An integrated comprehensive monitoring system for unmanned aerial vehicles and a method thereof

Abstract

The application discloses an unmanned aerial vehicle integrated comprehensive monitoring system and method, and relates to the technical field of unmanned aerial vehicle management. The system synchronously broadcasts a standard 5G synchronization signal block and receives airspace target echoes to generate a local detection spectrum; symbol-level fusion processing is performed on the local detection spectrum of multiple base stations, an improved spatial smoothing multiple signal classification algorithm is used for joint spectrum bias minimization processing, and the position and speed of a target unmanned aerial vehicle are extracted; the identity legality and flight category of the target unmanned aerial vehicle are identified; the perception capacity is dynamically estimated, and traffic scheduling is performed when overload occurs; flight instructions are generated or security linkage measures are triggered according to the identification result; and task load data returned by the unmanned aerial vehicle is processed and abnormality detection is performed. The application can improve the coverage and precision of low-altitude airspace unmanned aerial vehicle synchronous perception, accurately identify illegal flight behavior and quickly respond, and enhance the airspace safety monitoring capacity in complex environments.

Description

Technical Field

[0001] This invention relates to the field of data acquisition and processing technology, and in particular to a highly reliable lossless data acquisition and processing system and method. Background Technology

[0002] In recent years, unmanned aerial vehicles (UAVs) have been widely used in logistics, urban management, environmental monitoring, and security patrols, creating new demands for low-altitude airspace management and supervision technologies. Existing UAV supervision methods mainly include ground-based radar detection, base station wireless positioning, and active broadcasting of aircraft identification identifiers, supplemented by single-point data detection or rule-based anomaly behavior judgment to achieve UAV positioning, identification, and management. These traditional methods, to a certain extent, supported the supervision needs of early small-scale UAV applications, forming a basic flight monitoring system.

[0003] However, with the rapid increase in the number of drones in low-altitude airspace and the increasing complexity of application scenarios, existing monitoring technologies are gradually revealing several limitations. On the one hand, ground-based sensing methods have limited airspace coverage, resulting in blind spots and insufficient synchronization accuracy, making it difficult to achieve simultaneous high-precision detection of multiple targets. On the other hand, multi-base station collaborative sensing relies solely on simple fusion at the post-detection level, lacking underlying symbol-level data fusion optimization, leading to significant deviations in joint detection results and affecting the accuracy of target parameter extraction. Furthermore, traditional drone identification methods largely depend on static broadcasts or single-point data analysis, lacking intelligent classification and legitimacy determination mechanisms based on historical flight track features. In terms of system capacity management, existing technologies generally lack dynamic capacity estimation and traffic scheduling strategies based on real-time sensing results, failing to effectively address overload issues in high-density flight scenarios. Finally, in anomaly detection, existing methods mainly rely on single sensor thresholds or fixed models, lacking deep structured analysis of drone mission payload data and dynamic adaptive detection mechanisms, resulting in insufficient accuracy and real-time performance in anomaly identification.

[0004] Therefore, there is an urgent need to propose an integrated regulatory system that can achieve low-altitude wide-coverage synchronous perception, symbol-level data fusion optimization, flight identification based on flight path characteristics, dynamic capacity management and scheduling control, and intelligent anomaly detection based on mission payload data, so as to improve the overall efficiency, safety and intelligence level of UAV airspace management. Summary of the Invention

[0005] The purpose of this invention is to address the problems existing in current unmanned aerial vehicle (UAV) monitoring systems in terms of airspace perception coverage, data fusion accuracy, intelligent flight identification, dynamic capacity management, and mission anomaly detection. This invention provides an integrated UAV monitoring system and method to achieve low-altitude, wide-coverage synchronous perception, symbol-level data fusion optimization, flight identification based on flight path features, dynamic capacity management and scheduling control, and intelligent anomaly detection of mission payload data.

[0006] The present invention achieves the above objectives through the following technical solutions:

[0007] On the one hand, the present invention provides an integrated monitoring system for unmanned aerial vehicles, comprising:

[0008] The base station sensing module is used to synchronously broadcast the standard 5G synchronization signal block (SSB) and receive spatial target echoes to generate a local detection spectrum.

[0009] The data fusion module is used to perform symbol-level fusion processing on the local detection spectra of multiple base stations and extract the position and velocity of the UAV target based on the fusion results. The data fusion module adopts a symbol-level fusion method and performs joint spectral bias minimization processing based on the improved spatial smoothing multiple signal classification (MUSIC) algorithm.

[0010] The capacity management module is used to dynamically estimate the base station's sensing capacity and perform drone traffic scheduling when overloaded.

[0011] The flight identification module is used to combine fusion detection results and regulatory databases to identify the identity, legality, and flight category of target drones;

[0012] The dispatch and control module is used to issue flight commands or trigger security linkage measures based on the target classification results;

[0013] The intelligent analysis module is used to process the mission payload data transmitted back by the UAV and to perform anomaly detection.

