An intelligent management system for drone flight risks

Abstract

The present invention discloses an intelligent management system for unmanned aerial vehicle (UAV) flight risks, which relates to the field of UAV management and comprises a UAV management module, a flight acquisition module, a risk assessment module, an intelligent decision-making module and a decision feedback module; the UAV management module is used to set a device transmission communication code for UAV equipment; the flight acquisition module is used to collect flight position data, flight radar data, flight status data and flight environment data in real time; the risk assessment module is used to generate risk assessment data based on the flight position data and flight radar data; the intelligent decision-making module is used to generate corresponding path decision information based on the risk assessment data; the decision feedback module is used to perform feedback analysis on the path decision information and encrypt and transmit the data processing process according to the device transmission communication code; the present invention improves the safety of the UAV during flight.

Description

Technical Field

[0001] The present invention relates to the technical field of drone management, and in particular to an intelligent management system for drone flight risks. Background Art

[0002] With the rapid development of drone technology, its application areas are becoming increasingly broad, such as aerial photography, logistics, and medical treatment. However, due to the special characteristics of drones, there are many risks in their use, such as loss of control, collisions, and environmental impacts. Therefore, intelligent management of risks during drone flight and ensuring the safe and reliable operation of drones have become urgent issues.

[0003] After searching, the invention patent with Chinese patent number CN116841315A discloses a radar information analysis and management system and method based on big data, including: a radar detection module, a big data analysis module, a path planning module, a flight adjustment module and a data update module. The radar detection module is used to detect obstacles encountered by the UAV during flight. The big data analysis module is used to obtain records of other UAVs flying over the obstacle and determine whether the UAV can fly over the obstacle. The path planning module is used to plan its shortest detour path when the UAV cannot fly over the obstacle. The flight adjustment module is used to adjust the UAV's flight attitude and detect collision risks. The data update module is used to self-update the data after successful obstacle avoidance. The present invention can realize intelligent analysis of fixed obstacles, solve the problem of false alarms of radar, reduce the impact of multipath effects on airborne radars, and save time for UAV obstacle avoidance.

[0004] Compared with existing technologies, this invention patent with Chinese patent number CN116841315A enables drones to determine whether they can fly over obstacles when encountering obstacles based on records of other drones flying over the corresponding obstacles, thereby saving drones time in avoiding obstacles.

[0005] However, during use, the above system needs to obtain records of other drones flying over corresponding obstacles. When there is no new data to refer to, dynamic path planning cannot be performed during the drone flight, thereby affecting the safety and accuracy of the drone equipment during flight. Summary of the Invention

[0006] The purpose of the present invention is to solve the shortcomings of the existing technology that safety accidents caused by emergencies during the flight of UAV equipment cannot be effectively avoided, and to propose an intelligent management system for UAV flight risks.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] An intelligent management system for UAV flight risks, comprising a UAV management module, a flight collection module, a risk assessment module, an intelligent decision-making module, and a decision feedback module;

[0009] The drone management module is used to obtain drone device information, generate a corresponding drone device number based on the drone device information, and set a corresponding device transmission communication code based on the drone device number;

[0010] The flight acquisition module is used to collect flight position data, flight radar data, flight status data and flight environment data of the corresponding UAV equipment in real time during flight;

[0011] The risk assessment module is used to set a three-dimensional image of risk obstacles based on the flight position data and the flight radar data, analyze and process the corresponding three-dimensional image of risk obstacles based on the flight status data, and obtain corresponding risk assessment data in the three-dimensional image of risk obstacles;

[0012] The intelligent decision module is used to perform path analysis and processing based on the risk assessment data corresponding to the risk obstacle three-dimensional image to generate corresponding path planning information, and to analyze and process the path planning information based on the flight environment data to generate corresponding path decision information;

[0013] The decision feedback module is used to compare and analyze the obtained path decision information according to the flight position information, generate path feedback information based on the comparison and analysis, and encrypt and transmit the data processing process of the drone device according to the device transmission communication code.

[0014] The above technical solution further includes: the process of the drone management module setting the device transmission communication code includes:

[0015] Setting up a device management unit and a transmission management unit;

[0016] Enter the drone equipment information through the equipment management unit, divide the drone equipment information into fixed specification information and variable specification information, and encode it to obtain the fixed specification code and the variable specification code, set the corresponding wandering extraction method according to the variable specification code, obtain the corresponding characters in the fixed specification code according to the wandering extraction method, and mark the obtained character information as the drone equipment code;

[0017] The transmission management unit is preset with a transmission communication coding library to obtain the data timestamp corresponding to the transmission moment; the obtained drone equipment code is set to a transmission extraction method according to the corresponding data timestamp; the corresponding characters in the transmission communication coding library are obtained according to the transmission extraction method, and the obtained characters are set as the equipment transmission communication code.

