Methods and systems for early warning and countermeasures against low-altitude unmanned aerial vehicles (UAVs) in temporarily controlled areas

Abstract

This invention relates to the field of UAV early warning and countermeasure technology, specifically disclosing a method and system for early warning and countermeasure of low-altitude UAVs applicable to temporary control areas. It utilizes a multi-source detection device consisting of radio frequency sensors and infrared thermal imagers to collect real-time radio signal frequency offset data and surface temperature difference data of the UAV. The radio signals undergo zero-sequence processing and variational mode decomposition to calculate signal stability characteristic values ​​to assess the degree of communication link interference. Multi-scale wavelet transform is applied to the temperature data to extract temperature gradient change rate characteristic values ​​to identify abnormal operating states. The two types of characteristic values ​​are used to construct a behavioral feature vector, which is then input into a gradient boosting tree model for threat level assessment. Finally, based on the assessment results, tiered countermeasure strategies such as communication interference, navigation deception, or physical capture are dynamically activated.

Description

Technical Field

[0001] This invention relates to the field of drone early warning and countermeasures technology, specifically to a method and system for early warning and countermeasures of low-altitude drones applicable to temporarily controlled areas. Background Technology

[0002] With the rapid development of drone technology, its applications in logistics, inspection, surveying, and other fields are becoming increasingly widespread. However, this also brings low-altitude security threats, especially in temporarily controlled areas (such as security for major events, military restricted areas, etc.). Illegal intrusion by drones may lead to information leaks, security incidents, or even terrorist attacks. Currently, detection and countermeasures against drones mainly rely on single methods such as radar, radio detection, or electro-optical tracking. However, due to the small size, low flight altitude, and high maneuverability of drones, traditional methods suffer from problems such as detection blind spots, high false alarm rates, and delayed response in complex electromagnetic environments or adverse weather conditions, making it difficult to meet the needs of real-time, accurate early warning and tiered countermeasures against low-altitude targets in temporarily controlled areas. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for early warning and countermeasures against low-altitude unmanned aerial vehicles (UAVs) in temporarily controlled areas, so as to solve the problems mentioned above.

[0004] The objective of this invention can be achieved through the following technical solutions:

[0005] A method for early warning and countermeasures against low-altitude unmanned aerial vehicles (UAVs) applicable to temporarily controlled areas includes the following steps:

[0006] S1: Real-time acquisition of radio signal frequency offset data and fuselage surface temperature difference data of UAVs through multi-source detection equipment deployed in the temporary control area;

[0007] The multi-source detection device includes: a radio frequency sensor and an infrared thermal imager;

[0008] S2: Perform zero-order processing on the acquired radio signal frequency offset data, construct a zero-order frequency sequence, and calculate the signal stability characteristic value to assess the degree of interference to the UAV communication link;

[0009] S3: Based on the acquired surface temperature difference data, calculate the characteristic value of the temperature gradient change rate to identify whether the drone is in an abnormal operating state;

[0010] S4: Construct a drone behavior feature vector from the signal stability feature value and the temperature gradient change rate feature value, and input it into the recognition model for threat level assessment;

[0011] S5: Dynamically activate corresponding countermeasures based on the assessment results, including communication jamming, navigation deception, or physical capture methods, to achieve graded response and precise handling of intruding drones.

[0012] As a further aspect of the present invention: the assessment of the interference level of the UAV communication link specifically includes:

[0013] The system acquires real-time radio signal frequency offset data from drones, performs zero-sequence processing on the acquired radio signal frequency offset data to construct a zero-sequence frequency sequence, analyzes the zero-sequence frequency sequence, calculates the signal stability characteristic value based on the analysis results, and determines whether the signal stability characteristic value is greater than or equal to a preset threshold. If it is, the degree of interference to the drone communication link is considered minor; otherwise, the degree of interference to the drone communication link is considered severe.

[0014] As a further aspect of the present invention: the process of obtaining the signal stability feature value is as follows:

[0015] The frequency offset data of the UAV radio signal collected in real time is obtained and denoted as a time series function. The time series function is processed to remove the DC component and construct a zero-sequence frequency sequence.

[0016] The zero-sequence frequency sequence is adaptively decomposed using the variational mode decomposition algorithm, and then decomposed into... Each mode function has an intrinsic mode function and its corresponding center frequency. The instantaneous frequency of each mode component is calculated by differentiating the instantaneous phase.

