Atmospheric pollution real-time monitoring and early warning system based on big data

Abstract

The invention relates to the technical field of environmental monitoring, and discloses an atmospheric pollution real-time monitoring and early warning system based on big data. Comprising a data acquisition module, a data transmission module, a data storage module, a data processing and analysis module, an early warning and publishing module, a visualization module, a multi-level fault detection and recovery module, a complex pollution event real-time response module, a high-density data acquisition optimization module and a user feedback module. The data acquisition module is used for acquiring air quality data through various sensors and monitoring equipment; the data transmission module is used for transmitting the air quality data acquired by the data acquisition module to the data storage module in real time; and the data storage module is used for storing the transmitted data. Through periodic self-inspection and real-time monitoring, faults of a sensor, data transmission and a data center are rapidly identified, and continuity and reliability of data acquisition are ensured, so that availability and stability of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring, and in particular to a real-time monitoring and early warning system for air pollution based on big data. Background Art

[0002] In the process of modern urbanization, the problem of air pollution is becoming increasingly serious, directly affecting people's health and quality of life. With the acceleration of industrialization, the continuous increase in the number of motor vehicles and the frequent activities such as construction, the air quality in cities has continued to deteriorate, resulting in a significant increase in the concentration of pollutants such as PM2.5, PM10, NO2, SO2 and O3. The excessive emissions of these pollutants not only damage the ecological environment, but also pose a major threat to the respiratory system, cardiovascular health and overall quality of life of residents. According to a report by the World Health Organization, air pollution causes millions of premature deaths every year, especially in large cities. The decline in air quality is closely related to health problems such as chronic respiratory diseases, cardiovascular diseases and cancer. This has led to increasing attention from governments and the public to air quality. Therefore, establishing an effective real-time monitoring and early warning system has become an urgent need. However, the existing air quality monitoring system faces many challenges in practical applications.

[0003] First, existing air quality monitoring systems often lack effective fault detection and recovery mechanisms. When sensor nodes or data transmission fail, the system may not be able to identify them in time, resulting in data collection interruptions or errors. This not only affects the continuity of monitoring data, but may also cause serious data loss, affecting the overall reliability and stability of the system.

[0004] Secondly, the current monitoring system has insufficient response capabilities when facing complex sudden pollution incidents. Traditional systems can usually only conduct regular monitoring and cannot detect abnormal changes in sudden incidents in a timely manner, resulting in a slow response to pollution incidents and failure to issue early warning information to the public in the first place. This situation increases the health risks to the public, and the lack of timely information transmission makes it difficult to quickly implement emergency response measures.

[0005] Finally, in high-density urban areas, densely distributed sensors often lead to signal interference and repeated data collection, affecting the accuracy and credibility of the data. In addition, the existing system fails to effectively optimize the layout of sensors, resulting in insufficient data monitoring in some areas and an inability to fully reflect the air quality status. This inaccurate data problem makes it difficult for decision makers to rely on monitoring results to formulate relevant environmental policies and health guidance.

[0006] In summary, air quality monitoring systems have many problems in data collection, fault detection, and complex event response. Innovative technical solutions are urgently needed to improve the performance and reliability of the system to meet the growing needs of air quality monitoring. Summary of the invention

[0007] In view of the deficiencies in the prior art, the present invention provides a real-time monitoring and early warning system for air pollution based on big data, which solves the problem that the system cannot identify faults in a timely manner.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a real-time monitoring and early warning system for air pollution based on big data, including a data acquisition module, a data transmission module, a data storage module, a data processing and analysis module, an early warning and release module, a visualization module, a multi-level fault detection and recovery module, a real-time response module for complex pollution events, a high-density data acquisition optimization module and a user feedback module;

[0009] The data acquisition module is used to collect air quality data through various sensors and monitoring equipment;

[0010] The data transmission module is used to transmit the air quality data collected by the data collection module to the data storage module in real time;

