Atmospheric environment multi-parameter monitoring system and method

Abstract

The invention discloses an atmospheric environment multi-parameter monitoring system and method, and relates to the technical field of atmospheric environment measurement, the atmospheric environment multi-parameter monitoring system comprises a processor unit and an environment monitoring platform cluster composed of a plurality of environment monitoring platforms, through the environment monitoring platform cluster composed of the plurality of environment monitoring platforms, a large monitoring range can be covered, and the monitoring precision is improved. The real-time and effective monitoring of the atmospheric environment of the whole area can be realized with low cost; according to the invention, the position information of each environment monitoring platform can be automatically measured and obtained, rapid point distribution and automatic networking are realized, networking does not depend on an external network, rapid real-time measurement of atmospheric environment information is realized through communication between the server and the environment monitoring platform, and the method is especially suitable for high-density gridding atmospheric environment parameter real-time measurement application.

Description

Technical Field

[0001] The present invention relates to the technical field of atmospheric environment measurement, and particularly to a multi-parameter monitoring system and method for atmospheric environment. Background Art

[0002] In recent years, the awareness of environmental protection in China has been gradually increasing, and national environmental protection agencies have also promoted the construction of various environmental protection-related projects. In the field of environmental monitoring, such as in the field of air quality monitoring, various monitoring stations are set up in urban areas to monitor air pollution. Through the data collected by these monitoring stations, the comprehensive situation of air pollution and air quality in the city can be obtained, and the specific location of pollution can also be initially determined.

[0003] The invention with the publication number CN108414680A discloses an atmospheric environment monitoring system, including: an environmental monitoring platform and a plurality of atmospheric environment monitoring devices; wherein the atmospheric environment monitoring device includes: a processor module, an environmental detection module and a communication module connected to the processor module; the environmental detection module is adapted to send the collected environmental quality parameters to the processor module; and the processor module is adapted to send the environmental quality parameters to the environmental monitoring platform through the communication module.

[0004] As shown in the above invention, the existing atmospheric environment monitoring system generally realizes the collection of atmospheric environment quality parameters by setting a plurality of atmospheric environment monitoring devices, and an antenna cover based on metamaterials is provided outside the antenna module, which greatly improves the stability of signal transmission between the environmental monitoring platform and the atmospheric environment monitoring device. However, to achieve full coverage monitoring of an environmental area in the existing technical solution, a large number of monitoring stations need to be built, resulting in huge investment costs. At the same time, the existing technical solution does not analyze in combination with the pollution situation, and cannot obtain the sources and causes of air pollution, and cannot play an effective guiding role in subsequent air pollution control. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present invention provides a multi-parameter monitoring system and method for atmospheric environment, which solves the above problems of the prior art.

[0006] To achieve the above object, the present invention is realized through the following technical solutions: A multi-parameter monitoring system for atmospheric environment, including: A processor unit for receiving and processing data from multiple environmental monitoring platforms, and having an intelligent algorithm to identify data anomalies and give a preliminary warning; An environmental monitoring platform cluster composed of multiple environmental monitoring platforms, and the multiple environmental monitoring platforms are wirelessly connected through a ZIGBEE communication networking module to form a unified monitoring network, and a distributed consensus algorithm is adopted between the platforms to ensure data consistency; The environmental monitoring platform is carried on a mobile vehicle, which provides mobility and power support for the environmental monitoring platform, and automatically schedules the platform position according to environmental monitoring requirements and real-time traffic information using a path planning algorithm, or remotely controls the mobile monitoring through remote control; The environmental monitoring platform integrates an atmospheric environment parameter collection module, a communication module, and a positioning module. The atmospheric environment parameter collection module collects atmospheric environment parameters in real time through high-precision sensors, and ensures secure data transmission with the processor unit through an encrypted communication protocol; during the collection process, a data fusion algorithm is applied to integrate data from different sensors to improve measurement accuracy; the communication module is used to wirelessly transmit the data processed by the processor module to a remote server, and supports two-way communication to receive configuration updates or instructions issued by the server; the positioning module is used to locate the precise position of each environmental monitoring platform.

[0007] Preferably, the atmospheric environment parameter collection module includes measurement modules for temperature, humidity, rainfall, snowfall, wind speed, wind direction, air pressure, and environmental detection.

[0008] Preferably, the environmental detection module includes a carbon dioxide detection sensor, a sulfur dioxide detection sensor, a nitrogen dioxide detection sensor, a carbon monoxide detection sensor, and a PM2.5 detection sensor.