[0014] A further improvement of the present invention is that the base station sensing module includes:

[0015] A multi-beam transmitting unit is used to synchronously broadcast a standard 5G synchronization signal block (SSB) with a predetermined beam sequence.

[0016] The echo receiving unit is used to switch to the receiving mode after each transmission cycle to receive echo signals from airspace targets.

[0017] The time synchronization unit is used to perform time synchronization control based on the 5G NR system synchronization signal or the global navigation satellite system signal, so that the time synchronization error between base stations is controlled within a set threshold.

[0018] The signal processing unit is used to perform preprocessing and frequency domain transformation processing on the received echo signal;

[0019] The spatial spectrum estimation unit is used to perform spatial spectrum estimation on the processed signal based on the improved spatial smoothing multiple signal classification (MUSIC) algorithm, and generate local detection spectrum data.

[0020] A further improvement of the present invention is that the improved spatial smoothing multiple signal classification algorithm includes:

[0021] Two-dimensional parameter spectrum estimation is introduced, and a dual-parameter detection spectrum is constructed based on the joint search of distance and velocity parameters;

[0022] Composite spatial smoothing is applied to divide the array space into multiple overlapping sub-arrays and the frequency space into sub-bands, generating sub-array covariance matrices and averaging them.

[0023] Based on the reconstruction of the covariance matrix using multi-order statistics, the covariance matrix is ​​corrected by fusing statistical information from each subarray and subband under limited sample conditions.

[0024] Noise subspace adaptive optimization: The threshold for dividing the noise feature subspace and the signal feature subspace is dynamically set based on the local detection spectrum energy.

[0025] Local energy sensing adaptive scanning limits the search area based on the initial detection of spectral energy distribution, and only performs a refined search in areas where the spectral energy exceeds a set threshold;

[0026] The target relocation mechanism, when there are multiple detection peaks, re-estimates the initially detected target parameters based on the subspace matched filter and outputs the corrected target parameters.

[0027] Parameter estimation error compensation is performed by calculating the correction amount of the preliminary estimated point based on the joint spectral gradient, and then updating the final estimated values ​​of the distance and velocity parameters.

[0028] A further improvement of the present invention is that the data fusion module includes:

[0029] The input interface unit is used to receive local detection spectrum data from multiple base stations;

[0030] The joint spectrum calculation unit is used to calculate the joint detection spectrum according to the following formula:

[0031]

[0032] Where: P m (r,v) represents the local detection spectrum calculated by the m-th base station for the radial distance parameter r and the radial velocity parameter v; P sum(r,v) represents the joint detection spectrum obtained by fusing the local detection spectra of multiple base stations; M represents the number of base stations participating in the fusion process.

[0033] The bias suppression unit is used to introduce spectral bias minimization processing based on the joint detection spectrum, and to fuse and estimate the target parameter. The fusion estimation formula is as follows:

[0034]

[0035] Where: λ represents the spectral bias suppression weighting factor, which is used to suppress the impact of single-base station measurement errors on the fusion results; This represents the estimated radial distance and radial velocity parameters of the target UAV obtained through fusion estimation.

[0036] The output interface unit is used to output the radial distance and radial velocity parameters of the target UAV obtained by fusion estimation.

[0037] A further improvement of the present invention is that the capacity management module includes:

[0038] The drone count calculation unit is used to calculate the maximum number of drones N that can be supported at present, based on a dynamic estimation of the base station's carrying capacity. max , where N max Calculated using the following formula:

[0039]

[0040] Wherein: γ avail To effectively perceive the signal-to-noise ratio, For environmental noise power, γ min This is the minimum detection threshold;

[0041] The control unit is used to determine the maximum number of drones N calculated from the data. max Real-time traffic control is implemented when the number of drones approaches N. max At the same time, delay or guidance control is implemented to avoid system overload and ensure detection feasibility.

[0042] A further improvement of the present invention is that the flight identification module includes:

[0043] The trajectory feature extraction unit is used to extract the rate of change of velocity, trajectory curvature, and rate of change of flight altitude as trajectory feature parameters based on the historical trajectory data of the UAV target.

[0044] A classifier unit is used to determine the category of the trajectory feature parameters based on a trained machine learning model, wherein the machine learning model includes a support vector machine (SVM) model or a convolutional neural network (CNN) model.

[0045] The data comparison unit is used to compare the identification result of the target with the flight permit information and no-fly zone information in the regulatory database to verify the target's ID number, flight permit status and the legality of the flight area;

[0046] The output unit is used to output the legality classification result and flight category label of the target UAV.

[0047] A further improvement of the present invention is that the scheduling control module includes:

[0048] The illegal flight emergency response unit is used to automatically generate flight trajectory optimization instructions when illegal flight or abnormal drones approach, and control the drone to adjust its speed and heading to avoid entering restricted areas;

[0049] The illegal flight warning unit is used to compare the flight target with the geographic restriction database in real time, trigger an illegal flight warning and initiate relevant handling mechanisms.

[0050] When flight density is high, the path adjustment unit initiates backup flight path planning or adjusts the scheduling order of flight missions to avoid congested areas.

