Intelligent monitoring and early warning system and method for atmospheric pollution

Abstract

The invention relates to the technical field of environmental monitoring, provides an intelligent monitoring and early warning system and method for atmospheric pollution, solves the problems of insufficient distribution density and coverage range of monitoring equipment, and realizes comprehensive real-time monitoring and early warning by combining a digital twin model, a dynamic monitoring unit and an efficient data processing technology. The air quality sensor is used for collecting data, dynamic mobile terminal equipment (such as an unmanned aerial vehicle and a mobile inspection robot) is combined to fill the monitoring blank, and the data accuracy is improved. The dynamic monitoring unit optimizes sensor operation parameters through a deep learning model and improves data reliability, the air quality early warning unit comprehensively compares air quality data and generates early warning information in time, and the system further has knowledge base optimization and result visualization functions and provides powerful technical support for handling atmospheric pollution.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring, and in particular to an intelligent air pollution monitoring and early warning system and method. Background Art

[0002] The intelligent air pollution monitoring and early warning system is an environmental monitoring platform that integrates advanced sensors, communication technology, big data analysis, cloud computing and other technologies. By deploying sensors in every corner of the city, including industrial areas, traffic arteries, residential areas and other key areas, the system can collect air quality data in real time, provide effective early warning and management means for decision makers and the public, and thus deal with air pollution problems.

[0003] In existing technology applications, the intelligent monitoring and early warning system for air pollution mainly uses air quality sensors to collect air quality data at specific time points, such as the concentration of PM2.5, PM10, sulfur dioxide, nitrogen oxides and other pollutants. These data are transmitted to the data center in real time through efficient communication technology for storage and analysis. With the help of big data analysis technology, the system can identify changing trends and abnormal conditions of air quality, such as excessive emissions or sudden pollution events. When it is detected that the air quality reaches the warning standard, the system immediately issues a warning signal to relevant departments and the public through the information platform so that timely measures can be taken to protect health.

[0004] However, the intelligent monitoring and early warning system for air pollution also faces the following technical pain points. The data for intelligent monitoring of air pollution is based on monitoring equipment distributed in various places. Since the distribution density and coverage of the monitoring equipment cannot be high-density, the data used in the existing intelligent monitoring of air pollution has limitations. To this end, the present invention provides an intelligent monitoring and early warning system and method for air pollution, which are used to improve the accuracy of intelligent monitoring and early warning of air pollution. Summary of the invention

[0005] In view of the shortcomings of the existing technology, the present invention provides an intelligent monitoring and early warning system and method for air pollution, which solves the problem that the density of monitoring equipment and the coverage range cannot be high, resulting in limitations in the data used in the existing intelligent air pollution monitoring.

[0006] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows:

[0007] In a first aspect, the present invention provides an intelligent air pollution monitoring and early warning system, comprising:

[0008] Data collection module: obtains the operating data of the intelligent air pollution monitoring equipment, which includes the location data of the monitoring equipment and the operating status data of the monitoring equipment. The monitoring equipment includes an air quality sensor, and obtains the air quality data collected by the air quality sensor;

[0009] The data processing module substitutes the monitoring equipment location data into the preset digital twin model to obtain the monitoring equipment location image data, matches the monitoring equipment operation status data with the monitoring equipment location image data, and displays the normally operating monitoring equipment in the image;

[0010] A monitoring task receiving unit receives an air pollution monitoring task, extracts monitoring area features for the air pollution monitoring task, obtains the location of the area to be monitored, substitutes the location of the area to be monitored and the image data of the monitoring equipment location into a preset air quality monitorable area prediction model, and obtains the monitorable area of ​​the real-time monitoring equipment;

[0011] The dynamic monitoring unit compares the position of the monitorable area of ​​the real-time monitoring device with the position of the area to be monitored, obtains the area without corresponding monitoring equipment, collects the coordinate data of the area without corresponding monitoring equipment, obtains the position data of the dynamic mobile terminal device, substitutes the position data of the dynamic mobile terminal device and the coordinate data of the area without corresponding monitoring equipment into the preset dynamic air quality inspection model, generates the dynamic air quality monitoring path, and the dynamic mobile terminal device executes the dynamic air quality monitoring path and collects air quality data. The dynamic mobile terminal device includes a mobile inspection robot and a drone;

[0012] The air quality warning unit receives air quality data collected by dynamic mobile terminal devices and also receives air quality data collected by monitoring devices in the monitorable area of ​​the real-time monitoring device. It removes duplicate data with the same position coordinates from the air quality data collected by the dynamic mobile terminal devices and the air quality data collected by the monitoring devices in the monitorable area of ​​the real-time monitoring device according to the coordinate information to obtain air quality data to be compared. The air quality data to be compared is compared with preset standard air quality parameters. If there is a value in the air quality data to be compared that is greater than the preset standard air quality parameters, air quality warning information is generated.

[0013] Furthermore, in the intelligent air pollution monitoring and early warning system of the present invention, the dynamic monitoring unit is also used for:

[0014] If the model calculation results cannot be output after the location data of the dynamic mobile terminal device and the coordinate data of the corresponding monitoring device area are substituted into the preset dynamic air quality inspection model, the attribute information of each electrical component and sensor in the intelligent air pollution monitoring device is obtained;

[0015] According to the attribute information of each electrical component and sensor in the air pollution intelligent monitoring device, retrieve the corresponding historical data of each electrical component and sensor in the air pollution intelligent monitoring device from the preset cloud database;

[0016] The deep learning model is trained using the historical data of electrical components and sensors in the intelligent air pollution monitoring device to obtain an air pollution component screening simulation model;

[0017] Substituting the real-time collected air pollution sample data into the air pollution component screening simulation model to obtain the air pollution component screening simulation results, and comparing the air pollution component screening simulation results with the air pollution sample component characteristics. If the comparison result between the air pollution component screening simulation results and the air pollution sample component characteristics is greater than the preset error value, the sensor operating parameters are corrected;

[0018] Extracting attribute information of each electrical component and sensor from the air pollution intelligent monitoring device, the attribute information of the electrical component and sensor including model, specification, manufacturer, production date and most recent calibration date;

[0019] According to the acquired attribute information, the historical data of each electrical component and sensor in the corresponding intelligent air pollution monitoring device is retrieved from the preset cloud database, and the historical data of each electrical component and sensor includes historical usage records, historical performance and fault history;

[0020] Preprocess the retrieved historical data, and use the preprocessed historical data to train the deep learning model. After the training is completed, an atmospheric pollution component screening simulation model is obtained. The atmospheric pollution component screening simulation model is used to simulate the actual working process of the atmospheric pollution intelligent monitoring device and output the simulated atmospheric pollution component screening results;

[0021] Use intelligent air pollution monitoring devices to collect air pollution sample data in real time;

[0022] Substituting the real-time collected air pollution sample data into the air pollution component screening simulation model to obtain the air pollution component simulation results;

[0023] Compare the simulated results of atmospheric pollution components with the composition characteristics of atmospheric pollution samples collected in real time, and calculate the error value of the comparison results;

[0024] If the comparison result is greater than the preset error value, there is a deviation or fault in the sensor operating parameters;

[0025] According to the error value of the comparison result, a match is performed in a preset sensor fault knowledge base to obtain the sensor operating parameters and operating parameter adjustment values ​​that need to be corrected. The operating parameter adjustment values ​​include adjusting the sensitivity, calibration coefficient and measurement range of the sensor;

[0026] After the sensor executes the operating parameter adjustment value, it recollects the air pollution sample data and substitutes it into the air pollution component screening simulation model for verification;

[0027] If the comparison result between the simulated results of atmospheric pollution components and the characteristic scores of the atmospheric pollution sample components collected in real time is within the preset error range, the correction process is completed.