[0009] Preferably, all devices are connected to a power supply module with a redundant design to ensure continuous and stable power supply; the power supply module is a solar power supply device or a battery power supply device, and integrates an adaptive learning algorithm to predict energy demand based on historical weather data and real-time environmental monitoring results, and dynamically adjusts energy collection and storage strategies; at the same time, a deep learning algorithm is used to optimize the solar panel tracking strategy to maximize energy collection efficiency; the specific content includes: a1. Adaptive learning algorithm and energy demand prediction: The power supply module integrates an adaptive learning algorithm, which uses historical weather data (such as sunshine duration, cloud cover, temperature, etc.) and real-time environmental monitoring results (such as current light intensity, temperature, wind speed, etc.) to predict future energy demand: a1.1 Historical data collection: Collect weather data and environmental monitoring data over a past period of time, including the daily sunshine duration D i , average cloud cover C i , maximum temperature T max，i , minimum temperature T min，i , and the corresponding energy consumption data E i ; a1.2 Feature extraction: Extract key features from the collected data, including sunshine duration, cloud cover, temperature, and construct a feature vector F i =[D i , Ci , T max，i , T min，i , E i , …]; a1.3 Model training: Use machine learning algorithms (such as linear regression, support vector machines, random forests, or neural networks) to train an energy demand prediction model. The model input is the feature vector Fi, and the output is the predicted energy consumption E pred，i ; a1.4 Real-time prediction: Utilize real-time environmental monitoring data and weather forecast data, input them into the trained model, and predict the future energy consumption E pred ; a2. Dynamically adjust the energy collection and storage strategies: According to the predicted energy demand, the power supply module dynamically adjusts energy collection, including the tilt angle and orientation of solar panels, and storage strategies, including the charge and discharge plan of the battery: a2.1 Energy collection strategy: Adjust the tilt angle θ and orientation of the solar panel , to maximize the captured light energy; This can be achieved by optimizing the tracking strategy of the solar panel through deep learning algorithms: θ opt =arg ; where, I(θ, , t) represents the light intensity at time t under the given tilt angle θ and orientation ; a2.2 Energy storage strategy: According to the predicted energy consumption E pred and the remaining power E bat of the current battery, formulate the charge and discharge plan of the battery; E charge =max(0, E pred −E bat −E margin ); E discharge =max(0, E bat −E req +E margin ); where, E charge represents the amount of power to be charged, E discharge represents the amount of power to be discharged, E req represents the predicted real-time energy consumption, E margin represents the safety margin; a3. Optimize the solar panel tracking strategy using deep learning algorithms: Adopt deep learning algorithms (such as convolutional neural network CNN or recurrent neural network RNN) to optimize the solar panel tracking strategy to improve the energy collection efficiency: a3.1 Data collection: Collect the light intensity data of the solar panel under different tilt angles, orientations, and lighting conditions; a3.2 Model training: Use deep learning algorithms to train the model. The inputs of the model are the status information of the solar panel (such as tilt angle, orientation, time, etc.), and the output is the predicted light intensity; a3.3 Strategy optimization: Utilize the trained model to dynamically adjust the tilt angle θ and orientation of the solar panel according to the real-time lighting conditions and weather forecast data to maximize the captured light energy.

[0010] Preferably, the positioning module is an integrated positioning module that fuses multiple satellite systems. Each satellite positioning system provides the position and time information of the satellite, and the positioning module calculates the position of the receiver by receiving these signals; Let the position of the satellite be (x s , y s , z s ), the time when the satellite sends the signal be t s , and the time when the receiver receives the signal be t r . Given the speed of light c, the distance d between the receiver and the satellite can be expressed as: d = c × (t r -t s ); By receiving the signals of multiple satellites and calculating the distances between the receiver and each satellite, the three-dimensional position (x, y, z) of the receiver can be solved using spatial geometry methods; The calculation content of the integrated positioning module includes: b1 Receive and process the data of multiple satellite positioning systems, and calculate the distances between the receiver and each satellite; b2 Use spatial geometry methods to solve the three-dimensional position of the receiver; b3 Match the real-time positioning data with the high-precision map through the map matching algorithm to find the most likely driving path, and correct the positioning data according to the map matching result; b4 Optimize and correct the satellite positioning data using the particle filter algorithm; b5 Output the final vehicle position information.

[0011] Preferably, the basic steps of the map matching algorithm include: b3.1 Obtain the positioning data in real time, including information such as longitude, latitude, and speed; b3.2 Match the positioning data with the high-precision map to find the most likely driving path; b3.3 Correct the positioning data according to the matching result to obtain a more accurate vehicle position; The basic steps of the particle filter algorithm include: b4.1 Initialization: Generate a set of random particles in the positioning space, where each particle represents a possible vehicle position; b4.2 Prediction: Predict the position and velocity of each particle according to the vehicle's motion model and sensor data; b4.3 Update: Update the weight of each particle according to the observation data (such as satellite positioning data). The particles with higher weights are closer to the real position; b4.4 Resampling: Resample according to the weights of the particles, retain the particles with high weights, and eliminate the particles with low weights; b4.5 Position estimation: Calculate the estimated value of the vehicle position according to the positions and weights of all particles.

[0012] Preferably, the server is used to receive and store environmental parameters. The server further includes a data processing and analysis unit, which is used to analyze the sources and causes of pollution through environmental parameters, decompose the data processing and analysis process into multiple microservices through a microservices architecture, and optimize the communication between multiple microservices through a monitoring service mesh; the server is also used to transmit the processing and analysis result information of the data processing and analysis unit to the management terminal.

