Method for multi-missile task allocation based on binary gorilla troop optimizer

Abstract

The application provides a multi-missile task allocation method based on a binary gorilla troop optimizer, and comprises the following steps: obtaining combat parameters of missiles and targets, and determining an effectiveness matrix based on the combat parameters by using an improved analytic hierarchy process; determining an overall performance function based on the effectiveness matrix and a chaotic initialization discrete solution set space; and performing optimal solution on the overall performance function by using a discrete binary gorilla troop optimization algorithm to obtain a task allocation matrix. The application improves the efficiency and precision of multi-missile cooperative combat task allocation.

Description

Technical Field

[0001] This invention relates to the field of collaborative task allocation technology, and in particular to a multi-missile task allocation method based on the binary gorilla force optimizer. Background Technology

[0002] In modern large-scale information warfare scenarios, the detection range, penetration capability, and strike effect of a single missile currently face bottlenecks. Multi-missile coordination can effectively improve overall combat effectiveness. Faced with dangerous and complex combat environments and the ever-changing nature of missions, accurately and efficiently selecting targets is crucial. Mission allocation in multi-missile coordinated operations involves assigning multiple targets to multiple missiles based on given situational information and the performance parameters of both sides, according to certain tactical indicators and constraints. This ensures that specific mission requirements are met while also optimizing the overall effectiveness of the missile formation.

[0003] In the task allocation problem of multi-missile cooperative operations, three aspects need to be considered: the operational environment, resource constraints, and task requirement constraints. The operational environment refers to the environment in which multiple missile groups execute their designated tasks. Resource constraints refer to the constraints inherent in the missiles themselves, such as quantity, type, and guidance time, which must be met to complete the designated tasks. Task requirement constraints refer to the set of tasks to be completed; different task allocation combinations will generate corresponding benefits and costs, both of which are represented in the designed performance function (i.e., fitness function). Currently, the main drawbacks of task allocation in multi-missile cooperative operations are as follows: 1. The task allocation problem is a static target classification problem, which does not fully consider the real battlefield environment. 2. The cooperative combat task allocation problem is a typical NP-hard problem, and commonly used algorithms suffer from low efficiency and low accuracy. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a multi-missile task allocation method based on the binary gorilla force optimizer, so as to improve the efficiency and accuracy of multi-missile cooperative combat task allocation.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of the present invention are as follows:

[0006] In a first aspect, embodiments of the present invention provide a multi-missile task allocation method based on the binary gorilla force optimizer, comprising: acquiring the operational parameters of missiles and targets, and determining the benefit matrix based on the operational parameters using an improved hierarchical analysis method; determining the overall performance function based on the benefit matrix and the chaotic initialization of the discrete solution set space; and optimizing the overall performance function using a discrete binary gorilla force optimization algorithm to obtain the task allocation matrix.

[0007] In one implementation, an improved hierarchical analysis method is used to determine the benefit matrix based on operational parameters, including: determining a hierarchical model of benefit indices for multi-missile coordinated operations based on a pre-constructed hierarchical system of benefit indices; wherein the hierarchical system of benefit indices includes three layers: the first layer is the overall benefit index, the second layer is the situational benefit index and the performance benefit index, and the third layer is the altitude benefit index, the range benefit index, the angle benefit index, the speed benefit index, the electronic countermeasures performance benefit index, the maneuverability performance benefit index, and the attack performance benefit index. The hierarchical model of benefit indices is as follows:

[0008] w ij =e 11 ×(e 21 ×E h +e 22 ×E r +e 23 ×E a +e 24 ×E v )+e 12 ×(e 25 ×E e +e 26 ×E m +e 27 ×E att )

[0009] Among them, w ij E represents the overall effectiveness index of allocating the i-th missile to the j-th target. h E represents the high efficiency index. r E represents the distance benefit index. a E represents the angle benefit index. v E represents the speed-efficiency index. e E represents the electronic countermeasures performance benefit index. m E represents the performance efficiency index. att e represents the attack performance efficiency index. 11 ,e 12 ,e 21 ,e 22 ,e 23 ,e 24 ,e 25 ,e 26 ,e 27 These represent the weight coefficients for each layer;

[0010] Calculate the weight coefficient matrix of each level of benefit in the benefit index hierarchy; based on the benefit index hierarchy model, the weight coefficient matrix of each level of benefit, and the benefit index, calculate the overall benefit index to obtain the benefit matrix.

[0011] In one implementation, calculating the weight coefficient matrix of each layer of benefit in the benefit index hierarchy includes: determining an initial judgment matrix for each layer of benefit in the benefit index hierarchy; taking the logarithm of the initial judgment matrix to obtain a first judgment matrix; constructing an optimal transfer matrix based on the first judgment matrix; constructing an optimal consistency judgment matrix based on the optimal transfer matrix; and calculating the weight coefficient matrix based on the optimal consistency judgment matrix.

[0012] In one implementation, determining the overall performance function based on the benefit matrix and a chaotically initialized discrete solution set space includes: converting the 0-1 integer matrix of the missile-target mission allocation solution space into an m·n-dimensional solution vector space, and initializing the m·n-dimensional solution vector space using a chaotic mapping method to obtain a chaotically initialized discrete solution set space; wherein, the initialization of the m·n-dimensional solution vector space includes:

[0013] x k = rand(1, m·n) k = 1, ..., m·n

[0014]

[0015]

[0016] Where m represents the number of missiles, n represents the number of targets, and x k Let x represent an m·n dimensional random number vector, where a is a predetermined constant value between 0 and 1, and x... iB ,i=1,…,m·n denotes the chaotic initialization discrete solution set space;

[0017] The overall performance function is determined based on the chaotic initialization of the discrete solution space, the benefit matrix, and the pre-determined cost matrix of the missile group and the value matrix of the target; wherein, the overall performance function is:

[0018]

[0019] Where B = [b1,…,b n ] 1×n The value matrix representing the objective is C = [c1, ..., c2]. m ] 1×m Represents the cost matrix of a missile swarm. Representing the benefit matrix, Represents the task assignment matrix, x ij =0 / 1, where 0 means the i-th missile is not assigned to the j-th target, and 1 means the i-th missile is assigned to the j-th target.

