An adaptive control method and system for low-altitude targets

Abstract

The present invention belongs to the technical field of unmanned aerial vehicle (UAV) countermeasures and discloses an adaptive control method and system for low-altitude targets. The method comprises: collecting radar scanning information of the low-altitude target, performing feature extraction on the radar scanning information to obtain position features; collecting a target image of the low-altitude target, performing feature extraction on the target image to obtain the number of rotors, fuselage shape and color features; and comparing the image with a pre-stored color library to obtain the color of the low-altitude target; collecting a thermal radiation image and a signal frequency band; performing feature extraction on the thermal radiation image to obtain a thermal feature; performing feature extraction on the signal frequency band to obtain an electronic fingerprint; using the number of rotors, fuselage shape, thermal features and electronic fingerprint as inputs of a model analysis model to obtain the model of the low-altitude target. The present invention dynamically calculates a threat score through a trajectory analysis model, triggers the coordination of multiple countermeasures through the threat score, and effectively improves the interference coverage efficiency and the target recognition accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of UAV countermeasures, and more particularly to an adaptive control method and system for low-altitude targets. Background Art

[0002] With the popularization of drone technology and the development of hypersonic weapons, low-altitude targets are becoming more “low, slow, small”, stealthy and intelligent.

[0003] Patent application publication number CN114911267A discloses an intelligent autonomous drone countermeasure system, comprising an AI-enabled network attack module, an intelligent drone netting module, a GPS navigation decoy module, and a multi-band radio interference suppression module. The AI-enabled network attack module is used to host intelligent devices, invoke attack tools, and exploit software vulnerabilities to cut off the Wi-Fi link between the controller and the drone, enabling takeover of intruding drones. The intelligent drone netting module is used to autonomously track drones and launch drone nets for automated operations. The GPS navigation decoy module is used to generate navigation decoy signals to lure drones to a preset location. The multi-band radio interference suppression module is used to generate multi-band suppression signals to block communications between drones and user terminals. This technical solution, through multi-mode deployment, enables unmanned operation, accurately repelling or forcing intruding drones to land, and ensuring low-altitude airspace security.

[0004] Although the above method can meet most scenarios, research and practical application of the above method and existing technology have found that the above method and existing technology have at least the following defects:

[0005] There is a lack of dynamic countermeasures based on threat assessment through identification of low-altitude targets.

[0006] In view of this, the present invention proposes an adaptive control method and system for low-altitude targets to solve the above problems. Summary of the Invention

[0007] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: an adaptive control method for low-altitude targets, comprising the following steps:

[0008] Collect radar scanning information of low-altitude targets and extract features from the radar scanning information to obtain position features;

[0009] Collect target images of low-altitude targets, extract features from the target images, obtain the number of rotors, fuselage shape and color features; and compare them with the pre-stored color library to obtain the color of the low-altitude targets;

[0010] Collect the signal frequency bands of low-altitude targets received by the preset N collection points, analyze them, and calculate the pilot's position;

[0011] Collect thermal radiation images; extract features from thermal radiation images to obtain thermal signatures; extract features from signal frequency bands to obtain electronic fingerprints; use the number of rotors, fuselage shape, thermal signatures, and electronic fingerprints as inputs to the model analysis model to obtain the model of the low-altitude target;

[0012] Perform matching analysis on the electronic fingerprint to obtain a matching result; if the matching result is an unknown target, the location characteristics, color, thermal characteristics and model are used as inputs to the trajectory analysis model to obtain a threat score;

[0013] Collect environmental data. If the threat score exceeds the preset threat threshold, the aircraft will adopt a countermeasure mode to counter low-altitude targets through a dynamic defense strategy based on environmental data, location characteristics, color, thermal characteristics, model, and pilot position.

[0014] Furthermore, the method for obtaining an electronic fingerprint includes:

[0015] Passively receive the transmission signal of the low-altitude target, extract the serial number, MAC address, signal modulation mode and frame structure of the transmission signal of the low-altitude target, and detect whether the transmission signal of the low-altitude target is a forged signal based on the detection strategy. If it is a forged signal, directly activate the dynamic defense strategy and adopt the countermeasure mode. If it is not a forged signal, perform spectrum analysis and quantization on the transmission signal of the low-altitude target, extract the carrier frequency offset and phase noise, splice the carrier frequency offset and phase noise as the signal fingerprint, extract the heartbeat packet sending interval and data packet length distribution, splice the heartbeat packet sending interval and data packet length distribution as the behavioral fingerprint, quantify the signal characteristics through the statistical model, and use the signal fingerprint and behavioral fingerprint as the input of the fingerprint analysis model to obtain the electronic fingerprint. The detection strategy includes monitoring whether the carrier frequency of the transmission signal of the low-altitude target has frequency drift, comparing whether the signal modulation mode matches the pre-stored device protocol library, monitoring whether the signal strength exceeds the preset strength threshold, and monitoring whether the pilot's position is within the preset authorized area. If any of the detection results are yes, it is judged to be a forged signal, otherwise it is not a forged signal.

