Unmanned aerial vehicle multi-mode interference device based on digital source

Abstract

The invention discloses an unmanned aerial vehicle multi-mode interference device based on a digital source, and relates to the technical field of electromagnetic security and protection. According to the unmanned aerial vehicle multi-mode interference device based on the digital source, airspace wireless signals are monitored in real time through multi-channel software defined radio SDR equipment, frequency hopping data of a target unmanned aerial vehicle are collected, and historical data traceability analysis is combined; backtracking the frequency hopping decision logic of the unmanned aerial vehicle by using a digital source, extracting a communication mode and predicting possible frequency hopping points in the future; in the interference implementation stage, a predictive interference strategy is adopted, when a target unmanned aerial vehicle hops to a predictive frequency band, directional high-power interference is triggered immediately, a communication link of the target unmanned aerial vehicle is blocked, the frequency hopping logic of the target unmanned aerial vehicle is invalid, the target unmanned aerial vehicle is forced to enter a blind frequency hopping state, and the communication stability is reduced; the communication mode of the target unmanned aerial vehicle is copied in combination with a signal mirroring technology, and a part of credible communication signals are forged to guide the target unmanned aerial vehicle to misjudge the optimal communication frequency, so that the target unmanned aerial vehicle enters a frequency band susceptible to interference by mistake, the communication capability is further reduced, and the interference effect is improved.

Description

Technical Field

[0001] The invention relates to the field of electromagnetic security technology, in particular to a multi-mode jamming device for unmanned aerial vehicles based on a digital source. Background Art

[0002] In the field of modern electromagnetic confrontation and security, drone jamming technology has become a key defense method and is widely used in military reconnaissance and interception, protection of sensitive areas and airspace security management. Traditional drone jamming methods mainly rely on electromagnetic suppression, signal deception or network attacks to weaken their communication and navigation capabilities, making them unable to perform their assigned tasks.

[0003] Electromagnetic suppression mainly covers the control frequency band of the drone through high-power interference signals, forcing it to lose remote operation commands and then land or return. This method is still effective on drones with fixed frequency or broadband communication, but when facing drones using frequency hopping communication, the interference signal is difficult to accurately cover its dynamic frequency, resulting in ineffective interference; signal deception mainly targets the navigation system of the drone, such as forging GPS signals or ground beacons to cause it to deviate from its route or misposition. Although such means are more effective for drones with a single navigation mode, with the development of inertial navigation IMU, visual navigation and fusion perception technology, enemy drones have gradually acquired stronger anti-deception capabilities, and the role of traditional deception methods has been greatly weakened; network attack methods rely on communication link hijacking or command injection to remotely take over the drone, but modern drones use more complex communication protocols and have adaptive anti-attack mechanisms, which significantly increases the difficulty of infiltration.

[0004] In summary, it can be seen that traditional jamming methods are difficult to effectively counter UAVs with intelligent frequency hopping capabilities, especially UAVs that use Bayesian Q-learning or deep reinforcement learning to optimize frequency hopping strategies. They can dynamically adjust their communication strategies according to the interference environment. In this context, how to accurately predict the communication mode of UAVs and implement more covert and efficient jamming strategies has become a key issue that urgently needs to be broken through. Summary of the invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] The present invention provides a UAV multi-mode jamming device based on a digital source to solve the problems that fixed frequency band jamming is difficult to counter intelligent frequency hopping UAVs, blind frequency scanning has high energy consumption, and signal deception and network attacks are easy to be circumvented.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: The embodiment of the present invention provides a multi-mode jamming device for unmanned aerial vehicles based on a digital source, which includes: The target drone identification module is responsible for detecting and identifying target drones in the airspace and collecting their communication parameters; The frequency hopping prediction module is responsible for real-time tracking of the target UAV’s communication behavior based on its frequency hopping pattern, and predicting its next communication frequency; The frequency hopping prediction module relies on Markov chain modeling to analyze the frequency hopping pattern of the target drone, and combines deep reinforcement learning DQN to optimize signal tracking and lock the signal at the moment the target drone switches to the predicted frequency band; The frequency hopping interruption module is responsible for using the prediction information to destroy the communication stability of the target UAV when the target UAV hops to the predicted frequency band; An inductive signal deception module, which induces the target drone to make wrong decisions by forging signals; The inductive signal deception module uses signal mirroring technology to replicate the communication mode of the target drone and forge some credible communication signals; Interference effect monitoring module: This module is responsible for real-time evaluation of interference effects and dynamic optimization of interference strategies. It dynamically adjusts interference waveforms, power and time windows based on real-time feedback.

