Method for constructing dynamic defense model of unmanned aerial vehicle countermeasure

Abstract

The present application relates to the technical field of unmanned aerial vehicle countermeasure, and discloses a dynamic defense model construction method for unmanned aerial vehicle countermeasure, aiming at the safety management problems caused by the application of unmanned aerial vehicle and the limitations of existing countermeasure technology strategies, the method first collects data to determine model parameters, establishes a dynamic defense model based on an adaptive state space model, can accurately present the state changes of unmanned aerial vehicle and countermeasure equipment and adapt to environmental interference. By constructing an optimization model, the maximum countermeasure probability and the minimum resource consumption are taken as the target, and the resource allocation is optimized in combination with scientific and quantitative countermeasure success probability and other indexes. The improved genetic algorithm is used to solve the countermeasure strategy, and the algorithm search ability is enhanced. The beneficial effects are to improve the countermeasure accuracy and reliability, efficiently utilize resources, adapt to complex environment, realize dynamic optimization of countermeasure strategy, effectively cope with unmanned aerial vehicle security threats, and provide a scientific and efficient solution for unmanned aerial vehicle countermeasure.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of unmanned aerial vehicle countermeasure technology, in particular to a dynamic defense model construction method for unmanned aerial vehicle countermeasure. BACKGROUND

[0002] As a new type of aircraft, unmanned aerial vehicles (UAVs) have been widely used in various fields in recent years. In the civil field, they frequently appear in aerial surveying and mapping, logistics distribution, agricultural plant protection, power inspection, and other scenarios. For example, in aerial surveying and mapping, UAVs can quickly obtain high-resolution images and data due to their flexibility and maneuverability, providing strong support for urban planning and topographic mapping. In agricultural plant protection, UAVs can efficiently spray pesticides and fertilizers, significantly improving agricultural production efficiency. In the military field, UAVs have also shown great value, as they can perform reconnaissance, surveillance, electronic jamming, and even precision strikes, becoming an indispensable combat force in modern warfare.

[0003] However, the widespread use of UAVs has also brought a series of security and management issues that cannot be ignored. In terms of public safety, malicious use of UAVs can lead to serious consequences. For example, in the airport clearance protection zone, the intrusion of UAVs can interfere with the normal takeoff and landing of civil aviation aircraft, posing a significant safety hazard. In large event sites, illegal flight of UAVs can pose a threat to the safety of life and property of on-site personnel. In the field of information security, UAVs can be used to spy on sensitive areas and steal confidential information, posing risks to national security and business secrets. In addition, the rapid increase in the number of UAVs has made airspace use increasingly complex, with disordered flight phenomena occurring from time to time, posing a great challenge to traditional airspace management models.

[0004] To address these issues, various UAV countermeasure technologies have been developed. Radio frequency jamming technology is a common one, which works by transmitting jamming signals to block the communication link between the UAV and the remote controller or the GPS positioning signal, causing the UAV to lose control. While this technology can achieve countermeasure purposes to some extent, it has the problem of difficulty in accurately controlling the interference range, which may have adverse effects on surrounding legal wireless communication equipment. In addition, electromagnetic pulse-based countermeasure technology destroys the electronic components of UAVs by generating high-intensity electromagnetic pulses, but it may also cause damage to other electronic devices in the surrounding area; laser countermeasure technology uses high-energy laser beams to hard-kill UAVs, but is greatly limited by weather conditions (such as heavy fog, heavy rain, etc.), and the countermeasure effect is greatly reduced in adverse weather conditions.

[0005] In addition to technical problems, existing UAV countermeasures also have deficiencies in formulation. Most countermeasures are based on experience or simple rules, lacking comprehensive consideration of UAV dynamic characteristics and complex environmental factors. In actual countermeasures, due to the variability of UAV flight state and the complexity of the environment, these strategies often fail to achieve efficient and accurate countermeasures against UAVs. At the same time, the optimal allocation of countermeasure resources is not fully considered, which may lead to waste or insufficient resources in the countermeasure process, and cannot achieve optimal use of resources while ensuring countermeasure effectiveness. SUMMARY

[0006] The purpose of the present application is to provide a dynamic defense model construction method for UAV countermeasures to solve the problems raised in the background art.

[0007] To achieve the above purpose, the present application provides the following technical solution: a dynamic defense model construction method for UAV countermeasures, the method comprising:

[0008] Step S1: Collect real-time data of UAV flight environment, state data of UAV itself and related data of countermeasure equipment, and determine parameters required for model calculation; wherein the real-time data of UAV flight environment at least includes meteorological data and geographic information data; the state data of UAV itself at least includes flight speed, flight altitude and flight attitude data; the data of countermeasure equipment at least includes equipment location, equipment power and equipment effective countermeasure range data.