[0016] Furthermore, the method for obtaining the threat score includes:

[0017] The electronic fingerprint is compared with the pre-stored database to obtain the matching result corresponding to the low-altitude target. The matching result includes the unknown fingerprint and the whitelist and blacklist stored in the pre-stored database. When the matching result is the whitelist, it is released. When the matching result is the blacklist, the dynamic defense strategy is immediately triggered to adopt the countermeasure mode; when the matching result is an unknown fingerprint, the electronic fingerprint corresponding to the low-altitude target is stored in a temporary library, and the position characteristics, color, thermal characteristics and model are used as inputs of the trajectory analysis model to obtain the threat score.

[0018] Furthermore, the method for countering low-altitude targets includes:

[0019] Define the state space S: Obtain threat scores, signal frequency bands, and environmental data; environmental data includes wind speed, temperature, precipitation, electromagnetic interference intensity, and terrain obstruction coefficient;

[0020] Define action space A: Select the jamming signal frequency band and power level, generate false GPS coordinates that deviate from the preset no-fly zone, adjust the gimbal angle based on the angle of the low-altitude target, and activate the corresponding frequency band for interception. The actions in the action space also include combined actions.

[0021] Design reward function: Obtain the total reward function based on the weighted combination of counterattack success reward, energy consumption penalty, accidental injury penalty, and environmental adaptation reward;

[0022] Update the Q-value function: Use the Q-learning algorithm to learn the optimal strategy, initialize the Q-value function as a table, and the rows of the table correspond to different environmental states , columns correspond to different actions , set the learning rate , discount factor and exploration rate ; At each time step , detect the current environment status , according to the exploration rate ,by The probability of randomly choosing an action ,by The probability of selecting the action with the largest Q value in the current environment state ; Execute the selected action and obtain the new environment state At the same time, the total reward function value is calculated according to the reward function; the Q value function is updated according to the update formula;

[0023] Repeatedly update the Q-value function until the Q-value converges to obtain the corresponding optimal Q-value function. According to the environmental state, use the optimal Q-value function to select the optimal action from the action space and execute it.

[0024] Furthermore, the method for obtaining the pilot's position includes:

[0025] Obtain the coordinates of the acquisition points and the arrival time of the received signal, calculate the time difference between any two acquisition points, construct a hyperbola equation based on the time difference and coordinates, solve the hyperbola equation through an iterative algorithm, and obtain the pilot's coordinates.

[0026] Furthermore, the method for obtaining thermal characteristics includes:

[0027] The thermal radiation image is converted into a grayscale or pseudo-color image, in which the highlighted area corresponds to the high-temperature area. The image is segmented based on a preset segmentation threshold, and each independent heat source is marked based on the connected domain analysis to obtain the number of independent heat sources. The temperature values ​​corresponding to the pixel points of each independent heat source are traversed, and the maximum temperature value of each independent heat source is recorded. The maximum temperature value of each independent heat source is collected once at a preset time interval, and the average temperature change rate of each independent heat source is calculated; the number of independent heat sources, the maximum temperature value of each independent heat source, and the average temperature change rate of each independent heat source are spliced ​​as thermal features.

[0028] Furthermore, the method for obtaining the number of rotors includes:

[0029] Perform edge detection on the target image to extract the low-altitude target contour. Then use linear structuring elements and square structuring elements to erode the low-altitude target contour in sequence to obtain the eroded low-altitude target contour. Count the number of connected areas in the eroded low-altitude target contour, and combine it with the rotor symmetry judgment to obtain the first rotor number.

[0030] Collect Doppler frequency shift and obtain the number of the second rotor through spectrum analysis;

[0031] The first number of rotors and the second number of rotors are cross-validated. If the first number of rotors and the second number of rotors are the same, the values ​​of the first number of rotors and the second number of rotors are used as the number of rotors. If the first number of rotors and the second number of rotors are different, manual review or dynamic resampling is triggered to obtain the number of rotors.

[0032] Furthermore, the method for obtaining the color of the low-altitude target includes:

[0033] The color features of the low-altitude target are extracted by analyzing the target image through RGB pixels, and compared with the pre-stored color library to obtain the color of the low-altitude target.

[0034] Furthermore, the method for obtaining the fuselage shape includes:

[0035] Perform target detection on the target image, separate the target foreground, and use the target foreground as the input of the shape analysis model to obtain the fuselage shape.

[0036] Furthermore, the position features include three-dimensional position information, speed, and heading; and the method for obtaining the position features includes:

[0037] Step 1: Collect the time difference between the transmitted electromagnetic wave and the received electromagnetic wave, and calculate the distance of the low-altitude target based on the electromagnetic wave transmission speed;

[0038] Step 2: Calculate the low-altitude target speed by combining the radar transmission frequency and the Doppler shift of the reflected signal;

[0039] Step 3: Control the mechanical rotating antenna or the electronic scanning beam to point in different directions to calculate the direction of the low-altitude target; combine the distance of the low-altitude target to obtain the three-dimensional position information of the low-altitude target; the three-dimensional position information includes longitude, latitude and altitude;

[0040] Step 4: Repeat steps 1 to 3 at preset intervals to obtain second and third-dimensional position information of the low-altitude target, calculate a displacement vector between the second and third-dimensional position information and the third-dimensional position information, and calculate the heading of the low-altitude target based on an inverse tangent function combined with the displacement vector.

