Unmanned aerial vehicle flight risk intelligent management system

Abstract

The invention, which relates to the unmanned aerial vehicle management field, discloses an unmanned aerial vehicle flight risk intelligent management system comprising an unmanned aerial vehicle management module, a flight acquisition module, a risk assessment module, an intelligent decision-making module and a decision-making feedback module. The unmanned aerial vehicle management module is used for setting an equipment transmission communication code of the unmanned aerial vehicle equipment; the flight acquisition module is used for acquiring flight position data, flight radar data, flight state data and flight environment data in real time; the risk assessment module is used for generating risk assessment data according to the flight position data and the flight radar data; the intelligent decision module is used for generating corresponding path decision information according to the risk assessment data; the decision feedback module is used for carrying out feedback analysis on the path decision information and carrying out encrypted transmission on a data processing process according to a device transmission communication code; the safety of the unmanned aerial vehicle in the flight process is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle management, and particularly to an intelligent management system for unmanned aerial vehicle flight risks. Background Art

[0002] With the rapid development of unmanned aerial vehicle technology, its application fields are becoming more and more extensive, such as aerial photography, logistics, medical treatment, etc.; however, due to the particularity of unmanned aerial vehicles, there are many risks during their use, such as out of control, impact, environmental impact, etc.; therefore, intelligently managing the risks during the flight of unmanned aerial vehicles to ensure the safe and reliable operation of unmanned aerial vehicles has become an urgent problem to be solved currently; After retrieval, the invention patent with the 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 during the flight of the unmanned aerial vehicle. The big data analysis module is used to obtain the records when other unmanned aerial vehicles fly over the obstacle, and judge whether the unmanned aerial vehicle can fly over the obstacle. The path planning module is used to plan the shortest detour path when the unmanned aerial vehicle cannot fly over the obstacle. The flight adjustment module is used to adjust the flight attitude of the unmanned aerial vehicle and detect the collision risk. The data update module is used for self-updating of data after successful obstacle avoidance. The present invention can realize the intelligent analysis of fixed obstacles, solve the false alarm problem of the radar, reduce the influence of multipath effects on the airborne radar, and save the time for the unmanned aerial vehicle to avoid obstacles.

[0003] Compared with the prior art, the invention patent with the Chinese patent number CN116841315A can enable the unmanned aerial vehicle to judge whether it can fly over the corresponding obstacle based on the records when other unmanned aerial vehicles fly over the corresponding obstacle when encountering an obstacle, thereby saving the time for the unmanned aerial vehicle to avoid the obstacle; However, during the use of the above system, it is necessary to obtain the record basis when other unmanned aerial vehicles fly over the corresponding obstacle. When there is no new data for reference, dynamic path planning cannot be performed during the flight of the unmanned aerial vehicle, thereby affecting the safety and accuracy of the unmanned aerial vehicle equipment during the flight process. Summary of the Invention

[0004] The purpose of the present invention is to solve the defect in the prior art that safety accidents caused by unexpected situations during the flight of unmanned aerial vehicle equipment cannot be effectively avoided, and to propose an intelligent management system for unmanned aerial vehicle flight risks.

[0005] In order to achieve the above purpose, the present invention adopts the following technical solutions: An intelligent management system for unmanned aerial vehicle flight risks includes an unmanned aerial vehicle 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 obtain UAV device information, generate corresponding UAV device numbers according to the UAV device information, and set corresponding device transmission communication codes according to the UAV device numbers; The flight acquisition module is used to collect flight position data, flight radar data, flight status data, and flight environment data during the flight of the corresponding UAV device in real time; The risk assessment module is used to set a three-dimensional risk obstacle image according to the flight position data and flight radar data, analyze and process the corresponding three-dimensional risk obstacle image according to the flight status data, and obtain corresponding risk assessment data within the three-dimensional risk obstacle image; The intelligent decision-making module is used to perform path analysis and processing according to the risk assessment data corresponding to the three-dimensional risk obstacle image, generate corresponding path planning information, and analyze and process the path planning information according to the flight environment data to generate corresponding path decision-making information; The decision feedback module is used to compare and analyze the obtained path decision-making information according to the flight position information, generate path feedback information according to the comparison and analysis, and encrypt and transmit the data processing process of the UAV device according to the device transmission communication code.

