A method and system for carbon emission monitoring based on drones

Abstract

The present invention discloses a method and system for carbon emission monitoring based on an unmanned aerial vehicle (UAV). The system comprises: an UAV, a control terminal, and a data processing terminal; it also includes a carbon emission detection sensor assembly; the control terminal receives detection data obtained by the carbon emission detection sensor assembly and transmits the detection data or processed data to the data processing terminal via a wireless data transmission module, wherein the processed data is data on carbon emission detection results obtained after processing the detection data; the data processing terminal includes a data clustering processing module, an outlier detection module, a model building module, a route planning module, and a wireless data transmission module. The method can be implemented based on the system. This solution can be applied to carbon emission monitoring and has the characteristics of accurate and efficient carbon emission source positioning.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission monitoring, and in particular to a method and system for realizing carbon emission monitoring based on an unmanned aerial vehicle. Background Art

[0002] With the continuous development of industrialization, carbon emissions have become a major issue of global concern. Carbon emissions generally refer to greenhouse gas emissions, primarily carbon dioxide (CO2 is generally considered the most important gas, but others include water vapor, ozone, and methane). This is the general term for greenhouse gas emissions. The consequence of carbon emissions is the greenhouse effect, which causes global temperatures to rise and leads to global warming.

[0003] Carbon emissions and air pollution are generally considered separate concepts. However, monitoring carbon content in the air is a key indicator, similar to monitoring air pollution levels. Traditional carbon content monitoring methods primarily rely on stationary carbon monitoring instruments deployed at fixed locations. To obtain reliable data, fixed monitoring technology places high demands on the placement and accuracy of the instruments. Furthermore, fixed monitoring technology also suffers from limitations in monitoring range, high monitoring costs, and the inability to accurately identify carbon emission sources.

[0004] In carbon emission monitoring, in addition to using fixed sensors, sensors installed on mobile objects can also be used. These sensors move in space with the mobile objects, thereby expanding the monitoring area and accurately locating emission sources. Regarding mobile carbon emission monitoring, there are the following solutions in this field: Research on the theme of modern monitoring in megacities is committed to using vehicles and other carriers to achieve mobile monitoring or data collection. At the same time, mobile monitoring is a low-cost and promising method that can obtain relatively high-resolution air condition data at a lower cost and over a larger area. Among other mobile monitoring solutions, drone monitoring is receiving increasing attention: it not only enables more accurate air condition data collection, but also makes it easier to locate and track carbon emission sources.

[0005] Among the specific schemes currently disclosed, for example, the technical scheme provided by the invention with the application number CN202210556473.4 and the invention titled "A carbon emission online monitoring platform and analysis method" discloses a carbon emission monitoring subunit including multiple monitoring drones and drone consoles, setting multiple sets of drone monitoring point combinations based on three-dimensional model data, and obtaining the most reasonable drone monitoring point combination for buildings based on carbon dioxide emission data analysis; the technical scheme provided by the invention with the application number CN202210811684.8 and the invention titled "A multi-channel carbon emission comprehensive monitoring method" discloses a method based on carbon satellites, ground A carbon dioxide observation station and a preset fixed-point carbon dioxide emission detector are provided, and these data are monitored and judged. According to the judgment results, an electric drone device is selected to obtain the total atmospheric carbon dioxide emission data; the application number is CN202210925190.2, and the invention name is "Inversion of strong point source carbon emission intensity calculation method and system based on drone sampling". The technical solution provided discloses a method of using drones to sample carbon emissions, and establishing a carbon emission diffusion model based on the sampling data, and further using the corresponding algorithm to use the diffusion model to obtain carbon emission intensity and verify the carbon emission intensity.

[0006] In summary, carbon emission monitoring through drones has been applied in various technical solutions. At the same time, such data collection methods have incomparable advantages over other methods. Therefore, optimizing the use of drones in carbon emission monitoring has positive significance. Summary of the Invention

[0007] In response to the above-mentioned technical problem of optimizing the use of drones in carbon emission monitoring, which has positive significance, the present invention provides a method and system for realizing carbon emission monitoring based on drones. This solution can be applied to carbon emission monitoring and has the characteristic of accurate positioning of carbon emission sources.

[0008] The purpose of the present invention is mainly achieved through the following technical solutions:

[0009] A system for carbon emission monitoring based on drones, comprising drones, a control terminal, and a data processing terminal;

[0010] It also includes a carbon emission detection sensor component, and the control terminal and the carbon emission detection sensor component are both carried on the drone;

[0011] The control terminal receives the detection data obtained by the carbon emission detection sensor assembly and transmits the detection data or processed data to the data processing terminal through the wireless data transmission module. The processed data is data on the carbon emission detection results obtained after processing the detection data.

[0012] The data processing terminal includes a data clustering processing module, which performs clustering processing on the detection data or processing data from the control terminal to obtain a carbon content concentration data subset divided according to spatial regions;

[0013] The data processing terminal includes an outlier detection module, which performs outlier detection on a subset of carbon content concentration data: when it is determined that the carbon content concentration data therein exceeds a set threshold, the detection data collection area corresponding to the subset of carbon content concentration data is identified as an outlier, and the obtained outlier is marked;

[0014] The data processing terminal includes a model building module. When it is determined that there is an abnormal point, the model building module uses the obtained carbon content concentration data subset and meteorological data to build a carbon emission diffusion model;

[0015] The data processing terminal includes a route planning module, which uses a carbon emission diffusion model to perform carbon emission source tracking route planning;

[0016] The data processing terminal includes a wireless data transmission module for sending the tracking route data to the control terminal, and the control terminal controls the route of the UAV for the purpose of searching for carbon emission sources based on the tracking route data.

[0017] In the existing technology, drones equipped with carbon emission detection sensor components to complete carbon emission monitoring have incomparable advantages over ground monitoring methods. In flight missions for the purpose of carbon emission monitoring, such as the technical solution provided by patent application number CN202210556473.4, the acquired three-dimensional building model data is used to set up a drone monitoring point combination scheme. In other cases, when technical personnel in this field realize automatic monitoring of carbon emission data under a planned route, on the planned route, they generally only use terrain information, inspection range, monitoring height, inspection frequency and time to set the route. The drone carrying the carbon emission detection sensor component completes the carbon emission data collection within the inspection range under the specified route.