[0041] Step 5: Calculate the modulus of the displacement vector, calculate the ratio of the modulus to the preset time period, and obtain the speed of the low-altitude target.

[0042] An adaptive control system for a low-altitude target, implementing the adaptive control method for a low-altitude target, comprising:

[0043] Position analysis module: collects radar scanning information of low-altitude targets and extracts features from the radar scanning information to obtain position features;

[0044] Color analysis module: collects target images of low-altitude targets, extracts features from the target images, obtains the number of rotors, fuselage shape and color features; and compares the images with the pre-stored color library to obtain the color of the low-altitude targets;

[0045] Source tracing analysis module: collects and analyzes the signal frequency bands of low-altitude targets received by N preset collection points, and calculates the pilot's position;

[0046] Model analysis module: collects thermal radiation images; extracts features from thermal radiation images to obtain thermal signatures; extracts features from signal frequency bands to obtain electronic fingerprints; uses the number of rotors, fuselage shape, thermal signatures, and electronic fingerprints as inputs to the model analysis model to obtain the model of the low-altitude target;

[0047] Threat Analysis Module: This module performs matching analysis on electronic fingerprints to obtain matching results. If the matching result is an unknown target, the location characteristics, color, thermal characteristics, and model are used as inputs to the trajectory analysis model to obtain a threat score.

[0048] Intelligent countermeasure module: Collects environmental data. If the threat score exceeds the preset threat threshold, it will adopt a countermeasure mode to counter low-altitude targets through dynamic defense strategies based on environmental data, location characteristics, color, thermal characteristics, model and pilot position.

[0049] The technical effects and advantages of the adaptive control method and system for low-altitude targets of the present invention are as follows:

[0050] The present invention integrates four-dimensional perception data of radar, vision, thermal infrared and electromagnetic signals to build an intelligent defense system with full-spectrum feature fusion: radar scanning identifies centimeter-level position features, visual recognition achieves accurate classification of the number of rotors and fuselage shape, and thermal features and electronic fingerprints form a device-level unique identification to achieve accurate identification of low-altitude targets and precise positioning of the pilot's position; the system dynamically calculates the threat score through a trajectory analysis model, and triggers the coordination of multiple countermeasures through the threat score, effectively improving the interference coverage efficiency and target recognition accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 Schematic diagram of a flow chart of an adaptive control method for a low-altitude target according to the present invention;

[0052] Figure 2 Schematic diagram of the process of the method for countering low-altitude targets of the present invention;

[0053] Figure 3 Schematic diagram of the process of the dynamic defense strategy optimization method of the present invention;

[0054] Figure 4 This is a structural diagram of an adaptive control system for low-altitude targets according to the present invention. DETAILED DESCRIPTION

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0056] Example 1

[0057] See also Figure 1 As shown, the adaptive control method for a low-altitude target described in this embodiment includes the following steps:

[0058] Collect radar scanning information of low-altitude targets and extract features from the radar scanning information to obtain position features. Radar scanning information includes electromagnetic waves transmitted to low-altitude targets and the corresponding transmission time, and reflected signals received from low-altitude targets and the corresponding reception time. Position features include three-dimensional position information, speed, and heading.

[0059] Methods for obtaining location features include:

[0060] Step 1: Collect the time difference between the transmitted electromagnetic wave and the received electromagnetic wave, and calculate the distance of the low-altitude target based on the electromagnetic wave transmission speed;

[0061] Step 2: Calculate the low-altitude target speed by combining the radar transmission frequency and the Doppler shift of the reflected signal;

[0062] Step 3: Control the mechanical rotating antenna or the electronic scanning beam to point in different directions to calculate the direction of the low-altitude target; combine the distance of the low-altitude target to obtain the three-dimensional position information of the low-altitude target; the three-dimensional position information includes longitude, latitude and altitude;

[0063] Step 4: Repeat steps 1 to 3 at preset intervals to obtain second and third-dimensional position information of the low-altitude target, calculate a displacement vector between the second and third-dimensional position information and the third-dimensional position information, and calculate the heading of the low-altitude target based on an inverse tangent function combined with the displacement vector.

[0064] Step 5: Calculate the modulus of the displacement vector, calculate the ratio of the modulus to the preset time period, and obtain the speed of the low-altitude target.

[0065] Positional features play a core supporting role in low-altitude defense. Target location, speed, and other locational features acquired through radar scanning not only provide a spatiotemporal basis for multi-sensor data fusion, enabling continuous tracking and prediction of target trajectory, but also serve as input parameters for pilot positioning algorithms, enabling precise location of transmitters when combined with signal fingerprint analysis. Furthermore, positional features contribute to the construction of threat assessment models, calculating threat scores alongside trajectory features and environmental data, providing a quantitative basis for triggering thresholds in dynamic defense strategies. Furthermore, in distributed collaborative defense, positional features can support the optimal scheduling of countermeasure resources, achieving precise interference coverage through a multi-node interference power allocation model.

