Intelligent integrated unmanned aerial vehicle reconnaissance and countering system and method

Through the intelligent integrated drone reconnaissance and countermeasure system, combined with deep learning algorithms, the problems of low intelligence and poor autonomous coordination of existing equipment are solved, accurate identification and intelligent interference of drones are achieved, and defense is improved Capability and degree of system automation.

CN118897265APending Publication Date: 2024-11-05SICHUAN JIUZHOU ELECTRIC GROUP CO LTD
View PDF 0 Cites 7 Cited by

Patent Information

Application Number
CN202410957217.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-05

AI Technical Summary

Technical Problem

Existing drone reconnaissance and countermeasures are low in intelligence, unable to accurately identify targets, lack intelligent interference signal generation capabilities, poor autonomous coordination, and weak integration capabilities, making it difficult to accurately face low-slow and small drones. Identify and effectively interfere.

Method used

An intelligent integrated drone reconnaissance and countermeasure system was designed, including detection and reception module, interference transmission module, navigation deception module and signal processing module, using RF front-end module, digital baseband module, FPGA and other components, combined with deep learning Algorithm realizes accurate identification and intelligent interference signal generation of drones, and improves the system's independent coordination and integration capabilities.

Benefits of technology

It realizes efficient and accurate identification and interference of drones, improves drone defense capabilities, has high system automation, low cost, and has fast response and deployment capabilities, ensuring safety and effectiveness.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118897265A_ABST
    Figure CN118897265A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent integrated unmanned aerial vehicle reconnaissance and countering system and method. The intelligent integrated unmanned aerial vehicle reconnaissance and countering system comprises a radio frequency front-end module, a signal processing module and a signal processing module, the digital baseband module is used for realizing frequency mixing and analog-to-digital conversion of the filtered signal; the interference transmitting module is used for generating various interference signals and transmitting the interference signals through a radio frequency amplification link; the navigation deception module is used for completing positioning and ephemeris searching and transmitting a navigation deception signal; and the signal processing module is used for processing the detected and received digital signal, generating an interference emission signal, processing a navigation receiving signal, generating a navigation decoy signal and completing control scheduling work among the modules. The reconnaissance and countering efficiency is high, and the cost is low.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle (UAV) reconnaissance and countermeasure technology, and in particular to an intelligent integrated UAV reconnaissance and countermeasure system and method. Background Art

[0002] Electronic reconnaissance technology detects the remote control and image transmission signals of drones, and through effective comprehensive analysis and processing of the time and frequency domains of the signals, finds and identifies the target, determines the direction of the target radiation source, and effectively improves the probability of drone detection. Its working principle is that the drone needs to receive the remote control signal of the remote controller during flight, and the remote control operator receives the downlink image transmission signal of the drone. All these wireless communication links will occupy spectrum resources. The radio detection equipment can extract the signal features of interest from them through signal detection technology, and use spectrum feature recognition technology to compare with the established spectrum feature library to obtain model information.

[0003] Interference suppression technology mainly uses the remote control link to suppress interference mechanisms. The mechanism of remote control link suppression is to transmit interference signals of the same frequency based on the working frequency band of the remote control signal, which results in the inability to achieve normal information transmission between the drone and the ground remote control station. In this case, the drone's self-protection system is activated, forcing the drone to land or return. In order to enhance the anti-interference effect, the remote control link of the drone usually selects a frequency hopping communication mode, that is, the communication frequency jumps regularly within a larger bandwidth range.

[0004] Navigation deception technology mainly transmits deception signals that are consistent with the structure of real navigation signals, causing drones to obtain incorrect positioning information, thereby affecting the flight status of drones to achieve the purpose of countermeasures. It has high concealment and is an ideal countermeasure. Its working principle is that the GPS / GLONASS / Beidou signal source receives the ephemeris information from the receiver module or external annotations, as well as the time information synchronized locally, and obtains the code phase and Doppler information of the satellite signal by calculating the satellite position, speed, and simulated position. Then, through CA code generation, navigation bit modulation, and intermediate frequency carrier BPSK modulation, the satellite baseband intermediate frequency signal is obtained. After multi-channel combination, the RF up-conversion module obtains the RF transmission signal and sends it out through the antenna. The ground unmanned equipment triggers its own correction mechanism and drives the unmanned equipment to the designated area.

[0005] From the working principle of reconnaissance and countermeasures, it can be seen that the existing means are mainly aimed at modeling of drone signal spectrum or known models. For targets such as low-speed, slow and small drones, the existing radio reconnaissance and countermeasures equipment are difficult to accurately identify and interfere with. The specific performance is as follows:

[0006] (1) Signal reconnaissance intelligence is low and targets cannot be accurately identified

[0007] Existing reconnaissance equipment can only identify the WIFI system signals or spectrum distribution commonly used by commercial drones, and cannot accurately extract signal parameters to precisely identify drones; and the control signal modulation methods of modified drones are diverse, and their parameters must be intelligently and accurately identified in order to carry out precise interference.