[0011] The data storage module is used to store the transmitted data;

[0012] The data processing and analysis module is used to clean, analyze and mine the stored data;

[0013] The warning and release module is used to generate and release warning information;

[0014] The visualization module is used to display air quality data and warning information;

[0015] The multi-level fault detection and recovery module is used to implement rapid fault detection, recovery and switching from sensor nodes to data centers;

[0016] The complex pollution event real-time response module is used to realize real-time detection, analysis and response to complex sudden pollution events;

[0017] The high-density data acquisition optimization module is used to avoid interference between sensors and repeated data acquisition in high-density areas;

[0018] The user feedback module collects user feedback information through mobile applications and web page platforms.

[0019] Preferably, the data acquisition module includes a sensor unit and a mobile monitoring device unit;

[0020] The sensor unit is used to monitor the concentration of pollutants in the air in real time, including but not limited to PM2.5, PM10, NO2, SO2 and O3;

[0021] The mobile monitoring device unit collects air quality data through a mobile device.

[0022] Preferably, the data processing and analysis module includes a data cleaning unit, a data analysis unit and a machine learning unit;

[0023] The data cleaning unit is used to clean, remove duplicates and standardize the original data;

[0024] The data analysis unit is used to perform statistical analysis, trend analysis and model prediction on the stored data;

[0025] The machine learning unit uses machine learning algorithms to perform pollution source identification, trend prediction, and anomaly detection;

[0026] The learning algorithm comprises the following steps:

[0027] S1. Data preprocessing: normalize the original data;

[0028] S2. Feature selection: Use random forest-based feature importance evaluation to select important features;

[0029] S3, model selection: Support vector machine (SVM) is used as the model;

[0030] S4. Model training: Use cross-validation to optimize hyperparameters:

[0031] S41, dividing the data set into k subsets;

[0032] S42, training and validating the model for each subset;

[0033] S43, select the best hyperparameter combination;

[0034] In the step S1, the normalization formula is:

[0035]

[0036] Among them, X′ is the normalized data, X is the original data, μ is the mean, and σ is the standard deviation;

[0037] The algorithm formula of the vector machine in step S3 is:

[0038] f(x)=w·φ(x)+b

[0039] Among them, w is the weight vector, φ(x) is the feature mapping function, and b is the bias;

[0040] In the step S4, the model training step is specifically as follows:

[0041] S41, dividing the data set into k subsets;

[0042] S42, training and validating the model for each subset;

[0043] S43. Select the best hyperparameter combination.

[0044] Preferably, the warning and release module includes a warning algorithm unit and a warning release unit;

[0045] The warning algorithm unit is used to generate warning information according to the analysis results and determine the warning threshold;

[0046] The warning issuing unit issues warning information via SMS, email, or APP push.

[0047] Preferably, the visualization module includes a dashboard unit and a map display unit;

[0048] The instrument panel unit is used to display air quality data and warning information in real time;

[0049] The map display unit is used to mark the real-time air quality data of the monitoring points on the map.

[0050] Preferably, the multi-level fault detection and recovery module includes a sensor node fault detection unit, a data transmission fault detection unit and a data center fault detection unit;

[0051] The sensor node fault detection unit is used to monitor the working state of the sensor and detect the fault condition of the sensor, and the monitoring includes periodic self-checking and real-time state monitoring;

[0052] The data transmission fault detection unit is used to monitor abnormal conditions during data transmission, such as delay or packet loss, and the monitoring includes but is not limited to the sequence number and timestamp of the data packet;

[0053] The data center fault detection unit is used to monitor the operating status of the data center storage and processing equipment and perform fault detection.

[0054] Preferably, the complex pollution event real-time response module includes an event detection unit, an event analysis unit and an emergency response unit;

[0055] The event detection unit is used to monitor abnormal changes in data in real time and detect sudden pollution events;

[0056] The event analysis unit is used to analyze the detected abnormal changes and determine the nature and scope of the pollution event;

[0057] The emergency response unit is used to generate and publish emergency warning information according to the event analysis results.