[0017] The variance of the center frequency of the corresponding mode was obtained through statistical analysis.

[0018] The signal stability characteristic value is obtained by summing the variances of the center frequencies of all modes.

[0019] As a further aspect of the present invention: the identification of whether the drone is in an abnormal operating state specifically includes:

[0020] The system acquires real-time surface temperature difference data of the drone, analyzes the surface temperature difference data, calculates the characteristic value of the temperature gradient change rate based on the analysis results, and determines whether the characteristic value of the temperature gradient change rate is greater than or equal to a preset threshold. If it is, the drone is in an abnormal operating state; otherwise, the drone is not in an abnormal operating state.

[0021] As a further aspect of the present invention: the process for obtaining the characteristic value of the temperature gradient change rate is as follows:

[0022] The system acquires surface temperature distribution data of a UAV at multiple consecutive time points, filters and smooths the data to obtain a preprocessed temperature sequence, calculates the temperature difference between adjacent time points to obtain temperature difference data, and then applies this data to each spatial location. Performing a one-dimensional Haar wavelet transform on the temperature difference sequence at a given location yields the results at the scale level. and position index The detail coefficients are obtained for each position. Calculate the energy of the detail coefficients at each scale level;

[0023] The ratio of the total energy of the detail coefficients across all scales to the total energy across all scales is used to obtain the characteristic value of the temperature gradient rate of change.

[0024] As a further aspect of the present invention: based on the identification model, a drone risk score is output, specifically including:

[0025] The signal stability feature value and temperature gradient change rate feature value of the UAV are obtained. The signal stability feature value and temperature gradient change rate feature value are used to construct a UAV behavior feature vector, which is then input into the recognition model. The training objective of the recognition model is to minimize the error between the predicted UAV risk score and the actual UAV risk score. The UAV risk score is output based on the trained recognition model. The recognition model is a gradient boosting tree model.

[0026] As a further aspect of the present invention: the training process of the recognition model is as follows:

[0027] The signal stability features, surface temperature gradient change rate features, and actual drone risk scores of UAVs from multiple historical flight missions are obtained and used to construct a training dataset. A new decision tree is fitted based on the current residuals and weighted and superimposed on the overall model output according to the set learning rate. During the training process, regularization strategies are introduced to prevent overfitting, including limiting the maximum depth of the decision tree, setting the minimum number of samples in the leaf nodes, and using L1 / L2 regularization terms. The optimal hyperparameter combination is selected through cross-validation to ensure that the model has good generalization performance.

[0028] As a further aspect of the present invention: the threat level assessment specifically includes:

[0029] Determine if the drone risk score is greater than or equal to a preset first threshold. If yes, the threat level is the highest level. If no, determine if the drone risk score is less than or equal to a preset second threshold. If yes, the threat level is the lowest level. If no, the threat level is the medium level.

[0030] As a further aspect of the present invention: the graded response and precise handling of intruding drones specifically includes:

[0031] For drones with the highest threat level, i.e., those with serious communication interference and abnormal operating conditions, immediately activate high-intensity communication interference and navigation deception measures, and coordinate with physical capture devices to implement emergency interception and forced control.

[0032] For drones with a medium threat level, i.e., those with communication disturbances and local temperature anomalies but not yet posing a direct threat, directional communication jamming is initiated in conjunction with radar tracking and signal suppression, while warning commands are issued to guide them away from the controlled area.

[0033] For drones with the lowest threat level, i.e., aircraft with stable communication and normal temperature changes but still within the no-fly zone, only electronic fence restrictions and voice warning measures will be activated.

[0034] Low-altitude unmanned aerial vehicle (UAV) early warning and countermeasure systems suitable for temporarily controlled areas include:

[0035] The data acquisition module collects radio signal frequency offset data and fuselage surface temperature difference data of the UAV in real time through multi-source detection equipment deployed in the temporary control area.

[0036] The signal stability analysis module performs zero-sequence processing on the acquired radio signal frequency offset data, constructs a zero-sequence frequency sequence, and calculates signal stability characteristic values ​​to assess the degree of interference to the UAV communication link.