[0018] Furthermore, the process of the flight acquisition module collecting corresponding flight position data, flight radar data, flight status data and flight environment data includes:

[0019] Obtain sensor equipment within the drone, including Beidou satellite positioning equipment, radar monitoring equipment, inertial measurement equipment, and meteorological monitoring equipment;

[0020] Beidou satellite positioning equipment is used to obtain flight position data of the UAV during flight;

[0021] Radar monitoring equipment is used to obtain flight radar data of the UAV during flight;

[0022] Inertial measurement equipment is used to obtain flight status data of the UAV during flight;

[0023] Meteorological monitoring equipment is used to obtain flight environment data during the UAV flight;

[0024] The obtained flight position data, flight radar data, flight status data and flight environment data are marked according to the corresponding collection time, and sent to the risk assessment module after marking.

[0025] Furthermore, the process of setting the risk obstacle three-dimensional image by the risk assessment module includes:

[0026] Obtain the acquisition time corresponding to the flight position data and flight radar data, set the data analysis space corresponding to the corresponding unit time in sequence according to the acquisition time, set the data analysis node in the corresponding data analysis space, and construct the three-dimensional image of the risk obstacle corresponding to the corresponding acquisition time based on the data analysis results;

[0027] Set a three-dimensional spatial coordinate system, obtain flight position information, map the flight position information into the three-dimensional spatial coordinate system, use the flight position information as a reference point, obtain flight radar data, and perform analysis and noise reduction processing. Map the noise reduction processing results into a three-dimensional image coordinate system with corresponding reference points to obtain a corresponding three-dimensional image of the risk obstacle.

[0028] Furthermore, the process of the risk assessment module acquiring corresponding risk assessment data in the risk obstacle three-dimensional image includes:

[0029] The three-dimensional images of risk obstacles obtained in each data analysis space are set as image frames according to the acquisition time, and feature analysis processing is performed on each image frame in turn to obtain obstacle data outside the reference point and divide it into dynamic obstacle data and static obstacle data;

[0030] Set the risk assessment cycle according to the collection time, obtain the dynamic obstacle data and static obstacle data corresponding to each collection time within the risk assessment cycle, connect the dynamic space points and static space points corresponding to the reference points, and obtain the corresponding obstacle vector;

[0031] Analyze and process the changes in the vector starting point data and vector endpoint data of each obstacle vector during the risk assessment period based on the flight status data, and obtain the predicted flight range data of the UAV equipment and the corresponding obstacle points;

[0032] The obtained predicted flight range data is mapped to the corresponding risk obstacle three-dimensional image for visualization processing. According to the visualization processing results, the predicted flight range data corresponding to the UAV equipment and each spatial point are subjected to regional overlap analysis to obtain the corresponding risk assessment data.

[0033] Furthermore, the process of the intelligent decision module generating corresponding path planning information includes:

[0034] Acquire a three-dimensional image of the risk obstacle at a current moment, perform grid processing on the three-dimensional image of the risk obstacle, and obtain corresponding grid units;

[0035] Dynamic space points, static space points, predicted flight range data, and risk assessment data are respectively set with corresponding collision color data, gradient color data, overlapping color data, and blank color data. A corresponding color risk coefficient and path priority are set for each color data. Based on the data type corresponding to each grid cell in the risk obstacle 3D image, the corresponding color data is obtained for visualization.

[0036] A preset target point is used, and the selected target point is used to perform path analysis on the corresponding UAV equipment and target point in the risk obstacle three-dimensional image based on the RRT algorithm to obtain multiple path planning information, which includes the grid cells that the UAV equipment needs to pass through.

[0037] Furthermore, the process of the intelligent decision module generating corresponding path decision information includes:

[0038] Build an environmental offset impact model corresponding to the UAV equipment based on a deep learning algorithm, obtain flight environment data, input the obtained flight environment data into the environmental offset impact model, and obtain offset error data of the UAV equipment during flight;

[0039] Performing a comprehensive analysis on the color risk coefficients of the grid cells in each path planning information based on the offset error data to obtain comprehensive risk data corresponding to each path planning information;

[0040] Perform a ratio analysis on the number of different types of grid cells within the comprehensive risk coefficient, and set a bias priority coefficient for the comprehensive risk data based on the ratio analysis results; multiply the obtained bias priority coefficient by the comprehensive risk data to obtain the corresponding comprehensive risk assessment data;

[0041] The comprehensive risk assessment data corresponding to each path planning information is sorted, and the path planning information corresponding to the lowest comprehensive risk assessment data is obtained according to the sorting result, and marked as path decision information.

