A Decision-making Method and Device for Cooperative Strike of Aircraft Clustering and Swarming

Abstract

The present invention discloses a method and device for decision-making of cooperative strikes in a clustered UAV swarm, aiming to solve the problem of cooperative strikes in the offensive and defensive confrontation of UAV swarms. The method includes: First, by establishing a cooperative game model for the UAV swarm alliance, the cooperative strike problem is transformed into a cooperative game problem; Second, using an iterative clustering algorithm guided by the combat benefits of the cooperative alliance, an optimal alliance cooperation strategy is formulated to maximize the cooperative combat effectiveness of the swarm; Finally, based on the strike probability matrix, the optimal sequential cooperative strike strategy is determined to enhance the strike effect of the clustered swarm on enemy targets. The device adopts a modular design and can automatically realize the alliance construction and target allocation of the cooperative strikes of the UAV swarm, thereby effectively improving the cooperative combat effectiveness of the UAV swarm in complex confrontation environments. The present invention is relatively simple in structure and easy to implement.

Description

Technical Field

[0001] The present invention relates to the field of cluster task planning, and particularly to a method and device for decision-making of cooperative strikes by clustering unmanned aerial vehicles (UAVs). Background Art

[0002] In the modern computing environment, battlefield informatization and intelligence have become the main trends. As a new type of combat force, UAV clusters, with their characteristics of flexibility, high efficiency, and intelligence, have become an important part of the future battlefield. However, UAV clusters often have the characteristics of a large number of nodes, high moving speeds, and frequent changes in network topology. Using the traditional global communication network structure is likely to lead to communication delays and interference, thus affecting the cooperative combat effectiveness of the clusters.

[0003] To address the above challenges, clustering of clusters has emerged. Clustering of clusters means dividing a large-scale cluster into several smaller clusters, where the agents within each cluster cooperate to execute tasks, and information interaction and task allocation are carried out between different clusters through a coordination mechanism. This architecture helps to simplify the communication within the cluster and improve the stability and fault tolerance of the system. In recent years, many scholars have explored clustering methods applicable to UAV clusters. For example, the literature (T. Ma, H. Zhou, B. Qian, and A. Fu. A large-scale clustering and 3D trajectory optimization approach for UAV swarms. Science China Information Sciences, 2021, 64: 1-16.) proposed a K-Means clustering algorithm with high efficiency and low latency for UAV clusters to minimize the completion time of data collection tasks. The literature (M. Y. Arafat and S. Moh. Localization and clustering based on swarm intelligence in UAV networks for emergency communications. IEEE Internet of Things Journal, 2019, 6(5): 8958-8976.) proposed an efficient swarm intelligence algorithm based on particle swarm optimization for clustering of UAV clusters.

[0004] However, the above research mainly focuses on the clustering algorithm of the aircraft cluster, and does not further explore the collaborative strike problem of the clustered cluster. The confrontation decision-making is the core to achieve the combat advantages of the cluster. In the actual battlefield environment, in order to improve the combat effectiveness of the cluster, especially when striking important targets, it is necessary to consider how multiple aircraft cooperate in an alliance to improve the overall combat effectiveness of the aircraft cluster. Therefore, researching the collaborative strike strategy of the clustered cluster to achieve both coalition cooperation strikes and precision strikes has theoretical and strategic significance. Summary of the Invention

[0005] Object of the Invention: The present invention provides a collaborative strike decision-making method and device for aircraft clustered clusters, aiming to efficiently solve the collaborative strike problem of aircraft clusters in offensive and defensive confrontations, maximize the collaborative combat effectiveness of the cluster, and enhance the strike effect of the clustered cluster on enemy targets.