[0037] The temperature gradient analysis module calculates the characteristic value of the temperature gradient change rate based on the acquired fuselage surface temperature difference data, which is used to identify whether the UAV has an abnormal operating state.

[0038] The threat level assessment module constructs a drone behavior feature vector from signal stability feature values ​​and temperature gradient change rate feature values, and inputs it into the recognition model for threat level assessment.

[0039] The hierarchical countermeasure control module dynamically activates corresponding countermeasure strategies based on the evaluation results, including communication interference, navigation deception, or physical capture methods, to achieve hierarchical response and precise handling of intruding drones.

[0040] The beneficial effects of this invention are:

[0041] (1) This invention constructs a dual-modal perception system for low-altitude UAV behavior recognition by integrating multi-source detection methods of radio frequency sensors and infrared thermal imagers, realizing synchronous monitoring of UAV operating status from two physical dimensions: electromagnetic signals and thermodynamics. In terms of electromagnetic feature analysis, a method combining zero-sequence processing and variational mode decomposition is adopted to adaptively decompose the frequency offset sequence of radio signals, extract the center frequency variance of each modal component, and obtain the signal stability feature value by summation calculation, thereby realizing the quantitative assessment of the degree of interference of the communication link; in terms of thermal feature modeling, by performing one-dimensional Haar wavelet transform on the surface temperature difference data of the fuselage, the detail coefficients at different scales are extracted, and the temperature gradient change rate feature value is calculated by combining the multi-scale energy distribution and the total energy ratio relationship, which is used to identify whether the UAV has abnormal heating or unstable thermal diffusion phenomenon. This multi-source information fusion technical path not only effectively improves the robustness and discrimination ability of the system under complex electromagnetic and environmental interference, but also provides dual criterion support for the refined modeling of UAV behavior characteristics, significantly enhancing the intelligence level and practical application value of the early warning system.

[0042] (2) Based on the constructed UAV behavior feature vector, this invention uses a well-trained gradient boosting tree model to intelligently score the potential risks of intruding UAVs, and uses this as the core basis for threat level assessment, realizing end-to-end mapping from multi-dimensional feature input to risk quantification output. The identification model, by fusing signal stability features and temperature gradient change rate features, can accurately characterize the comprehensive performance of UAVs in terms of communication link disturbances and thermodynamic anomalies, thereby dividing the risk score into multiple level threshold intervals, each corresponding to a different level of security threat. The system automatically matches the corresponding countermeasures based on the assessment results: for high-risk targets, high-intensity communication interference and navigation deception are initiated, and physical capture devices are linked to implement forced control; for medium-risk targets, a combination of directional suppression and radar tracking is used to guide them away; and for low-risk targets in no-fly zones, only electronic fences and voice warning measures are used to avoid resource waste and accidental injury risks. More importantly, after each round of countermeasures, the system continuously collects the latest behavioral data of the target drone, dynamically updates its risk score, and feeds it back to the decision-making module in real time, forming a closed-loop response mechanism. This ensures that the countermeasures are always synchronized with the target's status, significantly improving the system's intelligence, adaptability, and combat effectiveness. It provides an efficient, accurate, and controllable low-altitude security solution for temporary control areas. Attached Figure Description

[0043] The invention will now be further described with reference to the accompanying drawings.

[0044] Figure 1 This is a flowchart of the low-altitude unmanned aerial vehicle (UAV) early warning and countermeasure method applicable to temporary control areas according to the present invention;

[0045] Figure 2 This is a flowchart of the low-altitude unmanned aerial vehicle (UAV) early warning and countermeasure system applicable to temporary control areas in this invention. Detailed Implementation

[0046] 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.

[0047] Please see Figure 1 As shown, this invention provides a method for early warning and countermeasures against low-altitude unmanned aerial vehicles (UAVs) applicable to temporarily controlled areas, comprising the following steps:

[0048] S1: Real-time acquisition of radio signal frequency offset data and fuselage surface temperature difference data of UAVs through multi-source detection equipment deployed in the temporary control area;

[0049] The multi-source detection device includes: a radio frequency sensor and an infrared thermal imager;

[0050] S2: Perform zero-order processing on the acquired radio signal frequency offset data, construct a zero-order frequency sequence, and calculate the signal stability characteristic value to assess the degree of interference to the UAV communication link;

[0051] S3: Based on the acquired surface temperature difference data, calculate the characteristic value of the temperature gradient change rate to identify whether the drone is in an abnormal operating state;

[0052] S4: Construct a drone behavior feature vector from the signal stability feature value and the temperature gradient change rate feature value, and input it into the recognition model for threat level assessment;

[0053] S5: Dynamically activate corresponding countermeasures based on the assessment results, including communication jamming, navigation deception, or physical capture methods, to achieve graded response and precise handling of intruding drones.

