A low-altitude unmanned aerial vehicle intelligent supervision system and method based on multi-source fusion

Abstract

This invention discloses a low-altitude unmanned aerial vehicle (UAV) intelligent monitoring system and method based on multi-source fusion, relating to the field of UAV monitoring technology. The monitoring method includes the following steps: capturing each flight path of the UAV and generating corresponding flight records; collecting flight data, confirming flight scenarios and performing anomaly assessment; obtaining the expected flight path of any flight record and analyzing the deviation of the flight record; extracting abnormal features from the flight data of any flight record and analyzing the impact of each abnormal feature on the deviation; setting corresponding deviation alarm thresholds for different flight scenarios based on the abnormal features contained in any flight record; generating a real-time flight record whenever the UAV flies in real time and confirming the deviation alarm threshold of the real-time flight record; analyzing the real-time deviation of the flight path and identifying anomalies in the flight path of the real-time flight record.

Description

Technical Field

[0001] This invention relates to the field of drone monitoring technology, specifically a low-altitude drone intelligent monitoring system and method based on multi-source fusion. Background Technology

[0002] With the rapid development of the low-altitude economy, the application scale of drones in various fields continues to expand, but the resulting flight safety issues are becoming increasingly prominent. Existing regulatory systems generally use fixed thresholds for flight deviation alarms, which has significant limitations.

[0003] Fixed thresholds cannot adapt to different flight environments. For example, a drone's brief deviation from its flight path during obstacle avoidance may be misjudged as abnormal, while a small deviation at the edge of a no-fly zone may be ignored. At the same time, existing systems lack intelligent analysis of historical flight data, making it difficult to identify long-standing systematic deviations or reasonable deviation patterns in specific scenarios. They also cannot dynamically adjust alarm thresholds according to the real-time environment, resulting in rigid regulatory strategies. Summary of the Invention

[0004] The purpose of this invention is to provide a low-altitude unmanned aerial vehicle (UAV) intelligent monitoring system and method based on multi-source fusion, so as to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a method for intelligent monitoring of low-altitude unmanned aerial vehicles based on multi-source fusion, the monitoring method comprising the following steps:

[0006] Step S100: By installing monitoring equipment on the drone, the drone's flight path is captured for each flight, and corresponding flight records are generated; the flight data of each flight record is collected, the flight scenario of any flight record is confirmed, and any flight record is evaluated for anomalies.

[0007] Step S200: Obtain the expected flight route of any flight record, compare it with the actual flight route, and analyze the deviation of the flight record; extract abnormal features from the flight data of any flight record based on the flight anomaly assessment results of the arbitrary flight record.

[0008] Step S300: Based on the deviation in any flight record, analyze the impact of each abnormal feature on the deviation and obtain the impact value of each abnormal feature; according to the abnormal feature content of any flight record, set corresponding deviation alarm thresholds for different flight scenarios.

[0009] Step S400: Generate a real-time flight record whenever the UAV flies in real time, analyze the flight scene of the real-time flight record, and confirm the deviation alarm threshold of the real-time flight record; capture the real-time flight path of the UAV, analyze the real-time deviation of the flight path, and identify anomalies in the flight path of the real-time flight record.

[0010] Furthermore, step S100 includes the following steps:

[0011] Step S101: Install several monitoring devices on the drone and select the positioning device included therein. Collect the coordinate data of the drone at every unit time interval, connect the coordinate data of the drone during flight, and obtain the flight path of the drone during flight.

[0012] Step S102: Collect monitoring data from other monitoring devices during flight, set the monitoring data of each monitoring device as a dimension, and summarize the dimension data of each dimension to obtain the UAV flight data; merge the UAV flight path and flight data to generate the flight record corresponding to the flight process; the dimension data of different dimensions include flight speed fluctuation frequency, attitude angle change, signal stability, flight path completion, etc., all of which can reflect the flight status of the UAV;

[0013] Step S103: Randomly select a flight record, and randomly select one dimension of the flight data from the selected flight record. Extract features from the dimension data to obtain several features of the selected dimension. Pre-set a flight scenario database and store several flight scenarios, where each flight scenario is matched with several scenario features. Randomly select a flight scenario, and compare the several scenario features of the selected flight scenario with the several features of each dimension. If any scenario feature has the same feature as the selected flight scenario, then the UAV is in the selected flight scenario in the selected flight record. Flight scenarios include open airspace such as grasslands and deserts, complex urban environments, enclosed spaces, and severe weather conditions.

[0014] Step S104: Obtain the location of scene features in the selected flight record. For each dimension other than the location dimension, preset corresponding evaluation rules. Evaluate the dimensional data of each dimension to obtain the corresponding evaluation value. Take the average of the evaluation values ​​of each dimension to obtain the evaluation value of the selected flight record. Preset an abnormal evaluation threshold. If the evaluation value of the selected flight record is lower than the abnormal evaluation threshold, the selected flight record is set as an abnormal flight record. Since the dimensions of the UAV include flight speed fluctuation frequency, attitude angle change, signal stability, flight route completion, etc., taking flight speed fluctuation frequency as an example, the deviation between the actual fluctuation frequency and the expected fluctuation frequency is used to reflect the flight quality. Similarly, the deviation of attitude angle change and the deviation of signal stability value can also be used.