[0042] Furthermore, the decision feedback module obtains corresponding path decision information and marks the position information corresponding to the corresponding grid unit according to the path decision information;

[0043] Obtain the flight position information and flight status data of the UAV equipment, compare and analyze the obtained flight position information with the path decision information, determine the accuracy data of the corresponding UAV during flight, and generate path feedback information based on the accuracy data;

[0044] The flight data and data processing process collected by the drone equipment are packaged to generate a flight data packet, the current transmission time is obtained, and the corresponding device transmission communication code is obtained according to the transmission time to encrypt and transmit the flight data packet.

[0045] The present invention has the following beneficial effects:

[0046] 0. In the present invention, by setting corresponding drone device numbers for different drone devices and setting corresponding device transmission communication codes for the set drone device numbers according to the corresponding transmission time, dynamic changes of the device transmission communication codes are achieved, thereby avoiding data confusion and data leakage caused by different drone devices during data transmission. In addition, the flight data packets are encrypted through the device transmission communication code, which improves the security of the flight data transmission process to a certain extent.

[0047] 1. In the present invention, a corresponding data analysis space is set according to the collection time of flight data, a corresponding three-dimensional image of risk obstacles is set in each data analysis space, a risk assessment period is set according to the collection time, and corresponding image frames are set for the three-dimensional image of risk obstacles according to the risk assessment period. Each image frame is analyzed and processed to obtain dynamic obstacle data and static obstacle data during the flight of the UAV device. According to the changes in the UAV device and dynamic obstacle data in each image frame, the predicted flight range data of the UAV device and the corresponding obstacle point is obtained, and the corresponding path planning information is set according to the predicted flight range data. This improves the accuracy and dynamic coordination of the path planning process to a certain extent, thereby improving the safety of the UAV device during flight.

[0048] 2. In the present invention, by setting up grid processing for the three-dimensional image of risk obstacles, and setting corresponding color data for each grid unit obtained from the grid processing result according to the different data types in the three-dimensional image of risk obstacles for visualization, and setting corresponding color risk coefficients for the corresponding color data, setting corresponding comprehensive risk data according to the color risk coefficients corresponding to each grid unit in the path planning information, and setting corresponding bias priority coefficients, the personalization and visualization in the process of generating path decision information are improved to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a structural diagram of an intelligent management system for UAV flight risks proposed by the present invention. DETAILED DESCRIPTION

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0051] Example 1

[0052] In this embodiment, Figure 1 As shown, the present invention proposes an intelligent management system for UAV flight risks, which includes a UAV management module, a flight collection module, a risk assessment module, an intelligent decision-making module and a decision feedback module.

[0053] The drone management module is used to obtain the drone device number, set the corresponding device transmission communication code according to the drone device number, and encrypt and transmit the flight data corresponding to the corresponding drone device number according to the device transmission communication code. The specific implementation process includes:

[0054] Setting up a device management unit and a transmission management unit;

[0055] The device management unit is used to obtain drone device information, which includes drone basic information, drone technical specification information, drone power information, drone hardware information, and drone safety certification information, wherein:

[0056] The basic information of the drone includes manufacturer information, production serial number information, production date, etc.

[0057] UAV technical specifications include UAV size and weight, flight data, etc.

[0058] Drone power information includes drone motor battery information and drone power consumption information;

[0059] Drone hardware information includes sensor equipment information and hardware equipment information inside the drone.

[0060] Drone safety certification information includes the drone’s corresponding safety certification information and compliance standard information;

[0061] Set the corresponding drone device number based on the obtained drone device information. The specific implementation process includes:

[0062] Obtaining drone equipment information, dividing the drone equipment information into fixed specification information and variable specification information, wherein the fixed specification information includes drone technical specification information, drone power information, drone hardware information, and drone safety certification information, and the variable specification information includes drone basic information;

[0063] Encode the drone equipment information contained in the fixed specification information respectively, obtain the type of drone equipment information corresponding to the fixed specification information, set a corresponding encoding method according to the type of drone equipment information, encode the drone equipment information in the fixed specification information in turn according to the corresponding encoding method, and obtain the fixed specification code corresponding to the fixed specification information;