[0054] In S1, multi-source detection equipment deployed within the temporary control area collects real-time data on the radio signal frequency offset and fuselage surface temperature difference of the UAV, specifically including:

[0055] The multi-source detection equipment includes a radio frequency sensor and an infrared thermal imager, used to collect radio signals in the UAV's communication link and thermal imaging information during flight, respectively. The radio frequency sensor is deployed at multiple monitoring points around the controlled area to continuously monitor the communication frequency band between the UAV and the remote controller, capturing the change in signal carrier frequency over time to form a frequency offset time series; the infrared thermal imager is installed on a ground monitoring platform or mobile observation equipment to perform non-contact temperature measurement on UAVs entering the controlled area, acquiring images of the fuselage surface temperature distribution at different time periods during flight.

[0056] During data acquisition, the radio frequency sensor digitizes the received radio signals and extracts their center frequency and instantaneous frequency offset, recording them as frequency offset data. The infrared thermal imager continuously captures thermal images of the drone at a set frame rate and performs pixel-level temperature inversion on each frame to obtain the temperature values ​​at each spatial coordinate point. All acquired data are synchronized using a unified timestamp to ensure the temporal consistency of signal characteristics and thermal characteristics in subsequent analysis, providing high-quality input for signal stability analysis and temperature gradient change analysis.

[0057] In S2, the acquired radio signal frequency offset data undergoes zero-order processing to construct a zero-order frequency sequence and calculates signal stability characteristic values ​​to assess the degree of interference in the UAV communication link. Specifically, this includes:

[0058] The system acquires real-time radio signal frequency offset data from drones, performs zero-sequence processing on the acquired radio signal frequency offset data to construct a zero-sequence frequency sequence, analyzes the zero-sequence frequency sequence, calculates the signal stability characteristic value based on the analysis results, and determines whether the signal stability characteristic value is greater than or equal to a preset threshold. If it is, the degree of interference to the drone communication link is considered minor; otherwise, the degree of interference to the drone communication link is considered severe.

[0059] The process for obtaining the signal stability feature values ​​is as follows:

[0060] The real-time collected UAV radio signal frequency offset data is acquired and denoted as a time series function. Zero-sequence processing is performed on the time series function to remove the DC component, constructing a zero-sequence frequency sequence. The calculation expression is as follows: ;in, Indicates the time point of data collection. This represents the mean of the frequency offset data for drone radio signals. Represents time series functions, Represents a zero-order frequency sequence;

[0061] The zero-sequence frequency sequence is adaptively decomposed using the variational mode decomposition algorithm, and then decomposed into... There are 1 intrinsic mode function and its corresponding center frequency, and the following constraints are satisfied: ;in, This indicates the number of intrinsic mode functions. This represents the total number of intrinsic mode functions. Let represent the intrinsic mode function. For each mode component, its instantaneous frequency is calculated as follows: For each mode component, its analytic signal is first constructed and represented in polar coordinates. The calculation expression is: ;in, Represents the instantaneous amplitude of the modal component. It is a complex exponential function, representing the rotation direction and frequency characteristics of the signal. Represents the imaginary unit. Indicates the instantaneous phase of the modal component. This represents the analytic signal corresponding to the modal components. The instantaneous frequency of each modal component is obtained by differentiating the instantaneous phase, and the calculation expression is: In the formula, The instantaneous frequency is represented; and the variance of the center frequency of the corresponding mode is obtained through statistical analysis; where the center frequency is the average frequency of the modal components, and its calculation expression is: ;in, Indicates the center frequency. The total duration of the signal is represented by the summation of the variances of the center frequencies of all modes to obtain the signal stability characteristic value.

