Ammunition configuration optimization method and system based on multi-layer optimization strategy and storage medium

Abstract

The invention provides an ammunition configuration optimization method and system based on a multi-layer optimization strategy, and a storage medium. The method comprises the following steps: obtaining a plurality of task targets based on a combat task; according to the plurality of task targets, matching a plurality of target precise guidance ammunitions, and based on the suitability of the target precise guidance ammunitions, matching a plurality of ammunition carrying platforms; quantifying the associated elements to obtain a target-ammunition quantitative mapping relation matrix of the multiple target accurate guidance ammunitions and the multiple task targets and an ammunition-platform quantitative mapping relation matrix of the multiple ammunition carrying platforms and the multiple target accurate guidance ammunitions; combining the target-ammunition quantitative mapping relation matrix and the ammunition-platform quantitative mapping relation matrix to construct an ammunition configuration double-layer optimization model; and solving the ammunition configuration double-layer optimization model to obtain an optimal loading configuration scheme of the target precise guidance ammunition. The method has the effect of improving the accuracy and efficiency of ammunition configuration optimization.

Description

Technical Field

[0001] The present invention belongs to the technical field of ammunition configuration optimization, and specifically relates to an ammunition configuration optimization method, system and storage medium based on a multi-layer optimization strategy. Background Art

[0002] The optimization of precision-guided ammunition configuration is a basic way to refine the strategic objectives and campaign tasks of joint operations into specific plans and achieve adaptive support. Considering a single strike mission, precision-guided ammunition has the characteristics of diverse carrier platforms, limited ammunition reserves, and high ammunition costs, which is a typical NP-hard problem. To further improve the precision strike ability, reduce the burden of precision strikes, and enhance the combat effectiveness of troops, it is necessary to conduct more in-depth research on the optimization methods for precision-guided ammunition configuration.

[0003] For the optimization of ammunition configuration, most of the existing technologies currently use heuristic algorithms such as Genetic Algorithm (GA), Adaptive Large Neighborhood Search Algorithm, Simulated Annealing Algorithm, etc. to solve it. However, the existing technologies usually only analyze the ammunition configuration problem. Traditional precision-guided ammunition configuration optimization only considers the quantity of precision-guided ammunition and ignores the diversity of ammunition carrier platforms, resulting in inaccurate ammunition configuration optimization results and low optimization efficiency. Summary of the Invention

[0004] The present invention provides an ammunition configuration optimization method, system and storage medium based on a multi-layer optimization strategy to solve the problems of inaccurate ammunition configuration optimization results and low optimization efficiency.

[0005] In the first aspect, the present invention provides an ammunition configuration optimization method based on a multi-layer optimization strategy, and the method includes the following steps:

[0006] Obtain multiple mission objectives based on the combat mission;

[0007] Match multiple target precision-guided ammunitions according to the multiple mission objectives, and match multiple ammunition carrier platforms based on the adaptability of the target precision-guided ammunitions;

[0008] Quantify the correlation factors between the multiple target precision-guided ammunitions and the multiple mission objectives to obtain a target-ammunition quantization mapping relationship matrix between the multiple target precision-guided ammunitions and the multiple mission objectives;

[0009] Quantify the correlation factors between the multiple ammunition carrier platforms and the multiple target precision-guided ammunitions to obtain an ammunition-platform quantization mapping relationship matrix between the multiple ammunition carrier platforms and the multiple target precision-guided ammunitions;

[0010] Combining the target-ammunition quantitative mapping relationship matrix and the ammunition-platform quantitative mapping relationship matrix, and taking the minimization of the total ammunition consumption when loading the target precision-guided ammunition to complete the combat mission as the optimization goal, a two-layer optimization model for ammunition configuration is constructed;

[0011] Solve the two-layer optimization model for ammunition configuration to obtain the optimal loading configuration plan of the target precision-guided ammunition.

[0012] Optionally, the construction of the two-layer optimization model for ammunition configuration by combining the target-ammunition quantitative mapping relationship matrix and the ammunition-platform quantitative mapping relationship matrix, and taking the minimization of the total ammunition consumption when loading the target precision-guided ammunition to complete the combat mission as the optimization goal includes the following steps:

[0013] Based on the target-ammunition quantitative mapping relationship matrix, and taking the minimization of the total ammunition consumption when loading the target precision-guided ammunition to complete the combat mission as the optimization goal, construct an upper-layer optimization model for target-ammunition configuration;

[0014] Solve the upper-layer optimization model for target-ammunition configuration to obtain the quantity of the target precision-guided ammunition that needs to be carried by the ammunition carrier platform;

[0015] Combining the ammunition quantity and the ammunition-platform quantitative mapping relationship matrix, and taking the minimization of the total ammunition consumption when loading the target precision-guided ammunition to complete the combat mission as the optimization goal, construct a lower-layer optimization model for ammunition-platform configuration;

[0016] Merge the upper-layer optimization model for target-ammunition configuration and the lower-layer optimization model for ammunition-platform configuration into a two-layer optimization model for ammunition configuration.

