A multi-band UAV signal jamming system

Abstract

This invention relates to the field of signal processing technology and discloses a multi-band UAV signal jamming system. The system includes modules for signal acquisition, frequency band analysis, jamming generation, signal modulation, and integrated control. The signal acquisition module collects various types of signals from the UAV, the frequency band analysis module precisely analyzes these signals, the jamming generation module adaptively generates jamming signals, the signal modulation module optimizes modulation, and the integrated control module regulates transmission and jamming effects in real time. This system can comprehensively acquire signals, deeply analyze frequency band characteristics, adaptively generate jamming signals and optimize modulation, and monitor and adjust the jamming effect in real time, significantly improving the accuracy, targeting, and persistence of jamming, effectively addressing the challenges of UAV supervision. Compared to traditional jamming technologies, it overcomes the limitations of single-band jamming and weak signal analysis and processing capabilities, possesses good versatility and scalability, is suitable for various scenarios, and provides reliable technical support for UAV management.

Description

Technical Field

[0001] This invention relates to the field of signal processing technology, specifically to a multi-band unmanned aerial vehicle (UAV) signal jamming system. Background Technology

[0002] In recent years, drone technology has developed rapidly, and its application areas have continued to expand, playing an important role in many scenarios such as aerial photography, agricultural plant protection, logistics distribution, and power line inspection. However, the widespread use of drones has also brought a series of safety and regulatory issues, such as unauthorized entry into sensitive areas, disruption of normal aviation order, and infringement of others' privacy. Therefore, effectively jamming drone signals to control their flight has become crucial.

[0003] In the early days, jamming techniques for drones were relatively simple. Some simple jamming devices could only operate on a single frequency band, and the jamming method was limited, mostly involving the emission of noise signals at a fixed frequency. However, this method had many limitations. With the continuous evolution of drone communication technology, modern drones often support multiple frequency bands. Single-band jamming devices cannot comprehensively jam multi-band drones. Once the drone switches to an unjammed frequency band, the jamming device becomes ineffective.

[0004] Traditional jamming systems are also relatively weak in signal acquisition and analysis capabilities. They can typically only collect limited signal features, making it difficult to obtain comprehensive information about UAV signals. For example, they cannot accurately obtain signal phase data and lack effective utilization of historical jamming records. In frequency band analysis, they often use simple filtering and frequency band division methods, which cannot deeply extract signal features, accurately identify the UAV's communication frequency band and the signal characteristics of each band, resulting in untargeted jamming and low efficiency.

[0005] Traditional techniques also have shortcomings in jamming signal generation and modulation. Early jamming generation models lacked adaptability and could not adjust jamming strategies according to real-time changes in UAV signals. In the signal modulation stage, the modulation method was fixed and could not be optimized by combining frequency band analysis results and jamming signal characteristics, making it difficult for jamming signals to effectively affect the UAV communication link and reliably control the UAV's flight.

[0006] Traditional jamming systems also have significant shortcomings in interference control and effectiveness evaluation. When transmitting jamming signals, they cannot flexibly adjust transmission power and frequency, making it difficult to adapt to different jamming scenarios and the characteristics of target drones. The evaluation of jamming effects often relies on human experience or simple indicator judgments, lacking comprehensive, real-time monitoring and quantitative assessment. It is impossible to adjust jamming parameters promptly based on the jamming effect, making it difficult to ensure the continuity and stability of the jamming. With the continuous innovation of drone technology, its communication frequency bands are constantly expanding and communication protocols are becoming increasingly complex, placing higher demands on drone signal jamming technology. Existing jamming technologies are insufficient to meet practical application needs, urgently requiring a multi-band drone signal jamming system capable of acquiring multi-band signals, accurately analyzing frequency band characteristics, adaptively generating jamming signals, and optimizing jamming effects in real time to address the increasingly severe challenges of drone regulation. Summary of the Invention

[0007] The purpose of this invention is to provide a multi-band UAV signal jamming system to solve the problems mentioned in the background art.

[0008] To achieve the above objectives, the present invention provides the following technical solution: a multi-band unmanned aerial vehicle (UAV) signal jamming system, the system comprising:

[0009] It includes a signal acquisition module, a frequency band analysis module, an interference generation module, a signal modulation module, and a comprehensive control module;

[0010] The signal acquisition module is used to acquire UAV signals, specifically by deploying a multi-band antenna array and acquiring signals to obtain raw UAV signal data, and then sending the raw UAV signal data to the frequency band analysis module.

[0011] The frequency band analysis module is used to perform frequency band analysis and feature extraction on the original signal. Specifically, it obtains frequency band analysis data by sequentially performing signal filtering and frequency band segmentation on the original UAV signal data, and sends the frequency band analysis data to the interference generation module and the signal modulation module. The specific steps include: signal filtering, frequency band segmentation, frequency band feature extraction and frequency band comprehensive processing.

[0012] The interference generation module is used to generate interference signals for different frequency bands. Specifically, based on the frequency band analysis data, it uses an interference generation model based on multi-band adaptive noise injection to generate interference signals and sends the interference signals to the signal modulation module.