[0013] Preferably, the management terminal includes a transceiver unit, an operation management system, and a display unit. The transceiver unit is used to receive the information transmitted by the server and transmit it to the operation management system. The operation management system is used to control the display unit to display the sources and causes of pollution. The operation management system integrates an artificial intelligence-assisted decision-making function and automatically proposes improvement suggestions according to historical decision data and real-time environmental data by using a reinforcement learning algorithm.

[0014] Preferably, the display unit introduces multi-dimensional visualization technologies, such as three-dimensional scatter plots, heat maps, etc., to display the sources and causes of pollution in a more intuitive way. By adjusting the visualization dimension n and the color mapping function f(x), the highlighting display and in-depth analysis of different data features are realized; Among them, the visualization dimension n determines the complexity and detail of the displayed data; the color mapping function f(x) is used to convert numerical data into color representation, and the color mapping function f(x) is expressed as: f(x)=RGB(r, g, b), where r, g, and b are the red, green, and blue components calculated according to the value of x; The reinforcement learning algorithm continuously learns, optimizes, and updates during the data processing process, enabling it to more efficiently utilize historical decision-making data and real-time environmental data. Let the learning rate α represent the control of the algorithm update speed, and the discount factor γ represent the importance of balancing the current reward and future rewards. The state space S and the action space A respectively represent the defined environment and possible operations of reinforcement learning; by adjusting the learning rate α and the discount factor γ to balance the convergence speed and stability of the algorithm, at the same time, refining the state space S and the action space A to improve the adaptability of the algorithm to complex environments. The specific formula is expressed as: Q(s, a) ← Q(s, a) + α[p + γ maxa′Q(s′, a′) - Q(s, a)], where s is the current state, a is the current action, p is the immediate reward, and s′ is the next state.

[0015] The present invention also discloses a multi-parameter monitoring method for the atmospheric environment, including the following steps: S1: Disperse multiple environmental monitoring platforms at different positions in the environmental monitoring operation area through a mobile carrier, and determine the positions of the environmental monitoring platforms through a positioning module; S2: Collect environmental data through the atmospheric environment parameter collection module on the environmental monitoring platform; S3: Transmit the collected environmental data to the processor unit, and after the processor unit receives and processes it, transmit the preliminarily processed data to the server through the communication module; S4: The data processing and analysis unit of the server uses the real-time monitored environmental parameters to build a spatio-temporal domain model of the environmental pollution situation, and analyze the sources and causes of environmental pollution; S5: The server transmits the processing and analysis results to the management terminal.

[0016] The present invention provides a multi-parameter monitoring system and method for the atmospheric environment. Compared with the prior art, it has the following beneficial effects: 1. The multi-parameter monitoring system and method for the atmospheric environment can achieve a large monitoring range through an environmental monitoring platform cluster composed of multiple environmental monitoring platforms, and can realize real-time and effective monitoring of the atmospheric environment of the entire region at a relatively low cost. The mobile carrier provides mobility and power support for the environmental monitoring platforms, enabling efficient mobilization of overall resources for high-density environmental monitoring in key areas. At the same time, the data processing and analysis unit of the server uses a microservices architecture, decomposing the data analysis process into multiple microservices, and decomposing the monolithic application with a large amount of data analysis into multiple small and interconnected microservices, making the data analysis simpler and making the continuous deployment and rapid deployment of the entire system easier.

[0017] 2. The multi-parameter monitoring system and method for atmospheric environment can automatically measure and obtain the location information of each environmental monitoring platform, realize rapid point layout and automatic networking, and do not rely on external network connection. Through the communication between the server and the environmental monitoring platform, rapid and real-time measurement of atmospheric environment information can be achieved, which is especially suitable for real-time measurement applications of high-density grid atmospheric environment parameters, such as real-time measurement of parameters such as temperature, humidity, rainfall, wind direction, wind speed, atmospheric composition, air quality, visibility, etc., improving the efficiency of atmospheric measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the system connection of the present invention; Figure 2 It is a schematic diagram of the connection of the environmental monitoring platform of the present invention; Figure 3 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0020] Refer to Figures 1-3 , the present invention provides the following two technical solutions: The first embodiment: A multi-parameter monitoring system for atmospheric environment, including: A processor unit, which not only receives and processes data from multiple environmental monitoring platforms, but also integrates advanced anomaly detection algorithms, such as the ARIMA model based on time series analysis or the LSTM network in deep learning, for real-time identification of data anomalies and preliminary early warning, and at the same time automatically classifies the anomaly types into natural fluctuations or potential pollution events.

[0021] An environmental monitoring platform cluster composed of multiple environmental monitoring platforms. The multiple environmental monitoring platforms are wirelessly connected through a ZIGBEE communication networking module to form a unified monitoring network. A distributed consensus algorithm (such as Raft or Paxos) is used between the platforms to ensure data consistency.

[0022] The environmental monitoring platform is mounted on a mobile vehicle, which provides mobility and power support for the environmental monitoring platform. Using path planning algorithms (such as the A* algorithm or Dijkstra algorithm), it automatically schedules the platform's position according to environmental monitoring requirements and real-time traffic information, or conducts remote control of mobile monitoring through remote control methods. It can also be directly installed on transportation facilities such as buses, taxis, ships, or drones to achieve automatic random movement, thereby reducing costs.