[0018] Based on this, this solution provides a carbon emission monitoring system based on drones. Unlike the existing technology, by reasonably configuring the system components, it can achieve the purpose of ensuring the effective cruising time of drones, being able to promptly detect abnormal carbon emission sources, and facilitating the precise positioning of carbon emission sources.

[0019] Specifically:

[0020] The carbon emission detection sensor assembly serves as a collection device for carbon emission data on a drone. The control terminal can serve as the drone's flight control module or a controller independent of the flight control module that is data-connected to the flight control module. The data processing terminal is a data processing device independent of the drone and can be a remote data processing server or a data processor in a remote control center, such as a cloud-based big data processing center. Furthermore, the data clustering processing module, outlier detection module, model building module, and route planning module can each be a substructure of the data processing terminal with different data processing functions, or virtual modules running on the same data processing terminal and implementing different functions through different computer programs.

[0021] Different from the existing technology, first of all, this solution incorporates the inspection data from the carbon emission detection sensor assembly into the carbon emission source tracking route planning. In this way, when the drone performs a flight mission, it can search for carbon emission sources through the tracking route based on the specific situation of the detection data during the flight, discover carbon emission anomalies at the first time, and obtain the specific location of the abnormal carbon emission source in time during the mission.

[0022] Secondly, given the correlation between carbon emission diffusion and meteorological data, the carbon content concentration data subset divided according to spatial regions is used as the data basis for outlier judgment and carbon emission diffusion model construction. In this way, a relatively accurate carbon emission diffusion model can be obtained, which is conducive to improving the efficiency and accuracy of carbon emission source search; the carbon content concentration data subset can be used to plan the carbon emission flow corresponding to the spatial area of ​​the subset, thereby improving the accuracy of outlier judgment.

[0023] Finally, when this solution is implemented, the data processing terminal needs to have better data computing capabilities. In this solution, it is set as a separate functional component from the drone and realizes two-way data transmission through wireless data transmission. This not only reduces the load of the drone, but also the power consumption of the data processing terminal does not affect the endurance of the drone. Therefore, this solution can effectively guarantee the cruising mileage of the drone in a single mission.

[0024] As a person skilled in the art, the obtaining of a subset of carbon content concentration data divided according to spatial regions refers to clustering the detection data or processing data from the same set spatial region and clustering them into a subset of carbon content concentration data. Moreover, since in an atmospheric environment, such as on a horizontal plane, meteorological data and altitude both affect the area and shape of the carbon emission diffusion model on the plane, the same set spatial region is preferably determined based on the measured value of the inspection data: the initial inspection route planned as the drone route is a horizontal route on the same plane, and when the carbon emission detection sensor component detects that the carbon content data at the current position is higher than the normal carbon content at the local altitude, it is determined that the position is in the carbon emission airflow, and then the drone continues to fly with the carbon emission detection sensor component, and obtains the boundary of the airflow on the set plane (not limited to the horizontal plane, vertical plane, preferably an inclined plane) through the detection data, and in order to obtain an accurate airflow boundary, the drone is now set to trigger the boundary cruise action and record the triggering boundary. The position coordinates of the UAV during the cruising action; then, according to the set boundary cruising action mode, after combining the meteorological data and the flight altitude (the meteorological data and the flight altitude both determine the three-dimensional shape of the airflow at the current position), multiple boundary positions of any cross-section of the airflow (preferably the cross-section is perpendicular to the flow direction of the airflow) are obtained. These boundary positions are located at different directions of the cross-section. Then, according to these boundary positions, the boundary of the airflow on the cross-section is obtained, and the carbon emission flow on the cross-section is obtained in combination with the multiple detection data obtained within the boundary, and it is determined whether the carbon emission source corresponding to the airflow has an emission problem exceeding the standard. If so, the position is determined to be an abnormal point, and subsequent carbon emission source search action is carried out; if not, the UAV returns to the recorded position coordinates of the UAV when the boundary cruising action is triggered, and continues to fly according to the original planned route.

[0025] In addition, the detection data is the data obtained directly through the carbon emission detection sensor component, and the processed data is the data about the carbon emission detection results obtained after averaging the detection data from multiple data sources, eliminating abnormal data, and correcting the data on the basis of the detection data.

[0026] As a further technical solution for the drone-based carbon emission monitoring system:

[0027] In a specific embodiment, the drone is further equipped with a camera for image acquisition, a meteorological data detection module for meteorological data acquisition, and a data storage device for storing the location of carbon emission sources;

[0028] The camera and the meteorological data detection module are both data-connected to the control terminal, and both the camera and the meteorological data detection module operate under the control of the control terminal;

[0029] After the carbon emission diffusion model is constructed, the data processing terminal sends the location of the carbon emission source to the control terminal, and the control terminal is data-connected to the data storage device to store the location of the carbon emission source in the data storage device.

[0030] In the specific implementation of this solution, the meteorological data can be obtained from data sources outside of this system, and the timeliness and accuracy of meteorological data acquisition can be guaranteed by equipping the drone with a meteorological data detection module. The camera can be used to collect images of carbon emission sources, or to collect images of carbon emission airflow with visual features. The images obtained can be used for evidence collection, obtaining the angle of the cross section, and assisting in the construction of a carbon emission diffusion model. Preferably, the camera includes an image sensor module for obtaining visual images, and also includes an infrared imaging module, so that when there is less material in the airflow for forming visual features, the carbon emission airflow shape can be obtained based on temperature. The data storage device is used to store the location of the carbon emission source locally on the drone, so as to achieve: when the drone is a separate front-end device and is working without a data processing terminal, it can quickly and efficiently achieve initial flight route planning through local data collection. Furthermore, in this solution, the camera and meteorological data detection module are both controlled by the control terminal. If a battery is provided on the drone to power the drone and these functional modules, the camera and meteorological data detection module are designed to be able to work when needed, thereby ensuring the drone's cruising range by reducing the power consumption of these functional modules.