[0013] The interference generation model based on multi-band adaptive noise injection specifically includes a frequency band noise injection operator, a frequency band interference optimization operator, a multi-band interference sub-model, a frequency band classification sub-model, and a parameter optimization operator;

[0014] The signal modulation module is used to modulate and optimize the interference signal. Specifically, based on the frequency band analysis data and the interference signal, it uses a frequency band modulation-based signal optimization model to perform signal modulation, obtain a modulated interference signal, and send the modulated interference signal to the integrated control module.

[0015] The integrated control module is used to comprehensively control the transmission and adjustment of the interference signal. Specifically, it controls the multi-band antenna array to transmit the modulated interference signal and monitors and adjusts the interference effect in real time.

[0016] Preferably, in the signal acquisition module, the raw UAV signal data specifically includes signal strength data, signal frequency data, signal phase data, and historical interference record data; the historical interference record data specifically includes historical interference frequency band data, historical interference effect data, and historical interference adjustment data.

[0017] Preferably, in the frequency band analysis module, the step of generating interference signals using an interference generation model based on multi-band adaptive noise injection includes: constructing a frequency band noise injection operator, constructing a frequency band interference optimization operator, constructing a multi-band interference sub-model, constructing a frequency band classification sub-model, constructing a parameter optimization operator, training the interference generation model, and generating interference signals.

[0018] The constructed frequency band noise injection operator is used to optimize the frequency band features in the frequency band analysis data and reduce the interference of noise on signal quality. Specifically, it adopts an adaptive noise injection algorithm to perform adaptive noise injection on the frequency band analysis data.

[0019] The construction of the frequency band interference optimization operator specifically involves extracting frequency band interference optimization from the frequency band feature data to obtain frequency band interference feature data, and calculating the standard deviation and mean of the frequency band interference feature data to obtain an optimized frequency band interference feature dataset.

[0020] The construction of the multi-band interference sub-model specifically involves constructing a standard multi-band interference neural network and performing in-depth extraction of frequency band features based on the acquisition frequency to obtain frequency band interference status output data.

[0021] The construction of the frequency band classification sub-model specifically involves training the classifier of the standard frequency band classification model based on the optimized frequency band interference feature dataset corresponding to different sampling frequencies, and classifying the frequency band type by using the frequency band interference state output data as the total input of the trained frequency band classification sub-model to obtain the frequency band classification output data.

[0022] The construction of the parameter optimization operator specifically involves using a tree-oriented Bayesian optimization algorithm to optimize the model parameters, obtaining an optimized combination of model hyperparameters, and applying the optimized combination of model hyperparameters to the training of the interference generation model.

[0023] The interference generation model training specifically involves training the interference generation model ModelG using the frequency band noise injection operator, the frequency band interference optimization operator, the multi-frequency band interference sub-model, the frequency band classification sub-model, and the parameter optimization operator.

[0024] The interference signal generation specifically involves using the interference generation model ModelG to generate the interference signal based on the frequency band analysis data.

[0025] Preferably, the frequency band classification output data specifically includes frequency band type reference data, frequency band strength reference data, and frequency band interference effect reference data;

[0026] The frequency band type reference data is used to indicate identifiable frequency band categories, specifically including low frequency band, mid frequency band, and high frequency band;

[0027] The frequency band strength reference data is used to represent the strength quantization value of the frequency band signal, and the value range is [0, 100%];

[0028] The frequency band interference effect reference data is used to provide a quantitative assessment of the frequency band interference effect, specifically including interference success rate, interference duration, and interference impact range.

[0029] Preferably, in the signal modulation module, a signal optimization model based on frequency band modulation is used to perform signal modulation to obtain a modulated interference signal. The specific steps include: signal integration, frequency band coding optimization, construction of modulation model, construction of optimization model, signal modulation model training, and modulation signal generation.

[0030] Preferably, the signal integration specifically involves integrating the frequency band analysis data and the interference signal to obtain an integrated modulation dataset, and performing signal cleaning operations on the integrated modulation dataset to obtain an integrated modulation optimization dataset.

[0031] The frequency band coding optimization specifically involves performing frequency band feature extraction operations from the integrated modulation optimization dataset to obtain a modulation feature dataset, and then performing one-hot coding on the frequency band features in the modulation feature dataset to obtain a coding feature matrix set.

[0032] The modulation feature dataset specifically includes frequency band type features, frequency band intensity features, historical modulation scheme features, modulation method features, and environmental condition auxiliary features;

[0033] The construction of the modulation model specifically involves using a modulation algorithm to perform frequency band modulation pre-classification training to obtain a frequency band modulation pre-classification recognition model.

[0034] The construction of the optimization model specifically involves using the frequency band modulation pre-classification and identification model to perform frequency band modulation pre-classification and identification based on the coding feature matrix set, obtaining frequency band modulation pre-identification data, and using a rule-based method to extract modulation schemes from the integrated modulation optimization dataset based on the frequency band modulation pre-identification data, obtaining a modulation scheme candidate list, and training the optimization model based on the modulation scheme candidate list to obtain a modulation effect prediction optimization model.

[0035] The modulation effect prediction optimization model is used to predict the effect based on the modulation scheme in the modulation scheme candidate list and obtain the modulation effect prediction output.

[0036] The signal modulation model training specifically involves training the signal modulation model through signal integration, frequency band coding optimization, construction of the modulation model, and construction of the optimization model to obtain the signal modulation model ModelSM.

[0037] The modulation signal generation specifically involves using the signal modulation model ModelSM to generate a modulation signal based on the frequency band analysis data and the interference signal, and then integrating the predicted output to obtain the modulation interference signal.