[0017] Optionally, the upper-layer optimization model for target-ammunition configuration is as follows:

[0018] Optimization goal:

[0019]

[0020] Constraints:

[0021]

[0022] In the formula: Min TC1 represents the optimization goal of the upper-layer optimization model for target-ammunition configuration, m represents the set of target types of the mission objectives, n represents the set of ammunition types of the target precision-guided ammunition, j represents the j-th type of the target precision-guided ammunition in the ammunition type set, i represents the i-th type of the mission objectives in the target type set, c i represents the quantity of the i-th type of mission objectives, d jIndicates the number of ammunitions of the target precision-guided ammunitions for which the types of ammunitions are concentrated for completing the combat mission, Price ij Indicates the unit price of the ammunitions of the target precision-guided ammunitions for completing the combat mission, a ij Indicates the matrix element in the target-ammunition quantization mapping relationship matrix, A ij Indicates the recommended quantity of ammunition measurement;

[0023] The lower-layer optimization model of the ammunition-platform configuration is as follows:

[0024] Optimization objective:

[0025]

[0026] Constraint conditions:

[0027]

[0028] In the formula: Min TC2 represents the optimization objective of the lower-layer optimization model of the ammunition-platform configuration, p represents the set of platform types of the ammunition-carrying platforms, k represents the k-th type of ammunition-carrying platform in the set of platform types, p k Indicates the number of ammunition-carrying platforms in the set of platform types for carrying the target precision-guided ammunitions, c j Indicates the number of ammunitions of the target precision-guided ammunitions that need to be carried by the ammunition-carrying platforms, Price jk Indicates the unit price of the ammunition-carrying platforms for carrying the target precision-guided ammunitions, b jk Indicates the matrix element in the ammunition-platform quantization mapping relationship matrix, B jk Indicates the number of ammunitions that can be successfully launched when using the k-th type of ammunition-carrying platform to launch the j-th type of target precision-guided ammunitions.

[0029] Optionally, the double-layer optimization model of the ammunition configuration is as follows:

[0030] Optimization objective:

[0031]

[0032] Constraint conditions:

[0033]

[0034] Optionally, solving the double-layer optimization model of the ammunition configuration to obtain the optimal loading configuration plan of the target precision-guided ammunitions includes the following steps:

[0035] Solve the double-layer optimization model of ammunition configuration by using the stage optimization method based on the exact algorithm to obtain the first loading configuration plan of the target precision-guided ammunition;

[0036] Solve the double-layer optimization model of ammunition configuration by using the generalized distance minimization method based on the exact algorithm to obtain the second loading configuration plan of the target precision-guided ammunition;

[0037] Take the plan with the minimum total ammunition consumption in the first loading configuration plan and the second loading configuration plan as the optimal loading configuration plan.

[0038] Optionally, the process of solving the double-layer optimization model of ammunition configuration by using the stage optimization method based on the exact algorithm to obtain the first loading configuration plan of the target precision-guided ammunition includes the following steps:

[0039] Solve the upper-layer optimization model of target-ammunition configuration in the double-layer optimization model of ammunition configuration by using the branch and bound method in the exact algorithm to obtain the quantity of the target precision-guided ammunition that needs to be carried on the ammunition carrier platform;

[0040] Substitute the quantity of the target precision-guided ammunition that needs to be carried on the ammunition carrier platform into the lower-layer optimization model of ammunition-platform configuration in the double-layer optimization model of ammunition configuration;

[0041] Solve the lower-layer optimization model of ammunition-platform configuration by using the branch and bound method to obtain the first loading configuration plan of the target precision-guided ammunition.

[0042] Optionally, the process of solving the double-layer optimization model of ammunition configuration by using the generalized distance minimization method based on the exact algorithm to obtain the second loading configuration plan of the target precision-guided ammunition includes the following steps:

[0043] Use the generalized distance weighting method to assign the same weight to the objective functions of the upper-layer optimization model of target-ammunition configuration and the lower-layer optimization model of ammunition-platform configuration;

[0044] Integrate the upper-layer optimization model of target-ammunition configuration and the lower-layer optimization model of ammunition-platform configuration based on the assignment of the weight to obtain an optimized integrated model, and the optimized integrated model is as follows:

[0045] Optimization objective:

[0046]

[0047] Constraint conditions:

[0048]

[0049] Solve the optimization integration model using the branch and bound method in the exact algorithm to obtain the second loading configuration plan of the target precision-guided munition.

[0050] Optionally, the steps for solving the double-layer optimization model of the ammunition configuration to obtain the optimal loading configuration plan of the target precision-guided munition are as follows:

[0051] Define the upper-layer chromosome encoding based on the upper-layer optimization model of the target-ammunition configuration, and define the lower-layer chromosome encoding based on the lower-layer optimization model of the ammunition-platform configuration;

[0052] According to the upper-layer chromosome encoding and using the greedy algorithm, construct the upper-layer initial population that satisfies the constraint conditions in the upper-layer optimization model of the target-ammunition configuration, and use the upper-layer initial population as the target population;

[0053] Execute the double-layer loop nested genetic algorithm in combination with the target population and the lower-layer chromosome encoding until the number of iterations of the double-layer loop nested genetic algorithm reaches the preset first iteration number threshold, and obtain the optimal upper-layer individual and the optimal lower-layer individual output by the final iteration;

[0054] Generate the optimal loading configuration plan of the target precision-guided munition by combining the optimal upper-layer individual and the optimal lower-layer individual output by the final iteration;

[0055] The double-layer loop nested genetic algorithm specifically includes the following steps:

[0056] Set the first fitness function values of all individuals in the target population based on the optimization objective of the upper-layer optimization model of the target-ammunition configuration;

[0057] Select the upper-layer parent individual and the upper-layer mother individual from the target population, and perform the crossover and mutation operations on the upper-layer parent individual and the upper-layer mother individual to obtain the optimal upper-layer individual in the target population and the optimal first fitness function value of the optimal upper-layer individual;