[0006] The above technical solution further includes: The process of the UAV management module setting the device transmission communication code includes: Set a device management unit and a transmission management unit; Enter UAV device information through the device management unit, divide the UAV device information into fixed specification information and variable specification information, and perform coding processing on them to obtain a fixed specification code and a variable specification code. Set a corresponding wandering extraction method according to the variable specification code, obtain corresponding characters in the fixed specification code according to the wandering extraction method, and mark the obtained character information as the UAV device code; There is a pre-set transmission communication coding library in the transmission management unit, and obtain the corresponding data timestamp at the transmission moment; Set the transmission extraction method according to the obtained UAV device code and the corresponding data timestamp; Obtain corresponding characters in the transmission communication coding library according to the transmission extraction method, and set the obtained characters as the device transmission communication code.

[0007] Further, the process of the flight acquisition module collecting the corresponding flight position data, flight radar data, flight status data, and flight environment data includes: Obtain the sensor devices in the UAV device, and the sensor devices include Beidou satellite positioning devices, radar monitoring devices, inertial measurement devices, and meteorological monitoring devices; The Beidou satellite positioning device is used to obtain the flight position data during the flight of the UAV; The radar monitoring device is used to obtain the flight radar data during the flight of the UAV; The inertial measurement device is used to obtain the flight state data during the flight of the UAV; The meteorological monitoring device is used to obtain the flight environment data during the flight of the UAV; Mark the obtained flight position data, flight radar data, flight state data and flight environment data according to the corresponding acquisition time, and send them to the risk assessment module after completion of marking.

[0008] Further, the process of the risk assessment module setting the three-dimensional image of the risk obstacle includes: Obtain the acquisition time corresponding to the flight position data and the flight radar data, set the data analysis space corresponding to the corresponding unit time in sequence according to the acquisition time, set data analysis nodes in the corresponding data analysis space, and construct the three-dimensional image of the risk obstacle corresponding to the corresponding acquisition time through the data analysis results; Set up a three-dimensional space coordinate system, obtain the flight position information, map the flight position information into the three-dimensional space coordinate system, take the flight position information as the reference point, obtain the flight radar data, and perform analysis and noise reduction processing, map the noise reduction processing result to the three-dimensional image coordinate system with the corresponding reference point, and obtain the corresponding three-dimensional image of the risk obstacle.

[0009] Further, the process of the risk assessment module obtaining the corresponding risk assessment data in the three-dimensional image of the risk obstacle includes: Set the three-dimensional images of the risk obstacles obtained in each data analysis space as image frames according to the acquisition time, perform feature analysis processing on each image frame in sequence, obtain the obstacle data outside the reference point, and divide it into dynamic obstacle data and static obstacle data; Set the risk assessment period according to the acquisition time, obtain the dynamic space points and static space points corresponding to the connection between the dynamic obstacle data and the static obstacle data corresponding to each acquisition time within the risk assessment period and the reference point, and obtain the corresponding obstacle vectors; Analyze and process the change conditions of the vector starting point data and the vector end point data of each obstacle vector within the risk assessment period according to the flight state data, and obtain the predicted flight range data of the UAV device and the corresponding obstacle points; Map the obtained predicted flight range data into the corresponding three-dimensional image of the risk obstacle for visualization processing, and perform regional overlap analysis on the predicted flight range data corresponding to the UAV device and each space point according to the visualization processing result to obtain the corresponding risk assessment data.

[0010] Further, the process of the intelligent decision-making module generating the corresponding path planning information includes: Obtain the three-dimensional image of the risk obstacle at the current moment, perform grid processing on the three-dimensional image of the risk obstacle, and obtain the corresponding grid cells; Set corresponding collision color data, gradient color data, overlapping color data, and blank color data for dynamic space points, static space points, predicted flight range data, and risk assessment data respectively, and set corresponding color risk coefficients and path priorities for each color data. Obtain the corresponding color data according to the data types corresponding to each grid unit in the risk obstacle three-dimensional image for visual display; Preset a target point, and perform path analysis on the corresponding UAV device and the target point in the risk obstacle three-dimensional image based on the RRT algorithm for the selected target point to obtain multiple path planning information, where the path planning information includes the grid units that the UAV device needs to pass through.