[0023] The environmental monitoring platform integrates an atmospheric environment parameter collection module, a communication module, and a positioning module. It also includes an offline data continuation transmission unit, which consists of a controller and a memory; the controller is connected to the communication module and is used to determine whether the environmental monitoring platform has established a communication connection with the server; the controller is also connected to the memory and is used to control the reading and writing of data to the memory; the memory is connected to the communication module and is used to store environmental parameters.

[0024] The atmospheric environment parameter collection module collects atmospheric environment parameters in real time through high-precision sensors and ensures the secure transmission of data with the processor unit through an encrypted communication protocol; during the collection process, a data fusion algorithm is applied to integrate data from different sensors to improve measurement accuracy. The atmospheric environment parameter collection module includes measurement modules for temperature, humidity, rainfall, snowfall, wind speed, wind direction, air pressure, and environmental detection. The environmental detection module includes carbon dioxide detection sensors, sulfur dioxide detection sensors, nitrogen dioxide detection sensors, carbon monoxide detection sensors, and PM2.5 detection sensors.

[0025] The communication module is used to wirelessly transmit the data processed by the processor module to a remote server and supports two-way communication to receive configuration updates or instructions issued by the server. The server is a cloud server. The environmental monitoring platform and the management terminal both use 4G communication methods to communicate with the cloud server. The server is also connected to a national control station pollutant concentration database and a meteorological station database across the country.

[0026] The server not only receives and stores environmental parameters but also integrates a pollution prediction model based on deep learning to automatically analyze the sources and causes of pollution; through microservice architecture and containerization technology, it realizes the rapid deployment and elastic expansion of services; using service mesh technology combined with API gateways and traffic management algorithms to optimize communication between microservices and improve the overall performance and reliability of the system; finally, the server transmits the processed analysis results to the management terminal through a secure encrypted channel, supports a variety of data visualization tools, and at the same time applies clustering algorithms to identify pollution hotspot areas to provide intuitive and accurate analysis results for decision-makers.

[0027] In the process of the data processing and analysis unit of the cloud server analyzing the sources and causes of air pollution, a very large number of parameters are involved. These parameters may be related to each other, and the types of these parameters may also change at any time. Using a microservices architecture to decompose the data analysis process into multiple microservices, and corresponding different microservices to the parameters and the relationships between the parameters respectively, the monolithic application with huge computing workload for data analysis can be decomposed into multiple small and interconnected microservices, making the data analysis simpler. At the same time, if the types of parameters change, only one of the microservices needs to be modified, which makes the continuous deployment and rapid deployment of the entire system easier.

[0028] By monitoring the service mesh, during the simultaneous operation of multiple microservices, functions such as service discovery, load balancing, encryption, authentication and authorization, and support for the circuit breaker pattern are provided; the communication between each microservice becomes fast, flexible and reliable, integrating resources as a whole, and enabling better results in data analysis and processing. The cloud server is also used to transmit the processing and analysis result information of the data processing and analysis unit to the management terminal.

[0029] The management terminal includes a transceiver unit, an operation management system and a display unit. The transceiver unit is used to receive the information transmitted by the server and transmit it to the operation management system, and the operation management system is used to control the display unit to display the sources and causes of pollution.

[0030] The management terminal preferably uses a desktop computer, a laptop computer, a tablet computer and a mobile phone. The transceiver unit is used to receive the information transmitted by the server and transmit it to the operation management system. For desktop computers and laptop computers, the transceiver unit preferably uses an optical fiber communication module, and the operation management system is a computer application program; for tablet computers and mobile phones, the transceiver unit preferably uses a 4G communication module, and the operation management system is a tablet computer APP and a mobile phone APP. Using a desktop computer and a laptop computer as the management terminal can complete more complex operation control of the system; using a tablet computer and a mobile phone as the management terminal is convenient to carry, and can conveniently view the relevant data of the system outdoors in real time and perform simple operation control of the system. After receiving the data analysis and processing results of the server, the operation management system converts them into image and text information and displays them on the display unit, showing the sources and causes of pollution. The operation management system integrates an artificial intelligence-assisted decision-making function, and uses a reinforcement learning algorithm to automatically propose improvement suggestions based on historical decision data and real-time environmental data; the display unit uses a high-resolution touch screen, supports interactive data display, and users can intuitively view the sources, causes and improvement suggestions of pollution and make quick responses through gesture operations; at the same time, natural language processing technology is applied to achieve voice command control and improve operation convenience.