[0015] Furthermore, step S200 includes the following steps:

[0016] Step S201: Select any flight record, set the flight path captured in the selected flight record as the actual flight path, and construct a three-dimensional coordinate system to present the expected flight path and the actual flight path of the selected flight record in the three-dimensional coordinate system respectively.

[0017] Step S202: Set the initial time point of the two flight routes to t0, obtain the unit time interval between two adjacent time points in the actual flight route as Δt, and then obtain the i-th time point as t(i) = t0 + i × Δt; divide the desired flight route according to the time points to obtain the desired position coordinates A of the i-th time point. ’ t(i) Obtain the actual position coordinates A at the i-th time point in the actual flight path. t(i) The distance difference between the coordinates of two locations at the i-th time point is calculated to be ΔA. t(i) ;

[0018] Step S203: Set the instantaneous flight direction at each time point in the desired flight path to 0°, obtain the instantaneous flight direction of the two flight paths at the i-th time point, and use the initial position coordinates as the vertex to obtain the angle Δθ formed between the actual flight path and the desired flight path at the i-th time point. t(i) If the actual flight path coordinates at time point i are in the clockwise direction of the desired flight path, then Δθ t(i) If the result is positive, then it is negative; according to the formula:

[0019]

[0020] Where i is a positive integer and i∈[1,m], and m is the number of time points of the actual flight route; the deviation value P of the actual flight route in the selected flight record is calculated; if the selected flight record is an abnormal flight record, the deviation value P is set as the abnormal deviation value; the deviation of the UAV flight route is reflected by the difference between the actual position and the expected position at each time point, as well as the deviation of the flight angle. However, considering that the UAV is allowed to return to the expected route in time after deviating, the deviation value will not continue to increase after the UAV deviates from the route. Therefore, it is necessary to set the positive and negative values ​​of the included angle to correct the deviation value in real time. The absolute value after accumulation reflects the comprehensive deviation of the UAV.

[0021] Step S204: Obtain the deviation value of each flight record, and divide the deviation values ​​of each flight into a normal deviation value set and an abnormal deviation value set according to whether they are abnormal deviation values. Obtain the minimum abnormal deviation value P in the abnormal deviation value set. min If the deviation value P ≥ P in the flight record is selected. min Then, several features from each dimension of the selected flight record are set as anomalous features to obtain the set of anomalous features of the selected flight record. Since different flight scenarios will lead to different allowable deviations, but using a single threshold to reflect anomalies will result in incorrect judgments. Therefore, although the deviation values ​​are high in each flight record that exceeds the minimum anomalous deviation value, there are still normal flight situations. Therefore, it is necessary to further analyze the anomalous features that affect the deviation value to facilitate the subsequent feature analysis.

[0022] Furthermore, step S300 includes the following steps:

[0023] Step S301: Select any flight scenario, obtain each flight record under the selected flight scenario to obtain a target flight record set, select any abnormal flight record from the target flight record set and set it as the target abnormal record, and extract the abnormal feature set and abnormal deviation value of the target abnormal record.

[0024] Step S302: Excluding the target abnormal record, select a new target flight record from the target flight record set. If the target flight record is not an abnormal flight record, extract the deviation value and several features of the target flight record. If the deviation value of the target flight record is an abnormal deviation value, compare each abnormal feature in the abnormal feature set of the target abnormal record with several features of the target flight record to obtain several identical features, and remove each identical feature from the abnormal feature set. If the deviation value of the target flight record is not an abnormal deviation value, retain each identical feature in the abnormal feature set and remove the remaining abnormal features. If the target flight record is an abnormal flight record, merge the target abnormal record with its two abnormal feature sets. If there are abnormal features of numerical type, merge the abnormal feature values ​​under the same dimension to obtain an abnormal value range and match it with the remaining abnormal features of the same dimension.

[0025] Compare the normal flight records with the abnormal flight records. If the deviation value of the normal flight record is an abnormal deviation value, it means that there are abnormal features that are the same but do not cause the difference in the results, and they need to be eliminated. Similarly, if the deviation value of the normal flight record is a normal deviation value, then the same features are actually abnormal features that affect the results.

[0026] Step S303: Correct the abnormal feature set obtained by comparing any two target flight records in the target flight record set, and summarize the corrected abnormal feature sets to obtain the abnormal feature set of the selected flight scene; randomly select an abnormal feature from the abnormal feature set of the selected flight scene to obtain the abnormal value interval corresponding to the selected abnormal feature, preset an expected value interval (x1, x2) for the dimension where the selected abnormal feature is located, set the abnormal value interval as (y1, y2), and calculate the deviation amplitude f of the selected abnormal feature according to the formula:

[0027]

[0028] Max() is the function to take the maximum value; by taking the average of the abnormal interval and the normal interval respectively, a fair judgment can be made on the deviation of the abnormal feature, and a more accurate result can be obtained.