[0011] Furthermore, the process of the intelligent decision-making module generating corresponding path decision information includes: Construct an environmental offset impact model corresponding to the UAV device based on the deep learning algorithm, obtain flight environment data, input the obtained flight environment data into the environmental offset impact model to obtain the offset error data during the flight of the UAV device; Comprehensively analyze the color risk coefficients of the grid units in each path planning information according to the offset error data to obtain the comprehensive risk data corresponding to each path planning information; Perform a proportion analysis on the number of different types of grid units in the comprehensive risk coefficient, and set a bias priority coefficient for the comprehensive risk data according to the proportion analysis result; 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, and obtain the path planning information corresponding to the lowest comprehensive risk assessment data according to the sorting result, and mark it as path decision information.

[0012] Furthermore, the decision feedback module obtains the corresponding path decision information and marks the position 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 device, compare and analyze the obtained flight position information with the path decision information to judge the accuracy data during the flight of the corresponding UAV, and generate path feedback information according to the accuracy data; Package the flight data collected by the UAV device and the data processing process to generate a flight data packet, obtain the current transmission time, and encrypt and transmit the flight data packet according to the transmission time to obtain the corresponding device transmission communication code.

[0013] The present invention has the following beneficial effects: 0. In the present invention, by setting corresponding UAV device numbers for different UAV devices and setting corresponding device transmission communication codes for the set UAV device numbers according to the corresponding transmission times, the dynamic change of the device transmission communication codes is realized, thereby avoiding data chaos and data leakage during the data transmission of different UAV devices. In addition, by encrypting the flight data packets with the device transmission communication codes, the security during the flight data transmission is improved to a certain extent.

[0014] 1. In the present invention, corresponding data analysis spaces are set according to the acquisition times of flight data, corresponding three-dimensional risk obstacle images are set in each data analysis space, a risk assessment period is set according to the acquisition time, corresponding image frames are set for the three-dimensional risk obstacle images 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, the predicted flight range data of the UAV device and the corresponding obstacle points are obtained according to the change situations of the UAV device and the dynamic obstacle data in each image frame, and corresponding path planning information is set according to the predicted flight range data, thereby improving the accuracy and dynamic coordination during the path planning process to a certain extent, and thus improving the security during the flight of the UAV device.

[0015] 2. In the present invention, by setting a grid processing for the three-dimensional risk obstacle images, and setting corresponding color data for the grid cells obtained from each grid processing result for visual display according to different data types in the three-dimensional risk obstacle images, and setting corresponding color risk coefficients for the corresponding color data, corresponding comprehensive risk data is set according to the color risk coefficients corresponding to each grid cell in the path planning information, and a corresponding bias priority coefficient is set, thereby improving the personalization and visualization during the generation of path decision information to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic structural diagram of an intelligent management system for UAV flight risks proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] Embodiment 1 In this embodiment, as Figure 1As shown in the figure, an intelligent management system for unmanned aerial vehicle (UAV) flight risks proposed by the present invention includes a UAV management module, a flight acquisition module, a risk assessment module, an intelligent decision-making module, and a decision feedback module.