[0009] Step S2: Considering the dynamic characteristics of UAV flight and various change factors in the countermeasure process, a dynamic defense model for UAV countermeasures based on adaptive state space model is established; by predicting the flight trajectory of UAV, the response time of countermeasure equipment and the time-varying characteristics of interference effect, time-varying state transition equation, observation equation and control input equation are established to handle various constraints in dynamic defense;

[0010] Step S3: Taking maximizing the effective countermeasure probability of UAV and minimizing the consumption of countermeasure resources as the goal, combining the actual operating environment of UAV countermeasure system, a new optimization method and optimization model of dynamic defense model are established to realize the predictive control of countermeasure strategy;

[0011] Step S4: For the constructed optimization model, an improved genetic algorithm is used to solve, and finally the countermeasure strategy with optimal comprehensive performance is obtained to realize effective dynamic defense against UAVs.

[0012] Preferably, the specific steps of establishing a dynamic defense model based on an adaptive state space model in S2 include:

[0013] Step S21: set a hypothetical condition, assuming that the countermeasure area boundary is clear, the flight behavior of the UAV in the countermeasure area follows the basic dynamics principle, and the interference signal propagation of the countermeasure device is not seriously affected by the complex terrain;

[0014] Step S22: establish a time-varying state transition equation for UAV flight; let represent the state vector of the UAV at time ; represent the control input vector of the countermeasure device at time ; represent the state transition matrix, which describes the change of the UAV's own dynamics characteristics over time; represent the control input matrix, which embodies the influence of the control input of the countermeasure device on the state of the UAV; then the time-varying state transition equation is: ;

[0015] Step S23: establish an observation equation, let represent the observation vector of the UAV state at time , represent the observation matrix, which is used to map the real state of the UAV to the observation space; the observation equation is: , wherein represents the observation noise vector, which is used to describe the uncertainty in the observation process;

[0016] Step S24: considering the interference factors and environmental changes in the countermeasure process, adaptively adjust the state transition equation and the observation equation; by introducing adaptive parameters , the state transition matrix , the control input matrix and the observation matrix are updated in real time to adapt to the dynamic changes of the UAV flight state and the countermeasure environment; the update formula is: , , .

[0017] Preferably, the specific steps of establishing an optimization model in step S3 include:

[0018] Step S31: set the hypothetical conditions of the model, assuming that each countermeasure device can only countermeasure one UAV at a time, the UAV will not exhibit abnormal flight behavior after being interfered by the countermeasure, and the total amount of countermeasure resources is limited and can be monitored in real time;

[0019] Step S32: set the symbols of known parameters or sets in the model and decision variables; let represent the set of UAVs that need to be countermeasured at present, represent the UAV, representing the countermeasure equipment to the UAV , the countermeasure success probability representing the countermeasure equipment resource consumption coefficient representing the maximum available resource amount of the countermeasure equipment representing the countermeasure equipment to the UAV decision variable whether to carry out the countermeasure representing carrying out the countermeasure representing not carrying out the countermeasure representing the time step

[0020] Step S33: constructing a target function, which is a comprehensive target of maximizing the effective countermeasure probability to the UAV and minimizing the countermeasure resource consumption, and the calculation formula is:

[0021]

[0022] wherein is a weight coefficient for balancing the relationship between the countermeasure probability and the resource consumption

[0023] Step S34: establishing the constraint conditions of the model:

[0024] Constraint condition 1: countermeasure equipment resource constraint, ensuring that the resource consumption of the countermeasure equipment in each countermeasure operation does not exceed its maximum available resource amount, i.e. ;

[0025] Constraint condition 2: countermeasure equipment working state constraint, ensuring that each countermeasure equipment can only countermeasure one UAV at the same time, i.e. ;

[0026] Constraint condition 3: decision variable value constraint, the decision variable can only take 0 or 1, i.e. .

[0027] Preferably, the specific steps of the improved genetic algorithm in step S4 include:

[0028] Step S41: initializing the population, randomly generating a certain number of initial individuals according to the decision variable range of the countermeasure strategy, each individual representing a combination of countermeasure strategies, forming an initial population;

[0029] Step S42: calculating the fitness value, calculating the fitness value of each individual according to the target function constructed in step S3, and the higher the fitness value, the better the countermeasure strategy

[0030] ​Step S43: using roulette wheel selection method, a certain number of individuals are selected from the current population into the next generation population according to the fitness value of the individuals, and the individual with a higher fitness value has a greater probability of being selected;

[0031] Step S44: performing a crossover operation on the selected individuals with a certain crossover probability randomly selecting two individuals, exchanging their partial genes to generate new individuals, and increasing the diversity of the population;

[0032] Step S45: performing a mutation operation on the new individuals with a certain mutation probability randomly changing some gene values of the individuals to prevent the algorithm from falling into a local optimal solution;

[0033] Step S46: repeating steps S42-S45 until a predetermined termination condition is met, at which time the individual with the highest fitness value in the population is the optimal countermeasure strategy.