[0051] A further improvement of the present invention is that the intelligent analysis module includes:

[0052] The data processing unit receives multimodal sensor data and uses a weighted decision algorithm to fuse the data from different sensors. The calculation result formula is as follows:

[0053]

[0054] Where: w i f represents the feature weights for each sensing mode. i (I) represents the modal feature function, and the anomaly score D is calculated through weighted fusion; N is the total number of sensing modes participating in the weighted fusion.

[0055] The dynamic evaluation unit is used to set dynamic thresholds based on the fusion evaluation values ​​and to perform anomaly detection on sensor data in order to determine whether the system status is abnormal.

[0056] The anomaly handling unit is used to activate predetermined emergency measures and provide alarm information when a system anomaly is detected.

[0057] A further improvement of the present invention is that the intelligent analysis module further includes:

[0058] The mission data parsing unit is used to perform structured parsing of the mission payload data transmitted back by the target UAV and extract a multi-dimensional feature set.

[0059] The dynamic feature selection unit is used to dynamically determine the feature subset for anomaly detection based on the real-time statistical characteristics of the extracted multidimensional feature set.

[0060] An adaptive threshold setting unit is used to dynamically adjust the judgment threshold for anomaly detection based on the distribution characteristics of feature subsets.

[0061] The anomaly detection unit is used to perform anomaly detection on the task payload data and generate anomaly detection results based on the results of dynamic feature selection and adaptive threshold setting.

[0062] On the other hand, the present invention provides an integrated monitoring method for unmanned aerial vehicles, comprising the following steps:

[0063] Step 1: Control the base station sensing module to synchronously broadcast the standard 5G synchronization signal block SSB, receive target echo signals in the airspace, and generate a local detection spectrum;

[0064] Step 2: Receive the local detection spectrum output by multiple base station sensing modules, perform symbol-level fusion processing on the local detection spectrum, and use the improved spatial smoothing multiple signal classification (MUSIC) algorithm to minimize joint spectral bias, thereby extracting the position and velocity parameters of the target UAV.

[0065] Step 3: Based on position and speed parameters, and combined with flight permit information and no-fly zone information stored in the regulatory database, identify the legality of the target drone and classify its flight category;

[0066] Step 4: Based on the local detection spectrum, dynamically estimate the base station's sensing capacity, and generate traffic scheduling instructions when the number of detected drones approaches or exceeds the capacity threshold;

[0067] Step 5: Based on the target UAV classification information and traffic scheduling instructions, generate flight instructions or security linkage measures, and send the instructions to ground control equipment or security system;

[0068] Step 6: Receive the mission payload data transmitted back by the target UAV, perform data structured analysis and anomaly feature extraction, and generate anomaly detection results for subsequent monitoring and processing.

[0069] This system enables wide-coverage, high-synchronization-precision real-time sensing of multiple targets in low-altitude airspace, improving the continuity and integrity of airspace monitoring. Local detection spectra generated by multiple base stations undergo symbol-level fusion processing and joint spectral bias minimization based on an improved spatial smoothing multiple signal classification (MUSIC) algorithm. This significantly improves the consistency and detection accuracy of multi-base station sensing data fusion, reducing target parameter estimation bias caused by observation errors and accurately extracting the position and velocity information of target UAVs. Combining the fused detection results with data from the regulatory database allows for dynamic identification of the legality and flight category of target UAVs, enhancing the ability to identify illegal flights and manage airspace. In terms of capacity management, the system can dynamically estimate the sensing capacity of base stations based on real-time sensing data and promptly execute UAV traffic scheduling when an overload trend is detected, effectively avoiding the risk of monitoring failure due to resource constraints and improving system stability in high-density flight scenarios. Through the scheduling control module, flight commands are generated or security linkage measures are triggered based on classification and identification results, enabling rapid intervention and response to illegal or abnormal flight targets, improving the timeliness and security of airspace anomaly handling. Meanwhile, the intelligent analysis module performs structured analysis on the mission payload data transmitted back by the UAV and employs an anomaly detection method with dynamic feature selection and adaptive threshold adjustment. This enables real-time identification and early warning of abnormal activities in the mission data, further enhancing the system's sensitivity and response speed to potential risk behaviors. The various modules of this invention form a complete closed loop of perception, fusion, identification, management, control, and intelligent analysis, effectively improving the overall efficiency, intelligence level, and airspace safety control capabilities of the integrated unmanned aerial vehicle (UAV) monitoring system. Attached Figure Description

[0070] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0071] in:

[0072] Figure 1 This is a modular diagram of the system of the present invention;

[0073] Figure 2 This is a flowchart of the method of the present invention. Detailed Implementation

[0074] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention are within the scope of protection of the present invention.

[0075] like Figure 1 As shown, this is one embodiment of the present invention, which provides an integrated monitoring system for unmanned aerial vehicles, including:

[0076] (1) Base station sensing module

[0077] Used to synchronously broadcast the standard 5G synchronization signal block SSB and receive airspace target echoes to generate a local detection spectrum;

[0078] A multi-beam transmitting unit is used to synchronously broadcast a standard 5G synchronization signal block (SSB) with a predetermined beam sequence.

