Individual drone countermeasure method and system based on radio frequency identification and dynamic jamming

Abstract

The present invention discloses a method and system for countering individual drones based on radio frequency identification and dynamic interference, belonging to the field of drone technology. By collecting wide-band IQ data, extracting hidden features such as instantaneous frequency deviation fluctuations and envelope entropy anomalies, and using variational autoencoders to achieve high-dimensional embedding expression, the system combines graph neural networks to perform structured signal recognition, significantly improving the ability to distinguish frequency hopping, spread spectrum or Wi-Fi / LTE simulation signals. Finally, a dynamic interference strategy is generated based on the recognition results, realizing accurate identification and intelligent suppression of illegal drone communications, effectively compensating for the technical defects of existing systems in insufficient recognition robustness and countermeasure effectiveness in complex environments.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles (UAVs), and in particular to a method and system for countering individual UAVs based on radio frequency identification and dynamic interference. Background Art

[0002] Individual drone countermeasures involve the use of technical means to detect, identify, disrupt, control, or force a single or small number of unauthorized drones that may pose a security threat, in order to effectively control or remove them. This method is commonly used in airports, sensitive areas, and major event venues to ensure airspace safety and public order.

[0003] The existing technology has the following shortcomings:

[0004] In RFID-based drone communication detection, malicious drones can employ signal spoofing to mimic legitimate communications (such as Wi-Fi and LTE) in their remote control or image transmission signals. Alternatively, they can employ frequency hopping and spread spectrum to intentionally weaken the stability of their signatures, thereby bypassing signature library matching and pattern recognition, causing the system to miss detection or misidentify the drone as an ordinary device. This type of signal deception is particularly subtle in complex environments and can render countermeasures ineffective, creating security vulnerabilities. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for countering individual drones based on radio frequency identification and dynamic interference to address the shortcomings of the background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for countering individual drones based on radio frequency identification and dynamic jamming, comprising:

[0007] Use wide-band radio frequency receiving equipment to collect communication signals in the airspace and obtain complex IQ data streams;

[0008] Perform bandpass filtering, window framing, and synchronization processing on the IQ data stream to extract the target signal segment;

[0009] Extracting radio frequency high-order micro-features based on the target signal segment, wherein the micro-features include instantaneous frequency deviation fluctuation features and envelope entropy anomaly features;

[0010] Inputting the instantaneous frequency deviation fluctuation feature and the envelope entropy abnormal feature into a representation learning model for high-dimensional encoding processing, wherein the representation learning model is a variational autoencoder and outputs an embedding vector for identification and discrimination;

[0011] Inputting the embedding vector into a signal classification model to determine whether the signal belongs to drone communication, wherein the signal classification model is selected from a graph neural network;

[0012] If the identification result indicates that the signal is an illegal drone communication signal, an interference strategy is generated based on its frequency, modulation characteristics and timing rules to dynamically interfere with the target signal segment.

[0013] Preferably, the method of collecting airspace communication signals using a wide-band radio frequency receiving device specifically includes: using a software-defined radio device with a frequency coverage range of 300 MHz to 6 GHz to collect wireless signals in the target airspace, and saving the collected original signals in the form of complex IQ samples. The IQ signal is represented as ; where I[t] and Q[t] are the in-phase and quadrature components respectively, and j is the imaginary unit.

[0014] Preferably, the method for obtaining the instantaneous frequency deviation fluctuation characteristics is: calculating the instantaneous frequency , represents the derivative of the signal phase with respect to time, defined as: ;in, is the instantaneous phase of the IQ signal, and the calculation formula is: ; By calculating the phase change of continuous sampling points , and divided by the sampling period T, we get the frequency offset sequence: ;Where, T is the sampling period; Represents the instantaneous frequency value of each sampling point; further calculating the standard deviation of the frequency sequence, we can get the frequency deviation fluctuation intensity value, and its formula is: ; Where SG is the frequency deviation fluctuation intensity value; is the average frequency offset, and M is the number of samples.