[0038] Preferably, the integrated control module is used to comprehensively control the transmission and adjustment of the interference signal. Specifically, it controls the transmission of the modulated interference signal by a multi-band antenna array and monitors and adjusts the interference effect in real time. The specific steps include: signal transmission control, interference effect monitoring, interference effect evaluation, and interference parameter adjustment.

[0039] Preferably, the signal transmission control specifically involves controlling a multi-band antenna array to transmit the modulated interference signal and adjusting the transmission power and transmission frequency in real time.

[0040] The interference effect monitoring specifically involves collecting UAV signals in real time, monitoring the interference effect, and generating interference effect monitoring data.

[0041] The interference effect assessment specifically involves evaluating the interference effect based on the interference effect monitoring data and generating an interference effect assessment report.

[0042] The interference parameter adjustment specifically involves adjusting the transmission power, transmission frequency, and modulation parameters of the interference signal based on the interference effect evaluation report.

[0043] Preferably, the interference effect monitoring data specifically includes interference success rate data, interference duration data, and interference impact range data;

[0044] The interference success rate data is used to represent the quantitative value of interference success, and the value range is [0, 100%];

[0045] The interference duration data is used to represent the duration of the interference, in milliseconds;

[0046] The interference impact range data is used to represent the area affected by the interference, with the unit being square meters.

[0047] Preferably, the interference effect evaluation report specifically includes an interference success rate evaluation, an interference duration evaluation, and an interference impact range evaluation;

[0048] The interference success rate assessment is used to evaluate the probability of successful interference.

[0049] The interference duration assessment is used to evaluate the duration of the interference.

[0050] The interference impact range assessment is used to evaluate the regional range affected by the interference.

[0051] Compared with the prior art, the beneficial effects of the present invention are:

[0052] By deploying a multi-band antenna array, the system can comprehensively collect UAV signals, acquiring rich raw data including signal strength, frequency, phase, and historical interference records. This data provides ample basis for subsequent analysis. Compared to traditional jamming systems that can only collect limited signal features, this system can more accurately grasp the communication status of UAVs. In the frequency band analysis module, signal filtering, frequency band segmentation, frequency band feature extraction, and frequency band comprehensive processing are performed sequentially. Advanced algorithms and models are used to deeply analyze the signal and accurately identify the UAV's communication frequency band and its characteristics. For example, through precise frequency band segmentation and feature extraction, the system can accurately distinguish the signal frequency bands of different UAVs in complex environments, providing strong support for subsequent targeted jamming and effectively improving the accuracy and targeting of the jamming.

[0053] The interference generation module employs a multi-band adaptive noise injection-based interference generation model, possessing strong adaptive capabilities. The model's frequency band noise injection operator, frequency band interference optimization operator, multi-band interference sub-model, frequency band classification sub-model, and parameter optimization operator work collaboratively to adjust the interference strategy in real time based on frequency band analysis data. For example, the frequency band noise injection operator can optimize frequency band characteristics and reduce noise interference on signal quality, making the interference signal more targeted; the parameter optimization operator uses a tree-oriented Bayesian optimization algorithm to optimize model parameters, ensuring that the generated interference signal effectively covers the UAV communication frequency bands, significantly improving the interference success rate. Compared to traditional fixed-mode interference signal generation methods, this system can adapt to signal variations from different UAVs, significantly improving the interference effect.

[0054] The signal modulation module modulates and optimizes the interference signal based on frequency band analysis data and the interference signal using a frequency band modulation-based signal optimization model. In a series of steps including signal integration, frequency band coding optimization, modulation model construction, and optimization model, various factors are fully considered, such as frequency band type, intensity, historical modulation schemes, and environmental conditions. Frequency band characteristics are processed using techniques such as one-hot coding to train accurate modulation and optimization models, enabling the generation of high-quality modulated interference signals. For example, the modulation effect prediction optimization model can predict the interference effect based on different modulation schemes, select the optimal scheme to generate the modulated interference signal, effectively enhancing the penetration capability and interference effect of the interference signal in complex environments, ensuring that the interference signal can reliably affect the UAV communication link, and achieving effective control of the UAV flight. The integrated control module implements comprehensive control over the transmission and adjustment of the interference signal. In terms of signal transmission control, the transmission power and frequency of the multi-band antenna array can be adjusted in real time, and transmission parameters can be flexibly optimized based on factors such as the distance to the UAV and signal strength, ensuring that the interference signal can effectively act on the UAV in different scenarios. The jamming effect monitoring stage acquires key data such as jamming success rate, duration, and impact range by collecting UAV signals in real time, enabling a comprehensive quantitative assessment of the jamming effect. Based on the assessment results, the system can automatically adjust the transmission power, frequency, and modulation parameters of the jamming signal, achieving dynamic optimization of the jamming strategy. This real-time monitoring and intelligent adjustment mechanism allows the system to continuously maintain optimal jamming status, effectively responding to various evasive behaviors of UAVs, ensuring the continuity and stability of jamming, and significantly improving the reliability and practicality of the jamming system.