[0019] The UAV management module is used to obtain the UAV device number, set the corresponding device transmission communication code according to the UAV device number, and encrypt and transmit the flight data corresponding to the UAV device number according to the device transmission communication code. The specific implementation process includes: Set up a device management unit and a transmission management unit; The device management unit is used to obtain UAV device information, which includes UAV basic information, UAV technical specification information, UAV power information, UAV hardware information, and UAV safety certification information. Among them: The UAV basic information includes production manufacturer information, production serial number information, production date, etc.; The UAV technical specification information includes UAV size and weight information, flight data information, etc.; The UAV power information includes UAV motor battery information and UAV power consumption information, etc.; The UAV hardware information includes sensor device information and hardware device information inside the UAV The UAV safety certification information includes the corresponding safety certification information and compliance standard information of the UAV, etc.; Set the corresponding UAV device number according to the obtained UAV device information. The specific implementation process includes: Obtain UAV device information, and divide the UAV device information into fixed specification information and variable specification information. Among them, the fixed specification information includes UAV technical specification information, UAV power information, UAV hardware information, and UAV safety certification information, and the variable specification information includes UAV basic information; Encode the UAV device information included in the fixed specification information respectively, obtain the types of UAV device information corresponding to the fixed specification information, set the corresponding encoding method according to the types of UAV device information, and encode the UAV device information in the fixed specification information in sequence according to the corresponding encoding method to obtain the fixed specification code corresponding to the fixed specification information; It should be further noted that in the specific implementation process, the encoding methods include binary encoding, ASCII encoding, Gray encoding, BCD encoding and other methods; Obtain the UAV basic information corresponding to the variable specification information, and encode the obtained UAV basic information with a corresponding encoding method to obtain the variable specification code corresponding to the variable specification information; Obtain the characters within the string corresponding to the variable specification code, and set the wandering extraction method according to each character in turn. The wandering extraction method is to set the corresponding extraction operation method for the character corresponding to the variable specification code; Obtain the corresponding character information in the fixed specification code in turn according to the wandering extraction method corresponding to the variable specification code. Obtain the corresponding character position information according to the corresponding character of the variable specification code with the corresponding extraction operation method, and obtain the corresponding character information in the fixed specification code according to the character position information; Starting from the obtained character information, extract according to the character position information obtained by the wandering extraction method to obtain multiple character information; Set the obtained character information as the UAV device number of the corresponding UAV; Send the obtained UAV device information and the corresponding UAV device number to the transmission management unit; The transmission management unit is used to set the device transmission communication code during the operation of the corresponding UAV according to the obtained UAV device information and UAV device number. The device transmission communication code is used for encrypting and transmitting the flight data corresponding to the UAV device corresponding to the UAV device number. The specific implementation process includes: Preset a transmission communication coding library, and obtain the UAV device code and the data timestamp of the transmitted data; Set the transmission extraction method for the obtained UAV device code according to the corresponding data timestamp; The data timestamp includes date timestamp, clock timestamp, minute timestamp, second timestamp, and minute-second timestamp; Set the corresponding operation method according to the difference of the data timestamp, set the operation coefficient according to the difference of the corresponding timestamp, and the operation coefficient is set according to the time of the data timestamp; Perform arithmetic processing on the UAV device code according to the operation method and operation coefficient, extract the corresponding characters in the transmission communication coding library according to the arithmetic processing result, and mark the obtained characters as the device transmission communication code of the UAV device at the current moment; Encrypt and transmit the obtained flight data according to the obtained device transmission communication code.

[0020] The flight acquisition module is used to collect the flight position data, flight radar data, flight status data, and flight environment data during the flight of the corresponding UAV in real time, and mark the acquisition time. The specific implementation process includes: Obtain the UAV device corresponding to the corresponding UAV device code, and obtain the flight data during the operation of the UAV device for real-time monitoring; Obtain the sensor device information in the UAV hardware information corresponding to the UAV device, associate the obtained sensor device information with the flight acquisition module in the UAV device respectively, and obtain the flight data obtained by the corresponding sensor device; The sensor devices include a Beidou satellite positioning device, a radar monitoring device, an inertial measurement device, and a meteorological monitoring device, where: The Beidou satellite positioning device is used to obtain the flight position data during the flight of the UAV. The flight position data includes the UAV spatial coordinate information, the UAV trajectory coordinate information, etc.; The radar monitoring device is used to obtain the flight radar data during the flight of the UAV. The flight radar data includes the spatial target radar data, the spatial echo signal data, etc.; The inertial measurement device is used to obtain the flight state data during the flight of the UAV. The flight state data includes the flight speed data, the flight direction data, the flight acceleration data, and the flight power data, etc.; The meteorological monitoring device is used to obtain the flight environment data during the flight of the UAV. The flight environment data includes the flight air pressure data, the flight wind force data, and the flight humidity data; Mark the flight position data, flight radar data, flight state data, and flight environment data obtained by each sensor device according to the corresponding acquisition time, and send the marked flight data to other modules.

