Multi-mode unmanned aerial vehicle cooperative interference control method and device, and medium

Abstract

The invention discloses a multi-mode unmanned aerial vehicle cooperative interference control method and device and a medium, and relates to the technical field of unmanned aerial vehicle interference, and the method comprises the steps: dynamically selecting an interference waveform parameter through employing an interference efficiency value of an unmanned aerial vehicle, obtaining a multi-mode interference instruction set, the method comprises the following steps: dynamically adjusting a waveform emission time sequence of an unmanned aerial vehicle by adopting a clock calibration protocol based on a consistency algorithm to form a composite interference signal, electing a coordination node according to a real-time interference efficiency value of the unmanned aerial vehicle, fusing radio frequency signal data and a multi-mode interference instruction set into the elected coordination node, and obtaining an interference scheme. And optimizing the transmitting power and frequency band selection of each unmanned aerial vehicle by adopting a game algorithm, generating an optimal interference parameter of each unmanned aerial vehicle, and controlling the array antennas of all unmanned aerial vehicles to radiate radio frequency interference signals to the interference target according to the composite interference signal, the optimal interference parameter and the interference scheme of each unmanned aerial vehicle. According to the unmanned aerial vehicle cooperative interference method, the cooperative interference capability, the intelligent level and the stability of multiple unmanned aerial vehicles are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of unmanned aerial vehicle jamming technology, and particularly relates to a multi-mode unmanned aerial vehicle cooperative jamming control method, device and medium. BACKGROUND

[0002] With the rapid development of modern electronic information technology, multi-unmanned aerial vehicle cooperative jamming technology, as an important means to improve electronic suppression capability, has been widely concerned. In recent years, with the integration of artificial intelligence, distributed control and adaptive signal processing technology, the cooperative jamming mechanism gradually evolves towards intelligence and autonomy. Among them, the use of beamforming and space-time coding technology enhances the spatial focusing ability of jamming energy. In addition, the distributed cooperative control mechanism based on consensus algorithm also provides theoretical support for the synchronization and coordination of multi-unmanned aerial vehicles under the condition of no central node. Overall, multi-unmanned aerial vehicle cooperative jamming technology is becoming a key component in the field of modern unmanned aerial vehicle jamming countermeasures.

[0003] However, the existing unmanned aerial vehicle cooperative jamming method still has room for improvement. First, the individual differences of unmanned aerial vehicles, such as endurance capability, communication quality and load performance, are not fully considered in the weight of dynamic state parameters in the jamming task, resulting in high-load or low-efficiency nodes still being assigned high-priority tasks, affecting the overall stability and sustained jamming capability. In addition, there is a lack of joint analysis capability of multi-dimensional features (spectrum, time domain and modulation pattern) of radio frequency signals, resulting in insufficient jamming mode matching accuracy. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides a multi-mode unmanned aerial vehicle cooperative jamming control method to solve the problem of insufficient unmanned aerial vehicle jamming mode matching accuracy.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a multi-mode unmanned aerial vehicle cooperative jamming control method, which comprises,

[0008] The radio frequency sensor carried by each unmanned aerial vehicle collects radio frequency signal data of the jamming target in the airspace, inputs the radio frequency signal data into the SVM model, and obtains the jamming waveform parameters;

[0009] According to the remaining endurance time, communication link quality and load state of the unmanned aerial vehicle, the jamming efficiency value of the unmanned aerial vehicle is calculated;

[0010] The jamming efficiency value of the unmanned aerial vehicle is used to dynamically select the jamming waveform parameters, and a multi-modal jamming instruction set is obtained;

[0011] The clock calibration protocol based on the consistency algorithm is adopted to dynamically adjust the waveform transmission timing of the unmanned aerial vehicle, and a composite jamming signal is formed.

[0012] According to the real-time jamming effectiveness value of the unmanned aerial vehicle, a coordination node is elected, radio frequency signal data and a multi-mode jamming instruction set are fused into the elected coordination node, and a jamming scheme is obtained.

[0013] A game algorithm is used to optimize the transmission power and frequency band selection of each unmanned aerial vehicle, and the optimal jamming parameters of each unmanned aerial vehicle are generated.

[0014] According to the composite jamming signal of each unmanned aerial vehicle, the optimal jamming parameters and the jamming scheme, the array antenna of all unmanned aerial vehicles is controlled to radiate radio frequency jamming signals to the jamming target.

[0015] As a preferred scheme of the multi-mode unmanned aerial vehicle cooperative jamming control method, the radio frequency sensor carried by each unmanned aerial vehicle collects radio frequency signal data of the jamming target in the airspace, inputs the radio frequency signal data into an SVM model, and obtains jamming waveform parameters.

[0016] The radio frequency sensor carried by each unmanned aerial vehicle collects radio frequency signals of the jamming target in the airspace in real time, and obtains radio frequency signal data.

[0017] The radio frequency signal data is input into an SVM model, and the jamming waveform parameters are obtained by analyzing the frequency spectrum characteristics, time domain characteristics and modulation style characteristics in the radio frequency signal data.