[0008] As a preferred solution of the UAV multi-mode jamming device based on digital source described in the present invention, wherein: in the target UAV identification module, a multi-channel software defined radio SDR device is used to monitor the wireless signals in the airspace in real time and extract the frequency hopping data of the target UAV; combined with the historical data tracing analysis, the digital source is used to trace back the frequency hopping decision logic of the target UAV, extract its communication mode, and predict possible frequency hopping points in the future.

[0009] As a preferred solution of the UAV multi-mode jammer based on digital source described in the present invention, the jamming mode of the UAV multi-mode jammer is: Step S1, using a multi-channel software defined radio (SDR) device to monitor the airspace in real time, collect the frequency hopping data of the target UAV, combine historical data tracing analysis, use digital sources to trace back the UAV's frequency hopping decision logic, extract its communication mode, and infer possible future frequency hopping points; Step S2, based on the frequency hopping pattern prediction result generated in step S1, real-time monitoring of the communication activity of the target UAV, and locking the signal to obtain communication data when it hops to the predicted frequency band; Step S3, when the target UAV hops to the predicted frequency band, directional high-power interference is immediately triggered to interrupt its frequency hopping logic, forcing it to enter a blind frequency hopping state, thereby reducing its communication stability; Step S4, continuously monitor the response of the target UAV, including frequency hopping failure rate, data packet loss rate and communication delay, and dynamically adjust the interference strategy based on real-time feedback to adaptively optimize the interference waveform, power and time window.

[0010] As a preferred solution of the UAV multi-mode jamming device based on digital source described in the present invention, the frequency hopping data includes frequency hopping sequence, frequency utilization mode and burst transmission characteristics.

[0011] As a preferred solution of the UAV multi-mode jammer based on digital source described in the present invention, the steps of combining historical data tracing analysis, using digital source to trace back the UAV's frequency hopping decision logic, extracting its communication mode, and inferring possible future frequency hopping points are as follows: A multi-channel software defined radio (SDR) device is used to monitor the airspace wireless signal, collect the frequency hopping data of the target drone, and define the frequency hopping sequence as follows: , in, Indicates at time The frequency hopping sequence within Indicates that the target drone is in The frequency used by the time slice, is the total number of frequency hopping within the sampling time window, The frequency hopping decision logic of the target UAV is analyzed, and the hidden Markov model is used for state modeling. The frequency hopping state transition probability matrix is ​​set as: , in, is the state transition probability matrix, Indicates the current frequency Jump to next frequency The probability of Indicates at time Frequency hopping status at the moment, Indicates at time Frequency hopping status at all times, combined with historical data Perform parameter estimation and use the Baum-Welch algorithm to calculate the state transition probability. The calculation formula is: , in, is the length of the historical data time window, is an indicator function, and when the condition is met, the value is , otherwise the value is , Speculate the possible future frequency hopping points of the target drone : .

[0012] As a preferred solution of the UAV multi-mode jamming device based on digital source described in the present invention, wherein: in step S2, Markov chain modeling and deep reinforcement learning DQN are used to optimize signal tracking.

[0013] As a preferred solution of the multi-mode jamming device for unmanned aerial vehicles based on digital sources described in the present invention, the steps of using Markov chain modeling and deep reinforcement learning DQN to optimize signal tracking are as follows: Based on step S1, Markov chain modeling and deep reinforcement learning DQN are used to optimize the tracking and prediction of the target UAV signal. The frequency hopping behavior of the target UAV is modeled by a first-order Markov chain. The modeling process is expressed as: , That is, the next frequency hopping point of the drone is based on the current frequency Determine, combine historical data, and construct the frequency hopping state transfer matrix: , in, Indicates the frequency of the drone Jump to The probability of the target UAV is calculated by long-term monitoring of the frequency hopping data of the target UAV and the maximum likelihood estimation MLE is used: , in, Indicates historical data arrive The number of frequency hopping, Represents the total number of all possible frequency hopping situations. The prediction formula for the next possible frequency hopping point of the target drone is: ; Based on Markov chain prediction, deep reinforcement learning is used to optimize signal tracking and adjust the tracking strategy at the moment of drone frequency hopping. Define the state space as : , in, is the currently monitored frequency hopping frequency, is the frequency hopping transfer matrix, is the current signal quality, Define the action space as : , that is, predict the next frequency hopping of the drone and adjust the tracking strategy, The reward function is defined as : If the target UAV's frequency hopping point is successfully predicted, then , If the prediction fails, , The DQN objective function is: , in, is the learning rate, is the discount factor, is the maximum Q value of the future state.

