Doppler Frequency Based Artificial Intelligence Electronic Warfare Jamming System and Method Thereof

Abstract

The present invention relates to an electronic warfare (EW) system and method for disrupting an enemy's radar or guidance system by analyzing Doppler frequency shift information and generating and transmitting an optimized jamming signal using artificial intelligence (AI). The system calculates the speed and direction based on the amount of Doppler shift of a received guidance signal, and after the AI ​​classifies the threat and generates a customized jamming signal, transmits it in a specific direction through a phased array antenna to adaptively respond to various threats such as high-speed missiles, stealth drones, and swarm drones.

Description

Technology Field

[0001] Doppler-based jamming technology is an electronic warfare technology that analyzes or manipulates Doppler frequency shift information used by radar or tracking equipment to mislead the actual speed and location information of a target. The present invention relates to the field of electronic warfare technology, and more specifically, to an active electronic warfare jamming system and method that analyzes an enemy radar or guidance system based on the Doppler effect and generates and transmits rapid and accurate jamming signals using artificial intelligence. The present invention is a technology applicable not only to military electronic warfare but also to high-frequency communication security applications in the civilian sector. Background Technology

[0002] Electronic Warfare (EW) is a core technology for securing information superiority on the battlefield, and various countermeasure systems are being developed, particularly to disrupt the guidance systems of guided weapons (e.g., missiles, drones, etc.). Among these, the Digital Radio Frequency Memory (DRFM) method is the most widely used traditional jamming technique, which confuses enemy sensors by digitally storing received radar signals and then copying and reflecting them.

[0003] However, the DRFM method has the following limitations:

[0004] 1. Lack of frequency adaptability: If the target rapidly changes frequency (frequency hopping), DRFM cannot adapt in real time.

[0005] 2. Limitations of phase and direction control: Because the received signal is simply copied, it is difficult to precisely control the phase or direction of the disturbance signal.

[0006] 3. Inability to counter multiple targets: When multiple guides approach simultaneously, effective defense is difficult with a single jamming signal.

[0007] 4. Inability to Evade Intelligent Radar Analysis: Simple duplicate signals of the DRFM are highly likely to be evaded as they are analyzed and identified by the latest AI-based guidance systems. The problem to be solved

[0008] [Purpose of the Invention]

[0009] The present invention has the following technical objectives to solve the above problems:

[0010] 1. Precisely estimate the enemy's movement speed and direction using the Doppler effect.

[0011] 2. Automatically generates optimized disturbance signals through AI-based frequency / phase analysis.

[0012] 3. Use a phased array antenna to transmit precise jamming signals in the direction of a specific target.

[0013] 4. Perform intelligent disruption strategies against multiple targets simultaneously.

[0014] [Tasks to be solved and characteristics]

[0015] means of solving the problem

[0016] [Composition of the Invention]

[0017] The system of the present invention consists of the following components [Figure 1]:

[0018] 1. Doppler Analysis Module [Figure 2]

[0019] · Signal Receiver: Receives radar / search signals transmitted from the target.

[0020] · Frequency Fourier Transform (FFT): Fourier transforms the signal to calculate the frequency distribution and Doppler shift.

[0021] · Speed / Distance Estimator: Calculates relative speed and distance information based on Doppler displacement.

[0022] 2. AI Signal Analysis and Generation Module [Figure 3]

[0023] · Neural network-based classification and disturbance signal generation through signal analysis using specific algorithms or CNNs, RNNs, reinforcement learning, etc.

[0024] · Neural network-based classifier: Classifies threat levels by analyzing the characteristics (frequency, phase, intensity, etc.) of the received signal.

[0025] · Disturbance Signal Generator: Generates a disturbance signal with the most effective phase, frequency, and intensity based on the analysis results.

[0026] 3. Phase Array Control Module [Figure 4]

[0027] · Phase control circuit: Adjusts the phase for individual antenna units.

[0028] · Beamforming circuit: Precisely transmits a disturbance beam in the direction of the selected target.

