Method, device and equipment for evaluating combat situation of unmanned aerial vehicle group and medium

Abstract

The invention discloses an unmanned aerial vehicle group combat situation assessment method, device and equipment and a medium, and relates to a fuzzy reasoning calculation technology in the field of artificial intelligence, and the method comprises the steps: screening out all first unmanned aerial vehicles, determining an unmanned aerial vehicle assessment range, and constructing all unmanned aerial vehicle sets based on all second unmanned aerial vehicles in the unmanned aerial vehicle assessment range; performing vector calculation on each unmanned aerial vehicle set by using the air combat situation advantage evaluation model to obtain each situation evaluation vector, and generating a corresponding comprehensive situation evaluation matrix based on each situation evaluation vector; and performing parallel fuzzy reasoning calculation on each comprehensive situation evaluation matrix by using a parallel fuzzy reasoning system based on the air combat situation advantage evaluation model to obtain a comprehensive evaluation value of each advantage, and realizing combat situation evaluation of the unmanned aerial vehicle group based on the comprehensive evaluation value of each advantage. According to the invention, real-time assessment of the combat situation of the unmanned aerial vehicle group can be realized, the analysis time of situation assessment is reduced, the accuracy and efficiency of situation assessment are improved, and an important basis is provided for subsequent combat decision making of the unmanned aerial vehicle group.

Description

Technical Field

[0001] The present invention relates to fuzzy reasoning computing technology in the field of artificial intelligence, and in particular to a combat situation assessment method, device, equipment and medium for a group of unmanned aerial vehicles. Background Art

[0002] The air combat situation is complicated and the battlefield situation changes rapidly. It is very difficult for the warring parties to quickly grasp the air combat situation and make accurate decisions. Therefore, making fast, effective and accurate decisions based on the situation of the two opposing parties has become an important topic in the field of drone combat research. In air combat, due to the existence of uncertainty, incomplete information and dynamics, drone swarm confrontation is a very complex problem, which makes multi-drone confrontation more nonlinear. In addition, drones are always in a high-speed maneuvering state. When the number is large, the solution space will increase explosively. At present, traditional methods are difficult to meet the real-time requirements of air combat situation analysis.

[0003] From the above, it can be seen that how to achieve real-time assessment of the combat situation of drone swarms, reduce the analysis time of situation assessment, and improve the accuracy and efficiency of situation assessment, so as to provide an important basis for subsequent drone swarm combat decisions is a problem to be solved in this field. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a method, device, equipment and medium for evaluating the combat situation of a drone swarm, which can realize real-time evaluation of the combat situation of a drone swarm, reduce the analysis time of situation evaluation, and improve the accuracy and efficiency of situation evaluation, thereby providing an important basis for subsequent drone swarm combat decisions. The specific scheme is as follows:

[0005] In a first aspect, the present application discloses a method for assessing the combat situation of a drone swarm, comprising:

[0006] Selecting first drones from the drone group, determining a drone evaluation range based on the first drones, and constructing a set of drones to be evaluated based on second drones in the drone evaluation range;

[0007] Performing vector calculation on each of the drone sets using a preset air combat situation advantage assessment model to obtain each situation assessment vector, and generating a corresponding comprehensive situation assessment matrix based on each of the situation assessment vectors;

[0008] A preset parallel fuzzy reasoning system is used to perform parallel fuzzy reasoning calculations on each of the comprehensive situation assessment matrices based on the air combat situation advantage assessment model to obtain each advantage comprehensive assessment value, and the combat situation assessment of the drone group is implemented based on each advantage comprehensive assessment value.

[0009] Optionally, the selecting each first drone from the drone group and determining a drone evaluation range according to each first drone includes:

[0010] Randomly selecting a single drone from all the drones in the drone group as a first drone to obtain each of the first drones;

[0011] Taking the first drone as the center and based on a preset radius, a drone spherical range is determined, and the drone spherical range is used as the drone evaluation range to obtain the evaluation range of each drone.

[0012] Optionally, the constructing a set of drones to be evaluated based on each second drone in the drone evaluation range includes:

[0013] Determining the number of all the second drones in the drone evaluation range;

[0014] It is determined whether the number is greater than a preset drone threshold; if the number is not greater than the preset drone threshold, a set of drones to be evaluated is generated based on all the second drones in the drone evaluation range.

[0015] Optionally, after determining whether the number is greater than a preset drone threshold, the method further includes:

[0016] If the number is greater than the preset drone threshold, determining the boundary range of the drone assessment range;

[0017] The second drones corresponding to the boundary range are clipped, and the sets of drones to be evaluated are generated based on the clipped second drones in the drone evaluation range.

[0018] Optionally, before performing vector calculation on each of the drone sets using a preset air combat situation advantage assessment model, the method further includes:

[0019] Construct distance advantage function model, angle advantage function model, speed advantage function model and height advantage function model respectively;

[0020] The air combat situation advantage assessment model is generated based on the distance advantage function model, the angle advantage function model, the speed advantage function model and the altitude advantage function model.

[0021] Optionally, the parallel fuzzy inference system consists of a fuzzy inference array, a data storage pool, a row scheduling module and a plurality of row distributors; wherein the fuzzy inference array consists of row and column fuzzy inference calculation units.