[0008] (2) Lack of intelligent jamming signal generation capability, resulting in significant collateral damage

[0009] In terms of countermeasures, the main method is to suppress the control and navigation signals of drones with high power. High-power interference suppression has limited countermeasure capabilities against autonomously navigated drones and is prone to secondary safety accidents. At the same time, high-power interference equipment is large in size and cannot be deployed quickly.

[0010] (3) Poor autonomous coordination and weak integration capabilities

[0011] Existing drone reconnaissance and countermeasure equipment has poor real-time and autonomous coordination. Most of them are interfered by operators using jammers or other equipment after being discovered by the detection system. They have weak integration capabilities and low intelligence levels. Summary of the invention

[0012] In view of the problems of low intelligence level, large collateral damage, poor autonomous coordination, weak integration capability, etc. in the above-mentioned existing reconnaissance and countermeasure means, the present invention provides an intelligent integrated UAV reconnaissance and countermeasure system and method, and carries out research on key technologies such as intelligent and precise identification, intelligent generation of jamming signals, intelligent navigation deception and integrated design to meet the needs of UAV defense.

[0013] The present invention discloses an intelligent integrated unmanned aerial vehicle reconnaissance and countermeasure system, which comprises a detection receiving module, an interference transmitting module, a navigation decoy module and a signal processing module; the detection receiving module comprises a radio frequency front-end module and a digital baseband module; the signal processing module is respectively connected with the detection receiving module, the interference transmitting module and the navigation decoy module;

[0014] The RF front-end module is used to achieve low-noise amplification and filtering of the received weak spatial signals; the digital baseband module is used to achieve mixing and analog-to-digital conversion of the filtered signals; the interference transmission module is used to generate various interference signals and transmit them through the RF amplification link; the navigation deception module is used to complete positioning and ephemeris search, and transmit navigation deception signals; the signal processing module is used to process the detected received digital signals, generate interference transmission signals, process navigation received signals and generate navigation deception signals, and complete the control and scheduling work between the modules.

[0015] Furthermore, the digital baseband module is composed of a mixer, an amplifier, a low-pass filter, an AD converter and an FPGA connected in sequence;

[0016] The mixer is used to mix the filtered RF signal and the local oscillator signal to obtain an intermediate frequency signal, complete the transfer of the RF signal to the intermediate frequency signal, and then amplify the intermediate frequency signal through the amplifier and input it into the low-pass filter. The AD converter then completes the conversion of the analog signal to the digital signal and transmits it to the FPGA. Finally, the FPGA converts the digital signal from the time domain to the frequency domain, and then the signal processing module completes the spectrum recognition.

[0017] Furthermore, the interference transmission module includes a radio frequency front-end module and an interference digital baseband module; the interference digital baseband module is composed of an FPGA, a digital-to-analog converter, a low-pass filter and a modulator connected in sequence;

[0018] The FPGA is used to process the interference waveform generated by the signal processing module. After the processed signal passes through the digital-to-analog converter and the low-pass filter in turn, the modulator mixes the interference signal and the RF signal; the RF front-end module is used to filter and amplify the mixed RF signal and transmit it through the antenna array.

[0019] Furthermore, the navigation deception module is composed of a radio frequency front-end module and a navigation deception digital baseband module, and the radio frequency front-end module is used to perform low-noise amplification and filtering on the received navigation radio frequency signal;

[0020] The digital baseband module is used to mix the filtered navigation RF signal and the local oscillator signal to form an intermediate frequency signal. After the intermediate frequency signal passes through low-pass filtering and analog-to-digital conversion, it is transmitted to the signal processing module after FPGA processing; after the signal processing module generates multi-standard navigation signals and UAV reverse track coordinates, they are returned to the FPGA for processing and clock synchronization, and then pass through digital-to-analog conversion and low-pass filter in turn. The filtered deceptive navigation signal and local oscillator signal are modulated in multiple standards through the IQ modulator, and the modulated signal is filtered and power amplified by the RF front-end module before output.

[0021] Furthermore, it also includes a duplexer group; the duplexer group is connected to the detection receiving module and the interference transmitting module respectively; the duplexer group is used to realize the transceiver switching of the detection and interference antennas, and ensure that the receiving and transmitting systems can work normally while sharing the antenna.