[0029] Step S304: Obtain each abnormal deviation value in the target flight record set and take the average value to obtain an average deviation value P. ave Let the selected anomalous feature be the k-th anomalous feature in the anomalous feature set. Then, find the number of remaining anomalous features in the dimension containing the k-th anomalous feature, excluding the anomalous value range. k According to the formula:

[0030]

[0031] Where d is a positive integer and d∈[1,s], s is the number of abnormal features contained in the abnormal feature set, and f k f represents the deviation magnitude of the k-th anomalous feature. d Let Y be the deviation magnitude of the d-th anomalous feature; calculate the influence value Y of the k-th anomalous feature. k The dimensions of different abnormal features differ. By eliminating the difference in dimensions through the deviation amplitude, the influence of each abnormal feature can be effectively identified.

[0032] Step S305: Randomly select one target flight record from the set of target flight records for the selected flight scenario, obtain the deviation value of the selected target flight record at each time point, and set the maximum deviation value P at the i-th time point. t(i) Extract the various anomalous features contained in the selected target flight record, and set the influence value of the j-th anomalous feature to Y. j According to the formula:

[0033]

[0034] Where j is a positive integer and j∈[1,r], and r is the number of abnormal features of the selected target flight records; the comprehensive deviation value P of the selected target flight records is calculated. ’ ;

[0035] Step S306: Obtain the comprehensive deviation value of each target flight record in the target flight record set, summarize the comprehensive deviation values ​​of abnormal flight records, and extract a minimum comprehensive deviation value P. ’ min Then, extract the maximum comprehensive deviation value P from the comprehensive deviation values ​​of the remaining target flight records. ’ max If P ’ min >P ’ max Then set the deviation alarm threshold P for the selected flight scenario. th =P ’ max Otherwise, P th =P ’ min .

[0036] Furthermore, step S400 includes the following steps:

[0037] Step S401: Collect flight data during the real-time flight of the UAV, capture the flight path of the UAV in real time, generate a real-time flight record, and update the flight path in the real-time flight record in real time.

[0038] Step S402: Extract features from the flight data of the real-time flight record, compare the features with each flight scenario in the flight scenario database, determine the flight scenario of the real-time flight record, and obtain the deviation alarm threshold P of the real-time flight record. th ;

[0039] Step S403: Obtain the set of abnormal features in the flight scenario of the real-time flight record; compare each feature of the real-time flight record with the abnormal features to obtain several actual abnormal features of the real-time flight record; obtain the real-time position coordinates of the real-time flight record at the current moment to obtain the deviation value P of the UAV at the current moment. now The influence values ​​of each actual anomaly are summed to obtain the comprehensive deviation value P of the real-time flight record. ’ now If P ’ now >P th If so, an abnormal alert will be sent regarding the current flight status of the drone.

[0040] To better implement the above methods, a low-altitude UAV intelligent monitoring system is also proposed. The monitoring system includes a historical route acquisition module, a route deviation analysis module, an expected deviation adjustment module, and a real-time anomaly analysis module.

[0041] The historical route acquisition module is used to capture the flight path of the drone for each time by installing monitoring equipment on the drone and generate corresponding flight records; it collects flight data for each flight record, confirms the flight scenario of any flight record, and performs anomaly assessment on any flight record;

[0042] The route deviation analysis module is used to obtain the expected flight route of any flight record, analyze the deviation of the flight record by comparing it with the actual flight route, and extract abnormal features from the flight data of any flight record based on the flight anomaly assessment results.

[0043] The expected deviation adjustment module is used to analyze the impact of various abnormal features on the deviation based on the deviation in any flight record, and obtain the impact value of each abnormal feature; according to the abnormal feature content of any flight record, it sets corresponding deviation alarm thresholds for different flight scenarios.

[0044] The real-time anomaly analysis module is used to generate a real-time flight record whenever the UAV flies in real time, analyze the flight scene of the real-time flight record, confirm the deviation alarm threshold of the real-time flight record, capture the real-time flight path of the UAV, analyze the real-time deviation of the flight path, and identify anomalies in the flight path of the real-time flight record.

[0045] Furthermore, the historical route acquisition module includes a flight route acquisition unit and a flight quality assessment unit;

[0046] The flight path acquisition unit is used to capture the flight path of the UAV for each flight by installing monitoring equipment on the UAV and generate corresponding flight records; the flight quality assessment unit is used to collect flight data for each flight record, confirm the flight scenario of any flight record and perform anomaly assessment for any flight record.

[0047] Furthermore, the route deviation analysis module includes a route deviation identification unit and an anomaly feature extraction unit;

[0048] The route deviation identification unit is used to obtain the expected flight route of any flight record and analyze the deviation of the flight record by comparing it with the actual flight route; the anomaly feature extraction unit is used to extract anomaly features from the flight data of any flight record based on the flight anomaly assessment results of any flight record.

[0049] Furthermore, the expected deviation adjustment module includes a feature deviation association unit and a deviation threshold division unit;

[0050] The feature deviation association unit is used to analyze the impact of each abnormal feature on the deviation based on the deviation in any flight record, and obtain the impact value of each abnormal feature; the deviation threshold division unit is used to set corresponding deviation alarm thresholds for different flight scenarios according to the abnormal feature content of any flight record.

[0051] Furthermore, the real-time anomaly analysis module includes a real-time deviation confirmation unit and an abnormal flight identification unit;

[0052] The real-time deviation confirmation unit is used to generate a real-time flight record whenever the UAV flies in real time, analyze the flight scene of the real-time flight record, and confirm the deviation alarm threshold of the real-time flight record; the abnormal flight identification unit is used to capture the real-time flight path of the UAV, analyze the real-time deviation of the flight path, and identify anomalies in the flight path of the real-time flight record.