[0058] Construct the lower-layer initial population that satisfies the constraint conditions in the lower-layer optimization model of the ammunition-platform configuration by combining the optimal upper-layer individual and the lower-layer chromosome encoding, and use the lower-layer initial population as the sub-target population;

[0059] Execute the single-layer loop genetic algorithm based on the sub-target population until the number of iterations of the single-layer loop genetic algorithm reaches the preset second iteration number threshold, and output the optimal second fitness function value of the optimal lower-layer individual in the sub-target population;

[0060] Take the sum of the optimal first fitness function value and the optimal second fitness function value as the global optimal fitness function value;

[0061] Re-select the optimal upper-layer individuals in the target population based on the global optimal fitness function value, and form the target population of the next generation with the re-selected optimal upper-layer individuals;

[0062] The single-layer loop genetic algorithm specifically includes the following steps:

[0063] Set the second fitness function values of all individuals in the sub-target population based on the optimization objective of the ammunition-platform configuration lower-layer optimization model;

[0064] Select lower-layer parent individuals and lower-layer mother individuals from the sub-target population, and perform crossover and mutation operations on the lower-layer parent individuals and the lower-layer mother individuals to obtain the optimal lower-layer individuals of the current generation, and form the sub-target population of the next generation with the optimal lower-layer individuals of the current generation.

[0065] In a second aspect, the present invention also provides an ammunition configuration optimization system based on a multi-layer optimization strategy, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the ammunition configuration optimization method based on the multi-layer optimization strategy as described in the first aspect.

[0066] In a third aspect, the present invention also provides a computer-readable storage medium, on which instructions are stored. When the instructions are executed by a processor, the processor is configured to execute the ammunition configuration optimization method based on the multi-layer optimization strategy as described in the first aspect.

[0067] The beneficial effects of the present invention are as follows:

[0068] Since different mission objectives need to match different precision-guided ammunitions, and different precision-guided ammunitions need to be adapted to different ammunition-carrying platforms, the present invention constructs a two-layer optimization model for ammunition configuration of the target-ammunition layer and the ammunition-platform layer by respectively quantifying the correlation factors between the target and the ammunition and the correlation factors between the ammunition and the platform. The constructed two-layer optimization model for ammunition configuration is a two-layer programming model based on a multi-layer optimization strategy. Compared with the prior art in which the optimization of precision-guided ammunition configuration only considers the quantity of precision-guided ammunitions and ignores the diversity of the carrying platforms, the present invention introduces a multi-layer optimization strategy and considers the mutual influence between each level of the target, ammunition, and platform, and conducts global optimization to solve, thereby improving the optimization efficiency and accuracy of precision-guided ammunition configuration. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 It is a schematic flowchart of the ammunition configuration optimization method based on the multi-layer optimization strategy in the present invention.

[0070] Figure 2Schematic diagram of the correlation relationship among the mission objective, the target precision-guided munition, and the munition carrier platform in the present invention.

[0071] Figure 3 Schematic diagram of the "target - munition - platform" double - layer correlation matrix in the present invention.

[0072] Figure 4 Schematic diagram of the weight assignment of the generalized distance minimization method in the present invention.

[0073] Figure 5 Schematic diagram of the complete process of the genetic algorithm in the present invention.

[0074] Figure 6 Schematic diagram of the convergence analysis of the genetic algorithm in the present invention. Detailed implementation manners

[0075] Next, the technical solutions in the embodiments of the present application will be clearly described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0076] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are usually of the same category, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally indicates an "or" relationship between the associated objects before and after.

[0077] The present invention discloses an ammunition configuration optimization method based on a multi - layer optimization strategy. Refer to Figure 1 , Figure 1 which is a schematic diagram of the process of the ammunition configuration optimization method based on a multi - layer optimization strategy in an embodiment. It should be understood that although Figure 1 the steps in the flowchart are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, Figure 1At least some of the steps may include multiple sub-steps or multiple stages, which do not necessarily need to be executed and completed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages does not necessarily need to be sequential, but can be executed alternately or in turn with at least some of the sub-steps or stages of other steps or other steps. As Figure 1 shown, the ammunition configuration optimization method based on the multi-layer optimization strategy specifically includes the following steps:

[0078] S101. Obtain multiple mission objectives based on the combat mission.

[0079] Among them, the combat mission can be obtained through the combat command system, and multiple different types of mission objectives that need to be accurately struck can be retrieved from the combat mission through target retrieval.

[0080] S102. Match multiple types of target precision-guided ammunitions according to multiple mission objectives, and match multiple ammunition carrying platforms based on the adaptability of the target precision-guided ammunitions.

[0081] Among them, the target precision-guided ammunition is usually a precision-guided missile. The target precision-guided ammunition is a weapon with a warhead, a power device, and a guidance device that can control the flight trajectory, and it can direct the warhead to the target and damage the mission objective. It can also be considered that the target precision-guided ammunition is a weapon that is driven by its own power and detects, processes, guides, and controls through the guidance system to hit the target. Refer to Figure 2 , in the precision-guided ammunition configuration optimization method based on the multi-layer optimization strategy in this embodiment, the main problem levels considered are "target - ammunition - platform", that is, to complete the task of accurately striking the mission objective with the target precision-guided ammunition and carrying the precision-guided ammunition on the corresponding ammunition carrying platform. Among them, the ammunition carrying platform mainly considers the base for launching the precision-guided ammunition, which is divided into land platforms, sea platforms, and air platforms, such as launch sites, aircraft carriers, fighter jets, etc.