[0015] Preferably, the method for obtaining the abnormal characteristics of envelope entropy is: is the IQ signal modulus, that is, the envelope, and the expression is: ; Normalize the signal envelope into a probability distribution form, and then calculate the entropy value based on the Shannon entropy definition: ; H is the envelope entropy, Represents the probability density of the i-th envelope amplitude interval; F is the number of segments. To detect anomalies, the envelope entropy anomaly deviation value is further defined. , the expression is: ;in, is the standard envelope entropy of known legal drones, Indicates the envelope entropy of the current signal.

[0016] Preferably, the instantaneous frequency deviation fluctuation feature and the envelope entropy abnormal feature are input into a representation learning model for high-dimensional encoding processing, specifically including:

[0017] The micro-features include instantaneous frequency deviation fluctuation features and envelope entropy anomaly features. The frequency deviation fluctuation intensity value and the envelope entropy anomaly deviation value are combined to form a two-dimensional input vector, which is input into the variational autoencoder model for high-dimensional encoding processing.

[0018] The variational autoencoder model includes an encoder network for extracting a latent variable mean vector and a standard deviation vector of an input feature vector, and calculating a latent variable embedding vector based on the latent variable mean and standard deviation;

[0019] The embedded vector is used as the input feature for subsequent drone signal discrimination.

[0020] Preferably, to determine whether a signal belongs to drone communication, the signal classification model is selected from a graph neural network, specifically including:

[0021] The embedding vector representing the output of the variational autoencoder is used as the node feature; each target signal segment corresponds to a node, and the embedding vector represents the attribute characteristics of the node, which is used to construct the graph structure;

[0022] Construct a graph G=(V,E), where V represents a set of nodes, each corresponding to a segment of RF signal; E represents a set of edges, representing the correlation between nodes. Build a graph neural network model: each layer aggregates and updates information about neighboring nodes, and the final layer outputs node label probabilities, indicating whether the target signal is a drone communication.

[0023] Output a binary classification label for each node: Label 1: indicates that the target signal segment belongs to drone communication; Label 0: indicates that the target signal segment is non-drone communication or background interference.

[0024] Preferably, the interference strategy generating step includes:

[0025] According to the center frequency of the target signal Calculate the interference center frequency, the expression is: ; represents the center frequency of the interference signal, represents the center frequency of the target signal; Δf represents the frequency offset compensation coefficient;

[0026] Based on target bandwidth Calculate the interference bandwidth using the expression: Where, represents the interference signal bandwidth, and α represents the safety frequency multiplication factor;

[0027] According to the target modulation mode Determine the interference modulation type, the expression is: Where, Indicates the interference modulation mode, Match is the modulation adaptation function;

[0028] According to the target signal strength Calculate the interference power, the expression is: Where, represents the interference transmission power, represents the target signal strength, β represents the power margin coefficient; Z represents the minimum interference threshold of the device;

[0029] According to the target communication cycle and signal timing Generate the interference time window set, the expression is: Where, represents the set of time windows in which the interference is applied, Indicates the detected target signal activity time; Indicates the target communication period.

[0030] The present invention also provides an individual UAV countermeasure system based on radio frequency identification and dynamic interference, which includes a radio frequency signal acquisition module, a signal preprocessing module, a micro-feature extraction module, a representation learning and encoding module, and a signal recognition and discrimination module;

[0031] RF signal acquisition module: uses wide-band RF receiving equipment to collect communication signals in the airspace and obtain complex IQ data streams;

[0032] Signal preprocessing module: performs bandpass filtering, window framing and synchronization processing on the IQ data stream to extract the target signal segment;

[0033] Micro-feature extraction module: extracts RF high-order micro-features based on the target signal segment, including instantaneous frequency deviation fluctuation features and envelope entropy anomaly features;

[0034] Representation learning encoding module: inputs the instantaneous frequency deviation fluctuation characteristics and envelope entropy abnormality characteristics into the representation learning model for high-dimensional encoding processing. The representation learning model is a variational autoencoder and outputs an embedded vector for identification and discrimination;

[0035] Signal recognition and discrimination module: inputs the embedding vector into a signal classification model to determine whether the signal belongs to drone communication, and the signal classification model is selected from a graph neural network;

[0036] Dynamic interference decision-making and execution module: If the identification result shows that the signal is an illegal drone communication signal, an interference strategy is generated based on its frequency, modulation characteristics and timing rules to dynamically interfere with the target signal segment.