[0079] The echo receiving unit is used to switch to the receiving mode after each transmission cycle to receive echo signals from airspace targets.

[0080] The time synchronization unit is used to perform time synchronization control based on the 5G NR system synchronization signal or the global navigation satellite system signal, so that the time synchronization error between base stations is controlled within a set threshold.

[0081] The signal processing unit is used to perform preprocessing and frequency domain transformation processing on the received echo signal;

[0082] The spatial spectrum estimation unit is used to perform spatial spectrum estimation on the processed signal based on the improved spatial smoothing multiple signal classification (MUSIC) algorithm, and generate local detection spectrum data.

[0083] In one embodiment, the improved spatially smoothed multiple signal classification algorithm includes:

[0084] Two-dimensional parameter spectrum estimation is introduced, and a dual-parameter detection spectrum is constructed based on the joint search of distance and velocity parameters;

[0085] Composite spatial smoothing is applied to divide the array space into multiple overlapping sub-arrays and the frequency space into sub-bands, generating sub-array covariance matrices and averaging them.

[0086] Based on the reconstruction of the covariance matrix using multi-order statistics, the covariance matrix is ​​corrected by fusing statistical information from each subarray and subband under limited sample conditions.

[0087] Noise subspace adaptive optimization: The threshold for dividing the noise feature subspace and the signal feature subspace is dynamically set based on the local detection spectrum energy.

[0088] Local energy sensing adaptive scanning limits the search area based on the initial detection of spectral energy distribution, and only performs a refined search in areas where the spectral energy exceeds a set threshold;

[0089] The target relocation mechanism, when there are multiple detection peaks, re-estimates the initially detected target parameters based on the subspace matched filter and outputs the corrected target parameters.

[0090] Parameter estimation error compensation is performed by calculating the correction amount of the preliminary estimated point based on the joint spectral gradient, and then updating the final estimated values ​​of the distance and velocity parameters.

[0091] With the above configuration, the base station sensing module in this embodiment employs multi-beam transmission and fast mode switching during standard 5G Synchronous Signal Block (SSB) broadcasting and echo reception to achieve continuous coverage and real-time detection of spatial targets. The introduced improved spatial smoothing multi-signal classification (MUSIC) algorithm performs dual-parameter search using both distance and velocity parameters to simultaneously estimate the target's spatial location and dynamic characteristics. Composite spatial smoothing is used, dividing the array space and frequency space into substructures and averaging them to improve the robustness and resolution of the covariance matrix estimation. Furthermore, by fusing multi-order statistical information from sub-arrays and sub-bands, estimation bias under limited sample conditions is effectively mitigated, improving the stability of spectral estimation. The noise subspace adaptive optimization mechanism dynamically sets the feature subspace boundary based on local detection spectral energy, enhancing the detectability of weak signal targets. The local energy sensing scanning strategy reduces interference and improves detection efficiency by limiting the search area. The target relocation and parameter estimation error compensation mechanism further optimizes the target parameter estimation accuracy through subspace matched filtering and joint spectral gradient correction. Compared to traditional base station sensing and single spatial spectrum estimation algorithms, this embodiment significantly improves the accuracy, stability and reliability of UAV target detection in low-altitude airspace through multi-dimensional processing and optimization, and has excellent application value and expansion potential.

[0092] (2) Data Fusion Module

[0093] This is used to perform symbol-level fusion processing on the local detection spectra of multiple base stations, and to extract the position and velocity of the UAV target based on the fusion results; wherein, the data fusion module adopts a symbol-level fusion method and performs joint spectral bias minimization processing based on the improved spatial smoothing multiple signal classification MUSIC algorithm;

[0094] The input interface unit is used to receive local detection spectrum data from multiple base stations;

[0095] The joint spectrum calculation unit is used to calculate the joint detection spectrum according to the following formula:

[0096]

[0097] Where: P m (r,v) represents the local detection spectrum calculated by the m-th base station for the radial distance parameter r and the radial velocity parameter v; P sum (r,v) represents the joint detection spectrum obtained by fusing the local detection spectra of multiple base stations; M represents the number of base stations participating in the fusion process.

[0098] The bias suppression unit is used to introduce spectral bias minimization processing based on the joint detection spectrum, and to fuse and estimate the target parameter. The fusion estimation formula is as follows:

[0099]

[0100] Where: λ represents the spectral bias suppression weighting factor, which is used to suppress the impact of single-base station measurement errors on the fusion results; This represents the estimated radial distance and radial velocity parameters of the target UAV obtained through fusion estimation.

[0101] The output interface unit is used to output the radial distance and radial velocity parameters of the target UAV obtained by fusion estimation.