[0082] S103. Quantify the correlation factors between multiple types of target precision-guided ammunitions and multiple mission objectives to obtain the target-ammunition quantization mapping relationship matrix of multiple types of target precision-guided ammunitions and multiple mission objectives.

[0083] Among them, the factors affecting the precision-guided ammunition configuration optimization problem in the context of joint operations are numerous, involving multiple targets, multiple types of ammunitions, and multiple platforms. Refer to Figure 3, in order to sort out the mathematical relationships among the target, ammunition, and platform, optimize the configuration process of precision-guided ammunition, and improve the efficiency of configuration optimization, the mapping relationship matrix method is now used to model and analyze the problem of optimizing the configuration of precision-guided ammunition under the background of joint operations. By designing a multi-layer mapping relationship matrix of "target-ammunition-platform", the quantifiable relationships corresponding to each other among the basic elements are found, and thus the mapping relationship frameworks of "target-ammunition" and "ammunition-platform" are constructed. As Figure 3 shown, there is a certain mapping relationship between "target-ammunition". The above-mentioned related elements can be quantified, and the correlation between the rows and columns of the "target-ammunition" matrix can be found. Referring to Table 1, by quantifying the related elements between various types of target precision-guided ammunition and multiple mission targets, the target-ammunition quantitative mapping relationship matrix of various types of target precision-guided ammunition and multiple mission targets can be obtained, and the related elements are such as target types and ammunition models.

[0084] Table 1 Target-Ammunition Quantitative Mapping Relationship Matrix

[0085] Ammunition 1 Ammunition 2 … Ammunition n Target 1 <![CDATA[A 11 > <![CDATA[A 12 > … <![CDATA[A 1n > Target 2 <![CDATA[A 21 > <![CDATA[A 22 > … <![CDATA[A 2n > … … … … … Target m <![CDATA[A m1 > <![CDATA[A m2 > … Amn

[0086] S104. Quantify the related elements between various ammunition carrier platforms and various types of target precision-guided ammunition to obtain the ammunition-platform quantitative mapping relationship matrix of various ammunition carrier platforms and various types of target precision-guided ammunition.

[0087] Among them, as Figure 3 shown, there is a certain mapping relationship between "ammunition-platform". The above-mentioned related elements can be quantified, and the correlation between the rows and columns of the "ammunition-platform" matrix can be found. Referring to Table 2, by quantifying the related elements between various ammunition carrier platforms and various types of target precision-guided ammunition, the ammunition-platform quantitative mapping relationship matrix of various ammunition carrier platforms and various types of target precision-guided ammunition can be obtained, and the related elements are such as ammunition models and carrier platform models.

[0088] Table 2 Ammunition-Platform Quantitative Mapping Relationship Matrix

[0089] Platform 1 Platform 2 … Platform p Ammunition 1 <![CDATA[B 11 > <![CDATA[B 12 > … <![CDATA[B 1p > Ammunition 2 <![CDATA[B 21 > <![CDATA[B 22 > … <![CDATA[B 2p > … … … … … Ammunition n <![CDATA[B n1 > <![CDATA[B n2 > … <![CDATA[B np >

[0090] S105. Combine the target-ammunition quantitative mapping relationship matrix and the ammunition-platform quantitative mapping relationship matrix, and take the minimum total ammunition consumption when loading target precision-guided ammunition to complete the combat mission as the optimization goal to construct a two-layer optimization model for ammunition configuration.

[0091] Among them, based on the target-ammunition quantization mapping relationship matrix and the ammunition-platform quantization mapping relationship matrix, combined with the precise guided ammunition configuration principle, on the basis of completing effective strikes, its economic benefits are further improved to provide resource guarantee for subsequent strike needs. Determine the total economic cost of combat consumption when the precise guided ammunition precisely completes the strike mission as the optimization goal, and construct an optimization model for the configuration of precise guided ammunition.

[0092] S106. Solve the two-layer optimization model for ammunition configuration to obtain the optimal loading configuration plan for the target precise guided ammunition.

[0093] Among them, use solution algorithms such as genetic algorithms and exact algorithms to optimize and solve the two-layer optimization model for ammunition configuration at the global level to obtain the optimization plan for the configuration of precise guided ammunition among "target-ammunition-platform".

[0094] The implementation principle of this embodiment is as follows:

[0095] The present invention constructs a two-layer optimization model for ammunition configuration of the target-ammunition layer and the ammunition-platform layer by respectively quantifying the correlation elements between the target and the ammunition and the correlation elements between the ammunition and the platform. The constructed two-layer optimization model for ammunition configuration is a two-layer programming model based on a multi-layer optimization strategy. Compared with the prior art where the optimization of the configuration of precise guided ammunition only considers the quantity of precise guided ammunition and ignores the diversity of the carrier platforms, the present invention introduces a multi-layer optimization strategy and considers the mutual influence among various levels of the target, ammunition, and platform, and conducts global optimization and solution, thereby improving the optimization efficiency and accuracy of the configuration of precise guided ammunition.