[0037] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0038] 1. This invention overcomes the technical bottleneck of traditional RFID systems, which rely on static feature libraries and are easily circumvented by signal camouflage, by constructing a drone-specific countermeasure method that integrates high-order RF signal feature extraction, deep representation learning, graph structure discrimination, and parameterized dynamic jamming. By introducing micro-features such as instantaneous frequency deviation fluctuations and envelope entropy anomalies, it effectively characterizes complex signal behaviors such as frequency hopping, spread spectrum, and camouflaged modulation. High-dimensional feature representation is achieved using a variational autoencoder, and combined with a graph neural network to model the timing and correlation between signals, significantly improving the robustness and accuracy of identifying illegal drone communications.

[0039] 2. This invention further combines the identification results to generate a jamming strategy. Based on the target signal's frequency, bandwidth, modulation method, power, and periodic structure, the jamming parameters are dynamically set to implement directional, synchronous, and adaptive jamming suppression. This mechanism enables precise jamming and guided suppression of camouflaged drones while reducing the risk of false interference and power consumption. It offers high recognition accuracy, high responsiveness, and strong environmental adaptability, making it suitable for deployment in scenarios such as airports, sensitive areas, and major events. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0041] Figure 1 This is a mind map of the method of the present invention.

[0042] Figure 2 This is a mind map of the system modules of the present invention. DETAILED DESCRIPTION

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0044] Example 1, please refer to Figure 1 As shown, the individual drone countermeasure method based on radio frequency identification and dynamic jamming described in this embodiment includes:

[0045] Use wide-band radio frequency receiving equipment to collect communication signals in the airspace and obtain complex IQ data streams;

[0046] Perform bandpass filtering, window framing, and synchronization processing on the IQ data stream to extract the target signal segment;

[0047] Extracting radio frequency high-order micro-features based on the target signal segment, wherein the micro-features include instantaneous frequency deviation fluctuation features and envelope entropy anomaly features;

[0048] Inputting the instantaneous frequency deviation fluctuation feature and the envelope entropy abnormal feature into a representation learning model for high-dimensional encoding processing, wherein the representation learning model is a variational autoencoder and outputs an embedding vector for identification and discrimination;

[0049] Inputting the embedding vector into a signal classification model to determine whether the signal belongs to drone communication, wherein the signal classification model is selected from a graph neural network;

[0050] If the identification result indicates that the signal is an illegal drone communication signal, an interference strategy is generated based on its frequency, modulation characteristics and timing rules to dynamically interfere with the target signal segment.

[0051] The radio frequency signal acquisition step of the present invention is intended to obtain the original data of all possible drone communication signals in the target airspace, providing a signal basis for subsequent identification and interference.

[0052] During flight, drones rely on control signals and image transmission signals to communicate with their controllers. Common frequency bands include but are not limited to 2.4GHz, 5.8GHz, 900MHz, and some Wi-Fi, Bluetooth, LTE, or 5G bands. To ensure wide coverage and adaptability, this step uses wide-band RF receiving equipment to simultaneously or continuously scan and monitor multiple frequency bands, acquiring wireless communication data streams and storing the original signals in complex IQ (In-Phase and Quadrature) sampling format.

[0053] The wide-band RF receiving device may include one or a combination of the following components: a software-defined radio (SDR) with a tunable frequency range covering 300 MHz to 6 GHz, such as USRP, HackRF, BladeRF, AirSpy, etc.; a front-end low-noise amplifier (LNA) to improve receiving sensitivity; a multi-band antenna or a steerable directional antenna array to enhance the ability to receive signals in a specific direction; a clock synchronization module (GPSDO or local frequency stabilization source) to ensure sampling consistency; and a high-speed data interface (USB 3.0, PCIe, Gigabit Ethernet, etc.) connected to the processing terminal to transmit IQ data streams.

[0054] The device is set to cover the commonly used communication frequency bands of drones (such as 2.4GHz±100MHz, 5.8GHz±150MHz, etc.), and can dynamically adjust the monitoring center frequency and bandwidth according to the scenario.