[0021] The risk assessment module is used to set a three-dimensional risk obstacle image according to the flight position data and flight radar data, analyze and process the corresponding three-dimensional risk obstacle image according to the flight state data, and obtain the corresponding risk assessment data in the three-dimensional risk obstacle image. The specific implementation process includes: Set up a flight analysis unit and a risk assessment unit; The flight analysis unit is used to obtain the flight position data and flight radar data, and set the three-dimensional risk obstacle image of the corresponding UAV device according to the flight position data and flight radar data. The specific implementation process 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 data analysis nodes in the corresponding data analysis space, and construct a three-dimensional risk obstacle image according to the corresponding flight position data and flight radar data within the acquisition time; Obtain the UAV spatial coordinate information in the corresponding flight position data within the UAV device. Taking the UAV spatial coordinate information as the reference point, set up a three-dimensional space coordinate system, obtain the flight radar data, perform analysis and noise reduction processing on the spatial target radar data and the spatial echo signal data, map according to the analysis and noise reduction processing results into the three-dimensional space coordinate system, obtain the corresponding three-dimensional risk obstacle images within the corresponding unit time, and store them; Obtain each three-dimensional risk obstacle image in the data analysis space in sequence according to the acquisition time, and send it to the risk assessment unit; The risk assessment unit is used to set the risk assessment density data according to the three-dimensional risk obstacle image, perform multi-dimensional assessment on the flight radar data according to the risk assessment density data, and obtain multi-dimensional assessment data; Set the three-dimensional risk obstacle images obtained in each data analysis space as image frames according to the acquisition time, and perform feature analysis processing on each image frame in sequence. The specific implementation process includes: Set the risk assessment period according to the acquisition time, and obtain the three-dimensional risk obstacle image corresponding to the data analysis space corresponding to the corresponding acquisition time within the risk assessment period; Perform comparative analysis on the three-dimensional risk obstacle images of each image frame within the risk assessment period in sequence, obtain the flight position information of the UAV device in each three-dimensional risk obstacle image in sequence, perform feature analysis processing according to the different positions of the UAV device in each flight obstacle image and the differences of each image frame within the risk assessment period, and obtain the dynamic obstacle data and static obstacle data in the three-dimensional risk obstacle image according to the feature analysis results; Mark the obtained dynamic obstacle data and static obstacle data in each three-dimensional risk obstacle image within the risk assessment period; Obtain the dynamic space points and static space points corresponding to the connection of the dynamic obstacle data and static obstacle data corresponding to each acquisition time within the risk assessment period to the reference point; Connect the reference point corresponding to the UAV device to the dynamic space point and the static space point respectively and set the corresponding obstacle vectors, and mark the corresponding obstacle vectors; Obtain the obstacle vectors corresponding to each marking result within the risk assessment period, perform analysis processing on the obstacle vectors corresponding to each unit time to construct a three-dimensional coordinate system, map the obstacle vectors of each unit time within the risk assessment period into the corresponding three-dimensional coordinate system respectively, and generate the three-dimensional obstacle images of the corresponding space points; It should be further noted that in the specific implementation process, the origin set in the three-dimensional obstacle image is based on the position information of the UAV device within the risk assessment period. Within the risk assessment period, according to the movement of the UAV device, map the starting point and ending point of the obstacle vector into the corresponding three-dimensional obstacle image; Obtain each three-dimensional obstacle image, and respectively set the corresponding radius density function within the corresponding obstacle image according to the dynamic space points and static space points; Obtain the positions of the endpoints of each obstacle vector within the three-dimensional obstacle image, and obtain the distance information from the endpoints to the starting points of the corresponding obstacle vectors within the three-dimensional obstacle image according to the positions of the endpoints; Input the obtained distance information into the radius density function, and output the risk assessment density data of the corresponding obstacle vector; Mark the risk assessment density data as FM, and mark the radius density function as , where the distance information is l, and (x, y) is the position information of the corresponding endpoint, is the Euclidean distance from the corresponding endpoint to the reference point ; ; Obtain the risk assessment density data, set the corresponding density grid according to the risk assessment density data, and obtain the vector change data of the obstacle vector within the corresponding density grid according to the density grid; The vector change data includes vector magnitude change data and vector direction change data; Obtain the vector change data within each density grid, perform analysis and processing according to the vector change data within each density grid, and obtain multi-dimensional assessment data; the obstacle vector at the corresponding acquisition moment is ); Obtain the vector starting point data corresponding to the corresponding acquisition time and mark it as , and mark the vector endpoint data as ; Obtain the flight operation data, obtain the flight speed data and flight acceleration data corresponding to the corresponding acquisition time, and mark them as respectively, where: ; ; Obtain the predicted position data according to the flight operation data and the obstacle vector: ; ; Mark the predicted position data as and respectively; Obtain the predicted flight angle corresponding to the vector starting point data and the vector endpoint data according to the predicted position data, and its specific implementation process includes: Mark the predicted flight angle as ; Among them, is the predicted flight angle corresponding to the flight starting point data, is the predicted flight angle corresponding to the flight end point data, ; ; Construct an operation prediction model, analyze and process the prediction data in each density grid within the risk assessment period, and respectively obtain the predicted flight range data corresponding to the UAV device and the spatial points; Map the obtained predicted flight range data into the corresponding three-dimensional risk obstacle image for visualization processing. According to the visualization processing results, conduct regional overlap analysis on the predicted flight range data corresponding to the UAV device and each spatial point, obtain the regional overlap data corresponding to the UAV device and each spatial point, mark the obtained regional overlap data as the risk assessment data corresponding to each spatial point, and send the obtained risk assessment data to the corresponding energy consumption analysis module.