[0096] In one of the embodiments, step S105 specifically includes the following steps:

[0097] Based on the target-ammunition quantization mapping relationship matrix, and with the minimization of the total ammunition consumption when loading the target precise guided ammunition to complete the combat mission as the optimization goal, construct the upper-layer optimization model for target-ammunition configuration;

[0098] Solve the upper-layer optimization model for target-ammunition configuration to obtain the quantity of ammunition of the target precise guided ammunition that needs to be carried by the ammunition carrier platform;

[0099] Combined with the ammunition quantity and the ammunition-platform quantization mapping relationship matrix, and with the minimization of the total ammunition consumption when loading the target precise guided ammunition to complete the combat mission as the optimization goal, construct the lower-layer optimization model for ammunition-platform configuration;

[0100] Merge the upper-layer optimization model for target-ammunition configuration and the lower-layer optimization model for ammunition-platform configuration into a two-layer optimization model for ammunition configuration.

[0101] In this embodiment, at the "target - ammunition" level where the target - ammunition quantization mapping relationship matrix is located, the targets are divided into m types, and the number of the i - th target that needs to be precisely struck for a certain task is c i ; the ammunitions are divided into n types, and the available quantity of the j - th type of ammunition is d j , and the unit price of the j - th type of available ammunition is Price ij . In this level, the quantity of ammunition consumed to precisely strike each task target is defined as the ammunition measurement recommended quantity A ij , which comprehensively considers factors such as target characteristics, damage ability of precision - guided ammunitions, and battlefield environment, and is calculated through the developed ammunition measurement system. A ij represents the number of precision - guided ammunitions that need to be successfully launched to achieve a damage effect when using only the j - th type of precision - guided ammunition to strike a single i - th type of target. When A ij = ∞, it means that the quantity of the j - th type of precision - guided ammunition required is infinite, that is, the j - th type of precision - guided ammunition cannot complete the precision - strike task of effectively striking the i - th type of target.

[0102] In this embodiment, the upper - layer optimization model of target - ammunition configuration is as follows:

[0103] Since the ammunition reserve quantity of precision - guided ammunitions is limited and the ammunition cost is high, considering the principle of precision - guided ammunition configuration to further reduce the consumption in the precision - strike process on the basis of achieving effective strikes and providing guarantee for subsequent strikes, the optimization objective is set as follows during the construction of the upper - layer optimization model of target - ammunition configuration:

[0104]

[0105] The constraint conditions consider the magnitude relationship between the ammunition carrying quantity and the ammunition launching quantity. The specific constraint conditions are as follows:

[0106]

[0107] In the formula: Min TC1 represents the optimization objective of the upper - layer optimization model of target - ammunition configuration, m represents the set of target types of task targets, n represents the set of ammunition types of target precision - guided ammunitions, j represents the j - th type of target precision - guided ammunition in the ammunition type set, i represents the i - th type of task target in the target type set, c i represents the number of the i - th type of task target, d j represents the quantity of the target precision - guided ammunition in the ammunition type set used to complete the combat mission, Price ij represents the unit price of the target precision - guided ammunition used to complete the combat mission, a ij represents the matrix element in the target - ammunition quantization mapping relationship matrix, and A ij represents the ammunition measurement recommended quantity.

[0108] At the "ammunition - platform" level where the ammunition - platform quantization mapping relationship matrix is located, the number of ammunitions that need to be carried by the ammunition - carrying platforms obtained through the calculation at the "target - ammunition" level is c j , the ammunition - carrying platforms are divided into p types, and the number of the k - th type of ammunition - carrying platforms is p k , and the unit price of the k - th type of ammunition - carrying platform is Price jk . In this level, the number of ammunitions that each platform can carry to complete the task of carrying precision - guided ammunitions is defined as the recommended carrying amount B of ammunitions jk , and this physical quantity is obtained by collecting through the theater dictionary, considering various factors such as the parameters of precision - guided ammunitions, the parameters of carrying platforms, and the battlefield environment. B jk represents the number of precision - guided ammunitions that can be successfully launched when using the k - th type of ammunition - carrying platform to launch the j - th type of target precision - guided ammunition. When B jk = 0, it means that the ammunition - carrying platform k cannot carry or has not carried the target precision - guided ammunition j

[0109] In this embodiment, the lower - layer optimization model of ammunition - platform configuration is as follows:

[0110] There is also an optimization configuration relationship between ammunitions and carrying platforms. Considering that on the basis of selecting a certain type of precision - guided ammunition, different platforms can be used for launching, and the number of precision - guided ammunitions that different carrying platforms can support for launching is different, and there are significant differences in the economic costs of using different carrying platforms for launching precision - guided ammunitions. Considering its economic benefits and the number of precision - guided ammunitions that different carrying platforms allow to carry comprehensively, there is also an optimization configuration problem to be considered at this level. Therefore, when constructing the lower - layer optimization model of ammunition - platform configuration, its optimization goal is set as:

[0111]

[0112] The constraint conditions consider the magnitude relationship between the ammunition carrying quantity and the ammunition launch quantity. The specific constraint conditions are as follows:

[0113]

[0114] In the formula: Min TC2 represents the optimization goal of the lower - layer optimization model of ammunition - platform configuration, p represents the set of platform types of ammunition - carrying platforms, k represents the k - th type of ammunition - carrying platform in the set of platform types, p k represents the number of platforms of ammunition - carrying platforms used to carry target precision - guided ammunitions in the set of platform types, c j represents the number of ammunitions of target precision - guided ammunitions that need to be carried by ammunition - carrying platforms, Price jk represents the unit price of the platforms of ammunition - carrying platforms used to carry target precision - guided ammunitions, bjk Denote the matrix element in the ammunition-platform quantization mapping relation matrix, B jk Denote the number of ammunitions that can be successfully launched when using the k-th type of ammunition carrier platform to launch the j-th type of target precision-guided ammunition.