[0055] Sampling parameter settings: Sampling rate: The preferred range is 10 MHz ~ 40 MHz, determined by signal bandwidth and device performance; Resolution bit: 8-bit or 12-bit complex sampling is commonly used, corresponding to the I / Q channels respectively; Data structure: Each frame of data is a complex vector IQ of length N, where . I(t) represents the in-phase component, that is, the part that has the same frequency and phase as the reference signal (usually the carrier signal). It usually represents the real part of the signal. Q(t) represents the quadrature component, that is, the part that is 90 degrees out of phase with the I component. It usually represents the imaginary part of the signal. j is the imaginary unit, which is used to represent the phase difference between the quadrature component Q(t) and the in-phase component I(t). The collected IQ data is stored in binary or HDF5 format, and the accompanying metadata includes: timestamp (Unix time), center frequency, bandwidth, sampling rate, device number; current receiving antenna direction (if applicable).

[0056] The complex IQ data stream may include but is not limited to the following types of signals:

[0057] Frequency-hopping control signals (e.g., FHSS) transmitted by the drone remote controller; continuous video streams (e.g., OFDM-encoded video signals) transmitted by the drone image transmission module; control and image data transmitted using Wi-Fi, Bluetooth, or LTE protocols; and other non-drone background wireless signals (as control samples or ambient noise).

[0058] This step supports the parallel deployment of multiple devices to improve spatial resolution and response speed; it can be combined with array antenna technology to achieve signal direction positioning; if it is necessary to cover 5G drone communication channels, the frequency band can be expanded to the Sub-6GHz and mmWave (millimeter wave) range.

[0059] Through this step, high-quality drone communication data can be stably obtained in real complex electromagnetic environments. It is particularly suitable for unbiased original capture of unknown or disguised communication signals, providing a basic guarantee for subsequent feature extraction and intelligent recognition, and has strong environmental adaptability and system scalability.

[0060] The present invention performs necessary signal preprocessing on the collected complex IQ data stream, including bandpass filtering, window framing and signal synchronization processing, to ensure the signal quality, structural consistency and processing efficiency of the input data.

[0061] Bandpass filtering is used to remove background interference signals that are irrelevant to the target frequency band, improve the signal-to-noise ratio, and isolate the effective energy area of the frequency band where the drone communicates.

[0062] According to the center frequency configured in the signal acquisition stage And bandwidth B, construct a bandpass filter: ; The filter can take one of the following forms:

[0063] Digital FIR filter (Finite Impulse Response);

[0064] IIR filters (such as Butterworth, Chebyshev);

[0065] Window function filters (Hanning window, Blackman window, etc.);

[0066] In the implementation process, the signal can be converted to the frequency domain based on FFT (Fast Fourier Transform), then filtered in the frequency domain and inversely transformed back to the time domain;

[0067] The filter design parameters are based on the sampling rate Determined by the target signal characteristics, for example, the center frequency of the image transmission signal is set to 5.8 GHz and the bandwidth is set to 20 MHz.

[0068] Windowing and Framing is used to divide a continuous IQ signal sequence into signal frames of equal length, facilitating batch processing and feature analysis while enhancing timing sensitivity.

[0069] Set the window length L (e.g. 1024 points, 2048 points) and the overlap ratio r (e.g. 50%) to prevent edge information loss. Use a window function to weight each frame to reduce spectrum leakage. Common window functions include Hamming window, Hanning window, Blackman window, etc. The signal after windowing is: Where x[n] is a real or complex sequence of original signal samples (such as IQ data). This is a frame of the signal, containing continuous samples of length L, expressed as sampled values in the time domain. It usually comes from a frame segmented from the IQ data. w[n] represents the window function coefficient, with a domain of [0, L−1]. The window function is a mathematical function used for weighted processing. Common windows include the Hamming window, the Hanning window, and the Blackman window. Its main function is to reduce the influence of frame edges and suppress spectral leakage. xw[n] represents the windowed signal, which is the result of multiplying each sample by the corresponding position of the window function. It is the input for subsequent feature extraction or spectrum analysis. n represents a discrete time index, from 0 to L−1, representing the position index of the signal sample currently being processed.

[0070] Sliding window processing obtains the frame sequence: ;in, Where, Frame shift.

[0071] Synchronous processing means unifying the reference starting point of the signal, ensuring the phase, frequency and structure alignment between different frames, and eliminating errors caused by sampling offset or carrier drift.

[0072] Starting point synchronization: Use the energy threshold method to detect the signal starting position and determine whether the frame contains a valid signal segment: ;like >θ (preset energy threshold), the frame is determined to be a signal frame.