[0018] The jamming waveform parameters include suppression jamming waveform parameters, aiming jamming waveform parameters and smart noise jamming waveform parameters.

[0019] As a preferred scheme of the multi-mode unmanned aerial vehicle cooperative jamming control method, the jamming effectiveness value of the unmanned aerial vehicle is calculated according to the remaining endurance time, the communication link quality and the load state of the unmanned aerial vehicle.

[0020] The remaining endurance time of the unmanned aerial vehicle is normalized to obtain an endurance coefficient.

[0021] The signal-to-noise ratio and the bit error rate of the communication link quality of the unmanned aerial vehicle are measured, and are converted into a communication quality coefficient through a Sigmoid function.

[0022] The jamming power amplifier efficiency and the antenna gain in the load state of the unmanned aerial vehicle are evaluated to generate a load effectiveness coefficient.

[0023] The endurance coefficient, the communication quality coefficient and the load effectiveness coefficient are weighted and summed to obtain the jamming effectiveness value of the unmanned aerial vehicle.

[0024] As a preferred scheme of the multi-mode unmanned aerial vehicle cooperative jamming control method, the jamming waveform parameters are dynamically selected by using the jamming effectiveness value of the unmanned aerial vehicle, and a multi-modal jamming instruction set is obtained, specifically,

[0025] Based on the jamming effectiveness value of the unmanned aerial vehicle, N jamming mode intervals are divided, and each jamming mode interval corresponds to the suppression jamming waveform parameters, the aiming jamming waveform parameters and the smart noise jamming waveform parameters in turn;

[0026] The jamming effectiveness value of the unmanned aerial vehicle is mapped to the jamming mode interval, the corresponding jamming waveform parameters are extracted, the corresponding jamming waveform parameters are matched with the scene where the jamming target is located, and a multi-modal jamming instruction set is obtained.

[0027] As a preferred scheme of the multi-mode unmanned aerial vehicle cooperative jamming control method, the clock synchronization protocol based on the consistency algorithm is used to dynamically adjust the waveform transmission timing of the unmanned aerial vehicle, and a composite jamming signal is formed, specifically,

[0028] Each unmanned aerial vehicle exchanges local clock data based on the clock synchronization protocol based on the consistency algorithm, and calculates the average value of the clock deviation;

[0029] Each unmanned aerial vehicle adjusts its carrier frequency, pulse width and phase parameters according to the average value of the clock deviation, so that the radio frequency signals of each unmanned aerial vehicle form a non-uniformly distributed composite jamming signal in time domain and frequency domain.

[0030] As a preferred scheme of the multi-mode unmanned aerial vehicle cooperative jamming control method, the real-time jamming effectiveness value of the unmanned aerial vehicle is used to elect a coordination node, and the radio frequency signal data and the multi-modal jamming instruction set are fused into the elected coordination node to obtain a jamming scheme, specifically,

[0031] The unmanned aerial vehicle with the highest current jamming effectiveness value is selected as the coordination node through comparison operation, and the radio frequency signal data collected by each unmanned aerial vehicle and the multi-modal jamming instruction set are transmitted to the coordination node;

[0032] The radio frequency signal data of each unmanned aerial vehicle is subjected to spectrum feature extraction and threat level evaluation by using the coordination node, and the multi-modal jamming instruction set is combined to optimize the jamming strategy, and a jamming scheme is generated.

[0033] As a preferred scheme of the multi-mode unmanned aerial vehicle cooperative jamming control method, the game algorithm is used to optimize the transmission power and frequency band selection of each unmanned aerial vehicle, and the optimal jamming parameters of each unmanned aerial vehicle are generated, specifically,

[0034] Based on the non-cooperative game theory, a power-frequency optimization model is constructed, each unmanned aerial vehicle (UAV) transmission power and frequency band selection is defined as a game strategy, and an utility function is established, and an optimal solution is found through an iterative Nash equilibrium algorithm, in each iteration, each UAV updates its strategy according to the current interference scenario, and receives the strategy information of other UAVs, after multiple rounds of iteration, the optimal interference parameters of each UAV are obtained.

[0035] As a preferred scheme of the multi-mode UAV cooperative jamming control method, wherein: according to the composite jamming signal of each UAV, the optimal jamming parameter and the jamming scheme, the array antenna of all UAVs radiates the radio frequency jamming signal to the jamming target, specifically,

[0036] The composite jamming signal of each UAV is input into a digital upconverter as a baseband signal, and carrier modulation is performed according to the center frequency and bandwidth specified in the optimal jamming parameter to generate the radio frequency jamming signal of each UAV,

[0037] According to the direction information of the jamming target specified in the jamming scheme, the phase distribution of the array antenna of each UAV is adjusted to make the main lobe of the beam point to the direction of the jamming target, and the sidelobe radiation in the non-target direction is suppressed by using the adaptive nulling method, finally, the radio frequency jamming signal of each UAV is fed into the array antenna through the power amplifier, and the radio frequency jamming signal is radiated to the jamming target.

