Low-altitude unmanned aerial vehicle weather guarantee system

Abstract

This invention discloses a low-altitude unmanned aerial vehicle (UAV) meteorological support system, relating to the field of meteorological monitoring technology. It constructs a control command set for several UAVs deployed within a UAV platform to control their low-altitude operations and acquire real-time flight parameters during these operations. This data is used to monitor the actual flight status of the UAVs and determine whether to participate in flight control. The system uses meteorological cloud images captured by the UAVs at different time intervals and locations to overlay and process these images into a meteorological cloud image set for the monitored location area on each UAV's local terminal. A data exchange network is constructed to conduct bidirectional data interaction with each UAV. The meteorological cloud image sets stored in each UAV are imported into the data exchange network, and all the meteorological cloud image sets are parsed to determine the actual meteorological conditions in different locations. Finally, support measures are implemented for locations where the actual meteorological conditions do not meet the standards.

Description

Technical Field

[0001] This invention relates to the field of meteorological monitoring technology, specifically a low-altitude unmanned aerial vehicle (UAV) meteorological support system. Background Technology

[0002] Existing meteorological monitoring and support systems typically rely on technologies such as ground-based meteorological stations and satellite remote sensing. While these technologies can provide meteorological data over a wide area to some extent, they have limitations in specific regions, especially in meteorological monitoring in the low-altitude region.

[0003] Low-altitude meteorological data is crucial for agriculture, aviation, urban planning, and other fields. However, current monitoring methods often fail to provide sufficiently accurate and real-time low-altitude meteorological information. Furthermore, existing meteorological support systems lack the ability to respond quickly and intervene precisely when monitoring locations with substandard meteorological conditions, making it difficult to provide effective protection for specific areas. Summary of the Invention

[0004] To address the aforementioned problems, the present invention aims to provide a low-altitude unmanned aerial vehicle (UAV) meteorological support system.

[0005] The objective of this invention can be achieved through the following technical solution: a low-altitude unmanned aerial vehicle (UAV) meteorological support system, comprising a monitoring center, wherein the monitoring center is communicatively connected to an UAV control module, a meteorological monitoring module, a data interaction module, a data parsing module, and a meteorological support module;

[0006] The drone management module is used to build a set of management instructions for several drones deployed within the drone platform, thereby controlling the drones to perform low-altitude operations and acquiring the flight parameters of the drones during low-altitude operations in real time. By monitoring the flight status of the drones through the flight parameters, it can decide whether to participate in flight control.

[0007] The meteorological monitoring module is used to capture meteorological cloud images of different time periods and locations using low-altitude drones, and to overlay and process them into a meteorological cloud image atlas of the monitored location area within the local terminal of each drone.

[0008] The data interaction module is used to construct a data interaction network, and to conduct bidirectional data interaction with each UAV through the data interaction network, thereby importing the meteorological cloud atlas stored in each UAV into the data interaction network;

[0009] The data parsing module is used to parse all the meteorological cloud atlases in the data exchange network, and then obtain the real-time meteorological conditions in different locations and regions.

[0010] The meteorological support module is used to implement support measures for locations and areas where the actual meteorological conditions do not meet the standards.

[0011] Furthermore, the process of building a control command set for several drones deployed within the drone platform, and then controlling the drones to perform low-altitude operations, includes:

[0012] Deploy several drones within the drone platform and number them i, i = 1, 2, 3, ..., n, where n is a natural number greater than 0. Set up a first operation period, a second operation period, and a third operation period.

[0013] During the first operational period, control commands are generated for the drone, including positioning and cruise commands, hovering and obstacle avoidance commands, and data acquisition commands. These commands are then integrated to form the initial control command set.

[0014] During the second operation period, the initial control command set is entered into each drone. While entering the initial control command set, the input environment is monitored simultaneously. When undefined alienation information is detected, the location of all alienation information is marked and iterated sequentially. Whenever alienation information at a location is encountered, it is corrected until all alienation information at all locations is corrected, and then the third operation period is started.

[0015] During the third operation period, the drone performs a low-altitude operation test according to the recorded control instruction set, and determines whether the drone meets the corresponding preset completion standards when performing positioning cruise, hovering obstacle avoidance and data collection according to the control instruction set.

[0016] If so, the control instruction set is complete, and the drone can be controlled to perform low-altitude operations.

[0017] If not, modify the control instructions that do not meet the completion standards.