[0031] In a specific embodiment, the data processing terminal includes a neural network module, and the neural network module is used to implement:

[0032] After the detection data or processed data is transmitted to the data processing terminal, the neural network module uses the neural network model to predict the carbon emission data. When the predicted carbon emission data exceeds the set threshold, the time and location when the carbon emission data exceeds the set threshold output by the neural network model are sent to the route planning module. The route planning module plans the route according to the time and location, so that at the time, the drone carrying the carbon emission detection sensor component flies to the location where the carbon emission data exceeds the set threshold, and collects the carbon content concentration data at the location.

[0033] This solution aims to provide a method for predicting future carbon emissions at a location using a neural network model based on current detection or processing data. When the predicted carbon emissions exceed a set threshold, the time and location at which the carbon emissions exceed the threshold, as output by the neural network model, are sent to a route planning module. The route planning module then enables a drone carrying a carbon emissions detection sensor assembly to fly to the location where the carbon emissions exceed the threshold at that time and collect carbon concentration data at that location. This solution provides a technical solution for efficiently monitoring potential carbon emissions exceeding standards in a region. Those skilled in the art will recognize that the neural network model uses local carbon emission patterns as input for training and outputs the time or location of an anomaly. The neural network model can be a separate substructure on a data processing terminal or a virtual module running on the same data processor or processor cluster, implementing corresponding functions solely through a corresponding computer program. Furthermore, when the route planning module plans routes based on the time and location output by the carbon emissions diffusion model and the neural network model, the planned routes should be understood as serving different functions. Those skilled in the art can prioritize the two routes based on specific needs, enabling the system to implement appropriate action settings based on specific requirements.

[0034] In one specific embodiment, the drone is a fixed-wing electric drone. This solution aims to provide a technical solution that eliminates carbon emissions while the drone is operating, thereby ensuring the accuracy of detection data. Furthermore, fixed-wing drones are a type of high-speed drone, which effectively ensures timely monitoring of carbon emission areas and improves monitoring coverage.

[0035] In a specific embodiment, a ground station is also included, and the data connection between the control terminal and the data processing terminal is established through the ground station: when the control terminal needs to send data to the data processing terminal, the data is first received by the ground station, and then the ground station sends the data to the data processing terminal. The ground station also includes a data storage module for completing local storage of the data at the ground station.

[0036] In this solution, the ground station acts as a relay station and is used to monitor carbon emissions in areas without operator mobile signal coverage. For example, multiple ground stations can be deployed at different locations within the monitoring range. Regarding communication between the drone and the ground station, the relative positions of the ground stations are determined based on the set wireless communication type and antenna performance. The data connection between the ground station and the data processing terminal can be achieved through wired communication or a combination of wired and wireless communication (data is transmitted via a wired communication solution to a location where data transmission can be achieved using wireless communication technology). The application of the above data storage module is intended to achieve the following purposes: according to the data communication process, the ground station serves as a node in the complete communication process. After storing relevant data such as detection data on the ground station, it can be used to obtain data source evidence when abnormal human carbon emissions are detected; considering the quality of wireless communication and the cost of setting up the ground station, the ground station does not need to be set up too densely. For example, it is allowed that the drone cannot establish reliable data communication with the ground station during some time periods under the current route. In this case, relevant data such as the control data of the drone from the data processing terminal will be stored locally. When the drone cruises to a position where it can establish wireless communication with a certain ground station, it can send these data to the control terminal of the drone in a relatively delayed manner, thereby improving the setup cost and controllability of the front-end equipment of this system.

[0037] This solution also discloses a method for realizing carbon emission monitoring based on a drone, comprising the following steps performed in sequence:

[0038] S1. Obtain detection data through the carbon emission detection sensor component carried on the drone;

[0039] S2. Transmitting the detection data or processed data to a data processing terminal, wherein the processed data is data on carbon emission detection results obtained after processing the detection data;

[0040] S3. The data processing terminal performs clustering processing on the detection data or the processed data to obtain a carbon content concentration data subset divided according to spatial regions;

[0041] S4. Detecting abnormal points on the carbon content concentration data subset: When it is determined that the carbon content concentration data exceeds a set threshold, the detection data collection area corresponding to the carbon content concentration data subset is identified as an abnormal point, and the abnormal point is marked and steps S5 to S7 are executed;

[0042] S5. constructing a carbon emission diffusion model using the obtained multiple carbon content concentration data subsets and meteorological data;

[0043] S6. Plan carbon emission source tracking routes based on the carbon emission diffusion model;

[0044] S7. The drone flies along the tracking route for the purpose of searching for carbon emission sources and collects carbon concentration data and ground image data. As described above, this method can be implemented based on the system and shares the same concept as the system. It uses a subset of carbon concentration data to accurately identify anomalies and construct a carbon emission diffusion model. Based on the carbon emission diffusion model, a tracking route is derived to efficiently and accurately identify carbon emission anomalies and effectively complete the carbon emission source search within the mission.

[0045] In a specific embodiment, before the drone takes off, a mission route of the drone is planned and the mission route is loaded into a control terminal on the drone, and the control terminal controls the drone to fly according to the mission route;

[0046] After step S6 is completed, the mission route is modified based on the tracking route. The drone then flies along the modified mission route under the control of the control terminal. In this solution, the mission route serves as the drone's initial route. After triggering the carbon emission source search, the mission route is modified based on the tracking route. This solution provides a technical solution for automatically completing carbon emission monitoring.

[0047] In a specific embodiment, after step S5 is completed, the location of the carbon emission source is obtained using the carbon emission diffusion model, and the location of the carbon emission source is stored in a data storage device;

[0048] When planning the mission route before the drone takes off, the carbon emission source locations stored in the data storage device are used as a reference for mission route planning. Similar to the above, this solution uses historical carbon emission source location data as the basis for mission route planning. Based on the fact that carbon emission sources are generally located in fixed locations or fixed areas, the mission route can be planned in a targeted manner to maximize the efficiency of carbon emission monitoring flights.