[0053] Compared with the prior art, the beneficial effects of the present invention are:

[0054] 1. This invention analyzes the abnormal features and deviations in historical flight records to dynamically adjust the abnormal alarm thresholds of UAVs in different flight scenarios. This solves the problem of incorrect judgments caused by the fixed thresholds used in traditional abnormal monitoring, greatly reduces the probability of false detections, and improves monitoring efficiency.

[0055] 2. This invention, by installing multiple monitoring devices on the drone, comprehensively analyzes the drone's flight status. Through feature recognition and scene matching, it accurately identifies the drone's flight scene and abnormal features at any given time, and can accurately grasp the drone's flight status in different environments.

[0056] 3. This invention makes real-time judgments on real-time flight data and the abnormal alarm threshold of the flight scenario, and calculates a comprehensive deviation value by combining the influence value of abnormal features. It can promptly identify abnormal route deviations, effectively prevent flight accidents, and improve the overall safety of low-altitude UAVs. Attached Figure Description

[0057] Figure 1 This is a schematic diagram illustrating the steps of a multi-source fusion-based intelligent monitoring method for low-altitude unmanned aerial vehicles (UAVs).

[0058] Figure 2 This is a schematic diagram of a low-altitude unmanned aerial vehicle (UAV) intelligent monitoring system based on multi-source fusion. Detailed Implementation

[0059] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0060] Example: Figures 1 to 2 As shown, this invention provides an intelligent monitoring method for low-altitude unmanned aerial vehicles (UAVs) based on multi-source fusion. The monitoring method includes the following steps:

[0061] Step S100: By installing monitoring equipment on the drone, the drone's flight path is captured for each flight, and corresponding flight records are generated; the flight data of each flight record is collected, the flight scenario of any flight record is confirmed, and any flight record is evaluated for anomalies.

[0062] Step S100 includes the following steps:

[0063] Step S101: Install several monitoring devices on the drone and select the positioning device included therein. Collect the coordinate data of the drone at every unit time interval, connect the coordinate data of the drone during flight, and obtain the flight path of the drone during flight.

[0064] Step S102: Collect monitoring data from the other monitoring devices during flight, set the monitoring data of each monitoring device as a dimension, summarize the dimension data of each dimension to obtain the UAV flight data; merge the UAV flight route and flight data to generate the flight record corresponding to the flight process.

[0065] Step S103: Randomly select a flight record, and randomly select one dimension of the flight data from the selected flight record. Extract features from the dimension data to obtain several features of the selected dimension. Pre-set a flight scene database and store several flight scenes, where each flight scene is matched with several scene features. Randomly select a flight scene, and compare the several scene features of the selected flight scene with the several features of each dimension. If any scene feature has the same feature as the selected scene, then it is determined that the drone is in the selected flight scene in the selected flight record.

[0066] Step S104: Obtain the dimension in which the scene features are located in the selected flight record; preset corresponding evaluation rules for each dimension other than the dimension in which they are located; evaluate the dimension data of each dimension to obtain the corresponding evaluation value; take the average of the evaluation values ​​of each dimension to obtain the evaluation value of the selected flight record; preset an abnormal evaluation threshold; if the evaluation value of the selected flight record is lower than the abnormal evaluation threshold, then the selected flight record is set as an abnormal flight record.

[0067] Step S200: Obtain the expected flight route of any flight record, compare it with the actual flight route, and analyze the deviation of the flight record; extract abnormal features from the flight data of any flight record based on the flight anomaly assessment results of the arbitrary flight record.

[0068] Step S200 includes the following steps:

[0069] Step S201: Select any flight record, set the flight path captured in the selected flight record as the actual flight path, and construct a three-dimensional coordinate system to present the expected flight path and the actual flight path of the selected flight record in the three-dimensional coordinate system respectively.

[0070] Step S202: Set the initial time point of the two flight routes to t0, obtain the unit time interval between two adjacent time points in the actual flight route as Δt, and then obtain the i-th time point as t(i) = t0 + i × Δt; divide the desired flight route according to the time points to obtain the desired position coordinates A of the i-th time point. ’ t(i) Obtain the actual position coordinates A at the i-th time point in the actual flight path. t(i) The distance difference between the coordinates of two locations at the i-th time point is calculated to be ΔA. t((i) ;

[0071] Step S203: Set the instantaneous flight direction at each time point in the desired flight path to 0°, obtain the instantaneous flight direction of the two flight paths at the i-th time point, and use the initial position coordinates as the vertex to obtain the angle Δθ formed between the actual flight path and the desired flight path at the i-th time point. t(i) If the actual flight path coordinates at time point i are in the clockwise direction of the desired flight path, then Δθ t(i) If the result is positive, then it is negative; according to the formula:

[0072]

[0073] Where i is a positive integer and i∈[1,m], and m is the number of time points of the actual flight route; calculate the deviation value P of the actual flight route in the selected flight record; if the selected flight record is an abnormal flight record, then set the deviation value P as the abnormal deviation value.