[0018] Furthermore, the process of acquiring real-time flight parameters of the drone during low-altitude operations and monitoring the drone's real-time flight status through these parameters includes:

[0019] Flight parameters include positioning and cruise parameters, hovering and obstacle avoidance parameters, and data acquisition parameters;

[0020] Positioning and navigation parameters include GPS signal strength, cruise speed, cruise altitude, and heading;

[0021] Hovering obstacle avoidance parameters include hovering height, vertical speed, horizontal speed, obstacle avoidance trajectory, hovering stabilization time, and obstacle avoidance response time;

[0022] Data acquisition parameters include sensor parameters, shooting speed, shooting frame rate, acquisition mode, lens shake angle, and lens imaging parameters;

[0023] Set up parameter lookup tables for positioning and navigation parameters, hovering and obstacle avoidance parameters, and data acquisition parameters. If any of these parameters does not conform to the corresponding lookup table, the monitoring result for the drone will be: the current flight status of the drone is abnormal; otherwise, the monitoring result will be: the current flight status of the drone is normal.

[0024] Furthermore, the process of deciding whether to participate in flight control includes:

[0025] When the drone's flight status is normal, no operation is performed;

[0026] When the flight status of a drone is abnormal, it is decided to take control of the corresponding drone.

[0027] Furthermore, the process of using low-altitude drones to capture meteorological cloud images at different time intervals and locations includes:

[0028] Each drone is responsible for performing low-altitude operations in a specific location area. The start time and end time of the low-altitude operation for drone number i are set and denoted as Start[i] and End[i], respectively. The total operation time of drone number i is then obtained and denoted as T[i].

[0029] T[i] = |End[i] - Start[i]|;

[0030] Set the imaging control duration and denot it as t;

[0031] Based on the total operation time and imaging control time of each drone, the shooting frequency corresponding to each drone is obtained. The shooting frequency of the drone numbered i when performing low-altitude operations is denoted as N[i]. Then, N[i] = T[i] / t.

[0032] Based on the shooting frequency of each drone, the total operation time of each drone is divided into N[i] time segments. Each drone takes a corresponding number of meteorological cloud map shots within its own N[i] time segments, thereby obtaining several meteorological cloud maps of the drone's location area under several time segments.

[0033] Furthermore, the process of overlaying and processing the data into a meteorological cloud atlas for the monitored location area within each drone's local terminal includes:

[0034] Each drone is equipped with a local terminal for overlaying all the meteorological cloud images obtained by the drone. The overlay processing includes: image correction, feature analysis and interval determination for each meteorological cloud image in chronological order.

[0035] The meteorological cloud image is converted into a standard image ready for operation through image correction.

[0036] Through feature analysis, several feature point clouds corresponding to the standard image to be operated on are obtained. Each feature point cloud is associated with and labeled with corresponding point cloud reference information and point cloud dispersion.

[0037] Set up point cloud dimension clusters for interval determination. Point cloud dimension clusters include high-dimensional interval clusters, medium-dimensional interval clusters and low-dimensional interval clusters. Different point cloud dimension clusters are associated with corresponding discrete intervals.

[0038] Let the discrete intervals of the high-dimensional interval cluster, the medium-dimensional interval cluster, and the low-dimensional interval cluster be denoted as Ω1, Ω2, and Ω3, respectively, and let the point cloud discreteness of the feature point cloud be denoted as τ.

[0039] Cluster all feature point clouds of τ∈Ω1 into a high-dimensional meteorological cloud map;

[0040] Cluster all feature point clouds of τ∈Ω2 into a mid-dimensional meteorological cloud map;

[0041] Cluster all feature point clouds of τ∈Ω3 into a low-dimensional meteorological cloud map;

[0042] By overlaying high-dimensional, medium-dimensional, and low-dimensional meteorological cloud images in the same location area, a meteorological cloud image set for the corresponding location area is obtained. The above operation is repeated to obtain the meteorological cloud image set for each location area.

[0043] Furthermore, the process of bidirectional data exchange with each UAV through the data exchange network, thereby importing the meteorological cloud atlas stored in each UAV into the data exchange network, includes:

[0044] Configure the network environment of the data exchange network, create several interaction ports corresponding to the data exchange network, and determine whether the network environment is in a normal state;

[0045] If so, assign an interaction port to each drone through the data interaction network, and enter the interaction file into the interaction port. Test whether the two-way data interaction between the data interaction network and the drone has been successfully established through the interaction file.

[0046] If so, the meteorological cloud atlas stored in each drone will be imported into the data exchange network;

[0047] If not, locate the abnormal data interaction direction of the two-way data interaction, retrieve the data information that caused the current data interaction direction to be abnormal, and input it into the preset historical database to match the processing steps and procedures for resolving the abnormality.