[0049] In a specific embodiment, before the drone takes off, a mission route of the drone is planned and the mission route is loaded into a control terminal on the drone, and the control terminal controls the drone to fly according to the mission route;

[0050] After step S2 is completed, the carbon emission data is predicted using a neural network model. When the predicted carbon emission data exceeds the set threshold, the time and location at which the carbon emission data exceeds the set threshold output by the neural network model are used to adjust the mission route, so that at the time, the drone carrying the carbon emission detection sensor assembly flies to the location where the carbon emission data exceeds the set threshold, and collects the carbon content concentration data at that location. Similar to the above scheme, this scheme uses a neural network model to predict the later carbon emission data. When it is predicted that carbon emissions may exceed the standard, the neural network model is used to obtain the time and location of the occurrence, and the location and time are used as the basis for adjusting the mission route. That is, this scheme provides a technical solution that can effectively monitor carbon emissions that may exceed the standard in a region.

[0051] In a specific embodiment, the UAV used in step S1 is a fixed-wing electric UAV;

[0052] Steps S3 to S6 are completed using a data processing terminal that is remotely connected to the drone;

[0053] The remote data connection includes a ground station that serves as a data relay station. When the ground station transmits data, the ground station locally stores the transmitted data. As mentioned above, the selection of the drone to be used aims to adopt a technical solution that is accurate in detection data, highly efficient in monitoring, and has a wide monitoring coverage. The setting method of steps S3 to S6 aims to provide a technical solution that can guarantee the data operation speed and the cruising range of the drone. The setting of the ground station can not only solve the data transmission problem in areas without commercial networks, but can also be used for local forensics of detection data and relatively delayed transmission of drone control data.

[0054] In summary, the present invention has the following beneficial effects compared with the prior art:

[0055] First, this solution incorporates the inspection data from the carbon emission detection sensor assembly into the carbon emission source tracking route planning. In this way, when the drone performs a flight mission, it can search for carbon emission sources through the tracking route based on the specific circumstances of the detection data during the flight, discover carbon emission anomalies at the first time, and obtain the specific location of the abnormal carbon emission source in time during the mission.

[0056] Secondly, given the correlation between carbon emission diffusion and meteorological data, the carbon content concentration data subset divided according to spatial regions is used as the data basis for outlier judgment and carbon emission diffusion model construction. In this way, a relatively accurate carbon emission diffusion model can be obtained, which is conducive to improving the efficiency and accuracy of carbon emission source search; the carbon content concentration data subset can be used to plan the carbon emission flow corresponding to the spatial area of ​​the subset, thereby improving the accuracy of outlier judgment.

[0057] Finally, when this solution is implemented, the data processing terminal needs to have better data computing capabilities. In this solution, it is set as a separate functional component from the drone and realizes two-way data transmission through wireless data transmission. This not only reduces the load of the drone, but also the power consumption of the data processing terminal does not affect the endurance of the drone. Therefore, this solution can effectively guarantee the cruising mileage of the drone in a single mission. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0059] Figure 1 This is a system topology diagram of a specific embodiment of the system for realizing carbon emission monitoring based on drones according to the present invention;

[0060] Figure 2 The figure is a flowchart of a specific embodiment of the method for realizing carbon emission monitoring based on drones described in the present invention.

[0061] It should be noted that in Figure 1 In the embodiment, the UAV device includes a UAV and a carbon emission detection sensor component, a control terminal, a meteorological data detection module, a data storage device, etc. carried on the UAV. DETAILED DESCRIPTION

[0062] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with examples and drawings. The exemplary embodiments of the present invention and their descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0063] Example 1:

[0064] like Figure 1 and Figure 2 As shown, this embodiment provides a system for realizing carbon emission monitoring based on a drone, including a drone, a control terminal, and a data processing terminal;

[0065] It also includes a carbon emission detection sensor component, and the control terminal and the carbon emission detection sensor component are both carried on the drone;

[0066] The control terminal receives the detection data obtained by the carbon emission detection sensor assembly and transmits the detection data or processed data to the data processing terminal through the wireless data transmission module. The processed data is data on the carbon emission detection results obtained after processing the detection data.

[0067] The data processing terminal includes a data clustering processing module, which performs clustering processing on the detection data or processing data from the control terminal to obtain a carbon content concentration data subset divided according to spatial regions;

[0068] The data processing terminal includes an outlier detection module, which performs outlier detection on a subset of carbon content concentration data: when it is determined that the carbon content concentration data therein exceeds a set threshold, the detection data collection area corresponding to the subset of carbon content concentration data is identified as an outlier, and the obtained outlier is marked;

[0069] The data processing terminal includes a model building module. When it is determined that there is an abnormal point, the model building module uses the obtained carbon content concentration data subset and meteorological data to build a carbon emission diffusion model;

[0070] The data processing terminal includes a route planning module, which uses a carbon emission diffusion model to perform carbon emission source tracking route planning;

[0071] The data processing terminal includes a wireless data transmission module for sending the tracking route data to the control terminal, and the control terminal controls the route of the UAV for the purpose of searching for carbon emission sources based on the tracking route data.

[0072] In the existing technology, drones equipped with carbon emission detection sensor components to complete carbon emission monitoring have incomparable advantages over ground monitoring methods. In flight missions for the purpose of carbon emission monitoring, such as the technical solution provided by patent application number CN202210556473.4, the acquired three-dimensional building model data is used to set up a drone monitoring point combination scheme. In other cases, when technical personnel in this field realize automatic monitoring of carbon emission data under a planned route, on the planned route, they generally only use terrain information, inspection range, monitoring height, inspection frequency and time to set the route. The drone carrying the carbon emission detection sensor component completes the carbon emission data collection within the inspection range under the specified route.

[0073] Based on this, this solution provides a carbon emission monitoring system based on drones. Unlike the existing technology, by reasonably configuring the system components, it can achieve the purpose of ensuring the effective cruising time of drones, being able to promptly detect abnormal carbon emission sources, and facilitating the precise positioning of carbon emission sources.