[0006] Technical Solution: To achieve the above object of the invention, the present invention adopts the following technical solutions:

[0007] A collaborative strike decision-making method for aircraft clustered clusters includes the following steps:

[0008] Simulate and create the environment of the aircraft cluster confrontation operation, including setting the combat areas of both sides, the number and initial positions of the aircraft clusters, the maximum range and safety range of the weapons carried by the aircraft, and the enemy alliance setting;

[0009] Based on the initial positions of the aircraft cluster, the value of the enemy aircraft, and the maximum range and safety range of the weapons carried by the aircraft, transform the collaborative strike problem into a cooperative game problem, including establishing the benefit index function f i for our aircraft a j to strike the enemy aircraft b ij , establishing the benefit index function j for q of our aircraft to cooperate in striking the enemy aircraft b combining f ij and to construct the cooperative alliance combat benefit function f of our aircraft cluster;

[0010] Formulate the optimal alliance cooperation strategy according to the cooperative game problem to maximize the collaborative combat effectiveness of the cluster; the optimal alliance cooperation strategy is based on the initial alliance cooperation strategy R A (0), and determine it by solving the strike target strategy R A (N A ) that maximizes the value benefit function f of our aircraft cluster striking the enemy aircraft cluster;

[0011] Construct the strike probability matrix of our aircraft based on the optimal coalition cooperation strategy and the priority of strike target selection, and determine the best sequential cooperative strike strategy for the clustered swarm.

[0012] An aircraft clustered swarm cooperative strike decision-making device, comprising: a scenario construction module, a model establishment module, a clustering decision module, and a strike decision module;

[0013] The scenario construction module is used to simulate and create the environment of aircraft swarm confrontation combat, including setting the combat areas of both sides, the number and initial positions of aircraft swarms, the maximum range and safety range of weapons carried by aircraft, and the setting of enemy alliances;

[0014] The model establishment module is used to transform the cooperative strike problem into a cooperative game problem based on the initial positions of the aircraft swarm, the value of enemy aircraft, the maximum range and safety range of weapons carried by aircraft, including establishing the benefit index function f of our aircraft a i striking enemy aircraft b j of, establishing the benefit index function of q of our aircraft cooperating to strike enemy aircraft b ij joint f j and to construct the cooperative coalition combat benefit function f of our aircraft swarm; ij and Construct the cooperative coalition combat benefit function f of our aircraft swarm;

[0015] The clustering decision module is used to formulate the optimal coalition cooperation strategy according to the cooperative game problem to maximize the cooperative combat benefit of the swarm; the optimal coalition cooperation strategy is based on the initial coalition cooperation strategy R A (0), by solving the strike target strategy R that maximizes the value benefit function f of our aircraft swarm striking the enemy aircraft swarm A (N A ) to determine;

[0016] The strike decision module is used to construct the strike probability matrix of our aircraft based on the optimal coalition cooperation strategy and the priority of strike target selection, and determine the best sequential cooperative strike strategy for the clustered swarm.

[0017] The present invention also provides a computer device, comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and when the program is executed by the processor, the steps of the above-mentioned aircraft clustered swarm cooperative strike decision-making method are implemented.

[0018] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for collaborative strike decision-making of clustered aircraft are implemented as described above.

[0019] The beneficial effects of the present invention are as follows: By constructing a cooperative game model for the aircraft cluster alliance, the present invention transforms the collaborative strike problem into a cooperative game problem and designs an iterative clustering algorithm oriented by the combat benefit of the cooperative alliance. This algorithm can effectively solve the optimal alliance cooperation strategy, thereby maximizing the collaborative combat benefit of the cluster. Further, based on the strike probability matrix of the optimal alliance cooperation strategy, the best sequential collaborative strike strategy is determined to enhance the strike effect of the clustered aircraft on the enemy target. In addition, the device adopts a modular design, which can automatically realize the alliance construction and target allocation of the aircraft cluster for collaborative strike, and thus effectively improve the collaborative combat effectiveness of the aircraft cluster in a complex confrontation environment. Therefore, the present invention is relatively simple in structure and easy to implement. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a schematic flow chart of the method of the present invention.

[0021] Figure 2 is a schematic diagram of the initial positions randomly generated by the enemy aircraft.

[0022] Figure 3 is a schematic diagram of the initial positions randomly generated by our aircraft.

[0023] Figure 4 、 Figure 5 is a schematic diagram of the optimal alliance cooperation strategy of our aircraft cluster in the embodiment of the present invention.