[0102] With the above configuration, the data fusion module in this embodiment receives local detection spectrum data generated by multiple base station sensing modules and performs joint processing based on a symbol-level fusion method. Compared with traditional schemes that mainly rely on decision-level fusion, this approach can achieve information fusion at the underlying signal level, fully preserving the phase and amplitude characteristics of the detection signals from each base station. In the fusion processing, an improved spatial smoothing multiple signal classification (MUSIC) algorithm is used to perform joint spectral deviation minimization estimation on the local detection spectrum data. During the fusion process, a spectral deviation suppression weight is introduced to effectively reduce the impact of single-base station measurement errors on the joint spectral estimation results, improving the consistency and accuracy of the fused detection. Specifically, in the fusion estimation process, the joint spectrum calculation unit first calculates the total joint detection spectrum based on each local detection spectrum, and then the deviation suppression unit adjusts the signal contribution of each base station based on a set spectral deviation weight factor, thereby achieving optimized extraction of target parameters. Through the above processing, this embodiment can still achieve high-precision estimation of the target UAV position and velocity parameters even when there are random errors, synchronization deviations, or partial interference in the multi-base station observation information. Compared with traditional methods, it achieves significant improvements in fusion accuracy, stability, and weak signal detection sensitivity, making it particularly suitable for the joint detection and tracking of multi-source UAV targets in complex airspace environments.

[0103] (3) Capacity Management Module

[0104] Used to dynamically estimate the base station's sensing capacity and perform drone traffic scheduling when overloaded;

[0105] The drone count calculation unit is used to calculate the maximum number of drones N that can be supported at present, based on a dynamic estimation of the base station's carrying capacity. max , where N max Calculated using the following formula:

[0106]

[0107] Wherein: γ avail To effectively perceive the signal-to-noise ratio, For environmental noise power, γ min This is the minimum detection threshold;

[0108] The control unit is used to determine the maximum number of drones N calculated from the data. max Real-time traffic control is implemented when the number of drones approaches N. max At the same time, delay or guidance control is implemented to avoid system overload and ensure detection feasibility.

[0109] In this embodiment, the capacity management module dynamically estimates the maximum number of drones that each base station can currently support based on real-time received sensing data. Specifically, the drone count calculation unit calculates the maximum drone capacity in real time using a capacity estimation formula based on three indicators: effective sensing signal-to-noise ratio, ambient noise power, and minimum detection threshold. When the system detects that the number of actually connected drones is close to or exceeds the capacity threshold, the control unit triggers a flow control mechanism based on the capacity estimation result, executing measures including delayed flight mission initiation, flight path guidance adjustment, or commanded flow reduction, thereby effectively avoiding the risk of monitoring failure due to system overload. Compared with existing technologies that only set capacity limits based on static parameters, this embodiment, by introducing a real-time dynamic estimation mechanism, can adaptively adjust the sensing capacity limit according to changes in the airspace environment, significantly improving the stability and reliability of the system in complex flight scenarios. Simultaneously, through the linkage of capacity control and flow scheduling, intelligent flow allocation is achieved in high-density drone flight environments, enhancing the system's resource utilization efficiency and flight safety assurance capabilities.

[0110] (4) Flight recognition module

[0111] Used to combine fusion detection results and regulatory databases to identify the identity, legitimacy, and flight category of target drones;

[0112] The trajectory feature extraction unit is used to extract the rate of change of velocity, trajectory curvature, and rate of change of flight altitude as trajectory feature parameters based on the historical trajectory data of the UAV target.

[0113] A classifier unit is used to determine the category of the trajectory feature parameters based on a trained machine learning model, wherein the machine learning model includes a support vector machine (SVM) model or a convolutional neural network (CNN) model.

[0114] The data comparison unit is used to compare the identification result of the target with the flight permit information and no-fly zone information in the regulatory database to verify the target's ID number, flight permit status and the legality of the flight area;

[0115] The output unit is used to output the legality classification result and flight category label of the target UAV.

[0116] In this embodiment, the flight identification module combines fused detection results with data from the regulatory database to comprehensively determine the legality and flight category of the target UAV. Specifically, the track feature extraction unit extracts dynamic feature parameters such as velocity change rate, track curvature, and flight altitude change rate based on the target UAV's historical track data, forming a track feature vector for identification. The classifier unit uses a trained machine learning model to classify the extracted track feature vector, supporting models including Support Vector Machine (SVM) or Convolutional Neural Network (CNN) models to achieve accurate classification of different flight categories. The data comparison unit automatically matches and verifies the identification results with flight permit information and no-fly zone delineation information stored in the regulatory database to verify the target UAV's ID code and flight permit status, determining its legality in the current airspace. The output unit outputs the legality classification result and flight category label of the target UAV based on the comprehensive results of comparison and classification. Compared to traditional flight identification methods that rely on single flight path features or static rule comparisons, this embodiment introduces multi-dimensional dynamic feature extraction and machine learning classification, combined with real-time database comparison, which significantly improves the accuracy of flight identification and the sensitivity of illegal target detection, and can adapt to the needs of drone supervision in highly dynamic and complex airspace environments.

[0117] (5) Scheduling and Control Module

[0118] Used to issue flight commands or trigger security linkage measures based on target classification results;

[0119] The illegal flight emergency response unit is used to automatically generate flight trajectory optimization instructions when illegal flight or abnormal drones approach, and control the drone to adjust its speed and heading to avoid entering restricted areas;

[0120] The illegal flight warning unit is used to compare the flight target with the geographic restriction database in real time, trigger an illegal flight warning and initiate relevant handling mechanisms.