[0038] In the second aspect, the present application provides a computer device, comprising a memory and a processor, the memory stores a computer program, wherein: the computer program is executed by the processor to realize any step of the multi-mode UAV cooperative jamming control method according to the first aspect of the present application.

[0039] In the third aspect, the present application provides a computer readable storage medium, which stores a computer program, wherein: the computer program is executed by the processor to realize any step of the multi-mode UAV cooperative jamming control method according to the first aspect of the present application.

[0040] The present application has the following advantages: by constructing the UAV jamming efficiency value based on the endurance, communication and load state, the dynamic quantitative evaluation of individual ability is realized, the interference mode is adaptively matched according to the UAV jamming efficiency value, the synergy of interference strategy and platform capability is improved, the multi-machine clock is calibrated through the consistency algorithm and the non-uniformly distributed composite jamming signal is generated, the unpredictability and anti-countermeasure ability of the jamming signal in the time-frequency domain are enhanced, and further, the game algorithm is introduced to optimize the transmission power and frequency band selection of each UAV, the Nash equilibrium of resource utilization and jamming efficiency is realized in a distributed environment, and overall, a closed-loop control mechanism of "ability perception-mode matching-time sequence cooperation-resource game" is formed, the cooperative jamming capability, intelligent level and stability of the multi-UAV are improved. Attached Figure Description

[0041] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Fig. 1 This is a flowchart of a multi-mode UAV cooperative interference control method.

[0043] Fig. 2 A flowchart for generating interference energy efficiency values.

[0044] Fig. 3 This is a flowchart for generating composite interference signals.

[0045] Fig. 4 A flowchart for generating optimal interference parameters. Detailed Implementation

[0046] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0047] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0048] 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 phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0049] Reference Figs. 1-4 As one embodiment of the present invention, this embodiment provides a multi-mode unmanned aerial vehicle (UAV) cooperative interference control method, comprising the following steps:

[0050] S1. Collect radio frequency signal data of interfering targets in the airspace using radio frequency sensors carried by each UAV, input the radio frequency signal data into the SVM model, and obtain the interference waveform parameters.

[0051] Each drone is equipped with a radio frequency sensor to collect radio frequency signals from interfering targets in the airspace in real time and obtain radio frequency signal data.

[0052] It should be explained that after the unmanned aerial vehicle carrying the radio frequency sensor is launched, it cruises in the designated airspace, and when the radio frequency sensor carried by the unmanned aerial vehicle finds the interference target in the designated airspace, the radio frequency sensor carried by the unmanned aerial vehicle immediately locks the target direction of the interference target, and collects the radio frequency signals emitted by the interference target through a wideband receiving channel, and records the spectrum, modulation pattern and time domain characteristics of the radio frequency signals in real time. During the collection process, the radio frequency sensor of the unmanned aerial vehicle automatically adjusts the gain and filter parameters to ensure the quality of the radio frequency signals. The spectrum, modulation pattern and time domain characteristics of the radio frequency signals are packaged together and transmitted back to the ground station through the data link for analysis and storage, forming radio frequency signal data.

[0053] The radio frequency signal data is input into the SVM model, and by analyzing the spectrum characteristics, time domain characteristics and modulation pattern characteristics in the radio frequency signal data, the interference waveform parameters are obtained.

[0054] Further, typical interference modes and corresponding parameters such as aiming interference, wideband jamming, suppression interference and smart interference are collected and stored in a structured medium to form an interference strategy library.

[0055] The historical radio frequency signal data is collected and divided into a training set and a test set, the training set is input into the SVM model for training, the grid search method is used to optimize the kernel function parameters and penalty coefficients of the SVM model, and the classification performance is evaluated through cross-validation. After training, the generalization ability of the SVM model is verified using the test set, and the trained SVM model is obtained.

[0056] After the radio frequency signal data is standardized, the power spectral density and frequency occupation degree of the spectrum, the pulse width and repetition period of the time domain characteristics, and the modulation type and symbol rate of the modulation pattern in the radio frequency signal data are extracted, and combined into a feature vector. The feature vector is input into the trained SVM model for classification calculation, and the SVM model matches the feature vector according to the decision boundary learned in the training process, and outputs the interference mode corresponding to the radio frequency signal data; according to the interference mode corresponding to the radio frequency signal data, the interference strategy library is queried to obtain the interference waveform parameters, including the suppression interference waveform parameters, the aiming interference waveform parameters and the smart noise interference waveform parameters.

[0057] S2, according to the remaining endurance time, communication link quality and load state of the unmanned aerial vehicle, the interference efficiency value of the unmanned aerial vehicle is calculated;

[0058] It should be explained that the current remaining endurance time and the maximum endurance time of the unmanned aerial vehicle are collected, the current remaining endurance time is compared with the maximum endurance time to obtain an initial ratio, then the initial ratio is linearly transformed to 0 to 1 by using the minimum-maximum normalization method, and if the initial ratio is already in the range of 0 to 1, it remains unchanged; finally, the normalized initial ratio is used as the endurance coefficient.