[0028] Furthermore, in the intelligent air pollution monitoring and early warning system of the present invention, the dynamic monitoring unit is also used for:

[0029] Obtain the characteristics of air pollution components, and compare the obtained comparison results of air pollution components with the preset error range. If the comparison results still exceed the preset error range, enter the next step of optimization process;

[0030] According to the deviation of the comparison results of the characteristics of atmospheric pollution components, the preset atmospheric pollution monitoring and diagnosis knowledge base is optimized using the machine learning algorithm, and the atmospheric pollution monitoring and diagnosis knowledge base after optimization is used to match the results of the atmospheric pollution component clustering analysis again. When the comparison results of the characteristics of atmospheric pollution components meet the preset error range, or the number of optimizations of the preset atmospheric pollution monitoring and diagnosis knowledge base reaches the preset maximum number of iterations, the final atmospheric pollution monitoring and diagnosis results and the status of the currently used atmospheric pollution monitoring and diagnosis knowledge base are output.

[0031] Furthermore, in the intelligent air pollution monitoring and early warning system of the present invention, the dynamic monitoring unit is also used for:

[0032] If the comparison result of the characteristics of the air pollution components is within the preset error range, the analysis result of the air pollution components is generated;

[0033] Establish a corresponding relationship between the monitored area and the analysis results of air pollution components to obtain the analysis results of air pollution components in the monitored area;

[0034] Matching the monitored area in the preset monitored areas to obtain the grouping information of the monitored areas, and detecting the information of the personnel authorized to see the atmospheric pollution monitoring and analysis results in the grouping information of the monitored areas;

[0035] Retrieve the air pollution component analysis results corresponding to the information of the person who authorized the visible air pollution monitoring and analysis results, obtain the visible air pollution monitoring and analysis result data set, perform cluster analysis on the visible air pollution monitoring and analysis result data set, and obtain the visible air pollution monitoring and analysis cluster analysis results;

[0036] The visible air pollution monitoring and analysis cluster analysis results and air pollution component analysis results are converted into visual information through a preset digital animation model and transmitted to the display device.

[0037] In a second aspect, an intelligent air pollution monitoring and early warning method is applied to the intelligent air pollution monitoring and early warning system as described above, comprising:

[0038] Step S101, obtaining operation data of an intelligent air pollution monitoring device, the operation data of the intelligent air pollution monitoring device including location data of the monitoring device and operation status data of the monitoring device, the monitoring device including an air quality sensor, obtaining air quality data collected by the air quality sensor;

[0039] Step S102, substitute the monitoring device location data into the preset digital twin model to obtain the monitoring device location image data, match the monitoring device operation status data with the monitoring device location image data, and display the normally operating monitoring device in the image;

[0040] Step S103, receiving an air pollution monitoring task, extracting monitoring area features for the air pollution monitoring task, obtaining the location of the area to be monitored, substituting the location of the area to be monitored and the image data of the monitoring equipment location into a preset air quality monitorable area prediction model, and obtaining the monitorable area of ​​the real-time monitoring equipment;

[0041] Step S104, comparing the position of the monitorable area of ​​the real-time monitoring device with the position of the area to be monitored, obtaining the area without corresponding monitoring equipment, collecting the coordinate data of the area without corresponding monitoring equipment, obtaining the position data of the dynamic mobile terminal device, substituting the position data of the dynamic mobile terminal device and the coordinate data of the area without corresponding monitoring equipment into the preset dynamic air quality inspection model, generating an air quality dynamic monitoring path, the dynamic mobile terminal device executes the air quality dynamic monitoring path and collects air quality data, and the dynamic mobile terminal device includes a mobile inspection robot and a drone;

[0042] Step S105, receiving air quality data collected by the dynamic mobile terminal device, and also receiving air quality data collected by the monitoring device in the monitorable area of ​​the real-time monitoring device, removing duplicate data with the same position coordinates of the air quality data collected by the dynamic mobile terminal device and the air quality data collected by the monitoring device in the monitorable area of ​​the real-time monitoring device according to the coordinate information, to obtain air quality data to be compared, and comparing the air quality data to be compared with the preset standard air quality parameters. If there is a value in the air quality data to be compared that is greater than the preset standard air quality parameters, air quality warning information is generated.

[0043] Furthermore, the air pollution intelligent monitoring and early warning method of the present invention, the step S104 includes: if the location data of the dynamic mobile terminal device and the coordinate data of the area without the corresponding monitoring device are substituted into the preset dynamic air quality inspection model, the model operation result cannot be output, then the attribute information of each electrical component and sensor in the air pollution intelligent monitoring device is obtained;

[0044] According to the attribute information of each electrical component and sensor in the air pollution intelligent monitoring device, retrieve the corresponding historical data of each electrical component and sensor in the air pollution intelligent monitoring device from the preset cloud database;

[0045] The deep learning model is trained using the historical data of electrical components and sensors in the intelligent air pollution monitoring device to obtain an air pollution component screening simulation model;

[0046] Substituting the real-time collected air pollution sample data into the air pollution component screening simulation model to obtain the air pollution component screening simulation results, and comparing the air pollution component screening simulation results with the air pollution sample component characteristics. If the comparison result between the air pollution component screening simulation results and the air pollution sample component characteristics is greater than the preset error value, the sensor operating parameters are corrected;

[0047] Extracting attribute information of each electrical component and sensor from the air pollution intelligent monitoring device, the attribute information of the electrical component and sensor including model, specification, manufacturer, production date and most recent calibration date;

[0048] According to the acquired attribute information, the historical data of each electrical component and sensor in the corresponding intelligent air pollution monitoring device is retrieved from the preset cloud database, and the historical data of each electrical component and sensor includes historical usage records, historical performance and fault history;

[0049] Preprocess the retrieved historical data, and use the preprocessed historical data to train the deep learning model. After the training is completed, an atmospheric pollution component screening simulation model is obtained. The atmospheric pollution component screening simulation model is used to simulate the actual working process of the atmospheric pollution intelligent monitoring device and output the simulated atmospheric pollution component screening results;

[0050] Use intelligent air pollution monitoring devices to collect air pollution sample data in real time;

[0051] Substituting the real-time collected air pollution sample data into the air pollution component screening simulation model to obtain the air pollution component simulation results;

[0052] Compare the simulated results of atmospheric pollution components with the composition characteristics of atmospheric pollution samples collected in real time, and calculate the error value of the comparison results;

[0053] If the comparison result is greater than the preset error value, there is a deviation or fault in the sensor operating parameters;

[0054] According to the error value of the comparison result, a match is performed in a preset sensor fault knowledge base to obtain the sensor operating parameters and operating parameter adjustment values ​​that need to be corrected. The operating parameter adjustment values ​​include adjusting the sensitivity, calibration coefficient and measurement range of the sensor;

[0055] After the sensor executes the operating parameter adjustment value, it recollects the air pollution sample data and substitutes it into the air pollution component screening simulation model for verification;

[0056] If the comparison result between the simulated results of atmospheric pollution components and the characteristic scores of the atmospheric pollution sample components collected in real time is within the preset error range, the correction process is completed.

[0057] Furthermore, in the air pollution intelligent monitoring and early warning method of the present invention, step S104 comprises:

[0058] Obtain the characteristics of air pollution components, and compare the obtained comparison results of air pollution components with the preset error range. If the comparison results still exceed the preset error range, enter the next step of optimization process;

[0059] According to the deviation of the comparison results of the characteristics of atmospheric pollution components, the preset atmospheric pollution monitoring and diagnosis knowledge base is optimized using the machine learning algorithm, and the atmospheric pollution monitoring and diagnosis knowledge base after optimization is used to match the results of the atmospheric pollution component clustering analysis again. When the comparison results of the characteristics of atmospheric pollution components meet the preset error range, or the number of optimizations of the preset atmospheric pollution monitoring and diagnosis knowledge base reaches the preset maximum number of iterations, the final atmospheric pollution monitoring and diagnosis results and the status of the currently used atmospheric pollution monitoring and diagnosis knowledge base are output.

