Near space detection method, device and equipment based on cooperation of multiple unmanned aerial vehicles, and storage medium

Abstract

The invention discloses a near space detection method, device and equipment based on cooperation of multiple unmanned aerial vehicles, and a storage medium, and the method comprises the steps: carrying out the region division of a near space according to a meteorological detection task, generating a plurality of detection regions, and determining the number of unmanned aerial vehicles needed by each detection region; distributing each unmanned aerial vehicle in the unmanned aerial vehicle network to a corresponding detection area according to the performance parameters of the unmanned aerial vehicles and the number of the unmanned aerial vehicles; the unmanned aerial vehicles carry out cooperative detection in the corresponding detection areas to obtain meteorological detection data; carrying out fusion processing on the meteorological detection data to generate meteorological data of a near space; predicting through a weather prediction model according to the weather data to obtain a weather change trend; according to the invention, meteorological early warning is carried out according to the meteorological change trend, efficient and accurate detection of near space meteorological data is realized through cooperative operation of the unmanned aerial vehicle, meteorological prediction is accurately carried out through the meteorological prediction model, meteorological early warning is timely carried out, and risks caused by meteorological disasters are effectively reduced.

Description

Technical Field

[0001] The present application relates to the field of data detection, and in particular to a near-space detection method, device, equipment and storage medium based on multi-UAV collaboration. Background Art

[0002] With the development of science and technology and the continuous advancement of drone technology, drone-based meteorological data detection has become a key means of meteorological monitoring. Traditional meteorological detection relies on ground-based weather stations and satellite observations. Although these methods can provide relatively comprehensive meteorological data, they still suffer from limited coverage, poor real-time performance, and incomplete data acquisition when monitoring near-space areas.

[0003] To overcome these limitations, recent research has begun applying drone technology to meteorological observation, particularly for near-space meteorological data collection. Drones can collect real-time data within a designated area, offering advantages such as high flexibility, rapid response, and low cost. However, traditional drone-based meteorological data detection methods often face the problem of multiple drones performing repeated detections in adjacent areas, resulting in low detection efficiency, data redundancy, and even insufficient data collection for certain key areas, making it impossible to fully and accurately reflect the meteorological conditions in near-space. Summary of the Invention

[0004] The main purpose of this application is to provide a near-space detection method, device, equipment and storage medium based on multi-UAV collaboration, aiming to solve the technical problems of repeated detection in traditional meteorological detection, resulting in low detection efficiency and incomplete data, and unable to accurately reflect the meteorological conditions in near space.

[0005] To achieve the above objectives, the present application proposes a near-space detection method based on multi-UAV collaboration, which includes:

[0006] Divide the near space into regions according to the meteorological detection mission, generate multiple detection areas and determine the number of drones required for each detection area;

[0007] Allocate each drone in the drone network to a corresponding detection area according to the performance parameters of the drone and the number of drones required for each detection area;

[0008] The UAVs perform coordinated detection in corresponding detection areas to obtain meteorological detection data corresponding to each detection area;

[0009] Fusing the meteorological detection data corresponding to each detection area to generate meteorological data of the adjacent space;

[0010] According to the meteorological data of the near space, a forecast is made using a meteorological forecast model to obtain a meteorological change trend of the near space;

[0011] A weather warning is issued based on the weather change trend in the near space.

[0012] In one embodiment, dividing the adjacent space into regions according to the meteorological detection mission, generating multiple detection regions, and determining the number of drones required for each detection region includes:

[0013] Obtaining meteorological detection requirements, and generating multiple meteorological detection tasks based on the detection requirements;

[0014] Determine the scope of the corresponding detection area according to the mission objectives of each of the meteorological detection tasks;

[0015] Dividing the adjacent space into a plurality of non-overlapping detection areas according to the range of the corresponding detection area, wherein each of the detection areas corresponds to one or more meteorological detection tasks;

[0016] The number of drones required for each detection area is determined based on the meteorological detection mission of each detection area and the endurance of the drone.

[0017] In one embodiment, allocating each drone in the drone network to a corresponding detection area based on the performance parameters of the drone and the number of drones required for each detection area includes:

[0018] Determine the flight speed, flight altitude, endurance, communication range, and payload capacity of the drone based on its performance parameters;

[0019] Obtain the area, height distribution, mission frequency, and mission duration of each detection area;

[0020] Performing a compatibility evaluation on each UAV in the UAV network based on the flight speed, flight altitude, endurance, communication range, payload capacity, and the area, altitude distribution, mission frequency, and mission duration of each detection area of ​​the UAV to obtain a compatibility degree;

[0021] According to the adaptability, each drone in the drone network is assigned to a corresponding detection area in order of priority.

[0022] In one embodiment, the obtaining of meteorological detection data corresponding to each detection area by each of the drones performing collaborative detection in the corresponding detection area includes:

[0023] Performing path planning for the UAVs in each detection area to obtain a target flight path for the UAVs in each detection area;

[0024] Controlling each of the UAVs to fly in a corresponding detection area according to the target flight path and perform a corresponding meteorological detection mission, and generating mission progress information for each UAV;

[0025] Sharing the task progress information of each drone through a drone network, and scheduling tasks for each drone based on the task progress information;

[0026] After detecting that each of the UAVs has completed the corresponding meteorological detection mission, the original detection data obtained when each of the UAVs performs the meteorological detection mission in the corresponding detection area is collected, and the original detection data is preprocessed to obtain the meteorological detection data corresponding to each detection area.

[0027] In one embodiment, performing path planning for the drones in each detection area to obtain a target flight path for the drones in each detection area includes:

[0028] When there are multiple drones in the detection area, generating an initial flight path for the drones in the detection area according to the take-off position of each drone, the target detection point, and the boundary conditions of the detection area;

[0029] Perform dynamic collision avoidance according to the initial flight path to generate a collision-free flight path;

[0030] Using the collision-free flight path as the initial population;

[0031] Performing fitness evaluation on individuals in the initial population according to the flight distance, flight time, energy consumption, and mission completion of the collision-free flight path to obtain fitness values ​​of the individuals in the initial population;

[0032] selecting individuals from the initial population as parents according to the fitness values, and performing selection, crossover and mutation operations on the parents to generate a new population;

[0033] The new population is used as the initial population, and the step of performing fitness evaluation on the individuals in the initial population according to the flight distance, flight time, energy consumption, and mission completion of the collision-free flight path to obtain the fitness values ​​of the individuals in the initial population is re-executed until a preset convergence condition is met or a maximum number of iterations is reached, thereby obtaining the target flight path of the UAV.