[0022] Optionally, the using of a preset parallel fuzzy inference system and performing parallel fuzzy inference calculations on each of the comprehensive situation assessment matrices based on the air combat situation advantage assessment model to obtain each advantage comprehensive assessment value includes:

[0023] Using the row-column fuzzy reasoning calculation unit in the preset parallel fuzzy reasoning system and based on the air combat situation advantage assessment model to obtain non-fuzzy data, and using a membership function to perform fuzzification processing on the non-fuzzy data to obtain processed data;

[0024] The processed data is subjected to inference mapping and defuzzification operations to obtain comprehensive evaluation values ​​of the advantages.

[0025] In a second aspect, the present application discloses a combat situation assessment device for a drone group, comprising:

[0026] A set construction module, used to select each first drone from the drone group, determine a drone evaluation range according to each first drone, and construct each drone set to be evaluated based on each second drone in the drone evaluation range;

[0027] An evaluation matrix generation module is used to perform vector calculation on each of the drone sets using a preset air combat situation advantage evaluation model to obtain each situation evaluation vector, and generate a corresponding comprehensive situation evaluation matrix based on each of the situation evaluation vectors;

[0028] The combat situation assessment module is used to utilize a preset parallel fuzzy reasoning system and perform parallel fuzzy reasoning calculations on each of the comprehensive situation assessment matrices based on the air combat situation advantage assessment model to obtain each advantage comprehensive assessment value, and realize combat situation assessment of the drone group based on each advantage comprehensive assessment value.

[0029] In a third aspect, the present application discloses an electronic device, comprising:

[0030] Memory, used to store computer programs;

[0031] A processor is used to execute the computer program to implement the aforementioned method for assessing the combat situation of a swarm of unmanned aerial vehicles.

[0032] In a fourth aspect, the present application discloses a computer storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the steps of the aforementioned method for assessing the combat situation of a drone swarm disclosed above are implemented.

[0033] It can be seen that the present application provides a method for assessing the combat situation of a swarm of drones, including screening out each first drone from the drone swarm, determining a drone assessment range based on each first drone, and constructing each drone set to be assessed based on each second drone in the drone assessment range; performing vector calculations on each of the drone sets using a preset air combat situation advantage assessment model to obtain each situation assessment vector, and generating a corresponding comprehensive situation assessment matrix based on each of the situation assessment vectors; performing parallel fuzzy reasoning calculations on each of the comprehensive situation assessment matrices using a preset parallel fuzzy reasoning system and based on the air combat situation advantage assessment model to obtain each advantage comprehensive assessment value, and realizing combat situation assessment of the drone swarm based on each of the advantage comprehensive assessment values. The present application analyzes the combat situation of each first drone relative to the second drone adjacent to it. First, the drone assessment range is defined with each first drone as the center to improve the accuracy and efficiency of the situation assessment. By constructing an air combat situation advantage assessment model, vector calculations are performed on each drone set to generate a corresponding comprehensive situation assessment matrix. A parallel fuzzy inference system is used to perform parallel fuzzy inference calculations on the comprehensive situation assessment matrix to obtain comprehensive evaluation values ​​of each advantage, thereby realizing real-time assessment of the combat situation of the drone group, reducing the analysis time of the situation assessment, and providing an important basis for subsequent drone group combat decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0035] Figure 1 A flowchart of a method for assessing the combat situation of a drone swarm disclosed in this application;

[0036] Figure 2 Constructing an example graph for a collection of drones disclosed in this application;

[0037] Figure 3 A flowchart of a method for assessing the combat situation of a drone swarm disclosed in this application;

[0038] Figure 4 A functional structure diagram of a fuzzy reasoning calculation unit disclosed in this application;

[0039] Figure 5 A structural diagram of a parallel fuzzy inference system disclosed in this application;

[0040] Figure 6This is a schematic diagram of the structure of a combat situation assessment device for a drone group disclosed in the present application;

[0041] Figure 7 A structural diagram of an electronic device provided for this application. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0043] The air combat situation is complicated and the battlefield situation changes rapidly. It is very difficult for the warring parties to quickly grasp the air combat situation and make accurate decisions. Therefore, making fast, effective and accurate decisions based on the situation of the two opposing parties has become an important topic in the field of drone combat research today. In air combat, due to the existence of uncertainty, incomplete information and dynamics, drone swarm confrontation is a very complex problem, which makes multi-drone confrontation more nonlinear. In addition, drones are always in a high-speed maneuvering state. When the number is large, the solution space will increase explosively. At present, traditional methods are difficult to meet the real-time requirements of air combat situation analysis. As can be seen from the above, how to realize the real-time evaluation of the combat situation of drone swarms, reduce the analysis time of situation evaluation, improve the accuracy and efficiency of situation evaluation, and thus provide an important basis for subsequent drone swarm combat decisions is a problem to be solved in this field.

[0044] See also Figure 1 As shown, the embodiment of the present invention discloses a method for assessing the combat situation of a drone group, which may specifically include:

[0045] Step S11: Filter out first drones from the drone group, determine a drone evaluation range based on the first drones, and construct a set of drones to be evaluated based on second drones in the drone evaluation range.

[0046] In this embodiment, a single drone is randomly selected from all the drones in the drone group as the first drone to obtain each of the first drones, and a drone spherical range is determined based on a preset radius with the first drone as the center, and the drone spherical range is used as the drone evaluation range to obtain the evaluation range of each drone, and each drone set to be evaluated is constructed based on each second drone in the drone evaluation range.