[0074] Specifically:

[0075] The carbon emission detection sensor assembly serves as a collection device for carbon emission data on a drone. The control terminal can serve as the drone's flight control module or a controller independent of the flight control module that is data-connected to the flight control module. The data processing terminal is a data processing device independent of the drone and can be a remote data processing server or a data processor in a remote control center, such as a cloud-based big data processing center. Furthermore, the data clustering processing module, outlier detection module, model building module, and route planning module can each be a substructure of the data processing terminal with different data processing functions, or virtual modules running on the same data processing terminal and implementing different functions through different computer programs.

[0076] Different from the existing technology, first of all, this solution incorporates the inspection data from the carbon emission detection sensor assembly into the carbon emission source tracking route planning. In this way, when the drone performs a flight mission, it can search for carbon emission sources through the tracking route based on the specific situation of the detection data during the flight, discover carbon emission anomalies at the first time, and obtain the specific location of the abnormal carbon emission source in time during the mission.

[0077] Secondly, given the correlation between carbon emission diffusion and meteorological data, the carbon content concentration data subset divided according to spatial regions is used as the data basis for outlier judgment and carbon emission diffusion model construction. In this way, a relatively accurate carbon emission diffusion model can be obtained, which is conducive to improving the efficiency and accuracy of carbon emission source search; the carbon content concentration data subset can be used to plan the carbon emission flow corresponding to the spatial area of ​​the subset, thereby improving the accuracy of outlier judgment.

[0078] Finally, when this solution is implemented, the data processing terminal needs to have better data computing capabilities. In this solution, it is set as a separate functional component from the drone and realizes two-way data transmission through wireless data transmission. This not only reduces the load of the drone, but also the power consumption of the data processing terminal does not affect the endurance of the drone. Therefore, this solution can effectively guarantee the cruising mileage of the drone in a single mission.

[0079] As a person skilled in the art, the obtaining of a subset of carbon content concentration data divided according to spatial regions refers to clustering the detection data or processing data from the same set spatial region and clustering them into a subset of carbon content concentration data. Moreover, since in an atmospheric environment, such as on a horizontal plane, meteorological data and altitude both affect the area and shape of the carbon emission diffusion model on the plane, the same set spatial region is preferably determined based on the measured value of the inspection data: the initial inspection route planned as the drone route is a horizontal route on the same plane, and when the carbon emission detection sensor component detects that the carbon content data at the current position is higher than the normal carbon content at the local altitude, it is determined that the position is in the carbon emission airflow, and then the drone continues to fly with the carbon emission detection sensor component, and obtains the boundary of the airflow on the set plane (not limited to the horizontal plane, vertical plane, preferably an inclined plane) through the detection data, and in order to obtain an accurate airflow boundary, the drone is now set to trigger the boundary cruise action and record the triggering boundary. The position coordinates of the UAV during the cruising action; then, according to the set boundary cruising action mode, after combining the meteorological data and the flight altitude (the meteorological data and the flight altitude both determine the three-dimensional shape of the airflow at the current position), multiple boundary positions of any cross-section of the airflow (preferably the cross-section is perpendicular to the flow direction of the airflow) are obtained. These boundary positions are located at different directions of the cross-section. Then, according to these boundary positions, the boundary of the airflow on the cross-section is obtained, and the carbon emission flow on the cross-section is obtained in combination with the multiple detection data obtained within the boundary, and it is determined whether the carbon emission source corresponding to the airflow has an emission problem exceeding the standard. If so, the position is determined to be an abnormal point, and subsequent carbon emission source search action is carried out; if not, the UAV returns to the recorded position coordinates of the UAV when the boundary cruising action is triggered, and continues to fly according to the original planned route.

[0080] In addition, the detection data is the data obtained directly through the carbon emission detection sensor component, and the processed data is the data about the carbon emission detection results obtained after averaging the detection data from multiple data sources, eliminating abnormal data, and correcting the data on the basis of the detection data.

[0081] Example 2:

[0082] This embodiment is further refined based on the embodiment 1:

[0083] The drone is also equipped with a camera for image acquisition, a meteorological data detection module for meteorological data acquisition, and a data storage device for storing the location of carbon emission sources;

[0084] The camera and the meteorological data detection module are both data-connected to the control terminal, and both the camera and the meteorological data detection module operate under the control of the control terminal;

[0085] After the carbon emission diffusion model is constructed, the data processing terminal sends the location of the carbon emission source to the control terminal, and the control terminal is data-connected to the data storage device to store the location of the carbon emission source in the data storage device.

[0086] In the specific implementation of this solution, the meteorological data can be obtained from data sources outside of this system, and the timeliness and accuracy of meteorological data acquisition can be guaranteed by equipping the drone with a meteorological data detection module. The camera can be used to collect images of carbon emission sources, or to collect images of carbon emission airflow with visual features. The images obtained can be used for evidence collection, obtaining the angle of the cross section, and assisting in the construction of a carbon emission diffusion model. Preferably, the camera includes an image sensor module for obtaining visual images, and also includes an infrared imaging module, so that when there is less material in the airflow for forming visual features, the carbon emission airflow shape can be obtained based on temperature. The data storage device is used to store the location of the carbon emission source locally on the drone, so as to achieve: when the drone is a separate front-end device and is working without a data processing terminal, it can quickly and efficiently achieve initial flight route planning through local data collection. Furthermore, in this solution, the camera and meteorological data detection module are both controlled by the control terminal. If a battery is provided on the drone to power the drone and these functional modules, the camera and meteorological data detection module are designed to be able to work when needed, thereby ensuring the drone's cruising range by reducing the power consumption of these functional modules.

[0087] Example 3:

[0088] This embodiment is further refined based on the embodiment 1:

[0089] The data processing terminal includes a neural network module, and the neural network module is used to implement:

[0090] After the detection data or processed data is transmitted to the data processing terminal, the neural network module uses the neural network model to predict the carbon emission data. When the predicted carbon emission data exceeds the set threshold, the time and location when the carbon emission data exceeds the set threshold output by the neural network model are sent to the route planning module. The route planning module plans the route according to the time and location, so that at the time, the drone carrying the carbon emission detection sensor component flies to the location where the carbon emission data exceeds the set threshold, and collects the carbon content concentration data at the location.