[0121] When flight density is high, the path adjustment unit initiates backup flight path planning or adjusts the scheduling order of flight missions to avoid congested areas.

[0122] In this embodiment, the scheduling and control module issues corresponding flight commands or triggers security linkage measures based on the classification results of the target UAVs, and adopts graded responses for different abnormal situations. Specifically, when the illegal flight emergency response unit detects illegal flight or abnormal UAVs approaching restricted areas, it automatically generates flight trajectory optimization commands and controls the target UAVs to adjust their speed and correct their heading, guiding them away from the controlled area and reducing the risk of intrusion. The illegal flight alarm unit promptly identifies behaviors that violate flight regulations by comparing flight targets with geographical restriction database information in real time, and activates a warning mechanism when illegal flight is identified, linking the ground control system or security equipment to perform further actions. When the path adjustment unit detects that the flight density exceeds a preset threshold, it dynamically plans alternative flight paths or adjusts the flight mission scheduling order to guide UAVs to avoid congested areas and reduce the risk of flight conflicts. Compared with the traditional scheduling method that mainly relies on static no-fly zone alarms, this embodiment, by combining real-time target classification, anomaly detection, and dynamic flight adjustment, forms an integrated flight scheduling and control system of early warning, avoidance, and linkage response, significantly improving the system's response speed and security control capabilities in complex and dynamic airspace environments.

[0123] (6) Intelligent Analysis Module

[0124] Used to process the mission payload data transmitted back by the drone and to perform anomaly detection.

[0125] The data processing unit receives multimodal sensor data and uses a weighted decision algorithm to fuse the data from different sensors. The calculation result formula is as follows:

[0126]

[0127] Where: w i f represents the feature weights for each sensing mode. i (I) represents the modal feature function, and the anomaly score D is calculated through weighted fusion; N is the total number of sensing modes participating in the weighted fusion.

[0128] The dynamic evaluation unit is used to set dynamic thresholds based on the fusion evaluation values ​​and to perform anomaly detection on sensor data in order to determine whether the system status is abnormal.

[0129] In one specific embodiment, the task data parsing unit is used to perform structured parsing on the task payload data transmitted back by the target UAV and extract a multi-dimensional feature set.

[0130] The dynamic feature selection unit is used to dynamically determine the feature subset for anomaly detection based on the real-time statistical characteristics of the extracted multidimensional feature set.

[0131] An adaptive threshold setting unit is used to dynamically adjust the judgment threshold for anomaly detection based on the distribution characteristics of feature subsets.

[0132] The anomaly detection unit is used to perform anomaly detection on the task payload data and generate anomaly detection results based on the results of dynamic feature selection and adaptive threshold setting.

[0133] In this embodiment, the intelligent analysis module performs anomaly detection on the mission payload data transmitted back by the UAV, achieving early detection and identification of abnormal states through multi-module collaboration. The data processing unit receives state data from multimodal sensors and uses a weighted decision algorithm to fuse different sensor data, calculating a comprehensive anomaly score. The dynamic evaluation unit sets a dynamic threshold based on the comprehensive score, monitors changes in the characteristics of the fused data, and determines in real time whether the system state is abnormal. In the specific implementation process, the mission data parsing unit first performs structured parsing on the transmitted mission payload data, extracting multi-dimensional feature information including speed, position, and mission progress; the dynamic feature selection unit filters the feature subset most relevant to anomaly detection from the multi-dimensional feature set, improving detection efficiency and accuracy. Subsequently, the adaptive threshold setting unit dynamically adjusts the anomaly detection judgment threshold based on the statistical characteristics of the feature subset, achieving adaptive sensitivity adjustment for different mission states. Finally, the anomaly identification unit comprehensively analyzes the payload data behavior based on the results of dynamic feature selection and adaptive threshold setting, generating anomaly detection and identification conclusions. Compared to traditional anomaly detection methods based on fixed rules or single feature monitoring, this embodiment significantly improves the accuracy and response speed of anomaly detection by introducing dynamic feature optimization, adaptive threshold adjustment, and multimodal fusion analysis. It is particularly suitable for UAV risk warning and abnormal behavior identification in complex dynamic flight mission environments.

[0134] like Figure 2 As shown, another embodiment of the present invention provides an integrated monitoring method for unmanned aerial vehicles, which applies an integrated monitoring system for unmanned aerial vehicles as described above, and includes the following steps:

[0135] Step 1: Control the base station sensing module to synchronously broadcast the standard 5G synchronization signal block SSB, receive target echo signals in the airspace, and generate a local detection spectrum;

[0136] Step 2: Receive the local detection spectrum output by multiple base station sensing modules, perform symbol-level fusion processing on the local detection spectrum, and use the improved spatial smoothing multiple signal classification (MUSIC) algorithm to minimize joint spectral bias, thereby extracting the position and velocity parameters of the target UAV.