[0024] Figures 6 - 15 is a schematic diagram of the sequential collaborative strike strategy of our aircraft cluster in the embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0025] In order to have a clearer understanding of the features and advantages of the technical solution of the present invention, the composition and implementation of the specific solution will be described below with reference to the drawings.

[0026] The present invention provides a method for collaborative strike decision-making of clustered aircraft. Referring to Figure 1 , the method includes the following steps:

[0027] Step 1: Establish an offensive and defensive confrontation scenario for the aircraft clusters of both sides of the enemy and us, and randomly generate the initial positions of the aircraft clusters.

[0028] The establishment of the offensive and defensive confrontation scenario for the aircraft clusters of both sides is specifically as follows: In a specific combat airspace Q, the aircraft cluster of our side is executing the task of striking the aircraft cluster of the enemy. Assume that there is a combat line in the combat airspace Q, which divides the combat area into our combat area Q A and the enemy combat area Q B . The aircraft of both sides are restricted within their respective areas and cannot cross the combat line into the combat area of the other side, and all aircraft execute tasks at the same flight altitude.

[0029] It is assumed that the aircraft cluster of the enemy adopts a cooperative alliance tactical deployment. By constructing a circular area with the alliance center as the core, it aims to achieve the optimal allocation of resources and the flexible application of tactics. The enemy randomly sets M alliance centers in its combat area Q B and randomly distributes N S aircraft within the circular area with each alliance center as the center and a radius of r, aiming to form multiple cooperative defense and attack alliances Denote the set of alliance centers as S = {S1, …, S m , …, S M}, and the set of enemy aircraft as where the initial position of aircraft bj is denoted as N B = MN S represents the number of enemy aircraft. The value of enemy aircraft b j is denoted as v j , which is related to factors such as the mission, performance, payload, and tactical position of the aircraft. The set of our aircraft is denoted as where the initial position of aircraft a i is denoted as N A represents the number of our aircraft. In addition, assume that each aircraft carries weapons with the same maximum range d max and safety range d min .

[0030] Step 2: Assume that our aircraft cluster can obtain information such as the position, performance, and payload of the enemy aircraft cluster through means such as situation awareness and radar detection, and evaluate the value of the enemy aircraft by synthesizing these data. Based on the combat information such as the initial positions of the aircraft clusters of both sides, the value of the enemy aircraft, and the maximum range and safety range of the weapons carried by the aircraft, establish a cooperative game model for the aircraft cluster alliance.

[0031] Specifically, it includes the following steps:

[0032] Step 21: Establish the benefit index function f for our aircraft a i to strike enemy aircraft b j ​ij ;

[0033] According to the initial positions of the aircraft of both sides, the value of the enemy aircraft, and the maximum range d of the weapons carried by the aircraft max and the safety range d min , define the benefit index function f i of our aircraft a j striking the enemy aircraft b ij as:

[0034]

[0035] where i = 1, …, N A , j = 1, …, N B , N A and N B are the numbers of our and enemy aircraft respectively; v j represents the value of the enemy aircraft b j , v max represents the maximum value in the enemy aircraft cluster B, that is p ij is the probability that our aircraft a i destroys the enemy aircraft b j , and its specific form is:

[0036]

[0037] where d ij is the distance between our aircraft a i and the target j, i.e., the enemy aircraft b j . When the distance d ij is closer to the safety range d min , the destruction probability p ij is higher, and the benefit index function f ij is larger.

[0038] Step 22: Establish the benefit index function of our q aircraft cooperating to strike the enemy aircraft b j The benefit index function

[0039] of our q aircraft cooperating and simultaneously striking the enemy aircraft b j is defined as:

[0040]

[0041] where r > 1 is the cooperation coefficient, which depends on the combat capabilities of our q aircraft and the enemy aircraft b j ​Properties. Specifically, the larger the cooperation coefficient r is, the stronger the cooperative combat ability of our q aircraft is or the weaker the defense ability of the enemy aircraft b is. By adjusting r, the strike effects under different combat conditions can be simulated and analyzed to optimize the clustering strategy and strike resource allocation. j Step 23: Construct the cooperative coalition combat benefit function f of our aircraft cluster.