[0047] Specifically, the temporary aircraft set (i.e., the drone set) of our aircraft is defined with each of our aircraft (i.e., the first drone) as the center. Figure 2 The red machine A in the figure identifies the nearby enemy drones ( Figure 2 An example of a drone set including the rest of the drones except the red drone A, i.e., the second drone, is as follows: Figure 2 As shown: at time t, in the air combat three-dimensional space coordinate system XYZ, with the red aircraft A (i.e. the first drone) as the center and R A A sphere is defined as the radius, and all the second drones enclosed in the three-dimensional space of the sphere are regarded as the red side’s adjacent enemy aircraft at the current moment (hereinafter referred to as temporary aircraft), and the temporary aircraft set of the red aircraft A (i.e., the drone set) P is constructed. A ={p i |D i ≤R,1≤i≤N E}, and the number of temporary machines cannot exceed the upper limit N of the number of temporary machines. E , where the i-th (1≤i≤N E ) The three-dimensional Euclidean distance D between the blue machine and the red machine i Should not be greater than the radius R of the sphere, the three-dimensional Euclidean distance D between the blue machine and the red machine i The calculation formula is as follows:

[0048]

[0049] Among them, the current coordinates of the i-th second drone are (x i ,y i , z i ), the coordinates of the first drone are (x A ,y A , z A ).

[0050] The specific construction process of the drone set is as follows: determine the number of all the second drones in the drone evaluation range; determine whether the number is greater than a preset drone threshold; if the number is not greater than the preset drone threshold, generate each drone set to be evaluated based on all the second drones in the drone evaluation range; if the number is greater than the preset drone threshold, determine the boundary range of the drone evaluation range, crop the second drones corresponding to the boundary range, and generate each drone set to be evaluated based on the cropped second drones in the drone evaluation range.

[0051] If the number of blue machines enclosed in the spherical space exceeds N E , it is necessary to cluster and prune the ad hoc set. Figure 2The temporary machines located at the boundary of the sphere are called boundary machines. E When , the boundary machines are trimmed and removed from the set of ad hoc machines. Figure 2 Several enemy aircraft with dense spatial positions in the middle sphere can form an aircraft cluster. At this time, the aircraft with the smallest Euclidean distance from red aircraft A can be selected from the cluster as the host of the cluster. The host of the cluster will replace all aircraft in the entire aircraft cluster to participate in the subsequent air combat situation assessment. For the delineation of specific aircraft in the aircraft cluster, several aircraft with dense spatial positions are selected. The selection basis is that the Chebyshev distance between aircraft does not exceed ε c Multiple ad-hoc clusters of c The calculation formula is as follows:

[0052] ε c =max{|x i -x j |,|y i -y j |,|z i -z j |},i,j∈P A , andi≠j.

[0053] Step S12: performing vector calculation on each of the drone sets using a preset air combat situation advantage assessment model to obtain each situation assessment vector, and generating a corresponding comprehensive situation assessment matrix based on each of the situation assessment vectors.

[0054] In this embodiment, the temporary machine set P for red machine A is A Each enemy is ready to construct a situation assessment vector E A , which can be expressed as:

[0055]

[0056] in, represents the temporary set P of red machine A A The situation assessment value of the ith emergency in N A Indicates P A The number of random machines and N A ≤N E Thus, we can construct a comprehensive situation assessment matrix of our drone swarm relative to the enemy drone swarm. Where N R is the number of our drones, N E The upper limit of the number of our drones is N. E , use 0 to fill. Use periodic collection of real data to PThe real-time situation assessment value is updated to facilitate the combat command system to conduct real-time analysis of the air combat situation and provide a basis for air combat maneuver decisions.

[0057] Step S13: Utilize a preset parallel fuzzy reasoning system and perform parallel fuzzy reasoning calculations on each of the comprehensive situation assessment matrices based on the air combat situation advantage assessment model to obtain each advantage comprehensive assessment value, and implement combat situation assessment of the drone group based on each advantage comprehensive assessment value.

[0058] In this embodiment, each first drone is screened out from the drone group, a drone evaluation range is determined based on each first drone, and each drone set to be evaluated is constructed based on each second drone in the drone evaluation range; vector calculation is performed on each drone set using a preset air combat situation advantage evaluation model to obtain each situation evaluation vector, and a corresponding comprehensive situation evaluation matrix is ​​generated based on each situation evaluation vector; parallel fuzzy reasoning calculation is performed on each comprehensive situation evaluation matrix based on the preset parallel fuzzy reasoning system and the air combat situation advantage evaluation model to obtain each advantage comprehensive evaluation value, and combat situation evaluation of the drone group is implemented based on each advantage comprehensive evaluation value. The present application analyzes the combat situation of each first drone relative to the second drone adjacent to it. First, the drone assessment range is defined with each first drone as the center to improve the accuracy and efficiency of the situation assessment. By constructing an air combat situation advantage assessment model, vector calculations are performed on each drone set to generate a corresponding comprehensive situation assessment matrix. A parallel fuzzy inference system is used to perform parallel fuzzy inference calculations on the comprehensive situation assessment matrix to obtain comprehensive evaluation values ​​of each advantage, thereby realizing real-time assessment of the combat situation of the drone group, reducing the analysis time of the situation assessment, and providing an important basis for subsequent drone group combat decisions.