[0048] If not, perform data cleaning on the data exchange network, filter out abnormal or suspected abnormal data in the data exchange network into the preset data isolation area, calculate the probability of abnormality of suspected abnormal data, further divide suspected abnormal data into normal data and abnormal data according to the probability of abnormality, remove abnormal data, and send normal data back to the data exchange network.

[0049] Furthermore, the process of analyzing all meteorological cloud atlases in the data exchange network to derive the actual meteorological conditions in different locations includes:

[0050] The data parsing module connects to the data exchange network to obtain meteorological cloud atlases for all locations in the data exchange network. The data parsing module consists of a preprocessing unit and a parsing unit. The preprocessing unit checks whether the integrity of the meteorological cloud atlas corresponding to each location area meets the standard, checks whether the image format of the meteorological cloud atlas conforms to the preset image format, and removes invalid data and noise data from the meteorological cloud atlas.

[0051] The meteorological cloud atlas processed by the preprocessing unit is entered into the parsing unit. The parsing unit performs data parsing, feature extraction, and real-time meteorological analysis on the meteorological cloud atlas of each location area to obtain the real-time meteorological conditions of each location area.

[0052] The analysis results of the real-time weather analysis are compiled to generate a real-time weather condition report for each location area.

[0053] Furthermore, the process by which the meteorological support module implements support measures for locations and areas where actual meteorological conditions do not meet the standards includes:

[0054] The meteorological support module includes an early warning database and a measures database.

[0055] The early warning database is used to input the real-time weather condition report corresponding to each location area. After the real-time weather condition report is entered into the early warning database, the real-time weather condition report is analyzed and early warning is issued simultaneously to obtain the risk coefficient, early warning level and early warning type of the location area corresponding to the real-time weather condition report.

[0056] The risk coefficient is denoted as γ. The maximum limit value of the risk coefficient corresponding to the meteorological conditions meeting the standard is set and denoted as Max-D. When γ < Max-D, it means that the meteorological conditions of the corresponding location area meet the standard. When γ ≥ Max-D, it means that the meteorological conditions of the corresponding location area do not meet the standard.

[0057] Input the warning level and warning type from the warning database into the measures database for all locations and areas where meteorological conditions do not meet the standards.

[0058] The measures database is used to match and execute corresponding safeguard measures for a location area based on the warning level and warning type. The measures database stores safeguard measures corresponding to different warning levels and warning types.

[0059] Compared with existing technologies, the beneficial effects of this invention are as follows: By using drones for low-altitude operations, meteorological cloud images of specific time periods and locations can be acquired, improving the accuracy and real-time performance of low-altitude meteorological monitoring. The drone management module can acquire the drone's flight parameters in real time and monitor its flight status, ensuring stable collection and transmission of meteorological data. The data interaction module constructs a data interaction network that enables two-way data interaction with the drone, allowing meteorological cloud atlases to be quickly imported into the data interaction network for subsequent processing and analysis. The data analysis module can accurately analyze the meteorological cloud atlases to obtain the actual meteorological conditions in different locations. Based on this, the meteorological support module implements support measures for areas where the actual meteorological conditions do not meet the standards, effectively improving the ability to respond to sudden meteorological disasters and realizing rapid response meteorological support measures. Attached Figure Description

[0060] Figure 1 This is a schematic diagram of the present invention. Detailed Implementation

[0061] like Figure 1 As shown, a low-altitude unmanned aerial vehicle (UAV) meteorological support system includes a monitoring center, which is communicatively connected to an UAV control module, a meteorological monitoring module, a data interaction module, a data parsing module, and a meteorological support module.

[0062] The drone management module is used to build a set of management instructions for several drones deployed within the drone platform, thereby controlling the drones to perform low-altitude operations and acquiring the flight parameters of the drones during low-altitude operations in real time. By monitoring the flight status of the drones through the flight parameters, it can decide whether to participate in flight control.

[0063] The meteorological monitoring module is used to capture meteorological cloud images of different time periods and locations using low-altitude drones, and to overlay and process them into a meteorological cloud image atlas of the monitored location area within the local terminal of each drone.

[0064] The data interaction module is used to construct a data interaction network, and to conduct bidirectional data interaction with each UAV through the data interaction network, thereby importing the meteorological cloud atlas stored in each UAV into the data interaction network;

[0065] The data parsing module is used to parse all the meteorological cloud atlases in the data exchange network, and then obtain the real-time meteorological conditions in different locations and regions.

[0066] The meteorological support module is used to implement support measures for locations and areas where the actual meteorological conditions do not meet the standards.