[0034] In one embodiment, the fusing of the meteorological detection data corresponding to each detection area to generate meteorological data of a nearby space includes:

[0035] Performing data preprocessing according to the type, format, and resolution of the meteorological detection data of each detection area to obtain preprocessed meteorological detection data of each detection area, wherein the preprocessing at least includes data format conversion, resolution unification, and abnormal data removal;

[0036] Performing spatiotemporal fusion on the pre-processed meteorological detection data of each detection area to obtain fused meteorological detection data;

[0037] Performing spatiotemporal interpolation processing on the fused meteorological detection data to obtain spatiotemporally continuous near-space meteorological data;

[0038] The formula for space-time fusion is:

[0039]

[0040] Where D(t,r) is the fused meteorological detection data, which represents the final result at time t and location r. i is the number of different meteorological detection areas, ranging from 1 to N (there are N detection areas in total). j is the number of the detection point in detection area i, ranging from 1 to M (there are M detection points in each detection area). W i (t) is the time weighting factor of detection area i at time t, ω ij (t, r) is the spatial weight between detection area i and detection point j at time t and spatial position r, D ij (t) is the meteorological detection data of detection point j in detection area i at time t.

[0041] In one embodiment, the weather forecast model is:

[0042]

[0043] Where D(t+1,r) represents the meteorological data forecast result at time t+1 and spatial position r, i is the number of different meteorological detection areas, ranging from 1 to N (there are N detection areas in total), j is the number of the detection point in detection area i, ranging from 1 to M (there are M detection points in each detection area), ω ij (t, r) represents the spatial weight of the detection area i and the detection point j to the target position r in the adjacent space, D ij (t) is the meteorological detection data of detection point j in meteorological detection area i at time t, f(D ij (t), r, t) represents the meteorological detection data D ij (t), spatial position r and time t to predict the meteorological change trend in nearby space.

[0044] In addition, to achieve the above-mentioned purpose, the present application also proposes a near-space detection device based on multi-UAV collaboration, the near-space detection device based on multi-UAV collaboration comprising:

[0045] The division module is used to divide the adjacent space into regions according to the meteorological detection mission, generate multiple detection areas and determine the number of drones required for each detection area;

[0046] An allocation module is used to allocate each drone in the drone network to a corresponding detection area according to the performance parameters of the drone and the number of drones required for each detection area;

[0047] A detection module is used to perform coordinated detection in corresponding detection areas by each of the drones to obtain meteorological detection data corresponding to each detection area;

[0048] A fusion module is used to fuse the meteorological detection data corresponding to each detection area to generate meteorological data of the adjacent space;

[0049] A prediction module, configured to perform predictions based on the meteorological data of the near space using a meteorological prediction model to obtain a meteorological change trend of the near space;

[0050] The early warning module is used to issue a weather early warning based on the weather change trend of the nearby space.

[0051] In addition, to achieve the above-mentioned purpose, the present application also proposes a near-space detection device based on multi-UAV collaboration, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the near-space detection method based on multi-UAV collaboration as described above.

[0052] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the near-space detection method based on multi-UAV collaboration as described above are implemented.

[0053] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the near-space detection method based on multi-UAV collaboration as described above.

[0054] One or more technical solutions proposed in this application divide the near space into regions according to the meteorological detection task, generate multiple detection regions and determine the number of drones required for each detection region; assign each drone in the drone network to the corresponding detection region according to the performance parameters of the drone and the number of drones required for each detection region; obtain meteorological detection data corresponding to each detection region by having each drone perform collaborative detection in the corresponding detection region; fuse the meteorological detection data corresponding to each detection region to generate meteorological data of the near space; predict the meteorological change trend of the near space through a meteorological prediction model based on the meteorological data of the near space; and issue a meteorological warning based on the meteorological change trend of the near space. In the above manner, by dividing the near space into multiple detection regions, drones perform meteorological data detection in the assigned detection regions, which can avoid repeated detection of the same area and improve the efficiency of data detection. Then, meteorological forecasts and timely meteorological warnings are made based on the meteorological data of the near space that is integrated with the detection data of multiple regions, effectively improving the accuracy of meteorological forecasts and reducing the risks brought by meteorological disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0056] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0057] Figure 1 A flowchart of the first embodiment of the near-space detection method based on multi-UAV collaboration provided in this application;

[0058] Figure 2 A flowchart of the second embodiment of the near-space detection method based on multi-UAV collaboration provided in this application;

[0059] Figure 3 This is a schematic diagram of the module structure of a near-space detection device based on multi-UAV collaboration in an embodiment of the present application;

[0060] Figure 4 This is a schematic diagram of the device structure of the hardware operating environment involved in the near-space detection device based on multi-UAV collaboration in an embodiment of the present application.

[0061] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0062] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0063] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0064] The main solutions of the embodiments of the present application are: dividing the near space into regions according to the meteorological detection tasks, generating multiple detection areas and determining the number of drones required for each detection area; allocating each drone in the drone network to the corresponding detection area according to the performance parameters of the drone and the number of drones required for each detection area; obtaining meteorological detection data corresponding to each detection area by having each drone perform collaborative detection in the corresponding detection area; fusing the meteorological detection data corresponding to each detection area to generate meteorological data of the near space; making predictions based on the meteorological data of the near space through a meteorological prediction model to obtain the meteorological change trend of the near space; and issuing meteorological warnings based on the meteorological change trend of the near space.

[0065] Traditional drone-based meteorological data detection methods often face the problem of multiple drones performing repeated detections in adjacent areas, resulting in low detection efficiency, data redundancy, and even insufficient meteorological data collection in certain key areas, making it impossible to fully and accurately reflect the meteorological conditions in the adjacent space.

[0066] This application provides a solution. By dividing the near-space into multiple detection areas, drones perform meteorological data detection in the assigned detection areas, which can avoid repeated detection of the same area and improve the efficiency of data detection. Then, based on the meteorological data of the near-space that integrates the detection data of multiple areas, meteorological forecasts and timely meteorological warnings are made, which effectively improves the accuracy of meteorological forecasts and reduces the risks brought by meteorological disasters.

[0067] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of implementing the above functions, a near-space detection device based on multi-UAV collaboration, etc. The following uses the near-space detection device based on multi-UAV collaboration as an example to illustrate this embodiment and the following embodiments.