[0059] The signal-to-noise ratio and bit error rate of the communication link quality of the unmanned aerial vehicle are measured, and the communication quality coefficient is converted through the Sigmoid function;

[0060] It should be noted that the signal-to-noise ratio and bit error rate data of the communication link quality of the unmanned aerial vehicle are collected in real time by the radio frequency receiver, and the signal-to-noise ratio and bit error rate are linearly normalized to make them in the same order of magnitude range; The normalized signal-to-noise ratio and bit error rate are input into the Sigmoid function for nonlinear transformation, wherein the signal-to-noise ratio is mapped by the forward Sigmoid function, and the bit error rate is mapped by the reverse Sigmoid function. The weighted sum of the forward Sigmoid function and the reverse Sigmoid function output results is obtained, and the communication quality coefficient with a value range of zero to one is obtained.

[0061] The interference power amplifier efficiency and the antenna gain in the load state of the unmanned aerial vehicle are evaluated to generate the load performance coefficient;

[0062] It should be noted that the input direct current power and output radio frequency power of the interference power amplifier of the unmanned aerial vehicle are monitored, and the interference power amplifier efficiency is calculated, which is expressed by the formula:

[0063]

[0064] Wherein, d represents the interference power amplifier efficiency, Δ represents the output radio frequency power, and i represents the input direct current power;

[0065] The gain characteristics of the current unmanned aerial vehicle antenna (including the main lobe gain and sidelobe suppression ratio measured value) are collected; The product of the interference power amplifier efficiency and the main lobe gain of the unmanned aerial vehicle antenna is obtained to obtain the load performance index, and the load performance index is nonlinearly transformed and compressed to the interval of 0 to 1; The sidelobe suppression ratio measured value of the unmanned aerial vehicle antenna is normalized according to the maximum sidelobe level to generate the sidelobe suppression ratio correction weight, which is expressed by the formula:

[0066]

[0067] Wherein, w represents the sidelobe suppression ratio correction weight, L represents the absolute value of the maximum sidelobe level, and S represents the sidelobe suppression ratio measured value.

[0068] Based on the load performance index in the interval of zero to one and the sidelobe suppression ratio correction weight, the load performance coefficient is calculated by combining the clipping function, which is expressed by the formula:

[0069] C=min(1,max(0,I×(1+α·w)));

[0070] Wherein, C represents the load performance coefficient, I represents the load performance index in the interval of zero to one, α represents the sidelobe suppression adjustment factor (typical value 0.1-0.3), and w represents the sidelobe suppression ratio correction weight.

[0071] The endurance coefficient, the communication quality coefficient and the load performance coefficient are weighted and summed to obtain an interference performance value of the UAV;

[0072] Further, the endurance coefficient, the communication quality coefficient and the load performance coefficient are respectively multiplied by corresponding weights to obtain weighted endurance coefficient, communication quality coefficient and load performance coefficient, wherein the endurance coefficient reflects the criticality of endurance time to the interference task, the weight is set to 0.5; the communication quality coefficient reflects the importance of link stability to cooperative interference, the weight is set to 0.3; the load performance coefficient represents the contribution of hardware performance to interference effect, the weight is set to 0.2; the weighted endurance coefficient, the communication quality coefficient and the load performance coefficient are arithmetically summed to obtain an initial interference performance value; the initial interference performance value is nonlinearly mapped using a Sigmoid function to eliminate the dimensional difference under different working conditions, and finally the UAV interference performance value with a value range of zero to one hundred is output.

[0073] S3, using the interference performance value of the UAV to dynamically select interference waveform parameters to obtain a multi-modal interference instruction set;

[0074] Based on the interference performance value of the UAV, N interference mode intervals are divided, and each interference mode interval corresponds to suppression type interference waveform parameters, aiming type interference waveform parameters and smart noise interference waveform parameters in turn;

[0075] It should be noted that based on the interference performance value of the UAV, the numerical range of zero to one hundred is divided into N continuous interference mode intervals, wherein the first interference mode interval (80-100 points) corresponds to suppression type interference waveform parameters, the second interference mode interval (50-79 points) corresponds to aiming type interference waveform parameters, and the third interference mode interval (0-49 points) corresponds to smart noise interference waveform parameters.