[0022] Furthermore, it also includes an antenna array; the antenna array includes a detection / interference antenna array, a navigation deception receiving antenna array and a navigation deception transmitting antenna array; the detection / interference antenna array includes a directional detection and strike integrated design antenna and an omnidirectional detection antenna; the detection / interference antenna arrays are all connected to the duplexer; the navigation deception receiving antenna array and the navigation deception transmitting antenna array are all connected to the navigation deception module;

[0023] The antenna array is used to convert the RF waveguide energy output by the transmitter into radio wave energy and radiate it into space, or to convert the incident space electromagnetic wave energy into RF waveguide energy and transmit it to the receiver.

[0024] Furthermore, it also includes a terminal module and an alarm module connected to the signal processing module;

[0025] The terminal module is used to control and dispatch each module, and display the detection results and interference signal selection; the alarm module is used to provide voice prompts for dangerous situations;

[0026] It also includes a power supply module; the power supply module is used to generate the direct current required by each module.

[0027] The present invention also discloses an intelligent integrated UAV reconnaissance and countermeasure method, which is applicable to any of the above-mentioned intelligent integrated UAV reconnaissance and countermeasure systems, and comprises:

[0028] After the system is started, it automatically enters the omnidirectional detection state and realizes long-distance detection within a 360° range. After detecting the drone signal, it generates an alarm voice to prompt the operator to use the equipment to find the direction of the target, and then starts interference suppression or navigation deception. No active human intervention is required in the whole process.

[0029] Furthermore, when in single-station working mode, the detection and receiving module in the system processes the electromagnetic signals it receives to complete the identification and direction determination of the UAV; after signal processing, the required information is intuitively displayed on the terminal module to execute the identification of the UAV; finally, for the identified UAV signal, radio countermeasures are initiated according to the preset plan, and low-power tracking interference is performed on the target with complete remote control signal detection; when only telemetry data can be detected, high-power suppression of the corresponding frequency band is turned on, and targeted suppression and countermeasures are performed according to the identification results; for unknown UAVs, their signals are recorded while suppressing and countering, and the sample library is updated after returning to the base.

[0030] Furthermore, when in multi-device networking mode, multiple devices are preferentially selected for cross-networking to cover the entire area. The network autonomously optimizes site selection, accurately locates intruding drones and pilots, and intelligently identifies drones by receiving drone radio signals. After behavioral-level threat assessment and intention deduction, corresponding processing measures are taken. For unknown drones, the signal energy threshold is used to determine whether it is a drone signal, and the target attributes are determined based on the TDOA time difference positioning principle and the characteristics of the drone signal. If it is determined to be a drone, the system intelligently generates countermeasures based on the signal characteristics and parameters of the drone, implements countermeasures and updates the sample library.

[0031] Due to the adoption of the above technical solution, the present invention has the following advantages:

[0032] (1) High efficiency and low cost in reconnaissance and countermeasures: The intelligent integrated UAV reconnaissance and countermeasures system is a system that uses artificial intelligence technology, software-defined radio technology, etc. to enhance the UAV reconnaissance and countermeasures capabilities. It can autonomously perceive environmental changes, adaptively formulate corresponding interference strategies, generate interference signals for real-time interference, and quickly respond. It has higher flexibility and adaptability.

[0033] Intelligent integrated countermeasure technology uses simple electronic or physical interference to interfere with the communication or navigation system of the drone to achieve the countermeasure purpose, with lower countermeasure cost and higher efficiency.

[0034] (2) Compared with the traditional weapon systems commonly used in the past to counter drones, the implementation of intelligent integrated reconnaissance and countermeasure system technology can respond to drone intrusion or attack more quickly and has the ability to move and deploy quickly. In addition, the system has a high degree of automation and strong modular design. There is no excessive manual intervention during use, which facilitates system upgrades and maintenance, ensuring the safety and effectiveness of personnel and equipment.

[0035] (3) Improving the ability to defend against drones: The intelligent integrated drone reconnaissance and countermeasure system has the characteristics of low cost and easy portability. Equipping an appropriate number of intelligent integrated drone reconnaissance and countermeasure equipment can improve the ability to defend against drones. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0037] Figure 1 A block diagram of an intelligent integrated UAV reconnaissance and countermeasure system according to an embodiment of the present invention;

[0038] Figure 2 A schematic diagram of a single-station workflow according to an embodiment of the present invention;

[0039] Figure 3 A schematic diagram of a networking workflow according to an embodiment of the present invention;

[0040] Figure 4 is a block diagram of a detection receiving module according to an embodiment of the present invention;

[0041] Figure 5 A schematic diagram of the structure of an interference transmission module according to an embodiment of the present invention;

[0042] Figure 6 A schematic diagram of the structure of a navigation deception module according to an embodiment of the present invention;

[0043] Figure 7 Schematic diagram of the structure of RadioImageDet algorithm according to an embodiment of the present invention;

[0044] Figure 8 A flowchart of a generative adversarial network according to an embodiment of the present invention;

[0045] Fig. 9 A schematic diagram of the basic structure of CGAN according to an embodiment of the present invention;

[0046] Fig.10 Schematic diagram of a channel switching strategy learning technology model based on a conditional generative adversarial network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The present invention is further described in conjunction with the accompanying drawings and embodiments, and the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field should fall within the scope of protection of the embodiments of the present invention.