[0068] Based on this, the embodiment of the present application provides a near space detection method based on multi-UAV collaboration, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the near-space detection method based on multi-UAV collaboration of this application.

[0069] In this embodiment, the near-space detection method based on multi-UAV collaboration includes steps S10 to S60:

[0070] Step S10: Divide the adjacent space into regions according to the meteorological detection mission, generate multiple detection regions, and determine the number of drones required for each detection region.

[0071] It should be noted that near-space refers to airspace within a certain altitude range. In this embodiment, near-space refers to the airspace between 20 and 100 kilometers above the ground. Meteorological detection tasks consist of different meteorological elements (such as temperature, humidity, wind speed, and wind direction), including temperature detection tasks, wind speed and direction detection tasks, cloud monitoring tasks, and precipitation monitoring tasks. This embodiment does not impose specific limitations on these tasks.

[0072] Specifically, the meteorological detection mission will be determined according to the meteorological detection needs. According to the needs of the meteorological detection mission, the nearby space will be divided into different detection areas. Each detection area can correspond to different meteorological elements or different detection priorities. According to the meteorological detection needs of each detection area, the number of drones required for each detection area will be determined.

[0073] In a feasible embodiment, step S10 may include: obtaining meteorological detection requirements, generating multiple meteorological detection tasks based on the detection requirements; determining the scope of the corresponding detection area according to the task objectives of each meteorological detection task; dividing the adjacent space into multiple non-overlapping detection areas according to the scope of the corresponding detection area, wherein each detection area corresponds to one or more meteorological detection tasks; determining the number of drones required for each detection area according to the meteorological detection tasks of each detection area and the endurance of the drone.

[0074] It should be noted that meteorological detection requirements are composed of detection targets, detection time and detection accuracy requirements. Among them, the detection target is the meteorological elements to be monitored, such as temperature (ground temperature, air temperature distribution, etc.), humidity (air humidity, dew point temperature), air pressure (ground pressure, air pressure at each altitude layer), wind speed and direction (wind speed, wind direction change, wind field), precipitation (precipitation intensity, precipitation type), cloud conditions (cloud height, cloud amount, cloud type, etc.), radiation (solar radiation, long-wave radiation, etc.), etc.; the detection time is used to determine the time frequency of detection, such as real-time monitoring, periodic monitoring and emergency monitoring; the detection accuracy is the accuracy and resolution requirements of meteorological data.

[0075] It should be understood that the meteorological detection requirements may include one or more meteorological elements to be monitored, and one or more meteorological detection tasks can be generated based on the meteorological elements to be monitored. Each meteorological detection task corresponds to a specific detection target, detection time, and detection accuracy requirement. For example, if the meteorological detection requirements include monitoring temperature and wind speed, two meteorological detection tasks can be generated, one is a temperature detection task, and the other is a wind speed detection task. These two tasks may have different detection time frequency and accuracy requirements. According to the objectives and requirements of these tasks, the scope of the corresponding detection area can be determined and these detection areas can be set to be non-overlapping to ensure that the meteorological data of each detection area can be collected independently and accurately. The size of each detection area depends on the requirements of the corresponding meteorological detection task. For example, for temperature detection tasks, a larger detection area may be required to obtain more comprehensive temperature distribution data; for wind speed and wind direction detection tasks, a smaller detection area may be required to obtain more detailed wind field information.

[0076] Specifically, the near space is divided into multiple non-overlapping detection areas based on the detection area range of each detection mission, and the number of drones required for each detection area is determined based on the requirements of the meteorological detection mission and the drone's endurance. For example, for temperature detection missions, it may be necessary to divide the near space into different altitude layers, set up corresponding detection areas at each altitude layer, and determine the number of drones required for each detection area based on the accuracy requirements of temperature detection and the drone's endurance. For wind speed and wind direction detection missions, it may be necessary to divide the near space into different wind direction belts or wind speed areas, set up corresponding detection points within these areas, and determine the number of drones and detection frequency based on the accuracy requirements of wind speed and wind direction detection and the drone's endurance.

[0077] It should be understood that by comprehensively considering the needs of the meteorological detection mission, the performance of the UAV and the characteristics of the detection area, UAV resources can be reasonably allocated to ensure that each detection area can be fully detected and covered.

[0078] Step S20: allocating each drone in the drone network to a corresponding detection area according to the performance parameters of the drone and the number of drones required for each detection area.

[0079] It's important to note that drone performance parameters refer to a drone's flight speed, altitude, endurance, payload capacity, detection accuracy, and communication capabilities. These parameters directly impact its performance during detection missions. For example, flight speed and endurance determine the range of detection areas a drone can cover; payload capacity determines the type and quantity of detection equipment a drone can carry, which in turn affects the accuracy and comprehensiveness of detection; detection accuracy directly determines the accuracy of meteorological data; and communication capabilities determine the efficiency and stability of data transmission between the drone and the command center.

[0080] It's understood that a drone network is a collaborative system consisting of multiple drones interconnected via a communication network. Each drone within the network can share information and collaborate on tasks, thereby improving the detection efficiency and accuracy of the entire system. A drone network can include a variety of different types of drones, such as fixed-wing, rotary-wing, and hybrid models, each with different performance parameters and applicable scopes. When assigning drones to specific detection areas, it's important to consider whether the drone's performance parameters match the requirements of the area. For example, for missions requiring rapid, large-scale detection, a fixed-wing drone with high speed and endurance can be selected; for missions requiring high-precision detection, a rotary-wing drone with high payload capacity and high detection accuracy can be selected. Through appropriate allocation, each drone can be maximized within the detection area best suited to its performance parameters, thereby improving the efficiency and accuracy of the entire detection mission.

[0081] In specific implementation, the drones in the drone network can be reasonably allocated to the corresponding detection areas based on the meteorological detection requirements of each detection area and the performance parameters of the drones, so as to ensure that each detection area can be fully detected and covered, while maximizing the performance advantages of the drones.

[0082] In a feasible embodiment, step S20 may include: determining the flight speed, flight altitude, endurance, communication range and load capacity of the drone based on the performance parameters of the drone; obtaining the area, height distribution, mission frequency and mission duration of each detection area; performing adaptability evaluation on each drone in the drone network based on the flight speed, flight altitude, endurance, communication range, load capacity and the area, height distribution, mission frequency and mission duration of each detection area to obtain adaptability; and allocating each drone in the drone network to the corresponding detection area in order of priority based on the adaptability.