[0091] This solution aims to provide a method for predicting future carbon emissions at a location using a neural network model based on current detection or processing data. When the predicted carbon emissions exceed a set threshold, the time and location at which the carbon emissions exceed the threshold, as output by the neural network model, are sent to a route planning module. The route planning module then enables a drone carrying a carbon emissions detection sensor assembly to fly to the location where the carbon emissions exceed the threshold at that time and collect carbon concentration data at that location. This solution provides a technical solution for efficiently monitoring potential carbon emissions exceeding standards in a region. Those skilled in the art will recognize that the neural network model uses local carbon emission patterns as input for training and outputs the time or location of an anomaly. The neural network model can be a separate substructure on a data processing terminal or a virtual module running on the same data processor or processor cluster, implementing corresponding functions solely through a corresponding computer program. Furthermore, when the route planning module plans routes based on the time and location output by the carbon emissions diffusion model and the neural network model, the planned routes should be understood as serving different functions. Those skilled in the art can prioritize the two routes based on specific needs, enabling the system to implement appropriate action settings based on specific requirements.

[0092] Example 4:

[0093] This embodiment is further refined based on the embodiment 1:

[0094] The drone is a fixed-wing electric drone. This solution aims to provide a technical solution that eliminates carbon emissions while operating, ensuring the accuracy of detection data. Furthermore, fixed-wing drones are a high-flying type of drone, effectively ensuring timely monitoring of carbon emission areas and improving monitoring coverage.

[0095] Example 5:

[0096] This embodiment is further refined based on the embodiment 1:

[0097] It also includes a ground station, and the data connection between the control terminal and the data processing terminal is established through the ground station: when the control terminal needs to send data to the data processing terminal, the data is first received by the ground station, and then the ground station sends the data to the data processing terminal. The ground station also includes a data storage module for completing local storage of the data at the ground station.

[0098] In this solution, the ground station acts as a relay station and is used to monitor carbon emissions in areas without operator mobile signal coverage. For example, multiple ground stations can be deployed at different locations within the monitoring range. Regarding communication between the drone and the ground station, the relative positions of the ground stations are determined based on the set wireless communication type and antenna performance. The data connection between the ground station and the data processing terminal can be achieved through wired communication or a combination of wired and wireless communication (data is transmitted via a wired communication solution to a location where data transmission can be achieved using wireless communication technology). The application of the above data storage module is intended to achieve the following purposes: according to the data communication process, the ground station serves as a node in the complete communication process. After storing relevant data such as detection data on the ground station, it can be used to obtain data source evidence when abnormal human carbon emissions are detected; considering the quality of wireless communication and the cost of setting up the ground station, the ground station does not need to be set up too densely. For example, it is allowed that the drone cannot establish reliable data communication with the ground station during some time periods under the current route. In this case, relevant data such as the control data of the drone from the data processing terminal will be stored locally. When the drone cruises to a position where it can establish wireless communication with a certain ground station, it can send these data to the control terminal of the drone in a relatively delayed manner, thereby improving the setup cost and controllability of the front-end equipment of this system.

[0099] Example 6:

[0100] This embodiment provides a method for realizing carbon emission monitoring based on a drone, including the following steps performed in sequence:

[0101] S1. Obtain detection data through the carbon emission detection sensor component carried on the drone;

[0102] S2. Transmitting the detection data or processed data to a data processing terminal, wherein the processed data is data on carbon emission detection results obtained after processing the detection data;

[0103] S3. The data processing terminal performs clustering processing on the detection data or the processed data to obtain a carbon content concentration data subset divided according to spatial regions;

[0104] S4. Detecting abnormal points on the carbon content concentration data subset: When it is determined that the carbon content concentration data exceeds a set threshold, the detection data collection area corresponding to the carbon content concentration data subset is identified as an abnormal point, and the abnormal point is marked and steps S5 to S7 are executed;

[0105] S5. constructing a carbon emission diffusion model using the obtained multiple carbon content concentration data subsets and meteorological data;

[0106] S6. Plan carbon emission source tracking routes based on the carbon emission diffusion model;

[0107] S7. The drone flies along the tracking route for the purpose of searching for carbon emission sources and collects carbon concentration data and ground image data. As described above, this method can be implemented based on the system described in the above embodiment and shares the same concept as the system. It uses a subset of carbon concentration data to accurately identify anomalies and construct a carbon emission diffusion model. Based on the carbon emission diffusion model, a tracking route is derived to efficiently and accurately identify carbon emission anomalies and effectively complete the carbon emission source search during the mission.

[0108] Example 7:

[0109] This embodiment is further refined based on embodiment 6:

[0110] Before the drone takes off, the mission route of the drone is planned and loaded into the control terminal on the drone. The control terminal controls the drone to fly according to the mission route.

[0111] After step S6 is completed, the mission route is modified based on the tracking route. The drone then flies along the modified mission route under the control of the control terminal. In this solution, the mission route serves as the drone's initial route. After triggering the carbon emission source search, the mission route is modified based on the tracking route. This solution provides a technical solution for automatically completing carbon emission monitoring.

[0112] Example 8:

[0113] This embodiment is further refined based on embodiment 7:

[0114] After step S5 is completed, the location of the carbon emission source is obtained using the carbon emission diffusion model, and the location of the carbon emission source is stored in a data storage device;

[0115] When planning a drone's mission route before takeoff, the carbon emission source locations stored in the data storage device are used as a reference. Similar to the previous embodiments, this solution uses historical carbon emission source location data as a basis for mission route planning. This allows for targeted mission route planning based on the fact that carbon emission sources are generally located in fixed locations or areas, thereby maximizing the efficiency of carbon emission monitoring flights.

[0116] Example 9:

[0117] This embodiment is further refined based on embodiment 6:

[0118] Before the drone takes off, the mission route of the drone is planned and loaded into the control terminal on the drone. The control terminal controls the drone to fly according to the mission route.