[0059] See also Figure 3 As shown, the embodiment of the present invention discloses a method for assessing the combat situation of a drone group, which may specifically include:

[0060] Step S21: Filter out first drones from the drone group, determine a drone evaluation range based on the first drones, and construct a set of drones to be evaluated based on second drones in the drone evaluation range.

[0061] Step S22: constructing a distance advantage function model, an angle advantage function model, a speed advantage function model and an altitude advantage function model respectively, and generating the air combat situation advantage assessment model based on the distance advantage function model, the angle advantage function model, the speed advantage function model and the altitude advantage function model.

[0062] The method for calculating the situation assessment value of red aircraft A relative to each adjacent aircraft in the situation assessment matrix of this application is mainly completed by constructing an air combat situation advantage assessment model: Under the air combat situation, the advantage of the attack aircraft over the attack target can be quantitatively measured by the situation advantage assessment value. When constructing the situation advantage assessment method, it is necessary to take into account the performance of airborne radars, missiles and the battlefield situation of both sides, which will be affected by the distance, angle, speed and altitude of the opposing sides. To this end, we construct an air combat situation advantage assessment model based on the distance, angle, speed and altitude advantage function model. (1) Distance advantage function model: The distance between the attack aircraft and the target can be divided into the maximum detection distance of the radar Maximum missile attack range Minimum missile attack distance The maximum distance the target cannot escape Minimum distance from the target that cannot be escaped When the enemy aircraft is within the inescapable zone of our missiles, the distance advantage takes the maximum value; when it exceeds the target inescapable zone, the distance advantage is normally distributed with respect to the distance between the enemy and our aircraft; when the distance is outside the missile attack range, the distance advantage takes the minimum value of 0. Therefore, the distance advantage model can be constructed as:

[0063]

[0064] (2) Angle advantage function model: Based on the analysis of the impact of the target azimuth on the advantage assessment, the azimuth is divided into four areas: the no-escape zone, the missile attack zone, the radar search zone, and the area outside the radar search zone. Therefore, the angle advantage model can be constructed as follows:

[0065]

[0066] Among them, α is the angle between the velocity vector of our attack aircraft and the line connecting the target, β is the angle between the velocity vector of the enemy aircraft and the line connecting ours, and β is in the interval [-180°, 180°]. is the maximum search angle of the radar, is the maximum off-axis launch angle of the missile, is the cone angle of the no-escape zone.

[0067] (3) Speed ​​advantage function model: When designing a speed advantage evaluation model, it is necessary to first define the optimal attack speed. The speed will be determined based on the distance D between the target and us and the maximum launch distance of the missile. Distance from the maximum no-escape zone To set, the optimal speed can be expressed as:

[0068]

[0069] Among them, V Ris the flight speed of our drone. Therefore, the speed advantage model can be constructed as:

[0070]

[0071] Among them, V B is the enemy aircraft's flight speed, γ 1 , γ 2 It is the ratio of enemy and friendly flight speed.

[0072] (4) Height advantage function model: During the confrontation, the height difference between the enemy and us is:

[0073] Δh=h R -h B ;

[0074] Among them, h R is our flight altitude, h B The enemy aircraft's flying altitude.

[0075] In order to gain the height advantage of launching missiles, Δh is usually increased and the optimal height difference is set at [h * ,h * +δ h ] range, when Δh is in this interval, the height advantage takes the maximum value of 1, and in other cases, the height advantage value follows a normal distribution. The height advantage model can be constructed as:

[0076]

[0077] Construction of air combat situation assessment model: Comprehensive analysis of distance, angle, speed, and altitude advantage parameters, the air combat situation assessment model can be constructed as follows:

[0078] M E =μ D ·M D (D)+μ α ·M α (α)+μ v ·M v (V R )+μ H ·M H (Δh);

[0079] where μ D , μ α , μ v , μ H are the weight factors of distance, angle, speed and height advantages, respectively, and M E The comprehensive evaluation value of the advantages of these four parameter factors is used to measure the advantages of our UAV's current situation relative to the enemy's UAV. This evaluation value can be used by the air combat command system to decide the next maneuver with the greatest advantage.

[0080] Step S23: performing vector calculation on each of the drone sets using a preset air combat situation advantage assessment model to obtain each situation assessment vector, and generating a corresponding comprehensive situation assessment matrix based on each of the situation assessment vectors.

[0081] Step S24: Utilize a preset parallel fuzzy reasoning system and perform parallel fuzzy reasoning calculations on each of the comprehensive situation assessment matrices based on the air combat situation advantage assessment model to obtain each advantage comprehensive assessment value, and implement combat situation assessment of the drone group based on each advantage comprehensive assessment value.

[0082] In this embodiment, the parallel fuzzy inference system is composed of a fuzzy inference array, a data storage pool, a row scheduling module and a plurality of row distributors; wherein the fuzzy inference array is composed of row-column fuzzy inference calculation units.

[0083] Specifically, the row-column fuzzy reasoning calculation unit in the preset parallel fuzzy reasoning system is used to obtain non-fuzzy data based on the air combat situation advantage assessment model, and the non-fuzzy data is fuzzified using a membership function to obtain processed data; the processed data is subjected to reasoning mapping and defuzzification operations to obtain each of the comprehensive advantage assessment values, and the combat situation assessment of the drone group is implemented based on each of the comprehensive advantage assessment values.