[0073] Estimate the carrier frequency offset Δf and phase offset Δϕ between adjacent frames and digitally down-convert the IQ data: Where, represents the complex exponential twiddle factor, represents the corrected IQ signal.

[0074] The spectrum center is fine-tuned using the Maximum Likelihood Frequency Offset Estimator (ML Estimator) or the pilot-based frequency offset estimation method. The degree of frequency offset can be determined and dynamically corrected by periodic pilot symbol matching.

[0075] Based on the processed frame sequence, a set of frames that may be drone communications is extracted as input for subsequent feature extraction and recognition steps.

[0076] Simple rules can be used for initial screening (e.g., continuous energy above the threshold for more than 3 consecutive frames); or a primary classifier (e.g., lightweight CNN, clustering algorithm) can be introduced to perform preliminary classification of signal segments; after extraction, the target signal segment data structure is generated: , each segment is of length L; each segment is accompanied by meta-information: center frequency, timestamp, preliminary confidence score, etc.

[0077] Through the above preprocessing process, background noise can be effectively filtered, signal morphology can be regularized, and key communication events can be aligned to ensure the data quality and discrimination efficiency of subsequent feature extraction and recognition tasks, especially in the face of complex multi-source interference scenarios with stability and accuracy.

[0078] After completing the extraction of the target signal segment, the present invention needs to perform RF high-order micro-feature analysis on the segment to explore the fine-grained properties of the signal that cannot be identified by traditional frequency domain features, and enhance the robustness of recognition of camouflaged, encrypted or frequency-hopping drone signals.

[0079] The instantaneous frequency deviation fluctuation feature is used to characterize the subtle changes in the frequency fluctuation of the signal on the time axis. This feature can reveal the communication behavior characteristics generated by the frequency hopping control signal or unstable carrier source.

[0080] Instantaneous frequency represents the derivative of the signal phase with respect to time and is defined as: ;in, is the instantaneous phase of the IQ signal, and the calculation formula is: ; By calculating the phase change of continuous sampling points , and divided by the sampling period T, the frequency offset sequence can be obtained: ;Where, T is the sampling period; Represents the instantaneous frequency value of each sampling point; further calculating the standard deviation of the frequency sequence, we can get the frequency deviation fluctuation intensity value, and its formula is: ; Where SG is the frequency deviation fluctuation intensity value; is the average frequency offset, and M is the number of samples.

[0081] High-frequency deviation fluctuation intensity: This is commonly seen in frequency-hopping remote controls or low-quality transmitters. Low-frequency deviation fluctuation intensity: This corresponds to industrial-grade image transmission modules or static relay signals and can be used as a key indicator to distinguish camouflaged signals from real drone signals.

[0082] The envelope entropy anomaly feature is used to evaluate the signal modulation depth and its randomness characteristics, and to capture modulation anomalies, masked modulation patterns or structural unnatural signals.

[0083] set up is the IQ signal modulus, that is, the envelope, and the expression is: ; Normalize the signal envelope into a probability distribution form (by constructing a histogram or kernel density estimation), and then calculate the entropy value based on the Shannon entropy definition: ; H is the envelope entropy, Indicates the probability density of the i-th envelope amplitude interval; F is the number of segments. If the signal has a high degree of certainty (such as fixed modulation image transmission), its entropy value is low; if the signal has strong modulation jitter or irregular envelope changes, its entropy value increases. In order to detect anomalies, the envelope entropy anomaly deviation value is further defined , the expression is: ;in, is the standard envelope entropy of known legal drones, Indicates the envelope entropy of the current signal. Large It may indicate that the signal has been artificially scrambled, mixed modulated, or simulated and forged; it is suitable for identifying mixed modulated drone control signals forged through SDR; combined with the high-frequency deviation fluctuation intensity value, it can improve the classification accuracy of complex signal sources.

[0084] The instantaneous frequency deviation fluctuation feature and the envelope entropy abnormal feature are input into the representation learning model for high-dimensional encoding processing. The representation learning model is a variational autoencoder that outputs an embedded vector for identification and discrimination, specifically including:

[0085] The micro features include instantaneous frequency deviation fluctuation features and envelope entropy anomaly features.