[0062] It should be noted that by acquiring the frequency offset data of UAV radio signals and performing zero-sequence processing to construct a zero-sequence frequency sequence, the DC drift component in the signal is effectively removed, improving the accuracy of subsequent feature extraction. A variational mode decomposition algorithm is used to adaptively decompose the zero-sequence frequency sequence, obtaining multiple intrinsic mode functions and their corresponding instantaneous frequencies and center frequency variances, fully exploring the signal's stability information in different frequency bands. By summing the center frequency variances of each mode, the signal stability characteristic value is calculated, enabling a quantitative assessment of the degree of interference in the UAV communication link. This method not only has good noise resistance and time-frequency local analysis capabilities but also dynamically adapts to signal changes under different flight states and interference environments, significantly improving the identification accuracy and response speed of low-altitude UAV early warning systems in complex electromagnetic environments. It possesses strong engineering practicality and technological innovation.

[0063] In S3, based on the acquired fuselage surface temperature difference data, a characteristic value of the temperature gradient change rate is calculated to identify whether the drone is in an abnormal operating state, specifically including:

[0064] The system acquires real-time surface temperature difference data of the drone, analyzes the surface temperature difference data, calculates the characteristic value of the temperature gradient change rate based on the analysis results, and determines whether the characteristic value of the temperature gradient change rate is greater than or equal to a preset threshold. If it is, the drone is in an abnormal operating state; otherwise, the drone is not in an abnormal operating state.

[0065] The process for obtaining the characteristic value of the temperature gradient change rate is as follows:

[0066] The system acquires surface temperature distribution data of a UAV at multiple consecutive time points, filters and smooths the data to obtain a preprocessed temperature sequence, calculates the temperature difference between adjacent time points to obtain temperature difference data, and then applies this data to each spatial location. Performing a one-dimensional Haar wavelet transform on the temperature difference sequence at a given location yields the results at the scale level. and position index The detail coefficients are obtained for each position. Calculate the energy of the detail coefficients at each scale level, using the following expression: ;in, Indicates position First Energy of detail coefficients at each scale level Indicates the quantity of scale, Indicates the number of positions. Indicates the first The first scale level The detail coefficients at each location are calculated; the ratio of the total energy of the detail coefficients across all scale levels to the total energy across all scale levels is used to obtain the characteristic value of the temperature gradient change rate. The total energy includes the sum of the energy of the detail coefficients and the energy of the approximation coefficients.

[0067] It should be noted that by collecting and analyzing the temperature difference data of the UAV fuselage surface, and combining it with Haar wavelet transform to perform multi-scale energy modeling of the temperature change process, the characteristic value of the temperature gradient change rate is calculated, realizing non-contact and dynamic anomaly identification of the UAV's operating status. This method first filters and smooths the raw temperature data to improve data quality, and then uses one-dimensional Haar wavelet transform to extract the detail coefficients of the temperature difference sequence at different scales, thereby calculating the local energy distribution at each scale. The degree of temperature change is quantified by the ratio of the detail coefficient energy to the total energy (including the energy of the approximation coefficient, which is obtained by calculating the square of the modulus of the approximation coefficient). Compared with traditional methods, this scheme can more sensitively capture local temperature rise anomalies and thermal diffusion instability of the fuselage, effectively distinguish between normal flight and abnormal operating states, and has good real-time performance, robustness and engineering feasibility. It significantly improves the accuracy and intelligence level of UAV health status monitoring and provides a reliable thermal feature criterion for low-altitude security systems.

[0068] In S4, the signal stability feature values ​​and the temperature gradient change rate feature values ​​are used to construct a drone behavior feature vector, which is then input into the recognition model for threat level assessment. Specifically, this includes:

[0069] The signal stability feature value and temperature gradient change rate feature value of the UAV are obtained. The signal stability feature value and temperature gradient change rate feature value are used to construct a UAV behavior feature vector, which is then input into the recognition model. The training objective of the recognition model is to minimize the error between the predicted UAV risk score and the actual UAV risk score. The UAV risk score is output based on the trained recognition model. The recognition model is a gradient boosting tree model.

[0070] The training process of the recognition model is as follows:

[0071] The signal stability features, surface temperature gradient change rate features, and actual drone risk scores of UAVs from multiple historical flight missions were obtained and constructed into a training dataset. A new decision tree was fitted based on the current residuals and weighted and superimposed into the overall model output according to the set learning rate. During the training process, regularization strategies were introduced to prevent overfitting, including limiting the maximum depth of the decision tree, setting the minimum number of samples in the leaf nodes, and using L1 / L2 regularization terms. At the same time, the optimal hyperparameter combination was selected through cross-validation to ensure that the model has good generalization performance.