[0020] In one implementation, the Discrete Binary Gorilla Squad optimization algorithm includes an exploration phase and an development phase. The algorithm solves for the performance function to obtain a task assignment matrix. The process includes: in the exploration phase, initializing the discrete solution set space based on chaos, updating the position information using multiple preset update methods to obtain updated first-volume position information; performing a discrete binary conversion on the updated first-volume position information to obtain a binary m·n-dimensional solution vector; calculating the fitness based on the overall performance function and the binary m·n-dimensional solution vector, and selectively retaining the optimal binary m·n-dimensional solution vector based on the fitness calculation results to obtain the optimized binary m·n-dimensional solution vector.

[0021] In one implementation, the updated first volume position information is subjected to discrete binary conversion to obtain a binary m·n-dimensional solution vector, including: performing discrete binary conversion according to the following formula:

[0022]

[0023] Where X(t) represents the individual's current location information;

[0024] The binary m·n-dimensional solution vector is determined according to the following formula:

[0025]

[0026] Among them, X iB (t) represents the binary m·n-dimensional solution vector.

[0027] In one implementation, after selecting and retaining the optimal binary m·n-dimensional solution vector based on the fitness calculation results to obtain the optimized binary m·n-dimensional solution vector, the method further includes: during the development phase, if the update parameter is greater than or equal to the judgment threshold, then the optimized binary m·n-dimensional solution vector is updated using a first update mechanism to obtain the updated second volume position information; if the update parameter is less than the judgment threshold, then the optimized binary m·n-dimensional solution vector is updated using a second update mechanism to obtain the updated second volume position information; the updated second volume position information is subjected to discrete binary conversion to obtain the updated discrete solution set space; fitness is calculated based on the overall performance function and the updated discrete solution set space to determine the final task assignment matrix.

[0028] Secondly, embodiments of the present invention provide a multi-missile cooperative combat task allocation device based on the binary gorilla force optimizer, comprising: a benefit matrix determination module, used to acquire the combat parameters of missiles and targets, and determine the benefit matrix based on the combat parameters using an improved analytic hierarchy process; an effectiveness function determination module, used to determine the overall effectiveness function based on the benefit matrix and a chaotic initialized discrete solution space; and a task allocation module, used to optimize the overall effectiveness function using a discrete binary gorilla force optimization algorithm to obtain a task allocation matrix.

[0029] Thirdly, embodiments of the present invention provide an electronic device including a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to implement the steps of any of the methods provided in the first aspect above.

[0030] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the method provided in any of the first aspects above.

[0031] The embodiments of the present invention bring the following beneficial effects:

[0032] The multi-missile task allocation method based on the binary gorilla force optimizer provided in this invention first obtains the operational parameters of the missiles and targets, and then determines the benefit matrix based on the operational parameters using an improved analytic hierarchy process (AHP). Next, it determines the overall effectiveness function based on the benefit matrix and a chaotically initialized discrete solution space. Finally, it uses a discrete binary gorilla force optimization algorithm to optimize the overall effectiveness function, obtaining the task allocation matrix. This method uses an improved AHP to determine the benefit matrix, incorporating the battlefield situation into the calculation of the benefit matrix. This solves the problem of considering both the combat situation and the strike effectiveness, making the final task allocation result more closely reflect the actual battlefield situation. Simultaneously, the use of a discrete binary gorilla force optimization algorithm to solve the overall effectiveness function improves the efficiency and accuracy of multi-missile collaborative combat task allocation.

[0033] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0034] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0035] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0036] Figure 1 A flowchart of a multi-missile mission allocation method based on the binary gorilla force optimizer provided in this embodiment of the invention;

[0037] Figure 2 A schematic diagram of a hierarchical system of benefit indices provided in an embodiment of the present invention;

[0038] Figure 3 A schematic diagram of a missile-target two-dimensional planar combat situation provided in an embodiment of the present invention;

[0039] Figure 4 A flowchart illustrating an improved analytic hierarchy process provided in an embodiment of the present invention;

[0040] Figure 5 A flowchart of an optimization algorithm for a binary gorilla force provided in an embodiment of the present invention;

[0041] Figure 6 A flowchart illustrating the overall process of a multi-missile task allocation method based on a binary gorilla force optimizer, as provided in this embodiment of the invention.

[0042] Figure 7 A schematic diagram of a multi-missile mission allocation device based on a binary gorilla force optimizer provided in an embodiment of the present invention;

[0043] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] Current research on task allocation in multi-missile coordinated operations suffers from the following main drawbacks: 1. The task allocation problem is a static target classification problem. Solving this type of problem often assumes that parameters such as the quantity, location, speed, and combat capabilities of all targets can be obtained and will not be changed in subsequent missions; similarly, the combat attributes of the missile group are also fixed. In the task allocation problem, calculating the effectiveness function is crucial. The effectiveness function consists of an allocation matrix, missile cost and benefit matrices, etc. The allocation matrix is ​​the solution space, often represented as a 0-1 matrix of a certain size. The missile cost is composed of fixed column vectors. The benefit matrix is ​​often determined by the battlefield performance of both sides in the operation, and most existing research directly provides this matrix without fully considering the real battlefield environment.