[0058] Preferably, the high-density data acquisition optimization module includes a sensor layout optimization unit, a data fusion unit and an interference elimination unit;

[0059] The sensor layout optimization unit is used to analyze and optimize the layout of sensors in high-density areas;

[0060] The data fusion unit is used to fuse data from different sensors to avoid repeated data collection;

[0061] The interference elimination unit is used to detect and eliminate signal interference between sensors.

[0062] Preferably, the user feedback module includes a user satisfaction survey unit and a user suggestion adoption unit;

[0063] The user satisfaction survey unit is used to collect user feedback on system usage;

[0064] The user suggestion adopting unit is used to collect and analyze the suggestions put forward by the users.

[0065] Preferably, the data transmission module transmits data using wireless technology, and the wireless technology includes but is not limited to 5G, Wi-Fi and LoRa.

[0066] The present invention provides a real-time monitoring and early warning system for air pollution based on big data.

[0067] Beneficial effects:

[0068] 1. The present invention can quickly identify faults in sensors, data transmission and data centers through a multi-level fault detection and recovery mechanism, combined with periodic self-test and real-time monitoring. This mechanism ensures the continuity and reliability of data collection, avoids data loss due to equipment failure, improves the availability and stability of the system, and thus provides users with stable and reliable air quality data.

[0069] 2. Through intelligent monitoring and analysis capabilities, the present invention can monitor abnormal changes in air quality data in real time and quickly identify sudden pollution events. Through in-depth analysis of abnormal situations, the module generates timely emergency warning information to ensure that relevant departments and the public can quickly obtain information and take appropriate measures to effectively reduce the potential threat of sudden pollution events to public health.

[0070] 3. The present invention uses a sensor layout optimization unit to analyze sensor positions through intelligent algorithms to minimize interference; a data fusion unit effectively integrates data from different sensors to avoid data redundancy; an interference elimination unit further improves the accuracy and reliability of data collection. The comprehensive application of these technologies significantly improves the performance of the system in complex environments, ensuring that users obtain high-quality monitoring data. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 It is a system module diagram of the present invention;

[0072] Figure 2 It is a schematic diagram of a data acquisition module of the present invention;

[0073] Figure 3 It is a schematic diagram of the data processing and analysis module of the present invention;

[0074] Figure 4 It is a schematic diagram of the early warning and release module of the present invention;

[0075] Figure 5 It is a schematic diagram of a visualization module of the present invention;

[0076] Figure 6 A schematic diagram of a multi-level fault detection and recovery module of the present invention;

[0077] Figure 7 This is a schematic diagram of a real-time response module for complex pollution events of the present invention;

[0078] Figure 8 It is a schematic diagram of a high-density data acquisition optimization module of the present invention;

[0079] Fig. 9 Schematic diagram of a user feedback module of the present invention. DETAILED DESCRIPTION

[0080] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. 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.

[0081] Example:

[0082] Please see attached Figure 1, an embodiment of the present invention provides a real-time monitoring and early warning system for air pollution based on big data, including a data acquisition module, a data transmission module, a data storage module, a data processing and analysis module, an early warning and release module, a visualization module, a multi-level fault detection and recovery module, a complex pollution event real-time response module, a high-density data acquisition optimization module and a user feedback module;

[0083] The data acquisition module is used to collect air quality data through various sensors and monitoring devices;

[0084] The data transmission module is used to transmit the air quality data collected by the data acquisition module to the data storage module in real time;

[0085] The data storage module is used to store the transmitted data;

[0086] The data processing and analysis module is used to clean, analyze and mine the stored data;

[0087] The early warning and release module is used to generate and release early warning information;

[0088] The visualization module is used to display air quality data and warning information;

[0089] The multi-level fault detection and recovery module is used to achieve fast fault detection, recovery and switching from sensor nodes to data centers;

[0090] The complex pollution incident real-time response module is used to realize the real-time detection, analysis and response to complex sudden pollution incidents;

[0091] The high-density data acquisition optimization module is used to avoid interference between sensors and repeated data acquisition in high-density areas;

[0092] The user feedback module collects user feedback information through mobile applications and web platforms.