[0055] The multi-band UAV signal jamming system of this invention possesses excellent versatility and scalability, enabling it to adapt to various complex application scenarios, such as UAV control in different environments including airports, military bases, and sensitive areas. Due to its modular design and advanced algorithm model, the system is easy to upgrade and optimize, and can be continuously updated and iterated with the development of UAV technology. For example, when new UAV communication frequency bands or technologies emerge, only adjustments to the algorithms and parameters of the corresponding modules are needed to effectively jam the new targets, providing a solid foundation for the continued development of future UAV surveillance technology. Attached Figure Description

[0056] Figure 1 This is a schematic diagram illustrating the working principle of the multi-band UAV signal jamming system described in this invention.

[0057] Figure 2 A schematic diagram illustrating the working principle of generating interference signals for multi-band adaptive noise injection;

[0058] Figure 3 This is a schematic diagram illustrating the working principle of a multi-band modulated signal optimization model. Detailed Implementation

[0059] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0060] Please see Figure 1-3 This invention provides a technical solution: a multi-band unmanned aerial vehicle (UAV) signal jamming system, the system comprising:

[0061] Signal Acquisition Module: By deploying a multi-band antenna array, this module extensively collects UAV signals, acquiring raw signal data. This raw data contains rich information, such as signal strength, frequency, phase, and historical interference records, providing fundamental data support for subsequent analysis and processing. The acquired data is promptly transmitted to the frequency band analysis module for further analysis.

[0062] Frequency band analysis module: After receiving the raw UAV signal data from the signal acquisition module, this module sequentially performs signal filtering, frequency band segmentation, frequency band feature extraction, and frequency band synthesis processing. Through these operations, the raw data is transformed into valuable frequency band analysis data, which is then transmitted to the interference generation module and the signal modulation module, respectively, providing a basis for generating targeted interference signals and optimizing modulation signals.

[0063] Interference Generation Module: Based on the frequency band analysis data provided by the frequency band analysis module, this module generates interference signals using an interference generation model based on multi-band adaptive noise injection. This model comprises several key components, including a frequency band noise injection operator, a frequency band interference optimization operator, a multi-band interference sub-model, a frequency band classification sub-model, and a parameter optimization operator. Through the synergistic effect of these components, effective interference signals targeting different frequency bands are generated and sent to the signal modulation module.

[0064] Signal modulation module: Combining frequency band analysis data and interference signals from the interference generation module, it uses a frequency band modulation-based signal optimization model to modulate and optimize the interference signals. After a series of processing steps, the modulated interference signal is obtained and transmitted to the integrated control module to ensure that the interference signal reaches its optimal state before transmission.

[0065] The integrated control module is responsible for controlling the transmission of modulated jamming signals by the multi-band antenna array, monitoring the jamming effect in real time, and adjusting the jamming signals based on the monitoring results. This process enables precise control of the jamming signal transmission, improves the jamming effect, and ensures that the jamming system can adapt to different UAV signal conditions.

[0066] The present invention will be further described below with reference to Examples 1 to 5:

[0067] Example 1:

[0068] This embodiment details the specific working method of the signal acquisition module and the acquisition and processing process of the raw UAV signal data involved, ensuring that comprehensive and accurate data is collected.

[0069] In practical applications, the deployment of multi-band antenna arrays needs to be optimized based on interference requirements and the environment. For example, in open areas, a uniformly distributed array can be used to achieve omnidirectional signal acquisition; while in urban environments, due to numerous obstacles such as buildings, an adaptive array deployment method can be adopted, which automatically adjusts the antenna direction based on signal reflection and obstruction.

[0070] The signal acquisition module collects UAV signals through a multi-band antenna array. During the acquisition process, a high-precision signal strength detection chip is used for signal strength data, with a detection accuracy of ±0.1dBm. For signal frequency data, a frequency counter is used for measurement, achieving accuracy to the Hz level. Signal phase data is acquired using a phase detection circuit, which determines the phase by comparing the phase difference between the reference signal and the acquired signal.

[0071] The mechanism for acquiring and updating historical interference data is crucial. After each interference operation, the system records information such as the frequency band, effect, and adjustment parameters. For example, if the interference achieved an 80% success rate in the 2.4GHz band, lasted for 5000 milliseconds, affected an area of ​​1000 square meters, and the transmit power was adjusted to 20dBm, the transmit frequency to 2.41GHz, and the modulation parameters to a specific combination, this data will be recorded in the historical interference frequency band data, historical interference effect data, and historical interference adjustment data. When signals are collected again, this historical data will be acquired together, providing a reference for subsequent analysis.

[0072] Example 2:

[0073] This embodiment provides a detailed explanation of the construction process of the interference generation model based on multi-band adaptive noise injection in the frequency band analysis module, as well as the specific application of relevant data in model construction and interference signal generation.

[0074] When constructing the frequency band noise injection operator, the value of the step size factor in the adaptive noise injection algorithm has a significant impact on the algorithm's performance. In actual debugging, through multiple experimental comparisons, it was found that when the value is between 0.001 and 0.01, it can both ensure the convergence speed of the algorithm and effectively optimize the frequency band characteristics.

[0075] Assume the input frequency band analysis data is Based on the adaptive noise injection algorithm, in each iteration, according to the current error signal... and input signal vector To adjust the weight vector This allows for the optimization of frequency band characteristics.

[0076] When constructing a frequency band interference optimization operator, frequency band feature data is extracted and optimized. For example, for signal strength feature data of a certain frequency band... Calculate its standard deviation and mean If the mean is calculated Standard deviation Based on these statistical characteristics, the signals in this frequency band can be analyzed and processed more accurately, and used as part of the optimized frequency band interference feature dataset.