[0046] 2. The collaborative combat mission allocation problem is a typical NP-hard problem. The solution space for this type of problem grows exponentially with the total number of missiles and targets. Common solutions can be categorized into mathematical programming, negotiation, and heuristic algorithms. Mathematical programming is a brute-force algorithm, suitable only for small-scale problems and requiring low real-time performance. However, it consumes a significant amount of time when there are many combinations of problems. Negotiation is a distributed mission allocation method. Although it is robust, it requires frequent data communication between missiles, increasing the risk of missile group exposure and limiting its practicality. Heuristic algorithms do not blindly search the global space. They combine random search with heuristic operations, balancing solution time and optimal performance, and are currently widely used methods. Common examples include genetic algorithms, particle swarm optimization, and gray wolf algorithms. However, they still suffer from low search efficiency, low convergence accuracy, and susceptibility to local optima.

[0047] In summary, current methods for allocating collaborative combat tasks suffer from low efficiency and low accuracy.

[0048] Based on this, the present invention provides a multi-missile task allocation method based on the binary gorilla force optimizer, which can improve the efficiency and accuracy of multi-missile collaborative combat task allocation.

[0049] To facilitate understanding of this embodiment, a multi-missile task allocation method based on the Binary Gorilla Force Optimizer disclosed in this invention will first be described in detail. This method can be executed by electronic devices, such as smartphones, computers, and tablets. See also Figure 1 The flowchart shown illustrates a multi-missile mission allocation method based on the binary gorilla force optimizer, indicating that the method mainly includes the following steps S101 to S103:

[0050] Step S101: Obtain the operational parameters of the missile and the target, and determine the benefit matrix based on the operational parameters using the improved analytic hierarchy process.

[0051] In one implementation, the system acquires the operational parameters of the missile and the target, including: position, speed, course of flight, maneuverability, attack capability, and electronic countermeasures capability, and establishes an evaluation system based on the operational parameters using an improved hierarchical analysis method, completes the optimization of the benefit matrix, and obtains the benefit matrix.

[0052] Step S102: Determine the overall performance function based on the benefit matrix and the chaotic initialization of the discrete solution space.

[0053] In one implementation, the system can pre-define the chaotic initial discrete solution space, consider relevant constraints, and use the optimized benefit matrix to obtain the overall performance function.

[0054] Step S103: The discrete binary gorilla army optimization algorithm is used to optimize the overall performance function and obtain the task allocation matrix.

[0055] In one implementation, the traditional heuristic algorithm is discretized to obtain the Discrete Binary Gorilla Army Optimization Algorithm, and the Discrete Binary Gorilla Army Optimization Algorithm is used to obtain the 0-1 integer matrix of the performance function (i.e., the task assignment matrix), which is the solution to the task assignment problem.

[0056] Specifically, assuming there are currently m missiles and n targets on the battlefield (where m > n), the cost matrix of the missile swarm can be represented as: C = [c1, ..., c m ] 1×m The value matrix of the target can be represented as: B = [b1, ..., b n ] 1×n The payoff matrix for each missile relative to the target is expressed as follows: Among them, w ij Let represent the assignment of the i-th missile to the j-th target. The solution space for the cooperative missile-target task allocation method is defined in integer encoding form as follows: Where, x ij =0 / 1, where 0 represents that the missile is not assigned to this target, and 1 represents the opposite. Therefore, the overall effectiveness function can be expressed as:

[0057]

[0058] The constraints on the overall performance function are:

[0059] (1) Each target should be assigned at least one missile: that is

[0060] (2) Each missile can be assigned to at most one target: that is

[0061] The multi-missile task allocation method based on the binary gorilla force optimizer provided in this invention uses an improved analytic hierarchy process to determine the benefit matrix, incorporating the battlefield situation into the calculation of the benefit matrix. This solves the problem of considering both the combat situation and the strike effectiveness, making the final task allocation result more in line with the actual battlefield situation. At the same time, the discrete binary gorilla force optimization algorithm is used to solve the overall effectiveness function, improving the efficiency and accuracy of multi-missile cooperative combat task allocation.

[0062] In one implementation, for the aforementioned step S101, i.e., when determining the benefit matrix using the improved analytic hierarchy process based on operational parameters, the following methods can be employed, including but not limited to the following steps 1 to 3:

[0063] Step 1: Determine the hierarchical model of the benefit index for multi-missile coordinated operations based on the pre-constructed benefit index hierarchy system.

[0064] In one implementation, see Figure 2 As shown, the benefit index hierarchy consists of three layers: the first layer is the overall benefit index; the second layer consists of the situational benefit index and the performance benefit index; and the third layer consists of the altitude benefit index, distance benefit index, angle benefit index, speed benefit index, electronic countermeasures performance benefit index, maneuverability performance benefit index, and attack performance benefit index. The benefit index hierarchy model (i.e., the overall benefit index or benefit matrix) is as follows:

[0065]

[0066] Among them, w ij E represents the overall benefit index of allocating the i-th missile to the j-th target, where i = 1, ..., m, j = 1, ..., n. h E represents the high efficiency index. r E represents the distance benefit index. a E represents the angle benefit index. v E represents the speed-efficiency index. e E represents the electronic countermeasures performance benefit index. m E represents the performance efficiency index. att e represents the attack performance efficiency index. 11 ,e 12 ,e 21 ,e 22 ,e 23 ,e 24 ,e 25 ,e 26 ,e 27 These represent the weight coefficients for each layer.

[0067] The following section provides a detailed introduction to the benefit parameters of the third layer. (See also...) Figure 3 The diagram shown illustrates a two-dimensional planar combat situation between a missile and a target, where v m ,v t θ represents the velocity of the missile and the velocity of the target, respectively. m ,θ t These represent the trajectory angles of the missile and the target, respectively. Let represent the leading angles of the missile and the target, respectively, and satisfy .