[0048] From the working principle of reconnaissance and countermeasures, it can be seen that the existing means are mainly aimed at modeling of drone signal spectrum or known models. For targets such as low-speed, slow and small drones, the existing radio reconnaissance and countermeasures equipment are difficult to accurately identify and interfere with. The specific performance is as follows:

[0049] 1. The signal reconnaissance intelligence is low and the target cannot be accurately identified

[0050] Existing anti-UAV equipment can only identify the WIFI system signals or spectrum distribution commonly used by commercial UAVs, and cannot accurately extract signal parameters to precisely identify UAVs. The control signals of modified UAVs are modulated in a variety of ways, and their parameters must be intelligently and accurately identified in order to perform precise interference.

[0051] 2. Lack of intelligent jamming signal generation capability, resulting in significant collateral damage

[0052] In terms of countermeasures, the main method is to suppress the control and navigation signals of drones with high power. High-power jamming and suppression has limited countermeasure capabilities against autonomously navigated drones and is prone to secondary safety accidents. At the same time, high-power jamming equipment is large in size and cannot be quickly deployed at the forefront.

[0053] 3. Poor autonomous coordination and weak integration capabilities

[0054] Existing drone reconnaissance and countermeasure equipment has poor real-time and autonomous coordination. Most of them are interfered by operators using jammers or other equipment after being discovered by the detection system. They have weak integration capabilities and low intelligence levels.

[0055] In view of the problems of low intelligence level, large collateral damage, poor autonomous coordination, and weak integration capability of the above-mentioned existing reconnaissance and countermeasure means, the present invention provides an embodiment of an intelligent integrated UAV reconnaissance and countermeasure system, which breaks through the weak UAV signal extraction, measurement, and identification technology in complex electromagnetic environments and the high-speed frequency hopping signal tracking and interference technology, so that the UAV reconnaissance and countermeasure system has the capabilities of convenient carrying, flexible deployment, precise positioning, real-time tracking, and efficient countermeasure, thereby achieving confrontation advantages, improving protection capabilities, and providing reliable technical guarantees for security. The main key technologies are as follows:

[0056] (1) Intelligent identification technology of drones based on space-time-frequency multi-dimensional

[0057] Research on electromagnetic background modeling technology and weak UAV signal extraction technology in complex electromagnetic environments, extract important characteristic parameters such as frequency hopping period, hopping time, frequency hopping frequency, modulation mode of unmanned remote control signals and image transmission signals, and combine the speed, trajectory, energy and other signals of UAVs to achieve accurate identification of UAVs. On this basis, construct a multi-feature UAV communication signal sample set; integrate feature engineering methods and introduce attention mechanisms, improve deep learning algorithms such as convolutional neural networks and graph neural networks, and break through the intelligent classification and identification technology of UAV electromagnetic signals; study autonomous learning technology, automatically identify unknown UAV electromagnetic signals and update the sample library.

[0058] (2) UAV automatic jamming technology

[0059] Research countermeasure strategies for drone signals with known signal characteristics or models, establish a signal or model countermeasure strategy library, and realize automatic generation of countermeasure signals; research radio signal adversarial sample generation technology, and based on the accurate identification of unknown drone signal characteristics, intelligently generate adversarial samples, evaluate interference results and update the strategy library.

[0060] (3) Navigation and positioning intelligent jamming and deception technology

[0061] Research multi-standard navigation signal generation technology and UAV reverse track coordinate injection technology, take over the UAV navigation link, realize intelligent interference and deception of UAV navigation signals, lure the UAV to a designated location or force it to return.

[0062] (4) Integrated design technology

[0063] Research on hardware integrated design technology that integrates radio reconnaissance, interference suppression and navigation deception functions to achieve lightweight, software-based, modular and integrated design of equipment.

[0064] Figure 1This is a block diagram of the intelligent integrated UAV reconnaissance and countermeasure system. The system is mainly composed of antenna array, duplexer group, detection and reception module, jamming transmission module, navigation deception module, signal processing module, power module, display and control terminal and alarm module.

[0065] The antenna array mainly transforms the RF waveguide energy output by the transmitter through the transmission line into radio wave energy to radiate into space, or transforms the incident space electromagnetic wave energy into RF waveguide energy to transmit to the receiver. It includes detection / interference antenna array, navigation deception receiving and transmitting antenna, among which the detection / interference antenna array includes directional detection and attack integrated design antenna and omnidirectional detection antenna.