[0076] The interference performance value of the UAV is mapped to the interference mode interval, the corresponding interference waveform parameters are extracted, the corresponding interference waveform parameters are matched with the scene where the interference target is located, and a multi-modal interference instruction set is obtained;

[0077] Further, based on the interference effectiveness value of the unmanned aerial vehicle, the interference effectiveness value is matched with the preset interference mode interval through an interval mapping algorithm, and the corresponding interference waveform parameters are extracted; the extracted interference waveform parameters are input into a scene adaptation algorithm. The scene adaptation algorithm first analyzes the spectral distribution characteristics of the interference target radio frequency signal, identifies the center frequency and bandwidth of the interference target radio frequency signal, and then detects the channel occupation state to determine the available frequency band and the interference window; based on the center frequency, bandwidth, channel occupation state and receiver sensitivity of the interference target radio frequency signal, the scene adaptation algorithm dynamically adjusts the center frequency in the interference waveform parameters, so that the center frequency in the interference waveform parameters is aligned with the center frequency of the interference target radio frequency signal, and the instantaneous bandwidth in the interference waveform parameters is recalculated according to the bandwidth and channel occupation state of the interference target radio frequency signal; the transmission power level in the interference waveform parameters is corrected with reference to the receiver sensitivity AZ and path loss value of the interference target; and finally the optimized interference waveform parameters are output. The transmission power level in the interference waveform parameters is corrected by the formula:

[0078]

[0079] Q=D+P+m;

[0080] Wherein, P represents the path loss value, π represents the circular constant, t represents the distance between the unmanned aerial vehicle and the interference target, λ represents the wavelength of the radio frequency signal of the unmanned aerial vehicle, Q represents the transmission power level, D represents the receiver sensitivity, and m represents the interference margin of the interference mode.

[0081] The optimized interference waveform parameters are matched and verified with the strategies in the interference strategy library using a multi-modal fusion engine to generate a multi-modal interference instruction set, including a suppression type interference instruction, a targeting type interference instruction and a smart noise interference instruction.

[0082] S4, the clock calibration protocol based on the consistency algorithm is used to dynamically adjust the waveform transmission timing of the unmanned aerial vehicle to form a composite interference signal;

[0083] Each unmanned aerial vehicle exchanges local clock data through the clock calibration protocol based on the consistency algorithm, and calculates the clock bias average value;

[0084] It should be noted that after each unmanned aerial vehicle establishes a communication connection through the clock calibration protocol based on the consistency algorithm, each unmanned aerial vehicle broadcasts clock data including local timestamp and clock accuracy through the communication connection; after the adjacent unmanned aerial vehicle receives the clock data, a distributed weighted average consistency algorithm is used to calculate the clock bias average value, which is expressed by the formula:

[0085]

[0086] δ=∑ j∈V K·o j ;

[0087] wherein K represents a weight coefficient in distributed clock synchronization, σ represents a standard deviation, j represents an index symbol of a neighboring UAV, and V represents a set of neighboring UAVs in direct communication with the current UAV; represents a clock variance of the neighboring UAV j, e represents a base of a natural logarithm, δ represents a clock bias average of the UAV, and o represents a clock bias;

[0088] Each UAV adjusts its carrier frequency, pulse width and phase parameters according to the clock bias average, so that the radio frequency signals of each UAV form a non-uniformly distributed composite jamming signal in the time domain and the frequency domain;

[0089] Further, the carrier frequency, pulse width and phase parameters of the UAV are dynamically adjusted according to the clock bias average. Specifically, the carrier frequency is superimposed with an offset proportional to the clock bias average on the basis of the reference frequency, the pulse width is scaled by the clock bias average, and the phase parameter is periodically compensated according to the clock bias average. The adjusted carrier frequency, pulse width and phase parameter jointly act on the radio frequency transmission link of the UAV, forming a radio frequency signal with non-uniform time domain characteristics, and the radio frequency signals of each UAV form a composite jamming signal with asynchronous jumping in the time domain and discrete distribution in the frequency domain after spatial superposition.

[0090] S5, electing a coordination node according to the real-time jamming effectiveness value of the UAV, fusing the radio frequency signal data and the multi-modal jamming instruction set into the elected coordination node, and obtaining a jamming scheme;

[0091] The current UAV with the highest jamming effectiveness value is selected as the coordination node through a comparison operation, and the radio frequency signal data collected by each UAV and the multi-modal jamming instruction set are transmitted to the coordination node;

[0092] It should be noted that based on the jamming effectiveness value of each UAV, the UAV node with the highest jamming effectiveness value is selected through a distributed comparison operation; the selected coordination node receives the radio frequency signal data sent by other UAVs through a wireless data link, and simultaneously receives the multi-modal jamming instruction set.

[0093] The radio frequency signal data of each UAV is subjected to spectral feature extraction and threat level assessment using the coordination node, and simultaneously subjected to jamming strategy optimization in combination with the multi-modal jamming instruction set, to generate a jamming scheme;

[0094] Further, the coordination node first collects the radio frequency signal data of each UAV, and performs spectral feature extraction through fast Fourier transform to obtain spectral amplitude, frequency occupation degree and instantaneous bandwidth.

[0095] Based on the spectrum amplitude, frequency occupation and instantaneous bandwidth of the unmanned aerial vehicle, a threat level evaluation model is constructed, which is composed of a multi-scale convolutional neural network and a long short-term memory network; wherein the multi-scale convolutional neural network is responsible for extracting the local time-frequency mode of the spectrum feature of the radio frequency signal, and the long short-term memory network captures the time dynamic characteristics of the spectrum feature.