[0014] As a preferred solution of the UAV multi-mode jamming device based on a digital source described in the present invention, wherein: in step S3, while implementing the interference, the communication mode of the target UAV is copied by using signal mirroring technology, and some credible communication signals are forged to guide it to misjudge the optimal communication frequency. By inducing interference, the target UAV selects a frequency band that is more susceptible to interference, weakens its communication capability, and increases the misjudgment rate, causing it to make wrong decisions and enter an inefficient communication state, thereby improving the interference effect.

[0015] As a preferred solution of the multi-mode jammer of a UAV based on a digital source described in the present invention, the step of triggering directional high-power jammer and interrupting its frequency hopping logic is as follows: When the target drone hops to the predicted frequency When the directional high-power interference is triggered immediately, the communication link is blocked and the directional high-power interference is triggered immediately, causing the directional high-power interference to enter the blind frequency hopping state. The interference signal is modeled as: , in, Indicates at time The interference signal applied, is the amplitude of the interference signal, is the current frequency hopping frequency of the target drone, is the current time, is the phase of the interference signal, The interference power is dynamically adjusted based on the signal-to-noise ratio (SNR) control mechanism in the following ways: like ,but , like ,but , in, For the current moment The applied interference signal power, The target drone is at the current frequency The signal-to-noise ratio, is the SNR threshold, and are the maximum and minimum available interference powers respectively; While implementing interference, the signal mirroring technology is used to copy the communication mode of the target drone and forge some credible communication signals to lead it to misjudge the optimal communication frequency. The original communication signal of the target UAV is defined as: , in, Indicates that the target drone is at time The communication mode, is the communication frequency currently used by the target drone, is the current transmission power of the target UAV, The modulation method of the target drone, is the burst transmission mode of the target drone, The characteristic of a forged signal is defined as : , in, Forged communication signals, is the original signal of the target drone, It is a misleading disturbance introduced artificially; When the target drone is interfered with, in order to guide it to hop to a frequency band that is more susceptible to interference, the most susceptible frequency band is calculated. : , in, is the frequency most susceptible to interference, The first frequency in the currently available communication frequency set frequency, For frequency The signal-to-noise ratio, For frequency The intensity of the interference, The table selects the frequency with the smallest signal-to-noise ratio and interference ratio.

[0016] As a preferred solution of the multi-mode jamming device for unmanned aerial vehicles based on digital sources described in the present invention, in step S4, the step of dynamically adjusting the jamming strategy according to real-time feedback is: Monitoring of interference effects, including: Frequency hopping failure rate, defines the frequency hopping failure rate for: , in, is the frequency hopping failure rate, is the number of frequency hopping failures of the target UAV under interference, is the total frequency hopping times of the target UAV, when The higher the value, the higher the jamming success rate, and the more difficult it is for the target drone to establish a stable communication link. Defining the packet loss rate for: , in, is the data packet loss rate, is the number of packets lost during the interference period, Total number of packets transmitted for the target drone, high The value indicates that the jamming caused significant damage to the communication link of the target UAV. Define the communication delay to the target drone for: , in, is the average communication delay, For the The transmission time of a data packet, is the total number of packets; the larger A value of means that the jamming successfully delayed the target UAV’s data transmission; According to the monitored interference effect, the interference parameters are dynamically optimized, including interference power, interference waveform and time window. Based on the frequency hopping failure rate Adjust the interference power , the adjustment formula is: , in, is the updated interference power, is the current interference power, is the interference power adjustment factor, is the target frequency hopping failure rate, when Below target When the interference power is automatically increased, the interference intensity is enhanced. If it is too high, reduce the power; Defining interference time windows And according to the communication delay Make adjustments, the adjustment formula is: , in, is the adjusted interference time window, is the current interference time window, is the time window adjustment factor, is the target communication delay, like Below target , indicating that the target UAV has restored some communication capabilities, then the interference time window is extended; Real-time calculation of optimal interference frequency band , jamming the target drone’s communication channel: , in, is the current optimal interference frequency band, For frequency band The interference intensity on is the communication weight of the target UAV in this frequency band. The goal is to select the communication frequency band with the strongest interference effect and the greatest impact on the target UAV.