[0119] After step S2 is completed, the carbon emission data is predicted using a neural network model. When the predicted carbon emission data exceeds the set threshold, the time and location at which the carbon emission data exceeds the set threshold output by the neural network model are used to adjust the mission route, so that at the time, the drone carrying the carbon emission detection sensor assembly flies to the location where the carbon emission data exceeds the set threshold, and collects the carbon content concentration data at that location. Similar to the solutions provided in the corresponding embodiments above, this solution uses a neural network model to predict the carbon emission data in the later period. When it is predicted that carbon emissions may exceed the standard, the neural network model is used to obtain the time and location of the occurrence of this situation, and the location and time are used as the basis for adjusting the mission route. That is, this solution provides a technical solution that can effectively monitor carbon emissions that may exceed the standard in a region.

[0120] Example 10:

[0121] This embodiment is further refined based on embodiment 6:

[0122] The drone used in step S1 is a fixed-wing electric drone;

[0123] Steps S3 to S6 are completed using a data processing terminal that is remotely connected to the drone;

[0124] The remote data connection includes a ground station as a data relay station. When the ground station transmits data, the ground station locally stores the transmitted data. As described in the corresponding embodiments above, the selection of the drone to be used is intended to adopt a technical solution that has accurate detection data, high monitoring efficiency, and wide monitoring coverage; the setting method of steps S3 to S6 is intended to provide a technical solution that can guarantee data calculation speed and the cruising range of the drone; the setting of the ground station can not only solve the data transmission problem in areas without commercial networks, but also be used for local forensics of detection data and relatively delayed transmission of drone control data.

[0125] Example 11:

[0126] This embodiment provides a further refined technical solution based on any of the above embodiments:

[0127] A system for realizing carbon emission monitoring based on a drone, comprising: a drone terminal including the drone, an intelligent control terminal including the control terminal, and a cloud-based big data processing center including the data processing terminal;

[0128] The drone terminal also includes a camera, a carbon emission detection sensor component, a GPS positioning module component, a drone main controller component, an altimeter, a data storage device, a power supply system, etc.

[0129] The intelligent control terminal predefines a cruising route as a mission route for the drone equipped with the carbon emission detection sensor assembly; during the drone's flight, the carbon emission detection sensor assembly collects carbon dioxide concentration data in the ambient air; the drone's intelligent control terminal collects the carbon content data collected by the sensor and sends it to a cloud-based big data processing center;

[0130] The intelligent control terminal sends predefined instructions to the drone to achieve real-time control of the drone. When tracking carbon emission sources, the intelligent control terminal sends control instructions to the drone, automatically adjusts the drone's flight route planning according to a preset tracking algorithm, and controls the drone to automatically search for carbon emission sources.

[0131] The big data processing center is used to process and analyze collected carbon content data to achieve real-time monitoring of carbon emissions. The big data processing center includes a data preprocessing module, a data clustering module, an outlier detection module, and a database. In this solution, the carbon content data collected by the monitoring device is first preprocessed by the preprocessing module. The data clustering module then clusters the preprocessed carbon content concentration data. The outlier detection module then detects outliers in the clustered carbon content data, labels the resulting outlier points, and stores them in the database.

[0132] Example 12:

[0133] This embodiment provides a further refined technical solution based on embodiment 11:

[0134] First, based on the collected inspection data, the carbon content information of the previous time period is obtained and corrected. At the same time, the carbon emission level within the time period is analyzed to obtain the law of carbon emission changes. Then, based on the above carbon content information and the law of change, a neural network model is established and trained. Next, the corrected carbon content information currently obtained is normalized and then substituted into the neural network model for prediction to obtain the predicted carbon content change under the current carbon content information. When the prediction result exceeds the set maximum carbon emission threshold, the data processing terminal adjusts the mission route according to the time and position when the set maximum carbon emission threshold is exceeded, so that the drone component can return to the predicted position to perform carbon content detection at the said time. This embodiment is: using a neural network model to predict the change of carbon content in the atmosphere, and the neural network model uses the corrected historical carbon content information as input and is trained.

[0135] Example 13:

[0136] This embodiment provides a further refined technical solution based on embodiment 11:

[0137] In the intelligent control terminal and the cloud-based big data processing center, relevant software includes: drone carbon emission monitoring mission planning software, carbon emission sensor data acquisition and processing software, remote sensing RS technology mathematical modeling and simulation calculation and visualization software, forming a mature technical solution for carbon measurement mission planning, carbon measurement data acquisition, processing, data integration and visualization, and obtaining a three-dimensional carbon measurement data pool and a visualization effect of carbon content changes that can change over time.

[0138] Example 14:

[0139] This embodiment provides a further refined technical solution based on embodiment 11:

[0140] The flight paths of drones with GPS positioning, the distribution of carbon content data at each location on the paths, and changes in carbon content are integrated and aggregated to generate massive amounts of carbon emission monitoring data, which are then transmitted to the cloud-based big data processing center for processing and analysis.

[0141] Example 15:

[0142] This embodiment provides a specific embodiment based on embodiment 11:

[0143] A system for carbon emission detection based on drones includes multiple drone devices and a cloud-based big data processing center. Each drone device includes a drone terminal and is connected to the big data processing center. Each drone device is used to collect carbon content data from multiple monitoring nodes within a monitoring area; the big data processing center is used to process and analyze the collected carbon content data and adjust the mission route based on the analysis results, thereby realizing real-time monitoring of carbon content concentration and efficient search for carbon emission sources when necessary.

[0144] The drone collects data through the carbon emission monitoring sensors, cameras, GPS positioning modules and other sensor equipment carried on it, and then transmits the monitored relevant data to the intelligent control terminal and the cloud-based big data processing platform to realize data collection at the perception layer.

[0145] The intelligent control terminal collects data on the transmission plane and uses the ZIGBEE module to transmit the data to a relay station, which then transmits it to the cloud-based big data processing platform, which serves as the service plane. The data collected by the drone reaches the cloud-based big data processing center via the transmission plane for storage, analysis, and processing. Carbon content is monitored and displayed, and, if necessary, the tracking route is calculated and distributed. Users can access carbon content data, drone cruising routes, and carbon emission source monitoring results through mobile terminal applications.