[0064] It should be further explained that, in the specific implementation process, the encoding method includes binary encoding, ASCII encoding, Gray encoding and BCD encoding;

[0065] Obtain basic information of the drone corresponding to the variable specification information, set the obtained basic information of the drone to a corresponding encoding method for encoding processing, and obtain the variable specification code corresponding to the variable specification information;

[0066] Obtain characters in a character string corresponding to a variable specification code, and set a wandering extraction method according to each character in turn, wherein the wandering extraction method sets a corresponding extraction operation method for obtaining characters corresponding to the variable specification code;

[0067] Sequentially obtaining corresponding character information within the fixed-size code using a floating extraction method corresponding to the variable-size code, obtaining corresponding character position information based on the corresponding character in the variable-size code using a corresponding extraction operation method, and obtaining corresponding character information within the fixed-size code based on the character position information; using the obtained character information as a starting point, extracting the character position information obtained using the floating extraction method to obtain multiple character information;

[0068] The obtained character information is set as the drone device number of the corresponding drone;

[0069] Send the obtained drone device information and the corresponding drone device number to the transmission management unit;

[0070] The transmission management unit is used to set a device transmission communication code corresponding to the operation of the drone according to the obtained drone device information and drone device number. The device transmission communication code is used to encrypt and transmit the flight data corresponding to the drone device corresponding to the drone device number. The specific implementation process includes:

[0071] Preset the transmission communication coding library to obtain the drone equipment code and the data timestamp of the transmitted data;

[0072] The obtained UAV device code is set to a transmission extraction mode according to the corresponding data timestamp; the data timestamp includes a date timestamp, a clock timestamp, a minute timestamp, a second timestamp, and a split-second timestamp;

[0073] Set the corresponding operation mode according to the different data timestamps, set the operation coefficient according to the different corresponding timestamps, and the operation coefficient is set according to the time of the data timestamp;

[0074] The UAV device code is processed according to the operation mode and operation coefficient, and the corresponding characters in the transmission communication code library are extracted according to the operation processing result, and the obtained characters are marked as the device transmission communication code of the UAV device at the current moment;

[0075] The obtained flight data is encrypted and transmitted according to the obtained device transmission communication code.

[0076] The flight acquisition module is used to collect the flight position data, flight radar data, flight status data and flight environment data of the corresponding UAV in real time during flight, and mark the collection time. The specific implementation process includes:

[0077] Obtain the drone device corresponding to the corresponding drone device code, and obtain the flight data of the drone device during operation for real-time monitoring;

[0078] Obtain sensor device information in the drone hardware information corresponding to the drone device, correlate the obtained sensor device information with the flight acquisition module in the drone device, and obtain flight data obtained by the corresponding sensor device;

[0079] Sensor equipment includes Beidou satellite positioning equipment, radar monitoring equipment, inertial measurement equipment, and meteorological monitoring equipment, including:

[0080] The Beidou satellite positioning device is used to obtain the flight position data of the UAV during flight, and the flight position data includes the UAV spatial coordinate information and the UAV trajectory coordinate information;

[0081] The radar monitoring equipment is used to obtain flight radar data of the UAV during flight, and the flight radar data includes space target radar data and space echo signal data;

[0082] The inertial measurement device is used to obtain flight status data of the UAV during flight, and the flight status data includes flight speed data, flight direction data, flight acceleration data, and flight power data;

[0083] The meteorological monitoring equipment is used to obtain flight environment data during the flight of the UAV, and the flight environment data includes flight pressure data, flight wind data, and flight humidity data;

[0084] The flight position data, flight radar data, flight status data and flight environment data obtained by each sensor device are marked and processed according to the corresponding collection time, and the marked flight data are sent to other modules.

[0085] The risk assessment module is used to set a three-dimensional image of risk obstacles based on flight position data and flight radar data, analyze and process the corresponding three-dimensional image of risk obstacles based on flight status data, and obtain corresponding risk assessment data in the three-dimensional image of risk obstacles. The specific implementation process includes:

[0086] Setting up a flight analysis unit and a risk assessment unit;

[0087] The flight analysis unit is used to obtain flight position data and flight radar data, and to set a three-dimensional image of risk obstacles for the corresponding UAV equipment based on the flight position data and flight radar data. The specific implementation process includes:

[0088] Obtain the acquisition time corresponding to the flight position data and flight radar data, set the data analysis space corresponding to the corresponding unit time in sequence according to the acquisition time, set the data analysis node in the corresponding data analysis space, and construct a three-dimensional image of the risk obstacle based on the corresponding flight position data and flight radar data within the acquisition time;

[0089] Obtain the drone's spatial coordinate information from the corresponding flight position data within the drone device, set a three-dimensional spatial coordinate system using the drone's spatial coordinate information as a reference point, obtain flight radar data, analyze and de-noise the spatial target radar data and spatial echo signal data, map the analysis and de-noising results into the three-dimensional spatial coordinate system, obtain a three-dimensional image of the risk obstacle corresponding to the corresponding unit time, and store it;

[0090] Sequentially acquire three-dimensional images of each risk obstacle in the data analysis space according to the acquisition time and send them to the risk assessment unit;

[0091] The risk assessment unit is used to set risk assessment density data according to the three-dimensional image of the risk obstacle, perform multi-dimensional assessment on the flight radar data according to the risk assessment density data, and obtain multi-dimensional assessment data;

[0092] The three-dimensional images of risk obstacles obtained in each data analysis space are set as image frames according to the acquisition time, and feature analysis processing is performed on each image frame in turn. The specific implementation process includes:

[0093] A risk assessment cycle is set according to the acquisition time, and a three-dimensional image of the risk obstacle corresponding to the data analysis space corresponding to the corresponding acquisition time within the risk assessment cycle is obtained;

[0094] Comparative analysis is performed on the three-dimensional images of the risk obstacle in each image frame within the risk assessment cycle, and the flight position information of the UAV device in each three-dimensional risk obstacle image is obtained in sequence. Based on the differences in the position of the UAV device in each flight obstacle image and the differences in each image frame within the risk assessment cycle, feature analysis processing is performed, and dynamic obstacle data and static obstacle data in the three-dimensional risk obstacle image are obtained based on the feature analysis results.

[0095] Marking the obtained dynamic obstacle data and static obstacle data in the three-dimensional image of each risk obstacle within the risk assessment cycle;

[0096] Obtain dynamic obstacle data and static obstacle data corresponding to each collection time within the risk assessment period and connect them with the dynamic spatial points and static spatial points corresponding to the reference points;

[0097] According to the reference points corresponding to the UAV equipment, they are connected to the dynamic space points and static space points respectively and the corresponding obstacle vectors are set and marked;

[0098] Obtain the obstacle vector corresponding to each marking result within the risk assessment period, analyze and process the obstacle vector corresponding to each unit time to construct a three-dimensional coordinate system, and map the obstacle vector of each unit time within the risk assessment period to the corresponding three-dimensional coordinate system to generate a three-dimensional obstacle image of the corresponding spatial point;

[0099] It should be further explained that, in the specific implementation process, the origin set in the 3D obstacle image is based on the position information of the UAV device during the risk assessment period. During the risk assessment period, the starting point and endpoint of the obstacle vector are mapped to the corresponding 3D obstacle image according to the movement of the UAV device.

[0100] Obtain each three-dimensional obstacle image, and set the radius density function corresponding to the corresponding obstacle image according to the dynamic space point and the static space point respectively;

[0101] Obtain the location of each obstacle vector endpoint in the three-dimensional obstacle image, and obtain the distance information from the location of the endpoint to the starting point of the corresponding obstacle vector in the three-dimensional obstacle image;

[0102] The obtained distance information is input into the radius density function, and the risk assessment density data of the corresponding obstacle vector is output;

[0103] The risk assessment density data is labeled FM and the radius density function is labeled , where the distance information is l, (x, y) is the location information of the corresponding endpoint, is the Euclidean distance between the corresponding endpoint and the reference point ;

[0104] ;

[0105] Obtain risk assessment density data, set a corresponding density grid according to the risk assessment density data, and obtain vector change data of the obstacle vector within the corresponding density grid according to the density grid;

[0106] The vector change data includes vector magnitude change data and vector direction change data;

[0107] Obtain the vector change data within each density grid, analyze and process the vector change data within each density grid, and obtain multi-dimensional evaluation data; the obstacle vector at the corresponding acquisition time is );

[0108] Get the vector starting point data corresponding to the corresponding acquisition time and mark it as , marking the vector endpoint data as ;

[0109] Get the flight operation data, get the flight speed data and flight acceleration data corresponding to the corresponding acquisition time, marked as ,in: ; ;

[0110] Get the predicted position data based on the flight operation data and obstacle vector:

[0111] ; ;

[0112] The predicted position data are marked as and ;