[0060] Furthermore, in the air pollution intelligent monitoring and early warning method of the present invention, step S104 comprises:

[0061] If the comparison result of the characteristics of the air pollution components is within the preset error range, the analysis result of the air pollution components is generated;

[0062] Establish a corresponding relationship between the monitored area and the analysis results of air pollution components to obtain the analysis results of air pollution components in the monitored area;

[0063] Matching the monitored area in the preset monitored areas to obtain the grouping information of the monitored areas, and detecting the information of the personnel authorized to see the atmospheric pollution monitoring and analysis results in the grouping information of the monitored areas;

[0064] Retrieve the air pollution component analysis results corresponding to the information of the person who authorized the visible air pollution monitoring and analysis results, obtain the visible air pollution monitoring and analysis result data set, perform cluster analysis on the visible air pollution monitoring and analysis result data set, and obtain the visible air pollution monitoring and analysis cluster analysis results;

[0065] The visible air pollution monitoring and analysis cluster analysis results and air pollution component analysis results are converted into visual information through a preset digital animation model and transmitted to the display device.

[0066] The beneficial effects of the present invention are mainly reflected in the following aspects:

[0067] The present invention realizes real-time monitoring and early warning of air pollution by combining digital twin models, dynamic monitoring units and efficient data processing technology. The system obtains the operating data of monitoring equipment, matches it with the digital twin model, obtains the monitorable area, and improves the data accuracy.

[0068] The dynamic monitoring unit uses mobile inspection robots and drones to perform dynamic air quality monitoring, filling the monitoring gap and providing timely support for decision makers and the public. The air quality early warning unit generates early warning information by comparing air quality data with preset standards, improving the timeliness and accuracy of early warnings.

[0069] If abnormal sensor data is found, the system will train the sensor's historical data through a deep learning model, simulate the actual working process of the intelligent air pollution monitoring device, and correct the sensor operating parameters based on the simulation results, thereby improving the reliability of the data.

[0070] According to the deviation of the comparison results of the characteristics of air pollution components, the preset air pollution monitoring and diagnosis knowledge base is optimized to improve the accuracy of diagnosis. The results of air pollution component analysis and cluster analysis are converted into visual information through preset digital animation models and transmitted to the display device to facilitate decision makers and the public to understand.

[0071] The present invention effectively improves the accuracy of intelligent monitoring and early warning of air pollution, and provides strong technical support for addressing air pollution problems. By comparing the locations of the areas that can be monitored by real-time monitoring equipment and the areas to be monitored, the layout of the monitoring equipment is optimized and the monitoring efficiency is improved. The dynamic air quality inspection model generates dynamic air quality monitoring paths, and the dynamic mobile terminal devices collect air quality data along these paths, which increases the flexibility of monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0073] Figure 1 A schematic flow chart of an intelligent air pollution monitoring and early warning method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings.

[0075] In order to better understand the purpose of the present invention, the present invention is described in further detail below.

[0076] In a first aspect, the present invention provides an intelligent air pollution monitoring and early warning system, comprising:

[0077] Data collection module: obtains the operating data of the intelligent air pollution monitoring equipment, which includes the location data of the monitoring equipment and the operating status data of the monitoring equipment. The monitoring equipment includes an air quality sensor, and obtains the air quality data collected by the air quality sensor;

[0078] Obtain the operating data of intelligent air pollution monitoring equipment, including the location data of the monitoring equipment and the operating status data of the monitoring equipment.

[0079] Obtain air quality data collected by air quality sensors. The data comes from intelligent atmospheric pollution monitoring equipment. These devices include air quality sensors, which are used to collect air quality data at a specific time point, such as the concentration of PM2.5, PM10, sulfur dioxide, nitrogen oxides and other pollutants.

[0080] Data collection technology uses sensor technology to collect air quality data in real time. The collected data is transmitted to the data center in real time through efficient communication technology.

[0081] Data processing flow, the data acquisition module further transmits the collected data to the data processing module for subsequent processing and analysis.

[0082] Air quality sensors are deployed in key areas of the city, such as industrial areas, traffic arteries, and residential areas, to ensure the comprehensiveness and representativeness of the data. Wireless communication technologies such as 4G / 5G and Wi-Fi may be used during data transmission to ensure the real-time and accuracy of the data.

[0083] The data acquisition module is the foundation of the entire intelligent air pollution monitoring and early warning system, ensuring that the system can obtain accurate and real-time air quality data, providing strong support for subsequent data analysis and early warning.

[0084] The data acquisition module works closely with the data processing module to ensure accurate data processing. At the same time, the data acquisition module provides necessary data support for the monitoring task receiving unit, dynamic monitoring unit and air quality early warning unit.

[0085] The data acquisition module is suitable for various scenarios that require real-time monitoring of air quality, such as urban environmental monitoring, industrial emission monitoring, etc. It is necessary to ensure the long-term stable operation of sensor equipment and the reliability and security of data transmission. It is necessary to process a large amount of real-time data, which places high demands on the system's storage and processing capabilities.

[0086] With the continuous development of Internet of Things technology, data collection modules may become more intelligent and automated in the future, improving the efficiency and accuracy of data collection.

[0087] In short, the data acquisition module realizes the real-time collection and transmission of the operating data of the intelligent atmospheric pollution monitoring equipment and the air quality data through advanced sensor technology and efficient communication technology, providing a solid data foundation for the operation of the entire system.

[0088] The data processing module substitutes the monitoring equipment location data into the preset digital twin model to obtain the monitoring equipment location image data, matches the monitoring equipment operation status data with the monitoring equipment location image data, and displays the normally operating monitoring equipment in the image;

[0089] The data processing module is responsible for substituting the monitoring equipment location data into the preset digital twin model to obtain the monitoring equipment location image data. It also matches the monitoring equipment operation status data with the monitoring equipment location image data to display the normally operating monitoring equipment in the image.

[0090] The data processing process obtains the operating data of the intelligent air pollution monitoring equipment, including the location data of the monitoring equipment and the operating status data of the monitoring equipment. The location data is substituted into the digital twin model to generate the corresponding monitoring equipment location image data. Finally, the monitoring equipment operating status data is matched with the image data to graphically display the normal operation of the monitoring equipment.

[0091] The digital twin model is an important tool for converting actual monitoring equipment location data into visual image data for better understanding and analysis.

[0092] Data matching technology ensures the accuracy and real-time nature of data by matching the operating status data of monitoring equipment with location image data.

[0093] The digital twin model needs to be established in advance and can dynamically generate corresponding images based on the input monitoring equipment location data. The data matching process needs to ensure accurate alignment of the data to avoid errors or omissions. The entire data processing process needs to be executed efficiently and accurately to ensure the timeliness of real-time monitoring and early warning.

[0094] The data processing module can effectively process and analyze the operating data of the intelligent air pollution monitoring equipment, providing reliable data support for subsequent monitoring and early warning.

[0095] A monitoring task receiving unit receives an air pollution monitoring task, extracts monitoring area features for the air pollution monitoring task, obtains the location of the area to be monitored, substitutes the location of the area to be monitored and the image data of the monitoring equipment location into a preset air quality monitorable area prediction model, and obtains the monitorable area of ​​the real-time monitoring equipment;

[0096] The specific implementation and technical details of the monitoring task receiving unit are as follows. The monitoring task receiving unit is responsible for receiving air pollution monitoring tasks. This is the input end of the entire monitoring and early warning system. All subsequent monitoring and analysis work is based on these received tasks. The received monitoring tasks will be subjected to monitoring area feature extraction. The purpose of this step is to determine the specific location of the area to be monitored so that the system can know where to perform air quality monitoring.

[0097] The location data is substituted into the prediction model, and the extracted location data of the area to be monitored, as well as the existing location image data of the monitoring equipment, are substituted into the preset prediction model of the air quality monitorable area. The function of this model is to predict the monitoring area that can be covered by the real-time monitoring equipment.

[0098] Predict the area that can be monitored by real-time monitoring equipment. Through the air quality monitorable area prediction model, the system can obtain the monitoring area that can be covered by the current real-time monitoring equipment. This is crucial for determining whether the dynamic monitoring unit needs to intervene for supplementary monitoring.