[0022] The intelligent decision-making module is used to conduct path analysis and processing based on the risk assessment data corresponding in the three-dimensional risk obstacle image, generate corresponding path planning information, and conduct analysis and processing on the path planning information according to the flight environment data to generate corresponding path decision-making information. Its specific implementation process includes: Set up a path analysis unit and an intelligent decision-making unit; The path analysis unit is used to obtain the three-dimensional risk obstacle image that has undergone visualization analysis and processing at the current moment, analyze and process the obtained three-dimensional risk obstacle image, and obtain the path data information that the UAV device can pass through; Perform grid processing on the obtained three-dimensional risk obstacle image to obtain the grid cells within the three-dimensional risk obstacle image, and conduct visualization processing on the corresponding grids within the three-dimensional risk obstacle image according to the dynamic spatial points, static spatial points, predicted flight range data, and risk assessment data; Set the dynamic spatial points and the positions where the dynamic spatial points are located as collision color data, obtain the predicted flight range data, and sequentially set corresponding gradient color data for the obtained predicted flight range data according to its distance from the corresponding spatial points, where the closer the distance, the deeper the color data; Obtain the risk assessment data, cover the gradient color data with the corresponding regional overlap data, and obtain the overlapping color data; Set corresponding blank color data for the grid cells that do not have dynamic spatial points, static spatial points, predicted flight range data, and risk assessment data; Obtain the collision color data of each grid cell within each three-dimensional risk obstacle image according to the visualization results; Set corresponding color risk coefficients according to the color data of the grid cells and mark them as , , where the color risk coefficient corresponding to the blank color data is 0; the color risk coefficient corresponding to the collision color data is 1; Obtain the three-dimensional risk obstacle image after color visualization analysis and processing for each grid cell; Preset the path planning radius, obtain the grid cells corresponding to each three-dimensional risk obstacle image within the path planning radius, obtain the blank color data, gradient color data, and overlapping color data existing at the endpoints corresponding to the path planning radius, set the priorities in sequence, and respectively select the corresponding target points; Analyze and process the selected target points and the corresponding drone devices within the three-dimensional risk obstacle image based on the RRT algorithm to obtain the corresponding path planning information; 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; The intelligent decision-making unit obtains the path planning information obtained within the corresponding three-dimensional risk obstacle image and the color data within the corresponding grid cells, and performs analysis and processing to obtain the corresponding path decision-making information. The specific implementation process includes: Obtain the number of grid cells corresponding to each path planning information and the color risk coefficient corresponding to the grid cells; Comprehensively analyze the number of grid cells corresponding to each path planning information and the color risk coefficient corresponding to the grid cells; Obtain the flight environment data, and set the offset error data of the grid cells corresponding to different visualization classification results according to the flight environment data; Obtain the historical flight environment data and historical flight operation data, and respectively set the corresponding training set and validation set according to the historical flight environment data and historical flight operation data; Analyze and process the corresponding training set based on the deep learning algorithm, construct the corresponding environmental offset influence model, and perform analysis and verification on the obtained environmental offset influence model by the corresponding validation set, and output the corresponding environmental offset influence model; Input the obtained flight environment data and flight state data into the environmental offset influence model, and perform analysis and processing by the environmental offset influence model to obtain the corresponding offset error data; Perform analysis and processing on the obtained offset error data for each path planning data; Multiply the color risk coefficient and the offset error data within the grid cell corresponding to the path planning data to obtain the risk data, and add the risk data of the grid cells to obtain the comprehensive risk data of each path planning data; Perform a proportion 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 according to the result of the proportion analysis. The bias priority coefficient includes a distance bias and a safety bias. The distance bias is the priority coefficient set according to the number of grid cells, and the safety bias is the priority coefficient set according to the color risk coefficient corresponding to the grid cells; Analyze and process the obtained comprehensive risk data and the corresponding bias priority coefficients to obtain the comprehensive risk assessment data corresponding to each path planning data; 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; Select the corresponding path planning data according to the decision priority, mark the obtained path planning data as path decision information, and send it to the decision feedback module.