[0034] Preferably, the updating method of the adaptive parameter in step S24 comprises:

[0035] The state estimation error of the unmanned aerial vehicle is calculated based on a Kalman filter algorithm, wherein is the estimated value of the state of the unmanned aerial vehicle;

[0036] The adaptive parameter is calculated according to the state estimation error and a preset adaptive rule.

[0037] Preferably, the calculation method of the countermeasure success probability in step S33 is:

[0038] The factors of the power of the countermeasure device , the distance from the unmanned aerial vehicle , and the matching degree of the interference signal frequency and the receiving frequency of the unmanned aerial vehicle are considered, and the calculation formula of the countermeasure success probability is:

[0039]

[0040] wherein is an influence coefficient.

[0041] Preferably, in step S44, a multi-point crossover method is used, and the specific steps are: generating a plurality of crossover points, and exchanging the genes of the two parent individuals at the crossover points to generate two child individuals.

[0042] ​Preferably, in step S45, an adaptive mutation probability is adopted, and the specific method is as follows:

[0043] With the increase of the iteration number , the mutation probability is gradually reduced, and the calculation formula is as follows: , wherein is the initial mutation probability, is the maximum iteration number.

[0044] Preferably, the present application further comprises an electronic device, comprising:

[0045] a processor; a memory for storing processor-executable instructions;

[0046] The processor is configured to call the instructions stored in the memory to execute the dynamic defense model construction method of the unmanned aerial vehicle countermeasure described above.

[0047] Preferably, the present application further comprises a computer readable storage medium having computer program instructions stored thereon, wherein the computer program instructions are executed by a processor to implement the dynamic defense model construction method of the unmanned aerial vehicle countermeasure described above.

[0048] Compared with the prior art, the present application has the following beneficial effects:

[0049] Based on the adaptive state space model, the dynamic defense model is constructed, and the dynamic changes of the speed, height, attitude and other factors of the unmanned aerial vehicle during flight, as well as the response time and time-varying interference effect of the countermeasure equipment are fully considered. By establishing accurate time-varying state transition equation, observation equation and control input equation, compared with the traditional simple fixed model, the state changes of the unmanned aerial vehicle and the countermeasure equipment can be more accurately simulated, which provides a solid and reliable basis for the countermeasure strategy, greatly improves the accuracy and timeliness of the countermeasure action, and effectively deals with the complex and variable flight state of the unmanned aerial vehicle.

[0050] In the model construction process, in view of the interference factors and environmental changes in the countermeasure process, adaptive parameters are introduced to update the state transition matrix, control input matrix and observation matrix in real time. With the help of Kalman filtering algorithm, the state estimation error of the unmanned aerial vehicle is accurately calculated, and the adaptive adjustment of the model is realized. This makes the model still maintain high accuracy and reliability in complex and variable environment, such as the existence of multiple interference sources or meteorological condition changes, which is significantly superior to the traditional model lacking adaptive ability.

[0051] An optimization model is established to maximize the effective countermeasure probability and minimize the countermeasure resource consumption, and actual constraint conditions such as limited countermeasure equipment resources and only one unmanned aerial vehicle can be countermeasured at the same time are comprehensively considered. Unlike traditional strategies that only focus on single targets such as countermeasure effect or resource consumption, the present invention can achieve an optimal balance between the two, realizing efficient use of resources. For example, under the condition of limited total countermeasure resources, the present invention prioritizes countermeasures against key unmanned aerial vehicles, avoiding resource waste and ensuring optimal countermeasure effect under limited resources.

[0052] By scientifically calculating the countermeasure success probability, factors such as countermeasure equipment power, distance from the unmanned aerial vehicle, and interference signal frequency matching degree are considered to provide accurate quantitative indicators for countermeasure strategy formulation. Based on these indicators, the correspondence between countermeasure equipment and unmanned aerial vehicles can be reasonably arranged, and combinations with high countermeasure success probability and low resource consumption are prioritized, realizing precise allocation of countermeasure resources and further improving resource utilization efficiency.

[0053] The establishment of an adaptive state space model and the real-time updating of related matrices enable the model to quickly adapt to the needs of unmanned aerial vehicle countermeasures under different environmental conditions. Whether in complex terrain with high-rise buildings or in harsh weather conditions, the model can adjust its parameters to accurately describe the state of unmanned aerial vehicles and countermeasure equipment, providing reliable support for countermeasure strategies and enhancing the adaptability of the countermeasure system in different environments.

[0054] In the improved genetic algorithm, strategies such as multi-point crossover and adaptive mutation probability are used to increase the search ability of the algorithm in the solution space. In complex environments, multi-point crossover can integrate more advantageous genes from parent individuals to generate more diverse offspring, expanding the search range; adaptive mutation probability can explore new solution spaces with a higher probability in the early stage and stabilize convergence in the later stage, ensuring that the algorithm can quickly find the globally optimal countermeasure strategy in complex and changing environments, effectively addressing the challenges brought by environmental changes.