[0099] The real-time monitoring equipment will compare the locations of the monitored areas with those of the areas to be monitored to identify those areas without corresponding monitoring equipment. The entire process is automated and does not require human intervention. This ensures that the system can respond to monitoring tasks efficiently and promptly, improving monitoring efficiency and accuracy.

[0100] The monitoring task receiving unit works closely with the dynamic monitoring unit. When an area without corresponding monitoring equipment is identified, the dynamic monitoring unit will intervene to conduct dynamic air quality monitoring.

[0101] The dynamic monitoring unit compares the position of the monitorable area of ​​the real-time monitoring device with the position of the area to be monitored, obtains the area without corresponding monitoring equipment, collects the coordinate data of the area without corresponding monitoring equipment, obtains the position data of the dynamic mobile terminal device, substitutes the position data of the dynamic mobile terminal device and the coordinate data of the area without corresponding monitoring equipment into the preset dynamic air quality inspection model, generates the dynamic air quality monitoring path, and the dynamic mobile terminal device executes the dynamic air quality monitoring path and collects air quality data. The dynamic mobile terminal device includes a mobile inspection robot and a drone;

[0102] Compare the locations of the areas that can be monitored by real-time monitoring equipment with those of the areas to be monitored, and identify areas without corresponding monitoring equipment. Collect coordinate data of the corresponding monitoring equipment areas, and obtain the location data of dynamic mobile terminal devices. Use these data to generate dynamic air quality monitoring paths and guide dynamic mobile terminal devices to perform monitoring tasks.

[0103] The location data of the dynamic mobile terminal device and the coordinate data of the corresponding monitoring device area are substituted into the preset dynamic air quality inspection model. The dynamic air quality inspection model generates an optimized air quality dynamic monitoring path based on the input data.

[0104] Dynamic mobile terminal devices include mobile inspection robots and drones, which can collect air quality data based on the generated paths.

[0105] If the dynamic air quality inspection model cannot output valid calculation results, the system obtains the attribute information of each electrical component and sensor in the intelligent air pollution monitoring device.

[0106] Use these attribute information to retrieve the corresponding historical data from the cloud database, train the deep learning model, and obtain the atmospheric pollution component screening simulation model.

[0107] The model accuracy is verified through real-time collected atmospheric pollution sample data, and the sensor operating parameters are adjusted when necessary.

[0108] Obtain the characteristics of air pollution components and compare them with the preset error range. If the comparison result exceeds the error range, optimize the air pollution monitoring and diagnosis knowledge base and use the optimized knowledge base for re-matching. When the comparison result meets the preset error range or reaches the maximum number of iterations, output the final air pollution monitoring and diagnosis results and the current knowledge base status.

[0109] Generate air pollution component analysis results and establish a corresponding relationship between them and the monitored area. Perform cluster analysis on the visible air pollution monitoring and analysis result data set, and convert it into visual information through a preset digital animation model and transmit it to the display device.

[0110] Correct the sensor operating parameters. When the comparison result between the atmospheric pollution component screening simulation result and the atmospheric pollution sample component characteristics collected in real time is greater than the preset error value, the system will correct the sensor operating parameters. The correction process includes adjusting the sensor's sensitivity, calibration coefficient, and measurement range, and re-verifying the effect after correction.

[0111] The air quality data collected by the dynamic mobile terminal device is used together with the data collected by the real-time monitoring device to generate the air quality data to be compared. The data is compared with the preset standard air quality parameters. If there is an excess, an air quality warning message is generated.

[0112] These technical details demonstrate how the dynamic monitoring unit can achieve intelligent monitoring and early warning of air pollution through intelligent means, thereby improving the accuracy and comprehensiveness of monitoring.

[0113] The air quality warning unit receives air quality data collected by dynamic mobile terminal devices and also receives air quality data collected by monitoring devices in the monitorable area of ​​the real-time monitoring device. It removes duplicate data with the same position coordinates from the air quality data collected by the dynamic mobile terminal devices and the air quality data collected by the monitoring devices in the monitorable area of ​​the real-time monitoring device according to the coordinate information to obtain air quality data to be compared. The air quality data to be compared is compared with preset standard air quality parameters. If there is a value in the air quality data to be compared that is greater than the preset standard air quality parameters, air quality warning information is generated.

[0114] The air quality early warning unit is a component of the air pollution intelligent monitoring and early warning system. It is responsible for receiving and processing air quality data and generating early warning information. According to the provided documents, the specific implementation and technical details of the air quality early warning unit are as follows:

[0115] Data source: air quality data collected by dynamic mobile terminal devices. Real-time monitoring equipment can monitor air quality data collected by monitoring equipment in the area.

[0116] Compare the coordinate information of the air quality data collected by the dynamic mobile terminal device and the real-time monitoring device, remove duplicate data, obtain the air quality data to be compared, and compare the air quality data to be compared with the preset standard air quality parameters

[0117] Warning conditions: If the air quality data to be compared contains a value greater than the preset standard air quality parameter, an air quality warning message will be generated. When the air quality data exceeds the preset standard, the system will automatically generate a warning message to indicate that the air quality is abnormal.

[0118] The system integrates data from different monitoring devices, including fixed monitoring stations and dynamic monitoring units (such as mobile inspection robots and drones), to improve the comprehensiveness and accuracy of early warnings.

[0119] Using efficient data processing technology, a large amount of air quality data can be quickly processed and compared. The preset standard air quality parameters can be adjusted according to actual conditions to adapt to environmental changes in different regions and time periods.

[0120] The air quality early warning unit is tightly integrated with other system modules (such as data acquisition module, data processing module, dynamic monitoring unit, etc.) to form a complete intelligent monitoring and early warning system for air pollution.

[0121] The application scenarios are suitable for air quality monitoring and early warning in multiple key areas such as cities, industrial areas, transportation arteries, and residential areas.

[0122] The system may also include a user interface for displaying warning information and air quality data to facilitate decision makers and the public to understand the current air quality status,

[0123] Specifically, in the air pollution intelligent monitoring and early warning system of the present invention, the dynamic monitoring unit is also used for:

[0124] If the model calculation results cannot be output after the location data of the dynamic mobile terminal device and the coordinate data of the corresponding monitoring device area are substituted into the preset dynamic air quality inspection model, the attribute information of each electrical component and sensor in the intelligent air pollution monitoring device is obtained;

[0125] According to the attribute information of each electrical component and sensor in the air pollution intelligent monitoring device, retrieve the corresponding historical data of each electrical component and sensor in the air pollution intelligent monitoring device from the preset cloud database;

[0126] The deep learning model is trained using the historical data of electrical components and sensors in the intelligent air pollution monitoring device to obtain an air pollution component screening simulation model;

[0127] Substituting the real-time collected air pollution sample data into the air pollution component screening simulation model to obtain the air pollution component screening simulation results, and comparing the air pollution component screening simulation results with the air pollution sample component characteristics. If the comparison result between the air pollution component screening simulation results and the air pollution sample component characteristics is greater than the preset error value, the sensor operating parameters are corrected;

[0128] Extracting attribute information of each electrical component and sensor from the air pollution intelligent monitoring device, the attribute information of the electrical component and sensor including model, specification, manufacturer, production date and most recent calibration date;

[0129] According to the acquired attribute information, the historical data of each electrical component and sensor in the corresponding intelligent air pollution monitoring device is retrieved from the preset cloud database, and the historical data of each electrical component and sensor includes historical usage records, historical performance and fault history;

[0130] Preprocess the retrieved historical data, and use the preprocessed historical data to train the deep learning model. After the training is completed, an atmospheric pollution component screening simulation model is obtained. The atmospheric pollution component screening simulation model is used to simulate the actual working process of the atmospheric pollution intelligent monitoring device and output the simulated atmospheric pollution component screening results;

[0131] Use intelligent air pollution monitoring devices to collect air pollution sample data in real time;

[0132] Substituting the real-time collected air pollution sample data into the air pollution component screening simulation model to obtain the air pollution component simulation results;

[0133] Compare the simulated results of atmospheric pollution components with the composition characteristics of atmospheric pollution samples collected in real time, and calculate the error value of the comparison results;

[0134] If the comparison result is greater than the preset error value, there is a deviation or fault in the sensor operating parameters;

[0135] According to the error value of the comparison result, a match is performed in a preset sensor fault knowledge base to obtain the sensor operating parameters and operating parameter adjustment values ​​that need to be corrected. The operating parameter adjustment values ​​include adjusting the sensitivity, calibration coefficient and measurement range of the sensor;

[0136] After the sensor executes the operating parameter adjustment value, it recollects the air pollution sample data and substitutes it into the air pollution component screening simulation model for verification;

[0137] If the comparison result between the simulated results of atmospheric pollution components and the characteristic scores of the atmospheric pollution sample components collected in real time is within the preset error range, the correction process is completed.