[0017] The beneficial effects of the present invention are as follows: the present invention monitors airspace wireless signals in real time through a multi-channel software defined radio (SDR) device, collects frequency hopping data of a target UAV, combines historical data tracing analysis, uses a digital source to trace back the frequency hopping decision logic of the UAV, extracts the communication mode and predicts possible future frequency hopping points; on this basis, a frequency hopping prediction model is constructed, a hidden Markov model (HMM) is used for state modeling, and the Baum-Welch algorithm is used to calculate the state transition probability, and the next frequency hopping point of the target UAV is inferred in combination with the maximum transition probability, thereby improving the accuracy of future frequency hopping point prediction; based on the prediction results, the Markov chain modeling and deep reinforcement learning (DQN) are used to optimize signal tracking, and the signal is accurately locked at the moment when the target UAV hops to the predicted frequency band, thereby improving the signal capture success rate and providing accurate data support for interference implementation; In the jamming implementation phase, a predictive jamming strategy is adopted. When the target UAV hops to the predicted frequency band, directional high-power jamming is immediately triggered to block its communication link, invalidate its frequency hopping logic, force it into a blind frequency hopping state, and reduce communication stability. In addition, the present invention combines signal mirroring technology to replicate the communication mode of the target drone and forge some credible communication signals, leading it to misjudge the optimal communication frequency and mistakenly enter the frequency band susceptible to interference, further reducing the communication capability and increasing the misjudgment rate, causing it to make wrong decisions and enter an inefficient communication state, thereby improving the interference effect; After the jamming is implemented, key indicators such as the frequency hopping failure rate, data packet loss rate and communication delay of the target UAV are continuously monitored, and the jamming strategy is dynamically adjusted based on real-time feedback, including adaptive optimization of the jamming waveform, power and time window, to maintain the continuity and pertinence of the jamming effect.

[0018] Compared with traditional jamming methods, the present invention improves the accuracy and real-time performance of jamming through intelligent signal tracking and predictive frequency hopping analysis, avoids high energy consumption and jamming instability caused by blind frequency scanning, and uses induced signal deception to make the target UAV enter an erroneous decision-making mode, thereby enhancing the jamming effect. In addition, an adaptive optimization mechanism is introduced to adjust the jamming strategy according to the real-time response of the target UAV, making the jamming method more flexible and difficult to circumvent. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0020] Figure 1 It is a schematic diagram of the framework of the multi-mode jamming device of UAV based on digital source of the present invention. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0022] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0023] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0024] Example 1, reference Figure 1 , this embodiment provides a UAV multi-mode jamming device based on a digital source, comprising: The target drone identification module is responsible for detecting and identifying target drones in the airspace and collecting their communication parameters; In the target drone identification module, a multi-channel software-defined radio (SDR) device is used to monitor the wireless signals in the airspace in real time and extract the frequency hopping data of the target drone. Combined with historical data traceability analysis, the target drone’s frequency hopping decision logic is traced back using digital sources to extract its communication mode and predict possible future frequency hopping points. The frequency hopping prediction module is responsible for real-time tracking of the target UAV’s communication behavior based on its frequency hopping pattern, and predicting its next communication frequency; The frequency hopping prediction module relies on Markov chain modeling to analyze the frequency hopping pattern of the target drone, and combines deep reinforcement learning DQN to optimize signal tracking and lock the signal at the moment the target drone switches to the predicted frequency band; The frequency hopping interruption module is responsible for using the prediction information to destroy the communication stability of the target UAV when the target UAV hops to the predicted frequency band; An inductive signal deception module, which induces the target drone to make wrong decisions by forging signals; The inductive signal deception module uses signal mirroring technology to replicate the communication mode of the target drone and forge some credible communication signals; Interference effect monitoring module: This module is responsible for real-time evaluation of interference effects and dynamic optimization of interference strategies. It dynamically adjusts interference waveforms, power and time windows based on real-time feedback.