[0093] Specifically, the system first uses the data acquisition module to collect air quality data in real time through a variety of sensors and monitoring equipment, including the concentrations of pollutants such as PM2.5, PM10, NO2, SO2 and O3; these data are quickly transmitted to the data storage module through the data transmission module for centralized storage to ensure the integrity and security of the data; then, the data processing and analysis module cleans, removes duplications and standardizes the stored data, uses statistical analysis and machine learning algorithms to conduct in-depth data mining, identifies pollution sources, predicts pollution trends, and generates corresponding analysis reports; based on the processing results, the early warning and release module generates and releases early warning information, and conveys real-time early warning information to the public and relevant departments through various means such as SMS, email and APP push, so that corresponding response measures can be taken; the visualization module presents air quality data and early warning information in an intuitive way, provides dashboards and map displays, and enables users to quickly understand Understand the current air quality status; in addition, the multi-level fault detection and recovery module ensures the high availability of the system. By monitoring the working status of sensor nodes, data transmission and data centers, it can quickly identify and recover faults and maintain the continuity of data collection and transmission. In response to sudden pollution events, the complex pollution event real-time response module has the ability of real-time detection, analysis and emergency response. It can promptly identify abnormal data changes and generate and release emergency warning information based on the event analysis results. In order to improve the system's working efficiency in high-density areas, the high-density data acquisition optimization module avoids interference between sensors and repeated data collection by optimizing sensor layout, data fusion and interference elimination technology. Finally, the user feedback module collects user feedback information through mobile applications and web platforms to help the system continuously optimize and improve, ensuring that the system can adapt to changing environmental needs, thereby achieving comprehensive monitoring and scientific management of air pollution.

[0094] Please see attached Figure 2 -Attached Figure 5 ,The data acquisition module includes a sensor unit and a mobile monitoring device unit;

[0095] The sensor unit is used to monitor the concentration of pollutants in the air in real time, including but not limited to PM2.5, PM10, NO2, SO2 and O3;

[0096] The mobile monitoring device unit collects air quality data through mobile devices;

[0097] The data processing and analysis module includes a data cleaning unit, a data analysis unit, and a machine learning unit;

[0098] The data cleaning unit is used to clean, remove duplicates and standardize the original data;

[0099] The data analysis unit is used to perform statistical analysis, trend analysis and model prediction on the stored data;

[0100] The machine learning unit uses machine learning algorithms for pollution source identification, trend prediction, and anomaly detection;

[0101] The learning algorithm consists of the following steps:

[0102] S1. Data preprocessing: normalize the original data;

[0103] S2. Feature selection: Use random forest-based feature importance evaluation to select important features;

[0104] S3, model selection: Support vector machine (SVM) is used as the model;

[0105] S4. Model training: Use cross-validation to optimize hyperparameters:

[0106] S41, dividing the data set into k subsets;

[0107] S42, training and validating the model for each subset;

[0108] S43, select the best hyperparameter combination;

[0109] In step S1, the normalization formula is:

[0110]

[0111] Among them, X′ is the normalized data, X is the original data, μ is the mean, and σ is the standard deviation;

[0112] The algorithm formula of the vector machine in step S3 is:

[0113] f(x)=w·φ(x)+b

[0114] Among them, w is the weight vector, φ(x) is the feature mapping function, and b is the bias;

[0115] In step S4, the model training steps are as follows:

[0116] S41, dividing the data set into k subsets;

[0117] S42, training and validating the model for each subset;