[0077] To construct a multi-band interference sub-model, a standard multi-band interference neural network can be constructed using a multilayer perceptron (MLP) structure. Assuming the network contains an input layer, two hidden layers, and an output layer, the number of nodes in the input layer is determined by the number of frequency band features; for example, if there are 10 frequency band features, the input layer will have 10 nodes. The number of nodes in the hidden layer can be determined using an empirical formula. (in This represents the number of hidden layer nodes. The number of nodes in the input layer. This represents the number of nodes in the output layer. The value is determined by a constant between 1 and 10. If the number of output layer nodes is 5, then... The number of hidden layer nodes are 8 and 6 respectively. During network training, the backpropagation algorithm is used to adjust the weights, the learning rate is set to 0.01, and the training is performed 1000 times, so that the network can accurately extract frequency band features based on the sampling frequency and output frequency band interference status data.

[0078] A frequency band classification sub-model is constructed, and the classifier of the standard frequency band classification model is trained based on the optimized frequency band interference feature datasets with different sampling frequencies. For example, support vector machines (SVMs) are used as classifiers to train the optimized frequency band interference feature datasets for low frequency, mid frequency, and high frequency bands, respectively.

[0079] During training, the kernel function parameters of the SVM are adjusted, such as by using the radial basis function. Determined through cross-validation The optimal value is 0.1. Input the frequency band interference status output data into the trained frequency band classification sub-model to obtain frequency band classification output data. For example, if a frequency band is classified as a mid-frequency band, the frequency band strength reference data is 60%, and the frequency band interference effect reference data predicts the interference success rate as 70%, the interference duration as 3000 milliseconds, and the interference impact range as 800 square meters.

[0080] A parameter optimization operator was constructed, and a tree-oriented Bayesian optimization algorithm was used to optimize the model parameters. During the optimization process, the objective function was defined as the accuracy of the interference generation model. Through continuous sampling and evaluation, the optimal combination of model hyperparameters was found. For example, after 50 iterations, the optimal combination of model hyperparameters was found to be a learning rate of 0.005, 3 network layers, and 10, 8, and 5 nodes per layer, respectively. This combination was applied to train the interference generation model, resulting in the interference generation model ModelG. Using this model, interference signals were generated based on frequency band analysis data, providing strong support for subsequent interference operations.

[0081] Example 3:

[0082] This embodiment describes in detail the specific implementation steps of the frequency band modulation-based signal optimization model in the signal modulation module, ensuring effective modulation and optimization of the interference signal and improving the interference effect.

[0083] In the signal integration phase, frequency band analysis data and interference signals are integrated. Assuming the frequency band analysis data includes information such as frequency band type and frequency band strength, it is represented in matrix form. The interference signal data is represented in vector form as follows During integration, the two data points are combined according to certain rules, such as concatenating each row of the frequency band analysis data with the corresponding element of the interference signal vector to obtain the integrated modulation dataset. Signal cleaning is performed on the integrated modulation dataset. Data anomaly judgment rules are set. If the signal strength data exceeds the normal range [0, 100] or the frequency band type is not within the preset low frequency band, mid frequency band, or high frequency band range, it is judged as abnormal data and removed to obtain the integrated modulation optimization dataset.

[0084] During frequency band coding optimization, frequency band features are extracted from the integrated modulation optimization dataset to obtain a modulation feature dataset. For example, in a certain data sample, the frequency band type feature is mid-frequency band (represented by the number 2), the frequency band intensity feature is 70% (represented by the number 0.7), the historical modulation scheme feature is scheme 3 (represented by the number 3), the modulation method feature is ASK (represented by the number 1), and the environmental condition auxiliary feature is indoor (represented by the number 0), forming a modulation feature dataset [2, 0.7, 3, 1, 0]. One-hot coding is performed on the frequency band features. Taking the frequency band type feature as an example, if there are three types: low-frequency band, mid-frequency band, and high-frequency band, then the mid-frequency band is coded as [0, 1, 0]. The other frequency band features are coded sequentially to obtain the coding feature matrix set.

[0085] Construct a modulation model and perform frequency band modulation pre-classification training using a modulation algorithm. Assuming the K-Nearest Neighbors (K-NN) algorithm is used, set... By training a large amount of labeled frequency band modulation data, a frequency band modulation pre-classification and recognition model is obtained. This model is then used to perform frequency band modulation pre-classification and recognition on the coded feature matrix set, resulting in frequency band modulation pre-identification data.

[0086] An optimization model is constructed, employing a rule-based approach to extract modulation schemes from the integrated modulation optimization dataset based on pre-identified data, resulting in a candidate list of modulation schemes. For example, if pre-identified data shows a certain frequency band as a mid-frequency band with high signal strength, modulation schemes such as increasing transmit power or using specific modulation method combinations may be extracted according to preset rules, forming a candidate list of modulation schemes [Scheme 1, Scheme 2, ...]. The optimization model is trained based on this list, assuming a neural network is used for training. The network structure has the same number of input layer nodes as the number of modulation scheme features, 10 hidden layer nodes, and 1 output layer node (representing the predicted modulation effect value). After training, a modulation effect prediction optimization model is obtained. This model is then used to predict the modulation effect based on the modulation schemes in the candidate list, yielding the predicted modulation effect output.