[0067] It should be further explained that, in the specific implementation process, the drone management module constructs a set of management instructions for several drones deployed within the drone platform, thereby controlling the drones to perform low-altitude operations. This process includes:

[0068] Several drones are deployed within the drone platform. These drones are numbered and denoted as i, where i = 1, 2, 3, ..., n, and n is a natural number greater than 0. The drone control module is set to have a first operation period, a second operation period, and a third operation period.

[0069] During the first operation period, control commands are generated for the drone, including positioning and cruise commands, hovering and obstacle avoidance commands, and data acquisition commands, which are then integrated to form the initial control command set.

[0070] The drone flies within the area where weather monitoring is required by executing positioning and navigation commands; it maintains its position or avoids obstacles encountered within the area where monitoring is required by executing hovering and obstacle avoidance commands; and it performs several shooting actions within the area where monitoring is required by executing data acquisition commands, with preset shooting frame rate, shooting time interval, and shooting parameters.

[0071] During the second operation period, the initial control command set is entered into each drone deployed in the drone platform. While entering the initial control command set, the input environment is monitored simultaneously. When undefined alienation information is detected in the input environment, the location of all alienation information in the input environment is marked, and the alienation information at all locations is traversed in turn.

[0072] Whenever the alienated information at a certain location is encountered, the alienated information is corrected until the alienated information at all locations is corrected, and then the third operation period is started.

[0073] During the third operation period, the drone performs a low-altitude operation test according to the recorded control instruction set, and determines whether the drone meets the corresponding preset completion standards when performing positioning cruise, hovering obstacle avoidance and data collection according to the control instruction set.

[0074] If yes, the control instruction set for the corresponding UAV to perform low-altitude operations is completed, and the control instruction set for the UAV is executed to control the UAV to perform low-altitude operations; if not, the control instructions that do not meet the completion standards are modified until the modified control instructions can meet the corresponding completion standards after being executed by the UAV.

[0075] Among them, the positioning, navigation, hovering and obstacle avoidance, and data collection performed by each drone in its respective location area all fall under the category of low-altitude operations.

[0076] It should be further explained that, in the specific implementation process, the process of acquiring flight parameters of the drone in real time during low-altitude operations, monitoring the drone's real-time flight status through these parameters, and deciding whether to participate in flight control includes:

[0077] The flight parameters of a drone during low-altitude operations include positioning and cruise parameters, hovering and obstacle avoidance parameters, and data acquisition parameters. Let the flight parameters corresponding to the drone numbered i be denoted as Fly[i]. Then Fly[i] = {A[i], B[i], C[i]}.

[0078] Where A[i] represents the positioning and navigation parameters corresponding to UAV number i, B[i] represents the hovering and obstacle avoidance parameters corresponding to UAV number i, and C[i] represents the data acquisition parameters corresponding to UAV number i.

[0079] The positioning and navigation parameters include GPS signal strength, cruise speed, cruise altitude, and heading;

[0080] The hovering obstacle avoidance parameters include hovering height, vertical speed, horizontal speed, obstacle avoidance trajectory, hovering stabilization duration, and obstacle avoidance response time.

[0081] The data acquisition parameters include sensor parameters, shooting speed, shooting frame rate, acquisition mode, lens shake angle, and lens imaging parameters;

[0082] Set up parameter lookup tables for positioning and navigation parameters, hovering and obstacle avoidance parameters, and data acquisition parameters. If any of these parameters does not match the corresponding lookup table, the result of monitoring the drone will be: the current flight status of the drone is abnormal; otherwise, the result of monitoring the drone will be: the current flight status of the drone is normal.

[0083] When the drone's flight status is normal, no operation is performed;

[0084] When the flight status of a drone is abnormal, it is decided to take control of the corresponding drone.

[0085] It should be further explained that, in the specific implementation process, the meteorological monitoring module uses low-altitude drones to capture meteorological cloud images of different time periods and locations, and then overlays and processes these images into a meteorological cloud atlas for the monitored location area on the local terminal of each drone. This process includes:

[0086] Once all drones deployed within the drone platform are started, each drone is responsible for performing low-altitude operations in a specific location area. Starting from number i=1 and ending at number i=n, ​​the value of i is incremented by one each time. The start and end times of the low-altitude operation corresponding to drone number i are set and denoted as Start[i] and End[i], respectively.

[0087] Then, the total operation time corresponding to the drone numbered i is obtained, denoted as T[i];

[0088] T[i] = |End[i] - Start[i]|;

[0089] Set the imaging control duration, and denot the imaging control duration as t;

[0090] Based on the total operation time and imaging control time of each drone, the shooting frequency corresponding to each drone is obtained. The shooting frequency of the drone numbered i when performing low-altitude operations is denoted as N[i]. Then, N[i] = T[i] / t.