[0066] Collect target images of low-altitude targets, extract features from the target images, and obtain the number of rotors, fuselage shape and color features; and compare them with the pre-stored color library to obtain the color of the low-altitude target; target image feature extraction plays a multi-dimensional supporting role in low-altitude defense disposal: through the identification of the number of rotors, the types of multi-rotor and fixed-wing drones can be quickly distinguished, and the target model can be further locked in combination with the fuselage shape analysis; the comparison of color features with the pre-stored library can assist in identifying camouflage or specific ownership, and at the same time provide a visual verification benchmark for multi-sensor data fusion; these features are jointly input into the model analysis model, which can effectively improve the accuracy of target identity discrimination, and update the threat assessment model through dynamic matching of color features, realizing cross-validation of target attributes and behavior patterns in complex environments, and providing a key basis for the accurate triggering of countermeasures.

[0067] Methods for obtaining the number of rotors include:

[0068] Perform edge detection on the target image to extract the low-altitude target contour. Then use linear structuring elements and square structuring elements to erode the low-altitude target contour in sequence to obtain the eroded low-altitude target contour. Count the number of connected areas in the eroded low-altitude target contour, and combine it with the rotor symmetry judgment to obtain the first rotor number.

[0069] Collect Doppler frequency shift and obtain the number of the second rotor through spectrum analysis;

[0070] The first number of rotors and the second number of rotors are cross-validated. If the first number of rotors and the second number of rotors are the same, the values ​​of the first number of rotors and the second number of rotors are used as the number of rotors. If the first number of rotors and the second number of rotors are different, manual review or dynamic resampling is triggered to obtain the number of rotors.

[0071] Methods for obtaining the fuselage shape include:

[0072] Perform target detection on the target image, separate the target foreground, and use the target foreground as the input of the shape analysis model to obtain the fuselage shape.

[0073] The training methods for the shape analysis model include:

[0074] F groups of shape analysis data are collected in advance, and the shape analysis data include the target foreground and the corresponding fuselage shape.

[0075] The target foreground is used as the input of the shape analysis model, and the corresponding fuselage shape is used as the output of the shape analysis model. The goal is to minimize the error between the output corresponding fuselage shape and the actual corresponding fuselage shape. The network parameters of the shape analysis model are optimized through a nature-inspired optimization algorithm to obtain the network parameters that minimize the error between the corresponding fuselage shape output by the shape analysis model and the actual corresponding fuselage shape. The shape analysis model constructed with the corresponding network parameters is used as the trained shape analysis model.

[0076] Methods for obtaining the color of low-altitude targets include:

[0077] The color features of the low-altitude target are extracted by analyzing the target image through RGB pixels, and compared with the pre-stored color library to obtain the color of the low-altitude target.

[0078] The signal frequency bands of low-altitude targets received by N preset collection points are collected and analyzed to calculate the pilot's position; by accurately locking the position of the drone operator, a spatial reference can be provided for countermeasures; the pilot's position information is combined with the target trajectory characteristics to dynamically evaluate the threat radiation range (such as the coverage radius of sensitive areas) and optimize the interference resource allocation strategy; at the same time, the precise positioning results provide a key chain of evidence when evidence collection is required, and combined with electronic fingerprint matching to achieve the "man-machine-signal" ternary association, reduce the probability of accidental injury, and significantly improve the compliance of the action while ensuring the effectiveness of the countermeasures.

[0079] Methods for obtaining the pilot position include;

[0080] Obtain the coordinates of the acquisition points and the arrival time of the received signal, calculate the time difference between any two acquisition points, construct a hyperbola equation based on the time difference and coordinates, solve the hyperbola equation through an iterative algorithm, and obtain the pilot's coordinates.

[0081] Collect thermal radiation images; extract features from thermal radiation images to obtain thermal features; extract features from signal frequency bands to obtain electronic fingerprints; use the number of rotors, fuselage shape, thermal features and electronic fingerprints as inputs to the model analysis model to obtain the model of the low-altitude target; thermal radiation images and signal frequency band features provide key judgment basis in low-altitude defense disposal: thermal features can effectively distinguish the type of drone and locate the position of the heat source, combined with the device-level unique recognition capability of electronic fingerprints, and form multi-modal feature fusion with the number of rotors and fuselage shape, which can effectively improve the accuracy of the model analysis model; among them, electronic fingerprint matching not only realizes the rapid identification of known models, but also triggers the threat assessment process through unknown target detection, providing model traceability and threat classification support for dynamic defense strategies, and improving target recognition accuracy by more than 30% compared with traditional single feature recognition, while providing data support for the accurate selection of countermeasures.

[0082] Methods for obtaining thermal signatures include:

[0083] The thermal radiation image is converted into a grayscale or pseudo-color image, wherein the highlighted area (such as the corresponding temperature value is greater than the preset temperature threshold) corresponds to the high temperature area. The image is segmented based on the preset segmentation threshold, and each independent heat source is marked based on the connected domain analysis to obtain the number of independent heat sources. The temperature values ​​corresponding to the pixel points of each independent heat source are traversed, and the maximum temperature value of each independent heat source is recorded. The maximum temperature value of each independent heat source is collected once at a preset time interval, and the average temperature change rate of each independent heat source is calculated; the number of independent heat sources, the maximum temperature value of each independent heat source, and the average temperature change rate of each independent heat source are spliced ​​as thermal features.