[0066] The duplexer group realizes the transmission and reception switching of the detection and interference antennas, ensuring that the receiving and transmitting systems can work normally while sharing the antenna.

[0067] Figure 4 This is a typical hardware design block diagram of a detection receiver. The detection receiving module completes the transfer of RF signals to IF signals, and the AD converter completes the conversion of analog signals to digital signals. The received RF signals are transmitted to the FPGA through a high-speed digital interface. The FPGA performs FFT processing on the collected data and then passes it to the signal processing module to complete the spectrum recognition function.

[0068] The overall design of the detection and reception module can be divided into two functional modules: the RF front-end module and the receiving digital baseband module. The RF front-end module mainly realizes the low-noise amplification and filtering functions of the weak spatial signals received by the antenna; the digital baseband module mainly realizes the mixing and analog-to-digital conversion of the filtered signal. First, the filtered RF signal and the input local oscillator signal are mixed to obtain the intermediate frequency signal, and the RF signal is moved to the intermediate frequency signal. Then, the intermediate frequency signal is amplified by the amplifier and passed through a low-pass filter, and then the analog signal is converted to a digital signal through an AD converter and transmitted to the FPGA. Finally, the FPGA converts the digital signal from the time domain to the frequency domain and hands it over to the signal processing module to complete the spectrum recognition function.

[0069] Figure 5 This is a typical jammer hardware design block diagram. The jammer module mainly generates various jammer signals and transmits them through the RF amplification link.

[0070] The overall design of the interference transmission module can be divided into two functions: the RF front-end module and the digital baseband module. The digital baseband module processes the interference waveform generated by the signal processing module through FPGA, and then uses a variety of modulation methods to mix the interference signal and the RF signal through digital-to-analog conversion (DAC) and low-pass filter; the RF front-end module mainly filters and amplifies the mixed RF signal and radiates it through the antenna array.

[0071] Figure 6 This is a typical hardware design block diagram of a navigation decoy transmitter. The navigation decoy module mainly completes the positioning and ephemeris search functions and transmits navigation deception signals.

[0072] The overall design of the navigation deception module can be divided into an RF front-end module and a digital baseband module. The RF front-end module mainly realizes low-noise amplification, filtering of the received navigation RF signal, filtering of the deceptive navigation signal, power amplification and radiation through the antenna array. The digital baseband module mainly mixes the filtered navigation RF signal and the local oscillator signal to form an intermediate frequency signal. After the intermediate frequency signal passes through low-pass filtering and analog-to-digital conversion, it is transmitted to the signal processing module after FPGA processing; the multi-standard navigation signals and drone reverse track coordinates generated by the signal processing module are sent to the FPGA for processing and clock synchronization, and after digital-to-analog conversion and low-pass filtering, the filtered deceptive navigation signal and local oscillator signal are modulated in multiple standards through the IQ modulator.

[0073] The signal processing module is mainly responsible for processing the detected and received digital signals, generating interference emission signals, processing the navigation received signals and generating navigation decoy signals, and completing the control and scheduling work between modules. It is the core algorithm processing module of the system.

[0074] The display terminal mainly controls and dispatches each module, and displays the detection results and interference signal selection.

[0075] The alarm module mainly provides voice prompts for dangerous situations.

[0076] The power module mainly generates the DC power required by each module.

[0077] The present invention also provides an embodiment of an intelligent integrated UAV reconnaissance and countermeasure method, which is applicable to the intelligent integrated UAV reconnaissance and countermeasure system described in the above embodiment, which includes detection and countermeasure, and is divided into two states: direction finding and search. After the system is started, it automatically enters the omnidirectional detection state to achieve long-distance detection within a 360° range. After detecting the UAV signal, an alarm voice is generated to prompt the operator to use the equipment to find the direction of the target, and then start interference suppression or navigation deception. The whole process does not require active human intervention.

[0078] The intelligent integrated drone reconnaissance and countermeasure system can work independently or in a multi-device network. Its main workflow is described as follows:

[0079] (1) Single station working mode

[0080] Figure 2It is the workflow of a single device. The detection receiving module in the system processes the electromagnetic signal it receives, completes the identification and direction determination of the drone, etc. After processing, the comprehensive situation will intuitively display the information such as elements and space situation on the terminal module to perform the identification of the drone. Finally, for the identified drone signal, the radio countermeasures are initiated according to the preset plan. For the target with complete remote control signal detection, low-power tracking interference can be performed, which has little impact on the surrounding electromagnetics; when only telemetry data can be detected due to location reasons, high-power suppression of the corresponding frequency band is turned on, and targeted suppression countermeasures are carried out according to the identification results.