[0137] Step 3: Based on position and speed parameters, and combined with flight permit information and no-fly zone information stored in the regulatory database, identify the legality of the target drone and classify its flight category;

[0138] Step 4: Based on the local detection spectrum, dynamically estimate the base station's sensing capacity, and generate traffic scheduling instructions when the number of detected drones approaches or exceeds the capacity threshold;

[0139] Step 5: Based on the target UAV classification information and traffic scheduling instructions, generate flight instructions or security linkage measures, and send the instructions to ground control equipment or security system;

[0140] Step 6: Receive the mission payload data transmitted back by the target UAV, perform data structured analysis and anomaly feature extraction, and generate anomaly detection results for subsequent monitoring and processing.

[0141] In summary, this invention addresses the shortcomings of existing technologies in areas such as synchronous airspace perception, data fusion accuracy, intelligent flight identification, dynamic capacity management, and anomaly detection of mission payload data. By constructing a multi-module collaborative comprehensive monitoring architecture, it achieves wide-coverage, high-precision, and intelligent monitoring of low-altitude airspace. This invention effectively improves the consistency and accuracy of UAV target detection, enhances the ability to identify illegal flight behavior, ensures the stability of system operation in high-density flight environments, and improves the real-time identification level of abnormal mission data activities. With its complete closed-loop chain of perception, fusion, identification, management, scheduling, and intelligent analysis, this invention has good scalability and adaptability, and can be widely applied to intelligent monitoring of urban airspace traffic management, low-altitude protection in important areas, emergency response command, and various UAV application scenarios, possessing high practical application value and promising prospects for promotion.

[0142] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0143] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process. Furthermore, the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functionality involved.

[0144] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in this application, and these should all be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An integrated monitoring system for unmanned aerial vehicles, characterized in that, include: The base station sensing module is used to synchronously broadcast the standard 5G synchronization signal block (SSB) and receive spatial target echoes to generate a local detection spectrum. The data fusion module is used to perform symbol-level fusion processing on the local detection spectra of multiple base stations and extract the position and velocity of the UAV target based on the fusion results. The data fusion module adopts a symbol-level fusion method and performs joint spectral bias minimization processing based on the improved spatial smoothing multiple signal classification (MUSIC) algorithm. The improved spatial smoothing multiple signal classification algorithm includes: Two-dimensional parameter spectrum estimation is introduced, and a dual-parameter detection spectrum is constructed based on the joint search of distance and velocity parameters; Composite spatial smoothing is applied to divide the array space into multiple overlapping sub-arrays and the frequency space into sub-bands, generating sub-array covariance matrices and averaging them. Based on the reconstruction of the covariance matrix using multi-order statistics, the covariance matrix is ​​corrected by fusing statistical information from each subarray and subband under limited sample conditions. Noise subspace adaptive optimization: The threshold for dividing the noise feature subspace and the signal feature subspace is dynamically set based on the local detection spectrum energy. Local energy sensing adaptive scanning limits the search area based on the initial detection of spectral energy distribution, and only performs a refined search in areas where the spectral energy exceeds a set threshold; The target relocation mechanism, when there are multiple detection peaks, re-estimates the initially detected target parameters based on the subspace matched filter and outputs the corrected target parameters. Parameter estimation error compensation is performed by calculating the correction amount of the initial estimation point based on the joint spectral gradient, and then updating the final estimated values ​​of the distance and velocity parameters. The capacity management module is used to dynamically estimate the base station's sensing capacity and perform drone traffic scheduling when overloaded. The flight identification module is used to combine fusion detection results and regulatory databases to identify the identity, legality, and flight category of target drones; The dispatch and control module is used to issue flight commands or trigger security linkage measures based on the target classification results; The intelligent analysis module is used to process the mission payload data transmitted back by the UAV and to perform anomaly detection.

2. The integrated monitoring system for unmanned aerial vehicles according to claim 1, characterized in that, The base station sensing module includes: A multi-beam transmitting unit is used to synchronously broadcast a standard 5G synchronization signal block (SSB) with a predetermined beam sequence. The echo receiving unit is used to switch to the receiving mode after each transmission cycle to receive echo signals from airspace targets. The time synchronization unit is used to perform time synchronization control based on the 5G NR system synchronization signal or the global navigation satellite system signal, so that the time synchronization error between base stations is controlled within a set threshold. The signal processing unit is used to perform preprocessing and frequency domain transformation processing on the received echo signal; The spatial spectrum estimation unit is used to perform spatial spectrum estimation on the processed signal based on the improved spatial smoothing multiple signal classification (MUSIC) algorithm, and generate local detection spectrum data.