[0068] (1) High efficiency index E h :

[0069]

[0070] Among them, h ij The difference in altitude between missile i and target j indicates that the missile located above the target is in a favorable attack position.

[0071] (2) Distance Benefit Index E r :

[0072]

[0073] Where r represents the relative distance between the missile and the target, r m ,r t r represents the maximum attack range of the missile and the target, respectively. s This indicates the maximum detection range of the missile's seeker.

[0074] (3) Angle Benefit Index E a :

[0075]

[0076] in, These represent the leading angles of the missile and the target, respectively.

[0077] (4) Speed ​​efficiency index E v :

[0078]

[0079] Among them, v m ,v t These represent the speeds of the missile and the target, respectively.

[0080] (5) Electronic countermeasures performance benefit index E e :

[0081]

[0082] Among them, E em E etThese represent the electronic countermeasures capabilities of the missile and the target, respectively.

[0083] (6) Mobility performance benefit index E m :

[0084]

[0085] Among them, E mm E mt These represent the maneuverability of the missile and the target, respectively.

[0086] (7) Attack performance efficiency index E att :

[0087]

[0088] Among them, E attm E attt These represent the attack capabilities of the missile and the target, respectively.

[0089] Step 2: Calculate the weight coefficient matrix of each level of benefit in the benefit index hierarchy.

[0090] In one implementation, after establishing the hierarchical model of the benefit index, the weight coefficients cannot be directly obtained and need to be indirectly obtained using an improved analytic hierarchy process (AHP). (See [link to AHP implementation details]). Figure 4 The flowchart shown is for an improved analytic hierarchy process. The calculation of the weight coefficient matrix mainly includes the following steps 21 to 25:

[0091] Step 21: For each level of benefit in the benefit index hierarchy, determine the initial judgment matrix.

[0092] In practical implementation, the improved analytic hierarchy process (AHP) calculates the relative importance (i.e., weight coefficients) between different parameters at each level based on the constructed multi-level judgment matrix. Specifically, it uses a fractional scaling method. The initial state of the judgment matrix at different levels can be obtained by scaling forces from 1 to 9 and using expert scoring. Taking the third-level situational benefits as an example, the initial judgment matrix for the third-level situational benefits is as follows:

[0093]

[0094] The initial judgment matrix is ​​improved by using the optimal consistency matrix so that the optimized judgment matrix directly satisfies the consistency condition, thus eliminating the need for multiple corrections and reducing the amount of computation. The optimization process includes the following steps S22 to S25.

[0095] Step 22: Take the logarithm of the initial judgment matrix to obtain the first judgment matrix.

[0096] Specifically, taking the logarithm of formula (10) yields the first judgment matrix H1:

[0097]

[0098] Step 23: Construct the optimal transfer matrix based on the first judgment matrix.

[0099] Specifically, the optimal transfer matrix is ​​constructed as follows:

[0100]

[0101] Step 24: Construct the optimal consistency judgment matrix based on the optimal transfer matrix.

[0102] Specifically, based on the calculation results of formula (12), the optimal consistency judgment matrix is ​​constructed as follows:

[0103]

[0104] Step 25: Calculate the weight coefficient matrix based on the optimal consistency judgment matrix.

[0105] Specifically, according to formula (13), the weight coefficient of each column is obtained by dividing the value 1 of each column by the parameter of that column, thus obtaining the corresponding weight coefficient matrix:

[0106] M=[0.1287 0.2336 0.2785 0.9185] T (14)

[0107] See Figure 4 As shown in this embodiment of the invention, after obtaining the weight coefficient matrix, consistency judgment and comprehensive evaluation of herders can be performed on it. Specifically, the consistency judgment includes:

[0108] (1) Determine the consistency index equation:

[0109]

[0110] Where CI represents the consistency index, RI represents the average random consistency index, and λ max Let represent the largest eigenvalue of the optimal consistency judgment matrix H3, and n represent the dimension of the optimal consistency judgment matrix H3.

[0111] In this embodiment of the invention, the optimal consistency judgment matrix obtained by the above-mentioned improved method can all meet the consistency requirement, that is, CR<0.1. There is no need to repeatedly adjust the parameters of the initial judgment matrix, which greatly reduces the workload. Similarly, the above method can be used to calculate the relative weight coefficient matrix of the performance benefits of the second and third layers.

[0112] On the other hand, embodiments of the present invention add fuzzy comprehensive evaluation to the traditional analytic hierarchy process, enabling quantitative analysis of the index parameters at each level while providing qualitative coefficients. Fuzzy comprehensive evaluation includes:

[0113] (1) Determine the evaluation level.

[0114] Specifically, the rating and score matrix can be represented as follows:

[0115] U = [100 (Excellent) 80 (Good) 60 (Average) 40 (Poor) 20 (Very Poor)] (16)

[0116] (2) Determine the single-factor fuzziness matrix.

[0117] Specifically, the single-factor ambiguity matrix includes two parts: the third-layer situational benefit and the third-layer performance benefit, which can be given by expert evaluation methods and expressed as follows:

[0118]

[0119]

[0120] Based on formulas (17) and (18), the comprehensive evaluation results of the third-layer situational benefits and performance benefits can be expressed as follows:

[0121]

[0122] Formula (19) constitutes the second-level ambiguity matrix, from which the second-level comprehensive evaluation result can be obtained:

[0123]

[0124] (3) Calculate the overall evaluation effectiveness score to obtain quantitative results:

[0125] Q = D·U T (twenty one)

[0126] Step 3: Calculate the overall benefit index based on the benefit index hierarchy model, the weight coefficient matrix of each level of benefit, and the benefit index to obtain the benefit matrix.

[0127] In one implementation, after obtaining the weight coefficient matrix of each layer of benefits, the overall benefit index can be calculated based on each benefit index, and the benefit matrix W can be calculated according to formula (2).