[0086] And includes the following representation learning encoding steps:

[0087] The frequency deviation fluctuation intensity value and the envelope entropy abnormal deviation value are combined into a two-dimensional input vector, which is input into the variational autoencoder model for high-dimensional encoding processing.

[0088] The variational autoencoder model includes an encoder network for extracting a latent variable mean vector and a standard deviation vector of an input feature vector; a reparameter sampling module for calculating a latent variable embedding vector based on the latent variable mean and standard deviation;

[0089] The embedded vector is used as an input feature for subsequent drone signal discrimination to improve the accuracy of classification and recognition of camouflaged, frequency-hopping or abnormal radio frequency communication signals.

[0090] The present invention inputs the embedding vector into a signal classification model to determine whether the signal belongs to drone communication. The signal classification model is selected from a graph neural network and specifically includes:

[0091] The embedding vector representing the output of the variational autoencoder is used as the node feature; each target signal segment corresponds to a node, and the embedding vector represents the attribute characteristics of the node, which is used to construct the graph structure.

[0092] Construct a graph G=(V,E), where V represents a set of nodes, each corresponding to a segment of RF signal; E represents a set of edges, representing the correlation between nodes (such as time proximity, frequency proximity, and feature similarity); optional edge construction methods include: time series edges: connecting signal segments that are consecutive in time; similarity edges: measuring proximity in feature space based on cosine similarity, Euclidean distance, etc.

[0093] Constructing a graph neural network model (such as GCN, GraphSAGE, GAT): Each layer aggregates and updates the information of neighboring nodes, expressed as: ;in: Represents the features of the i-th node at the l-th layer; represents the neighbor set of the i-th node; represents a learnable weight matrix; σ represents an activation function (such as ReLU); the output of the last layer is the node label probability, indicating whether the signal is a drone communication.

[0094] A binary classification label is output for each node (i.e., each segment of the embedding vector): Label 1: indicates that the signal segment belongs to drone communication (control signal or image transmission); Label 0: indicates that the signal segment is not drone communication or background interference. At the same time, the classification confidence (softmax or sigmoid) is output for reference by the interference decision module.

[0095] If the identification result indicates that the signal is an illegal drone communication signal, a jamming strategy is generated based on its frequency, modulation characteristics, and timing patterns to dynamically jam the target signal segment, specifically including:

[0096] Interference frequency selection (frequency alignment) includes: ; represents the center frequency of the interference signal, Indicates the center frequency of the target signal (provided by the identification module). Δf represents the frequency offset compensation coefficient, which is used for dynamic frequency tracking. The initial value can be 0 and can be adjusted to cope with frequency hopping behavior.

[0097] Interference bandwidth matching includes: Where, represents the interference signal bandwidth, It represents the effective bandwidth of the target communication signal, and α represents the safe frequency multiplication factor (the recommended value range is 1.1~1.5), which is used to ensure coverage of the target spectrum range and to effectively suppress it even in the case of frequency deviation or frequency hopping.

[0098] Interference modulation mode adaptation includes: Where, Indicates the interference modulation mode (such as CW, Noise, Chirp, OFDM, Sweep, etc.), Indicates the modulation mode of the target signal (such as QPSK, FSK, DSSS, etc.); Match is the modulation adaptation function, and the rule can be set as: If it is frequency hopping (FHSS), then Use broad spectrum noise; if For fixed modulation image transmission (such as OFDM), Use frequency suppression or anti-modulation deception.

[0099] Dynamic power control (based on signal strength) includes: Where, represents the interference transmission power, represents the target signal strength (which can be obtained through RSSI or energy estimation); β represents the power margin factor (1.5-3.0 is recommended); and Z represents the minimum interference threshold of the device (taking into account the ambient noise floor).

[0100] Interference timing control (synchronization time window) includes: Where, represents the set of time windows in which the interference is applied, Indicates the detected target signal activity time; Represents the target communication cycle (which can estimate the time interval of the target image transmission or control signal); interference is performed at the key alignment points of the target communication cycle to improve interference efficiency and reduce energy consumption.

[0101] Through the dynamic jamming strategy generation method, it is possible to accurately suppress or deceive complex drone signals such as frequency hopping, time division, and multi-modulation. At the same time, it reduces power output and the risk of false positives while ensuring the effectiveness of the jamming. This is conducive to building a rule-driven + learning-optimized composite jamming system architecture.