[0113] The predicted flight angle corresponding to the vector start point data and the vector endpoint data is obtained based on the predicted position data. The specific implementation process includes:

[0114] The predicted flight angle is marked as ;in, is the predicted flight angle corresponding to the flight starting point data, is the predicted flight angle corresponding to the flight endpoint data, ; ;

[0115] Construct an operational prediction model, analyze and process the prediction data in each density grid within the risk assessment cycle, and obtain the predicted flight range data corresponding to the UAV equipment and spatial points respectively;

[0116] The obtained predicted flight range data is mapped to the corresponding risk obstacle three-dimensional image for visualization processing. According to the visualization processing results, the regional overlap data corresponding to the UAV equipment and each spatial point are analyzed to obtain the regional overlap data corresponding to the UAV equipment and each spatial point. The obtained regional overlap data is marked as the risk assessment data corresponding to each spatial point, and the obtained risk assessment data is sent to the corresponding energy consumption analysis module.

[0117] The intelligent decision module is used to perform path analysis and processing based on the risk assessment data corresponding to the risk obstacle three-dimensional image to generate corresponding path planning information, and analyze and process the path planning information based on the flight environment data to generate corresponding path decision information. The specific implementation process includes:

[0118] Set up a path analysis unit and an intelligent decision-making unit;

[0119] The path analysis unit is used to obtain a three-dimensional image of the risk obstacle that has been visually analyzed and processed at the current moment, analyze and process the obtained three-dimensional image of the risk obstacle, and obtain path data information that the UAV device can pass through;

[0120] Gridding the obtained three-dimensional image of the risk obstacle to obtain grid cells within the three-dimensional image of the risk obstacle, and visualizing the corresponding grids within the three-dimensional image of the risk obstacle based on the dynamic space points, static space points, predicted flight range data, and risk assessment data;

[0121] The dynamic space point and the position of the dynamic space point are set as collision color data, and the predicted flight range data is obtained. The obtained predicted flight range data is sequentially set as corresponding gradient color data according to the position of the predicted flight range data from the corresponding space point, wherein the closer the distance, the darker the color data;

[0122] Obtain risk assessment data, overlay the gradient color data with the corresponding regional overlapping data, and obtain overlapping color data;

[0123] For grid cells that do not have dynamic space points, static space points, predicted flight range data, or risk assessment data, corresponding blank color data is set;

[0124] Obtain collision color data of each grid cell in the three-dimensional image of each risk obstacle according to the visualization results;

[0125] According to the color data of the grid cell, the corresponding color risk coefficient is set and marked as , , where the color risk coefficient corresponding to blank color data is 0; the color risk coefficient corresponding to collision color data is 1;

[0126] Obtain a three-dimensional image of risk obstacles after color visualization analysis and processing of each grid cell;

[0127] Preset the path planning radius, obtain the grid cells corresponding to the three-dimensional images of each risk obstacle within the path planning radius, obtain the blank color data, gradient color data, and overlapping color data at the endpoints corresponding to the path planning radius, set the priorities in turn, and select the corresponding target points respectively;

[0128] The selected target points are analyzed and processed based on the RRT algorithm for the corresponding UAV equipment and target points in the risk obstacle 3D image to obtain the corresponding path planning information;

[0129] The path planning information includes the color data corresponding to the grid cells that the drone device needs to pass through, and sends it to the intelligent decision-making unit;

[0130] The intelligent decision-making unit obtains the path planning information obtained in the corresponding risk obstacle three-dimensional image and the color data in the corresponding grid unit, and performs analysis and processing to obtain the corresponding path decision information. The specific implementation process includes:

[0131] Obtain the number of grid cells corresponding to each path planning information and the color risk coefficient corresponding to the grid cell;

[0132] Comprehensively analyze the number of grid cells corresponding to each path planning information and the color risk coefficient corresponding to the grid cells;

[0133] Obtain flight environment data, and set offset error data of grid cells corresponding to different visualization classification results based on the flight environment data;

[0134] Obtain historical flight environment data and historical flight operation data, and set corresponding training sets and validation sets based on the historical flight environment data and historical flight operation data respectively;

[0135] Analyze and process the corresponding training set based on the deep learning algorithm, build the corresponding environmental offset impact model, analyze and verify the obtained environmental offset impact model with the corresponding validation set, and output the corresponding environmental offset impact model;

[0136] The obtained flight environment data and flight status data are input into the environmental offset impact model, which performs analysis and processing to obtain corresponding offset error data;