[0128] After obtaining the benefit matrix, the efficiency function can be determined based on the benefit matrix and the chaotic initialization of the discrete solution space. Then, the binary gorilla team optimization algorithm is used to solve for the task allocation matrix.

[0129] The following section introduces the Binary Golem Troop Optimization (GTO) algorithm. Glem Troop Optimization is a gradient-free optimization algorithm that simulates the lifestyle of gorillas within a population: a gorilla group consists of one adult male (silverback) and several adult females and their offspring. The silverback is the leader of the group, and the young males are also called blackbacks. Typically, both male and female gorillas may migrate from their birth group to a new one. Additionally, adult males may leave their original group to form new troops by attracting migrating females. However, some adult males sometimes choose to remain in their original group, continuing to follow the silverback. After the silverback dies, these adult males may fight for leadership and mate with adult females. However, the particle updates in the existing GTO algorithm are performed in the real number domain, which is not suitable for 0-1 integer programming problems. Therefore, the embodiments of the present invention improve the algorithm by discretization, so that it can be successfully applied to the cooperative combat task allocation problem.

[0130] See Figure 5 The flowchart shown is for an optimization algorithm for a binary gorilla army. First, the chaotic initialization discrete solution set space, the preset population size Pop, the maximum number of iterations T, and the algorithm input parameters W are determined. Then, fitness is calculated, i.e., the performance function (i.e., the fitness function) is determined. Specifically, when determining the performance function based on the benefit matrix and the chaotic initialization discrete solution set space, the following methods can be used, including but not limited to:

[0131] First, the 0-1 integer matrix of the missile-target mission allocation solution space is converted into an m·n-dimensional solution vector space, and the m·n-dimensional solution vector space is initialized by a chaotic mapping to obtain a chaotic initialized discrete solution set space.

[0132] In practical implementation, the 0-1 integer matrix of the missile-target mission allocation solution space is transformed into an m·n-dimensional solution vector space, i.e., [x 11 …x 1n …x ij …x m1 …x mn ] 1×mn , where x ij =0 / 1, the initialization of the m·n dimensional solution vector space includes:

[0133]

[0134] Formula (22) is the initial random distribution of the population. In this embodiment of the invention, chaotic mapping is used to improve it so that the distribution is more uniform. The specific process is as follows:

[0135] x k =rand(1,m·n) k=1,…,m·n (23)

[0136]

[0137]

[0138] Where m represents the number of missiles, n represents the number of targets, and x k Let x represent an m·n dimensional random number vector, where a is a predetermined constant value between 0 and 1, and x... iB ,i=1,…,m·n represents the chaotic initialization discrete solution set space.

[0139] Then, the overall performance function is determined based on the chaotic initialization discrete solution space, the benefit matrix, and the predetermined cost matrix of the missile group and the value matrix of the target; where the overall performance function is shown in Equation (1).

[0140] Next, iterative processing will be carried out, mainly including the exploration phase and the development phase.

[0141] The exploration phase includes: First, based on the chaotic initialization of the discrete solution set space, the position information is updated using a variety of preset update methods to obtain the updated first volume position information.

[0142] In one implementation, all gorillas in the binary GTO algorithm are considered candidate solutions, with the silverback gorilla being the optimal solution generated in each iteration. During the exploration phase, the gorilla position update equation incorporates three different methods:

[0143]

[0144] Where GX(t+1) represents the candidate position of the individual in the next iteration, X(t) represents the current position of the gorilla individual, and t represents the current iteration number. r and X r Let r1, r2, r3, and rand represent the candidate position and current position of a gorilla randomly selected from the population, respectively. r1, r2, r3, and rand represent random values ​​within the range [0, 1] updated in each iteration. ub and lb represent the upper and lower bounds of the variable, respectively, which are set to 1 and 0 in this embodiment. p represents an initially given fixed parameter between [0, 1], which determines the probability of selecting a migration mechanism to an unknown position. The other parameters C, L, and H in the above formula are calculated as follows:

[0145] F = cos(2 × r⁴) + 1 (27)

[0146]

[0147] In the original GTO algorithm, the parameter C is updated as shown in formula (28). In this embodiment, a nonlinear convergence method is used to update the parameter C. Some improvements have been made, namely:

[0148]

[0149] L=C×l (30)

[0150] H=Z×X(t) (31)

[0151] Where T represents the maximum number of iterations, l represents a random value in the range [-1,1], r4 represents a random value in the range [0,1] updated in each iteration, and Z represents a random value in the range [-C,C].

[0152] Then, the updated first volume position information is subjected to discrete binary conversion to obtain a binary m·n-dimensional solution vector.

[0153] In one implementation, all updates to the individual positions of the population are performed in the real number domain, requiring discrete binary conversion. The discrete conversion function is:

[0154]

[0155] And based on formula (32), the binary m·n-dimensional solution vector is obtained:

[0156]

[0157] Finally, fitness is calculated based on the overall performance function and the binary m·n-dimensional solution vector, and the binary m·n-dimensional solution vector is selectively retained according to the fitness calculation results to obtain the optimized binary m·n-dimensional solution vector.

[0158] At the end of the exploration phase, the fitness of each individual in the population is calculated based on the overall performance function. If the fitness function value satisfies f(GX(t))>f(X(t)), then the individual GX(t) is used to replace X(t), and the best individual produced in this phase is regarded as a silverback gorilla.

[0159] Further, the development stage includes: if the update parameter is greater than or equal to the determination threshold value, the first update mechanism is adopted to update the optimized binary m·n-dimensional solution vector, and the updated second individual position information is obtained; if the update parameter is less than the determination threshold value, the second update mechanism is adopted to update the optimized binary m·n-dimensional solution vector, and the updated second individual position information is obtained; the updated second individual position information is subjected to discrete binary conversion to obtain the updated discrete solution set space; fitness calculation is performed based on the overall efficiency function and the updated discrete solution set space to determine the task allocation matrix.

