uses intelligent algorithms such as particle swarm optimization to dynamically adjust the location and number of monitoring nodes based on historical monitoring data and real-time feedback information to achieve optimal coverage of the monitoring area; S2. Select particulate matter monitoring equipment and pollutant gas monitoring equipment with different monitoring accuracy and response time based on the characteristics of the monitoring area and monitoring needs. Equip the monitoring equipment with an adaptive control module that automatically adjusts the monitoring equipment's sampling frequency, measurement range, and other parameters based on the real-time monitored pollutant concentration and change trends. S3, build a hybrid data transmission network based on wireless sensor networks and mobile networks to transmit monitoring data to the data processing center; In the data processing center, big data processing technology and cloud computing platforms are used to store, analyze and process monitoring data in real time. Data mining algorithms and machine learning models are used to extract information such as the temporal and spatial distribution characteristics, change patterns and possible locations of pollution sources of pollutants. S4. Develop an adaptive dynamic tracking algorithm based on the Kalman filter algorithm, etc., which dynamically adjusts the monitoring strategy of the monitoring platform according to the real-time changes of the monitoring data; Combined with meteorological data, numerical simulation methods are used to predict the diffusion path of pollutants and optimize the dynamic tracking strategy of the monitoring platform.

2. The method for constructing an adaptive dynamic tracking atmospheric monitoring platform for particulate matter and pollutant gases according to claim 1 is characterized by: In the optimization of monitoring node layout, the density of monitoring nodes should be increased in areas with dense pollution sources or where pollutant concentrations vary greatly, and the number of nodes should be appropriately reduced in areas where pollution is relatively stable.

3. The method for constructing an adaptive dynamic tracking atmospheric monitoring platform for particulate matter and pollutant gases according to claim 2 is characterized by: The particulate matter monitoring equipment includes a laser scattering dust monitor, a beta-ray absorption particulate matter monitor, etc.; the polluted gas monitoring equipment includes a Fourier transform infrared spectrometer, an electrochemical gas sensor, etc.

4. The method for constructing an adaptive dynamic tracking atmospheric monitoring platform for particulate matter and pollutant gases according to claim 3 is characterized by: During the data transmission process, for monitoring nodes that are relatively close and have a small amount of data, WSN is used for data transmission; for nodes that are relatively far away or have a large amount of data, transmission is carried out through the mobile network.

5. The method for constructing an adaptive dynamic tracking atmospheric monitoring platform for particulate matter and pollutant gases according to claim 4 is characterized by: When the adaptive dynamic tracking algorithm is running, when it detects abnormal changes in the pollutant concentration in a certain area, the algorithm automatically starts nearby backup monitoring equipment or adjusts the monitoring direction of existing monitoring equipment to conduct key tracking and monitoring of the area.

6. The method for constructing an adaptive dynamic tracking atmospheric monitoring platform for particulate matter and pollutant gases according to claim 5 is characterized by: When constructing an urban regional atmospheric monitoring platform, GIS technology was used to identify key areas such as city centers, industrial areas, transportation hubs, and surrounding residential areas and parks as monitoring priorities. The locations of monitoring nodes were initially determined, and the locations and number of nodes were then adjusted based on historical data and the particle swarm optimization algorithm. In heavily polluted areas, such as industrial zones and transportation hubs, select high-precision, fast-response monitoring equipment equipped with adaptive control modules. In relatively lightly polluted areas, such as residential areas, select low-cost, easy-to-maintain monitoring equipment. Build wireless sensor networks and 4G networks to transmit data, and use cloud computing platforms to build big data processing systems to analyze data; Adaptive dynamic tracking is performed using the Kalman filter algorithm combined with meteorological data.

7. The method for constructing an adaptive dynamic tracking atmospheric monitoring platform for particulate matter and pollutant gases according to claim 6 is characterized by: When constructing the industrial park air monitoring platform, we conducted a geographic information analysis of the industrial park, determined the initial monitoring node locations based on factory distribution and pollutant differences, and used a particle swarm optimization algorithm to adjust the nodes based on factory production plans and historical emission data. Select composite monitoring equipment with multiple monitoring functions and equipped with adaptive control modules to adjust the measurement range according to the factory's production cycle and emission characteristics; Build high-speed wireless networks to transmit data, use distributed databases to store data, and use machine learning models to analyze data; When the concentration of pollutants around the factory fluctuates abnormally, the adaptive dynamic tracking algorithm is activated, combining the meteorological conditions and terrain characteristics of the park to predict the spread of pollutants.

Images