[0031] All devices are connected to the power supply module with redundant design to ensure continuous and stable power supply. The power supply module is a solar power supply device or a battery power supply device, and integrates an adaptive learning algorithm to predict energy demand based on historical weather data and real-time environmental monitoring results, and dynamically adjusts energy collection and storage strategies. At the same time, a deep learning algorithm is used to optimize the solar panel tracking strategy to maximize the energy collection efficiency. The specific content includes: a1. Adaptive learning algorithm and energy demand prediction: The power supply module integrates an adaptive learning algorithm, which uses historical weather data (such as sunshine duration, cloud cover, temperature, etc.) and real-time environmental monitoring results (such as current light intensity, temperature, wind speed, etc.) to predict future energy demand: a1.1 Historical data collection: Collect weather data and environmental monitoring data over a past period, including the daily sunshine duration D i , average cloud cover C i , maximum temperature T max，i , minimum temperature T min，i , and the corresponding energy consumption data E i ; a1.2 Feature extraction: Extract key features from the collected data, including sunshine duration, cloud cover, temperature, and construct a feature vector F i =[D i , C i , T max，i , T min，i , E i ,…]; a1.3 Model training: Use machine learning algorithms (such as linear regression, support vector machine, random forest or neural network) to train the energy demand prediction model. The input of the model is the feature vector Fi, and the output is the predicted energy consumption E pred，i ; a1.4 Real-time prediction: Use real-time environmental monitoring data and weather forecast data, input them into the trained model, and predict the future energy consumption E pred ; a2. Dynamically adjust energy collection and storage strategies: According to the predicted energy demand, the power supply module dynamically adjusts energy collection, including the tilt angle and orientation of solar panels, and storage strategies, including the charge and discharge plan of the battery: a2.1 Energy collection strategy: Adjust the tilt angle θ and orientation of solar panels , to maximize the captured light energy; This can be achieved by optimizing the tracking strategy of solar panels through a deep learning algorithm: θ opt =arg ; where, I(θ, , t) represents the light energy captured at a given tilt angle θ and orientation Under this condition, the light intensity at time t; a2. 2 Energy storage strategy: According to the predicted energy consumption E pred and the remaining power E of the current battery bat , formulate the charging and discharging plan of the battery; E charge = max(0, E pred − E bat − E margin ); E discharge = max(0, E bat − E req + E margin ); Among them, E charge represents the amount of power that needs to be charged, E discharge represents the amount of power that needs to be discharged, E req represents the predicted real-time energy consumption, E margin represents the safety margin; a3. Optimize the solar panel tracking strategy with deep learning algorithms: Use deep learning algorithms (such as convolutional neural network CNN or recurrent neural network RNN) to optimize the solar panel tracking strategy to improve the energy collection efficiency: a3. 1 Data collection: Collect the light intensity data of the solar panel under different tilts, orientations and lighting conditions; a3. 2 Model training: Use deep learning algorithms to train the model. The input of the model is the state information of the solar panel (such as tilt, orientation, time, etc.), and the output is the predicted light intensity; a3. 3 Strategy optimization: Use the trained model to dynamically adjust the tilt θ and orientation of the solar panel according to the real-time lighting conditions and weather forecast data to maximize the captured light energy.

[0032] By integrating the adaptive learning algorithm and the deep learning algorithm, the power supply module can accurately predict the energy demand and dynamically adjust the energy collection and storage strategy accordingly, thus ensuring the continuous and stable supply of electricity. In addition, the application of the deep learning algorithm also optimizes the solar panel tracking strategy and significantly improves the energy collection efficiency. These improvements not only enhance the reliability and stability of the power supply system, but also effectively reduce the energy consumption and operation and maintenance costs, providing a strong power guarantee for the continuous operation of various devices, and having broad application prospects and important social value.

[0033] The positioning module is an integrated positioning module that fuses multiple satellite systems. Each satellite positioning system provides the position and time information of the satellite, and the positioning module calculates the position of the receiver by receiving these signals; Let the position of the satellite be (xs , y s , z s ), the time when the satellite sends the signal is t s , the time when the receiver receives the signal is t r , the speed of light is c, then the distance d between the receiver and the satellite can be expressed as: d = c×(t r -t s ); By receiving the signals of multiple satellites and calculating the distances between the receiver and each satellite, the three-dimensional position (x, y, z) of the receiver can be solved using spatial geometric methods; The calculation content of the integrated positioning module includes: b1 Receiving and processing the data of multiple satellite positioning systems, and calculating the distances between the receiver and each satellite; b2 Solving the three-dimensional position of the receiver using spatial geometric methods; b3 Matching the real-time positioning data with a high-precision map through a map matching algorithm to find the most likely driving path, and correcting the positioning data according to the map matching result; b4 Optimizing and correcting the satellite positioning data using a particle filter algorithm; b5 Outputting the final vehicle position information.