[0138] The specific implementation and technical details of the processing steps of the dynamic monitoring unit when it is unable to output the model calculation results are as follows:

[0139] Obtain attribute information. When the dynamic monitoring unit cannot output the model calculation results, it will first obtain the attribute information of each electrical component and sensor in the intelligent air pollution monitoring device. The attribute information includes model, specification, manufacturer, production date and the most recent calibration date.

[0140] Retrieving historical data, based on the acquired property information of electrical components and sensors, the dynamic monitoring unit will retrieve the historical data of each electrical component and sensor in the corresponding intelligent atmospheric pollution monitoring device from the preset cloud database. These data include historical usage records, historical performance, and fault history, etc.

[0141] Data preprocessing: preprocess the historical data retrieved from the cloud database to ensure that the quality and format of the data meet the needs of subsequent analysis.

[0142] Model training: Use preprocessed historical data to train the deep learning model to obtain an air pollution component screening simulation model. This model is used to simulate the actual working process of the air pollution intelligent monitoring device and output simulated air pollution component screening results.

[0143] Real-time data collection, use the intelligent air pollution monitoring device to collect air pollution sample data in real time.

[0144] Comparison of simulation results: Substitute the real-time collected air pollution sample data into the air pollution component screening simulation model to obtain the air pollution component simulation results. Then compare this simulation result with the real-time collected air pollution sample component characteristics, and calculate the error value of the comparison result.

[0145] Parameter correction: If the comparison result is greater than the preset error value, it means that the sensor operating parameters are deviated or faulty. At this time, the dynamic monitoring unit will match the preset sensor fault knowledge base according to the error value of the comparison result to obtain the sensor operating parameters that need to be corrected and the operating parameter adjustment values ​​(such as adjusting the sensor sensitivity, calibration coefficient and measurement range).

[0146] Verification correction: After the sensor executes the operating parameter adjustment value, the dynamic monitoring unit will re-collect the air pollution sample data and substitute it into the air pollution component screening simulation model for verification. If the comparison result of the air pollution component simulation result and the real-time collected air pollution sample component characteristics is within the preset error range, the correction process is completed.

[0147] These steps together form a closed-loop feedback mechanism to ensure that when the model calculation results cannot be output, the system can automatically detect and correct potential problems, thereby maintaining the accuracy and reliability of monitoring.

[0148] Specifically, in the air pollution intelligent monitoring and early warning system of the present invention, the dynamic monitoring unit is also used for:

[0149] Obtain the characteristics of air pollution components, and compare the obtained comparison results of air pollution components with the preset error range. If the comparison results still exceed the preset error range, enter the next step of optimization process;

[0150] According to the deviation of the comparison results of the characteristics of atmospheric pollution components, the preset atmospheric pollution monitoring and diagnosis knowledge base is optimized using the machine learning algorithm, and the atmospheric pollution monitoring and diagnosis knowledge base after optimization is used to match the results of the atmospheric pollution component clustering analysis again. When the comparison results of the characteristics of atmospheric pollution components meet the preset error range, or the number of optimizations of the preset atmospheric pollution monitoring and diagnosis knowledge base reaches the preset maximum number of iterations, the final atmospheric pollution monitoring and diagnosis results and the status of the currently used atmospheric pollution monitoring and diagnosis knowledge base are output.

[0151] The specific implementation and technical details of the dynamic monitoring unit's processing steps after obtaining and comparing the characteristics of atmospheric pollution components are as follows:

[0152] Compare the characteristics of air pollution components, and compare the obtained comparison results of air pollution components with the preset error range. If the comparison result exceeds the preset error range, enter the next step of the optimization process.

[0153] Optimize the air pollution monitoring and diagnosis knowledge base. According to the deviation of the comparison results of air pollution component characteristics, use machine learning algorithms to optimize the preset air pollution detection and diagnosis knowledge base. Use the optimized air pollution monitoring and diagnosis knowledge base to re-match the results of air pollution component cluster analysis.

[0154] When the comparison result of the characteristics of atmospheric pollution components meets the preset error range, or the number of optimizations of the preset atmospheric pollution monitoring and diagnosis knowledge base reaches the preset maximum number of iterations, the final atmospheric pollution monitoring and diagnosis result and the status of the currently used atmospheric pollution monitoring and diagnosis knowledge base are output.

[0155] Generate the analysis results of atmospheric pollution components. If the comparison results of atmospheric pollution components are within the preset error range, the analysis results of atmospheric pollution components are generated. Establish a corresponding relationship between the monitored area and the analysis results of atmospheric pollution components, and obtain the analysis results of atmospheric pollution components in the monitored area.

[0156] Match the monitored area grouping information, match the monitored area in the preset monitored area, obtain the monitored area grouping information, and detect the personnel information authorized to see the atmospheric pollution monitoring and analysis results in the monitored area grouping information.

[0157] Retrieve visible air pollution monitoring and analysis results, retrieve air pollution component analysis results corresponding to the information of personnel who authorized visible air pollution monitoring and analysis results, and obtain visible air pollution monitoring and analysis result data set.

[0158] Cluster analysis is performed on the visible air pollution monitoring and analysis results. The visible air pollution monitoring and analysis result data set is clustered to obtain the visible air pollution monitoring and analysis cluster analysis results.

[0159] Transmit visual information, convert the visible air pollution monitoring and analysis cluster analysis results and air pollution component analysis results into visual information through a preset digital animation model, and transmit the visual information to a display device.

[0160] Specifically, in the air pollution intelligent monitoring and early warning system of the present invention, the dynamic monitoring unit is also used for:

[0161] If the comparison result of the characteristics of the air pollution components is within the preset error range, the analysis result of the air pollution components is generated;

[0162] Establish a corresponding relationship between the monitored area and the analysis results of air pollution components to obtain the analysis results of air pollution components in the monitored area;

[0163] Matching the monitored area in the preset monitored areas to obtain the grouping information of the monitored areas, and detecting the information of the personnel authorized to see the atmospheric pollution monitoring and analysis results in the grouping information of the monitored areas;

[0164] Retrieve the air pollution component analysis results corresponding to the information of the person who authorized the visible air pollution monitoring and analysis results, obtain the visible air pollution monitoring and analysis result data set, perform cluster analysis on the visible air pollution monitoring and analysis result data set, and obtain the visible air pollution monitoring and analysis cluster analysis results;

[0165] The visible air pollution monitoring and analysis cluster analysis results and air pollution component analysis results are converted into visual information through a preset digital animation model and transmitted to the display device.

[0166] The specific implementation and technical details of the processing steps of the dynamic monitoring unit after generating the atmospheric pollution component analysis results are as follows:

[0167] Generate analysis results of air pollution components: The dynamic monitoring unit generates analysis results of air pollution components within a preset error range based on the comparison results of the characteristics of air pollution components.

[0168] A corresponding relationship is established between the monitored area and the analysis results of the atmospheric pollution components to obtain the analysis results of the atmospheric pollution components in the monitored area.