[0102] Example 2, please refer to Figure 2 As shown, the drone individual countermeasure system based on radio frequency identification and dynamic interference described in this embodiment includes a radio frequency signal acquisition module, a signal preprocessing module, a micro-feature extraction module, a representation learning and encoding module, and a signal recognition and discrimination module;

[0103] RF signal acquisition module: uses wide-band RF receiving equipment to collect communication signals in the airspace and obtain complex IQ data streams;

[0104] Signal preprocessing module: performs bandpass filtering, window framing and synchronization processing on the IQ data stream to extract the target signal segment;

[0105] Micro-feature extraction module: extracts RF high-order micro-features based on the target signal segment, including instantaneous frequency deviation fluctuation features and envelope entropy anomaly features;

[0106] Representation learning encoding module: inputs the instantaneous frequency deviation fluctuation characteristics and envelope entropy abnormality characteristics into the representation learning model for high-dimensional encoding processing. The representation learning model is a variational autoencoder and outputs an embedded vector for identification and discrimination;

[0107] Signal recognition and discrimination module: inputs the embedding vector into a signal classification model to determine whether the signal belongs to drone communication, and the signal classification model is selected from a graph neural network;

[0108] Dynamic interference decision-making and execution module: If the identification result shows that the signal is an illegal drone communication signal, an interference strategy is generated based on its frequency, modulation characteristics and timing rules to dynamically interfere with the target signal segment.

[0109] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0110] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0111] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0112] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A method for countering individual drones based on radio frequency identification and dynamic jamming, characterized by: include: Use wide-band radio frequency receiving equipment to collect communication signals in the airspace and obtain complex IQ data streams; Perform bandpass filtering, window framing, and synchronization processing on the IQ data stream to extract the target signal segment; Extracting radio frequency high-order micro-features based on the target signal segment, wherein the micro-features include instantaneous frequency deviation fluctuation features and envelope entropy anomaly features; Inputting the instantaneous frequency deviation fluctuation feature and the envelope entropy abnormal feature into a representation learning model for high-dimensional encoding processing, wherein the representation learning model is a variational autoencoder and outputs an embedding vector for identification and discrimination; Inputting the embedding vector into a signal classification model to determine whether the signal belongs to drone communication, wherein the signal classification model is selected from a graph neural network; If the identification result indicates that the signal is an illegal drone communication signal, an interference strategy is generated based on its frequency, modulation characteristics and timing rules to dynamically interfere with the target signal segment.

2. The method for countering individual drones based on radio frequency identification and dynamic jamming according to claim 1, characterized in that: The method of collecting airspace communication signals using a wide-band radio frequency receiving device specifically includes: using a software-defined radio device with a frequency coverage range of 300 MHz to 6 GHz to collect wireless signals in the target airspace, and saving the collected original signals in the form of complex IQ samples. The IQ signal is represented as ; where I[t] and Q[t] are the in-phase and quadrature components respectively, and j is the imaginary unit.

3. The method for countering individual drones based on radio frequency identification and dynamic jamming according to claim 1, characterized in that: The method for obtaining the instantaneous frequency deviation fluctuation characteristics is: calculate the instantaneous frequency , represents the derivative of the signal phase with respect to time, defined as: ;in, is the instantaneous phase of the IQ signal, and the calculation formula is: ; By calculating the phase change of continuous sampling points , and divided by the sampling period T, we get the frequency offset sequence: ;Where, T is the sampling period; Represents the instantaneous frequency value of each sampling point; further calculating the standard deviation of the frequency sequence, we can get the frequency deviation fluctuation intensity value, and its formula is: ; Where SG is the frequency deviation fluctuation intensity value; is the average frequency offset, and M is the number of samples.

4. The method for countering individual drones based on radio frequency identification and dynamic jamming according to claim 3, characterized in that: The method for obtaining the abnormal characteristics of envelope entropy is as follows: is the IQ signal modulus, i.e., envelope, and is expressed as: ; Normalize the signal envelope into a probability distribution form, and then calculate the entropy value based on the Shannon entropy definition: ; H is the envelope entropy, represents the probability density of the i-th envelope amplitude interval; F is the number of segments. To find anomalies, we further define the envelope entropy anomaly deviation value. , the expression is: ;in, is the standard envelope entropy of known legal drones, Indicates the envelope entropy of the current signal.