[0084] Methods for obtaining electronic fingerprints include:

[0085] Passively receive the transmission signal of the low-altitude target, extract the serial number, MAC address, signal modulation mode and frame structure of the transmission signal of the low-altitude target, and detect whether the transmission signal of the low-altitude target is a forged signal based on the detection strategy. If it is a forged signal, directly activate the dynamic defense strategy and adopt the countermeasure mode. If it is not a forged signal, perform spectrum analysis and quantization on the transmission signal of the low-altitude target, extract the carrier frequency offset and phase noise, splice the carrier frequency offset and phase noise as the signal fingerprint, extract the heartbeat packet sending interval and data packet length distribution, splice the heartbeat packet sending interval and data packet length distribution as the behavioral fingerprint, quantify the signal characteristics through the statistical model, and use the signal fingerprint and behavioral fingerprint as the input of the fingerprint analysis model to obtain the electronic fingerprint. The detection strategy includes monitoring whether the carrier frequency of the transmission signal of the low-altitude target has frequency drift, comparing whether the signal modulation mode matches the pre-stored device protocol library, monitoring whether the signal strength exceeds the preset strength threshold, and monitoring whether the pilot's position is within the preset authorized area. If any of the detection results are yes, it is judged to be a forged signal, otherwise it is not a forged signal.

[0086] The training methods for the model analysis model include:

[0087] Collect Group B training data in advance. The training data includes model analysis data and corresponding models; model analysis data includes the number of rotors, fuselage shape, thermal characteristics, and electronic fingerprints;

[0088] The model analysis data is used as the input of the model analysis model, and the model is used as the output of the model analysis model. The goal is to minimize the error between the output model and the actual model. The network parameters of the model analysis model are optimized through the nature-inspired optimization algorithm to obtain the network parameters that minimize the error between the model output by the model analysis model and the actual model. The model analysis model constructed with the corresponding network parameters is used as the trained model analysis model.

[0089] The training methods for the fingerprint analysis model include:

[0090] Collect C group of fingerprint training data in advance. The fingerprint training data includes signal fingerprint and behavior fingerprint, as well as the corresponding electronic fingerprint;

[0091] The fingerprint training data is used as the input of the fingerprint analysis model, and the electronic fingerprint is used as the output of the fingerprint analysis model. The goal is to minimize the error between the output electronic fingerprint and the actual electronic fingerprint. The network parameters of the fingerprint analysis model are optimized through a nature-inspired optimization algorithm to obtain the network parameters that minimize the error between the electronic fingerprint output by the fingerprint analysis model and the actual electronic fingerprint. The fingerprint analysis model constructed with the corresponding network parameters is used as the trained fingerprint analysis model.

[0092] The electronic fingerprint is matched and analyzed to obtain a matching result; if the matching result is an unknown target, the position characteristics, color, thermal characteristics and model are used as inputs to the trajectory analysis model to obtain a threat score; the electronic fingerprint matching analysis and threat score calculation form an intelligent decision-making closed loop in low-altitude defense disposal: the device-level unique identification of the electronic fingerprint realizes the rapid classification of known targets and provides an accurate model basis for the countermeasure strategy; when the match fails, the position characteristics, color characteristics, thermal characteristics and model analysis results are dynamically calculated through the trajectory analysis model to calculate the threat score, and the target track and environmental data are combined to realize the quantification of the threat level, providing a scientific basis for the countermeasure threshold decision, reducing the misjudgment rate, and optimizing the allocation of countermeasure resources through threat priority sorting to maximize the defense effectiveness in a complex electromagnetic environment.

[0093] Methods for deriving threat scores include:

[0094] The electronic fingerprint is compared with the pre-stored database to obtain the matching result corresponding to the low-altitude target. The matching result includes the unknown fingerprint and the whitelist and blacklist stored in the pre-stored database. When the matching result is the whitelist, it is released. When the matching result is the blacklist, the dynamic defense strategy is immediately triggered to adopt the countermeasure mode; when the matching result is an unknown fingerprint, the electronic fingerprint corresponding to the low-altitude target is stored in a temporary library, and the position characteristics, color, thermal characteristics and model are used as inputs of the trajectory analysis model to obtain the threat score.

[0095] The training methods for the trajectory analysis model include:

[0096] Group C trajectory analysis data is collected in advance. The trajectory analysis data includes input data and corresponding threat scores; the input data includes location characteristics, color, thermal characteristics and model.

[0097] The input data is used as the input of the trajectory analysis model, and the threat score is used as the output of the trajectory analysis model. The goal is to minimize the error between the output threat score and the actual threat score. The network parameters of the trajectory analysis model are optimized through a nature-inspired optimization algorithm to obtain the network parameters that minimize the error between the threat score output by the trajectory analysis model and the actual threat score. The trajectory analysis model constructed with the corresponding network parameters is used as the trained trajectory analysis model.