[0034] The map matching algorithm is to match the real-time positioning data with a pre-constructed high-precision map to achieve accurate positioning of the vehicle or mobile device in the geographical space; the map matching technology can eliminate positioning errors and improve the accuracy and stability of positioning; the basic steps of the map matching algorithm include: b3.1 Obtaining positioning data in real time, including information such as longitude, latitude, and speed; b3.2 Matching the positioning data with a high-precision map to find the most likely driving path; b3.3 Correcting the positioning data according to the matching result to obtain a more accurate vehicle position; In the process of map matching, common algorithms include the point-to-point map matching algorithm, the point-to-arc map matching algorithm, and the arc-to-arc map matching algorithm, etc.; the core idea of these algorithms is to match the positioning data with map features to find the vehicle position that most conforms to the actual situation; The particle filter algorithm is a filtering algorithm based on Bayesian statistics and Monte Carlo methods, which is suitable for processing dynamic systems with non-linear and non-Gaussian distributions; in the positioning module, the particle filter algorithm can be used to optimize and correct satellite positioning data to improve the accuracy and robustness of positioning; the basic steps of the particle filter algorithm include: b4.1 Initialization: Generate a set of random particles in the positioning space, where each particle represents a possible vehicle position; b4.2 Prediction: Predict the position and velocity of each particle according to the vehicle's motion model and sensor data; b4.3 Update: Update the weight of each particle according to the observation data (such as satellite positioning data). The higher the weight of a particle, the closer it is to the real position; b4.4 Resampling: Resample according to the weights of the particles, retain the particles with high weights, and eliminate the particles with low weights; b4.5 Position Estimation: Calculate the estimated value of the vehicle position according to the positions and weights of all particles; By integrating the integrated positioning module of multiple satellite systems, the accuracy and reliability of positioning are significantly improved. The application of the map matching algorithm further eliminates positioning errors and ensures the precise positioning of vehicles or mobile devices in the geographical space. At the same time, the introduction of the particle filter algorithm optimizes and corrects the satellite positioning data, enhancing the adaptability of the positioning system in non-linear and non-Gaussian distribution environments. These improvements jointly enhance the overall performance of the positioning system, providing more accurate and stable position information for applications such as vehicle navigation, tracking, and monitoring, which helps to improve the user experience and system security.

[0035] The service mesh is preferably Istio. To specifically describe the working mode of monitoring Istio, this embodiment is described by taking the support for the circuit breaker mode as an example: Suppose there is a very simple microservice architecture, including: a backend service and a frontend service. The frontend service is used for data comparison, and the backend service is used for data extraction. The frontend service and the backend service communicate through a certain protocol. When in the process of data processing and analysis, the frontend service needs to obtain some information, such as environmental monitoring data. However, in the microservice architecture, since the function of the frontend service is only data comparison, the frontend service does not have a corresponding database; the database is connected to the backend service, and the backend service extracts environmental monitoring data from the database; therefore, the frontend will call the backend service to obtain the data necessary for the processing task.

[0036] However, in the actual operation of the system, many problems may occur due to network communication. For example: network failures between the front-end and the back-end, back-end service failures caused by a certain bug in the back-end, failures of the database relied on by the back-end, etc. The communication between the front-end and the back-end will encounter failures. When the back-end service becomes unavailable for various reasons, in some cases, the front-end service's call to the back-end service will be cancelled due to timeout. During the process of data processing and analysis, if multiple tasks need to call the front-end service simultaneously, this actually becomes multiple calls to the back-end service: many requests of the front-end service will be in a timeout state. This will make the overall effect of data processing and analysis not optimized, some operations of calling the front-end service become invalid, and resources are wasted. In this case, a reasonable solution is to fail fast: the front-end service should be made aware of the problem with the back-end service and immediately return the failure to the data processing and analysis unit that initiated the task.

[0037] Istio achieves this through the concept of "sidecar", which is a container that runs together with the data processing and analysis application and provides data. The sidecar can identify the communication protocol being used by the data processing and analysis application, thus sniffing out a large amount of information related to requests for communication between various microservices. Through Istio's monitoring, monitoring of this information can be achieved. When the monitored information indicates a communication failure between the front-end and the back-end, the circuit breaker pattern is used for processing in a timely manner to optimize the communication between multiple microservices, quickly initiate new tasks, achieve fast, flexible and reliable communication among various microservices, and make the use of resources more optimized. The advantage of using the Istio circuit breaker is also that it does not require any knowledge of underlying code and is very simple to set up.

[0038] For convenient monitoring, Istio also provides a mixer component. The mixer component is an attribute processor responsible for providing policy control and telemetry collection. For the data formed by communication requests of each microservice, the mixer component will process all this data and route them to the correct adapters respectively. The adapter is a handler attached to the mixer component, which can enable the mixer to connect to different infrastructure backends that provide core functions, such as monitoring tools, authorization backends, or logging stacks, etc.; it can achieve the flexibility of the mixer component to handle different backends. The exact set of adapters used at runtime is determined through configuration and can be easily extended to target new or custom infrastructure backends. Through the mixer component and the adapter, better observability can be obtained in the microservice architecture.

[0039] The second implementation method: An atmospheric environment multi-parameter monitoring method, including the following steps: S1: Disperse multiple environmental monitoring platforms at different positions in the environmental monitoring operation area through a mobile carrier, and determine the positions of the environmental monitoring platforms through a positioning module; S2: Collect environmental data through the atmospheric environmental parameter collection module on the environmental monitoring platform; S3: Transmit the collected environmental data to the processor unit. After receiving and processing, the processor unit transmits the preliminarily processed data to the server through the communication module; S4: The data processing and analysis unit of the server uses the real-time monitored environmental parameters to build a spatio-temporal domain model of the environmental pollution situation, and analyzes the sources and causes of environmental pollution; S5: The server transmits the processing and analysis results to the management terminal.