[0081] For unknown drones, their signals are recorded while suppressing and countering them, and the sample library is updated after returning to the base.

[0082] (2) Networking working mode

[0083] Figure 3 A single device can determine whether there is a drone signal, and multiple devices can be deployed in a networked manner. The cross-network can cover the entire area. The network can automatically optimize site selection, accurately locate intruding drones and pilots, and intelligently identify drones by receiving drone radio signals, conduct behavioral-level threat assessments, and perform intention deductions before taking corresponding measures.

[0084] For unknown drones, the system intelligently generates adversarial signals based on their signal characteristics and parameters to implement countermeasures and update the sample library.

[0085] The key technologies used in this embodiment include:

[0086] (1) Radio signal recognition based on RadioImageDet algorithm

[0087] Deeply integrate artificial intelligence with traditional radio signal recognition technology, use artificial intelligence machine learning methods, especially deep learning algorithms, to automatically extract pattern features of radio waves, avoid experience-based manual feature extraction, and improve the ability to recognize radio signals in complex electromagnetic environments.

[0088] An algorithm model based on RadioImageDet is adopted. The algorithm is based on an end-to-end neural network. It can simultaneously identify the waveform types of multiple signals in the environment in a complex electromagnetic environment with time / frequency aliasing, and can locate the start and end time and frequency range of each of these signals. Figure 7 The algorithm structure.

[0089] The RadioImageDet algorithm consists of two parts: a preprocessing module and an end-to-end target detection module. The preprocessing module takes the original I / Q sampling data of the observation window as input, and transforms the time domain data into a more recognizable frequency domain expression through discrete Fourier Transform (DFT); then, after data imaging, the results of multiple consecutive DFTs are combined into a two-dimensional spectrum waterfall diagram. The end-to-end target detection module takes the spectrum waterfall diagram obtained by preprocessing as input, and obtains the concrete signal features through the CNN feature extraction layer; then, after the target detection layer, the abstract features are converted into output results with definite meanings such as signal waveform type and time / frequency coordinates. Among them, the end-to-end target detection module is implemented using an end-to-end deep neural network model. The end-to-end deep neural network model used is based on the YOLOv2 model and is constructed through transfer learning, so it is called the RadioYOLO model.

[0090] (2) Communication interference waveform generation based on generative adversarial networks

[0091] There are three common feasible ways to interfere with digital communication systems: interference with channels, interference with synchronization systems, and interference with transmitted information. Interference with channels is interference imposed on the characteristics of the demodulator, requiring the interference signal to be similar to the target signal at the signal level, that is, requiring the interference signal to have similar time domain, frequency domain, and modulation domain characteristics as the target signal, so that the interference signal can enter the input of the demodulator together with the communication signal, disrupting the threshold decision process of the demodulator, causing errors in the decision, and increasing the bit error rate (BER). The interference waveform generated by Generative Adversarial Networks (GAN) is used to interfere with the channel.

[0092] GAN is derived from game adversarial theory and consists of two parts: the generator G and the discriminator D. The function of the generator is to gradually generate outputs from the input noise Z through a series of transposed convolution (or fully connected) layers, and finally fit the generated samples G(Z) that are close to the real distribution Pdata and can deceive and interfere with the discriminator D. The discriminator D is a binary classifier that receives the samples generated by the generator and the real samples as input, and outputs a probability value to indicate whether the input sample is a real sample x or a generated sample G(Z). The two networks are constantly trained against each other. The generator continuously generates fake and real generated samples that can confuse the discriminator, and the discriminator continuously learns and improves its ability to distinguish between generated samples and real samples. The two will reach a Nash equilibrium. Finally, the generator G generates fake and real generated samples G(Z); because G(Z) approaches the real distribution, the discriminator D cannot make correct judgments on the generated samples G(Z) and the real samples x. Figure 8 Flowchart for generating adversarial networks.

[0093] (3) Channel switching strategy learning technology based on conditional GAN

[0094] During the interference process, when the communication party switches the communication channel to avoid interference, the interference party often has to observe for a period of time before it can determine the communication channel of the communication party at the next moment and switch the interference channel to implement interference, but at this time it may have missed the best time for interference. Therefore, in order to enable the interference party to adaptively learn the channel switching strategy of the communication party, predict the communication channel at the next moment, and to a certain extent, proactively interfere with the communication channel at the next moment. This technology takes the communication channel of the communication party at the current moment as the input of the generation network, and the communication channel transferred to the next moment after interference as the real sample, and trains the CGAN, so that the generation network can predict the communication channel at the next moment based on the input communication channel at the current moment.