[0029] 4. Directional transmitting antenna

[0030] · Phased Array Antenna: A transmitting antenna capable of direction control.

[0031] · Multiple transmission paths: Can disrupt in multiple directions simultaneously. Effects of the invention

[0032] 1. Capable of real-time response to enemy high-speed guidance systems

[0033] 2. Effective against the latest technologies such as frequency hopping and LPI (low probability of intercept).

[0034] 3. Enables 'intelligent camouflage' rather than simple reflection → Improved detection evasion

[0035] 4. Capable of AI-based autonomous disruption on the battlefield → Easy integration with unmanned combat systems

[0036] 5. Enhanced multi-target engagement capability → Enhanced realism Brief explanation of the drawing

[0037] Figure 1 is an overall system configuration diagram of the present invention. Figure 2 is a block diagram of the Doppler analysis module. Figure 3 is a flowchart of AI-based threat analysis and disturbance signal generation. Figure 4 is a diagram of the configuration and transmission direction control structure of a phase array antenna. Figure 5 is an example flowchart of a response scenario for high-speed missiles. Figure 6 is a flowchart of an example response scenario for swarm drones. Figure 7 is a block diagram of a phase array control circuit. Figure 8 is a schematic diagram showing an example of radar Doppler waveform analysis. Figure 9 is a structural diagram for calculating the directionality and transmission angle of disturbance transmission. Specific details for implementing the invention

[0038] [Example]

[0039] Example 1:

[0040] Example of jamming operation against high-speed approach missiles [Figure 5]

[0041] In a situation where an enemy guided missile approaches at supersonic speed, the electronic warfare system of the present invention operates in the following steps.

[0042] 1. Signal reception:

[0043] This system detects frequency modulated continuous wave (FMCW) induction signals received in the 8–12 GHz band. The strength of the received signal is approximately -60 dBm.

[0044] 2. Doppler Analysis:

[0045] As a result of performing FFT analysis on the received guidance signal, a frequency shift of approximately +150 kHz was detected, and based on this, the approach speed of the enemy missile was calculated to be approximately 1200 km / h. The direction was estimated to be at an angle of 23 degrees from the front relative to this system.

[0046] 3. AI Threat Analysis:

[0047] The AI-based analysis module classified the corresponding Doppler frequency and signal characteristics as a high-speed radar-guided missile and identified it as a priority target.

[0048] 4. Generation of disturbance signals:

[0049] The disturbance signal was generated as a Linear Frequency Modulation (LFM) signal with phase randomization and spectrum spreading techniques applied, and a Doppler correction algorithm was applied.

[0050] 5. Transmission:

[0051] The generated jamming signal transmitted a highly directional beam at a 23-degree forward direction through a phased array antenna. As a result, the enemy missile suffered a guidance error and deviated from its course.

[0052] 6. Disruption Scenario for High-Speed ​​Approach Missiles

[0053] The jamming system of the present invention may include a scenario in which, in a situation where an enemy missile approaches using a Ka-band (34.2 GHz) LPI (low probability of intercept) signal, the relative speed of the enemy missile is calculated in real time by analyzing the amount of Doppler shift of the enemy missile to be 900 m / s and the angle of approach is 35 degrees, and based on this, a CNN-based AI classifies the signal as a “high-speed evasion type waveform,” and generates and transmits a jamming waveform using 3D beamforming technology within 0.6 ms, thereby causing a guidance error.

[0054]

[0055] Example 2: Example of a response to a mass intrusion by swarm drones

[0056] In a situation where five enemy drones simultaneously enter as a group, the system of the present invention responded with the following procedure.

[0057] 1. Signal reception:

[0058] Multiple signals with different phases and frequencies were received simultaneously. These were confirmed to be guidance signals generated from each drone.