[0115] In this embodiment, the above-mentioned upper-layer optimization model of target-ammunition configuration and the lower-layer optimization model of ammunition-platform configuration are integrated into a two-layer optimization model of ammunition configuration. The two-layer optimization model of ammunition configuration is specifically as follows:

[0116] Optimization objective:

[0117]

[0118] Constraint conditions:

[0119]

[0120] In one of the embodiments, step S106 specifically includes the following steps:

[0121] Solve the two-layer optimization model of ammunition configuration by using the stage optimization method based on the exact algorithm to obtain the first loading configuration plan of the target precision-guided ammunition;

[0122] Solve the two-layer optimization model of ammunition configuration by using the generalized distance minimization method based on the exact algorithm to obtain the second loading configuration plan of the target precision-guided ammunition;

[0123] Take the plan with the minimum total ammunition consumption in the first loading configuration plan and the second loading configuration plan as the optimal loading configuration plan.

[0124] In this embodiment, considering that both the upper-layer optimization model of target-ammunition configuration and the lower-layer optimization model of ammunition-platform configuration are integer linear programming problems, in order to further obtain the local optimal solution and the global optimal solution of the two-layer optimization model of ammunition configuration, the stage optimization method based on the exact algorithm can be used for solving to obtain the first loading configuration plan. On the other hand, considering that the solution complexity of the two-layer optimization model of ammunition configuration is relatively high and it is an NP-hard problem, it is not very realistic to use the enumeration method to list and solve one by one. Therefore, the generalized distance minimization method based on the exact algorithm can also be used to optimize and solve the above model to obtain the second loading configuration plan. By comparing the first loading configuration plan and the second loading configuration plan, take the plan with the minimum total ammunition consumption in the first loading configuration plan and the second loading configuration plan as the optimal loading configuration plan.

[0125] In one of the embodiments, the step of solving the two-layer optimization model of ammunition configuration by using the stage optimization method based on the exact algorithm to obtain the first loading configuration plan of the target precision-guided ammunition specifically includes the following steps:

[0126] Use the branch and bound method in the exact algorithm to solve the upper-level optimization model of target-ammunition allocation in the double-layer optimization model of ammunition allocation, and obtain the quantity of ammunition for the target precision-guided ammunition that needs to be carried on the ammunition-carrying platform.

[0127] Substitute the quantity of ammunition for the target precision-guided ammunition that needs to be carried on the ammunition-carrying platform into the lower-level optimization model of ammunition-platform allocation in the double-layer optimization model of ammunition allocation.

[0128] Use the branch and bound method to solve the lower-level optimization model of ammunition-platform allocation, and obtain the first loading configuration plan for the target precision-guided ammunition.

[0129] In this embodiment, it is obvious that using the exact algorithm to solve the integer linear programming problem can only optimize and solve for a single level. Therefore, the stage optimization method is first adopted to gradually expand the optimization and solution layer by layer to obtain the final solution result. Based on the stage optimization method for optimization and solution, first solve the upper-level optimization model of target-ammunition allocation constructed for the upper level, that is, the "target-ammunition" level, to obtain the upper-level loading configuration plan, and obtain the quantity c of ammunition for the target precision-guided ammunition that needs to be carried on the ammunition-carrying platform. j Then substitute this parameter c j into the constructed lower-level optimization model of ammunition-platform allocation, and also use the branch and bound method to solve to obtain the lower-level loading configuration plan. Finally, summarize the upper-level loading configuration plan and the lower-level loading configuration plan to obtain the first loading configuration plan for the target precision-guided ammunition.

[0130] In one of the embodiments, the step of using the generalized distance minimization method based on the exact algorithm to solve the double-layer optimization model of ammunition allocation to obtain the second loading configuration plan for the target precision-guided ammunition specifically includes the following steps:

[0131] Adopt the generalized distance weighting method to assign the same weight to the objective functions of the upper-level optimization model of target-ammunition allocation and the lower-level optimization model of ammunition-platform allocation.

[0132] Based on the assignment of weights, integrate the upper-level optimization model of target-ammunition allocation and the lower-level optimization model of ammunition-platform allocation to obtain an optimized integrated model. The optimized integrated model is as follows:

[0133] Optimization objective:

[0134]

[0135] Constraint conditions:

[0136]

[0137] Solve the optimization integration model using the branch and bound method in the exact algorithm to obtain the second loading configuration plan for the target precision-guided munition.

[0138] In this embodiment, the double-layer programming model of "target - ammunition - platform" is considered as a whole. Considering the analysis and solution based on the generalized distance minimization method, it is necessary to optimize and integrate the upper-layer optimization model of target-ammunition configuration and the lower-layer optimization model of ammunition-platform configuration to obtain the integer linear programming model of "target - ammunition - platform", that is, the optimization integration model.