[0146] The intelligent control terminal uses Bluetooth wireless transmission to control the drone's flight and transmission. It receives and analyzes status data sent back by the drone in real time, such as pitch, yaw, and roll information, and sends commands to the drone for real-time control. The inertial navigation module (IMU)'s gyroscope and accelerometer acquire the drone's six degrees of freedom (DOF) information. An attitude calculation algorithm is then used to calculate and display real-time status parameters. The system also displays mission routes and carbon emission source target points or key areas from historical missions on a map.

[0147] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A system for carbon emission monitoring based on drones, characterized in that: Including drones, control terminals, and data processing terminals; It also includes a carbon emission detection sensor component, and the control terminal and the carbon emission detection sensor component are both carried on the drone; The control terminal receives the detection data obtained by the carbon emission detection sensor assembly and transmits the detection data or processed data to the data processing terminal through the wireless data transmission module. The processed data is data on the carbon emission detection results obtained after processing the detection data. The data processing terminal includes a data clustering processing module, which performs clustering processing on the detection data or processing data from the control terminal to obtain a carbon content concentration data subset divided according to spatial regions; The data processing terminal includes an outlier detection module, which performs outlier detection on a subset of carbon content concentration data: when it is determined that the carbon content concentration data therein exceeds a set threshold, the detection data collection area corresponding to the subset of carbon content concentration data is identified as an outlier, and the obtained outlier is marked; The data processing terminal includes a model building module. When it is determined that there is an abnormal point, the model building module uses the obtained carbon content concentration data subset and meteorological data to build a carbon emission diffusion model; The data processing terminal includes a route planning module, which uses a carbon emission diffusion model to perform carbon emission source tracking route planning; The data processing terminal includes a wireless data transmission module for transmitting the tracking route data to the control terminal, and the control terminal controls the route of the UAV for the purpose of searching for carbon emission sources based on the tracking route data; The data processing terminal includes a neural network module, and the neural network module is used to implement: After the detection data or processed data is transmitted to the data processing terminal, the neural network module uses the neural network model to predict the carbon emission data. When the predicted carbon emission data exceeds the set threshold, the time and location when the carbon emission data exceeds the set threshold output by the neural network model are sent to the route planning module. The route planning module plans the route according to the time and location, so that at the time, the drone carrying the carbon emission detection sensor component flies to the location where the carbon emission data exceeds the set threshold, and collects the carbon content concentration data at the location.

2. The system for carbon emission monitoring based on drones according to claim 1 is characterized in that: The drone is also equipped with a camera for image acquisition, a meteorological data detection module for meteorological data acquisition, and a data storage device for storing the location of carbon emission sources; The camera and the meteorological data detection module are both data-connected to the control terminal, and both the camera and the meteorological data detection module operate under the control of the control terminal; After the carbon emission diffusion model is constructed, the data processing terminal sends the location of the carbon emission source to the control terminal, and the control terminal is data-connected to the data storage device to store the location of the carbon emission source in the data storage device.

3. The system for carbon emission monitoring based on drones according to claim 1 is characterized in that: The UAV is a fixed-wing electric UAV.

4. The system for carbon emission monitoring based on drones according to claim 1 is characterized in that: It also includes a ground station, and the data connection between the control terminal and the data processing terminal is established through the ground station: when the control terminal needs to send data to the data processing terminal, the data is first received by the ground station, and then the ground station sends the data to the data processing terminal. The ground station also includes a data storage module for completing local storage of the data at the ground station.

5. A method for carbon emission monitoring based on drones, characterized in that: The process includes the following steps, performed in sequence: S1. Obtain detection data through the carbon emission detection sensor component carried on the drone; S2. Transmitting the detection data or processed data to a data processing terminal, wherein the processed data is data on carbon emission detection results obtained after processing the detection data; S3. The data processing terminal performs clustering processing on the detection data or the processed data to obtain a carbon content concentration data subset divided according to spatial regions; S4. Detecting abnormal points on the carbon content concentration data subset: When it is determined that the carbon content concentration data exceeds a set threshold, the detection data collection area corresponding to the carbon content concentration data subset is identified as an abnormal point, and the abnormal point is marked and steps S5 to S7 are executed; S5. constructing a carbon emission diffusion model using the obtained multiple carbon content concentration data subsets and meteorological data; S6. Plan carbon emission source tracking routes based on the carbon emission diffusion model; S7. The UAV flies along the tracking route for the purpose of searching for carbon emission sources and collecting carbon content concentration data and ground image data; Before the drone takes off, the mission route of the drone is planned and loaded into the control terminal on the drone. The control terminal controls the drone to fly according to the mission route. After step S2 is completed, the carbon emission data is predicted using the neural network model. When the predicted carbon emission data exceeds the set threshold, the time and location when the carbon emission data exceeds the set threshold output by the neural network model are used to adjust the mission route, so that at the said time, the drone carrying the carbon emission detection sensor assembly flies to the location where the carbon emission data exceeds the set threshold, and collects the carbon content concentration data at that location.

6. The method for realizing carbon emission monitoring based on drone according to claim 5, characterized in that: Before the drone takes off, the mission route of the drone is planned and loaded into the control terminal on the drone. The control terminal controls the drone to fly according to the mission route. After step S6 is completed, the mission route is changed according to the tracking route, and then the UAV flies according to the changed mission route under the control of the control terminal.

7. The method for realizing carbon emission monitoring based on drone according to claim 6, characterized in that: After step S5 is completed, the location of the carbon emission source is obtained using the carbon emission diffusion model, and the location of the carbon emission source is stored in a data storage device; When planning a mission route before the UAV takes off, the location of the carbon emission source in the data storage device is used as a reference for mission route planning.

8. The method for realizing carbon emission monitoring based on a drone according to any one of claims 5 to 7, characterized in that: The drone used in step S1 is a fixed-wing electric drone; Steps S3 to S6 are completed using a data processing terminal that is remotely connected to the drone; The remote data connection includes a ground station serving as a data relay station. When the ground station transmits data, the ground station stores the transmitted data locally.

Images