[0059] 2. Doppler Analysis:

[0060] The Doppler shift of each received signal was as follows:

[0061] o Drone A: +22kHz [Drone actually holding a bomb]

[0062] o Drone B: +21kHz

[0063] o Drone C: +20kHz

[0064] o Drone D: +23kHz

[0065] Based on this, the relative speed and position of each drone were mapped.

[0066] 3. AI Analysis:

[0067] The AI ​​analysis module analyzed this distribution and pattern as a cluster tactic and identified the central drone A as a communication hub, setting it as a priority target for disruption.

[0068] 4. Generation of disturbance signals:

[0069] For each drone, customized electronic warfare signals containing different frequency modulations and phase disturbances were generated. They were also designed to induce communication interference within the swarm.

[0070] 5. Transmission:

[0071] The phased array antenna utilized a multi-beamforming technique to simultaneously form four directional beams, thereby performing simultaneous disturbance on each drone. As a result, communication failures and collisions occurred between the drones.

[0072] 6. Disruption Behavior Scenario During Multi-Drone Approach

[0073] [Drawing Figure 6]

[0074] Example 3: Stealth Drone Detection and Response Example [Drawing 7]

[0075] In a situation where an enemy drone (A) equipped with stealth capabilities approaches covertly at a low altitude, the electronic warfare system of the present invention operates in the following steps:

[0076] 1. Signal reception stage

[0077] · Signals that are difficult to identify with conventional radar -85 dBm Detected at the level

[0078] · The signal in question is LPI (Low Probability of Interception) Having characteristics,

[0079] → Attempts to evade detection through methods such as frequency hopping and spectrum spreading.

[0080] · The received signal is A level close to noise Therefore, it is difficult to distinguish using a general system.

[0081] 2. Doppler Analysis

[0082] 2-1. Received Signal Information

[0083] · Received power: -85 dBm

[0084] · Signal Type: LPI signal

[0085] · Doppler shift: +5 kHz

[0086] 2-2. Analysis Method

[0087] Doppler analysis is used when the transmitter approaches the receiver Increase in frequency And, if you leave decrease Utilizes the principle of doing.

[0088] · Doppler shift calculation formula:

[0089]

[0090] Δf: change in frequency ( +5 kHz )

[0091] v: Target velocity (value to be calculated)

[0092] f0: Center frequency of the transmitted signal ( 34.2 GHz, Ka-band )

[0093] θ: Approach angle ( 63° )

[0094] c: speed of light ( 3 × 10 8 m / s )

[0095] · Speed ​​calculation:

[0096]

[0097] · Consequently, the approach speed was analyzed to be in the range of approximately 50–70 km / h.

[0098] · The lateral approach direction is estimated to be 63 degrees.

[0099] 3. AI-based threat analysis

[0100] · The AI ​​module, along with previously learned threat patterns Abnormal difference recognize

[0101] · Anomaly Detection By applying the algorithm

[0102] → Classify the signal as a stealth approach attempt

[0103] 4. Generation of disturbance signals [Drawing 10]

[0104] · Generates a signal in the form of spread-spectrum radar noise

[0105] · AI infuses DRFM and uses CNNs to generate Adaptive Jamming jamming signals to track guided missiles and radars; utilizes Generative Adversarial Networks (GANs) and Long Short Term Memory (LSTMs) to emit False Target Echo signals to confuse target detection systems; uses DRFM to generate Coherent Replays for jamming; employs GANs and Autoencoders for LPI (Low Probability of Intercept)-Like Noise jamming to evade detection; uses Adversarial AI to emit Feature Masking signals to neutralize AI-based detection; uses a Chaos Generator to impart Time Chaos signal camouflage characteristics to evade filter tracking; and generates Cognitive Jamming jamming signals through response analysis via AI reinforcement learning, thereby causing confusion in the drone's signal receiver.

[0106] 5. Transmission of jamming signal

[0107] · Calculation required for phased array antenna transmit angle control structure [Figure 9]

[0108] · Transmits a directional beam in a 63-degree lateral direction using a phased array antenna

[0109] · A stealth drone responds to a mistaken guidance signal

[0110] → Induces a result of changing direction or colliding with terrain

[0111] 6. Example of Stealth Function Detection and Response Scenario.