[0169] Matching the monitored area, matching the monitored area in the preset monitored area, and obtaining the grouping information of the monitored area.

[0170] The detection authorization can see the personnel information, and the detection monitored area grouping information can see the personnel information authorized to see the air pollution monitoring and analysis results.

[0171] Retrieve the visible analysis results, retrieve the atmospheric pollution component analysis results corresponding to the information of the personnel who authorized the visible atmospheric pollution monitoring and analysis results, and obtain the visible atmospheric pollution monitoring and analysis result data set.

[0172] Cluster analysis, performs cluster analysis on the visible air pollution monitoring and analysis result data set to obtain the visible air pollution monitoring and analysis cluster analysis results.

[0173] Convert the visible air pollution monitoring and analysis cluster analysis results and the air pollution component analysis results into visual information through a preset digital animation model.

[0174] The converted visual information is transmitted to a display device for viewing and analysis by relevant personnel.

[0175] In a second aspect, an intelligent air pollution monitoring and early warning method is applied to the intelligent air pollution monitoring and early warning system as described above, comprising:

[0176] Step S101, obtaining operation data of an intelligent air pollution monitoring device, the operation data of the intelligent air pollution monitoring device including location data of the monitoring device and operation status data of the monitoring device, the monitoring device including an air quality sensor, obtaining air quality data collected by the air quality sensor;

[0177] Step S102, substitute the monitoring device location data into the preset digital twin model to obtain the monitoring device location image data, match the monitoring device operation status data with the monitoring device location image data, and display the normally operating monitoring device in the image;

[0178] Step S103, receiving an air pollution monitoring task, extracting monitoring area features for the air pollution monitoring task, obtaining the location of the area to be monitored, substituting the location of the area to be monitored and the image data of the monitoring equipment location into a preset air quality monitorable area prediction model, and obtaining the monitorable area of ​​the real-time monitoring equipment;

[0179] Step S104, comparing the position of the monitorable area of ​​the real-time monitoring device with the position of the area to be monitored, obtaining the area without corresponding monitoring equipment, collecting the coordinate data of the area without corresponding monitoring equipment, obtaining the position data of the dynamic mobile terminal device, substituting the position data of the dynamic mobile terminal device and the coordinate data of the area without corresponding monitoring equipment into the preset dynamic air quality inspection model, generating an air quality dynamic monitoring path, the dynamic mobile terminal device executes the air quality dynamic monitoring path and collects air quality data, and the dynamic mobile terminal device includes a mobile inspection robot and a drone;

[0180] Step S105, receiving air quality data collected by the dynamic mobile terminal device, and also receiving air quality data collected by the monitoring device in the monitorable area of ​​the real-time monitoring device, removing duplicate data with the same position coordinates of the air quality data collected by the dynamic mobile terminal device and the air quality data collected by the monitoring device in the monitorable area of ​​the real-time monitoring device according to the coordinate information, to obtain air quality data to be compared, and comparing the air quality data to be compared with the preset standard air quality parameters. If there is a value in the air quality data to be compared that is greater than the preset standard air quality parameters, air quality warning information is generated.

[0181] Specifically, the air pollution intelligent monitoring and early warning method of the present invention, the step S104 includes: if the location data of the dynamic mobile terminal device and the coordinate data of the area without the corresponding monitoring device are substituted into the preset dynamic air quality inspection model, the model operation result cannot be output, then the attribute information of each electrical component and sensor in the air pollution intelligent monitoring device is obtained;

[0182] According to the attribute information of each electrical component and sensor in the air pollution intelligent monitoring device, retrieve the corresponding historical data of each electrical component and sensor in the air pollution intelligent monitoring device from the preset cloud database;

[0183] The deep learning model is trained using the historical data of electrical components and sensors in the intelligent air pollution monitoring device to obtain an air pollution component screening simulation model;

[0184] Substituting the real-time collected air pollution sample data into the air pollution component screening simulation model to obtain the air pollution component screening simulation results, and comparing the air pollution component screening simulation results with the air pollution sample component characteristics. If the comparison result between the air pollution component screening simulation results and the air pollution sample component characteristics is greater than the preset error value, the sensor operating parameters are corrected;

[0185] Extracting attribute information of each electrical component and sensor from the air pollution intelligent monitoring device, the attribute information of the electrical component and sensor including model, specification, manufacturer, production date and most recent calibration date;

[0186] According to the acquired attribute information, the historical data of each electrical component and sensor in the corresponding intelligent air pollution monitoring device is retrieved from the preset cloud database, and the historical data of each electrical component and sensor includes historical usage records, historical performance and fault history;

[0187] Preprocess the retrieved historical data, and use the preprocessed historical data to train the deep learning model. After the training is completed, an atmospheric pollution component screening simulation model is obtained. The atmospheric pollution component screening simulation model is used to simulate the actual working process of the atmospheric pollution intelligent monitoring device and output the simulated atmospheric pollution component screening results;

[0188] Use intelligent air pollution monitoring devices to collect air pollution sample data in real time;

[0189] Substituting the real-time collected air pollution sample data into the air pollution component screening simulation model to obtain the air pollution component simulation results;

[0190] Compare the simulated results of atmospheric pollution components with the composition characteristics of atmospheric pollution samples collected in real time, and calculate the error value of the comparison results;

[0191] If the comparison result is greater than the preset error value, there is a deviation or fault in the sensor operating parameters;

[0192] According to the error value of the comparison result, a match is performed in a preset sensor fault knowledge base to obtain the sensor operating parameters and operating parameter adjustment values ​​that need to be corrected. The operating parameter adjustment values ​​include adjusting the sensitivity, calibration coefficient and measurement range of the sensor;

[0193] After the sensor executes the operating parameter adjustment value, it recollects the air pollution sample data and substitutes it into the air pollution component screening simulation model for verification;

[0194] If the comparison result between the simulated results of atmospheric pollution components and the characteristic scores of the atmospheric pollution sample components collected in real time is within the preset error range, the correction process is completed.

[0195] Specifically, the air pollution intelligent monitoring and early warning method of the present invention, step S104 includes:

[0196] Obtain the characteristics of air pollution components, and compare the obtained comparison results of air pollution components with the preset error range. If the comparison results still exceed the preset error range, enter the next step of optimization process;

[0197] According to the deviation of the comparison results of the characteristics of atmospheric pollution components, the preset atmospheric pollution monitoring and diagnosis knowledge base is optimized using the machine learning algorithm, and the atmospheric pollution monitoring and diagnosis knowledge base after optimization is used to match the results of the atmospheric pollution component clustering analysis again. When the comparison results of the characteristics of atmospheric pollution components meet the preset error range, or the number of optimizations of the preset atmospheric pollution monitoring and diagnosis knowledge base reaches the preset maximum number of iterations, the final atmospheric pollution monitoring and diagnosis results and the status of the currently used atmospheric pollution monitoring and diagnosis knowledge base are output.

[0198] Specifically, the air pollution intelligent monitoring and early warning method of the present invention, step S104 includes:

[0199] If the comparison result of the characteristics of the air pollution components is within the preset error range, the analysis result of the air pollution components is generated;

[0200] Establish a corresponding relationship between the monitored area and the analysis results of air pollution components to obtain the analysis results of air pollution components in the monitored area;

[0201] Matching the monitored area in the preset monitored areas to obtain the grouping information of the monitored areas, and detecting the information of the personnel authorized to see the atmospheric pollution monitoring and analysis results in the grouping information of the monitored areas;

[0202] Retrieve the air pollution component analysis results corresponding to the information of the person who authorized the visible air pollution monitoring and analysis results, obtain the visible air pollution monitoring and analysis result data set, perform cluster analysis on the visible air pollution monitoring and analysis result data set, and obtain the visible air pollution monitoring and analysis cluster analysis results;

[0203] The visible air pollution monitoring and analysis cluster analysis results and air pollution component analysis results are converted into visual information through a preset digital animation model and transmitted to the display device.