5. The method for countering individual drones based on radio frequency identification and dynamic jamming according to claim 4, characterized in that: Inputting the instantaneous frequency deviation fluctuation characteristics and envelope entropy abnormality characteristics into the representation learning model for high-dimensional encoding processing, specifically including: The micro-features include instantaneous frequency deviation fluctuation features and envelope entropy anomaly features. The frequency deviation fluctuation intensity value and the envelope entropy anomaly deviation value are combined to form a two-dimensional input vector, which is input into the variational autoencoder model for high-dimensional encoding processing. The variational autoencoder model includes an encoder network for extracting a latent variable mean vector and a standard deviation vector of an input feature vector, and calculating a latent variable embedding vector based on the latent variable mean and standard deviation; The embedded vector is used as the input feature for subsequent drone signal discrimination.

6. The method for countering individual drones based on radio frequency identification and dynamic jamming according to claim 5, characterized in that: To determine whether the signal belongs to drone communication, the signal classification model is selected from a graph neural network, specifically including: The embedding vector representing the output of the variational autoencoder is used as the node feature; each target signal segment corresponds to a node, and the embedding vector represents the attribute characteristics of the node, which is used to construct the graph structure; Construct a graph G=(V,E), where V represents a set of nodes, each corresponding to a segment of RF signal; E represents a set of edges, representing the correlation between nodes. Build a graph neural network model: each layer aggregates and updates information about neighboring nodes, and the final layer outputs node label probabilities, indicating whether the target signal is a drone communication. Output a binary classification label for each node: Label 1: indicates that the target signal segment belongs to drone communication; Label 0: indicates that the target signal segment is non-drone communication or background interference.

7. The method for countering individual drones based on radio frequency identification and dynamic jamming according to claim 6, characterized in that: The interference strategy generation step includes: According to the center frequency of the target signal Calculate the interference center frequency, the expression is: ; represents the center frequency of the interference signal, represents the center frequency of the target signal; Δf represents the frequency offset compensation coefficient; Based on target bandwidth Calculate the interference bandwidth using the expression: Where, represents the interference signal bandwidth, and α represents the safety frequency multiplication factor; According to the target modulation mode Determine the interference modulation type, the expression is: Where, Indicates the interference modulation mode, Match is the modulation adaptation function; According to the target signal strength Calculate the interference power, the expression is: Where, represents the interference transmission power, represents the target signal strength, β represents the power margin coefficient; Z represents the minimum interference threshold of the device; According to the target communication cycle and signal timing Generate the interference time window set, the expression is: Where, represents the set of time windows in which the interference is applied, Indicates the detected target signal activity time; Indicates the target communication period.

8. A system for countering individual drones based on radio frequency identification and dynamic jamming, for implementing the method for countering individual drones based on radio frequency identification and dynamic jamming as described in any one of claims 1 to 7, characterized in that: It includes RF signal acquisition module, signal preprocessing module, micro-feature extraction module, representation learning encoding module and signal recognition and discrimination module; RF signal acquisition module: uses wide-band RF receiving equipment to collect communication signals in the airspace and obtain complex IQ data streams; Signal preprocessing module: performs bandpass filtering, window framing and synchronization processing on the IQ data stream to extract the target signal segment; Micro-feature extraction module: extracts RF high-order micro-features based on the target signal segment, including instantaneous frequency deviation fluctuation features and envelope entropy anomaly features; Representation learning encoding module: inputs the instantaneous frequency deviation fluctuation characteristics and envelope entropy abnormality characteristics into the representation learning model for high-dimensional encoding processing. The representation learning model is a variational autoencoder and outputs an embedded vector for identification and discrimination; Signal recognition and discrimination module: inputs the embedding vector into a signal classification model to determine whether the signal belongs to drone communication, and the signal classification model is selected from a graph neural network; Dynamic interference decision-making and execution module: If the identification result shows that the signal is an illegal drone communication signal, an interference strategy is generated based on its frequency, modulation characteristics and timing rules to dynamically interfere with the target signal segment.

Images