[0098] Environmental data is collected. If the threat score exceeds the preset threat threshold, a dynamic defense strategy is used to implement a countermeasure mode against low-altitude targets, combining environmental data, location characteristics, color, thermal characteristics, model, and pilot position. Environmental data and dynamic defense strategies form an intelligent response closed loop in low-altitude defense operations: by collecting real-time environmental parameters such as terrain, population density, and obstacle distribution, and combining them with the threat score, the system can dynamically select the optimal countermeasure mode to improve countermeasure effectiveness. Environmental data supports countermeasure path planning (such as avoiding residential areas), and combined with the pilot's location, precise strikes are achieved to reduce the probability of accidental injury. At the same time, dynamic strategies maximize defense efficiency while ensuring safety by linking threat levels with environmental sensitivity thresholds. For example, full-band jamming is triggered around airports, while deception mode is used in commercial areas, significantly improving the compliance and targeting of countermeasures.

[0099] See also Figure 2 As shown, the methods for countering low-altitude targets include:

[0100] Define the state space S: Obtain threat scores, signal frequency bands, and environmental data; environmental data includes wind speed, temperature, precipitation, electromagnetic interference intensity, and terrain obstruction coefficient;

[0101] Define action space A: Select the jamming signal frequency band and power level, generate false GPS coordinates that deviate from the preset no-fly zone, adjust the gimbal angle based on the low-altitude target angle, and activate the corresponding frequency band for interception. Actions in the action space can also include combined actions, such as selecting a jamming signal frequency band and combining it with generating false GPS coordinates that deviate from the preset no-fly zone.

[0102] Design reward function: Obtain the total reward function based on the weighted combination of counterattack success reward, energy consumption penalty, accidental injury penalty, and environmental adaptation reward;

[0103] Update the Q-value function: Use the Q-learning algorithm to learn the optimal strategy, initialize the Q-value function as a table, and the rows of the table correspond to different environmental states , columns correspond to different actions , set the learning rate , discount factor and exploration rate ; At each time step , detect the current environment status , according to the exploration rate ,by The probability of randomly choosing an action ,by The probability of selecting the action with the largest Q value in the current environment state ; Execute the selected action and obtain the new environment state At the same time, the total reward function value is calculated according to the reward function; the Q value function is updated according to the update formula;

[0104] Repeatedly update the Q-value function until the Q-value converges to obtain the corresponding optimal Q-value function. According to the environmental state, use the optimal Q-value function to select the optimal action from the action space and execute it.

[0105] Example 2

[0106] See also Figure 3 As shown, this embodiment provides a dynamic defense strategy optimization method, including the following steps:

[0107] The model of the low-altitude target is used as an antibody, and each antibody stores the corresponding electronic fingerprint and thermal characteristics to calculate the characteristic affinity ; The calculation formula is as follows:

[0108] ;

[0109] ;

[0110] ;

[0111] in, and are the physical affinity and network affinity corresponding to the antibody, respectively; is the preset temperature adjustment coefficient; is the maximum temperature value; is the preset temperature threshold; The angle between the electronic fingerprint and the preset electronic fingerprint;

[0112] Calculate threat level based on feature affinity; e.g. threat level ;

[0113] Calculate the pheromone baseline value according to the threat level, and iteratively update the threat pheromone based on the pheromone baseline value; ;in, is the distance between the low-altitude target and the jamming device;

[0114] The device selection probability is calculated based on threat pheromones, and devices whose device selection probability exceeds the preset probability threshold are selected as the action basis for action space selection. Detailed action data, such as the interference signal frequency band and power level, can be further obtained based on dynamic defense strategies.

[0115] The above steps define drone models as antibodies and store their electronic fingerprints and thermal signatures. The system then calculates the antibody's characteristic affinity in real time, combining the temperature adjustment coefficient with a preset threshold to quantify the multimodal threat level. The threat level is further converted into a pheromone baseline value, and the threat pheromone concentration is dynamically updated based on the target distance, guiding the ant colony algorithm to probabilistically select jamming devices. Ultimately, a dynamic defense strategy determines countermeasures (such as frequency band and power) to achieve optimal resource scheduling. This improves target identification accuracy and shortens response time. Furthermore, by optimizing the spatial distribution of threat pheromones, jamming coverage efficiency is increased, significantly enhancing the effectiveness of low-altitude defense in complex electromagnetic environments.

[0116] Example 3

[0117] See also Figure 4 As shown, this embodiment discloses an adaptive control system for low-altitude targets, including:

[0118] Position analysis module: collects radar scanning information of low-altitude targets and extracts features from the radar scanning information to obtain position features;

[0119] Color analysis module: collects target images of low-altitude targets, extracts features from the target images, obtains the number of rotors, fuselage shape and color features; and compares the images with the pre-stored color library to obtain the color of the low-altitude targets;

[0120] Source tracing analysis module: collects and analyzes the signal frequency bands of low-altitude targets received by N preset collection points, and calculates the pilot's position;

[0121] Model analysis module: collects thermal radiation images; extracts features from thermal radiation images to obtain thermal signatures; extracts features from signal frequency bands to obtain electronic fingerprints; uses the number of rotors, fuselage shape, thermal signatures, and electronic fingerprints as inputs to the model analysis model to obtain the model of the low-altitude target;

[0122] Threat Analysis Module: This module performs matching analysis on electronic fingerprints to obtain matching results. If the matching result is an unknown target, the location characteristics, color, thermal characteristics, and model are used as inputs to the trajectory analysis model to obtain a threat score.