[0084] This application uses a parallel fuzzy inference system to perform reasoning calculations on the situation assessment matrix EP of our drone group relative to the enemy drone group. Each element value in the matrix is ​​calculated by a fuzzy inference calculation unit to complete the calculation of the situation assessment value. The fuzzy inference calculation unit is constructed from the fuzzy inference model and rules, mainly including a data fuzzification unit, a knowledge base, a reasoning decision unit, and a data defuzzification unit. The functional structure of the fuzzy inference calculation unit is as follows: Figure 4 As shown in the figure, the knowledge base mainly includes the fuzzy inference library and the fuzzy set database. The specific implementation process of the fuzzy reasoning calculation unit is as follows: 1) Obtain input information. The input data mainly includes data such as speed, angle, distance, height and initialization data of the advantages of each parameter factor, as well as non-fuzzy data such as the current position coordinate information of our aircraft. 2) Fuzzification of input information. The membership function is used to fuzzify the input information. The relevant data of various parameter factors will be sent to the fuzzy set database of the database for use in reasoning. 3) Reasoning process. The fuzzified input information is mapped to the rule library, and then the fuzzy reasoning decision unit uses the reasoning rules to perform fuzzy reasoning. 4) Defuzzification. The inferred fuzzy result is converted into a non-fuzzy value, and the specific output result is the comprehensive evaluation value of the advantages of each parameter factor.

[0085] This application mainly uses the triangle membership function to perform fuzzy processing on the input information. (1) Membership function calculation: The specific triangle membership function formula is as follows:

[0086]

[0087] The values ​​of a, b, and c have different basic settings depending on the parameters.

[0088] (2) Rule base setting criteria: The fuzzy rule base is mainly constructed based on the decision-making knowledge of expert experience, describing the actions that the two opposing parties can take under different situations. The rule base generally uses production rules to describe empirical knowledge. According to a set of tactical descriptions summarized from the inference and decision-making experience used in the confrontation, production rules are formulated, and then a reasonable rule base is formed through expert analysis and improvement. Production rules consist of two parts: conditions (if) and conclusions (then). The multiple multidimensional reasoning rules are as follows:

[0089] Premise 1: if m 1 is M D and m 2 is M α and m 3 is M v and m 4 is M H ,

[0090] then u 1 is μ D or u 2 is μ α or u 3 is μ v Or 4 is μ H .

[0091] Premise 2: if m 1 *is M D *andm 2 *is M α *and m 3 *is M v *and m 4 *is M H *,

[0092] Conclusion: then u 1 *is μ D *or u 2 *is μ α *or u 3 *is μv *or u 4 *is μ H *.

[0093] Among them, m 1 , m 2 , m 3 , m 4 is the input parameter M D , M α , M v , M H The value of u 1 ,u 2 ,u 3 ,u 4 is the output parameter weight μ D , μ α , μ v , μ H The value of m 1 *, m 2 *, m 3 *, m 4 * is the input parameter M D *, M α *, M v *, M H * value, u 1 *,u 2 *,u 3 *,u 4 * Output parameter weight μ D *, μ α *, μ v *, μ H *Value. Based on the above-described influence of the distance, angle, speed, and altitude of the two drones on the combat, the following criteria are used to set the rules:

[0094] Principle 1: Avoid a significant disadvantage in a certain parameter factor. If a parameter factor has a shortcoming, we should try to choose a rule that compensates for the deficiency of the factor to quickly improve our advantage. For example, when we are in the missile attack area of ​​the enemy aircraft or the target's inescapable area, we should increase the distance between the two sides as soon as possible, or increase the angle between the enemy aircraft's velocity vector and our position, and escape from the enemy aircraft's attack area as soon as possible.

[0095] Principle 2: If a parameter factor is in a state of altitude advantage, the advantages of other parameters should be continuously increased in the hope of achieving the conditions for attacking the enemy aircraft. In close-range air combat, speed has the greatest advantage; the second is altitude, which can convert potential energy into kinetic energy; and then angle, which is the basis for launching an effective attack on the enemy aircraft. Therefore, when the enemy aircraft is in the area where our target cannot escape or the missile attack area, we can appropriately increase the speed or angle advantage on the premise that we have a high altitude advantage to increase the probability of hitting the enemy aircraft at close range.

[0096] Principle 3: If our advantage over the enemy in a certain parameter factor is small, we should adopt an escape strategy to avoid the enemy's attack while preventing it from getting worse. For example, if our current azimuth angle is not advantageous, but we have an advantage in the distance parameter, we should choose to abandon the distance advantage and appropriately increase the height and speed advantages to avoid the angle disadvantage.

[0097] (3) Defuzzification calculation: In order to achieve a smoother fuzzy reasoning output result, the centroid method is selected as the defuzzification algorithm, and the fuzzy output of each parameter factor is defuzzified. The specific formula is as follows:

[0098]

[0099] Among them, μ z is the result after defuzzification of advantage weights, G z (M i ) is the centroid value calculated based on the advantage evaluation value of each parameter factor, A i The area value calculated according to the advantage evaluation value of each parameter factor is obtained by dividing the cumulative sum of the product of the center of gravity and the area by the cumulative sum of the area through the centroid method, and the advantage comprehensive evaluation value of each parameter factor after defuzzification can be obtained.