[0083] It should be noted that the characteristics of the detection area, such as its size, altitude distribution, mission frequency, and mission duration, will directly influence the selection and allocation of drones. Larger detection areas may require drones with high flight speeds and long endurance to ensure comprehensive coverage; detection areas with complex altitude distribution may require drones that can flexibly adjust their flight altitude; detection areas with high mission frequency require drones with short takeoff preparation times and high data transmission efficiency; and detection areas with long mission durations require drones with long endurance and stable communication capabilities.

[0084] Specifically, during the suitability assessment process, each drone's performance parameters are compared against the requirements of each detection area, calculating each drone's suitability within each detection area. Suitability is a comprehensive score that considers flight speed, altitude, endurance, communication range, payload capacity, and detection area characteristics. A higher score indicates a drone's superior performance within that detection area.

[0085] It is worth noting that after the compatibility assessment is completed, each drone in the drone network can be assigned to the corresponding detection area in order of priority based on the compatibility. The priority order can be determined according to actual needs. For example, drones with high compatibility can be assigned to detection areas with high mission importance or high detection difficulty to ensure that these areas can be fully detected and covered. Through this allocation method, the performance advantages of drones can be maximized, improving the efficiency and accuracy of the entire detection mission.

[0086] Step S30: The UAVs perform collaborative detection in corresponding detection areas to obtain meteorological detection data corresponding to each detection area.

[0087] It's understandable that when drones conduct collaborative surveys within their respective detection areas, they use a variety of onboard meteorological sensors, such as temperature, humidity, and wind speed and direction sensors, to collect real-time meteorological data within the detection area. These sensors accurately measure various meteorological elements, ensuring the accuracy and reliability of the data. Furthermore, drones share information and collaborate via a communication network, ensuring efficient and orderly data collection across each detection area.

[0088] Specifically, during collaborative detection, drones will conduct comprehensive and detailed coverage of the detection area based on the planned detection path and detection frequency, ensuring that every detection point is fully detected and avoiding data omissions or redundancy. Furthermore, drones can dynamically adjust detection paths and detection frequencies based on real-time meteorological data and forecast models to respond to sudden weather events or improve detection efficiency.

[0089] Step S40: performing fusion processing on the meteorological detection data corresponding to each detection area to generate meteorological data of the adjacent space.

[0090] It should be noted that fusion processing refers to the integration of meteorological data from various detection areas to obtain more comprehensive, accurate, and reliable near-space meteorological data. During the fusion process, factors such as the data characteristics of each detection area, the accuracy and reliability of the detection sensors, and the detection path and frequency of the drone are considered. Appropriate algorithms and models are used to process the data. For example, methods such as weighted averaging, Kalman filtering, or neural networks can be used to fuse data from various detection areas to improve data accuracy and reliability.

[0091] In a feasible embodiment, step S30 may include: performing data preprocessing according to the type, format and resolution of the meteorological detection data of each detection area to obtain the preprocessed meteorological detection data of each detection area, wherein the preprocessing at least includes data format conversion, resolution unification and abnormal data elimination; performing spatiotemporal fusion on the preprocessed meteorological detection data of each detection area to obtain fused meteorological detection data; performing spatiotemporal interpolation processing on the fused meteorological detection data to obtain spatiotemporally continuous adjacent space meteorological data.

[0092] It should be noted that since meteorological data from various detection areas may come from different types of sensors with different data types, formats, and resolutions, they need to be preprocessed before fusion processing to ensure data consistency and comparability. The data preprocessing process includes at least data format conversion, resolution unification, and abnormal data removal. Data format conversion converts data of different formats into a unified format for subsequent processing; resolution unification resamples or interpolates data of different resolutions to obtain data of the same resolution; and abnormal data removal uses statistical methods or expert experience to identify and remove abnormal data that significantly deviates from the normal range to improve data accuracy and reliability.

[0093] It can be understood that spatiotemporal fusion refers to the integration of meteorological detection data from various detection areas in time and space to form a continuous meteorological data field. This process needs to consider factors such as the spatiotemporal distribution characteristics of the data, the accuracy of the detection sensors, and the sampling frequency to ensure that the fused data can truly reflect the meteorological conditions in the adjacent space. In the spatiotemporal fusion process, various advanced algorithms and models can be used, such as spatiotemporal kriging interpolation and dynamic weighted averaging, to improve the fusion effect and accuracy of the data. In this embodiment, the spatiotemporal fusion formula is:

[0094]

[0095] Where D(t,r) is the fused meteorological detection data, which represents the final result at time t and location r. i is the number of different meteorological detection areas, ranging from 1 to N (there are N detection areas in total). j is the number of the detection point in detection area i, ranging from 1 to M (there are M detection points in each detection area). W i (t) is the time weighting factor of detection area i at time t, ω ij (t, r) is the spatial weight between detection area i and detection point j at time t and spatial position r, D ij (t) is the meteorological detection data of detection point j in detection area i at time t.

[0096] Spatiotemporal interpolation further refines the fused meteorological data to produce spatiotemporally continuous near-space meteorological data. This process involves analyzing the spatiotemporal distribution characteristics of the data and employing appropriate interpolation methods, such as linear interpolation, nonlinear interpolation, or interpolation based on physical models, to fill gaps or improve the spatiotemporal resolution of the data. Spatiotemporal interpolation yields more detailed, continuous, and accurate meteorological data.

[0097] Step S50: performing a prediction using a meteorological prediction model based on the meteorological data of the near space to obtain a meteorological change trend of the near space.

[0098] It should be noted that the weather forecast model is built based on big data and machine learning algorithms. It automatically learns and extracts the patterns and characteristics of weather changes based on input near-space weather data, thereby predicting future weather trends. During training, the model fully utilizes historical weather data, numerical weather forecast data, and other relevant data sources, and through continuous iteration and optimization, it improves the accuracy and reliability of forecasts.