[0118] S43, select the best hyperparameter combination;

[0119] The early warning and release module includes an early warning algorithm unit and an early warning release unit;

[0120] The early warning algorithm unit is used to generate early warning information based on the analysis results and determine the early warning threshold;

[0121] The warning release unit releases warning information via SMS, email, and APP push;

[0122] The visualization module includes a dashboard unit and a map display unit;

[0123] The instrument panel unit is used to display air quality data and warning information in real time;

[0124] The map display unit is used to mark the real-time air quality data of the monitoring points on the map;

[0125] Please see attached Fig. 9 ,The user feedback module includes the user satisfaction survey unit and the user ,suggestion adoption unit;

[0126] The user satisfaction survey unit is used to collect user feedback on the use of the system;

[0127] The user suggestion adoption unit is used to collect and analyze the suggestions put forward by users;

[0128] The data transmission module transmits data using wireless technology, which includes but is not limited to 5G, Wi-Fi and LoRa.

[0129] Specifically, data collection starts with the sensor unit, which continuously monitors the concentration of pollutants in the air, including PM2.5, PM10, NO2, SO2 and O3, and transmits these real-time data to the data processing and analysis unit; at the same time, the mobile monitoring device unit flexibly collects air quality data through smart mobile devices to supplement the monitoring blind spots of fixed sensors; the data processing and analysis unit first cleans the original data, removes redundant and erroneous information, and performs standardization to ensure data quality; then, statistical analysis and trend analysis are used to deeply explore the potential information in the data. At the same time, the machine learning unit identifies pollution sources and detects anomalies through a series of steps; specifically, in the data preprocessing stage, the original data is standardized through a normalization formula to make it suitable for subsequent machine learning algorithms. This process helps to improve the training effect of the model; in the feature selection stage, feature importance evaluation based on random forests is used to select the features that have the greatest impact on prediction to ensure the accuracy of the model; in the model In terms of selection, support vector machine (SVM) was adopted to improve the classification ability by optimizing the feature mapping function and combining weight vectors and biases. In the model training stage, cross-validation method was used to optimize hyperparameters. The data set was divided into k subsets for training and verification, and finally the best hyperparameter combination was selected to ensure the generalization ability of the model. After the analysis results were generated, the early warning algorithm unit determined the early warning threshold based on these data and generated early warning information, which was quickly released to relevant users and departments through SMS, email, APP push and other methods so that timely response measures could be taken. The visualization module displays air quality data and early warning information in the form of dashboards and maps, so that users can intuitively view the real-time air quality status of each monitoring point. At the same time, the user feedback module is responsible for collecting user satisfaction and suggestions on the system. The user satisfaction survey unit will summarize the feedback information, and the user suggestion adoption unit will analyze these suggestions to optimize system functions and user experience. The data transmission module adopts advanced wireless technologies, including 5G, Wi-Fi and LoRa, to ensure efficient transmission of data during collection, processing and release, so that the entire system can work in real time and efficiently, and ultimately achieve scientific monitoring and management of air pollution.

[0130] Please see attached Figure 6 -Attached Figure 8 ,The multi-level fault detection and recovery module includes a sensor node fault detection unit, a data transmission fault detection unit, and a data center fault detection unit;

[0131] The sensor node fault detection unit is used to monitor the working status of the sensor and detect the fault condition of the sensor. The monitoring includes periodic self-test and real-time status monitoring;

[0132] The data transmission fault detection unit is used to monitor abnormal conditions during data transmission, such as delay or packet loss, and the monitoring includes but is not limited to the sequence number and time stamp of the data packet;

[0133] The data center fault detection unit is used to monitor the operating status of the data center storage and processing equipment and perform fault detection;

[0134] The real-time response module for complex pollution events includes an event detection unit, an event analysis unit, and an emergency response unit;

[0135] The event detection unit is used to monitor abnormal changes in data in real time and detect sudden pollution events;