[0042] Step 23, construct the cooperative coalition combat benefit function f of our aircraft cluster.

[0043] The cooperative coalition combat benefit function f of our aircraft cluster A can be established as:

[0044]

[0045] where f j is the value benefit function of our aircraft striking the enemy aircraft b j and its specific form is:

[0046]

[0047] where α j ∈{0,1}, j = 1, …, N B , by adjusting α j the cooperative coalition combat benefits of our aircraft cluster under different strike mode combinations can be calculated. When α j = 0, it indicates that only one of our aircraft a i strikes the enemy aircraft b j ; when α j = 1, it indicates that q of our aircraft cooperate to strike the enemy aircraft b j .

[0048] Step 3: Design an iterative clustering algorithm guided by the cooperative coalition combat benefit to solve the optimal coalition cooperation strategy of our aircraft cluster.

[0049] Specifically, it includes the following steps:

[0050] Step 31: Initialize the coalition cooperation strategy;

[0051] Define the value benefit function i of the aircraft a m striking the coalition center S as:

[0052]

[0053] where represents the value of the enemy coalition center S m , represents the maximum value in the set S of enemy coalition centers, that is Denote our aircraft a i The probability of destroying the enemy alliance center S m . By solving to maximize the value benefit function The strike target That is:

[0054]

[0055] Initialize our aircraft a i The strike target is the enemy alliance center Similarly, all our remaining aircraft select the enemy alliance center that can maximize their value benefits as the strike target according to the above steps. According to the strike targets selected by the aircraft, the aircraft that strike the same alliance center are grouped into an alliance, thereby generating the initial alliance cooperation strategy of our aircraft cluster

[0056] Step 32: Update the alliance cooperation strategy;

[0057] For any iteration round t ∈ {1,…, N A},select an aircraft in the candidate aircraft set A t-1 For a strike strategy redeployment. In particular, when the iteration round t = 1, the candidate aircraft set Given the alliance cooperation strategy of the (t - 1)-th round of iteration And Define the strategy space H(t) = {h1(t),…, h (t),…, h m (t)}, where h M (t) represents the feasible strategy formed by removing aircraft a m From the current alliance i And adding it to the new alliance . According to the definition of the cooperative alliance combat benefit function f described above, calculate the combat benefits f(h (t)) under different strategies h m (t), and select the strategy that maximizes the combat benefits m (t) As the alliance cooperation strategy R A (t) of the t-th round of iteration. In addition, update the candidate aircraft set A t = A t-1 \a i , to ensure that the aircraft selected in each iteration are different.

[0058] Step 33: Solve the optimal alliance cooperation strategy;

[0059] After N AIn the round iteration to update the coalition cooperation strategy, the optimal coalition cooperation strategy of our UAV cluster is determined as where represents the UAV set of coalition , and this strategy maximizes the combat benefit of the cooperative coalition.

[0060] Step 4: Based on the strike probability matrix of our UAVs, formulate a sequential cooperative strike strategy for the clustered UAVs.

[0061] Specifically, it includes the following steps:

[0062] Step 41: Establish the priority of strike target selection;

[0063] First, calculate the probability that each UAV in our coalition strikes the center S of the enemy coalition m . Second, sort all UAVs in descending order according to the strike probability. Finally, according to the sorting result, generate the priority of strike target selection for the UAVs in coalition

[0064] Step 42: Initialize the strike probability matrix;

[0065] According to the optimal coalition cooperation strategy R A (N A ) and the priority of strike target selection , construct the strike probability matrix P m (0) for each coalition, where m ∈ {1, …, M}, that is

[0066]

[0067] where p ij , i ∈ {T1, …, TN m} and j ∈ {1, …, N S} represent the probability that UAV a in our coalition i destroys UAV b in the enemy coalition j .