[0100] The present invention uses a parallel fuzzy inference system composed of multiple fuzzy inference calculation units to calculate the situation assessment matrix E p , where each fuzzy inference calculation unit is used to calculate the matrix E P The parallel fuzzy inference system is mainly composed of a fuzzy inference computing unit array. The number of fuzzy inference computing units in each row corresponds to the matrix E P The number of columns N E , we can realize the matrix E P Parallel reasoning and calculation of the value of a row of elements; at the same time, the matrix E P The multiple rows are dispatched to the multiple rows of fuzzy inference calculation units of the parallel fuzzy inference system to perform inference calculations in parallel. The specific structure diagram is as follows Figure 5 shown. Figure 5The parallel fuzzy inference system consists of a fuzzy inference array, a data storage pool, a row scheduling module, and multiple row distributors. The fuzzy inference array is used to complete the calculation of the situation assessment matrix. It consists of row and column fuzzy inference calculation units. The number of calculation units in each row is fixed N. E The data storage pool is used to store the location information data of each red and blue drone in the enemy and friendly dual-engine drone group at the current moment, the basic parameters used for situation assessment calculation, the situation assessment matrix calculation results and other data. When storing, the data of each red drone and its temporary drone set are stored in a centralized manner to facilitate the calculation of the parallel reasoning system; at the same time, the data in the data storage pool will be updated periodically, and a new round of situation assessment calculation will be started each time the data is updated. The row scheduling module is used to update the situation assessment matrix F P Manage the matrix row calculation, record the information of uncalculated and calculated rows, complete the scheduling of row calculation, and send the information of the rows to be calculated to the corresponding row distributor. The row distributor receives the information of the rows to be calculated from the row scheduling module, obtains all the data to be calculated in the corresponding row from the corresponding position in the data storage pool according to the row information, and distributes it to the corresponding number of fuzzy reasoning calculation units according to the number of elements in the row to be calculated for calculation, and finally recovers the reasoning calculation results and stores them in the data storage pool.

[0101] The process of completing the situation assessment matrix calculation by the parallel fuzzy reasoning system is as follows: Step 1, start this round of situation data update of the enemy and our fleet, and update the latest situation data to the data storage pool; Step 2, the row scheduling module receives the start command of a new round of situation assessment calculation, obtains the row and column information of the current situation assessment matrix and the data storage information, and starts the calculation; Step 3, the row scheduling module distributes the uncalculated row information to m row distributors at the same time, and marks the distributed rows as distributed identifiers; Step 4, the row distributor receives the row information of the matrix to be calculated sent by the row scheduling module, and according to the address information of the data storage, goes to the data storage pool to read all the data in the row to be calculated, and according to the number of elements in this row, sends the calculated data to the fuzzy reasoning array row corresponding to the row distributor. ; Step 5, the fuzzy reasoning calculation unit receives the calculation data sent from the row distributor, starts the fuzzy reasoning calculation, and returns the calculation result to the row distributor; Step 6, the row distributor receives the calculation result returned by the fuzzy reasoning calculation unit, and after all the calculation results are recovered, they are stored in the data storage space of the corresponding row of the situation assessment matrix in the data storage pool; Step 7, the row distributor sends a calculation completion confirmation to the row scheduling module; Step 8, the row scheduling module receives the calculation completion confirmation sent from the row distributor, checks whether there is any uncalculated row information, if so, go to step 3, and the row scheduling module sends the row information to be calculated to the designated row distributor; otherwise, all row data have been distributed, go to step 9; Step 9, this round of calculation of the situation assessment matrix is ​​completed.

[0102] The present application adopts the method of defining an ad hoc set for each of our drones, dividing enemy aircraft into several clusters with our aircraft as the center, and evaluating the combat situation of our aircraft relative to the enemy aircraft in the ad hoc set, so as to improve the accuracy and efficiency of our aircraft situation evaluation; a situation evaluation model is proposed to analyze and model the situation of our aircraft relative to the enemy aircraft, and the situation evaluation values ​​of our fleet relative to the enemy fleet are organized into a situation evaluation matrix, which is conducive to achieving the real-time and maneuverability of the situation evaluation of our drones, and provides an important basis for making correct maneuver decisions; and, the present application proposes a parallel fuzzy reasoning system to calculate the situation evaluation matrix of the drone fleet. The system adopts a fuzzy reasoning calculation array to complete the calculation of the situation evaluation matrix, and adopts scheduling based on the behavior unit of the situation evaluation matrix to realize the parallel calculation of the situation analysis of a single our aircraft relative to the ad hoc set, and at the same time realizes the parallel calculation of the situation evaluation of multiple our aircraft, which can effectively reduce the time of situation analysis, and is conducive to improving the real-time and efficiency of the combat situation evaluation of the drone fleet.