[0055] Using the improved genetic algorithm to solve the countermeasure strategy, compared with traditional experience or simple rule-based strategies, it can search in a wider strategy space and find the optimal countermeasure strategy. Through multiple iterations and optimization, the selection of countermeasure equipment for unmanned aerial vehicles and the timing of countermeasures are constantly adjusted, realizing efficient and dynamic defense of unmanned aerial vehicles, improving the success rate of countermeasures, and reducing the probability of missed detection and false positives.

[0056] During the countermeasure process, as the state of unmanned aerial vehicles and environmental factors change in real time, the model and algorithm can update the countermeasure strategy in a timely manner. For example, when new unmanned aerial vehicles enter the countermeasure area or existing unmanned aerial vehicles change their flight trajectories, the system can quickly recalculate and adjust the countermeasure strategy to ensure optimal countermeasure effect at all times and adapt to the needs of dynamic countermeasure scenarios. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 The working principle diagram of the dynamic defense model construction method of the present application;

[0058] Figure 2 The construction flowchart based on the adaptive state space model;

[0059] Figure 3 The construction flowchart of the optimized model;

[0060] Figure 4 The implementation step diagram of the improved genetic algorithm. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0062] Please refer to Figures 1-4 The present application provides a dynamic defense model construction method for unmanned aerial vehicle countermeasures, which aims to realize efficient countermeasures against unmanned aerial vehicles by constructing a dynamic defense model and optimizing countermeasures strategies, while reducing the consumption of countermeasures resources. The overall implementation scheme is as follows:

[0063] Step S1: Collect data to determine model parameters: Collect real-time data of the unmanned aerial vehicle flight environment, the state data of the unmanned aerial vehicle itself and the related data of the countermeasures equipment through various sensors and data acquisition equipment. Obtain meteorological data such as wind speed, wind direction, air temperature and air pressure by using meteorological monitoring stations, satellite remote sensing technology, etc.; obtain geographic information data including topography, building distribution, etc. by means of geographic information system (GIS). Collect flight speed, flight altitude and flight attitude data through the sensors such as gyroscopes, accelerometers and GPS modules on the unmanned aerial vehicle. For the data of the countermeasures equipment, obtain the equipment position through the positioning device of the equipment, and obtain the equipment power and effective countermeasures range data from the equipment parameter manual or real-time monitoring. Organize and analyze these data to determine the parameters required for model calculation.

[0064] Step S2: Establishing a dynamic defense model based on an adaptive state space model: Considering the dynamic characteristics of UAV flight and various changing factors in the countermeasure process, a UAV countermeasure dynamic defense model based on an adaptive state space model is constructed. A time-varying state transition equation, an observation equation, and a control input equation are established to handle various constraints in dynamic defense. By analyzing and modeling the prediction of UAV flight trajectory, the response time of countermeasure equipment, and the time-varying characteristics of interference effect, it is ensured that the model can accurately reflect the state changes of UAV and countermeasure equipment at different times.

[0065] Step S3: Establishing an optimization model to realize predictive control: A new optimization method and optimization model of the dynamic defense model are established to maximize the effective countermeasure probability of the UAV and minimize the consumption of countermeasure resources, in combination with the actual operating environment of the UAV countermeasure system. In practical applications, different combinations of countermeasure equipment and UAVs will produce different countermeasure effects and resource consumption. Through the optimization model, the best countermeasure strategy can be found to realize predictive control of the countermeasure strategy.

[0066] Step S4: Solving the countermeasure strategy using an improved genetic algorithm: For the constructed optimization model, an improved genetic algorithm is used for solving. Through initialization of the population, calculation of the fitness value, selection, crossover, and mutation operations, iterative optimization is continuously performed, and finally the countermeasure strategy with the optimal comprehensive performance is obtained to realize effective dynamic defense of the UAV. In actual scenarios, different initial population, crossover probability, and mutation probability parameter settings will affect the convergence speed and final result of the algorithm, which need to be adjusted according to specific circumstances.

[0067] The implementation of the present application will be further described below in connection with Examples 1 to 5.

[0068] Example 1:

[0069] This example details the establishment process of the adaptive state space model, which makes the model more accurately simulate the dynamic changes in the UAV flight and countermeasure process through reasonable assumptions, equation establishment, and adaptive adjustment. Specifically, it includes:

[0070] Step S21: Set hypothetical conditions: assume that the countermeasure area boundary is clear, set obvious signs on the periphery of the countermeasure area or use electronic fence technology to clearly demarcate the boundary, so as to facilitate determination of whether the UAV enters the countermeasure area. Assume that the flight behavior of the UAV in the countermeasure area follows the basic dynamics principle. In actual application, the flight dynamics characteristics of most normal flying UAVs conform to the basic dynamics principle such as Newton's law of motion, which provides a theoretical basis for subsequent model establishment. Assume that the interference signal propagation of the countermeasure device is not seriously affected by complex terrain. When selecting the deployment location of the countermeasure device in actual application, an open and simple terrain area is selected as much as possible, or technical means such as signal enhancement and signal compensation are used to reduce the influence of terrain on interference signal propagation.