[0087] The signal modulation model is trained using the steps described above to obtain the signal modulation model ModelSM. This model is then used to generate a modulated signal based on frequency band analysis data and interference signals. The modulated interference signal is obtained by integrating the predicted outputs. For example, given a set of frequency band analysis data and interference signals, ModelSM outputs the predicted effects of multiple modulation schemes. The scheme with the best effect is selected to generate the modulated interference signal, providing a high-quality signal source for subsequent interference signal transmission.

[0088] Example 4:

[0089] This embodiment details the process by which the integrated control module controls the transmission of interference signals and monitors, evaluates, and adjusts the interference effect, ensuring that the interference system can optimize the interference strategy in real time according to the actual situation, thereby improving the effectiveness and stability of the interference.

[0090] In the signal transmission control stage, the control of the multi-band antenna array is crucial. Precise control of the antenna array is achieved through control circuits, such as using programmable logic devices (PLDs) to write control programs that adjust the antenna's transmission direction, transmission power, and transmission frequency according to interference requirements. The transmission power can be adjusted within a range of 10-30 dBm, and the transmission frequency can be flexibly adjusted within the commonly used frequency bands for UAVs (e.g., 2.4 GHz-5.8 GHz). During interference, the transmission power and frequency are dynamically adjusted based on real-time monitoring of the UAV signal strength and distance. If a weak UAV signal is detected at a long distance, the transmission power is appropriately increased to 25 dBm, and the transmission frequency is adjusted to the center frequency of the UAV signal to enhance the interference effect.

[0091] During interference effect monitoring, the interference effect is monitored by real-time acquisition of drone signals. For example, within a certain time period, drone signals are acquired every 100 milliseconds to analyze characteristics such as signal strength and frequency changes. If the drone signal strength is stable at -50dBm before interference and drops to -80dBm after interference, with the duration exceeding 1000 milliseconds, it is preliminarily judged that the interference has achieved a certain effect. Interference effect monitoring data is generated based on the acquired data, including interference success rate data, interference duration data, and interference impact range data. The interference success rate is calculated as follows: the number of successful interference attempts within a certain time period divided by the total number of interference attempts, then multiplied by 100%. Assuming 8 successful interference attempts out of 10 attempts, the interference success rate is 80%. The interference duration is determined by recording the time difference between the start and end of each interference attempt, in milliseconds. The interference impact range is determined by combining a signal strength attenuation model and actual measurements, assuming a signal strength attenuation formula... (in To receive signal strength, For the transmitted signal strength, For distance, (Including other losses), and based on the actual measured signal strength distribution, the interference range was determined to be 1500 square meters.

[0092] The interference effectiveness assessment is based on interference monitoring data. Detailed assessment criteria are established, such as a good interference effectiveness if the interference success rate is greater than 70%, the interference duration exceeds 2000 milliseconds, and the interference impact area exceeds 1000 square meters. An interference effectiveness assessment report is generated based on these criteria, including assessments of the interference success rate, interference duration, and interference impact area. For example, this interference effectiveness assessment report shows an 80% interference success rate (assessed as good); an interference duration of 2500 milliseconds (assessed as good); and an interference impact area of ​​1200 square meters (assessed as good).

[0093] Adjust the interference parameters based on the interference effect assessment report. If the interference success rate does not meet expectations, the transmission power can be appropriately increased, with each adjustment increment being 2dBm. If the interference duration is short, modulation parameters can be adjusted, such as changing the modulation method or increasing the complexity of the modulation signal. If the interference impact range is small, the transmission frequency can be adjusted to find a more effective interference frequency band. By continuously adjusting the interference parameters, the interference effect can be optimized, ensuring that the interference system is always in its best working condition.

[0094] Example 5:

[0095] This embodiment illustrates the collaborative working mechanism between the modules of the entire multi-band UAV signal jamming system, and how to optimize performance during actual operation to improve the overall efficiency and stability of the system.

[0096] After system startup, the signal acquisition module begins operation, continuously acquiring UAV signals and transmitting the raw data to the frequency band analysis module. Upon receiving the data, the frequency band analysis module rapidly performs signal filtering, frequency band segmentation, frequency band feature extraction, and frequency band synthesis processing. In this process, each step is closely integrated; for example, the result of signal filtering is directly used as input for frequency band segmentation, ensuring the consistency and accuracy of data processing. After completing the analysis, the frequency band analysis module sends the frequency band analysis data to the interference generation module and the signal modulation module, respectively.

[0097] The interference generation module invokes an interference generation model based on multi-band adaptive noise injection, using frequency band analysis data. During the model building phase, the frequency band noise injection operator, frequency band interference optimization operator, multi-band interference sub-model, frequency band classification sub-model, and parameter optimization operator collaborate. While the frequency band noise injection operator optimizes frequency band features, the frequency band interference optimization operator extracts key interference feature data, the multi-band interference sub-model performs deep feature extraction, the frequency band classification sub-model provides frequency band classification information, and the parameter optimization operator continuously adjusts model parameters to improve model performance. After training to obtain the interference generation model ModelG, the interference signal is generated and transmitted to the signal modulation module.