[0103] In this embodiment, each first drone is screened out from the drone group, a drone evaluation range is determined based on each first drone, and each drone set to be evaluated is constructed based on each second drone in the drone evaluation range; vector calculation is performed on each drone set using a preset air combat situation advantage evaluation model to obtain each situation evaluation vector, and a corresponding comprehensive situation evaluation matrix is ​​generated based on each situation evaluation vector; parallel fuzzy reasoning calculation is performed on each comprehensive situation evaluation matrix based on the preset parallel fuzzy reasoning system and the air combat situation advantage evaluation model to obtain each advantage comprehensive evaluation value, and combat situation evaluation of the drone group is implemented based on each advantage comprehensive evaluation value. The present application analyzes the combat situation of each first drone relative to the second drone adjacent to it. First, the drone assessment range is defined with each first drone as the center to improve the accuracy and efficiency of the situation assessment. By constructing an air combat situation advantage assessment model, vector calculations are performed on each drone set to generate a corresponding comprehensive situation assessment matrix. A parallel fuzzy inference system is used to perform parallel fuzzy inference calculations on the comprehensive situation assessment matrix to obtain comprehensive evaluation values ​​of each advantage, thereby realizing real-time assessment of the combat situation of the drone group, reducing the analysis time of the situation assessment, and providing an important basis for subsequent drone group combat decisions.

[0104] See also Figure 6 As shown, the embodiment of the present invention discloses a combat situation assessment device for a drone group, which may specifically include:

[0105] A set construction module 11 is used to select each first drone from the drone group, determine a drone evaluation range according to each first drone, and construct each drone set to be evaluated based on each second drone in the drone evaluation range;

[0106] An evaluation matrix generation module 12 is used to perform vector calculation on each of the drone sets using a preset air combat situation advantage evaluation model to obtain each situation evaluation vector, and generate a corresponding comprehensive situation evaluation matrix based on each of the situation evaluation vectors;

[0107] The combat situation assessment module 13 is used to utilize a preset parallel fuzzy reasoning system and perform parallel fuzzy reasoning calculations on each of the comprehensive situation assessment matrices based on the air combat situation advantage assessment model to obtain each advantage comprehensive evaluation value, and realize combat situation assessment of the drone group based on each advantage comprehensive evaluation value.

[0108] In this embodiment, each first drone is screened out from the drone group, a drone evaluation range is determined based on each first drone, and each drone set to be evaluated is constructed based on each second drone in the drone evaluation range; vector calculation is performed on each drone set using a preset air combat situation advantage evaluation model to obtain each situation evaluation vector, and a corresponding comprehensive situation evaluation matrix is ​​generated based on each situation evaluation vector; parallel fuzzy reasoning calculation is performed on each comprehensive situation evaluation matrix based on the preset parallel fuzzy reasoning system and the air combat situation advantage evaluation model to obtain each advantage comprehensive evaluation value, and combat situation evaluation of the drone group is implemented based on each advantage comprehensive evaluation value. The present application analyzes the combat situation of each first drone relative to the second drone adjacent to it. First, the drone assessment range is defined with each first drone as the center to improve the accuracy and efficiency of the situation assessment. By constructing an air combat situation advantage assessment model, vector calculations are performed on each drone set to generate a corresponding comprehensive situation assessment matrix. A parallel fuzzy inference system is used to perform parallel fuzzy inference calculations on the comprehensive situation assessment matrix to obtain comprehensive evaluation values ​​of each advantage, thereby realizing real-time assessment of the combat situation of the drone group, reducing the analysis time of the situation assessment, and providing an important basis for subsequent drone group combat decisions.

[0109] In some specific embodiments, the set building module 11 may specifically include:

[0110] A screening module, used for randomly screening out a single drone from all the drones in the drone group as a first drone, so as to obtain each of the first drones;

[0111] The range determination module is used to determine the drone spherical range with the first drone as the center and based on a preset radius, and use the drone spherical range as the drone evaluation range to obtain the evaluation range of each drone.

[0112] In some specific embodiments, the set building module 11 may specifically include:

[0113] A quantity determination module, used to determine the quantity of all the second drones in the drone evaluation range;

[0114] The judging module is used to judge whether the number is greater than a preset drone threshold, and if the number is not greater than the preset drone threshold, generate a set of drones to be evaluated based on all the second drones in the drone evaluation range.

[0115] In some specific embodiments, the set building module 11 may specifically include:

[0116] a boundary range determination module, configured to determine a boundary range of the drone assessment range if the number is greater than the preset drone threshold;

[0117] The clipping module is used to clip the second drones corresponding to the boundary range, and generate the set of drones to be evaluated based on the clipped second drones in the drone evaluation range.

[0118] In some specific embodiments, the evaluation matrix generation module 12 may specifically include:

[0119] A model building module, used to respectively build a distance advantage function model, an angle advantage function model, a speed advantage function model and a height advantage function model;

[0120] An evaluation model generation module is used to generate the air combat situation advantage evaluation model based on the distance advantage function model, the angle advantage function model, the speed advantage function model and the altitude advantage function model.

[0121] In some specific embodiments, the parallel fuzzy inference system is composed of a fuzzy inference array, a data storage pool, a row scheduling module and a plurality of row distributors; wherein the fuzzy inference array is composed of row-column fuzzy inference computing units.

[0122] In some specific embodiments, the combat situation assessment module 13 may specifically include:

[0123] A fuzzy processing module, used to obtain non-fuzzy data based on the air combat situation advantage assessment model by using the row-column fuzzy reasoning calculation unit in the preset parallel fuzzy reasoning system, and to perform fuzzy processing on the non-fuzzy data by using a membership function to obtain processed data;

[0124] The evaluation value determination module is used to perform reasoning mapping and defuzzification operations on the processed data to obtain the comprehensive evaluation values ​​of each advantage.