[0068] Step 43: Select the strike target;

[0069] According to the priority determined in Step 41 , the UAV a T1 with the highest priority first selects the enemy UAV m as the strike target according to the first row of the strike probability matrix P (0). If the selected enemy UAV is eliminated by updating the strike probability matrix P​m Set the \(l\)-th column in \((0)\) to \(0\) and update the strike probability matrix \(P\). m (1), that is

[0070]

[0071] Meanwhile, update the coalition sequential cooperative strike strategy \(\Omega\). m (1)=\(\{b\) l ,0,\(\cdots\),0\}. Subsequently, the aircraft with the next highest priority selects the next strike target and updates the strike probability matrix and the sequential cooperative strike strategy. Repeat this process until all aircraft have completed the selection of strike targets.

[0072] In particular, when the aircraft selects a strike target, if all elements in the \(k\)-th row of the strike probability matrix \(P\) m (k - 1) are \(0\), that is p Tkj = 0, then define a target set \(J\) that satisfies being less than the preset strike probability threshold \(\tau\leq1\) k =\(\{b\) j |0 \lt p Tkj \lt\tau\}, where the preset strike probability threshold \(\tau\) is used to evaluate whether a target is effectively struck. If the strike probability of a target exceeds the set threshold \(\tau\), it indicates that the target aircraft has basically lost its combat effectiveness. If the set then select the enemy aircraft m as the strike target according to the initial strike probability matrix \(P\) (0), otherwise do not select any strike target. By setting the priority and the threshold \(\tau\), this method can further optimize the allocation of strike resources, thereby enhancing the cooperative strike effect on enemy targets.

[0073] Use MATLAB 2022b as the simulation calculation software to simulate the offensive and defensive confrontation scenario of an aircraft cluster. By solving the optimal coalition cooperation strategy and sequential cooperative strike strategy of our aircraft cluster, evaluate the effectiveness of the present invention, and conduct a simulation comparison of the combat benefits between the clustered cooperative strike of the present invention and the case where aircraft execute strike tasks individually. The parameter settings of the offensive and defensive confrontation scenario of the aircraft cluster in the simulation include: Assume that the effective combat area \(Q\) of our aircraft cluster A =[0,100]\(\times\)[0,45), and the enemy combat area is \(Q\) B =[0,100]\(\times\)(55,100]. The enemy randomly distributes \(N\) B = 12 aircraft within a circular area with each coalition center as the center and a radius of \(r\) in its combat area \(Q\) S , forming 10 cooperative defense and attack coalitions, with a total of \(N\) B= 120 aircraft. The initial positions of the enemy aircraft cluster are as Figure 2 shown. We have N A = 120 aircraft, with a maximum weapon range d max of 15 unit lengths and a safe range d min of 8 unit lengths. The initial positions of our aircraft cluster are as Figure 3 shown. Figure 4 and Figure 5 are schematic diagrams of 10 optimal coalition cooperation strategies formed by our aircraft cluster according to the positions of enemy aircraft and the alliance center, as well as mission requirements. Figure 4 is the optimal coalition cooperation strategy for our aircraft to strike enemy alliances 1 to 5. In the effective combat area of our side, the circles of the same color represent the clustered clusters of aircraft belonging to the same alliance, and this cluster is responsible for striking the enemy alliance of the corresponding color. For example, the red circles represent our aircraft alliance 1, and its mission is to strike the aircraft in enemy alliance 1. The same applies to other colors, corresponding to enemy alliances 2 to 5 respectively. Figure 5 is the optimal coalition cooperation strategy for our aircraft to strike enemy alliances 6 to 10. The optimal coalition cooperation strategy R A (N A ) of our aircraft cluster is formulated by an iterative clustering algorithm guided by the combat benefits of coalition operations of the present invention. According to the optimal coalition cooperation strategy R A (N A ), a sequential cooperative strike strategy Ω = {Ω1,…,Ω 10} of the clustered clusters is formulated. Figures 6 to 15 respectively show the specific strike strategies of our 10 clustered clusters, and the arrows represent the strike relationships between our aircraft and the enemy aircraft. For example, Figure 6 each aircraft in our alliance 1 points to a certain enemy aircraft through an arrow, indicating that these aircraft have respectively selected the pointed enemy aircraft as the strike target. If a certain aircraft of ours does not point to any enemy aircraft through an arrow (as shown in Figure 8 ), it means that the aircraft has not been assigned any strike task. This situation is due to its poor expected strike effect, or its desired target has been selected by aircraft with higher priority and has been effectively struck, that is, the probability of the desired target being struck is greater than the preset strike probability threshold τ = 0.8. This method can optimize the allocation of strike resources, thereby enhancing the cooperative strike effect on enemy targets.