[0040] Meanwhile, the content not described in detail in this specification belongs to the prior art well-known to those skilled in the art, and the model parameters of each electrical appliance are not specifically limited, and conventional equipment can be used.

[0041] It should be noted that, in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0042] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An atmospheric environment multi-parameter monitoring system, characterized in that, Including: A processor unit for receiving and processing data from multiple environmental monitoring platforms, equipped with intelligent algorithms to identify data anomalies and give preliminary warnings; An environmental monitoring platform cluster composed of multiple environmental monitoring platforms. The multiple environmental monitoring platforms are wirelessly connected through ZIGBEE communication networking modules to form a unified monitoring network. A distributed consensus algorithm is adopted among the platforms to ensure data consistency; The environmental monitoring platform is carried on a mobile carrier. The mobile carrier provides mobility and power support for the environmental monitoring platform, and uses path planning algorithms to automatically dispatch the platform position according to environmental monitoring requirements and real-time traffic information, or conducts remote control and mobile monitoring through remote control methods; The environmental monitoring platform integrates an atmospheric environment parameter collection module, a communication module, and a positioning module. The atmospheric environment parameter collection module collects atmospheric environment parameters in real time through high-precision sensors, and ensures the secure transmission of data with the processor unit through an encrypted communication protocol; During the collection process, data fusion algorithms are applied to integrate data from different sensors to improve measurement accuracy; The communication module is used to wirelessly transmit the data processed by the processor module to a remote server, and supports two-way communication to receive configuration updates or instructions issued by the server; The positioning module is used to locate the precise positions of each environmental monitoring platform.

2. An atmospheric environment multi-parameter monitoring system according to claim 1, characterized in that: The atmospheric environment parameter collection module includes measurement modules for temperature, humidity, rainfall, snowfall, wind speed, wind direction, air pressure, and environmental detection.

3. The multi-parameter monitoring system for atmospheric environment according to claim 2, characterized in that: The environmental detection module includes a carbon dioxide detection sensor, a sulfur dioxide detection sensor, a nitrogen dioxide detection sensor, a carbon monoxide detection sensor, and a PM2.5 detection sensor.

4. An atmospheric environment multi-parameter monitoring system according to claim 1, characterized in that: All devices are connected to a power supply module with redundant design to ensure continuous and stable power supply; The power supply module is a solar power supply device or a battery power supply device, and integrates an adaptive learning algorithm to predict energy demand based on historical weather data and real-time environmental monitoring results, and dynamically adjusts energy collection and storage strategies; At the same time, deep learning algorithms are used to optimize the solar panel tracking strategy to maximize the energy collection efficiency; The specific content includes: a1. Adaptive learning algorithm and energy demand prediction: The power supply module integrates an adaptive learning algorithm and uses historical weather data and real-time environmental monitoring results to predict future energy demand: a1.1 Historical data collection: Collect weather data and environmental monitoring data over a past period, including the daily sunshine duration D i , average cloud cover C i , maximum temperature T max，i , minimum temperature T min，i , and the corresponding energy consumption data E i ; a1.2 Feature extraction: Extract key features from the collected data, including sunshine duration, cloud cover, temperature, and construct a feature vector F i =[D i ,C i ,T max，i ,T min，i ,E i ,…]; a1.3 Model training: Use machine learning algorithms to train an energy demand prediction model. The input of the model is the feature vector Fi, and the output is the predicted energy consumption E pred，i ; a1.4 Real-time prediction: Using real-time environmental monitoring data and weather forecast data, input them into the trained model to predict the future energy consumption E pred ; a2. Dynamically adjust energy collection and storage strategies: According to the predicted energy demand, the power supply module dynamically adjusts energy collection, including the tilt angle and orientation of solar panels, and storage strategies, including the charge and discharge plans of batteries: a2. 1 Energy harvesting strategy: Adjust the tilt angle θ and orientation of the solar panel , to maximize the captured light energy, achieved by optimizing the tracking strategy of the solar panel through a deep learning algorithm: θ opt =arg ; Among them, I(θ, , t) represents the light intensity at time t under a given inclination angle θ and orientation ; a2. 2 Energy storage strategy: Based on the predicted energy consumption E pred and the remaining power of the current battery E bat , formulate the charging and discharging plan of the battery; E charge = max(0, E pred - E bat - E margin ); E discharge = max(0, E bat − E req + E margin )); Among them, E charge represents the amount of electricity to be charged, E discharge represents the amount of electricity to be discharged, E req represents the predicted real-time energy consumption, E margin represents the safety margin; a3. Deep learning algorithm to optimize the solar panel tracking strategy: Deep learning algorithms are used to optimize the solar panel tracking strategy to improve the energy collection efficiency: a3.1 Data collection: Collect the light intensity data of solar panels under different tilt angles, orientations, and lighting conditions; a3.2 Model training: Use deep learning algorithms to train the model. The input of the model is the status information of the solar panel, and the output is the predicted light intensity; a3. 3 Strategy Optimization: Using the trained model, dynamically adjust the tilt angle θ and orientation of the solar panels according to real-time lighting conditions and weather forecast data to maximize the captured lighting energy.