[0123] Intelligent countermeasure module: Collects environmental data. If the threat score exceeds the preset threat threshold, it will adopt a countermeasure mode to counter low-altitude targets through dynamic defense strategies based on environmental data, location characteristics, color, thermal characteristics, model and pilot position.

[0124] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0125] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An adaptive control method for low-altitude targets, characterized in that: The steps include: Collect radar scanning information of low-altitude targets and extract features from the radar scanning information to obtain position features; Collect target images of low-altitude targets, extract features from the target images, and obtain the number of rotors, fuselage shape, and color features; And compare it with the pre-stored color library to obtain the color of the low-altitude target; Collect the signal frequency bands of low-altitude targets received by the preset N collection points, analyze them, and calculate the pilot's position; Collect thermal radiation images; Extract features from thermal radiation images to obtain thermal features; Extract features from the signal frequency band to obtain electronic fingerprints; use the number of rotors, fuselage shape, thermal characteristics, and electronic fingerprints as inputs to the model analysis model to obtain the model of the low-altitude target; Perform matching analysis on the electronic fingerprint to obtain a matching result; if the matching result is an unknown target, the location characteristics, color, thermal characteristics and model are used as inputs to the trajectory analysis model to obtain a threat score; Collect environmental data. If the threat score exceeds the preset threat threshold, a dynamic defense strategy is used to counter low-altitude targets using a countermeasure mode based on environmental data, location characteristics, color, thermal characteristics, model, and pilot position. The method for obtaining an electronic fingerprint comprises: Passively receive the transmission signal of the low-altitude target, extract the serial number, MAC address, signal modulation mode and frame structure of the transmission signal of the low-altitude target, and detect whether the transmission signal of the low-altitude target is a forged signal based on the detection strategy. If it is a forged signal, directly activate the dynamic defense strategy and adopt the countermeasure mode. If it is not a forged signal, perform spectrum analysis and quantization on the transmission signal of the low-altitude target, extract the carrier frequency offset and phase noise, splice the carrier frequency offset and phase noise as the signal fingerprint, extract the heartbeat packet sending interval and data packet length distribution, splice the heartbeat packet sending interval and data packet length distribution as the behavioral fingerprint, quantify the signal characteristics through the statistical model, and use the signal fingerprint and behavioral fingerprint as the input of the fingerprint analysis model to obtain the electronic fingerprint. The detection strategy includes monitoring whether the carrier frequency of the transmission signal of the low-altitude target has frequency drift, comparing whether the signal modulation mode matches the pre-stored device protocol library, monitoring whether the signal strength exceeds the preset strength threshold, and monitoring whether the pilot's position is within the preset authorized area. If any of the detection results are yes, it is judged to be a forged signal, otherwise it is not a forged signal.

2. The adaptive control method for low-altitude targets according to claim 1, characterized in that: The method for obtaining the threat score includes: The electronic fingerprint is compared with the pre-stored database to obtain the matching result corresponding to the low-altitude target. The matching result includes the unknown fingerprint and the whitelist and blacklist stored in the pre-stored database. When the matching result is the whitelist, it is released. When the matching result is the blacklist, the dynamic defense strategy is immediately triggered to adopt the countermeasure mode; when the matching result is an unknown fingerprint, the electronic fingerprint corresponding to the low-altitude target is stored in a temporary library, and the position characteristics, color, thermal characteristics and model are used as inputs of the trajectory analysis model to obtain the threat score.

3. The adaptive control method for low-altitude targets according to claim 1, characterized in that: The method for countering low-altitude targets includes: Define the state space S: Obtain threat scores, signal frequency bands, and environmental data; environmental data includes wind speed, temperature, precipitation, electromagnetic interference intensity, and terrain obstruction coefficient; Define action space A: Select the jamming signal frequency band and power level, generate false GPS coordinates that deviate from the preset no-fly zone, adjust the gimbal angle based on the angle of the low-altitude target, and activate the corresponding frequency band for interception. The actions in the action space also include combined actions. Design reward function: Obtain the total reward function based on the weighted combination of counterattack success reward, energy consumption penalty, accidental injury penalty, and environmental adaptation reward; Update the Q-value function: Use the Q-learning algorithm to learn the optimal strategy, initialize the Q-value function as a table, and the rows of the table correspond to different environmental states , columns correspond to different actions , set the learning rate , discount factor and exploration rate ; At each time step , detect the current environment status , according to the exploration rate ,by The probability of randomly choosing an action ,by The probability of selecting the action with the largest Q value in the current environment state ; Execute the selected action and obtain the new environment state At the same time, the total reward function value is calculated according to the reward function; the Q value function is updated according to the update formula; Repeatedly update the Q-value function until the Q-value converges to obtain the corresponding optimal Q-value function. According to the environmental state, use the optimal Q-value function to select the optimal action from the action space and execute it.