[0025] This embodiment also provides a jamming method of a multi-mode jamming device for a drone based on a digital source, including: Step S1, using a multi-channel software defined radio (SDR) device to monitor the airspace in real time, collect the frequency hopping data of the target UAV, combine historical data tracing analysis, use digital sources to trace back the UAV's frequency hopping decision logic, extract its communication mode, and infer possible future frequency hopping points; Frequency hopping data includes frequency hopping sequence, frequency utilization pattern and burst transmission characteristics; Combined with historical data traceability analysis, the steps of using digital sources to trace back the UAV's frequency hopping decision logic, extracting its communication mode, and inferring possible future frequency hopping points are as follows: A multi-channel software defined radio (SDR) device is used to monitor the airspace wireless signal, collect the frequency hopping data of the target drone, and define the frequency hopping sequence as follows: , in, Indicates at time The frequency hopping sequence within Indicates that the target drone is in The frequency used by the time slice, is the total number of frequency hopping within the sampling time window, The frequency hopping decision logic of the target UAV is analyzed, and the hidden Markov model is used for state modeling. The frequency hopping state transition probability matrix is ​​set as: , in, is the state transition probability matrix, Indicates the current frequency Jump to next frequency The probability of Indicates at time Frequency hopping status at the moment, Indicates at time Frequency hopping status at all times, combined with historical data Perform parameter estimation and use the Baum-Welch algorithm to calculate the state transition probability. The calculation formula is: , in, is the length of the historical data time window, is an indicator function, and when the condition is met, the value is , otherwise the value is , Speculate the possible future frequency hopping points of the target drone : , Specifically, in this step, the SDR device is used to collect the frequency hopping data of the target UAV, and the frequency hopping law is modeled through the hidden Markov model HMM. The Baum-Welch algorithm is used to estimate the state transition probability, and the next frequency hopping point of the target UAV is predicted based on the maximum transition probability. The communication mode of the target UAV can be deeply analyzed in combination with historical data to improve the prediction accuracy of future frequency hopping points. Step S2, based on the frequency hopping pattern prediction result generated in step S1, real-time monitoring of the communication activity of the target UAV, and locking the signal to obtain communication data when it hops to the predicted frequency band; In step S2, Markov chain modeling and deep reinforcement learning DQN are used to optimize signal tracking; The steps of using Markov chain modeling and deep reinforcement learning DQN to optimize signal tracking are: Based on step S1, Markov chain modeling and deep reinforcement learning DQN are used to optimize the tracking and prediction of the target UAV signal. The frequency hopping behavior of the target UAV is modeled by a first-order Markov chain. The modeling process is expressed as: , That is, the next frequency hopping point of the drone is based on the current frequency Determine, combine historical data, and construct the frequency hopping state transfer matrix: , in, Indicates the frequency of the drone Jump to The probability of the target UAV is calculated by long-term monitoring of the frequency hopping data of the target UAV and the maximum likelihood estimation MLE is used: , in, Indicates historical data arrive The number of frequency hopping, Represents the total number of all possible frequency hopping situations. The prediction formula for the next possible frequency hopping point of the target drone is: ; Based on Markov chain prediction, deep reinforcement learning is used to optimize signal tracking and adjust the tracking strategy at the moment of drone frequency hopping. Define the state space as : , in, is the currently monitored frequency hopping frequency, is the frequency hopping transfer matrix, is the current signal quality, Define the action space as : , that is, predict the next frequency hopping of the drone and adjust the tracking strategy, The reward function is defined as : If the target UAV's frequency hopping point is successfully predicted, then , If the prediction fails, , The DQN objective function is: , in, is the learning rate, is the discount factor, is the maximum Q value of the future state; Specifically, Markov chain modeling is used here to predict the frequency hopping behavior of the target UAV, and deep reinforcement learning DQN is combined to optimize signal tracking. On the basis of Markov modeling, DQN is used to enhance the agent's adaptability to UAV signals, so that it can quickly lock the signal when the target UAV hops to the predicted frequency band, effectively improving the success rate of UAV signal monitoring.