[0071] Step S22: Establish a time-varying state transition equation for UAV flight: let represent the state vector of the UAV at time . For example, at a certain time, the state vector of the UAV can be represented as , where , are the flight speeds of the UAV in the , directions, respectively, is the flight height, is the flight attitude angle. Let represent the control input vector of the countermeasure device at time . For example, the parameters such as the power and frequency of the interference signal emitted by the countermeasure device can constitute the control input vector. Let represent the state transition matrix, the elements of which are determined according to the change of the UAV's own dynamics characteristics over time. Assume that the flight speed of the UAV in the horizontal direction is affected by air resistance, and the dynamics equation is , where is the mass of the UAV, is the air resistance coefficient. After discretization processing, the element corresponding to the change of the horizontal speed in the state transition matrix may be represented as , where is the time interval. Let represent the control input matrix. For example, when the countermeasure device changes the flight attitude of the UAV by emitting an interference signal, the element corresponding to the change of the attitude angle in the control input matrix may be determined according to the influence degree of the interference signal on the attitude angle. Then the time-varying state transition equation is: .

[0072] Step S23: Establish an observation equation: let represent the observation equation at time In practical applications, the observation vector of the UAV's state can be obtained through devices such as radar and photoelectric sensors, for example... The values ​​marked with the subscript "obs" represent the observed values. Let... This represents the observation matrix, used to map the actual state of the UAV to the observation space. Assuming the observation equipment has a certain scaling error when measuring the UAV's horizontal velocity, the observation matrix... The element corresponding to horizontal velocity can be represented as ,in This represents the proportion of the horizontal velocity measurement error. The observation equation is: ,in This represents the observation noise vector, which can be obtained through statistical analysis of multiple measurements from the observation equipment. For example, the covariance matrix of the noise vector can be determined by calculating the standard deviation of the measurement data.

[0073] Step S24: Adaptively adjust the state transition equation and observation equation: Considering the disturbance factors and environmental changes in the countermeasure process, adaptive parameters are introduced. For the state transition matrix Control input matrix and observation matrix Real-time updates are performed. The state estimation error of the UAV is assessed based on the Kalman filter algorithm. Perform calculations. ,in This is an estimate of the UAV's state. The Kalman filter algorithm continuously optimizes the estimated UAV state through two steps: prediction and update. In the prediction step, the state at the current moment is predicted based on the state estimate from the previous moment and the state transition equation. In the update step, the predicted values ​​are corrected based on the observed values ​​and the observation equation, i.e. , ,in To predict the error covariance, To observe the noise covariance, This is the Kalman gain. Based on the state estimation error... Calculate adaptive parameters based on preset adaptive rules. For example, the preset adaptive rule is: ,in These are the adaptive coefficients. Then, the matrix is ​​updated based on the adaptive parameters, using the following formula: , assuming (where is the identity matrix) (for adjustment factors), then ; Assumption ,but ; , assuming , then .

[0074] Embodiment 2:

[0075] This embodiment details the establishment process of the optimization model. By reasonably setting the assumption conditions, defining the parameters and variables, constructing the objective function, and establishing the constraint conditions, an effective mathematical model is provided for the goal of maximizing the countermeasure probability and minimizing the resource consumption, which provides a clear direction and basis for the optimization of the countermeasure strategy, including:

[0076] Step S31: Set the assumption conditions of the model: assume that each countermeasure device can only countermeasure one unmanned aerial vehicle at a time, which is based on the current technical implementation of most countermeasure devices, such as the common radio frequency interference type countermeasure device, which can only emit interference signals of a specific frequency at the same time to target one unmanned aerial vehicle. Assume that the unmanned aerial vehicle will not exhibit abnormal flight behavior after being subjected to countermeasure interference, resulting in unpredictable situations. In actual applications, most normally designed unmanned aerial vehicles still follow certain rules when subjected to reasonable countermeasure interference, such as only changing flight attitude or speed, without sudden loss of control or unpredictable flight trajectories. Assume that the total amount of countermeasure resources is limited and can be monitored in real time. By installing power monitoring modules, signal transmission power monitoring modules, and other devices on the countermeasure device, the resource consumption of the countermeasure device can be obtained in real time, and the upper limit of the total amount of countermeasure resources is set, such as the limited power of the countermeasure device or the limited interference signal transmission consumables carried.