[0099] It is understandable that after inputting the meteorological data of the near space into the meteorological forecast model, the model will extract the key information and features hidden behind the data based on its internal complex algorithms and logic, according to factors such as the relationship between various meteorological elements, the law of temporal evolution, and spatial distribution characteristics. Based on this information and features, the model will predict future meteorological change trends and generate corresponding forecast results. The formula of the meteorological forecast model is:

[0100]

[0101] Where D(t+1,r) represents the meteorological data forecast result at time t+1 and spatial position r, i is the number of different meteorological detection areas, ranging from 1 to N (there are N detection areas in total), j is the number of the detection point in detection area i, ranging from 1 to M (there are M detection points in each detection area), ω ij (t, r) represents the spatial weight of the detection area i and the detection point j to the target position r in the adjacent space, D ij (t) is the meteorological detection data of detection point j in meteorological detection area i at time t, f(D ij (t), r, t) represents the meteorological detection data D ij (t), spatial position r and time t to predict the meteorological change trend in nearby space.

[0102] Step S60: issuing a weather warning based on the weather change trend in the nearby space.

[0103] It should be noted that meteorological warnings are based on the meteorological change trends in the near space, combined with preset meteorological warning rules and thresholds, to provide early warnings of possible extreme weather or meteorological disasters.

[0104] It should be understood that during the meteorological warning process, the meteorological change trends in the near space are analyzed in real time and compared with the preset warning rules. Once the data reaches or exceeds the warning threshold, the warning mechanism is immediately triggered, and the warning information is sent to relevant personnel or institutions in a timely manner through SMS, email, APP push, etc., to reduce the losses and impacts caused by meteorological disasters.

[0105] This embodiment provides a near-space detection method based on multi-UAV collaboration, which divides the near-space into regions according to the meteorological detection task, generates multiple detection regions and determines the number of UAVs required for each detection region; allocates each UAV in the UAV network to the corresponding detection region according to the performance parameters of the UAV and the number of UAVs required for each detection region; obtains meteorological detection data corresponding to each detection region by each UAV performing collaborative detection in the corresponding detection region; fuses the meteorological detection data corresponding to each detection region to generate meteorological data for the near-space; predicts the meteorological change trend of the near-space based on the meteorological data of the near-space using a meteorological prediction model; and issues meteorological warnings based on the meteorological change trend of the near-space. In the above manner, by dividing the near-space into multiple detection regions, the UAVs perform meteorological data detection in the assigned detection regions, which can avoid repeated detection of the same area and improve the efficiency of data detection. Then, based on the meteorological data of the near-space that is integrated with the detection data of multiple regions, meteorological forecasts are made and meteorological warnings are issued in a timely manner, effectively improving the accuracy of meteorological forecasts while reducing the risks brought by meteorological disasters.

[0106] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2 , step S30 includes steps S301 to S304:

[0107] Step S301: Path planning is performed on the UAVs in each detection area to obtain the target flight path of the UAVs in each detection area.

[0108] It should be noted that path planning is based on factors such as the meteorological detection requirements of each detection area, the performance parameters of the UAV, and flight restrictions. Combined with the UAV's take-off point, detection point, flight altitude, speed, and heading, advanced algorithms and optimization techniques are used to calculate the optimal flight path of the UAV in the detection area. This path can ensure that the UAV can complete its mission while saving flight time and energy consumption as much as possible, thereby improving detection efficiency.

[0109] It is understandable that when planning the path, the flight safety of the drone must also be considered to avoid collisions with other drones or obstacles and ensure the smooth progress of the flight. Through path planning, the drone can perform orderly meteorological data detection in the detection area according to the predetermined flight path.

[0110] In a feasible embodiment, step S301 may include: when there are multiple drones in the detection area, generating an initial flight path for the drones in the detection area according to the take-off position, target detection point and boundary conditions of each drone; performing dynamic collision avoidance according to the initial flight path to generate a collision-free flight path; using the collision-free flight path as an initial population; performing fitness evaluation on individuals in the initial population according to the flight distance, flight time, energy consumption and task completion of the collision-free flight path to obtain fitness values ​​of individuals in the initial population; selecting individuals from the initial population as parents according to the fitness values, and performing selection, crossover and mutation operations on the parents to generate a new population; using the new population as the initial population, and re-executing the step of performing fitness evaluation on individuals in the initial population according to the flight distance, flight time, energy consumption and task completion of the collision-free flight path to obtain fitness values ​​of individuals in the initial population, until a preset convergence condition is met or the maximum number of iterations is reached, thereby obtaining the target flight path of the drone.

[0111] It should be noted that when there are multiple drones in the detection area, there may be situations where their paths intersect or overlap. To effectively avoid this, detailed design and calculation are required during the path planning phase. When generating the drone's initial flight path, the flight trajectories of other drones need to be taken into account to ensure that a safe distance is maintained between the paths of each drone. In addition, during the dynamic collision avoidance phase, by monitoring the drone's flight status and location information in real time, the flight path can be adjusted in a timely manner to avoid potential collision risks. Through this series of measures, it can be ensured that when multiple drones conduct collaborative detection in the detection area, they can not only complete the task efficiently, but also ensure the safety and reliability of the flight.

[0112] It is understood that during dynamic collision avoidance, advanced collision detection algorithms are used to monitor the relative positions and speeds of drones in real time, predict potential collision risks, and implement appropriate collision avoidance strategies, such as adjusting flight altitude, speed, or heading, to prevent collisions. Furthermore, to ensure efficient and accurate path planning, parallel or distributed computing can be used to simultaneously optimize the flight paths of multiple drones, improving computational speed and optimization effectiveness, thereby generating collision-free flight paths.

[0113] It should be understood that after generating a collision-free flight path, it is further optimized using a genetic algorithm to obtain the optimal flight path. Genetic algorithms, as search algorithms that simulate natural selection and genetic mechanisms, continuously and iteratively optimize individuals within a population through operations such as selection, crossover, and mutation, thereby gradually approaching the optimal solution. In this embodiment, the collision-free flight path serves as the initial population for the genetic algorithm. The fitness of individuals is evaluated based on metrics such as flight distance, flight time, energy consumption, and mission completion. Individuals with higher fitness are selected as parents for genetic manipulation to generate a new population. Through continuous iterative optimization until the preset convergence conditions are met or the maximum number of iterations is reached, the target flight path for the UAV is ultimately obtained. This target flight path maximizes detection efficiency and reduces energy consumption while ensuring safe flight, thereby meeting the requirements of the meteorological detection mission.

[0114] Step S302: Control each of the UAVs to fly in a corresponding detection area according to the target flight path and perform a corresponding meteorological detection mission, and generate mission progress information for each UAV.