[0026] Step S3, when the target UAV hops to the predicted frequency band, directional high-power interference is immediately triggered to interrupt its frequency hopping logic, forcing it to enter a blind frequency hopping state, thereby reducing its communication stability; In step S3, while implementing the interference, the communication mode of the target UAV is copied by using the signal mirroring technology, and some credible communication signals are forged to guide it to misjudge the optimal communication frequency. By inducing interference, the target UAV selects a frequency band that is more susceptible to interference, weakens its communication capability, and increases the misjudgment rate, causing it to make wrong decisions and enter an inefficient communication state, thereby improving the interference effect; The steps to trigger directional high-power interference and interrupt its frequency hopping logic are: When the target drone hops to the predicted frequency When the directional high-power interference is triggered immediately, the communication link is blocked and the directional high-power interference is triggered immediately, causing the directional high-power interference to enter the blind frequency hopping state. The interference signal is modeled as: , in, Indicates at time The interference signal applied, is the amplitude of the interference signal, is the current frequency hopping frequency of the target drone, is the current time, is the phase of the interference signal, The interference power is dynamically adjusted based on the signal-to-noise ratio (SNR) control mechanism in the following ways: like ,but , like ,but , in, For the current moment The applied interference signal power, The target drone is at the current frequency The signal-to-noise ratio, is the SNR threshold, and are the maximum and minimum available interference powers respectively; While implementing interference, the signal mirroring technology is used to copy the communication mode of the target drone and forge some credible communication signals to lead it to misjudge the optimal communication frequency. The original communication signal of the target UAV is defined as: , in, Indicates that the target drone is at time The communication mode, is the communication frequency currently used by the target drone, is the current transmission power of the target UAV, The modulation method of the target drone, is the burst transmission mode of the target drone, The characteristic of a forged signal is defined as : , in, Forged communication signals, is the original signal of the target drone, It is a misleading disturbance introduced artificially; When the target drone is interfered with, in order to guide it to hop to a frequency band that is more susceptible to interference, the most susceptible frequency band is calculated. : , in, is the frequency most susceptible to interference, The first frequency in the currently available communication frequency set frequency, For frequency The signal-to-noise ratio, For frequency The intensity of the interference, The table selects the frequency with the smallest signal-to-noise ratio and interference ratio; Specifically, high-power directional interference and signal mirror deception are combined here to interfere with and guide the frequency hopping behavior of the target drone: High-power jamming applies directional jamming signals at the moment when the target drone hops to the predicted frequency band, making it unable to communicate stably. Signal mirror deception forges credible communication signals to guide the target drone to make wrong decisions and choose a communication frequency band that is more susceptible to interference. The adaptive jamming strategy monitors the signal-to-noise ratio and dynamically adjusts the jamming power to maximize the jamming effect. Step S4, continuously monitor the response of the target UAV, including frequency hopping failure rate, data packet loss rate and communication delay, and dynamically adjust the interference strategy according to real-time feedback, adaptively optimize the interference waveform, power and time window; The steps of continuously monitoring the response of the target UAV, including the frequency hopping failure rate, data packet loss rate and communication delay, and dynamically adjusting the jamming strategy based on real-time feedback are as follows: Monitoring of interference effects, including: Frequency hopping failure rate, defines the frequency hopping failure rate for: , in, is the frequency hopping failure rate, is the number of frequency hopping failures of the target UAV under interference, is the total frequency hopping times of the target UAV, when The higher the value, the higher the jamming success rate, and the more difficult it is for the target drone to establish a stable communication link. Defining the packet loss rate for: , in, is the data packet loss rate, is the number of packets lost during the interference period, Total number of packets transmitted for the target drone, high The value indicates that the jamming caused significant damage to the communication link of the target UAV. Define the communication delay to the target drone for: , in, is the average communication delay, For the The transmission time of a data packet, is the total number of packets; the larger A value of means that the jamming successfully delayed the target UAV’s data transmission; According to the monitored interference effect, the interference parameters are dynamically optimized, including interference power, interference waveform and time window. Based on the frequency hopping failure rate Adjust the interference power , the adjustment formula is: , in, is the updated interference power, is the current interference power, is the interference power adjustment factor, is the target frequency hopping failure rate, when Below target When the interference power is automatically increased, the interference intensity is enhanced. If it is too high, reduce the power; Defining interference time windows And according to the communication delay Make adjustments, the adjustment formula is: , in, is the adjusted interference time window, is the current interference time window, is the time window adjustment factor, is the target communication delay, like Below target , indicating that the target UAV has restored some communication capabilities, then the interference time window is extended; Real-time calculation of optimal interference frequency band , jamming the target drone’s communication channel: , in, is the current optimal interference frequency band, For frequency band The interference intensity on is the communication weight of the target UAV in this frequency band. The goal is to select the communication frequency band with the strongest interference effect and the greatest impact on the target UAV; Specifically, this step monitors the frequency hopping failure rate, data packet loss rate and communication delay of the target UAV in real time to evaluate the interference effect, and adaptively adjusts the interference strategy based on the feedback data. Specifically: adaptively adjust the interference power to maintain appropriate interference intensity, optimize the interference time window to ensure the continuity of interference, destroy the stable communication of the target UAV, and optimize the spectrum dynamic interference to make the interference strategy more accurate and effective.