[0077] Step S32: Set the symbols of known parameters or sets and decision variables in the model: let represent the set of unmanned aerial vehicles that need to be countermeasured at present. In a specific countermeasure scenario, assume that 3 unmanned aerial vehicles are detected by radar entering the countermeasure area, then . Let represent the unmanned aerial vehicle, for example represents the first monitored unmanned aerial vehicle. Let represent the countermeasure device , and represent the countermeasure success probability of the countermeasure device to the unmanned aerial vehicle , which will be described in detail later. Let represent the resource consumption coefficient of the countermeasure device , for example, the power consumption of a certain countermeasure device is 0.1 degrees per transmission of interference signal. If the power is used as a resource measure, and the time of each countermeasure operation is the same, then its resource consumption coefficient . Let represent the maximum available resource amount of the countermeasure device , such as the power upper limit of the above-mentioned countermeasure device being 1 degree, then Let denote the countermeasure equipment Let denote the decision variable of whether to countermeasure the UAV Let denote the countermeasure Let denote the time step, in actual application, the time step is determined according to the response speed of the countermeasure system and the data update frequency, for example, the countermeasure system updates data every 1 second, then second.

[0078] Step S33: Construct the objective function: the objective function is the comprehensive goal of maximizing the effective countermeasure probability of the UAV and minimizing the countermeasure resource consumption, the calculation formula is:

[0079]

[0080] wherein is the weight coefficient, used to balance the relationship between the countermeasure probability and the resource consumption. In actual application, the value of the weight coefficient can be determined through multiple tests and data analysis. For example, in a certain test scene, respectively set , , perform multiple countermeasure simulations, and select the optimal value according to the countermeasure effect and resource consumption.

[0081] Step S34: Establish the constraint condition of the model

[0082] Constraint condition 1, countermeasure equipment resource constraint: ensure that the resource consumption of the countermeasure equipment in each countermeasure operation does not exceed its maximum available resource amount, that is . Assuming that at a certain time, there are 3 UAVs , , , the resource consumption coefficient of the countermeasure equipment is , and the maximum available resource amount is . If , , , then , which does not meet the constraint condition, meaning that the countermeasure equipment cannot simultaneously countermeasure the 3 UAVs, and the countermeasure decision needs to be adjusted.

[0083] Constraint condition 2: countermeasure equipment working state constraint: ensure that each countermeasure equipment can only countermeasure one UAV at the same time, that is . For example, at the same time, the countermeasure equipment countermeasures the UAV , that is Then , The decision variable corresponding to other UAVs must be 0 to prevent the countermeasure device from simultaneously transmitting interference signals to multiple targets, resulting in poor interference effect.

[0084] Constraint 3: Value constraint of decision variable: decision variable can only take 0 or 1, that is . This is because the countermeasure device either implements a countermeasure operation (value 1) or does not perform a countermeasure (value 0), and there is no other intermediate state, ensuring the clarity and operability of the decision.

[0085] Embodiment 3:

[0086] This embodiment details the calculation method of the success probability of the countermeasure, comprehensively considers multiple influencing factors, provides accurate quantitative indicators for the optimization model, and makes the formulation of the countermeasure strategy more scientific and accurate, which specifically includes:

[0087] In step S33, the success probability of the countermeasure is calculated by comprehensively considering the power of the countermeasure device, the distance from the UAV, the matching degree of the interference signal frequency and the UAV receiving frequency and other factors, and the calculation formula is:

[0088]

[0089] wherein is the influence coefficient. These influence coefficients are obtained by fitting a large amount of experimental data. For example, in a special UAV countermeasure test site, set up countermeasure devices with different powers, change the distance from the UAV, and adjust the matching degree of the interference signal frequency and the UAV receiving frequency, and perform multiple countermeasure experiments. Record the countermeasure results (success or failure) of each experiment, and use nonlinear regression analysis method to determine the value of the influence coefficient.

[0090] Suppose in a certain actual countermeasure scene, the power of the countermeasure device is 80W, the distance from the UAV is 800m, and the matching degree of the interference signal frequency and the UAV receiving frequency is 0.7. The influence coefficients , , are determined through a large number of previous experiments. Substitute these values into the formula to obtain:

[0091]

[0092] Through the calculation method, the anti-drone equipment can quantize the success possibility of anti-drone for different unmanned aerial vehicles, and provide a key basis for subsequent anti-drone strategy formulation. For example, in a complex scene of multiple anti-drone equipment and multiple unmanned aerial vehicles, according to the anti-drone success probability, the anti-drone equipment with high anti-drone success probability for high-value target unmanned aerial vehicles is preferentially arranged for operation, and the overall anti-drone effect is improved.

[0093] Embodiment 4:

[0094] This embodiment details the specific steps of adopting the multi-point crossover method in the improved genetic algorithm. By increasing the crossover points, the diversity of the population genes is promoted, so that the algorithm can more comprehensively explore the solution space in the process of searching for the optimal solution, avoid falling into local optimum, and improve the ability to find the global optimal anti-drone strategy. Specifically, it includes:

[0095] In step S44, a multi-point crossover method is adopted. The specific steps are as follows: first, randomly generate multiple crossover points. Assuming that the gene encoding length of the current anti-drone strategy individual is 30 bits, in one crossover operation, 4 crossover points are randomly generated, which are the 6th, 12th, 18th and 24th. Then, the genes of the two parent individuals at the crossover points are exchanged to generate two offspring individuals.