5. The multi-parameter monitoring system for atmospheric environment according to claim 1, characterized in that: The positioning module is an integrated positioning module that integrates multiple satellite systems. Each satellite positioning system provides the position and time information of the satellite. The positioning module calculates the position of the receiver by receiving these signals; Let the position of the satellite be (x s , y s , z s ). Let the time when the satellite sends the signal be t s , and the time when the receiver receives the signal be t r . Let the speed of light be c. Then the distance d between the receiver and the satellite is expressed as: d = c×(t r −t s ); By receiving the signals of multiple satellites and calculating the distances between the receiver and each satellite, the three-dimensional position (x, y, z) of the receiver is solved using spatial geometry methods; The calculation content of the integrated positioning module includes: b1 Receive and process the data of multiple satellite positioning systems, and calculate the distances between the receiver and each satellite; b2 Solve the three-dimensional position of the receiver using spatial geometry methods; b3 Match the real-time positioning data with the high-precision map through the map matching algorithm to find the most likely driving path, and correct the positioning data according to the map matching result; b4 Optimize and correct the satellite positioning data using the particle filter algorithm; b5 Output the final vehicle position information.

6. An atmospheric environment multi-parameter monitoring system according to claim 5, characterized in that: The steps of the map matching algorithm include: b3.1 Obtain the positioning data in real time, including longitude, latitude, and speed information; b3.2 Match the positioning data with the high-precision map to find the most likely driving path; b3.3 Correct the positioning data according to the matching result to obtain a more accurate vehicle position; The steps of the particle filter algorithm include: b4.1 Initialization: Generate a set of random particles in the positioning space, and each particle represents a possible vehicle position; b4.2 Prediction: Predict the position and speed of each particle according to the motion model of the vehicle and the sensor data; b4.3 Update: Update the weight of each particle according to the observation data. The higher the weight, the closer the particle is to the real position; b4.4 Resampling: Resample according to the weights of the particles, retain the particles with high weights, and eliminate the particles with low weights; b4.5 Position estimation: Calculate the estimated value of the vehicle position according to the positions and weights of all particles.

7. An atmospheric environment multi-parameter monitoring system according to claim 1, characterized in that: The server is used to receive and store environmental parameters. The server also includes a data processing and analysis unit, which is used to analyze the sources and causes of pollution through environmental parameters, decompose the data processing and analysis process into multiple microservices through the microservices architecture, and optimize the communication between multiple microservices through the monitoring service mesh; The server is also used to transmit the processing and analysis result information of the data processing and analysis unit to the management terminal.

8. An atmospheric environment multi-parameter monitoring system according to claim 7, characterized in that: The management terminal includes a transceiver unit, an operation management system, and a display unit. The transceiver unit is used to receive the information transmitted by the server and transmit it to the operation management system. The operation management system is used to control the display unit to display the sources and causes of pollution. The operation management system integrates an artificial intelligence-assisted decision-making function and automatically proposes improvement suggestions using the reinforcement learning algorithm according to historical decision data and real-time environmental data.

9. The multi-parameter monitoring system for atmospheric environment according to claim 8, wherein: The display unit introduces multi-dimensional visualization technology, and realizes the prominent display and in-depth analysis of different data features by adjusting the visualization dimension n and the color mapping function f(x); Among them, the visualization dimension n determines the complexity and detail level of the displayed data; the color mapping function f(x) is used to convert numerical data into color representation, and the color mapping function f(x) is expressed as: f(x) = RGB(r, g, b), where r, g, and b are the red, green, and blue components calculated according to the value of x; The reinforcement learning algorithm continuously learns, optimizes, and updates during the data processing. Let the learning rate α represent the control of the algorithm update speed, and the discount factor γ represent the importance of balancing the current reward and future rewards. The state space S and the action space A respectively represent the defined environment and possible operations of the reinforcement learning; by adjusting the learning rate α and the discount factor γ to balance the convergence speed and stability of the algorithm. At the same time, refine the state space S and the action space A to improve the adaptability of the algorithm to complex environments. The specific formula is expressed as: Q(s, a) ← Q(s, a) + α[p + γmaxa′Q(s′, a′) − Q(s, a)], where s is the current state, a is the current action, p is the immediate reward, and s′ is the next state.

10. A multi-parameter monitoring method for the atmospheric environment, which is implemented based on the multi-parameter monitoring system for the atmospheric environment according to any one of claims 1-9, characterized in that, It includes the following steps: S1: Disperse multiple environmental monitoring platforms at different positions in the environmental monitoring operation area through a moving carrier, and determine the positions of the environmental monitoring platforms through a positioning module; S2: Collect environmental data through the atmospheric environment parameter collection module on the environmental monitoring platform; S3: Transmit the collected environmental data to the processor unit. After receiving and processing, the processor unit transmits the preliminarily processed data to the server through the communication module; S4: The data processing and analysis unit of the server uses the real-time monitored environmental parameters to build a spatio-temporal domain model of the environmental pollution situation, and analyze the sources and causes of environmental pollution; S5: The server transmits the processing and analysis results to the management terminal.

Images