[0074] Example 1: The desired flight path of the UAV is divided into 4 time points, and the actual flight path is also divided into 4 time points. The distance difference between the position coordinates of the two paths at each time point is 1, 2, 3, and 4, respectively, and the angles on both sides at each time point are 60, 30, -30, and -45, respectively. The deviation of the actual flight path is calculated to be P = |60×1 + 30×2 - 30×3 - 45×4| = 90.

[0075] Step S204: Obtain the deviation value of each flight record, and divide the deviation values ​​of each flight into a normal deviation value set and an abnormal deviation value set according to whether they are abnormal deviation values. Obtain the minimum abnormal deviation value P in the abnormal deviation value set. min If the deviation value P ≥ P in the flight record is selected. min Then, several features from each dimension of the selected flight record will be set as anomalous features, resulting in a set of anomalous features for the selected flight record.

[0076] Step S300: Based on the deviation in any flight record, analyze the impact of each abnormal feature on the deviation and obtain the impact value of each abnormal feature; according to the abnormal feature content of any flight record, set corresponding deviation alarm thresholds for different flight scenarios.

[0077] Step S300 includes the following steps:

[0078] Step S301: Select any flight scenario, obtain each flight record under the selected flight scenario to obtain a target flight record set, select any abnormal flight record from the target flight record set and set it as the target abnormal record, and extract the abnormal feature set and abnormal deviation value of the target abnormal record.

[0079] Step S302: Excluding the target abnormal record, select a new target flight record from the target flight record set. If the target flight record is not an abnormal flight record, extract the deviation value and several features of the target flight record. If the deviation value of the target flight record is an abnormal deviation value, compare each abnormal feature in the abnormal feature set of the target abnormal record with several features of the target flight record to obtain several identical features, and remove each identical feature from the abnormal feature set. If the deviation value of the target flight record is not an abnormal deviation value, retain each identical feature in the abnormal feature set and remove the remaining abnormal features. If the target flight record is an abnormal flight record, merge the target abnormal record with its two abnormal feature sets. If there are abnormal features of numerical type, merge the abnormal feature values ​​under the same dimension to obtain an abnormal value range and match it with the remaining abnormal features of the same dimension.

[0080] Step S303: Correct the abnormal feature set obtained by comparing any two target flight records in the target flight record set, and summarize the corrected abnormal feature sets to obtain the abnormal feature set of the selected flight scene; randomly select an abnormal feature from the abnormal feature set of the selected flight scene to obtain the abnormal value interval corresponding to the selected abnormal feature, preset an expected value interval (x1, x2) for the dimension where the selected abnormal feature is located, set the abnormal value interval as (y1, y2), and calculate the deviation amplitude f of the selected abnormal feature according to the formula:

[0081]

[0082] Max() is the function to find the maximum value;

[0083] Example 2: Set the expected value range corresponding to an abnormal feature as (14, 20). If the abnormal value range is (24, 30), then f = |17-27| / (30-14) = 0.625. If the abnormal value range is (10, 12), then f = |11-17| / (20-10) = 0.6.

[0084] Step S304: Obtain each abnormal deviation value in the target flight record set and take the average value to obtain an average deviation value P. ave Let the selected anomalous feature be the k-th anomalous feature in the anomalous feature set. Then, find the number of remaining anomalous features in the dimension containing the k-th anomalous feature, excluding the anomalous value range. k According to the formula:

[0085]

[0086] Where d is a positive integer and d∈[1,s], s is the number of abnormal features contained in the abnormal feature set, and f k f represents the deviation magnitude of the k-th anomalous feature. d Let Y be the deviation magnitude of the d-th anomalous feature; calculate the influence value Y of the k-th anomalous feature. k ;

[0087] Step S305: Randomly select one target flight record from the set of target flight records for the selected flight scenario, obtain the deviation value of the selected target flight record at each time point, and set the maximum deviation value P at the i-th time point. t(i) Extract the various anomalous features contained in the selected target flight record, and set the influence value of the j-th anomalous feature to Y. j According to the formula:

[0088]

[0089] Where j is a positive integer and j∈[1,r], and r is the number of abnormal features of the selected target flight records; the comprehensive deviation value P of the selected target flight records is calculated. ’ ;

[0090] Step S306: Obtain the comprehensive deviation value of each target flight record in the target flight record set, summarize the comprehensive deviation values ​​of abnormal flight records, and extract a minimum comprehensive deviation value P. ’ min Then, extract the maximum comprehensive deviation value P from the comprehensive deviation values ​​of the remaining target flight records. ’ max If P ’ min >P ’ maxThen set the deviation alarm threshold P for the selected flight scenario. th =P ’ max Otherwise, P th =P ’ min .

[0091] Step S400: Generate a real-time flight record whenever the UAV flies in real time, analyze the flight scene of the real-time flight record, and confirm the deviation alarm threshold of the real-time flight record; capture the real-time flight path of the UAV, analyze the real-time deviation of the flight path, and identify anomalies in the flight path of the real-time flight record.

[0092] Step S400 includes the following steps:

[0093] Step S401: Collect flight data during the real-time flight of the UAV, capture the flight path of the UAV in real time, generate a real-time flight record, and update the flight path in the real-time flight record in real time.