[0074] To better demonstrate the combat effectiveness of the clustered cluster cooperative strike system of the present invention, the strike task execution efficiency index is defined as where f* represents the combat benefits of the coalition operation under the optimal coalition cooperation strategy R A (N A ) and the sequential cooperative strike strategy Ω; It represents the total target value benefit obtained when the aircraft does not cooperate with other aircraft and selects the enemy aircraft with the highest strike probability as the strike target respectively. To ensure the robustness of the result, by randomizing the initial positions of our aircraft cluster and running the simulation program 100 times, the average mission execution efficiency index can be obtained as Compared with the aircraft executing strike missions alone, the present invention can effectively solve the cooperative strike problem of the aircraft cluster in the offensive and defensive confrontation, improve the cooperative combat benefit of the cluster, and enhance the strike effect of the cluster on enemy targets.

[0075] Based on the same technical concept as the method embodiment, the present invention also provides an aircraft clustering cluster cooperative strike decision-making device, including: a scenario construction module, a model establishment module, a clustering decision module, and a strike decision module;

[0076] The scenario construction module is used to simulate and create the environment of the aircraft cluster confrontation operation, including setting the combat areas of both sides of the enemy and us, the number and initial positions of the aircraft cluster, the maximum range and safety range of the weapons carried by the aircraft, and the enemy alliance setting;

[0077] The model establishment module is used to transform the cooperative strike problem into a cooperative game problem based on the initial positions of the aircraft cluster, the value of the enemy aircraft, and the maximum range and safety range of the weapons carried by the aircraft, including establishing the benefit index function f i for our aircraft a j striking the enemy aircraft b ij , establishing the benefit index function j for q of our aircraft cooperating to strike the enemy aircraft b combining f ij and to construct the cooperative alliance combat benefit function f of our aircraft cluster;

[0078] The clustering decision module is used to formulate the optimal alliance cooperation strategy according to the cooperative game problem to maximize the cooperative combat benefit of the cluster; the optimal alliance cooperation strategy is based on the initial alliance cooperation strategy R A (0), and the strike target strategy R A (N A ) that maximizes the value benefit function f of our aircraft cluster striking the enemy aircraft cluster is determined by solving;

[0079] The strike decision module is used to construct the strike probability matrix of our aircraft based on the optimal alliance cooperation strategy and the strike target selection priority, and determine the best sequential cooperative strike strategy of the clustering cluster.

[0080] It should be understood that the aircraft clustering and collaborative strike decision-making device in the embodiments of the present invention can implement all the technical solutions in the above method embodiments. The functions of its respective functional modules can be specifically implemented according to the methods in the above method embodiments, and the specific implementation process can refer to the relevant descriptions in the above embodiments, which will not be elaborated here.

[0081] The present invention also provides a computer device, including: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and when the program is executed by the processor, it implements the steps of the aircraft clustering and collaborative strike decision-making method as described above.

[0082] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the aircraft clustering and collaborative strike decision-making method as described above.

[0083] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a device (system), a computer device, or a computer program product. Therefore, the present invention can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0084] The present invention is described with reference to the flowcharts of the methods according to the embodiments of the present invention. It should be understood that each process in the flowchart and the combination of the processes in the flowchart can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes.

[0085] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one process or multiple processes.

[0086] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus, causing a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one process Figure 1 or multiple processes.