[0125] Figure 7A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the combat situation assessment method of a drone swarm executed by an electronic device disclosed in any of the aforementioned embodiments.

[0126] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0127] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon include an operating system 221, a computer program 222 and data 223, etc. The storage method can be temporary storage or permanent storage.

[0128] Among them, the operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20 to realize the operation and processing of the data 223 in the memory 22 by the processor 21, which can be Windows, Unix, Linux, etc. In addition to including a computer program that can be used to complete the combat situation assessment method of the drone swarm executed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks. In addition to including data transmitted from an external device received by the combat situation assessment device of the drone swarm, the data 223 can also include data collected by its own input and output interface 25, etc.

[0129] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0130] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium, in which a computer program is stored. When the computer program is loaded and executed by a processor, the steps of the method for assessing the combat situation of a drone swarm disclosed in any of the aforementioned embodiments are implemented.

[0131] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0132] The above is a detailed introduction to the combat situation assessment method, device, equipment and storage medium of a drone swarm provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for evaluating the combat situation of a drone swarm, characterized in that: include: Selecting first drones from the drone group, determining a drone evaluation range based on the first drones, and constructing a set of drones to be evaluated based on second drones in the drone evaluation range; Performing vector calculation on each of the drone sets using a preset air combat situation advantage assessment model to obtain each situation assessment vector, and generating a corresponding comprehensive situation assessment matrix based on each of the situation assessment vectors; A preset parallel fuzzy reasoning system is used to perform parallel fuzzy reasoning calculations on each of the comprehensive situation assessment matrices based on the air combat situation advantage assessment model to obtain each advantage comprehensive assessment value, and the combat situation assessment of the drone group is implemented based on each advantage comprehensive assessment value.

2. The method for evaluating the combat situation of a drone swarm according to claim 1, characterized in that: The step of selecting each first drone from the drone group and determining a drone evaluation range according to each first drone includes: Randomly selecting a single drone from all the drones in the drone group as a first drone to obtain each of the first drones; Taking the first drone as the center and based on a preset radius, a drone spherical range is determined, and the drone spherical range is used as the drone evaluation range to obtain the evaluation range of each drone.

3. The method for evaluating the combat situation of a drone group according to claim 1, characterized in that: The step of constructing a set of drones to be evaluated based on the second drones in the drone evaluation range includes: Determining the number of all the second drones in the drone evaluation range; It is determined whether the number is greater than a preset drone threshold; if the number is not greater than the preset drone threshold, a set of drones to be evaluated is generated based on all the second drones in the drone evaluation range.

4. The method for evaluating the combat situation of a drone group according to claim 3, characterized in that: After determining whether the number is greater than a preset drone threshold, the method further includes: If the number is greater than the preset drone threshold, determining the boundary range of the drone assessment range; The second drones corresponding to the boundary range are clipped, and the sets of drones to be evaluated are generated based on the clipped second drones in the drone evaluation range.

5. The method for evaluating the combat situation of a drone group according to claim 1, characterized in that: Before performing vector calculation on each of the drone sets using the preset air combat situation advantage assessment model, the method further includes: Construct distance advantage function model, angle advantage function model, speed advantage function model and height advantage function model respectively; The air combat situation advantage assessment model is generated based on the distance advantage function model, the angle advantage function model, the speed advantage function model and the altitude advantage function model.

6. The method for evaluating the combat situation of a drone swarm according to any one of claims 1 to 5, characterized in that: The parallel fuzzy inference system is composed of a fuzzy inference array, a data storage pool, a row scheduling module and a plurality of row distributors; wherein the fuzzy inference array is composed of row-column fuzzy inference calculation units.

7. The method for evaluating the combat situation of a drone swarm according to claim 6, characterized in that: The method of using a preset parallel fuzzy inference system and performing parallel fuzzy inference calculations on each of the comprehensive situation assessment matrices based on the air combat situation advantage assessment model to obtain each comprehensive advantage assessment value includes: Using the row-column fuzzy reasoning calculation unit in the preset parallel fuzzy reasoning system and based on the air combat situation advantage assessment model to obtain non-fuzzy data, and using a membership function to perform fuzzification processing on the non-fuzzy data to obtain processed data; The processed data is subjected to inference mapping and defuzzification operations to obtain comprehensive evaluation values ​​of the advantages.

8. A combat situation assessment device for a drone group, characterized in that: include: A set construction module, used to select each first drone from the drone group, determine a drone evaluation range according to each first drone, and construct each drone set to be evaluated based on each second drone in the drone evaluation range; An evaluation matrix generation module is used to perform vector calculation on each of the drone sets using a preset air combat situation advantage evaluation model to obtain each situation evaluation vector, and generate a corresponding comprehensive situation evaluation matrix based on each of the situation evaluation vectors; The combat situation assessment module is used to utilize a preset parallel fuzzy reasoning system and perform parallel fuzzy reasoning calculations on each of the comprehensive situation assessment matrices based on the air combat situation advantage assessment model to obtain each advantage comprehensive assessment value, and realize combat situation assessment of the drone group based on each advantage comprehensive assessment value.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, used to execute the computer program to implement the combat situation assessment method of a drone swarm as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein, when the computer program is executed by a processor, the combat situation assessment method of a drone swarm as described in any one of claims 1 to 7 is implemented.

Images