[0098] After receiving the frequency band analysis data and the interference signal, the signal modulation module operates based on the frequency band modulation-based signal optimization model. The signal integration step fuses the two types of data, the frequency band coding optimization processes the features, and the processes of building the modulation model and the optimization model work together to obtain the signal modulation model ModelSM through continuous training. Then, the modulated interference signal is generated and sent to the integrated control module.

[0099] Upon receiving the modulated interference signal, the integrated control module immediately controls the multi-band antenna array to transmit, adjusting the transmission power and frequency in real time during transmission. In the interference effect monitoring phase, UAV signals are continuously collected, and the acquired interference success rate, duration, and impact range data are used to evaluate the interference effect. If the evaluation finds that the interference effect does not meet expectations, the transmission power, frequency, and modulation parameters of the interference signal are adjusted based on the evaluation results. The adjusted parameter information is fed back to the interference generation module and the signal modulation module, enabling these two modules to optimize the subsequently generated interference signals and modulation methods, achieving closed-loop optimization of the entire system.

[0100] To further optimize system performance, parameter calibration and performance evaluation of each module can be performed periodically. For example, the antenna array gain of the signal acquisition module can be calibrated every certain period (e.g., weekly) to ensure the accuracy of the acquired signals. For the frequency band analysis module, the parameters of signal filtering and frequency band segmentation can be updated based on the characteristics of newly emerging UAV signals to improve the accuracy of the analysis. The interference generation module and signal modulation module can continuously optimize the parameters of their respective models based on feedback from actual interference effects to improve the generation quality and modulation effect of interference signals.

[0101] In terms of hardware, key hardware devices can be upgraded according to actual usage scenarios and interference requirements. For example, in scenarios with a large interference range, a more powerful and higher-performance transmitting antenna can be used to enhance the coverage of interference signals; for scenarios with high signal processing speed requirements, the processor chip can be upgraded to improve data processing efficiency and ensure that the system can quickly respond to and process drone signals.

[0102] Furthermore, the system can incorporate a self-learning mechanism based on artificial intelligence. By collecting a large amount of interference case data, including interference data from different drone models and under different environments, the system can automatically learn the optimal interference strategy. For example, based on historical data, the system can analyze which interference signal generation and modulation methods can achieve the best interference effect in specific frequency bands and environments, thereby automatically selecting the optimal solution in subsequent interference operations, further improving the system's intelligence level and interference effectiveness.

[0103] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0104] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A multi-band UAV signal jamming system, characterized in that: It includes a signal acquisition module, a frequency band analysis module, an interference generation module, a signal modulation module, and a comprehensive control module; The signal acquisition module is used to acquire UAV signals, specifically by deploying a multi-band antenna array and acquiring signals to obtain raw UAV signal data, and then sending the raw UAV signal data to the frequency band analysis module. The frequency band analysis module is used to perform frequency band analysis and feature extraction on the original signal. Specifically, it obtains frequency band analysis data by sequentially performing signal filtering and frequency band segmentation on the original UAV signal data, and sends the frequency band analysis data to the interference generation module and the signal modulation module. The specific steps include: signal filtering, frequency band segmentation, frequency band feature extraction and frequency band comprehensive processing. The interference generation module is used to generate interference signals for different frequency bands. Specifically, based on the frequency band analysis data, it uses an interference generation model based on multi-band adaptive noise injection to generate interference signals and sends the interference signals to the signal modulation module. The interference generation model based on multi-band adaptive noise injection specifically includes a frequency band noise injection operator, a frequency band interference optimization operator, a multi-band interference sub-model, a frequency band classification sub-model, and a parameter optimization operator; The signal modulation module is used to modulate and optimize the interference signal. Specifically, based on the frequency band analysis data and the interference signal, it uses a frequency band modulation-based signal optimization model to perform signal modulation, obtain a modulated interference signal, and send the modulated interference signal to the integrated control module. The integrated control module is used to comprehensively control the transmission and adjustment of the interference signal. Specifically, it controls the multi-band antenna array to transmit the modulated interference signal and monitors and adjusts the interference effect in real time.

2. The multi-band UAV signal jamming system according to claim 1, characterized in that, In the signal acquisition module, the raw UAV signal data specifically includes signal strength data, signal frequency data, signal phase data, and historical interference record data; the historical interference record data specifically includes historical interference frequency band data, historical interference effect data, and historical interference adjustment data.

3. The multi-band UAV signal jamming system according to claim 2, characterized in that, In the interference generation module, the step of generating interference signals using an interference generation model based on multi-band adaptive noise injection includes: constructing a frequency band noise injection operator, constructing a frequency band interference optimization operator, constructing a multi-band interference sub-model, constructing a frequency band classification sub-model, constructing a parameter optimization operator, training the interference generation model, and generating interference signals. The constructed frequency band noise injection operator is used to optimize the frequency band features in the frequency band analysis data and reduce the interference of noise on signal quality. Specifically, it adopts an adaptive noise injection algorithm to perform adaptive noise injection on the frequency band analysis data. The construction of the frequency band interference optimization operator specifically involves extracting frequency band interference optimization from the frequency band feature data to obtain frequency band interference feature data, and calculating the standard deviation and mean of the frequency band interference feature data to obtain an optimized frequency band interference feature dataset. The construction of the multi-band interference sub-model specifically involves constructing a standard multi-band interference neural network and performing in-depth extraction of frequency band features based on the acquisition frequency to obtain frequency band interference status output data. The construction of the frequency band classification sub-model specifically involves training the classifier of the standard frequency band classification model based on the optimized frequency band interference feature dataset corresponding to different sampling frequencies, and classifying the frequency band type by using the frequency band interference state output data as the total input of the trained frequency band classification sub-model to obtain the frequency band classification output data. The construction of the parameter optimization operator specifically involves using a tree-oriented Bayesian optimization algorithm to optimize the model parameters, obtaining an optimized combination of model hyperparameters, and applying the optimized combination of model hyperparameters to the training of the interference generation model. The interference generation model training specifically involves training the interference generation model ModelG using the frequency band noise injection operator, the frequency band interference optimization operator, the multi-frequency band interference sub-model, the frequency band classification sub-model, and the parameter optimization operator. The interference signal generation specifically involves using the interference generation model ModelG to generate the interference signal based on the frequency band analysis data.