[0096] For example, there are parent individual A: 110010 011011 100101 011011 001010, and parent individual B: 001101100100 011010 100100 110111. After exchanging according to the above crossover points, offspring individual C: 110010100100 011010 011011 110111 is obtained, and offspring individual D: 001101 011011 100101 100100 001010 is obtained.

[0097] Through multi-point crossover, the offspring individual combines gene fragments of different positions of the parent individuals, increasing the diversity of the population. In the process of multiple iterations, different crossover point selection will produce diversified offspring individuals, so that the algorithm can explore more solution space. Compared with single-point crossover, multi-point crossover can more fully utilize the information of parent individuals, improve the search efficiency and optimization ability of the algorithm. For example, in the process of dealing with complex unmanned aerial vehicle anti-drone scenes, single-point crossover may not effectively integrate the advantage genes of different parent individuals, resulting in slow convergence speed of the algorithm or falling into local optimum. Multi-point crossover can combine genes in a larger range, and is more likely to find the global optimal anti-drone strategy combination.

[0098] Embodiment 5:

[0099] This embodiment illustrates the method of using adaptive mutation probability in improved genetic algorithm. By adjusting mutation probability with the number of iterations, enough exploration ability is ensured in the early stage of the algorithm, and stable convergence is realized in the later stage, improving the overall performance and solution accuracy of the algorithm.

[0100] In step S45, adaptive mutation probability is used. With the increase of the number of iterations t, the mutation probability gradually decreases, and the calculation formula is:

[0101] , wherein is the initial mutation probability, is the maximum number of iterations.

[0102] Suppose the initial mutation probability , and the maximum number of iterations . In the early stage of iteration, such as , the mutation probability is:

[0103]

[0104] In the later stage of iteration, such as , the mutation probability is:

[0105]

[0106] In practical applications, the initial mutation probability and the maximum number of iterations are set reasonably according to the complexity and size of the countermeasure problem. For complex countermeasure scenarios, a larger maximum number of iterations and a relatively higher initial mutation probability may be needed to ensure that the algorithm has enough time and ability to explore the solution space; for simple scenarios, these parameters can be appropriately reduced to improve the algorithm running efficiency. Through this adaptive mutation probability method, the algorithm can adjust the mutation degree according to the actual situation at different stages.

[0107] It should be noted that in this paper, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device.

[0108] While embodiments of the application have been shown and described, it is to be understood that the embodiments described are merely exemplary of the principles and application of the present application. Numerous modifications and adaptions can be effected without departing from the spirit and scope of the present application, which is not limited to the exact construction and arrangement described. It is intended, therefore, to cover all modifications and adaptions that fall within the scope of the claims and their equivalents.

Claims

1. A method for constructing a dynamic defense model for drone countermeasures, characterized in that, The method includes: Step S1: Collect real-time data of the UAV's flight environment, the UAV's own status data, and relevant data of the countermeasures equipment to determine the parameters required for model calculation; among which, the real-time data of the UAV's flight environment includes at least meteorological data and geographic information data; the UAV's own status data includes at least flight speed, flight altitude, and flight attitude data; the countermeasures equipment data includes at least equipment location, equipment power, and equipment effective countermeasure range data. Step S2: Considering the dynamic characteristics of UAV flight and various changing factors in the countermeasure process, establish a UAV countermeasure dynamic defense model based on an adaptive state space model; by predicting the UAV flight trajectory, the response time of the countermeasure equipment, and the time-varying characteristics of the interference effect, establish time-varying state transition equations, observation equations, and control input equations to handle various constraints in dynamic defense. Step S3: With the goal of maximizing the effective countermeasure probability against UAVs and minimizing the countermeasure resource consumption, and in combination with the actual operating environment of the UAV countermeasure system, establish a new optimization method and an optimization model of the dynamic defense model to achieve predictive control of the countermeasure strategy. Step S4: For the constructed optimization model, the improved genetic algorithm is used to solve it, and finally the countermeasure strategy with the best comprehensive performance is obtained, so as to achieve effective dynamic defense against UAVs. The specific steps for establishing the optimization model in step S3 include: Step S31: Set the assumptions of the model, assuming that each countermeasure device can only countermeasure one drone at a time, that the drone will not exhibit abnormal flight behavior after being subjected to countermeasure interference, and that the total amount of countermeasure resources is limited and can be monitored in real time. Step S32: Set the signs of known parameters or sets in the model and the decision variables; This indicates the set of drones that currently require countermeasures. Indicates the first A drone, Indicates countermeasure equipment For drones The probability of a successful counterattack. Indicates countermeasure equipment Resource consumption coefficient, Indicates countermeasure equipment The maximum available resources, Indicates countermeasure equipment For drones The decision variable regarding whether to retaliate. This indicates that countermeasures will be taken. This indicates that no countermeasures will be taken. Indicates the time step; Step S33: Construct the objective function, which is a comprehensive objective of maximizing the effective countermeasure probability against UAVs and minimizing the countermeasure resource consumption. The calculation formula is as follows: ； in These are weighting coefficients used to balance the relationship between the probability of counterattack and resource consumption; Step S34: Establish the constraints for the model: Constraint 1: Countermeasure equipment resource constraint, ensuring that the resource consumption of the countermeasure equipment in each countermeasure operation does not exceed its maximum available resource amount, i.e. ; Constraint 2: Countermeasure equipment operating status constraint, ensuring that each countermeasure device can only counter one drone at a time, i.e. ; Constraint 3: Value constraints for decision variables, decision variables It can only take the value 0 or 1, that is .