[0139] Specifically, in order to accurately reflect the hierarchical structure of the system, referring to Figure 4 , in this embodiment, for the relative weights of different levels and the objective functions of the same level, the method of assigning weights by generalized distance is adopted to optimize and integrate the above models. This method has the advantages of simplicity and effectiveness compared with the stage optimization method in solving multi-layer programming problems. In the double-layer decision-making of this embodiment, the upper and lower layer optimization objectives (that is, Figure 4 f1 and f2 in ) are fully cooperative, that is, the nature of the optimization objectives is the same, and both are to minimize the task consumption of completing an accurate strike mission. It can be considered that the nature of the objective functions at different levels is the same, so the same weight is assigned. Thus, the optimization integration model under the generalized distance minimization method can be obtained, and then the second loading configuration plan of the model is obtained by using the exact algorithm. The second loading configuration plan is obtained by globally optimizing and solving the double-layer optimization model of ammunition configuration, while the first loading configuration plan is obtained by stage optimizing and solving the double-layer optimization model of ammunition configuration.

[0140] In one of the embodiments, step S106 specifically includes the following steps:

[0141] Define the upper-layer chromosome encoding based on the upper-layer optimization model of target-ammunition configuration, and define the lower-layer chromosome encoding based on the lower-layer optimization model of ammunition-platform configuration;

[0142] According to the upper-layer chromosome encoding and using the greedy algorithm, construct the upper-layer initial population that satisfies the constraint conditions in the upper-layer optimization model of target-ammunition configuration, and take the upper-layer initial population as the target population;

[0143] Execute the double-loop nested genetic algorithm by combining the target population and the lower-layer chromosome encoding until the number of iterations of the double-loop nested genetic algorithm reaches the preset first iteration number threshold, and obtain the optimal upper-layer individual and the optimal lower-layer individual output by the final iteration;

[0144] Generate the optimal loading configuration plan for the target precision-guided munition by combining the optimal upper-layer individual and the optimal lower-layer individual output by the final iteration;

[0145] The double-loop nested genetic algorithm specifically includes the following steps:

[0146] Set the first fitness function value of all individuals in the target population based on the optimization objective of the upper-layer optimization model for target-ammunition configuration.

[0147] Select upper-layer parental individuals and upper-layer maternal individuals from the target population, and perform crossover and mutation operations on the upper-layer parental individuals and upper-layer maternal individuals to obtain the optimal upper-layer individual in the target population and the optimal first fitness function value of the optimal upper-layer individual.

[0148] Combine the optimal upper-layer individual and the lower-layer chromosome encoding to construct a lower-layer initial population that satisfies the constraint conditions in the lower-layer optimization model for ammunition-platform configuration, and use the lower-layer initial population as the sub-target population.

[0149] Execute the single-loop genetic algorithm based on the sub-target population until the number of iterations of the single-loop genetic algorithm reaches the preset second iteration number threshold, and output the optimal second fitness function value of the optimal lower-layer individual in the sub-target population.

[0150] Take the sum of the optimal first fitness function value and the optimal second fitness function value as the global optimal fitness function value.

[0151] Re-select the optimal upper-layer individual in the target population based on the global optimal fitness function value, and form the next-generation target population with the re-selected optimal upper-layer individuals.

[0152] The single-loop genetic algorithm specifically includes the following steps:

[0153] Set the second fitness function value of all individuals in the sub-target population based on the optimization objective of the lower-layer optimization model for ammunition-platform configuration.

[0154] Select lower-layer parental individuals and lower-layer maternal individuals from the sub-target population, and perform crossover and mutation operations on the lower-layer parental individuals and lower-layer maternal individuals to obtain the optimal lower-layer individual of the current generation, and form the next-generation sub-target population with the optimal lower-layer individuals of the current generation.

[0155] In this embodiment, referring to Figure 5 , first, perform the encoding of the genetic algorithm. The decision variables that need to be given in the "target-ammunition" and "ammunition-platform" layers are the weapon ammunition configuration plan and the platform loading plan respectively. The decision variables exist in the form of matrices. For the encoding of such problems, if directly using matrices for encoding, it is difficult to perform subsequent genetic, crossover, and mutation, resulting in the algorithm being unable to run normally, and it cannot be achieved using traditional binary encoding. Therefore, it can be achieved by defining the chromosome individuals.

[0156] Specifically, define the upper-layer chromosome encoding of the "target-ammunition" layer as S1 based on the upper-layer optimization model for target-ammunition configuration

[0157] S1 = {a1, a2, a3, ..., a i}, a i ∈ {1, 2, 3, ..., n}

[0158] where S1 is the chromosome of the "target - ammunition" layer; a i is a gene, n represents the ammunition type; i is the number of targets. a i That is, it means using the nth type of ammunition to achieve precise strikes on the ith target.

[0159] Based on the lower - layer optimization model of the ammunition - platform configuration, the lower - layer chromosome coding of the "ammunition - platform" layer is defined as S2

[0160] S2 = {b1, b2, b3, ..., b j}, b j ∈ {1, 2, 3, ..., p}

[0161] where S2 is the chromosome of the "ammunition - platform" layer; b j is a gene, p represents the ammunition - carrying platform type; j is the number of ammunitions to be carried onto the platform. b j That is, it means using the pth type of platform to complete the task of carrying precision - guided ammunitions for the jth target.

[0162] After the coding is completed, considering the initialization of the population, in the actual operation process, since the randomly generated initial solutions may not satisfy the constraints, the search range of the algorithm is large and the overall efficiency is low. Therefore, when initializing the population, a feasible initial solution that satisfies the constraints is constructed based on the greedy idea. This method greatly reduces the search range of the algorithm, enabling the solution to converge faster and better towards the optimal direction, and greatly improving the optimization efficiency of the algorithm.