3. The integrated monitoring system for unmanned aerial vehicles according to claim 1, characterized in that, The data fusion module includes: The input interface unit is used to receive local detection spectrum data from multiple base stations; The joint spectrum calculation unit is used to calculate the joint detection spectrum according to the following formula: ； in: Indicates the first Each base station targets radial distance parameters With radial velocity parameters The calculated local detection spectrum; This represents the joint detection spectrum obtained by fusing the local detection spectra of multiple base stations; Indicates the number of base stations participating in the fusion processing; The bias suppression unit is used to introduce spectral bias minimization processing based on the joint detection spectrum, and to fuse and estimate the target parameter. The fusion estimation formula is as follows: ； in: This represents the spectral bias suppression weighting factor, used to suppress the impact of single-base station measurement errors on the fusion results; This represents the estimated radial distance and radial velocity parameters of the target UAV obtained through fusion estimation. The output interface unit is used to output the radial distance and radial velocity parameters of the target UAV obtained by fusion estimation.

4. The integrated monitoring system for unmanned aerial vehicles according to claim 1, characterized in that, The capacity management module includes: The drone count calculation unit is used to calculate the maximum number of drones that can be supported at present, based on a dynamic estimation of the base station's carrying capacity. The calculation formula is: ； in: To effectively perceive the signal-to-noise ratio, For environmental noise power, This is the minimum detection threshold; The control unit is used to determine the maximum number of drones calculated. Real-time traffic control is implemented when the number of drones approaches [a certain threshold]. At that time, execute delay or guidance control.

5. The integrated monitoring system for unmanned aerial vehicles according to claim 1, characterized in that, The flight identification module includes: The trajectory feature extraction unit is used to extract the rate of change of velocity, trajectory curvature, and rate of change of flight altitude as trajectory feature parameters based on the historical trajectory data of the UAV target. The classifier unit is used to determine the category of the trajectory feature parameters based on the trained machine learning model, wherein the machine learning model includes a support vector machine (SVM) model or a convolutional neural network (CNN) model. The data comparison unit is used to compare the identification result of the target with the flight permit information and no-fly zone information in the regulatory database to verify the target's ID number, flight permit status and the legality of the flight area; The output unit is used to output the legality classification result and flight category label of the target UAV.

6. The integrated monitoring system for unmanned aerial vehicles according to claim 1, characterized in that, The scheduling control module includes: The illegal flight emergency response unit is used to automatically generate flight trajectory optimization instructions when illegal flight or abnormal drones approach, and control the drone to adjust its speed and heading to avoid entering restricted areas; The illegal flight warning unit is used to compare the flight target with the geographic restriction database in real time, trigger an illegal flight warning and initiate relevant handling mechanisms. When flight density is high, the path adjustment unit initiates backup flight path planning or adjusts the scheduling order of flight missions to avoid congested areas.

7. The integrated monitoring system for unmanned aerial vehicles according to claim 1, characterized in that, The intelligent analysis module includes: The data processing unit receives multimodal sensor data and uses a weighted decision algorithm to fuse the data from different sensors. The calculation result formula is as follows: ； in: For the feature weights of each sensing mode, The anomaly score is calculated using modal feature functions and weighted fusion. ; The total number of sensor modes participating in the weighted fusion; The dynamic evaluation unit is used to set dynamic thresholds based on the fusion evaluation values ​​and to detect anomalies in the sensor data. The anomaly handling unit is used to activate predetermined emergency measures and provide alarm information when a system anomaly is detected.

8. The integrated monitoring system for unmanned aerial vehicles according to claim 7, characterized in that, The intelligent analysis module also includes: The data parsing unit is used to perform structured parsing of the mission payload data transmitted back by the target UAV and extract a multi-dimensional feature set. The dynamic feature selection unit is used to dynamically determine the feature subset for anomaly detection based on the real-time statistical characteristics of the extracted multidimensional feature set. An adaptive threshold setting unit is used to dynamically adjust the judgment threshold for anomaly detection based on the distribution characteristics of feature subsets. The anomaly detection unit is used to perform anomaly detection on the task payload data and generate anomaly detection results based on the results of dynamic feature selection and adaptive threshold setting.

9. A method for integrated monitoring of unmanned aerial vehicles, employing an integrated monitoring system for unmanned aerial vehicles as described in any one of claims 1-8, characterized in that, Includes the following steps: Step 1: Control the base station sensing module to synchronously broadcast the standard 5G synchronization signal block SSB, receive target echo signals in the airspace, and generate a local detection spectrum; Step 2: Receive the local detection spectrum output by multiple base station sensing modules, perform symbol-level fusion processing on the local detection spectrum, and use the improved spatial smoothing multiple signal classification (MUSIC) algorithm to minimize joint spectral bias, thereby extracting the position and velocity parameters of the target UAV. Step 3: Based on position and speed parameters, and combined with flight permit information and no-fly zone information stored in the regulatory database, identify the legality of the target drone and classify its flight category; Step 4: Based on the local detection spectrum, dynamically estimate the base station's sensing capacity, and generate traffic scheduling instructions when the number of detected drones approaches or exceeds the capacity threshold; Step 5: Based on the target UAV classification information and traffic scheduling instructions, generate flight instructions or security linkage measures, and send the instructions to ground control equipment or security system; Step 6: Receive the mission payload data transmitted back by the target UAV, perform data structured analysis and anomaly feature extraction, and generate anomaly detection results for subsequent monitoring and processing.

Images