[0160] In one implementation, there are two update mechanisms in the development stage, which respectively correspond to the behaviors of two biological groups, namely following the silverback gorilla (i.e., the first update mechanism) and competing adult females (i.e., the second update mechanism). The two update mechanisms are related to the update parameter C and the determination threshold value W.

[0161] (1) If C≥W, then select the update mechanism of following the silverback gorilla:

[0162] GX(t + 1) = L×GX avg ×(X(t) - X silverback ) + X(t) (34)

[0163]

[0164] g = 2 L (36)

[0165] Where, X silverback represents the position of the silverback gorilla (optimal solution), and N represents the total number of gorilla individuals, that is, the population size.

[0166] (2) If C < W, then select the update mechanism of competing adult females:

[0167] GX(t + 1) = X silverback - (X silverback ×Q - X(t)×Q)⊙A (37)

[0168] Q = 2×r5 - 1 (38)

[0169] A = β×E (39)

[0170]

[0171] Where Q simulates combat power, r5 represents a random value in the range [0,1] updated in each iteration, coefficient vector A represents the degree of violence in the conflict process, β represents a fixed parameter given before the optimization operation, and E is used to simulate the impact of the conflict on the dimension of the solution. If rand≥0.5, the value of E is an m·n-dimensional random vector that conforms to a normal distribution. If rand<0.5, the value of E is a random value that conforms to a normal distribution.

[0172] Similarly, the updated individual location information obtained during the development phase requires discrete binary conversion of the solution set for that phase:

[0173]

[0174] At the end of the development phase, the fitness of each individual in the population is calculated again. If the fitness function value satisfies f(GX(t))>f(X(t)), then the individual GX(t) is used to replace X(t). At the same time, the best individual generated in this phase is regarded as a silverback gorilla. Finally, the global optimal solution is output, which is the final task assignment matrix.

[0175] For ease of understanding, this embodiment of the invention also provides an overall flowchart of a multi-missile task allocation method based on the binary gorilla force optimizer, see [link / reference]. Figure 6 As shown, this method consists of two main parts: a benefit matrix evaluation based on an improved analytic hierarchy process (AHP) and a discrete binary gorilla force optimization algorithm. First, the system provides operational parameters such as the missile's and target's position, speed, flight direction, maneuverability, attack capability, and electronic countermeasures capability. Based on these conditions, an evaluation system is established using an improved AHP to optimize the benefit matrix. Second, the solution space after chaotic initialization is given. Considering relevant constraints and using the optimized benefit matrix, the group effectiveness function is obtained. Then, the traditional heuristic algorithm is discretized to obtain the binary gorilla force optimization algorithm, which calculates the 0-1 integer matrix, i.e., the solution to the task allocation problem.

[0176] This invention employs a discrete binary gorilla force optimization algorithm to allocate multi-missile cooperative combat tasks. First, it improves the analytic hierarchy process (AHP) by using an optimal consistency matrix and fuzzy comprehensive evaluation, incorporating battlefield situation into the calculation of the benefit matrix. This solves the problem of considering both the combat situation and strike effectiveness, making the final task allocation result more aligned with actual battlefield conditions. Second, addressing the NP-hard and discrete nature of task allocation, a novel binary gorilla force optimization algorithm is proposed. This algorithm is discretized to improve the original algorithm, enabling its successful application in task allocation. Furthermore, the improved method features fast search speed and high solution accuracy, exhibiting better performance compared to other heuristic algorithms.

[0177] In addition to the multi-missile mission allocation method based on the binary gorilla force optimizer provided in the foregoing embodiments, this invention also provides a multi-missile mission allocation device based on the binary gorilla force optimizer. See [link to relevant documentation]. Figure 7 The schematic diagram shown illustrates the structure of a multi-missile mission allocation device based on the binary gorilla force optimizer, indicating that the device mainly includes the following parts:

[0178] The benefit matrix determination module 701 is used to acquire the operational parameters of the missile and the target, and to determine the benefit matrix based on the operational parameters using an improved analytic hierarchy process.

[0179] The efficiency function determination module 702 is used to determine the overall efficiency function based on the benefit matrix and the chaotic initialization discrete solution space.

[0180] The task allocation module 703 is used to optimize the overall performance function using the discrete binary gorilla army optimization algorithm to obtain the task allocation matrix.

[0181] The multi-missile task allocation device based on the binary gorilla force optimizer provided in this embodiment of the invention uses an improved hierarchical analysis method to determine the benefit matrix, and introduces the battlefield situation into the calculation of the benefit matrix. This solves the problem of needing to consider both the combat situation and the strike benefit, making the final result of task allocation more in line with the actual battlefield. At the same time, the discrete binary gorilla force optimization algorithm is used to solve the overall effectiveness function, which improves the efficiency and accuracy of multi-missile cooperative combat task allocation.

[0182] In one embodiment, the aforementioned benefit matrix determination module 701 is further configured to: determine a benefit index hierarchy model for multi-missile coordinated operations based on a pre-constructed benefit index hierarchy system; wherein the benefit index hierarchy system comprises three layers: the first layer is the overall benefit index, the second layer is the situation benefit index and the performance benefit index, and the third layer is the altitude benefit index, the distance benefit index, the angle benefit index, the speed benefit index, the electronic countermeasures performance benefit index, the maneuverability performance benefit index, and the attack performance benefit index; the benefit index hierarchy model is as follows:

[0183] w ij =e 11 ×(e 21 ×E h +e 22 ×E r +e 23 ×E a +e 24 ×E v )

[0184] +e 12 ×(e 25 ×Ee +e 26 ×E m +e 27 ×E att )

[0185] Among them, w ij E represents the overall effectiveness index of allocating the i-th missile to the j-th target. h E represents the high efficiency index. r E represents the distance benefit index. a E represents the angle benefit index. v E represents the speed-efficiency index. e E represents the electronic countermeasures performance benefit index. m E represents the performance efficiency index. att e represents the attack performance efficiency index. 11 ,e 12 ,e 21 ,e 22 ,e 23 ,e 24 ,e 25 ,e 26 ,e 27 These represent the weight coefficients for each layer;

[0186] Calculate the weight coefficient matrix of each level of benefit in the benefit index hierarchy; based on the benefit index hierarchy model, the weight coefficient matrix of each level of benefit, and the benefit index, calculate the overall benefit index to obtain the benefit matrix.