[0091] According to the shooting frequency of each drone, the total operation time of each drone is divided into N[i] time segments. Each drone takes meteorological cloud map shooting a corresponding number of times within its own N[i] time segments, thereby obtaining several meteorological cloud maps under several time segments in the drone's location area.

[0092] Each drone is equipped with a corresponding local terminal, which is used to overlay all the meteorological cloud images obtained by the drone. The overlay processing includes: image correction, feature analysis and interval determination for each meteorological cloud image in chronological order.

[0093] The meteorological cloud image is converted into a standard image ready for operation through image correction.

[0094] Image correction includes removing image noise, distorted points, bad pixels, and blurred areas from meteorological cloud images;

[0095] Through feature analysis, several feature point clouds corresponding to the standard image to be operated on are obtained. Each feature point cloud is associated with and labeled with corresponding point cloud reference information and point cloud dispersion.

[0096] The point cloud reference information includes the point cloud type, point cloud size, point cloud vector information, point cloud origin coordinates, and the position coordinates of each point cloud data in the feature point cloud relative to the point cloud origin coordinates. The point cloud origin coordinates are denoted as P0 = (0, 0), and the position coordinates of each point cloud data relative to the point cloud origin coordinates are denoted as P = (x, y). x is the horizontal distance between the point cloud data and the point cloud origin coordinates, and y is the vertical distance between the point cloud data and the point cloud origin coordinates. Both x and y are real numbers greater than 0.

[0097] Set up point cloud dimension clusters for interval determination. Point cloud dimension clusters include high-dimensional interval clusters, medium-dimensional interval clusters and low-dimensional interval clusters. Different point cloud dimension clusters are associated with corresponding discrete intervals. The discrete intervals of high-dimensional interval clusters, medium-dimensional interval clusters and low-dimensional interval clusters are denoted as Ω1, Ω2 and Ω3, respectively.

[0098] Ω1, Ω2, and Ω3 are detailed below:

[0099] Ω1 = [0.8, 1);

[0100] Ω2 = [0.5, 0.8);

[0101] Ω3 = (0, 0.5);

[0102] The range of the point cloud discreteness corresponding to the feature point cloud is (0, 1);

[0103] Let τ denote the point cloud discreteness corresponding to the feature point cloud.

[0104] Cluster all feature point clouds of τ∈Ω1 into a high-dimensional meteorological cloud map;

[0105] Cluster all feature point clouds of τ∈Ω2 into a mid-dimensional meteorological cloud map;

[0106] Cluster all feature point clouds of τ∈Ω3 into a low-dimensional meteorological cloud map;

[0107] By overlaying high-dimensional, medium-dimensional, and low-dimensional meteorological cloud images in the same location area, a meteorological cloud image set for the corresponding location area is obtained. The above operation is repeated to obtain the meteorological cloud image set for each location area.

[0108] It should be further explained that, in the specific implementation process, the data interaction module constructs a data interaction network, and through this network, it conducts bidirectional data interaction with each UAV, thereby importing the meteorological cloud atlas stored in each UAV into the data interaction network. This process includes:

[0109] The data interaction module constructs a data interaction network, configures the network environment of the data interaction network, creates several interaction ports corresponding to the data interaction network, and associates each interaction port with a corresponding port code to determine whether the network environment is in a normal state.

[0110] If so, assign an interaction port to each drone through the data interaction network, and enter the interaction file into the interaction port. Test whether the two-way data interaction between the data interaction network and the drone has been successfully established through the interaction file.

[0111] If so, the meteorological cloud atlas stored in each drone will be imported into the data exchange network;

[0112] If not, the abnormal data interaction direction of the two-way data interaction is located, the data information that caused the current abnormal data interaction direction is retrieved, the retrieved data information is input into the preset historical database, and then the processing steps to resolve the abnormality are matched from the historical database. After the processing steps are executed, the two-way data interaction between the UAV and the data interaction network is restored.

[0113] If not, data cleaning is performed on the data exchange network. Abnormal or suspected abnormal data in the data exchange network is filtered into a preset data isolation area through data cleaning. The abnormal probability of suspected abnormal data is counted in the data isolation area. Based on the abnormal probability, suspected abnormal data is further divided into normal data and abnormal data. Abnormal data is removed, and normal data is sent back to the data exchange network.

[0114] The probability of anomalies in suspected abnormal data is denoted as Py. An anomaly judgment threshold is set and denoted as μ. Both Py and μ are real numbers greater than 0 and less than 1. Suspected abnormal data are divided according to the relationship between the values ​​of Py and μ.