4. A multi-band UAV signal jamming system according to claim 3, characterized in that, The frequency band classification output data specifically includes frequency band type reference data, frequency band strength reference data, and frequency band interference effect reference data. The frequency band type reference data is used to indicate identifiable frequency band categories, specifically including low frequency band, mid frequency band, and high frequency band; The frequency band strength reference data is used to represent the strength quantization value of the frequency band signal, and the value range is [0, 100%]; The frequency band interference effect reference data is used to provide a quantitative assessment of the frequency band interference effect, specifically including interference success rate, interference duration, and interference impact range.

5. A multi-band UAV signal jamming system according to claim 4, characterized in that, In the signal modulation module, a signal optimization model based on frequency band modulation is used to modulate the signal and obtain a modulated interference signal. The specific steps include: signal integration, frequency band coding optimization, construction of modulation model, construction of optimization model, signal modulation model training, and modulation signal generation.

6. A multi-band UAV signal jamming system according to claim 5, characterized in that, The signal integration specifically involves integrating the frequency band analysis data and the interference signal to obtain an integrated modulation dataset, and performing signal cleaning operations on the integrated modulation dataset to obtain an integrated modulation optimization dataset. The frequency band coding optimization specifically involves performing frequency band feature extraction operations from the integrated modulation optimization dataset to obtain a modulation feature dataset, and then performing one-hot coding on the frequency band features in the modulation feature dataset to obtain a coding feature matrix set. The modulation feature dataset specifically includes frequency band type features, frequency band intensity features, historical modulation scheme features, modulation method features, and environmental condition auxiliary features; The construction of the modulation model specifically involves using a modulation algorithm to perform frequency band modulation pre-classification training to obtain a frequency band modulation pre-classification recognition model. The construction of the optimization model specifically involves using the frequency band modulation pre-classification and identification model to perform frequency band modulation pre-classification and identification based on the coding feature matrix set, obtaining frequency band modulation pre-identification data, and using a rule-based method to extract modulation schemes from the integrated modulation optimization dataset based on the frequency band modulation pre-identification data, obtaining a modulation scheme candidate list, and training the optimization model based on the modulation scheme candidate list to obtain a modulation effect prediction optimization model. The modulation effect prediction optimization model is used to predict the effect based on the modulation scheme in the modulation scheme candidate list and obtain the modulation effect prediction output. The signal modulation model training specifically involves training the signal modulation model through signal integration, frequency band coding optimization, construction of the modulation model, and construction of the optimization model to obtain the signal modulation model ModelSM. The modulation signal generation specifically involves using the signal modulation model ModelSM to generate a modulation signal based on the frequency band analysis data and the interference signal, and then integrating the predicted output to obtain the modulation interference signal.

7. A multi-band UAV signal jamming system according to claim 1, characterized in that, The integrated control module is used to comprehensively control the transmission and adjustment of the interference signal. Specifically, it controls the transmission of the modulated interference signal by a multi-band antenna array and monitors and adjusts the interference effect in real time. The specific steps include: signal transmission control, interference effect monitoring, interference effect evaluation, and interference parameter adjustment.

8. A multi-band UAV signal jamming system according to claim 7, characterized in that, The signal transmission control specifically involves controlling a multi-band antenna array to transmit the modulated interference signal and adjusting the transmission power and transmission frequency in real time. The interference effect monitoring specifically involves collecting UAV signals in real time, monitoring the interference effect, and generating interference effect monitoring data. The interference effect assessment specifically involves evaluating the interference effect based on the interference effect monitoring data and generating an interference effect assessment report. The interference parameter adjustment specifically involves adjusting the transmission power, transmission frequency, and modulation parameters of the interference signal based on the interference effect evaluation report.

9. A multi-band UAV signal jamming system according to claim 8, characterized in that, The interference effect monitoring data specifically includes interference success rate data, interference duration data, and interference impact range data; The interference success rate data is used to represent the quantitative value of interference success, and the value range is [0, 100%]; The interference duration data is used to represent the duration of the interference, in milliseconds; The interference impact range data is used to represent the area affected by the interference, with the unit being square meters.

10. A multi-band UAV signal jamming system according to claim 8, characterized in that, The interference effectiveness assessment report specifically includes interference success rate assessment, interference duration assessment, and interference impact range assessment. The interference success rate assessment is used to evaluate the probability of successful interference. The interference duration assessment is used to evaluate the duration of the interference. The interference impact range assessment is used to evaluate the regional range affected by the interference.

Images