[0072] The threat level assessment specifically includes:

[0073] Determine if the drone risk score is greater than or equal to a preset first threshold. If yes, the threat level is the highest level. If no, determine if the drone risk score is less than or equal to a preset second threshold. If yes, the threat level is the lowest level. If no, the threat level is the medium level.

[0074] In S5, corresponding countermeasures are dynamically activated based on the assessment results, including communication jamming, navigation deception, or physical capture methods, to achieve graded response and precise handling of intruding drones. Specifically, these include:

[0075] For drones with the highest threat level, i.e., those with serious communication interference and abnormal operating conditions, immediately activate high-intensity communication interference and navigation deception measures, and coordinate with physical capture devices (such as net-capture drones or electromagnetic capture devices) to implement emergency interception and forced control.

[0076] For drones with a medium threat level, i.e., those with some communication disturbances or local temperature anomalies but not yet posing a direct threat, directional communication jamming is initiated in conjunction with radar tracking and signal suppression, while warning commands are issued to guide them away from the controlled area.

[0077] For drones with the lowest threat level, namely aircraft with stable communication and normal temperature changes but still within the no-fly zone, only electronic fence restrictions and voice warning measures will be activated to avoid accidental damage and waste of resources.

[0078] After each round of countermeasures, the system continuously monitors changes in the target drone's behavior, re-collects its radio signal frequency offset data and surface temperature difference data, updates the risk score, and determines whether the threat status should be lifted or the countermeasure intensity should be adjusted, forming a closed-loop control system to achieve dynamic response and precise handling of intruding drones.

[0079] Please see Figure 2 As shown, a low-altitude unmanned aerial vehicle (UAV) early warning and countermeasure system suitable for temporary control areas includes:

[0080] The data acquisition module collects radio signal frequency offset data and fuselage surface temperature difference data of the UAV in real time through multi-source detection equipment deployed in the temporary control area.

[0081] The signal stability analysis module performs zero-sequence processing on the acquired radio signal frequency offset data, constructs a zero-sequence frequency sequence, and calculates signal stability characteristic values ​​to assess the degree of interference to the UAV communication link.

[0082] The temperature gradient analysis module calculates the characteristic value of the temperature gradient change rate based on the acquired fuselage surface temperature difference data, which is used to identify whether the UAV has an abnormal operating state.

[0083] The threat level assessment module constructs a drone behavior feature vector from signal stability feature values ​​and temperature gradient change rate feature values, and inputs it into the recognition model for threat level assessment.

[0084] The hierarchical countermeasure control module dynamically activates corresponding countermeasure strategies based on the evaluation results, including communication interference, navigation deception, or physical capture methods, to achieve hierarchical response and precise handling of intruding drones.

[0085] The working principle of this invention: This invention aims to solve the technical challenges of detecting, identifying, and handling illegal intrusions by drones in low-altitude airspace. This solution deploys multi-source detection equipment, including radio frequency sensors and infrared thermal imagers, to collect real-time data on the frequency offset of the drone's radio signals and the temperature difference data of its fuselage surface. By performing zero-sequence processing and variational mode decomposition on the radio signals, the variance of the center frequencies of each mode is extracted and summed to calculate signal stability feature values, which are used to assess the degree of interference to the communication link. Simultaneously, based on the temperature difference data, a temperature gradient change rate feature value is constructed, and Haar wavelet transform is used to extract multi-scale energy distribution. The ratio of detail coefficient energy to total energy is used to identify abnormal operating states. Furthermore, these two types of features are used to construct a drone behavior feature vector, which is input into a trained gradient boosting tree model for threat level assessment. Based on the risk score, a tiered countermeasure strategy is dynamically activated, including communication interference, navigation deception, and physical capture, achieving a precise and closed-loop response mechanism. This invention integrates electromagnetic and thermodynamic dual-dimensional feature analysis, improving the identification accuracy and response speed of the early warning system. It has strong anti-interference capabilities and engineering practicality, providing efficient and intelligent technical support for low-altitude security in temporary control areas.