[0115] When Py≥μ, the corresponding suspected outlier data is classified as outlier data;

[0116] When Py < μ, the corresponding suspected abnormal data is classified as normal data.

[0117] It should be further explained that, in the specific implementation process, the data parsing module parses all the meteorological cloud atlases in the data exchange network to obtain the actual meteorological conditions for different locations and regions. This process includes:

[0118] The data parsing module connects to the data exchange network to obtain meteorological cloud atlases corresponding to all locations in the data exchange network. The data parsing module consists of a preprocessing unit and a parsing unit. The preprocessing unit checks whether the integrity of the meteorological cloud atlas corresponding to each location meets the standard, and also checks whether the image format of the meteorological cloud atlas conforms to the preset image format, and removes invalid data and noisy data from the meteorological cloud atlas.

[0119] The meteorological cloud atlas processed by the preprocessing unit is entered into the parsing unit. The parsing unit performs data parsing, feature extraction, and real-time meteorological analysis on the meteorological cloud atlas of each location area, thereby obtaining the real-time meteorological conditions of each location area.

[0120] The real-time meteorological conditions are used to characterize the weather conditions, precipitation probability, and wind conditions of the corresponding location area; weather conditions include sunny, cloudy, overcast, rainy, snowy, and foggy, etc., and wind conditions include wind intensity and wind direction;

[0121] Data parsing includes parsing metadata, image decoding, and image registration;

[0122] The metadata parsing process involves extracting metadata such as timestamps, locations, and sensor information corresponding to the meteorological cloud atlas.

[0123] The image decoding process involves decoding the image format of the meteorological cloud atlas and then converting the current image format into a compilable format.

[0124] The content of image registration is as follows: meteorological cloud images with different timestamps and shooting angles are marked from the meteorological cloud image collection, a Cartesian coordinate system is established, and meteorological cloud images with different timestamps and shooting angles are mapped to the Cartesian coordinate system;

[0125] Feature extraction includes cloud type identification and cloud height estimation;

[0126] Different types of clouds are identified and located, including cumulus, stratus, and cumulonimbus clouds. Cloud features are extracted from meteorological cloud atlases, and cloud height is estimated based on these features to determine the height of the cloud layer in each location area.

[0127] The content of the real-time meteorological analysis is as follows: using the relevant data corresponding to the meteorological cloud atlas after feature extraction as the real-time analysis data, and taking the real-time analysis data as the analysis object, firstly, the cloud cover in different locations is calculated to determine the weather conditions of the corresponding locations, including sunny, cloudy, partly cloudy, rainy, snowy, and foggy weather; then, based on the cloud map characteristics, the possibility and probability of precipitation in the current location area are analyzed; finally, wind field inference is performed to determine the downwind direction and wind intensity of the current location area.

[0128] The analysis results of the real-time weather analysis are compiled to generate a real-time weather condition report for each location area. The person in charge of each location area is used as the distinguishing identifier for the real-time weather condition report for that location area.

[0129] It should be further explained that, in the specific implementation process, the meteorological support module's implementation of support measures for locations and areas where actual meteorological conditions do not meet the standards includes:

[0130] The meteorological support module includes an early warning database and a measures database.

[0131] The early warning database is used to input the real-time meteorological condition report corresponding to each location area. After the real-time meteorological condition report is entered into the early warning database, the real-time meteorological condition report is analyzed and issued early warnings simultaneously, thereby obtaining the risk coefficient, early warning level and early warning type of the location area corresponding to the real-time meteorological condition report.

[0132] The risk coefficient is denoted as γ. The maximum limit value of the risk coefficient corresponding to the meteorological conditions meeting the standard is set and denoted as Max-D. When γ < Max-D, it means that the meteorological conditions of the corresponding location area meet the standard. When γ ≥ Max-D, it means that the meteorological conditions of the corresponding location area do not meet the standard.

[0133] Input the warning level and warning type from the warning database into the measures database for all locations and areas where meteorological conditions do not meet the standards.

[0134] The measures database is used to match and execute corresponding safeguard measures for a location area based on the warning level and warning type of the location area. The measures database stores safeguard measures corresponding to different warning levels and warning types.

[0135] The safeguards include emergency response measures, safety protection measures, and meteorological intervention measures.