[0187] In one embodiment, the benefit matrix determination module 701 is further configured to: determine an initial judgment matrix for each layer of benefit in the benefit index hierarchy; perform a logarithmic operation on the initial judgment matrix to obtain a first judgment matrix; construct an optimal transfer matrix based on the first judgment matrix; construct an optimal consistency judgment matrix based on the optimal transfer matrix; and calculate a weight coefficient matrix based on the optimal consistency judgment matrix.

[0188] In one embodiment, the performance function determination module 702 is further configured to: convert the 0-1 integer matrix of the missile-target mission allocation solution space into an m·n-dimensional solution vector space, and initialize the m·n-dimensional solution vector space using a chaotic mapping method to obtain a chaotic initialized discrete solution set space; wherein, the initialization of the m·n-dimensional solution vector space includes:

[0189] x k =rand(1,m·n) k=1,…,m·n

[0190]

[0191]

[0192] Where m represents the number of missiles, n represents the number of targets, and x k Let x represent an m·n dimensional random number vector, where a is a predetermined constant value between 0 and 1, and x... iB ,i=1,…,m·n denotes the chaotic initialization discrete solution set space;

[0193] The overall performance function is determined based on the chaotic initialization of the discrete solution space, the benefit matrix, and the pre-determined cost matrix of the missile group and the value matrix of the target; wherein, the overall performance function is:

[0194]

[0195] Where B = [b1,…,b n ] 1×n The value matrix representing the objective is C = [c1, ..., c2]. m ] 1×m Represents the cost matrix of a missile swarm. Representing the benefit matrix, Represents the task assignment matrix, x ij =0 / 1, where 0 means the i-th missile is not assigned to the j-th target, and 1 means the i-th missile is assigned to the j-th target.

[0196] In one implementation, the discrete binary gorilla army optimization algorithm includes an exploration phase and an development phase. The task allocation module 703 is further configured to: in the exploration phase, initialize the discrete solution set space based on chaos, update the position information using a variety of preset update methods to obtain the updated first volume position information; perform discrete binary conversion on the updated first volume position information to obtain a binary m·n-dimensional solution vector; calculate the fitness based on the overall performance function and the binary m·n-dimensional solution vector, and selectively retain the binary m·n-dimensional solution vector according to the fitness calculation results to obtain the optimized binary m·n-dimensional solution vector.

[0197] In one embodiment, the task allocation module 703 is further configured to: perform discrete binary conversion according to the following formula:

[0198]

[0199] Where X(t) represents the individual's current location information;

[0200] The binary m·n-dimensional solution vector is determined according to the following formula:

[0201]

[0202] Among them, X iB(t) represents the binary m·n-dimensional solution vector.

[0203] In one embodiment, the task allocation module 703 is further configured to: during the development phase, if the update parameter is greater than or equal to the judgment threshold, then use a first update mechanism to update the optimized binary m·n-dimensional solution vector to obtain the updated second volume position information; if the update parameter is less than the judgment threshold, then use a second update mechanism to update the optimized binary m·n-dimensional solution vector to obtain the updated second volume position information; perform discrete binary conversion on the updated second volume position information to obtain the updated discrete solution set space; and perform fitness calculation based on the overall performance function and the updated discrete solution set space to determine the task allocation matrix.

[0204] The device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0205] This invention also provides an electronic device, specifically, the electronic device includes a processor and a storage device; the storage device stores a computer program, and the computer program, when run by the processor, executes the method described in any of the above embodiments.

[0206] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 100 includes: a processor 80, a memory 81, a bus 82, and a communication interface 83. The processor 80, the communication interface 83, and the memory 81 are connected through the bus 82. The processor 80 is used to execute executable modules, such as computer programs, stored in the memory 81.

[0207] The memory 81 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 83 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc.

[0208] Bus 82 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 8 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0209] The memory 81 is used to store programs. After receiving an execution instruction, the processor 80 executes the program. The method executed by the device for defining the flow process disclosed in any of the foregoing embodiments of the present invention can be applied to the processor 80 or implemented by the processor 80.

[0210] The processor 80 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 80 or by software instructions. The processor 80 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 81. The processor 80 reads the information in memory 81 and, in conjunction with its hardware, completes the steps of the above method.

[0211] The computer program product of the readable storage medium provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the foregoing method embodiments. For specific implementation, please refer to the foregoing method embodiments, which will not be repeated here.