[0095] In the original GAN, the input of the generator network is a random noise sequence, which cannot generate samples with a certain specified feature. In order to enable GAN to generate conditionally, the conditional generative adversarial network (CGAN) is introduced. Constraint conditions c are added to the generator network, the discriminator network and the real sample for marking. c can be a category label, data attribute or any other additional information. By controlling c, GAN can generate samples that meet the specified conditions. Take adding label c as an example. Fig. 9 This is the basic structure of CGAN.

[0096] Fig.10This is a channel switching strategy learning technology model based on conditional generative adversarial networks. In order to enable the generative network to learn the channel switching strategy of the target communication system and proactively predict the communication channel at the next moment, the channel switching history of the target communication system is used as a data set to train CGAN. The input of the generative network G is the communication channel at the current moment, and the output is the generated channel (that is, the communication channel at the next moment predicted by the generative network). The input of the discriminant network is the current channel and the generated channel or the current channel and the real channel at the next moment. The discriminant network will use the current channel as a condition to determine whether the input channel at the next moment is real or generated by the generative network. After training, when the network converges and the generated channel can deceive the discriminant network, it is considered that the generative network has learned the channel switching strategy of the target communication system and can predict the communication channel at the next moment.

[0097] The present invention adopts modular design ideas and combines deep learning algorithms to realize the intelligence, portability, softwareization and integration of the system, and can adapt to new targets that continue to emerge through firmware upgrades. The system integrates detection, tracking, countermeasures, navigation deception, and networking functions. A single device can realize the full process of drone management and control. It can be used by a single soldier on duty or unified command and management through a cloud platform, making up for the problems of traditional jammers without detection and inability to be uniformly managed.

[0098] The present invention combines analog channelization, digital channelization, signal fine analysis and detection technologies to achieve a small, light-weight integrated design of a wide-band signal reconnaissance and countermeasure module, which can be used as a single device or deployed through a multi-device network, such as Figures 1 to 6 shown.

[0099] The present invention proposes a method for accurately identifying drones based on space-time-frequency multi-dimensionality, performs multi-domain fine analysis on signal communication parameters, time-varying characteristics, clutter background characteristics, etc., seeks the influence and interaction between non-orthogonal signals, reveals more detailed time-frequency characteristics and geometric structure characteristics of signals, and improves the ability to accurately extract and identify drone signals. Figure 7 shown.

[0100] The present invention explores the deep-level mutual relationship between drone communication signals and adversarial sample generation, makes decisions, provides feedback, coordinates and negotiates accordingly, and relies on machine learning to form an intelligent jamming signal generation sample library to enhance drone countermeasure capabilities, such as Figures 8 to 10 shown.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An intelligent integrated drone reconnaissance and countermeasure system, characterized in that: It includes a detection receiving module, an interference transmitting module, a navigation decoy module and a signal processing module; the detection receiving module includes a radio frequency front-end module and a digital baseband module; the signal processing module is respectively connected with the detection receiving module, the interference transmitting module and the navigation decoy module; The RF front-end module is used to achieve low-noise amplification and filtering of the received weak spatial signals; the digital baseband module is used to achieve mixing and analog-to-digital conversion of the filtered signals; the interference transmission module is used to generate various interference signals and transmit them through the RF amplification link; the navigation deception module is used to complete positioning and ephemeris search, and transmit navigation deception signals; the signal processing module is used to process the detected received digital signals, generate interference transmission signals, process navigation received signals and generate navigation deception signals, and complete the control and scheduling work between the modules.

2. The intelligent integrated UAV reconnaissance and countermeasure system according to claim 1 is characterized in that: The digital baseband module consists of a mixer, an amplifier, a low-pass filter, an AD converter, and an FPGA connected in sequence; The mixer is used to mix the filtered RF signal and the local oscillator signal to obtain an intermediate frequency signal, complete the transfer of the RF signal to the intermediate frequency signal, and then amplify the intermediate frequency signal through the amplifier and input it into the low-pass filter. The AD converter then completes the conversion of the analog signal to the digital signal and transmits it to the FPGA. Finally, the FPGA converts the digital signal from the time domain to the frequency domain, and then the signal processing module completes the spectrum recognition.

3. The intelligent integrated UAV reconnaissance and countermeasure system according to claim 1 is characterized in that: The interference transmission module includes a radio frequency front-end module and an interference digital baseband module; the interference digital baseband module is composed of an FPGA, a digital-to-analog converter, a low-pass filter and a modulator connected in sequence; The FPGA is used to process the interference waveform generated by the signal processing module. After the processed signal passes through the digital-to-analog converter and the low-pass filter in sequence, the modulator mixes the interference signal and the RF signal; The RF front-end module is used to filter and amplify the mixed RF signal and transmit it through the antenna array.