[0136] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A low-altitude unmanned aerial vehicle (UAV) meteorological support system, comprising a monitoring center, characterized in that, The monitoring center is connected to a drone management module, a meteorological monitoring module, a data interaction module, a data analysis module, and a meteorological support module. The drone management module is used to build a set of management instructions for several drones deployed within the drone platform, thereby controlling the drones to perform low-altitude operations and acquiring the flight parameters of the drones during low-altitude operations in real time. By monitoring the flight status of the drones through the flight parameters, it can decide whether to participate in flight control. The meteorological monitoring module is used to capture meteorological cloud images of different time periods and locations using low-altitude drones, and to overlay and process them into a meteorological cloud image atlas of the monitored location area within the local terminal of each drone. The data interaction module is used to construct a data interaction network, and to conduct bidirectional data interaction with each UAV through the data interaction network, thereby importing the meteorological cloud atlas stored in each UAV into the data interaction network; The data parsing module is used to parse all the meteorological cloud atlases in the data exchange network, and then obtain the real-time meteorological conditions in different locations and regions. The meteorological support module is used to implement support measures for locations and areas where the actual meteorological conditions do not meet the standards. The process of using low-altitude drones to capture meteorological cloud images of different time periods and locations includes: Each drone is responsible for performing low-altitude operations in a specific location area. The start time and end time of the low-altitude operation for drone number i are set and denoted as Start[i] and End[i], respectively. The total operation time of drone number i is then obtained and denoted as T[i]. T[i] = |End[i] - Start[i]|; Set the imaging control duration and denot it as t; Based on the total operation time and imaging control time of each drone, the shooting frequency corresponding to each drone is obtained. The shooting frequency of the drone numbered i when performing low-altitude operations is denoted as N[i]. Then, N[i] = T[i] / t. According to the shooting frequency of each drone, the total operation time of each drone is divided into N[i] time segments. Each drone takes meteorological cloud map shooting a corresponding number of times within its own N[i] time segments, thereby obtaining several meteorological cloud maps under several time segments in the drone's location area. The process of overlaying and processing meteorological cloud atlases for the monitored location area within each drone's local terminal includes: Each drone is equipped with a local terminal for overlaying all the meteorological cloud images obtained by the drone. The overlay processing includes: image correction, feature analysis and interval determination for each meteorological cloud image in chronological order. The meteorological cloud image is converted into a standard image ready for operation through image correction. Through feature analysis, several feature point clouds corresponding to the standard image to be operated on are obtained. Each feature point cloud is associated with and labeled with corresponding point cloud reference information and point cloud dispersion. Set up point cloud dimension clusters for interval determination. Point cloud dimension clusters include high-dimensional interval clusters, medium-dimensional interval clusters and low-dimensional interval clusters. Different point cloud dimension clusters are associated with corresponding discrete intervals. Let the discrete intervals of the high-dimensional interval cluster, the medium-dimensional interval cluster, and the low-dimensional interval cluster be denoted as Ω1, Ω2, and Ω3, respectively, and let the point cloud discreteness of the feature point cloud be denoted as τ. Cluster all feature point clouds of τ∈Ω1 into a high-dimensional meteorological cloud map; Cluster all feature point clouds of τ∈Ω2 into a mid-dimensional meteorological cloud map; Cluster all feature point clouds of τ∈Ω3 into a low-dimensional meteorological cloud map; High-dimensional meteorological cloud images, medium-dimensional meteorological cloud images, and low-dimensional meteorological cloud images in the same location area are overlaid to obtain meteorological cloud image sets for the corresponding location area. The above operation is repeated to obtain the meteorological cloud image sets for each location area. The process of constructing a data exchange network, enabling bidirectional data exchange with each UAV, and importing the meteorological cloud atlas stored in each UAV into the data exchange network includes: Configure the network environment of the data exchange network, create several interaction ports corresponding to the data exchange network, and determine whether the network environment is in a normal state; If so, assign an interaction port to each drone through the data interaction network, and enter the interaction file into the interaction port. Test whether the two-way data interaction between the data interaction network and the drone has been successfully established through the interaction file. If so, the meteorological cloud atlas stored in each drone will be imported into the data exchange network; If not, locate the abnormal data interaction direction of the two-way data interaction, retrieve the data information that caused the current data interaction direction to be abnormal, and input it into the preset historical database to match the processing steps and procedures for resolving the abnormality. If not, perform data cleaning on the data exchange network, filter out abnormal or suspected abnormal data in the data exchange network into the preset data isolation area, calculate the probability of abnormality of suspected abnormal data, further divide suspected abnormal data into normal data and abnormal data according to the probability of abnormality, remove abnormal data, and send normal data back to the data exchange network.