[0212] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0213] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A multi-missile task allocation method based on the binary gorilla force optimizer, characterized in that, include: The operational parameters of the missile and the target are obtained, and the benefit matrix is ​​determined based on the improved analytic hierarchy process (AHP) using the operational parameters. The overall performance function is determined based on the aforementioned benefit matrix and the chaotic initialization discrete solution space. The overall performance function is optimized using the Discrete Binary Gorilla Force Optimization Algorithm to obtain the task allocation matrix; The Discrete Binary Gorilla Squad Optimization Algorithm includes an exploration phase and an development phase. The algorithm optimizes the overall performance function to obtain the task allocation matrix. This includes: in the exploration phase, initializing the discrete solution set space based on chaos, updating the position information using multiple preset update methods to obtain the updated first volume position information; and then performing a discrete binary conversion on the updated first volume position information to obtain binary... dimensional solution vector; based on the overall performance function and the binary... The fitness of the solution vector is calculated, and the binary representation is selected based on the fitness calculation results. The dimensional solution vector yields the optimized binary solution. 1D solution vector; The updated first volume position information is then subjected to discrete binary conversion to obtain binary data. The solution vector, including: a discrete binary conversion according to the following formula: in, Indicates the individual's current location information; The optimized binary number is determined according to the following formula. 1D solution vector: in, X iB ( t ) represents the optimized binary Dimensional solution vector.

2. The method according to claim 1, characterized in that, Based on the aforementioned operational parameters, an improved analytic hierarchy process (AHP) is used to determine the benefit matrix, including: A hierarchical model of the benefit index for multi-missile coordinated operations is determined based on a pre-constructed hierarchical system of benefit indices. This hierarchical system comprises three layers: the first layer is the overall benefit index; the second layer consists of the situational benefit index and the performance benefit index; and the third layer includes the altitude benefit index, range benefit index, angle benefit index, speed benefit index, electronic countermeasures performance benefit index, maneuverability performance benefit index, and attack performance benefit index. The hierarchical model of the benefit index is as follows: in, Indicates the first i Missiles were assigned to the first j The overall benefit index of each objective E h Indicating a high efficiency index, E r Indicates the distance benefit index, E a Indicating the angle of benefit index, E v Indicating speed efficiency index, E e Indicates the performance benefit index of electronic countermeasures. E m Indicates the efficiency index of motor performance. E att This represents the attack performance efficiency index. These represent the weight coefficients for each layer; Calculate the weight coefficient matrix of each level of benefit in the benefit index hierarchy; Based on the aforementioned hierarchical model of benefit index, the weight coefficient matrix of each layer of benefit, and the benefit index, the overall benefit index is calculated to obtain the benefit matrix.

3. The method according to claim 2, characterized in that, Calculating the weight coefficient matrix of each level of benefit in the benefit index hierarchy includes: For each level of benefit in the benefit index hierarchy, determine the initial judgment matrix; The initial judgment matrix is ​​logarithmically divided to obtain the first judgment matrix; Construct an optimal transfer matrix based on the first judgment matrix; Construct the optimal consistency judgment matrix based on the optimized transfer matrix; The weight coefficient matrix is ​​calculated based on the optimal consistency judgment matrix.

4. The method according to claim 1, characterized in that, The overall performance function is determined based on the aforementioned benefit matrix and the chaotic initialization discrete solution space, including: Convert the 0-1 integer matrix of the missile-target mission allocation solution space into... The solution vector space is dimensional, and a chaotic mapping method is used to apply the solution. The chaotic initialization discrete solution set space is obtained by initializing the dimensional solution vector space; wherein, the The initialization of the dimensional solution vector space includes: in, m Indicates the number of missiles, n Indicates the number of targets. express 3D random number vector, a For a predetermined constant value between 0 and 1, This represents the initial discrete solution space of chaos; The overall performance function is determined based on the chaotic initialization discrete solution space, the benefit matrix, and the pre-determined cost matrix of the missile group and the value matrix of the target; wherein, the overall performance function is: in, A value matrix representing the objective. Represents the cost matrix of a missile swarm. Representing the benefit matrix, Represents the task allocation matrix. 0 indicates the first i The missile was not allocated j The nth target, 1 represents the nth target. i Missile allocation number j One goal.

5. The method according to claim 1, characterized in that, Based on the fitness calculation results, binary numbers are selected for retention. The dimensional solution vector yields the optimized binary solution. Following the solution vector, the method further includes: During the development phase, if the update parameter is greater than or equal to the judgment threshold, the first update mechanism is used to update the optimized binary. The solution vector is updated to obtain the updated second volume position information; If the updated parameter is less than the judgment threshold, then the second update mechanism is used to update the optimized binary. The solution vector is updated to obtain the updated second volume position information; The updated second volume position information is subjected to discrete binary conversion to obtain binary position information, and the updated discrete solution set space is determined based on the binary position information; Fitness is calculated based on the overall performance function and the updated discrete solution space to determine the task assignment matrix.

6. A multi-missile cooperative combat mission allocation device based on the binary gorilla force optimizer, characterized in that, include: The benefit matrix determination module is used to acquire the operational parameters of the missile and the target, and to determine the benefit matrix based on the operational parameters using an improved analytic hierarchy process. The efficiency function determination module is used to determine the overall efficiency function based on the efficiency matrix and the chaotic initialized discrete solution space; The task allocation module is used to optimize the overall performance function using the discrete binary gorilla army optimization algorithm to obtain the task allocation matrix. The discrete binary gorilla army optimization algorithm includes an exploration phase and an development phase. The task allocation module is specifically used for: in the exploration phase, based on the chaotic initialization of the discrete solution set space, updating the position information using multiple preset update methods to obtain the updated first volume position information; and performing a discrete binary conversion on the updated first volume position information to obtain binary... dimensional solution vector; based on the overall performance function and the binary... The fitness of the solution vector is calculated, and the binary representation is selected based on the fitness calculation results. The dimensional solution vector yields the optimized binary solution. 1D solution vector; The task allocation module is specifically used to perform discrete binary conversion according to the following formula: in, Indicates the individual's current location information; The optimized binary number is determined according to the following formula. 1D solution vector: in, X iB ( t ) represents the optimized binary Dimensional solution vector.

7. An electronic device, characterized in that, The method includes a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to implement the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program thereon, characterized in that, The computer program is executed by the processor to perform the steps of the method described in any one of claims 1 to 5.

Images