[0204] The present invention solves the problem that the density of monitoring equipment and coverage cannot be high, resulting in limitations in the data used in existing intelligent air pollution monitoring, through the following technical solutions:

[0205] Dynamic monitoring of areas without corresponding monitoring equipment: The system compares the areas that can be monitored by real-time monitoring equipment with the locations of the areas to be monitored to determine the areas without corresponding monitoring equipment. The data of these areas are collected by dynamic mobile terminal equipment (such as mobile inspection robots and drones), filling the monitoring gaps.

[0206] The dynamic air quality inspection model generates dynamic air quality monitoring paths, and dynamic mobile terminal devices collect air quality data along these paths, increasing the flexibility and coverage of monitoring.

[0207] Monitoring equipment location image data: Substitute the monitoring equipment location data into the preset digital twin model to generate monitoring equipment location image data, thereby improving data visualization and accuracy.

[0208] Monitoring equipment operation status matching, matching monitoring equipment operation status data with location image data, and displaying normally operating monitoring equipment in the image, helps to promptly discover and handle equipment failures.

[0209] The real-time monitoring equipment can predict the monitoring area. By analyzing the location of the monitored area and the image data of the monitoring equipment, the monitoring area that the real-time monitoring equipment can cover is predicted, thereby optimizing the layout of the monitoring equipment.

[0210] Comprehensive data comparison and early warning, receiving air quality data collected by dynamic mobile terminal devices and real-time monitoring equipment, removing duplicate data, and comparing it with the preset standard air quality parameters. If excessive data is found, air quality early warning information will be generated, which improves the timeliness and accuracy of the early warning.

[0211] Deep learning and model training. During the dynamic monitoring process, if sensor data is abnormal, the sensor historical data is trained through a deep learning model to obtain an atmospheric pollution component screening simulation model, which is used to simulate the actual working process of the atmospheric pollution intelligent monitoring device. The sensor operating parameters are corrected according to the simulation results, thereby improving the reliability of the data.

[0212] Knowledge base optimization: According to the deviation of the comparison results of the characteristics of atmospheric pollution components, the preset atmospheric pollution monitoring and diagnosis knowledge base is optimized to improve the accuracy of diagnosis.

[0213] Results visualization: The results of atmospheric pollution component analysis and cluster analysis are converted into visual information through preset digital animation models and transmitted to display devices to facilitate understanding by decision makers and the public.

[0214] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations, and the above-described embodiments of the present invention do not constitute a limitation on the scope of protection of the present invention.

Claims

1. An intelligent air pollution monitoring and early warning system, characterized in that: include: Data collection module: obtains the operating data of the intelligent air pollution monitoring equipment, which includes the location data of the monitoring equipment and the operating status data of the monitoring equipment. The monitoring equipment includes an air quality sensor, and obtains the air quality data collected by the air quality sensor; The data processing module substitutes the monitoring equipment location data into the preset digital twin model to obtain the monitoring equipment location image data, matches the monitoring equipment operation status data with the monitoring equipment location image data, and displays the normally operating monitoring equipment in the image; A monitoring task receiving unit receives an air pollution monitoring task, extracts monitoring area features for the air pollution monitoring task, obtains the location of the area to be monitored, substitutes the location of the area to be monitored and the image data of the monitoring equipment location into a preset air quality monitorable area prediction model, and obtains the monitorable area of ​​the real-time monitoring equipment; The dynamic monitoring unit compares the position of the monitorable area of ​​the real-time monitoring device with the position of the area to be monitored, obtains the area without corresponding monitoring equipment, collects the coordinate data of the area without corresponding monitoring equipment, obtains the position data of the dynamic mobile terminal device, substitutes the position data of the dynamic mobile terminal device and the coordinate data of the area without corresponding monitoring equipment into the preset dynamic air quality inspection model, generates the dynamic air quality monitoring path, and the dynamic mobile terminal device executes the dynamic air quality monitoring path and collects air quality data. The dynamic mobile terminal device includes a mobile inspection robot and a drone; The air quality warning unit receives air quality data collected by dynamic mobile terminal devices and also receives air quality data collected by monitoring devices in the monitorable area of ​​the real-time monitoring device. It removes duplicate data with the same position coordinates from the air quality data collected by the dynamic mobile terminal devices and the air quality data collected by the monitoring devices in the monitorable area of ​​the real-time monitoring device according to the coordinate information to obtain air quality data to be compared. The air quality data to be compared is compared with preset standard air quality parameters. If there is a value in the air quality data to be compared that is greater than the preset standard air quality parameters, air quality warning information is generated.

2. The air pollution intelligent monitoring and early warning system according to claim 1, characterized in that: The dynamic monitoring unit is further used for: If the model calculation results cannot be output after the location data of the dynamic mobile terminal device and the coordinate data of the corresponding monitoring device area are substituted into the preset dynamic air quality inspection model, the attribute information of each electrical component and sensor in the intelligent air pollution monitoring device is obtained; According to the attribute information of each electrical component and sensor in the air pollution intelligent monitoring device, retrieve the corresponding historical data of each electrical component and sensor in the air pollution intelligent monitoring device from the preset cloud database; The deep learning model is trained using the historical data of electrical components and sensors in the intelligent air pollution monitoring device to obtain an air pollution component screening simulation model; Substituting the real-time collected air pollution sample data into the air pollution component screening simulation model to obtain the air pollution component screening simulation results, and comparing the air pollution component screening simulation results with the air pollution sample component characteristics. If the comparison result between the air pollution component screening simulation results and the air pollution sample component characteristics is greater than the preset error value, the sensor operating parameters are corrected; Extracting attribute information of each electrical component and sensor from the air pollution intelligent monitoring device, the attribute information of the electrical component and sensor including model, specification, manufacturer, production date and most recent calibration date; According to the acquired attribute information, the historical data of each electrical component and sensor in the corresponding intelligent air pollution monitoring device is retrieved from the preset cloud database, and the historical data of each electrical component and sensor includes historical usage records, historical performance and fault history; Preprocess the retrieved historical data, and use the preprocessed historical data to train the deep learning model. After the training is completed, an atmospheric pollution component screening simulation model is obtained. The atmospheric pollution component screening simulation model is used to simulate the actual working process of the atmospheric pollution intelligent monitoring device and output the simulated atmospheric pollution component screening results; Use intelligent air pollution monitoring devices to collect air pollution sample data in real time; Substituting the real-time collected air pollution sample data into the air pollution component screening simulation model to obtain the air pollution component simulation results; Compare the simulated results of atmospheric pollution components with the composition characteristics of atmospheric pollution samples collected in real time, and calculate the error value of the comparison results; If the comparison result is greater than the preset error value, there is a deviation or fault in the sensor operating parameters; According to the error value of the comparison result, a match is performed in a preset sensor fault knowledge base to obtain the sensor operating parameters and operating parameter adjustment values ​​that need to be corrected. The operating parameter adjustment values ​​include adjusting the sensitivity, calibration coefficient and measurement range of the sensor; After the sensor executes the operating parameter adjustment value, it re-collects the atmospheric pollution sample data and substitutes it into the atmospheric pollution component screening simulation model for verification; If the comparison result between the simulated results of atmospheric pollution components and the characteristic scores of the atmospheric pollution sample components collected in real time is within the preset error range, the correction process is completed.

3. The intelligent air pollution monitoring device according to claim 2, characterized in that: The dynamic monitoring unit is further used for: Obtain the characteristics of air pollution components, and compare the obtained comparison results of air pollution components with the preset error range. If the comparison results still exceed the preset error range, enter the next step of optimization process; According to the deviation of the comparison results of the characteristics of atmospheric pollution components, the preset atmospheric pollution monitoring and diagnosis knowledge base is optimized using the machine learning algorithm, and the atmospheric pollution monitoring and diagnosis knowledge base after optimization is used to match the results of the atmospheric pollution component clustering analysis again. When the comparison results of the characteristics of atmospheric pollution components meet the preset error range, or the number of optimizations of the preset atmospheric pollution monitoring and diagnosis knowledge base reaches the preset maximum number of iterations, the final atmospheric pollution monitoring and diagnosis results and the status of the currently used atmospheric pollution monitoring and diagnosis knowledge base are output.