[0023] 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 according to the comparison analysis, and encrypt and transmit the data processing process of the drone device according to the device transmission communication code. Its specific implementation process includes: Set up a flight feedback unit and a flight transmission unit; The flight feedback unit obtains the corresponding path decision information and marks the position information corresponding to the corresponding grid cells according to the path decision information; Obtain the flight position information and flight status data of the drone device, compare and analyze the obtained flight position information with the path decision information, judge the accuracy data during the corresponding drone flight, generate path feedback information according to the accuracy data, and generate a warning information according to the path feedback information; The flight transmission unit is used to pack the data information and data processing process collected in the drone device in real time to generate a flight data packet, encrypt the obtained flight data packet according to the device transmission communication code corresponding to the corresponding transmission time, and transmit the corresponding flight data packet according to the encryption processing result.

[0024] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent management system for unmanned aerial vehicle flight risks, characterized in that, It includes a drone management module, a flight acquisition module, a risk assessment module, an intelligent decision-making module, and a decision feedback module; The drone management module is used to obtain drone device information, generate corresponding drone device numbers according to the drone device information, and set corresponding device transmission communication codes according to the drone device numbers; The flight acquisition module is used to collect flight position data, flight radar data, flight status data, and flight environment data during the flight of the corresponding drone device in real time; The risk assessment module is used to set a three-dimensional risk obstacle image according to the flight position data and flight radar data, analyze and process the corresponding three-dimensional risk obstacle image according to the flight status data, and obtain corresponding risk assessment data in the three-dimensional risk obstacle image; The intelligent decision-making module is used to perform path analysis and processing according to the risk assessment data corresponding in the three-dimensional risk obstacle image, generate corresponding path planning information, and analyze and process the path planning information according to the flight environment data to generate corresponding path decision-making information; The decision feedback module is used to perform comparative analysis on the obtained path decision-making information according to the flight position information, generate path feedback information according to the comparative analysis, and perform encrypted transmission on the data processing process of the drone device according to the device transmission communication code.

2. The intelligent management system for unmanned aerial vehicle flight risks according to claim 1, characterized in that The process of the drone management module setting the device transmission communication code includes: Setting a device management unit and a transmission management unit; Entering drone device information through the device management unit, dividing the drone device information into fixed specification information and variable specification information, performing coding processing on the fixed specification information and variable specification information respectively to obtain a fixed specification code and a 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 device code; A transmission communication coding library is preset in the transmission management unit, and the data timestamp corresponding to the transmission moment is obtained; setting a transmission extraction method for the obtained drone device code according to the corresponding data timestamp; obtaining corresponding characters in the transmission communication coding library according to the transmission extraction method, and setting the obtained characters as the device transmission communication code.

3. The intelligent management system for unmanned aerial vehicle flight risks according to claim 2, characterized in that The process of the flight acquisition module collecting the corresponding flight position data, flight radar data, flight status data, and flight environment data includes: Obtaining sensor devices in the drone device, and the sensor devices include a Beidou satellite positioning device, a radar monitoring device, an inertial measurement device, and a meteorological monitoring device; The Beidou satellite positioning device is used to obtain flight position data during the flight of the drone; The radar monitoring device is used to obtain flight radar data during the flight of the drone; The inertial measurement device is used to obtain flight status data during the flight of the drone; The meteorological monitoring device is used to obtain flight environment data during the flight of the drone; Marking the obtained flight position data, flight radar data, flight status data, and flight environment data according to the corresponding collection time, and sending them to the risk assessment module after completion of the marking.