[0096] After recovering the radio frequency signal data collected by the unmanned aerial vehicle and labeling it with high, medium and low threat labels, the data is divided into a training set and a validation set; the training set is input into the threat level evaluation model for training; during the training process, the focal loss function is applied to solve the class imbalance problem; the learning rate is adjusted by the Adam optimizer combined with the cosine annealing strategy; Dropout and L2 regularization are combined to prevent overfitting. Finally, after the validation set reaches stable performance, the trained threat level evaluation model is saved;

[0097] The spectrum amplitude, frequency occupation and instantaneous bandwidth of each unmanned aerial vehicle extracted by the coordination node are input into the threat level evaluation model; the input layer of the threat level evaluation model receives the time series data of the spectrum amplitude, frequency occupation and instantaneous bandwidth; after passing through a feature encoder composed of three layers of dilated convolution kernel and max pooling layer, the time series features extracted by the bidirectional long short-term memory network are channel spliced; finally, the threat level is output through the full connection layer and the Softmax activation function.

[0098] Based on the threat level of each unmanned aerial vehicle and the multi-modal jamming instruction set, a genetic algorithm is used to optimize the jamming strategy; specifically, first, initialize the population, and encode the suppression jamming instruction, aiming jamming instruction and smart noise jamming instruction into chromosomes; set the fitness function according to the threat level of the unmanned aerial vehicle, and comprehensively consider the jamming effectiveness, energy efficiency and spectrum compliance; through selection, crossover and mutation operations, the population is iteratively optimized, and the individual with the highest fitness score is retained; after multiple rounds of iterative optimization, the optimal chromosome is decoded to obtain the jamming scheme.

[0099] S6, adopt game algorithm to optimize the transmission power and frequency band selection of each unmanned aerial vehicle, and generate the optimal jamming parameters of each unmanned aerial vehicle;

[0100] Based on the non-cooperative game theory, a power-frequency optimization model is constructed; the core function of the power-frequency optimization model is to realize the optimal allocation of jamming resources of the unmanned aerial vehicle group in complex electromagnetic environment through mathematical modeling and distributed decision-making.

[0101] According to the power-frequency optimization model, the transmission power level and center frequency band selection of each unmanned aerial vehicle are encoded into the current game strategy vector; through the non-cooperative game framework, an utility function is constructed, which comprehensively considers the signal-to-interference-and-noise ratio gain, energy efficiency and spectrum utilization; wherein the utility function is expressed by the formula:

[0102] U = H · M + β · η + γ · G;

[0103] wherein, U represents the utility function value, M represents the signal-to-interference ratio, H represents the signal-to-interference ratio weight coefficient, η represents the energy efficiency, β represents the energy efficiency weight coefficient, G represents the spectrum utilization rate, and γ represents the spectrum utilization rate weight coefficient;

[0104] wherein, the signal-to-interference ratio gain is the core index for measuring the interference suppression effect.

[0105] An iterative Nash equilibrium solving algorithm is adopted. In each iteration period, each UAV calculates the utility function value under the current game strategy vector according to the real-time perceived interference target signal power spectral density, channel occupation matrix and path loss value, and uses the gradient ascent method to update the current game strategy vector to improve the utility function value. After updating, the game strategy vector broadcast by the adjacent UAV is received, and the utility function in the interactive environment is re-evaluated. After a plurality of times of strategy optimization, the iterative Nash equilibrium solving algorithm converges to the Nash equilibrium point. At this time, the game strategy vector of each UAV makes the utility function reach the local optimum, and finally the optimal interference parameters of each UAV, including the center frequency, bandwidth parameter and transmission power level, are obtained.

[0106] S7, according to the composite interference signal of each UAV, the optimal interference parameter and the interference scheme, controlling the array antenna of all UAVs to radiate the radio frequency interference signal to the interference target;

[0107] The composite interference signal of each UAV is input into the digital upconverter as a baseband signal, and carrier modulation is performed according to the center frequency and bandwidth specified in the optimal interference parameter to generate the radio frequency interference signal of each UAV;

[0108] It should be noted that each UAV inputs the composite interference signal into the digital upconverter as a baseband signal, and the digital upconverter generates a quadrature carrier signal according to the center frequency in the optimal interference parameter. The digital mixer synthesizes the baseband signal and the quadrature carrier signal to form a digital signal. The digital filter sets the passband range according to the bandwidth parameter in the optimal interference parameter, suppresses the spurious components outside the digital signal, and then the digital-to-analog converter converts the digital signal into an analog radio frequency signal at a sampling rate of no less than twice the bandwidth. The power amplifier linearly amplifies the analog radio frequency signal according to the transmission power level in the optimal interference parameter, and the bandpass filter further filters out the harmonic and spurious components, and outputs the radio frequency interference signal.