[0027] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-mode jammer for drones based on digital sources, characterized by: include, The target drone identification module is responsible for detecting and identifying target drones in the airspace and collecting their communication parameters; The frequency hopping prediction module is responsible for real-time tracking of the target UAV’s communication behavior based on its frequency hopping pattern, and predicting its next communication frequency; The frequency hopping prediction module relies on Markov chain modeling to analyze the frequency hopping pattern of the target drone, and combines deep reinforcement learning DQN to optimize signal tracking and lock the signal at the moment the target drone switches to the predicted frequency band; The frequency hopping interruption module is responsible for using the prediction information to destroy the communication stability of the target UAV when the target UAV hops to the predicted frequency band; An inductive signal deception module, which induces the target drone to make wrong decisions by forging signals; The inductive signal deception module uses signal mirroring technology to replicate the communication mode of the target drone and forge some credible communication signals; Interference effect monitoring module: This module is responsible for real-time evaluation of interference effects and dynamic optimization of interference strategies. It dynamically adjusts interference waveforms, power and time windows based on real-time feedback.

2. A multi-mode jamming device for unmanned aerial vehicles based on a digital source as claimed in claim 1, characterized in that: In the target drone identification module, a multi-channel software-defined radio (SDR) device is used to monitor the wireless signals in the airspace in real time and extract the frequency hopping data of the target drone. Combined with historical data traceability analysis, the digital source is used to trace the frequency hopping decision logic of the target drone, extract its communication mode, and predict possible frequency hopping points in the future.

3. A multi-mode jamming device for unmanned aerial vehicles based on digital sources as claimed in claim 2, characterized in that: The interference mode of the drone multi-mode jammer is: Step S1, using a multi-channel software defined radio (SDR) device to monitor the airspace in real time, collect the frequency hopping data of the target UAV, combine historical data tracing analysis, use digital sources to trace back the UAV's frequency hopping decision logic, extract its communication mode, and infer possible future frequency hopping points; Step S2, based on the frequency hopping pattern prediction result generated in step S1, real-time monitoring of the communication activity of the target UAV, and locking the signal to obtain communication data when it hops to the predicted frequency band; Step S3, when the target UAV hops to the predicted frequency band, directional high-power interference is immediately triggered to interrupt its frequency hopping logic; Step S4, continuously monitor the response of the target UAV, including frequency hopping failure rate, data packet loss rate and communication delay, and dynamically adjust the interference strategy based on real-time feedback to adaptively optimize the interference waveform, power and time window.

4. A multi-mode jamming device for unmanned aerial vehicles based on a digital source as claimed in claim 3, characterized in that: The frequency hopping data includes a frequency hopping sequence, a frequency utilization mode and a burst transmission feature.

5. A multi-mode jamming device for unmanned aerial vehicles based on a digital source as claimed in claim 4, characterized in that: The steps of combining historical data tracing analysis, using digital sources to trace back the frequency hopping decision logic of the drone, extracting its communication mode, and inferring possible future frequency hopping points are as follows: A multi-channel software defined radio (SDR) device is used to monitor the airspace wireless signal, collect the frequency hopping data of the target drone, and define the frequency hopping sequence as follows: ， in, Indicates at time The frequency hopping sequence within Indicates that the target drone is in The frequency used by the time slice, is the total number of frequency hopping within the sampling time window, The frequency hopping decision logic of the target UAV is analyzed, and the hidden Markov model is used for state modeling. The frequency hopping state transition probability matrix is ​​set as: , in, is the state transition probability matrix, Indicates the current frequency Jump to next frequency The probability of Indicates at time Frequency hopping status at the moment, Indicates at time Frequency hopping status at all times, combined with historical data Perform parameter estimation and use the Baum-Welch algorithm to calculate the state transition probability. The calculation formula is: ， in, is the length of the historical data time window, is an indicator function, and when the condition is met, the value is , otherwise the value is , Speculate the possible future frequency hopping points of the target drone : 。 6. A multi-mode jamming device for unmanned aerial vehicles based on digital sources as claimed in claim 5, characterized in that: In step S2, Markov chain modeling and deep reinforcement learning DQN are used to optimize signal tracking.

7. A multi-mode jamming device for unmanned aerial vehicles based on digital sources as claimed in claim 6, characterized in that: The steps of using Markov chain modeling and deep reinforcement learning DQN to optimize signal tracking are: Based on step S1, Markov chain modeling and deep reinforcement learning DQN are used to optimize the tracking and prediction of the target UAV signal. The frequency hopping behavior of the target UAV is modeled by a first-order Markov chain. The modeling process is expressed as: ， That is, the next frequency hopping point of the drone is based on the current frequency Determine, combine historical data, and construct the frequency hopping state transfer matrix: ， in, Indicates the frequency of the drone Jump to The probability of the target UAV is calculated by long-term monitoring of the frequency hopping data of the target UAV and the maximum likelihood estimation MLE is used: ， in, Indicates historical data arrive The number of frequency hopping, Represents the total number of all possible frequency hopping situations. The prediction formula for the next possible frequency hopping point of the target drone is: ； Based on Markov chain prediction, deep reinforcement learning is used to optimize signal tracking and adjust the tracking strategy at the moment of drone frequency hopping. Define the state space as : ， in, is the currently monitored frequency hopping frequency, is the frequency hopping transfer matrix, is the current signal quality, Define the action space as : , that is, predict the next frequency hopping of the drone and adjust the tracking strategy, The reward function is defined as : If the target UAV's frequency hopping point is successfully predicted, then , If the prediction fails, , The DQN objective function is: ， in, is the learning rate, is the discount factor, is the maximum Q value of the future state.