Claims

1. A method for decision-making on aircraft clustering and coordinated attack, characterized in that: The following steps are involved: Simulate and create an environment for aircraft swarm confrontation operations, including setting the combat areas for both sides, the number and initial position of aircraft swarms, the maximum range and safe range of weapons carried by aircraft, and enemy alliance settings; Based on the initial position of the aircraft cluster, the value of the enemy aircraft, the maximum range and safe range of the aircraft's weapons, the coordinated strike problem is transformed into a cooperative game problem, including establishing a i Strike enemy aircraft j The profit index function f ij , establish our q aircraft to cooperate to attack the enemy aircraft b j The profit indicator function Joint ij and Construct the cooperative alliance combat benefit function f of our aircraft cluster; According to the cooperative game problem, the optimal alliance cooperation strategy is formulated to maximize the collaborative combat benefits of the cluster; the optimal alliance cooperation strategy is based on the initial alliance cooperation strategy R A (0), by solving the attack target strategy R that maximizes the value benefit function f of our aircraft cluster attacking the enemy aircraft cluster A (N A ) to be determined; Based on the optimal alliance cooperation strategy and the priority of target selection, we build a probability matrix for our aircraft strike and determine the optimal sequential coordinated strike strategy for clusters, including: Step 41: According to the optimal alliance cooperation strategy R A (N A ) and target selection priority Construct the attack probability matrix P for each alliance separately m (0),m∈{1,…,M}, we have: Among them, p ij ,i∈{T1,…,TN m },j∈{1,…,N S } indicates our alliance Medium Aircraft i Destroy the enemy alliance Medium aircraft b j probability; Step 42: Based on the determined priority The highest priority aircraft a T1 First, according to the attack probability matrix P m The first row of (0) selects the enemy aircraft As a target, if the selected enemy aircraft By transforming the hit probability matrix P m (0) where the first column is set to 0 and the attack probability matrix P is updated m (1) , we have: At the same time, update the alliance Sequential coordinated attack strategy Ω m (1) = {b l ,0,…,0}; then the aircraft with the second highest priority selects the next attack target and updates the attack probability matrix and sequential coordinated attack strategy, and repeats this process until all aircraft have completed the selection of attack targets.

2. The method according to claim 1, characterized in that Build our aircraft a i Strike enemy aircraft j The profit index function f ij ,include: According to the initial positions of the enemy and our aircraft, the enemy aircraft value and the maximum range of the aircraft weapons max With safe range d min , define our aircraft a i Strike enemy aircraft j The profit index function f ij for: Where i = 1,…,N A ,j=1,…,N B , N A and N B are the number of our and enemy aircraft respectively; v j Indicates enemy aircraft b j The value of v max represents the maximum value in the enemy aircraft cluster B, that is, p ij For our aircraft a i Destroy enemy aircraft j The probability of is: Among them, d ij For our aircraft a i and target j, i.e. enemy aircraft b j The distance between them, when the distance d ij The closer to the safe range d min When the probability of destruction is p ij The higher the return index function f ij The bigger.

3. The method according to claim 2, characterized in that Our q aircraft cooperate to attack the enemy aircraft b at the same time j The profit indicator function Defined as: Among them, r>1 is the cooperation coefficient, which depends on the combat capability of our q aircraft and the enemy aircraft b. j The larger the cooperation coefficient r, the stronger the cooperative combat capability of our q aircraft or the stronger the enemy aircraft b j The weaker the defense capability.

4. The method according to claim 3, characterized in that Joint ij and Construct the cooperative alliance combat benefit function f of our aircraft cluster, including: The cooperative alliance combat profit function f of our aircraft cluster A is established as: Among them, f j B is used to attack enemy aircrafts for our aircraft j The value-benefit function of is: Among them, α j ∈{0,1},j=1,…,N B , by adjusting α j It can calculate the cooperative alliance combat benefits of our aircraft cluster under different attack mode combinations. j =0, indicating that we have only one aircraft a i Strike enemy aircraft j ; When α j =1, indicating that our aircraft q cooperate to attack the enemy aircraft b j .