2. The low-altitude unmanned aerial vehicle (UAV) meteorological support system according to claim 1, characterized in that, The process of building a control command set for several drones deployed within a drone platform, and then controlling the drones to perform low-altitude operations, includes: Deploy several drones within the drone platform and number them i, i = 1, 2, 3, ..., n, where n is a natural number greater than 0. Set up a first operation period, a second operation period, and a third operation period. During the first operational period, control commands are generated for the drone, including positioning and cruise commands, hovering and obstacle avoidance commands, and data acquisition commands. These commands are then integrated to form the initial control command set. During the second operation period, the initial control command set is entered into each drone. While entering the initial control command set, the input environment is monitored simultaneously. When undefined alienation information is detected, the location of all alienation information is marked and iterated sequentially. Whenever alienation information at a location is encountered, it is corrected until all alienation information at all locations is corrected, and then the third operation period is started. During the third operation period, the drone performs a low-altitude operation test according to the recorded control instruction set, and determines whether the drone meets the corresponding preset completion standards when performing positioning cruise, hovering obstacle avoidance and data collection according to the control instruction set. If so, the control instruction set is complete, and the drone can be controlled to perform low-altitude operations. If not, modify the control instructions that do not meet the completion standards.

3. A low-altitude unmanned aerial vehicle (UAV) meteorological support system according to claim 2, characterized in that, The process of acquiring real-time flight parameters of drones during low-altitude operations and monitoring the drone's real-time flight status using these parameters includes: Flight parameters include positioning and cruise parameters, hovering and obstacle avoidance parameters, and data acquisition parameters; Positioning and navigation parameters include GPS signal strength, cruise speed, cruise altitude, and heading; Hovering obstacle avoidance parameters include hovering height, vertical speed, horizontal speed, obstacle avoidance trajectory, hovering stabilization time, and obstacle avoidance response time; Data acquisition parameters include sensor parameters, shooting speed, shooting frame rate, acquisition mode, lens shake angle, and lens imaging parameters; Set up parameter lookup tables for positioning and navigation parameters, hovering and obstacle avoidance parameters, and data acquisition parameters. If any of these parameters does not conform to the corresponding lookup table, the monitoring result for the drone will be: the current flight status of the drone is abnormal; otherwise, the monitoring result will be: the current flight status of the drone is normal.

4. A low-altitude unmanned aerial vehicle (UAV) meteorological support system according to claim 3, characterized in that, The process of deciding whether to participate in flight control includes: When the drone's flight status is normal, no operation is performed; When the flight status of a drone is abnormal, it is decided to take control of the corresponding drone.

5. A low-altitude unmanned aerial vehicle (UAV) meteorological support system according to claim 4, characterized in that, The process of analyzing all meteorological cloud atlases in the data exchange network to obtain the actual meteorological conditions in different locations includes: The data parsing module connects to the data exchange network to obtain meteorological cloud atlases for all locations in the data exchange network. The data parsing module consists of a preprocessing unit and a parsing unit. The preprocessing unit checks whether the integrity of the meteorological cloud atlas corresponding to each location area meets the standard, checks whether the image format of the meteorological cloud atlas conforms to the preset image format, and removes invalid data and noise data from the meteorological cloud atlas. The meteorological cloud atlas processed by the preprocessing unit is entered into the parsing unit. The parsing unit performs data parsing, feature extraction, and real-time meteorological analysis on the meteorological cloud atlas of each location area to obtain the real-time meteorological conditions of each location area. The analysis results of the real-time weather analysis are compiled to generate a real-time weather condition report for each location area.

6. A low-altitude unmanned aerial vehicle (UAV) meteorological support system according to claim 5, characterized in that, The process by which the meteorological support module implements support measures for locations and areas where actual meteorological conditions do not meet the standards includes: The meteorological support module includes an early warning database and a measures database. The early warning database is used to input the real-time weather condition report corresponding to each location area. After the real-time weather condition report is entered into the early warning database, the real-time weather condition report is analyzed and early warning is issued simultaneously to obtain the risk coefficient, early warning level and early warning type of the location area corresponding to the real-time weather condition report. The risk coefficient is denoted as γ. The maximum limit value of the risk coefficient corresponding to the meteorological conditions meeting the standard is set and denoted as Max-D. When γ < Max-D, it means that the meteorological conditions of the corresponding location area meet the standard. When γ ≥ Max-D, it means that the meteorological conditions of the corresponding location area do not meet the standard. Input the warning level and warning type from the warning database into the measures database for all locations and areas where meteorological conditions do not meet the standards. The measures database is used to match and execute corresponding safeguard measures for a location area based on the warning level and warning type. The measures database stores safeguard measures corresponding to different warning levels and warning types.

Images