[0136] The event analysis unit is used to analyze the detected abnormal changes and determine the nature and scope of the pollution incident;

[0137] The emergency response unit is used to generate and release emergency warning information based on the event analysis results;

[0138] The high-density data acquisition optimization module includes a sensor layout optimization unit, a data fusion unit, and an interference elimination unit;

[0139] The sensor layout optimization unit is used to analyze and optimize the layout of sensors in high-density areas;

[0140] The data fusion unit is used to fuse data from different sensors to avoid repeated data collection;

[0141] The interference cancellation unit is used to detect and cancel signal interference between sensors.

[0142] Specifically, in the multi-level fault detection and recovery module, the sensor node fault detection unit is responsible for regularly performing self-inspections on each sensor and monitoring its working status in real time to ensure that each sensor is within the normal working range; once a fault is detected, the system will immediately trigger an alarm and start the backup sensor to ensure the continuity of data collection; at the same time, the data transmission fault detection unit monitors abnormal conditions in the data transmission process, including delays or packet loss, and confirms the integrity of data transmission by recording the sequence number and timestamp of the data packet, and quickly adjusts the data transmission strategy or switches to the backup transmission channel when a problem is detected; the data center fault detection unit monitors the status of storage and processing equipment in real time to ensure that the system can respond to faults quickly and perform necessary recovery operations, thereby reducing system downtime; for real-time response to complex pollution events, the event detection unit monitors abnormal changes in air quality data, can quickly identify sudden pollution events, and The data is transmitted to the event analysis unit for in-depth analysis to determine the nature and scope of the pollution event; based on the event analysis results, the emergency response unit can quickly generate and issue emergency warning information to ensure that relevant personnel can obtain information in a timely manner and take corresponding response measures; in the high-density data acquisition optimization module, the sensor layout optimization unit is responsible for analyzing and optimizing the sensor layout in high-density areas, determining the optimal layout through intelligent algorithms, and reducing interference between sensors; at the same time, the data fusion unit fuses data from different sensors to ensure data consistency, avoid repeated collection, and improve data accuracy; the interference elimination unit monitors signal interference between sensors and takes corresponding measures to eliminate it, further improving data quality and reliability; through the close collaboration of these units, this system can not only achieve efficient and accurate air quality monitoring, but also maintain the stability and reliability of the system under various faults and complex environments.

[0143] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A real-time monitoring and early warning system for air pollution based on big data, It is characterized in that It includes data acquisition module, data transmission module, data storage module, data processing and analysis module, early warning and release module, visualization module, multi-level fault detection and recovery module, real-time response module for complex pollution events, high-density data acquisition optimization module and user feedback module; The data acquisition module is used to collect air quality data through various sensors and monitoring equipment; The data transmission module is used to transmit the air quality data collected by the data collection module to the data storage module in real time; The data storage module is used to store the transmitted data; The data processing and analysis module is used to clean, analyze and mine the stored data; The warning and release module is used to generate and release warning information; The visualization module is used to display air quality data and warning information; The multi-level fault detection and recovery module is used to implement rapid fault detection, recovery and switching from sensor nodes to data centers; The complex pollution event real-time response module is used to realize real-time detection, analysis and response to complex sudden pollution events; The high-density data acquisition optimization module is used to avoid interference between sensors and repeated data acquisition in high-density areas; The user feedback module collects user feedback information through mobile applications and web page platforms.

2. According to the big data-based real-time air pollution monitoring and early warning system of claim 1, It is characterized in that The data acquisition module includes a sensor unit and a mobile monitoring device unit; The sensor unit is used to monitor the concentration of pollutants in the air in real time, including but not limited to PM2.5, PM10, NO2, SO2 and O3; The mobile monitoring device unit collects air quality data through a mobile device.