[0094] Step S402: Extract features from the flight data of the real-time flight record, compare the features with each flight scenario in the flight scenario database, determine the flight scenario of the real-time flight record, and obtain the deviation alarm threshold P of the real-time flight record. th ;

[0095] Step S403: Obtain the set of abnormal features in the flight scenario of the real-time flight record; compare each feature of the real-time flight record with the abnormal features to obtain several actual abnormal features of the real-time flight record; obtain the real-time position coordinates of the real-time flight record at the current moment to obtain the deviation value P of the UAV at the current moment. now The influence values ​​of each actual anomaly are summed to obtain the comprehensive deviation value P of the real-time flight record. ’ now If P ’ now >P th If so, an abnormal alert will be sent regarding the current flight status of the drone.

[0096] A low-altitude unmanned aerial vehicle (UAV) intelligent monitoring system, comprising a historical route acquisition module, a route deviation analysis module, an expected deviation adjustment module, and a real-time anomaly analysis module;

[0097] The historical route acquisition module is used to capture the flight path of the drone for each time by installing monitoring equipment on the drone and generate corresponding flight records; it collects flight data for each flight record, confirms the flight scenario of any flight record, and performs anomaly assessment on any flight record;

[0098] The route deviation analysis module is used to obtain the expected flight route of any flight record, analyze the deviation of the flight record by comparing it with the actual flight route, and extract abnormal features from the flight data of any flight record based on the flight anomaly assessment results.

[0099] The expected deviation adjustment module is used to analyze the impact of various abnormal features on the deviation based on the deviation in any flight record, and obtain the impact value of each abnormal feature; according to the abnormal feature content of any flight record, it sets corresponding deviation alarm thresholds for different flight scenarios.

[0100] The real-time anomaly analysis module is used to generate a real-time flight record whenever the UAV flies in real time, analyze the flight scene of the real-time flight record, confirm the deviation alarm threshold of the real-time flight record, capture the real-time flight path of the UAV, analyze the real-time deviation of the flight path, and identify anomalies in the flight path of the real-time flight record.

[0101] The historical route acquisition module includes a flight route acquisition unit and a flight quality assessment unit.

[0102] The flight path acquisition unit is used to capture the flight path of the UAV for each flight by installing monitoring equipment on the UAV and generate corresponding flight records; the flight quality assessment unit is used to collect flight data for each flight record, confirm the flight scenario of any flight record and perform anomaly assessment for any flight record.

[0103] The route deviation analysis module includes a route deviation identification unit and an anomaly feature extraction unit.

[0104] The route deviation identification unit is used to obtain the expected flight route of any flight record and analyze the deviation of the flight record by comparing it with the actual flight route; the anomaly feature extraction unit is used to extract anomaly features from the flight data of any flight record based on the flight anomaly assessment results of any flight record.

[0105] The expected deviation adjustment module includes a feature deviation association unit and a deviation threshold division unit.

[0106] The feature deviation association unit is used to analyze the impact of each abnormal feature on the deviation based on the deviation in any flight record, and obtain the impact value of each abnormal feature; the deviation threshold division unit is used to set corresponding deviation alarm thresholds for different flight scenarios according to the abnormal feature content of any flight record.

[0107] The real-time anomaly analysis module includes a real-time deviation confirmation unit and an abnormal flight identification unit.

[0108] The real-time deviation confirmation unit is used to generate a real-time flight record whenever the UAV flies in real time, analyze the flight scene of the real-time flight record, and confirm the deviation alarm threshold of the real-time flight record; the abnormal flight identification unit is used to capture the real-time flight path of the UAV, analyze the real-time deviation of the flight path, and identify anomalies in the flight path of the real-time flight record.

[0109] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for intelligent monitoring of low-altitude unmanned aerial vehicles (UAVs) based on multi-source fusion, characterized in that: The regulatory approach includes the following steps: Step S100: By installing monitoring equipment on the drone, the drone's flight path is captured for each flight, and corresponding flight records are generated; the flight data of each flight record is collected, the flight scenario of any flight record is confirmed, and any flight record is evaluated for anomalies. Step S200: Obtain the expected flight route of any flight record, compare it with the actual flight route, and analyze the deviation of the flight record; extract abnormal features from the flight data of any flight record based on the flight anomaly assessment results of the arbitrary flight record. Step S301: Select any flight scenario and obtain a target flight record set by acquiring all flight records under the selected flight scenario; Step S303: Correct the abnormal feature set obtained by comparing any two target flight records in the target flight record set, and summarize the corrected abnormal feature sets to obtain the abnormal feature set of the selected flight scene; randomly select an abnormal feature from the abnormal feature set of the selected flight scene to obtain the abnormal value interval corresponding to the selected abnormal feature, preset an expected value interval (x1, x2) for the dimension where the selected abnormal feature is located, set the abnormal value interval as (y1, y2), and calculate the deviation amplitude f of the selected abnormal feature according to the formula: ； Max() is the function to find the maximum value; Step S304: Obtain each abnormal deviation value in the target flight record set and take the average value to obtain an average deviation value P. ave Let the selected anomalous feature be the k-th anomalous feature in the anomalous feature set. Then, find the number of remaining anomalous features in the dimension containing the k-th anomalous feature, excluding the anomalous value range. k According to the formula: ； Where d is a positive integer and d∈[1,s], s is the number of abnormal features contained in the abnormal feature set, and f k f represents the deviation magnitude of the k-th anomalous feature. d The deviation magnitude of the d-th anomalous feature is given; the influence value Y of the k-th anomalous feature is calculated. k ; Step S305: Randomly select one target flight record from the set of target flight records for the selected flight scenario, obtain the deviation value of the selected target flight record at each time point, and set the maximum deviation value P at the i-th time point. t(i) Extract the various anomalous features contained in the selected target flight record, and set the influence value of the j-th anomalous feature to Y. j According to the formula: ； Where j is a positive integer and j∈[1,r], and r is the number of abnormal features of the selected target flight records; the comprehensive deviation value P of the selected target flight records is calculated. ’ ; Step S306: Obtain the comprehensive deviation value of each target flight record in the target flight record set, summarize the comprehensive deviation values ​​of abnormal flight records, and extract a minimum comprehensive deviation value P. ’ min Then, extract the maximum comprehensive deviation value P from the comprehensive deviation values ​​of the remaining target flight records. ’ max If P ’ min >P ’ max Then set the deviation alarm threshold P for the selected flight scenario. th =P ’ max Otherwise, P th =P ’ min ; Step S400: Generate a real-time flight record whenever the UAV flies in real time, analyze the flight scene of the real-time flight record, and confirm the deviation alarm threshold of the real-time flight record; capture the real-time flight path of the UAV, analyze the real-time deviation of the flight path, and identify anomalies in the flight path of the real-time flight record.