4. The intelligent integrated UAV reconnaissance and countermeasure system according to claim 1 is characterized in that: The navigation deception module is composed of a radio frequency front-end module and a navigation deception digital baseband module. The radio frequency front-end module is used to perform low-noise amplification and filtering on the received navigation radio frequency signal; The digital baseband module is used to mix the filtered navigation RF signal and the local oscillator signal to form an intermediate frequency signal. The intermediate frequency signal is low-pass filtered and converted to analog-to-digital, and then processed by FPGA and transmitted to the signal processing module. After the signal processing module generates multi-standard navigation signals and UAV reverse track coordinates, they are returned to the FPGA for processing and clock synchronization, and then pass through digital-to-analog conversion and low-pass filter in turn. The filtered deception navigation signal and local oscillator signal are modulated in multiple standards through the IQ modulator. The modulated signal is filtered and power amplified by the RF front-end module before being output.

5. The intelligent integrated UAV reconnaissance and countermeasure system according to claim 1 is characterized in that: It also includes a duplexer group; the duplexer group is connected to the detection receiving module and the interference transmitting module respectively; the duplexer group is used to realize the transceiver switching of the detection and interference antennas, and ensure that the receiving and transmitting systems can work normally while sharing the antenna.

6. The intelligent integrated UAV reconnaissance and countermeasure system according to claim 5 is characterized in that: It also includes an antenna array; the antenna array includes a detection / interference antenna array, a navigation decoy receiving antenna array and a navigation decoy transmitting antenna array; The detection / interference antenna array includes a directional detection and strike integrated design antenna and an omnidirectional detection antenna; the detection / interference antenna arrays are all connected to the duplexer; the navigation decoy receiving antenna array and the navigation decoy transmitting antenna array are all connected to the navigation decoy module; The antenna array is used to convert the RF waveguide energy output by the transmitter into radio wave energy and radiate it into space, or to convert the incident space electromagnetic wave energy into RF waveguide energy and transmit it to the receiver.

7. The intelligent integrated UAV reconnaissance and countermeasure system according to claim 1 is characterized in that: It also includes a terminal module and an alarm module connected to the signal processing module; The terminal module is used to control and dispatch each module, and display the detection results and interference signal selection; the alarm module is used to provide voice prompts for dangerous situations; It also includes a power supply module; the power supply module is used to generate the direct current required by each module.

8. An intelligent integrated UAV reconnaissance and countermeasure method, applicable to the intelligent integrated UAV reconnaissance and countermeasure system according to any one of claims 1 to 7, characterized in that: include: After the system is started, it automatically enters the omnidirectional detection state and realizes long-distance detection within a 360° range. After detecting the drone signal, it generates an alarm voice to prompt the operator to use the equipment to find the direction of the target, and then starts interference suppression or navigation deception. No active human intervention is required in the whole process.

9. The intelligent integrated UAV reconnaissance and countermeasure method according to claim 8 is characterized in that: When in single-station working mode, the detection and receiving module in the system processes the electromagnetic signals it receives to complete the identification and direction determination of the UAV; after signal processing, the required information is intuitively displayed on the terminal module to execute the identification of the UAV; finally, for the identified UAV signal, radio countermeasures are initiated according to the preset plan, and low-power tracking interference is performed on the target with complete remote control signal detection; when only telemetry data can be detected, high-power suppression of the corresponding frequency band is turned on, and targeted suppression and countermeasures are performed according to the identification results; for unknown UAVs, their signals are recorded while suppressing and countering, and the sample library is updated after returning to the base.

10. The intelligent integrated UAV reconnaissance and countermeasure method according to claim 8, characterized in that: When in multi-device networking mode, multiple devices are preferentially selected to cross-network and cover the entire area. The network automatically optimizes site selection, accurately locates intruding drones and pilots, and intelligently identifies drones by receiving drone radio signals, conducts behavioral-level threat assessments, and performs intention deductions before taking appropriate measures. For unknown drones, the signal energy threshold is used to determine whether it is a drone signal, and the target attributes are determined based on the TDOA time difference positioning principle and the characteristics of the drone signal. If it is determined to be a drone, the system intelligently generates a countermeasure signal based on the drone's signal characteristics and parameters, implements countermeasures and updates the sample library.

Citation Information

Cited By

  • Small unmanned aerial vehicle investigation system and method based on weak signals

    CN119575298A

  • Small Unmanned Aerial Vehicle Reconnaissance System Based on Weak Signals and Its Method

    CN119575298B

  • Accurate interference method and system for pilot signal of remote controller of unmanned aerial vehicle

    CN119652446A

  • Unmanned aerial vehicle information level management and control method based on deep generative adversarial network

    CN120825222A

  • Unmanned aerial vehicle instruction link blocking interference method and device based on communication protocol identification

    CN121000333A