4. An intelligent management system for unmanned aerial vehicle flight risks according to claim 3, characterized in that The process of the risk assessment module setting the three-dimensional risk obstacle image includes: Obtain the acquisition time corresponding to the flight position data and the flight radar data. Set the data analysis space corresponding to the corresponding unit time in sequence according to the acquisition time. Set data analysis nodes in the corresponding data analysis space. Construct a three-dimensional risk obstacle image corresponding to the corresponding acquisition time through the data analysis results; Set up a three-dimensional space coordinate system, obtain the flight position information, map the flight position information into the three-dimensional space coordinate system. Take the flight position information as the reference point, obtain the flight radar data, and perform analysis and noise reduction processing. Map the noise reduction processing result to the three-dimensional image coordinate system with the relative position of the corresponding reference point to obtain the corresponding three-dimensional risk obstacle image.

5. The intelligent management system for UAV flight risks according to claim 4, wherein, The process by which the risk assessment module obtains the corresponding risk assessment data in the three-dimensional risk obstacle image includes: Set the three-dimensional risk obstacle images obtained in each data analysis space as image frames according to the acquisition time. Perform feature analysis processing on each image frame in sequence to obtain obstacle data outside the reference point, and divide it into dynamic obstacle data and static obstacle data; Set the risk assessment period according to the acquisition time. Obtain the dynamic space points and static space points corresponding to the connection between the dynamic obstacle data and the static obstacle data and the reference point corresponding to each acquisition time within the risk assessment period, and obtain the corresponding obstacle vectors; Analyze and process the change conditions of the vector start point data and the vector end point data of each obstacle vector within the risk assessment period according to the flight state data to obtain the predicted flight range data of the UAV device and the corresponding obstacle points; Map the obtained predicted flight range data into the corresponding three-dimensional risk obstacle image for visualization processing. Perform regional overlap analysis on the predicted flight range data corresponding to the UAV device and each space point according to the visualization processing result to obtain the corresponding risk assessment data.

6. The intelligent management system for UAV flight risks according to claim 5, characterized in that, The process by which the intelligent decision-making module generates the corresponding path planning information includes: Obtain the three-dimensional risk obstacle image at the current moment, perform grid processing on the three-dimensional risk obstacle image to obtain the corresponding grid cells; Set the collision color data, gradient color data, overlap color data, and blank color data for the dynamic space points, static space points, predicted flight range data, and risk assessment data respectively, and set the corresponding color risk coefficients and path priorities for each color data. Obtain the corresponding color data according to the data types corresponding to each grid cell in the three-dimensional risk obstacle image for visualization display; Preset the target point. Perform path analysis on the UAV device and the target point corresponding to the three-dimensional risk obstacle image based on the RRT algorithm for the selected target point to obtain multiple path planning information, and the path planning information includes the grid cells that the UAV device needs to pass through.

7. An intelligent management system for unmanned aerial vehicle flight risks according to claim 6, characterized in that, The process by which the intelligent decision-making module generates the corresponding path decision information includes: Construct an environmental offset influence model corresponding to the UAV device based on the deep learning algorithm, obtain the flight environment data, input the obtained flight environment data into the environmental offset influence model to obtain the offset error data during the flight of the UAV device; Based on the offset error data, comprehensively analyze the color risk coefficients of grid cells in each path planning information to obtain the comprehensive risk data corresponding to each path planning information; Conduct a proportion analysis on the quantities of different types of grid cells in the comprehensive risk coefficients, set a bias priority coefficient for the comprehensive risk data according to the proportion 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 according to the sorting results, and mark it as path decision information.

8. An intelligent management system for UAV flight risks according to claim 7, characterized in that, The decision feedback module obtains the corresponding path decision information and marks the position information corresponding to the corresponding grid cells according to the path decision information; Obtain the flight position information and flight status data of the drone device, compare and analyze the obtained flight position information with the path decision information, judge the accuracy data during the corresponding drone flight, and generate path feedback information according to the accuracy data; Package the flight data collected by the drone device and the data processing process to generate a flight data packet, obtain the current transmission time, and encrypt and transmit the flight data packet according to the transmission time to obtain the corresponding device transmission communication code.

Images