[0115] It should be noted that when the drone is controlled to fly along the target flight path, the meteorological detection equipment on board the drone will collect real-time meteorological data, such as temperature, humidity, air pressure, wind speed, wind direction, etc. During the flight, the drone will also generate mission progress information, including current location, explored area, and remaining mission quantity.

[0116] Step S303: sharing the task progress information of each drone through the drone network, and performing task scheduling on each drone according to the task progress information.

[0117] It's important to note that each drone in the drone network can share mission progress information in real time via wireless communication. If a drone completes its mission early or detects unusual weather conditions, the system can use this shared mission progress information to promptly adjust the detection missions of other drones, achieving more efficient weather data detection. For example, if a drone completes its detection mission early, it can be deployed to provide support to an unfinished detection area. Alternatively, if a drone detects unusual weather conditions, other drones can be directed to focus detection on that area to obtain more detailed weather data. This task scheduling method can further improve the efficiency and accuracy of weather data detection.

[0118] Step S304: After detecting that each of the UAVs has completed the corresponding meteorological detection mission, the original detection data obtained when each of the UAVs performs the meteorological detection mission in the corresponding detection area is collected, and the original detection data is preprocessed to obtain meteorological detection data corresponding to each detection area.

[0119] It should be noted that when it is detected that all drones have completed the corresponding meteorological detection tasks, the original detection data obtained by each drone in the detection area are collected, including various meteorological parameters such as temperature, humidity, air pressure, wind speed, and wind direction.

[0120] Understandably, raw detection data may contain various noise and outliers, which can affect subsequent data analysis and weather forecast results. To improve the accuracy and efficiency of data processing, this raw detection data needs to be preprocessed to eliminate noise and outliers, thereby enhancing data quality and reliability. Preprocessing steps may include data cleaning, denoising, calibration, and interpolation to eliminate outliers, missing values, or errors, thereby improving data reliability and consistency.

[0121] In this embodiment, the target flight path of the drone is accurately and efficiently generated by performing path planning on the drone. The drone performs detection tasks according to the target flight path, which can maximize the detection efficiency while avoiding the risk of collision. The drones share task progress to schedule tasks, thereby generating meteorological detection data corresponding to each detection area, further improving the efficiency and accuracy of meteorological data detection.

[0122] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the near-space detection method based on multi-UAV collaboration of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0123] This application also provides a near-space detection device based on multi-UAV collaboration, please refer to Figure 3 The near-space detection device based on multi-UAV collaboration includes:

[0124] The division module 10 is used to divide the adjacent space into regions according to the meteorological detection mission, generate multiple detection areas and determine the number of drones required for each detection area.

[0125] The allocation module 20 is configured to allocate each drone in the drone network to a corresponding detection area according to the performance parameters of the drone and the number of drones required for each detection area.

[0126] The detection module 30 is used to perform coordinated detection in the corresponding detection area by each of the drones to obtain meteorological detection data corresponding to each detection area.

[0127] The fusion module 40 is used to fuse the meteorological detection data corresponding to each detection area to generate meteorological data of the adjacent space.

[0128] A prediction module 50 is configured to perform a prediction based on the meteorological data of the near space using a meteorological prediction model to obtain a meteorological change trend of the near space;

[0129] The early warning module 60 is used to issue a weather early warning according to the weather change trend in the nearby space.

[0130] The near-space detection device based on multi-UAV collaboration provided by this application adopts the near-space detection method based on multi-UAV collaboration in the above-mentioned embodiment, which can solve the technical problems of repeated detection in traditional meteorological detection, resulting in low detection efficiency and incomplete data, and unable to accurately reflect the meteorological conditions of near-space. Compared with the existing technology, the beneficial effects of the near-space detection device based on multi-UAV collaboration provided by this application are the same as the beneficial effects of the near-space detection method based on multi-UAV collaboration provided by the above-mentioned embodiment, and the other technical features of the near-space detection device based on multi-UAV collaboration are the same as the features disclosed in the above-mentioned embodiment method, and are not repeated here.

[0131] In one embodiment, the division module 10 is also used to obtain meteorological detection needs and generate multiple meteorological detection tasks based on the detection needs; determine the scope of the corresponding detection area according to the task objectives of each meteorological detection task; divide the adjacent space into multiple non-overlapping detection areas according to the scope of the corresponding detection area, wherein each of the detection areas corresponds to one or more meteorological detection tasks; determine the number of drones required for each detection area according to the meteorological detection tasks of each detection area and the endurance of the drone.

[0132] In one embodiment, the allocation module 20 is further used to determine the flight speed, flight altitude, endurance, communication range and payload capacity of the UAV based on the performance parameters of the UAV; obtain the area, altitude distribution, mission frequency and mission duration of each detection area; perform adaptability evaluation on each UAV in the UAV network based on the flight speed, flight altitude, endurance, communication range, payload capacity and the area, altitude distribution, mission frequency and mission duration of each detection area of ​​the UAV to obtain the adaptability; and allocate each UAV in the UAV network to the corresponding detection area in order of priority based on the adaptability.

[0133] In one embodiment, the detection module 30 is also used to plan paths for the drones in each of the detection areas to obtain target flight paths for the drones in each detection area; control each of the drones to fly in the corresponding detection area according to the target flight path and perform corresponding meteorological detection tasks, and generate task progress information for each drone; share the task progress information of each drone through a drone network, and schedule tasks for each drone based on the task progress information; after detecting that each drone has completed the corresponding meteorological detection task, collect the original detection data obtained by each drone when performing the meteorological detection task in the corresponding detection area, and pre-process the original detection data to obtain meteorological detection data corresponding to each detection area.

[0134] In one embodiment, the detection module 30 is further configured to, when there are multiple drones in the detection area, generate an initial flight path for the drones in the detection area based on the take-off position, target detection point, and boundary conditions of each drone; perform dynamic collision avoidance based on the initial flight path to generate a collision-free flight path; use the collision-free flight path as an initial population; perform fitness evaluation on individuals in the initial population based on the flight distance, flight time, energy consumption, and mission completion of the collision-free flight path to obtain fitness values ​​of the individuals in the initial population; select individuals from the initial population as parents based on the fitness values, and perform selection, crossover, and mutation operations on the parents to generate a new population; use the new population as the initial population, and re-execute the step of performing fitness evaluation on individuals in the initial population based on the flight distance, flight time, energy consumption, and mission completion of the collision-free flight path to obtain fitness values ​​of the individuals in the initial population, until a preset convergence condition is met or a maximum number of iterations is reached, thereby obtaining the target flight path of the drone.