5. The method according to claim 1, characterized in that Formulating the optimal alliance cooperation strategy specifically includes: Step 31: Initialize alliance cooperation strategy; Define aircraft a i Strike the enemy alliance center S m The value-benefit function for: in, Indicates the enemy alliance center S m The value of represents the maximum value in the enemy alliance center set S, that is, Indicates our aircraft a i Destroy the enemy alliance center S m The probability of The biggest target Right now: Initialize our aircraft a i The target of the attack is the enemy alliance center The remaining aircraft of our side select the enemy alliance center that can maximize its value benefit as the attack target according to the above steps; according to the attack target selected by the aircraft, the aircraft that attack the same alliance center will form an alliance, thus generating the initial alliance cooperation strategy of our aircraft cluster Step 32: Update the alliance cooperation strategy; For any number of iterations t∈{1,…,N A }, select candidate aircraft set A t-1 An aircraft in Perform strike strategy redeployment, where when the iteration number t = 1, the candidate aircraft set Given the alliance cooperation strategy of the t-1th iteration and Define the strategy space H(t) = {h1(t),…,h m (t),…,h M (t)}, where h m (t) represents aircraft a i From the current alliance Remove and join a new alliance The feasible strategies formed; according to the definition of the cooperative alliance combat benefit function f, calculate the m (t) under the combat benefit f(h m (t)) and choose the strategy that maximizes the combat benefit As the alliance cooperation strategy R of the tth round iteration A (t); Update the candidate aircraft set A t =A t-1 \a i , to ensure that the selected aircraft is different in each iteration; Step 33, solving the optimal alliance cooperation strategy; After N A The optimal alliance cooperation strategy of our aircraft cluster is determined as in Represents Alliance of aircraft, this strategy maximizes the combat benefits of the cooperative alliance.

6. The method according to claim 1, characterized in that The priority of target selection is determined according to the following method: First calculate our alliance Each aircraft strikes the enemy alliance center S m The probability of Sort them from high to low according to the probability of attack; finally, generate an alliance based on the sorting results. The priority of target selection for medium aircraft 7. An aircraft clustering and grouping coordinated attack decision-making device, characterized in that: include: The scenario building module is used to simulate and create an environment for aircraft cluster confrontation operations, including setting the combat areas of the enemy and our side, the number and initial position of the aircraft cluster, the maximum range and safe range of the weapons carried by the aircraft, and the enemy alliance settings; The model building module is used to transform the coordinated strike problem into a cooperative game problem based on the initial position of the aircraft cluster, the value of the enemy aircraft, the maximum range and safe range of the aircraft's weapons, including the establishment of our aircraft a i Strike enemy aircraft j The profit index function f ij , establish our q aircraft to cooperate to attack the enemy aircraft b j The profit indicator function Joint ij and Construct the cooperative alliance combat benefit function f of our aircraft cluster; The clustering decision module is used to formulate the optimal alliance cooperation strategy according to the cooperative game problem to maximize the collaborative combat efficiency of the cluster; the optimal alliance cooperation strategy is based on the initial alliance cooperation strategy R A (0), by solving the attack target strategy R that maximizes the value benefit function f of our aircraft cluster attacking the enemy aircraft cluster A (N A ) to be determined; The strike decision module is used to build the strike probability matrix of our aircraft based on the optimal alliance cooperation strategy and the strike target selection priority, and determine the best sequential coordinated strike strategy for clusters, including: Step 41: According to the optimal alliance cooperation strategy R A (N A ) and target selection priority Construct the attack probability matrix P for each alliance separately m (0),m∈{1,…,M}, we have: Among them, p ij ,i∈{T1,…,TN m },j∈{1,…,N S } indicates our alliance Medium Aircraft i Destroy the enemy alliance Medium aircraft b j probability; Step 42: Based on the determined priority The highest priority aircraft a T1 First, according to the attack probability matrix P m The first row of (0) selects the enemy aircraft As a target, if the selected enemy aircraft By transforming the hit probability matrix P m (0) where the first column is set to 0 and the attack probability matrix P is updated m (1) , we have: At the same time, update the alliance Sequential coordinated attack strategy Ω m (1) = {b l ,0,…,0}; then the aircraft with the second highest priority selects the next attack target and updates the attack probability matrix and sequential coordinated attack strategy, and repeats this process until all aircraft have completed the selection of attack targets.

8. A computer device, characterized in that: include: one or more processors; Memory; And one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and when the programs are executed by the processors, the steps of the aircraft clustering and coordinated strike decision-making method as described in any one of claims 1-6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the aircraft clustering and coordinated attack decision-making method as described in any one of claims 1 to 6 are implemented.

Images