4. The adaptive control method for low-altitude targets according to claim 1, characterized in that: The method for obtaining the pilot's position includes: Obtain the coordinates of the acquisition points and the arrival time of the received signal, calculate the time difference between any two acquisition points, construct a hyperbola equation based on the time difference and coordinates, solve the hyperbola equation through an iterative algorithm, and obtain the pilot's coordinates.

5. The adaptive control method for low-altitude targets according to claim 1, characterized in that: The method for obtaining thermal characteristics comprises: The thermal radiation image is converted into a grayscale or pseudo-color image, in which the highlighted area corresponds to the high-temperature area. The image is segmented based on a preset segmentation threshold, and each independent heat source is marked based on the connected domain analysis to obtain the number of independent heat sources. The temperature values ​​corresponding to the pixel points of each independent heat source are traversed, and the maximum temperature value of each independent heat source is recorded. The maximum temperature value of each independent heat source is collected once at a preset time interval, and the average temperature change rate of each independent heat source is calculated; the number of independent heat sources, the maximum temperature value of each independent heat source, and the average temperature change rate of each independent heat source are spliced ​​as thermal features.

6. The adaptive control method for low-altitude targets according to claim 1, characterized in that: The method for obtaining the number of rotors includes: Perform edge detection on the target image to extract the low-altitude target contour. Then use linear structuring elements and square structuring elements to erode the low-altitude target contour in sequence to obtain the eroded low-altitude target contour. Count the number of connected areas in the eroded low-altitude target contour, and combine it with the rotor symmetry judgment to obtain the first rotor number. Collect Doppler frequency shift and obtain the number of the second rotor through spectrum analysis; The first number of rotors and the second number of rotors are cross-validated. If the first number of rotors and the second number of rotors are the same, the values ​​of the first number of rotors and the second number of rotors are used as the number of rotors. If the first number of rotors and the second number of rotors are different, manual review or dynamic resampling is triggered to obtain the number of rotors.

7. The adaptive control method for low-altitude targets according to claim 1, characterized in that: The method for obtaining the color of the low-altitude target comprises: The color features of the low-altitude target are extracted by analyzing the target image through RGB pixels, and compared with the pre-stored color library to obtain the color of the low-altitude target.

8. The adaptive control method for low-altitude targets according to claim 1, characterized in that: The method for obtaining the fuselage shape includes: Perform target detection on the target image, separate the target foreground, and use the target foreground as the input of the shape analysis model to obtain the fuselage shape.

9. The adaptive control method for low-altitude targets according to claim 1, characterized in that: The position characteristics include three-dimensional position information, speed and heading; Methods for obtaining location features include: Step 1: Collect the time difference between the transmitted electromagnetic wave and the received electromagnetic wave, and calculate the distance of the low-altitude target based on the electromagnetic wave transmission speed; Step 2: Calculate the low-altitude target speed by combining the radar transmission frequency and the Doppler shift of the reflected signal; Step 3: Control the mechanical rotating antenna or the electronic scanning beam to point in different directions to calculate the direction of the low-altitude target; combine the distance of the low-altitude target to obtain the three-dimensional position information of the low-altitude target; the three-dimensional position information includes longitude, latitude and altitude; Step 4: Repeat steps 1 to 3 at preset intervals to obtain second and third-dimensional position information of the low-altitude target, calculate a displacement vector between the second and third-dimensional position information and the third-dimensional position information, and calculate the heading of the low-altitude target based on an inverse tangent function combined with the displacement vector. Step 5: Calculate the modulus of the displacement vector, calculate the ratio of the modulus to the preset time period, and obtain the speed of the low-altitude target.

10. An adaptive control system for a low-altitude target, implementing the adaptive control method for a low-altitude target according to any one of claims 1 to 9, characterized in that: include: Position analysis module: collects radar scanning information of low-altitude targets and extracts features from the radar scanning information to obtain position features; Color analysis module: collects target images of low-altitude targets, extracts features from the target images, obtains the number of rotors, fuselage shape and color features; and compares the images with the pre-stored color library to obtain the color of the low-altitude targets; Source tracing analysis module: collects and analyzes the signal frequency bands of low-altitude targets received by N preset collection points, and calculates the pilot's position; Model analysis module: collects thermal radiation images; Extract features from thermal radiation images to obtain thermal features; Extract features from the signal frequency band to obtain electronic fingerprints; use the number of rotors, fuselage shape, thermal characteristics, and electronic fingerprints as inputs to the model analysis model to obtain the model of the low-altitude target; Threat Analysis Module: This module performs matching analysis on electronic fingerprints to obtain matching results. If the matching result is an unknown target, the location characteristics, color, thermal characteristics, and model are used as inputs to the trajectory analysis model to obtain a threat score. Intelligent countermeasure module: Collects environmental data. If the threat score exceeds the preset threat threshold, it will adopt a countermeasure mode to counter low-altitude targets through dynamic defense strategies based on environmental data, location characteristics, color, thermal characteristics, model and pilot position.

Images