[0135] In one embodiment, the fusion module 40 is further configured to perform data preprocessing based on the type, format, and resolution of the meteorological detection data of each detection area to obtain preprocessed meteorological detection data of each detection area, wherein the preprocessing includes at least data format conversion, resolution unification, and abnormal data removal; perform spatiotemporal fusion on the preprocessed meteorological detection data of each detection area to obtain fused meteorological detection data; and perform spatiotemporal interpolation processing on the fused meteorological detection data to obtain spatiotemporally continuous near-space meteorological data.

[0136] The formula for space-time fusion is:

[0137]

[0138] Where D(t,r) is the fused meteorological detection data, which represents the final result at time t and location r. i is the number of different meteorological detection areas, ranging from 1 to N (there are N detection areas in total). j is the number of the detection point in detection area i, ranging from 1 to M (there are M detection points in each detection area). W i (t) is the time weighting factor of detection area i at time t, ω ij (t, r) is the spatial weight between detection area i and detection point j at time t and spatial position r, D ij (t) is the meteorological detection data of detection point j in detection area i at time t.

[0139] In one embodiment, the weather forecast model is:

[0140]

[0141] Where D(t+1,r) represents the meteorological data forecast result at time t+1 and spatial position r, i is the number of different meteorological detection areas, ranging from 1 to N (there are N detection areas in total), j is the number of the detection point in detection area i, ranging from 1 to M (there are M detection points in each detection area), ω ij (t, r) represents the spatial weight of the detection area i and the detection point j to the target position r in the adjacent space, D ij (t) is the meteorological detection data of detection point j in meteorological detection area i at time t, f(D ij (t), r, t) represents the meteorological detection data D ij (t), spatial position r and time t to predict the meteorological change trend in nearby space.

[0142] The present application provides a near-space detection device based on multi-UAV collaboration, and the near-space detection device based on multi-UAV collaboration includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the near-space detection method based on multi-UAV collaboration in the above-mentioned embodiment one.

[0143] Reference below Figure 4 , which shows a schematic structural diagram of a near-space detection device based on multi-UAV collaboration suitable for implementing an embodiment of the present application. The near-space detection device based on multi-UAV collaboration in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The near-space detection device based on multi-UAV collaboration shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0144] like Figure 4As shown, the near-space detection device based on multi-UAV collaboration may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in ROM (Read Only Memory) 1002 or the program loaded from the storage device 1003 to RAM (Random Access Memory) 1004. Various programs and data required for the operation of the near-space detection device based on multi-UAV collaboration are also stored in RAM 1004. The processing device 1001, ROM 1002 and RAM 1004 are connected to each other via a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input device 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output device 1008 including, for example, an LCD (Liquid Crystal Display), speaker, vibrator, etc.; storage device 1003 including, for example, a magnetic tape, hard disk, etc.; and communication device 1009. Communication device 1009 can allow the multi-UAV collaborative near-space detection device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a multi-UAV collaborative near-space detection device with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0145] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0146] The near-space detection device based on multi-UAV collaboration provided by this application adopts the near-space detection method based on multi-UAV collaboration in the above-mentioned embodiment, which can solve the technical problems of repeated detection in traditional meteorological detection, resulting in low detection efficiency and incomplete data, and unable to accurately reflect the meteorological conditions of near-space. Compared with the existing technology, the beneficial effects of the near-space detection device based on multi-UAV collaboration provided by this application are the same as the beneficial effects of the near-space detection method based on multi-UAV collaboration provided by the above-mentioned embodiment, and the other technical features of the near-space detection device based on multi-UAV collaboration are the same as the features disclosed in the method of the previous embodiment, and are not repeated here.

[0147] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0148] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0149] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, and the computer-readable program instructions are used to execute the near-space detection method based on multi-UAV collaboration in the above-mentioned embodiment.

[0150] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash memory), an optical fiber, a CD-ROM (CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0151] The above-mentioned computer-readable storage medium can be included in the near-space detection device based on multi-UAV collaboration; or it can exist independently without being assembled into the near-space detection device based on multi-UAV collaboration.

[0152] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by a near-space detection device based on multi-UAV collaboration, the near-space detection device based on multi-UAV collaboration: divides the near-space into regions according to the meteorological detection task, generates multiple detection regions and determines the number of UAVs required for each detection region; allocates each UAV in the UAV network to a corresponding detection region according to the performance parameters of the UAV and the number of UAVs required for each detection region; obtains meteorological detection data corresponding to each detection region by having each UAV perform collaborative detection in the corresponding detection region; fuses the meteorological detection data corresponding to each detection region to generate meteorological data of the near-space; predicts the meteorological data of the near-space through a meteorological prediction model to obtain the meteorological change trend of the near-space; and issues meteorological warnings based on the meteorological change trend of the near-space.

[0153] The computer program code for performing the operations of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a LAN (Local Area Network) or a WAN (Wide Area Network), or can be connected to an external computer (e.g., using an Internet service provider to connect via the Internet).

[0154] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0155] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0156] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned near-space detection method based on multi-UAV collaboration. This computer-readable storage medium can solve the technical problems of repeated detection in traditional meteorological detection, resulting in low detection efficiency and incomplete data, and an inability to accurately reflect the meteorological conditions in near-space. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the near-space detection method based on multi-UAV collaboration provided in the above-mentioned embodiment, and will not be elaborated here.

[0157] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned near-space detection method based on multi-UAV collaboration.

[0158] The computer program product provided in this application can address the technical issues in traditional meteorological detection, such as repeated detection, resulting in low detection efficiency and incomplete data, and an inability to accurately reflect near-space meteorological conditions. Compared to the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the multi-UAV collaborative near-space detection method provided in the aforementioned embodiment, and are not further elaborated here.

[0159] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A near-space detection method based on multi-UAV collaboration, characterized in that: The method comprises: Divide the near space into regions according to the meteorological detection mission, generate multiple detection areas and determine the number of drones required for each detection area; Allocate each drone in the drone network to a corresponding detection area according to the performance parameters of the drone and the number of drones required for each detection area; The UAVs perform coordinated detection in corresponding detection areas to obtain meteorological detection data corresponding to each detection area; Fusing the meteorological detection data corresponding to each detection area to generate meteorological data of the adjacent space; According to the meteorological data of the near space, a forecast is made using a meteorological forecast model to obtain a meteorological change trend of the near space; A weather warning is issued based on the weather change trend in the near space.