[0112] The figure below is a schematic diagram visualizing the intelligent response procedure (detection → analysis → disruption) of an electronic warfare system at a glance, which is a diagram that very effectively explains how AI-based adaptive disruption works.

[0113]

[0114] 7. Actual radar waveform analysis spectrum image.

[0115] The graph in [Figure 8] shows the results of radar waveform analysis simulated based on an actual stealth drone scenario (Doppler +5kHz, -85dBm signal strength):

[0116] · The first graph of Figure 8 shows the received signal in the time domain, and contains Doppler modulation within a weak signal close to noise.

[0117] · The second graph in Figure 8 is the result of FFT analysis. When the reception time and amplitude of the signal are converted using a frequency converter, a Doppler shift is observed where energy is concentrated at the +5kHz point in cases like this example.

[0118] [Other Matters]

[0119] · Application platforms: Fighter jets, drones, warships, tanks, anti-aircraft weapon systems, etc.

[0120] · Compatible Technologies: Can be integrated with GPS jamming, LIDAR interference, RF spoofing, etc.

[0121] · Can be utilized as a component of next-generation electronic warfare systems

[0122] · Maintenance / Calibration Module, Simulation Test Platform, Training Sample Dataset Structure Industrial applicability

[0123] The present invention belongs to the field of electronic warfare technology and relates to an active jamming system and method that calculates the speed and direction of an enemy based on Doppler frequency shift information, classifies threats using artificial intelligence (AI), and transmits an adaptive jamming signal through a phased array antenna.

[0124] The present invention is applicable to the following industrial fields.

[0125] First, it can be utilized as electronic warfare equipment mounted on military aircraft, unmanned aerial vehicles (UAVs), and missile defense systems, and has high potential for industrial use as an active defense system capable of responding to the latest guided weapons such as high-speed missiles, stealth drones, and swarm drones.

[0126] Second, it can be applied as an anti-drone system or communications security system at airports and critical infrastructure, and can also be applied in civilian security systems through its ability to identify and block threats to wireless communications.

[0127] Third, autonomous jamming systems utilizing AI-based threat analysis and signal generation can be integrated into next-generation defense technologies, particularly Autonomous Weapon Systems (LAWS) and sensor-shooter integrated systems, and can be utilized in the intelligent defense solutions industry, where demand is increasing globally.

[0128] The present invention is considered to be a technology that is feasible at the current level of technology and applicable to various defense and security industries, as its components consist of technical elements already widely used industrially (RF receivers, FFT analyzers, AI classifiers, phased array antennas, etc.), allowing for repetitive manufacturing and operation.

[0129] Therefore, the present invention is recognized as having industrial applicability pursuant to Article 29, Paragraph 1, Subparagraph 3 of the Patent Act.

[0130] [Differences from existing technology]

[0131] Accordingly, the present invention overcomes the limitations of existing technology and implements adaptive electronic warfare jamming technology by analyzing relative movement based on the Doppler effect in real time, classifying guidance signals by type using artificial intelligence, and generating and transmitting a jamming waveform optimized for them.