4. The intelligent air pollution monitoring device according to claim 3, characterized in that: The dynamic monitoring unit is further used for: If the comparison result of the characteristics of the air pollution components is within the preset error range, the analysis result of the air pollution components is generated; Establish a corresponding relationship between the monitored area and the analysis results of air pollution components to obtain the analysis results of air pollution components in the monitored area; Matching the monitored area in the preset monitored areas to obtain the grouping information of the monitored areas, and detecting the information of the personnel authorized to see the atmospheric pollution monitoring and analysis results in the grouping information of the monitored areas; Retrieve the air pollution component analysis results corresponding to the information of the person who authorized the visible air pollution monitoring and analysis results, obtain the visible air pollution monitoring and analysis result data set, perform cluster analysis on the visible air pollution monitoring and analysis result data set, and obtain the visible air pollution monitoring and analysis cluster analysis results; The visible air pollution monitoring and analysis cluster analysis results and air pollution component analysis results are converted into visual information through a preset digital animation model and transmitted to the display device.

5. An intelligent monitoring and early warning method for air pollution, applied to the intelligent monitoring and early warning system for air pollution as claimed in any one of claims 1 to 4, characterized in that: include: Step S101, obtaining operation data of an intelligent air pollution monitoring device, the operation data of the intelligent air pollution monitoring device including location data of the monitoring device and operation status data of the monitoring device, the monitoring device including an air quality sensor, obtaining air quality data collected by the air quality sensor; Step S102, substitute the monitoring device location data into the preset digital twin model to obtain the monitoring device location image data, match the monitoring device operation status data with the monitoring device location image data, and display the normally operating monitoring device in the image; Step S103, receiving an air pollution monitoring task, extracting monitoring area features for the air pollution monitoring task, obtaining the location of the area to be monitored, substituting the location of the area to be monitored and the image data of the monitoring equipment location into a preset air quality monitorable area prediction model, and obtaining the monitorable area of ​​the real-time monitoring equipment; Step S104, comparing the position of the monitorable area of ​​the real-time monitoring device with the position of the area to be monitored, obtaining the area without corresponding monitoring equipment, collecting the coordinate data of the area without corresponding monitoring equipment, obtaining the position data of the dynamic mobile terminal device, substituting the position data of the dynamic mobile terminal device and the coordinate data of the area without corresponding monitoring equipment into the preset dynamic air quality inspection model, generating an air quality dynamic monitoring path, the dynamic mobile terminal device executes the air quality dynamic monitoring path and collects air quality data, and the dynamic mobile terminal device includes a mobile inspection robot and a drone; Step S105, receiving air quality data collected by the dynamic mobile terminal device, and also receiving air quality data collected by the monitoring device in the monitorable area of ​​the real-time monitoring device, removing duplicate data with the same position coordinates of the air quality data collected by the dynamic mobile terminal device and the air quality data collected by the monitoring device in the monitorable area of ​​the real-time monitoring device according to the coordinate information, to obtain air quality data to be compared, and comparing the air quality data to be compared with the preset standard air quality parameters. If there is a value in the air quality data to be compared that is greater than the preset standard air quality parameters, air quality warning information is generated.

6. The intelligent air pollution monitoring method according to claim 5, characterized in that: The step S104 includes: if the model operation result cannot be output after the location data of the dynamic mobile terminal device and the coordinate data of the corresponding monitoring device area are substituted into the preset dynamic air quality inspection model, then the attribute information of each electrical component and sensor in the air pollution intelligent monitoring device is obtained; According to the attribute information of each electrical component and sensor in the air pollution intelligent monitoring device, retrieve the corresponding historical data of each electrical component and sensor in the air pollution intelligent monitoring device from the preset cloud database; The deep learning model is trained using the historical data of electrical components and sensors in the intelligent air pollution monitoring device to obtain an air pollution component screening simulation model; Substituting the real-time collected air pollution sample data into the air pollution component screening simulation model to obtain the air pollution component screening simulation results, and comparing the air pollution component screening simulation results with the air pollution sample component characteristics. If the comparison result between the air pollution component screening simulation results and the air pollution sample component characteristics is greater than the preset error value, the sensor operating parameters are corrected; Extracting attribute information of each electrical component and sensor from the air pollution intelligent monitoring device, the attribute information of the electrical component and sensor including model, specification, manufacturer, production date and most recent calibration date; According to the acquired attribute information, the historical data of each electrical component and sensor in the corresponding intelligent air pollution monitoring device is retrieved from the preset cloud database, and the historical data of each electrical component and sensor includes historical usage records, historical performance and fault history; Preprocess the retrieved historical data, and use the preprocessed historical data to train the deep learning model. After the training is completed, an atmospheric pollution component screening simulation model is obtained. The atmospheric pollution component screening simulation model is used to simulate the actual working process of the atmospheric pollution intelligent monitoring device and output the simulated atmospheric pollution component screening results; Use intelligent air pollution monitoring devices to collect air pollution sample data in real time; Substituting the real-time collected air pollution sample data into the air pollution component screening simulation model to obtain the air pollution component simulation results; Compare the simulated results of atmospheric pollution components with the composition characteristics of atmospheric pollution samples collected in real time, and calculate the error value of the comparison results; If the comparison result is greater than the preset error value, there is a deviation or fault in the sensor operating parameters; According to the error value of the comparison result, a match is performed in a preset sensor fault knowledge base to obtain the sensor operating parameters and operating parameter adjustment values ​​that need to be corrected. The operating parameter adjustment values ​​include adjusting the sensitivity, calibration coefficient and measurement range of the sensor; After the sensor executes the operating parameter adjustment value, it re-collects the atmospheric pollution sample data and substitutes it into the atmospheric pollution component screening simulation model for verification; If the comparison result between the simulated results of atmospheric pollution components and the characteristic scores of the atmospheric pollution sample components collected in real time is within the preset error range, the correction process is completed.

7. The intelligent air pollution monitoring method according to claim 6, characterized in that: The step S104 includes: Obtain the characteristics of air pollution components, and compare the obtained comparison results of air pollution components with the preset error range. If the comparison results still exceed the preset error range, enter the next step of optimization process; According to the deviation of the comparison results of the characteristics of atmospheric pollution components, the preset atmospheric pollution monitoring and diagnosis knowledge base is optimized using the machine learning algorithm, and the atmospheric pollution monitoring and diagnosis knowledge base after optimization is used to match the results of the atmospheric pollution component clustering analysis again. When the comparison results of the characteristics of atmospheric pollution components meet the preset error range, or the number of optimizations of the preset atmospheric pollution monitoring and diagnosis knowledge base reaches the preset maximum number of iterations, the final atmospheric pollution monitoring and diagnosis results and the status of the currently used atmospheric pollution monitoring and diagnosis knowledge base are output.

8. The intelligent air pollution monitoring method according to claim 7, characterized in that: The step S104 includes: If the comparison result of the characteristics of the air pollution components is within the preset error range, the analysis result of the air pollution components is generated; Establish a corresponding relationship between the monitored area and the analysis results of air pollution components to obtain the analysis results of air pollution components in the monitored area; Matching the monitored area in the preset monitored areas to obtain the grouping information of the monitored areas, and detecting the information of the personnel authorized to see the atmospheric pollution monitoring and analysis results in the grouping information of the monitored areas; Retrieve the air pollution component analysis results corresponding to the information of the person who authorized the visible air pollution monitoring and analysis results, obtain the visible air pollution monitoring and analysis result data set, perform cluster analysis on the visible air pollution monitoring and analysis result data set, and obtain the visible air pollution monitoring and analysis cluster analysis results; The visible air pollution monitoring and analysis cluster analysis results and air pollution component analysis results are converted into visual information through a preset digital animation model and transmitted to the display device.

Images