2. The method according to claim 1, wherein The method of dividing the near space into regions according to the meteorological detection mission, generating multiple detection regions and determining the number of drones required for each detection region includes: Obtaining meteorological detection requirements, and generating multiple meteorological detection tasks based on the detection requirements; Determine the scope of the corresponding detection area according to the mission objectives of each of the meteorological detection tasks; Dividing the adjacent space into a plurality of non-overlapping detection areas according to the range of the corresponding detection area, wherein each of the detection areas corresponds to one or more meteorological detection tasks; The number of drones required for each detection area is determined based on the meteorological detection mission of each detection area and the endurance of the drone.

3. The method according to claim 1, wherein Allocating each drone in the drone network to a corresponding detection area according to the performance parameters of the drone and the number of drones required for each detection area includes: Determine the flight speed, flight altitude, endurance, communication range, and payload capacity of the drone based on its performance parameters; Obtain the area, height distribution, mission frequency, and mission duration of each detection area; Performing a compatibility evaluation on each drone in the drone network based on the flight speed, flight altitude, endurance, communication range, payload capacity, and the area, altitude distribution, mission frequency, and mission duration of each detection area of ​​the drone to obtain a degree of compatibility; According to the adaptability, each drone in the drone network is assigned to a corresponding detection area in order of priority.

4. The method according to claim 1, wherein The obtaining of meteorological detection data corresponding to each detection area by each of the drones performing collaborative detection in the corresponding detection area includes: Performing path planning for the UAVs in each detection area to obtain a target flight path for the UAVs in each detection area; Controlling each of the UAVs to fly in a corresponding detection area according to the target flight path and perform a corresponding meteorological detection mission, and generating mission progress information for each UAV; Sharing the task progress information of each drone through a drone network, and scheduling tasks for each drone based on the task progress information; After detecting that each of the UAVs has completed the corresponding meteorological detection mission, the original detection data obtained when each of the UAVs performs the meteorological detection mission in the corresponding detection area is collected, and the original detection data is preprocessed to obtain the meteorological detection data corresponding to each detection area.

5. The method according to claim 4, wherein The path planning of the UAVs in each detection area to obtain the target flight path of the UAVs in each detection area includes: When there are multiple drones in the detection area, generating an initial flight path for the drones in the detection area according to the take-off position of each drone, the target detection point, and the boundary conditions of the detection area; Perform dynamic collision avoidance according to the initial flight path to generate a collision-free flight path; Using the collision-free flight path as the initial population; Performing fitness evaluation on individuals in the initial population according to the flight distance, flight time, energy consumption, and mission completion of the collision-free flight path to obtain fitness values ​​of the individuals in the initial population; selecting individuals from the initial population as parents according to the fitness values, and performing selection, crossover and mutation operations on the parents to generate a new population; The new population is used as the initial population, and the step of performing fitness evaluation on the individuals in the initial population according to the flight distance, flight time, energy consumption, and mission completion of the collision-free flight path to obtain the fitness values ​​of the individuals in the initial population is re-executed until a preset convergence condition is met or a maximum number of iterations is reached, thereby obtaining the target flight path of the UAV.

6. The method according to claim 1, wherein The fusing of the meteorological detection data corresponding to each detection area to generate meteorological data of a nearby space includes: Performing data preprocessing according to the type, format, and resolution of the meteorological detection data of each detection area to obtain preprocessed meteorological detection data of each detection area, wherein the preprocessing at least includes data format conversion, resolution unification, and abnormal data removal; Performing spatiotemporal fusion on the pre-processed meteorological detection data of each detection area to obtain fused meteorological detection data; Performing spatiotemporal interpolation processing on the fused meteorological detection data to obtain spatiotemporally continuous near-space meteorological data; The formula for space-time fusion is: Where D(t,r) is the fused meteorological detection data, which represents the final result at time t and location r. i is the number of different meteorological detection areas, ranging from 1 to N (there are N detection areas in total). j is the number of the detection point in detection area i, ranging from 1 to M (there are M detection points in each detection area). W i (t) is the time weighting factor of detection area i at time t, ω ij (t, r) is the spatial weight between detection area i and detection point j at time t and spatial position r, D ij (t) is the meteorological detection data of detection point j in detection area i at time t.

7. The method according to claim 1, wherein The weather forecast model is: Where D(t+1, r) represents the meteorological data forecast result at time t+1 and spatial position r, i is the number of different meteorological detection areas, ranging from 1 to N (there are N detection areas in total), j is the number of the detection point in detection area i, ranging from 1 to M (there are M detection points in each detection area), ω ij (t, r) represents the spatial weight of the detection area i and the detection point j to the target position r in the adjacent space, D ij (t) is the meteorological detection data of detection point j in meteorological detection area i at time t, f(D ij (t), r, t) represents the meteorological detection data D ij (t), spatial position r and time t to predict the meteorological change trend in the nearby space.

8. A near-space detection device based on multi-UAV collaboration, characterized in that: The near-space detection device based on multi-UAV collaboration includes: The division module is used to divide the adjacent space into regions according to the meteorological detection mission, generate multiple detection areas and determine the number of drones required for each detection area; An allocation module is used to allocate each drone in the drone network to a corresponding detection area according to the performance parameters of the drone and the number of drones required for each detection area; The detection module is used to perform coordinated detection in the corresponding detection area by each of the drones to obtain meteorological detection data corresponding to each detection area: A fusion module is used to fuse the meteorological detection data corresponding to each detection area to generate meteorological data of the adjacent space; A prediction module, configured to perform predictions based on the meteorological data of the near space using a meteorological prediction model to obtain a meteorological change trend of the near space; The early warning module is used to issue a weather early warning based on the weather change trend of the nearby space.

9. A near-space detection device based on multi-UAV collaboration, characterized in that: The near-space detection device based on multi-UAV collaboration includes: a memory, a processor, and a near-space detection program based on multi-UAV collaboration stored on the memory and executable on the processor. The near-space detection program based on multi-UAV collaboration is configured to implement the near-space detection method based on multi-UAV collaboration as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a near-space detection program based on multi-UAV collaboration, and when the near-space detection program based on multi-UAV collaboration is executed by the processor, the near-space detection method based on multi-UAV collaboration as described in any one of claims 1 to 7 is implemented.

Images