3. According to the big data-based real-time air pollution monitoring and early warning system of claim 1, It is characterized in that The data processing and analysis module includes a data cleaning unit, a data analysis unit and a machine learning unit; The data cleaning unit is used to clean, remove duplicates and standardize the original data; The data analysis unit is used to perform statistical analysis, trend analysis and model prediction on the stored data; The machine learning unit uses machine learning algorithms to perform pollution source identification, trend prediction, and anomaly detection; The learning algorithm comprises the following steps: S1. Data preprocessing: normalize the original data; S2. Feature selection: Use random forest-based feature importance evaluation to select important features; S3, model selection: Support vector machine (SVM) is used as the model; S4. Model training: Use cross-validation to optimize hyperparameters: S41, dividing the data set into k subsets; S42, training and validating the model for each subset; S43, select the best hyperparameter combination; In the step S1, the normalization formula is: Among them, X′ is the normalized data, X is the original data, μ is the mean, and σ is the standard deviation; The algorithm formula of the vector machine in step S3 is: f(x)=w·φ(x)+b Among them, w is the weight vector, φ(x) is the feature mapping function, and b is the bias; In the step S4, the model training step is specifically as follows: S41, dividing the data set into k subsets; S42, training and validating the model for each subset; S43. Select the best hyperparameter combination.

4. According to the big data-based real-time air pollution monitoring and early warning system of claim 1, It is characterized in that The warning and release module includes a warning algorithm unit and a warning release unit; The warning algorithm unit is used to generate warning information according to the analysis results and determine the warning threshold; The warning issuing unit issues warning information via SMS, email, or APP push.

5. According to the big data-based real-time air pollution monitoring and early warning system of claim 1, It is characterized in that The visualization module includes a dashboard unit and a map display unit; The instrument panel unit is used to display air quality data and warning information in real time; The map display unit is used to mark the real-time air quality data of the monitoring points on the map.

6. According to claim 1, a real-time monitoring and early warning system for air pollution based on big data, It is characterized in that The multi-level fault detection and recovery module includes a sensor node fault detection unit, a data transmission fault detection unit and a data center fault detection unit; The sensor node fault detection unit is used to monitor the working state of the sensor and detect the fault condition of the sensor, and the monitoring includes periodic self-checking and real-time state monitoring; The data transmission fault detection unit is used to monitor abnormal conditions during data transmission, such as delay or packet loss, and the monitoring includes but is not limited to the sequence number and timestamp of the data packet; The data center fault detection unit is used to monitor the operating status of the data center storage and processing equipment and perform fault detection.

7. According to claim 1, a real-time monitoring and early warning system for air pollution based on big data, It is characterized in that The complex pollution event real-time response module includes an event detection unit, an event analysis unit and an emergency response unit; The event detection unit is used to monitor abnormal changes in data in real time and detect sudden pollution events; The event analysis unit is used to analyze the detected abnormal changes and determine the nature and scope of the pollution event; The emergency response unit is used to generate and publish emergency warning information according to the event analysis results.

8. According to claim 1, a real-time monitoring and early warning system for air pollution based on big data, It is characterized in that The high-density data acquisition optimization module includes a sensor layout optimization unit, a data fusion unit and an interference elimination unit; The sensor layout optimization unit is used to analyze and optimize the layout of sensors in high-density areas; The data fusion unit is used to fuse data from different sensors to avoid repeated data collection; The interference elimination unit is used to detect and eliminate signal interference between sensors.

9. According to claim 1, a real-time monitoring and early warning system for air pollution based on big data, It is characterized in that The user feedback module includes a user satisfaction survey unit and a user suggestion adoption unit; The user satisfaction survey unit is used to collect user feedback on system usage; The user suggestion adopting unit is used to collect and analyze the suggestions put forward by the users.

10. The real-time air pollution monitoring and early warning system based on big data according to claim 1, It is characterized in that The data transmission module transmits data using wireless technology, which includes but is not limited to 5G, Wi-Fi and LoRa.

Images