2. The intelligent monitoring method for low-altitude unmanned aerial vehicles based on multi-source fusion according to claim 1, characterized in that: Step S100 includes the following steps: Step S101: Install several monitoring devices on the drone and select the positioning device included therein. Collect the coordinate data of the drone at every unit time interval, connect the coordinate data of the drone during flight, and obtain the flight path of the drone during flight. Step S102: Collect monitoring data from the other monitoring devices during flight, set the monitoring data of each monitoring device as a dimension, summarize the dimension data of each dimension to obtain the UAV flight data; merge the UAV flight route and flight data to generate the flight record corresponding to the flight process. Step S103: Randomly select a flight record, and randomly select one dimension of the flight data from the selected flight record. Extract features from the dimension data to obtain several features of the selected dimension. Pre-set a flight scene database and store several flight scenes, where each flight scene is matched with several scene features. Randomly select a flight scene, and compare the several scene features of the selected flight scene with the several features of each dimension. If any scene feature has the same feature as the selected scene, then it is determined that the drone is in the selected flight scene in the selected flight record. Step S104: Obtain the dimension in which the scene features are located in the selected flight record; preset corresponding evaluation rules for each dimension other than the dimension in which they are located; evaluate the dimension data of each dimension to obtain the corresponding evaluation value; take the average of the evaluation values ​​of each dimension to obtain the evaluation value of the selected flight record; preset an abnormal evaluation threshold; if the evaluation value of the selected flight record is lower than the abnormal evaluation threshold, then the selected flight record is set as an abnormal flight record.

3. The intelligent monitoring method for low-altitude unmanned aerial vehicles based on multi-source fusion according to claim 2, characterized in that: Step S200 includes the following steps: Step S201: Select any flight record, set the flight path captured in the selected flight record as the actual flight path, and construct a three-dimensional coordinate system to present the expected flight path and the actual flight path of the selected flight record in the three-dimensional coordinate system respectively. Step S202: Set the initial time point of the two flight paths to t0, obtain the unit time interval between two adjacent time points in the actual flight path as Δt, and then obtain the i-th time point as t(i) = t0 + i × Δt; divide the desired flight path according to the time points to obtain the desired position coordinates A of the i-th time point. ’ t(i) Obtain the actual position coordinates A at the i-th time point in the actual flight path. t(i) The distance difference between the coordinates of two locations at the i-th time point is calculated to be ΔA. t(i) ; Step S203: Set the instantaneous flight direction at each time point in the desired flight path to 0°, obtain the instantaneous flight direction of the two flight paths at the i-th time point, and use the initial position coordinates as the vertex to obtain the angle Δθ formed between the actual flight path and the desired flight path at the i-th time point. t(i) If the actual flight path coordinates at time point i are in the clockwise direction of the desired flight path, then Δθ t(i) If the result is positive, then it is negative; according to the formula: ； Where i is a positive integer and i∈[1,m], and m is the number of time points of the actual flight route; calculate the deviation value P of the actual flight route in the selected flight record; if the selected flight record is an abnormal flight record, then set the deviation value P as the abnormal deviation value. Step S204: Obtain the deviation value of each flight record, and divide the deviation values ​​of each flight into a normal deviation value set and an abnormal deviation value set according to whether they are abnormal deviation values. Obtain the minimum abnormal deviation value P in the abnormal deviation value set. min If the deviation value P ≥ P in the flight record is selected. min Then, several features from each dimension of the selected flight record will be set as anomalous features, resulting in a set of anomalous features for the selected flight record.