[0109] According to the direction information of the interference target specified in the interference scheme, the phase distribution of the array antenna of each UAV is adjusted so that the main lobe of the beam is aligned in the direction of the interference target, and the adaptive nulling method is used to suppress the sidelobe radiation in the non-target direction. Finally, the radio frequency interference signal of each UAV is fed into the array antenna through the power amplifier, and the radio frequency interference signal is radiated to the interference target;

[0110] Further, each unmanned aerial vehicle calculates the phase compensation value of the array antenna according to the interference target direction information specified in the interference scheme through a beamforming algorithm, so that the main lobe of the beam is accurately aligned with the direction of the interference target, which is expressed by the formula:

[0111]

[0112] Wherein, φ represents the phase compensation value of the unmanned aerial vehicle array antenna, λ represents the wavelength of the radio frequency signal of the unmanned aerial vehicle, f represents the distance between the unmanned aerial vehicle array antennas, b represents the index of the unmanned aerial vehicle array antenna, and θ represents the azimuth angle of the interference target relative to the normal direction of the unmanned aerial vehicle array antenna.

[0113] An adaptive nulling algorithm is used to calculate the complex weighting coefficient for suppressing radiation in non-target directions. Specifically, first, the statistical characteristics of the interference and noise are estimated according to the signal data received by the unmanned aerial vehicle array antenna to form an interference and noise covariance matrix. Then, a constraint matrix including the spatial response of the target direction and the non-target direction is constructed, wherein the gain corresponding to the target direction is set to 1 and the gain corresponding to the non-target direction is set to 0. The complex weighting coefficient is calculated according to the interference and noise covariance matrix and the constraint matrix, which is expressed by the formula:

[0114] Y = R -1 E(E l R -1 E) -1 J;

[0115] Wherein, Y represents the complex weighting coefficient, R represents the interference and noise covariance matrix, E represents the constraint matrix, J represents the expected response vector [1, 0], E l represents the conjugate transpose of the constraint matrix, and l represents the conjugate transpose.

[0116] The digital beamformer adjusts the amplitude and phase response of the unmanned aerial vehicle array antenna according to the phase compensation value and the complex weighting coefficient, and the power amplifier amplifies the radio frequency interference signal to the power level specified in the interference scheme and feeds it into the unmanned aerial vehicle array antenna. Finally, the array antenna of each unmanned aerial vehicle radiates a radio frequency interference signal to the interference target.

[0117] The embodiment also provides a computer device suitable for the multi-mode unmanned aerial vehicle cooperative interference control method, which comprises a memory and a processor. The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to realize the multi-mode unmanned aerial vehicle cooperative interference control method proposed in the above embodiment.

[0118] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected by a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved by WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0119] The embodiment also provides a storage medium having a computer program stored thereon, the program being executed by a processor to implement the multi-mode UAV cooperative jamming control method proposed in the above embodiment; and the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage, a flash memory, a magnetic disk or an optical disk.

[0120] To sum up, the present application realizes dynamic quantitative evaluation of individual capability by constructing a UAV jamming effectiveness value based on endurance, communication and load state, improves the synergy of jamming strategy and platform capability by adaptively matching the jamming mode according to the UAV jamming effectiveness value, enhances the unpredictability and anti-countermeasure capability of the jamming signal in the time-frequency domain by realizing multi-UAV clock calibration and generating a non-uniformly distributed composite jamming signal through a consensus algorithm, and further introduces a game algorithm to optimize the transmission power and frequency band selection of each UAV, so as to realize Nash equilibrium of resource utilization and jamming effectiveness in a distributed environment. Overall, a closed-loop control mechanism of "capability awareness-mode matching-time sequence synergy-resource game" is formed, and the cooperative jamming capability, intelligent level and stability of the multi-UAV are improved.

[0121] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not to limit the present application. Although the present application 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 application can be modified or equivalently replaced without departing from the spirit and scope of the present application, and all modifications and equivalents should be included in the scope of the claims of the present application.

Claims

1. A multi-mode UAV cooperative interference control method, characterized in that: include, By using the radio frequency sensors carried by each UAV, radio frequency signal data of interfering targets in the airspace are collected, and the radio frequency signal data is input into the SVM model to obtain the interference waveform parameters. Calculate the interference effectiveness value of the UAV based on its remaining flight time, communication link quality, and payload status. Dynamically select interference waveform parameters using the interference effectiveness value of the UAV to obtain a multi-mode interference command set; A clock calibration protocol based on a consensus algorithm is used to dynamically adjust the transmission timing of the UAV waveform, thereby generating a composite interference signal. Based on the real-time jamming effectiveness value of the UAV, a coordination node is selected, and radio frequency signal data and multi-mode jamming command set are integrated into the selected coordination node to obtain the jamming scheme. A game theory algorithm is used to optimize the transmission power and frequency band selection of each UAV, generating the optimal interference parameters for each UAV. Based on the composite interference signals of each UAV, the optimal interference parameters, and the interference scheme, control the array antennas of all UAVs to radiate radio frequency interference signals toward the interference target.