[0086] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0087] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0088] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0089] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0090] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A method for early warning and countermeasures against low-altitude unmanned aerial vehicles (UAVs) applicable to temporarily controlled areas, characterized in that: Includes the following steps: S1: Real-time acquisition of radio signal frequency offset data and fuselage surface temperature difference data of UAVs through multi-source detection equipment deployed in the temporary control area; The multi-source detection device includes: a radio frequency sensor and an infrared thermal imager; S2: Perform zero-order processing on the acquired radio signal frequency offset data, construct a zero-order frequency sequence, and calculate the signal stability characteristic value to assess the degree of interference to the UAV communication link; The process for obtaining the signal stability feature values ​​is as follows: The real-time collected UAV radio signal frequency offset data is acquired and denoted as a time series function. Zero-sequence processing is performed on the time series function to remove the DC component, constructing a zero-sequence frequency sequence. The calculation expression is as follows: ;in, Indicates the time point of data collection. This represents the mean of the frequency offset data for drone radio signals. Represents time series functions, Representing the zero-sequence frequency sequence; the variational mode decomposition algorithm is used to adaptively decompose the zero-sequence frequency sequence into its spectral components. There are 1 intrinsic mode function and its corresponding center frequency, and the following constraints are satisfied: ;in, This indicates the number of intrinsic mode functions. This represents the total number of intrinsic mode functions. Let the intrinsic mode function be represented. For each mode component, its instantaneous frequency is calculated as follows: For each mode component, its analytic signal is first constructed and represented in polar coordinates. The calculation expression is: ;in, This represents the instantaneous amplitude of the modal component. It is a complex exponential function, representing the rotation direction and frequency characteristics of the signal. Represents the imaginary unit. Indicates the instantaneous phase of the modal component. This represents the analytic signal corresponding to the modal components. The instantaneous frequency of each modal component is obtained by differentiating the instantaneous phase, and the calculation expression is: In the formula, The instantaneous frequency is represented; and the variance of the center frequency of the corresponding mode is obtained through statistical analysis; where the center frequency is the average frequency of the modal components, and its calculation expression is: ;in, Indicates the center frequency. The total duration of the signal is represented by the summation of the variances of the center frequencies of all modes to obtain the signal stability characteristic values. S3: Based on the acquired surface temperature difference data, calculate the characteristic value of the temperature gradient change rate to identify whether the drone is in an abnormal operating state; The process for obtaining the characteristic value of the temperature gradient change rate is as follows: The system acquires surface temperature distribution data of a UAV at multiple consecutive time points, filters and smooths the data to obtain a preprocessed temperature sequence, calculates the temperature difference between adjacent time points to obtain temperature difference data, and then applies this data to each spatial location. Performing a one-dimensional Haar wavelet transform on the temperature difference sequence at a given location yields the results at the scale level. and position index The detail coefficients are obtained for each position. Calculate the energy of the detail coefficients at each scale level, using the following expression: ;in, Indicates position First Energy of detail coefficients at each scale level Indicates the quantity of scale, Indicates the number of positions. Indicates the first The first scale level The detail coefficients at each location are calculated; the ratio of the total energy of the detail coefficients across all scale levels to the total energy across all scale levels is used to obtain the characteristic value of the temperature gradient change rate, where the total energy includes the sum of the energy of the detail coefficients and the energy of the approximation coefficients; S4: Construct a drone behavior feature vector from the signal stability feature value and the temperature gradient change rate feature value, and input it into the recognition model for threat level assessment; S5: Dynamically activate corresponding countermeasures based on the assessment results, including communication jamming, navigation deception, or physical capture methods, to achieve graded response and precise handling of intruding drones.

2. The method for early warning and countermeasures against low-altitude unmanned aerial vehicles (UAVs) applicable to temporary control areas according to claim 1, characterized in that, The assessment of the degree of interference in the UAV communication link specifically includes: The system acquires real-time radio signal frequency offset data from drones, performs zero-sequence processing on the acquired radio signal frequency offset data to construct a zero-sequence frequency sequence, analyzes the zero-sequence frequency sequence, calculates the signal stability characteristic value based on the analysis results, and determines whether the signal stability characteristic value is greater than or equal to a preset threshold. If it is, the degree of interference to the drone communication link is considered minor; otherwise, the degree of interference to the drone communication link is considered severe.