4. The intelligent monitoring method for low-altitude unmanned aerial vehicles based on multi-source fusion according to claim 3, characterized in that: Step S300 includes the following steps: Randomly select an abnormal flight record from the target flight record set and set it as the target abnormal record, and extract the abnormal feature set and abnormal deviation value of the target abnormal record; Step S302: Excluding the target abnormal record, select a new target flight record from the target flight record set. If the target flight record is not an abnormal flight record, extract the deviation value and several features of the target flight record. If the deviation value of the target flight record is an abnormal deviation value, compare each abnormal feature in the abnormal feature set of the target abnormal record with several features of the target flight record to obtain several identical features, and remove each identical feature from the abnormal feature set. If the deviation value of the target flight record is not an abnormal deviation value, retain each identical feature in the abnormal feature set and remove the remaining abnormal features. If the target flight record is an abnormal flight record, merge the target abnormal record with its two abnormal feature sets. If there are abnormal features of numerical type, merge the abnormal feature values ​​under the same dimension to obtain an abnormal value range and match it with the remaining abnormal features of the same dimension.

5. The intelligent monitoring method for low-altitude unmanned aerial vehicles based on multi-source fusion according to claim 4, characterized in that: Step S400 includes the following steps: Step S401: Collect flight data during the real-time flight of the UAV, capture the flight path of the UAV in real time, generate a real-time flight record, and update the flight path in the real-time flight record in real time. Step S402: Extract features from the flight data of the real-time flight record, compare the features with each flight scenario in the flight scenario database, determine the flight scenario of the real-time flight record, and obtain the deviation alarm threshold P of the real-time flight record. th ; Step S403: Obtain the set of abnormal features in the flight scenario of the real-time flight record; compare each feature of the real-time flight record with the abnormal features to obtain several actual abnormal features of the real-time flight record; obtain the real-time position coordinates of the real-time flight record at the current moment to obtain the deviation value P of the UAV at the current moment. now The influence values ​​of each actual anomaly are summed to obtain the comprehensive deviation value P of the real-time flight record. ’ now If P ’ now >P th If so, an abnormal alert will be sent regarding the current flight status of the drone.

6. A low-altitude unmanned aerial vehicle (UAV) intelligent monitoring system, used to execute the low-altitude UAV intelligent monitoring method based on multi-source fusion as described in any one of claims 1-5, characterized in that: The monitoring system includes a historical route acquisition module, a route deviation analysis module, an expected deviation adjustment module, and a real-time anomaly analysis module. The historical route acquisition module is used to capture each flight route of the UAV by installing monitoring equipment on the UAV, generate corresponding flight records, collect flight data of each flight record, confirm the flight scenario of any flight record, and perform anomaly assessment on any flight record. The route deviation analysis module is used to obtain the expected flight route of any flight record, analyze the deviation of the flight record by comparing it with the actual flight route, and extract abnormal features from the flight data of any flight record based on the flight anomaly assessment results. The expected deviation adjustment module is used to analyze the impact of various abnormal features on the deviation based on the deviation in any flight record, and obtain the impact value of each abnormal feature; and to set corresponding deviation alarm thresholds for different flight scenarios according to the abnormal features contained in any flight record. The real-time anomaly analysis module is used to generate a real-time flight record whenever the UAV flies in real time, analyze the flight scene of the real-time flight record, confirm the deviation alarm threshold of the real-time flight record, capture the real-time flight path of the UAV, analyze the real-time deviation of the flight path, and identify anomalies in the flight path of the real-time flight record.

7. A low-altitude unmanned aerial vehicle (UAV) intelligent monitoring system according to claim 6, characterized in that: The historical route acquisition module includes a flight route acquisition unit and a flight quality assessment unit; The flight path acquisition unit is used to capture each flight path of the UAV by installing monitoring equipment on the UAV and generate corresponding flight records; the flight quality assessment unit is used to collect flight data of each flight record, confirm the flight scenario of any flight record and perform anomaly assessment on any flight record.

8. A low-altitude unmanned aerial vehicle (UAV) intelligent monitoring system according to claim 6, characterized in that: The route deviation analysis module includes a route deviation identification unit and an anomaly feature extraction unit; The route deviation identification unit is used to obtain the expected flight route of any flight record and analyze the deviation of the flight record by comparing it with the actual flight route; the abnormal feature extraction unit is used to extract abnormal features from the flight data of any flight record based on the flight anomaly assessment results of any flight record.

9. A low-altitude unmanned aerial vehicle (UAV) intelligent monitoring system according to claim 6, characterized in that: The expected deviation adjustment module includes a feature deviation association unit and a deviation threshold division unit; The feature deviation association unit is used to analyze the impact of each abnormal feature on the deviation based on the deviation in any flight record, and obtain the impact value of each abnormal feature; the deviation threshold division unit is used to set corresponding deviation alarm thresholds for different flight scenarios according to the abnormal feature content of any flight record.

10. A low-altitude unmanned aerial vehicle (UAV) intelligent monitoring system according to claim 6, characterized in that: The real-time anomaly analysis module includes a real-time deviation confirmation unit and an abnormal flight identification unit; The real-time deviation confirmation unit is used to generate a real-time flight record whenever the UAV flies in real time, analyze the flight scene of the real-time flight record, and confirm the deviation alarm threshold of the real-time flight record; the abnormal flight identification unit is used to capture the real-time flight path of the UAV, analyze the real-time deviation of the flight path, and identify anomalies in the flight path of the real-time flight record.

Images