8. The multi-mode jamming device for unmanned aerial vehicles based on digital sources as claimed in claim 7, characterized in that: In step S3, while implementing interference, the communication mode of the target drone is copied using signal mirroring technology, and some credible communication signals are forged.

9. A multi-mode jamming device for unmanned aerial vehicles based on a digital source as claimed in claim 8, characterized in that: The steps of triggering directional high-power interference and interrupting its frequency hopping logic are: When the target drone hops to the predicted frequency When the directional high-power interference is triggered immediately, the communication link is blocked and the directional high-power interference is triggered immediately, causing the directional high-power interference to enter the blind frequency hopping state. The interference signal is modeled as: ， in, Indicates at time The interference signal applied, is the amplitude of the interference signal, is the current frequency hopping frequency of the target drone, is the current time, is the phase of the interference signal, The interference power is dynamically adjusted based on the signal-to-noise ratio (SNR) control mechanism in the following ways: like ,but , like ,but , in, For the current moment The applied interference signal power, The target drone is at the current frequency The signal-to-noise ratio, is the SNR threshold, and are the maximum and minimum available interference powers respectively; While implementing interference, the signal mirroring technology is used to copy the communication mode of the target drone and forge some credible communication signals to lead it to misjudge the optimal communication frequency. The original communication signal of the target UAV is defined as: ， in, Indicates that the target drone is at time The communication mode, is the communication frequency currently used by the target drone, is the current transmission power of the target UAV, The modulation method of the target drone, is the burst transmission mode of the target drone, The characteristic of a forged signal is defined as : ， in, Forged communication signals, is the original signal of the target drone, It is a misleading disturbance introduced artificially; When the target drone is interfered with, in order to guide it to hop to a frequency band that is more susceptible to interference, the most susceptible frequency band is calculated. : ， in, is the frequency most susceptible to interference, The first frequency in the currently available communication frequency set frequency, For frequency The signal-to-noise ratio, For frequency The intensity of the interference, The table selects the frequency with the smallest signal-to-noise ratio and interference ratio.

10. A multi-mode jamming device for unmanned aerial vehicles based on digital sources as claimed in claim 2, characterized in that: In step S4, the step of dynamically adjusting the interference strategy according to the real-time feedback is: Monitoring of interference effects, including: Frequency hopping failure rate, defines the frequency hopping failure rate for: ， in, is the frequency hopping failure rate, is the number of frequency hopping failures of the target UAV under interference, is the total frequency hopping times of the target UAV, when The higher the value, the higher the jamming success rate, and the more difficult it is for the target drone to establish a stable communication link. Defining the packet loss rate for: ， in, is the data packet loss rate, is the number of packets lost during the interference period, The total number of packets transmitted for the target drone, Define the communication delay to the target drone for: ， in, is the average communication delay, For the The transmission time of a data packet, is the total number of data packets; According to the monitored interference effect, the interference parameters are dynamically optimized, including interference power, interference waveform and time window. Based on the frequency hopping failure rate Adjust the interference power , the adjustment formula is: ， in, is the updated interference power, is the current interference power, is the interference power adjustment factor, is the target frequency hopping failure rate, when Below target When the interference power is automatically increased, the interference intensity is enhanced. If it is too high, reduce the power; Defining interference time windows And according to the communication delay Make adjustments, the adjustment formula is: ， in, is the adjusted interference time window, is the current interference time window, is the time window adjustment factor, is the target communication delay, like Below target , indicating that the target UAV has restored some communication capabilities, then the interference time window is extended; Real-time calculation of optimal interference frequency band , jamming the target drone’s communication channel: ， in, is the current optimal interference frequency band, For frequency band The interference intensity on is the communication weight of the target UAV in this frequency band. The goal is to select the communication frequency band with the strongest interference effect and the greatest impact on the target UAV.

Images