3. The method for early warning and countermeasures against low-altitude unmanned aerial vehicles (UAVs) applicable to temporary control areas according to claim 1, characterized in that, The identification of whether the drone is in an abnormal operating state specifically includes: The system acquires real-time surface temperature difference data of the drone, analyzes the surface temperature difference data, calculates the characteristic value of the temperature gradient change rate based on the analysis results, and determines whether the characteristic value of the temperature gradient change rate is greater than or equal to a preset threshold. If it is, the drone is in an abnormal operating state; otherwise, the drone is not in an abnormal operating state.

4. The method for early warning and countermeasures against low-altitude unmanned aerial vehicles (UAVs) applicable to temporary control areas according to claim 1, characterized in that, Based on the identification model, a drone risk score is output, specifically including: The signal stability feature value and temperature gradient change rate feature value of the UAV are obtained. The signal stability feature value and temperature gradient change rate feature value are used to construct a UAV behavior feature vector, which is then input into the recognition model. The training objective of the recognition model is to minimize the error between the predicted UAV risk score and the actual UAV risk score. The UAV risk score is output based on the trained recognition model. The recognition model is a gradient boosting tree model.

5. The method for early warning and countermeasures against low-altitude unmanned aerial vehicles (UAVs) in temporary controlled areas according to claim 4, characterized in that, The training process of the recognition model is as follows: The signal stability features, surface temperature gradient change rate features, and actual drone risk scores of UAVs from multiple historical flight missions are obtained and used to construct a training dataset. A new decision tree is fitted based on the current residuals and weighted and superimposed on the overall model output according to the set learning rate. During the training process, regularization strategies are introduced to prevent overfitting, including limiting the maximum depth of the decision tree, setting the minimum number of samples in the leaf nodes, and using L1 / L2 regularization terms. The optimal hyperparameter combination is selected through cross-validation to ensure that the model has good generalization performance.

6. The method for early warning and countermeasures against low-altitude unmanned aerial vehicles (UAVs) applicable to temporary control areas according to claim 1, characterized in that, The threat level assessment specifically includes: Determine if the drone risk score is greater than or equal to a preset first threshold. If yes, the threat level is the highest level. If no, determine if the drone risk score is less than or equal to a preset second threshold. If yes, the threat level is the lowest level. If no, the threat level is the medium level.

7. The method for early warning and countermeasures against low-altitude unmanned aerial vehicles (UAVs) applicable to temporary control areas according to claim 1, characterized in that, The tiered response and precise handling of intruding drones specifically include: For drones with the highest threat level, i.e., those with serious communication interference and abnormal operating conditions, immediately activate high-intensity communication interference and navigation deception measures, and coordinate with physical capture devices to implement emergency interception and forced control. For drones with a medium threat level, i.e., those with communication disturbances and local temperature anomalies but not yet posing a direct threat, directional communication jamming is initiated in conjunction with radar tracking and signal suppression, while warning commands are issued to guide them away from the controlled area. For drones with the lowest threat level, i.e., aircraft with stable communication and normal temperature changes but still within the no-fly zone, only electronic fence restrictions and voice warning measures will be activated.

8. A low-altitude unmanned aerial vehicle (UAV) early warning and countermeasure system suitable for temporarily controlled areas, characterized in that: The method for early warning and countermeasures against low-altitude unmanned aerial vehicles (UAVs) applicable to temporary control areas as described in any one of claims 1-7 includes: The data acquisition module collects radio signal frequency offset data and fuselage surface temperature difference data of the UAV in real time through multi-source detection equipment deployed in the temporary control area. The signal stability analysis module performs zero-sequence processing on the acquired radio signal frequency offset data, constructs a zero-sequence frequency sequence, and calculates signal stability characteristic values ​​to assess the degree of interference to the UAV communication link. The temperature gradient analysis module calculates the characteristic value of the temperature gradient change rate based on the acquired fuselage surface temperature difference data, which is used to identify whether the UAV has an abnormal operating state. The threat level assessment module constructs a UAV behavior feature vector from signal stability feature values ​​and temperature gradient change rate feature values, which is then input into the identification model for threat level assessment. The graded countermeasure control module dynamically activates corresponding countermeasure strategies based on the assessment results, including communication interference, navigation deception, or physical capture methods, to achieve graded response and precise handling of intruding UAVs.

Images