Claims

Claim 1 An electronic warfare jamming system based on Doppler frequency and artificial intelligence comprises: (a) a Doppler analysis module that calculates the frequency shift of a received signal and calculates the relative speed and direction therefrom; (b) an artificial intelligence-based signal analysis and generation module that classifies the received signal based on the Doppler analysis results and generates a jamming signal corresponding thereto; (c) a phase array control module that controls the antenna phase to transmit the jamming signal in a specific direction; and (d) a directional transmitting antenna that transmits multiple jamming signals in a selected direction using a phase array method, wherein the system is characterized by real-time analysis of an enemy's guidance signal and intelligent jamming signal generation based on the Doppler effect. An example of the system according to claim 1 is illustrated in [Figure 1]. Claim 2 An electronic warfare jamming method based on Doppler frequency and artificial intelligence comprises: (a) receiving a guidance signal from an enemy guidance system; (b) analyzing the amount of Doppler shift of the received signal to estimate relative velocity and direction; (c) analyzing the waveform of the received signal using artificial intelligence to analyze its characteristics, classifying it by type, and generating a jamming waveform with optimized frequency, phase, amplitude, directivity, duration, etc.; (d) generating an 'adaptive' jamming signal according to the analyzed information; and (e) transmitting the jamming signal in a specific target direction using a phase array antenna, wherein the jamming signal has phase and frequency characteristics that reflect the Doppler effect. An example of the system according to claim 2 is illustrated in [Figures 5 and 7]. Claim 3 A case in which the analysis module includes a CNN or reinforcement learning-based neural network structure and is characterized by classifying threat signals according to the characteristics of the received signal and calculating a disruption strategy optimized therefor. An example of the system according to Claim 3 is illustrated in [Figure 3]. Claim 4 AI-based phased array antenna control system An AI-based phased array antenna control system comprising: (a) a signal receiving module that receives an electromagnetic wave signal entering from the outside and extracts information on the Doppler shift amount, received power, and direction; (b) an AI-based control module that analyzes the characteristics of the received signal to classify the type of threat and calculates an optimized beam divergence angle and a directing angle according to the classification result; (c) a phased array antenna control module that adjusts the phase of multiple antenna elements based on phase and amplitude control values ​​provided by the AI-based control module and transmits a disturbance signal with a selected directing angle and beam width; and (d) a disturbance signal generator that generates a disturbance signal in the form of a spectrum spread, LPI-responsive type, or false target reflection wave according to the type of threat analyzed by the AI, wherein the system adjusts the beam divergence in real time according to the result of the threat signal analysis to perform optimized directional disturbance for a single or multiple targets. An example of the system according to claim 4 is illustrated in [Figures 4 and 9]. Claim 5 In the case where the disturbance signal includes spectrum dispersion technology (SDR) for LPI response, an example of the system according to claim 5 is illustrated in [Figure 10]. Claim 6 An electronic warfare jamming method based on Doppler frequency and artificial intelligence, comprising: (a) receiving a guidance signal or LPI signal from an enemy guidance system or a stealth approach; (b) analyzing the Doppler shift amount, reception direction, and power of the received signal to generate a feature vector that can be input to an AI analysis module; (c) classifying the threat type of the signal through a CNN or reinforcement learning-based artificial intelligence analysis module and determining an optimized jamming waveform type, directional angle, and beam divergence angle according to the threat analysis result; (d) applying a phase difference according to the result to a phase array antenna to transmit a directional jamming signal in a set direction; (e) the jamming signal comprises at least one of a spectrum spread signal, a False Echo signal, a Coherent Replay signal, an LPI pseudo-noise signal, or a Feature Masking signal, and the method is characterized by repeatedly generating an adaptive jamming signal according to the threat type and response pattern. An example of a system according to claim 6 is illustrated in [Figures 7 and 8]. Claim 7 A method according to claim 6, wherein the artificial intelligence analysis module combines a CNN-based classifier and a reinforcement learning-based strategy selector for an input feature vector to select an optimal disturbance strategy based on threat attributes and response prediction. An example of a system according to claim 7 is illustrated in [Figure 3]. Claim 8 A method according to claim 8, wherein the phase array antenna has an N×M array structure and beamforming is performed by calculating the phase difference (Δφ) according to the directional angle (θ) and element spacing (d), is illustrated as an example in [Figure 9]. Claim 9 The method of claim 6 further comprises the step of receiving compensation feedback according to an enemy's response (e.g., guidance change, signal pattern change, etc.) and updating the waveform, phase, or direction angle of the disturbance signal in real time through a reinforcement learning-based algorithm. An example of the system according to claim 9 is illustrated in [Figure 10].

Images