[0137] Analyze and process each path planning data using the obtained offset error data;

[0138] Multiplying the color risk coefficient and the offset error data in the grid cells corresponding to the path planning data to obtain risk data, and adding the risk data of the grid cells to obtain the comprehensive risk data of each path planning data;

[0139] Perform a ratio analysis on the number of different types of grid cells within the comprehensive risk coefficient, and set a bias priority coefficient for the comprehensive risk data based on the ratio analysis results. The bias priority coefficient includes a distance bias and a safety bias. The distance bias is a priority coefficient set according to the number of grid cells, and the safety bias is a priority coefficient set according to the color risk coefficient corresponding to the grid cell.

[0140] Analyze and process the obtained comprehensive risk data and the corresponding bias priority coefficient to obtain the comprehensive risk assessment data corresponding to each path planning data;

[0141] Sort the corresponding path planning data according to the comprehensive risk assessment data, and obtain the decision priority of each path planning data according to the sorting result;

[0142] The corresponding path planning data is selected according to the decision priority, the obtained path planning data is marked as path decision information, and sent to the decision feedback module.

[0143] The decision feedback module is used to compare and analyze the obtained path decision information according to the flight position information, generate path feedback information based on the comparison and analysis, and encrypt and transmit the data processing process of the UAV device according to the device transmission communication code. The specific implementation process includes:

[0144] Set up a flight feedback unit and a flight transmission unit;

[0145] The flight feedback unit obtains corresponding path decision information and marks the position information corresponding to the corresponding grid unit according to the path decision information;

[0146] Obtain the flight position information and flight status data of the UAV equipment, compare and analyze the obtained flight position information with the path decision information, determine the accuracy data of the corresponding UAV during flight, generate path feedback information based on the accuracy data, and generate warning information based on the path feedback information;

[0147] The flight transmission unit is used to package the data information and data processing process collected in the drone equipment in real time, generate a flight data packet, encrypt the obtained flight data packet according to the device transmission communication code of the corresponding transmission time, and transmit the corresponding flight data packet according to the encryption processing result.

[0148] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent management system for drone flight risks, characterized by: It includes drone management module, flight collection module, risk assessment module, intelligent decision-making module and decision feedback module; The drone management module is used to obtain drone device information, generate a corresponding drone device number based on the drone device information, and set a corresponding device transmission communication code based on the drone device number; The flight acquisition module is used to collect flight position data, flight radar data, flight status data and flight environment data of the corresponding UAV equipment in real time during flight; The risk assessment module is used to set a three-dimensional image of risk obstacles based on the flight position data and the flight radar data, and analyze and process the corresponding three-dimensional image of risk obstacles based on the flight status data. The process of obtaining the corresponding risk assessment data in the three-dimensional image of risk obstacles includes: The three-dimensional images of risk obstacles obtained in each data analysis space are set as image frames according to the acquisition time, and feature analysis processing is performed on each image frame in turn to obtain obstacle data outside the reference point and divide it into dynamic obstacle data and static obstacle data; Set the risk assessment cycle according to the collection time, obtain the dynamic obstacle data and static obstacle data corresponding to each collection time within the risk assessment cycle, connect the dynamic space points and static space points corresponding to the reference points, and obtain the corresponding obstacle vector; Analyze and process the changes in the vector starting point data and vector endpoint data of each obstacle vector during the risk assessment period based on the flight status data, and obtain the predicted flight range data of the UAV equipment and the corresponding obstacle points; The obtained predicted flight range data is mapped to the corresponding risk obstacle three-dimensional image for visualization processing. Based on the visualization processing results, the predicted flight range data corresponding to the UAV equipment and each spatial point are subjected to regional overlap analysis to obtain the corresponding risk assessment data; The intelligent decision module is used to perform path analysis and processing based on the risk assessment data corresponding to the risk obstacle three-dimensional image to generate corresponding path planning information, and to analyze and process the path planning information based on the flight environment data to generate corresponding path decision information; The process of generating corresponding path planning information includes: Acquire a three-dimensional image of the risk obstacle at a current moment, perform grid processing on the three-dimensional image of the risk obstacle, and obtain corresponding grid units; Dynamic space points, static space points, predicted flight range data, and risk assessment data are respectively set with corresponding collision color data, gradient color data, overlapping color data, and blank color data. A corresponding color risk coefficient and path priority are set for each color data. Based on the data type corresponding to each grid cell in the risk obstacle 3D image, the corresponding color data is obtained for visualization. Preset target points, perform path analysis on the corresponding UAV equipment and target points in the risk obstacle three-dimensional image based on the selected target points based on the RRT algorithm, and obtain multiple path planning information, wherein the path planning information includes the grid cells that the UAV equipment needs to pass through; The process of generating corresponding path decision information includes: Build an environmental offset impact model corresponding to the UAV equipment based on a deep learning algorithm, obtain flight environment data, input the obtained flight environment data into the environmental offset impact model, and obtain offset error data of the UAV equipment during flight; Performing a comprehensive analysis on the color risk coefficients of the grid cells in each path planning information based on the offset error data to obtain comprehensive risk data corresponding to each path planning information; Perform a ratio analysis on the number of different types of grid cells within the comprehensive risk coefficient, and set a bias priority coefficient for the comprehensive risk data based on the ratio analysis results; multiply the obtained bias priority coefficient by the comprehensive risk data to obtain the corresponding comprehensive risk assessment data; Sort the comprehensive risk assessment data corresponding to each path planning information, obtain the path planning information corresponding to the lowest comprehensive risk assessment data based on the sorting result, and mark it as path decision information; The decision feedback module is used to compare and analyze the obtained path decision information according to the flight position information, generate path feedback information based on the comparison and analysis, and encrypt and transmit the data processing process of the drone device according to the device transmission communication code.