2. The method for constructing a dynamic defense model for drone countermeasures according to claim 1, characterized in that, The specific steps for establishing the adaptive state-space model in S2 include: Step S21: Set the assumptions, assuming that the boundaries of the countermeasures area are clear, the flight behavior of the UAV in the countermeasures area follows the basic dynamics principle, and the propagation of the interference signal of the countermeasures equipment is not severely affected by complex terrain. Step S22: Establish the time-varying state transition equation for the UAV flight; let... Indicates the drone at a certain time The state vector; Indicates the countermeasures equipment at any time The control input vector; The state transition matrix represents the change of the UAV's own dynamic characteristics over time. The control input matrix represents the influence of the countermeasure device's control input on the UAV's state; therefore, the time-varying state transition equation is: ; Step S23: Establish the observation equation, let... Indicates at time The observation vector of the UAV's state. The observation matrix represents the mapping of the UAV's actual state to the observation space; the observation equation is: ,in This represents the observation noise vector, used to describe the uncertainties during the observation process; Step S24: Considering the interference factors and environmental changes during the countermeasure process, adaptively adjust the state transition equation and observation equation; by introducing adaptive parameters. For the state transition matrix Control input matrix and observation matrix Real-time updates are performed to adapt to dynamic changes in the drone's flight status and the countermeasure environment; the update formula is: , , .

3. The method for constructing a dynamic defense model for drone countermeasures according to claim 1, characterized in that, The specific steps of the improved genetic algorithm in step S4 include: Step S41: Initialize the population. Based on the decision variable range of the countermeasure strategy, randomly generate a certain number of initial individuals. Each individual represents a combination of countermeasure strategies to form the initial population. Step S42: Calculate the fitness value. Based on the objective function constructed in step S3, calculate the fitness value of each individual. The higher the fitness value, the better the countermeasure strategy. Step S43: Using the roulette wheel selection method, a certain number of individuals are selected from the current population to enter the next generation population based on their fitness values. Individuals with higher fitness values ​​have a greater probability of being selected. Step S44: Perform a crossover operation on the selected individuals with a certain crossover probability. Two individuals are randomly selected, and some of their genes are exchanged to generate new individuals, increasing the diversity of the population; Step S45: With a certain mutation probability Mutation operations are performed on newly generated individuals to randomly change some gene values ​​of the individuals, preventing the algorithm from getting trapped in local optima. Step S46: Repeat steps S42-S45 until the preset termination condition is met. At this point, the individual with the highest fitness value in the population is the optimal countermeasure strategy.

4. The method for constructing a dynamic defense model for drone countermeasures according to claim 2, characterized in that, Adaptive parameters in step S24 The update methods include: Error in UAV state estimation based on Kalman filter algorithm Perform calculations. ,in This is an estimate of the drone's state; Based on state estimation error Calculate adaptive parameters based on preset adaptive rules. .

5. The method for constructing a dynamic defense model for drone countermeasures according to claim 1, characterized in that, The probability of successful countermeasure in step S33 The calculation method is as follows: Considering the power of countermeasures equipment Distance from the drone The degree of matching between the interference signal frequency and the UAV's receiving frequency Factors affecting the probability of successful countermeasures The calculation formula is: ； in This is the influence coefficient.

6. The method for constructing a dynamic defense model for drone countermeasures according to claim 3, characterized in that, In step S44, a multi-point crossover method is adopted. The specific steps are as follows: multiple crossover points are randomly generated, and the genes of the two parent individuals are exchanged at the crossover points to generate two offspring individuals.

7. The method for constructing a dynamic defense model for drone countermeasures according to claim 3, characterized in that, In step S45, an adaptive mutation probability is used, specifically as follows: With the number of iterations The increase in mutation probability Gradually decrease, the calculation formula is: ,in The initial mutation probability, This represents the maximum number of iterations.

8. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to invoke instructions stored in the memory to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1 to 7.

Images