2. The multi-mode UAV cooperative interference control method as described in claim 1, characterized in that: The process involves using radio frequency sensors mounted on each UAV to collect radio frequency signal data of interfering targets in the airspace, inputting the radio frequency signal data into an SVM model to obtain interference waveform parameters. Specifically, Each drone is equipped with a radio frequency sensor to collect radio frequency signals from interfering targets in the airspace in real time and obtain radio frequency signal data. Radio frequency signal data is input into the SVM model, and interference waveform parameters are obtained by analyzing the spectral characteristics, time domain characteristics and modulation pattern characteristics in the radio frequency signal data. The interference waveform parameters include suppression interference waveform parameters, aiming interference waveform parameters, and agile noise interference waveform parameters.

3. The multi-mode UAV cooperative interference control method as described in claim 2, characterized in that: The method involves calculating the interference effectiveness value of the UAV based on its remaining flight time, communication link quality, and payload status. The remaining flight time of the drone is normalized to obtain the flight time coefficient; The signal-to-noise ratio and bit error rate of the communication link quality of the UAV are measured and converted into communication quality coefficients using the Sigmoid function; Evaluate the efficiency of the interference power amplifier and the antenna gain in the UAV payload state, and generate the payload efficiency coefficient; The interference effectiveness value of the UAV is obtained by weighted summation of the endurance coefficient, communication quality coefficient, and payload effectiveness coefficient.

4. The multi-mode UAV cooperative interference control method as described in claim 3, characterized in that: The method of dynamically selecting interference waveform parameters using the interference effectiveness value of the UAV and obtaining a multi-mode interference command set specifically involves: Based on the interference effectiveness value of the UAV, N interference mode intervals are divided, and each interference mode interval corresponds to the suppression interference waveform parameters, the aiming interference waveform parameters, and the agile noise interference waveform parameters in sequence. The interference effectiveness value of the UAV is mapped to the interference mode range, the corresponding interference waveform parameters are extracted, and the corresponding interference waveform parameters are matched with the scene where the interference target is located to obtain the multi-modal interference command set.

5. The multi-mode UAV cooperative interference control method as described in claim 4, characterized in that: The method employs a clock calibration protocol based on a consensus algorithm to dynamically adjust the UAV waveform transmission timing, thereby generating a composite interference signal. Specifically, After each UAV exchanges local clock data through a clock calibration protocol based on a consensus algorithm, the average clock deviation is calculated. Each drone adjusts its own carrier frequency, pulse width, and phase parameters based on the average clock deviation, so that the radio frequency signal of each drone forms a non-uniformly distributed composite interference signal in the time and frequency domains.

6. The multi-mode UAV cooperative interference control method as described in claim 5, characterized in that: The process involves selecting a coordination node based on the real-time jamming effectiveness value of the UAV, fusing radio frequency signal data and multi-mode jamming command sets into the selected coordination node, and obtaining an jamming scheme. Specifically, By comparing and calculating, the drone with the highest current interference effectiveness value is selected as the coordination node, and the radio frequency signal data and multi-mode interference command set collected by each drone are transmitted to the coordination node. The coordination node is used to extract spectral features and assess the threat level of radio frequency signal data from each UAV. At the same time, the interference strategy is optimized by combining the multi-modal interference instruction set to generate an interference scheme.

7. The multi-mode UAV cooperative interference control method as described in claim 6, characterized in that: The game theory algorithm is used to optimize the transmission power and frequency band selection of each UAV, generating the optimal interference parameters for each UAV. Specifically, A power-frequency band optimization model is constructed based on non-cooperative game theory. The transmit power and frequency band selection of each UAV are defined as game strategies, and a utility function is established. The optimal solution is found by an iterative Nash equilibrium solution algorithm. In each iteration, each UAV updates its own strategy according to the current interference scenario and receives strategy information from other UAVs. After multiple rounds of iteration and convergence, the optimal interference parameters of each UAV are obtained.

8. The multi-mode UAV cooperative interference control method as described in claim 7, characterized in that: The process involves controlling the array antennas of all UAVs to radiate radio frequency interference signals toward the target based on the composite interference signals, optimal interference parameters, and interference scheme of each UAV. The composite interference signals of each UAV are input as baseband signals into the digital upconverter, and carrier modulation is performed according to the center frequency and bandwidth specified in the optimal interference parameters to generate radio frequency interference signals for each UAV. Based on the target azimuth information specified in the jamming scheme, the phase distribution of the array antennas of each UAV is adjusted so that the main lobe of the beam is aligned with the direction of the jamming target. At the same time, an adaptive null method is used to suppress sidelobe radiation in non-target directions. Finally, the radio frequency jamming signals of each UAV are fed into the array antenna through a power amplifier and the radio frequency jamming signals are radiated toward the jamming target.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the multi-mode UAV cooperative interference control method according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the multi-mode UAV cooperative interference control method according to any one of claims 1 to 8.

Images