2. The intelligent management system for UAV flight risk according to claim 1, characterized in that: The process of setting the device transmission communication code in the drone management module includes: Setting up a device management unit and a transmission management unit; Entering drone equipment information through the equipment management unit, dividing the drone equipment information into fixed specification information and variable specification information, encoding the fixed specification information and the variable specification information respectively, obtaining the fixed specification code and the variable specification code, setting a corresponding wandering extraction method according to the variable specification code, obtaining corresponding characters in the fixed specification code according to the wandering extraction method, and marking the obtained character information as the drone equipment code; The transmission management unit is preset with a transmission communication coding library to obtain the data timestamp corresponding to the transmission moment; the obtained drone equipment code is set to a transmission extraction method according to the corresponding data timestamp; the corresponding characters in the transmission communication coding library are obtained according to the transmission extraction method, and the obtained characters are set as the equipment transmission communication code.

3. The intelligent management system for UAV flight risk according to claim 2 is characterized in that: The process of the flight acquisition module collecting corresponding flight position data, flight radar data, flight status data and flight environment data includes: Obtain sensor equipment within the drone, including Beidou satellite positioning equipment, radar monitoring equipment, inertial measurement equipment, and meteorological monitoring equipment; Beidou satellite positioning equipment is used to obtain flight position data of the UAV during flight; Radar monitoring equipment is used to obtain flight radar data of the UAV during flight; Inertial measurement equipment is used to obtain flight status data of the UAV during flight; Meteorological monitoring equipment is used to obtain flight environment data during the UAV flight; The obtained flight position data, flight radar data, flight status data and flight environment data are marked according to the corresponding collection time, and sent to the risk assessment module after marking.

4. The intelligent management system for UAV flight risk according to claim 3 is characterized in that: The process of setting up a 3D image of risk barriers in the risk assessment module includes: Obtain the acquisition time corresponding to the flight position data and flight radar data, set the data analysis space corresponding to the corresponding unit time in sequence according to the acquisition time, set the data analysis node in the corresponding data analysis space, and construct the three-dimensional image of the risk obstacle corresponding to the corresponding acquisition time based on the data analysis results; A three-dimensional spatial coordinate system is set up, flight position information is obtained, the flight position information is mapped into the three-dimensional spatial coordinate system, flight radar data is obtained with the flight position information as a reference point, and noise reduction processing is performed after analysis. The noise reduction processing result is mapped into the three-dimensional image coordinate system with the relative position of the corresponding reference point to obtain the corresponding three-dimensional image of the risk obstacle.

5. The intelligent management system for UAV flight risk according to claim 1, characterized in that: The decision feedback module obtains the corresponding path decision information and marks the location information corresponding to the corresponding grid unit according to the path decision information; Obtain the flight position information and flight status data of the UAV equipment, compare and analyze the obtained flight position information with the path decision information, determine the accuracy data of the corresponding UAV during flight, and generate path feedback information based on the accuracy data; The flight data and data processing process collected by the drone equipment are packaged to generate a flight data packet, the current transmission time is obtained, and the corresponding device transmission communication code is obtained according to the transmission time to encrypt and transmit the flight data packet.

Images