[0163] Then, a fitness function is set. The fitness function is an evaluation of the ability of an individual to adapt to a specific environment. According to the fitness value of an individual, its survival ability in the current population can be judged. Considering that the precision - guided ammunition configuration optimization model is an integer linear programming model, its fitness function is the optimization objective of the model. To optimize the solution within the feasible region, a penalty function is introduced in this paper to limit the search range of the solution. Thus, by using the selection operator to eliminate individuals with lower fitness function values, the genetic algorithm searches within the feasible region, and thus the global optimal solution that satisfies the model constraints can be ensured to be found.

[0164] Regarding the optimization solution of the precision - guided ammunition configuration optimization model by the genetic algorithm, a convergence analysis is also required to analyze when the genetic algorithm obtains the optimal solution of the algorithm. By statistically analyzing the data of each global iteration, a convergence graph of the genetic algorithm solution is drawn, referring to Figure 6 . AnalysisFigure 6 It can be seen that during the process of optimizing and solving by the genetic algorithm, its convergence rate continuously decreases. Analyzing the reason, it is because it is getting closer and closer to the optimal solution of the model, resulting in the continuous decrease of its convergence rate. In addition, when iterating to the 70th time, the genetic algorithm stops converging, that is, the algorithm optimal solution of the constructed algorithm model is obtained. Thus, it can be analyzed that setting the first iteration number threshold and the second iteration number threshold to 100 in the early stage is quite appropriate.

[0165] The present invention also discloses an ammunition configuration optimization system based on a multi-layer optimization strategy, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the ammunition configuration optimization method based on the multi-layer optimization strategy described in any one of the above embodiments.

[0166] Among them, the processor can adopt a central processing unit (CPU). Of course, according to the actual usage situation, other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. can also be adopted. The general-purpose processor can adopt a microprocessor or any conventional processor, etc. The present application does not make any restrictions on this.

[0167] Among them, the memory can be an internal storage unit of the computer device. For example, the hard disk or memory of the computer device, or it can also be an external storage device of the computer device. For example, the plug-in hard disk, smart media card (SMC), secure digital card (SD) or flash card (FC) etc. equipped on the computer device. And the memory can also be a combination of the internal storage unit and the external storage device of the computer device. The memory is used to store the computer program and other programs and data required by the computer device. The memory can also be used to temporarily store the data that has been output or will be output. The present application does not make any restrictions on this.

[0168] The present invention also discloses a computer-readable storage medium. The instruction is stored on the computer-readable storage medium, and is characterized in that when the instruction is executed by the processor, the processor is configured to execute the ammunition configuration optimization method based on the multi-layer optimization strategy described in any one of the above embodiments.

[0169] Among them, the computer program can be stored in a machine-readable medium. The computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some middleware form, etc. The machine-readable medium includes any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the machine-readable medium includes but is not limited to the above components.

[0170] Those of ordinary skill in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the protection scope of the present application is limited to these examples; under the concept of the present application, the technical features in the above embodiments or different embodiments can also be combined, and the steps can be implemented in any order, and there are many other variations in different aspects of one or more embodiments in the present application as above, and they are not provided in detail for the sake of brevity.

[0171] One or more embodiments of the present application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of one or more embodiments of the present application shall be included within the protection scope of the present application.

Claims

1. An ammunition configuration optimization method based on a multi-layer optimization strategy, characterized in that It includes the following steps: Obtain multiple mission objectives based on the combat mission; Match multiple target precision guided munitions according to the multiple mission objectives, and match multiple ammunition carrying platforms based on the adaptability of the target precision guided munitions; Quantify the correlation factors between multiple target precision guided munitions and multiple mission objectives to obtain a target-ammunition quantization mapping relationship matrix of multiple target precision guided munitions and multiple mission objectives; Quantify the correlation factors between multiple ammunition carrying platforms and multiple target precision guided munitions to obtain an ammunition-platform quantization mapping relationship matrix of multiple ammunition carrying platforms and multiple target precision guided munitions; Combine the target-ammunition quantization mapping relationship matrix and the ammunition-platform quantization mapping relationship matrix, and construct a two-layer optimization model for ammunition configuration with the minimization of the total ammunition consumption when loading the target precision guided munitions to complete the combat mission as the optimization objective; Solve the two-layer optimization model for ammunition configuration to obtain the optimal loading configuration plan of the target precision guided munitions.

2. The ammunition configuration optimization method based on a multi-layer optimization strategy according to claim 1, characterized in that The step of combining the target-ammunition quantization mapping relationship matrix and the ammunition-platform quantization mapping relationship matrix, and constructing a two-layer optimization model for ammunition configuration with the minimization of the total ammunition consumption when loading the target precision guided munitions to complete the combat mission as the optimization objective includes the following steps: Based on the target-ammunition quantization mapping relationship matrix, and with the minimization of the total ammunition consumption when loading the target precision guided munitions to complete the combat mission as the optimization objective, construct an upper-layer optimization model for target-ammunition configuration; Solve the upper-layer optimization model for target-ammunition configuration to obtain the ammunition quantity of the target precision guided munitions that need to be carried by the ammunition carrying platform; Combine the ammunition quantity and the ammunition-platform quantization mapping relationship matrix, and with the minimization of the total ammunition consumption when loading the target precision guided munitions to complete the combat mission as the optimization objective, construct a lower-layer optimization model for ammunition-platform configuration; Merge the upper-layer optimization model for target-ammunition configuration and the lower-layer optimization model for ammunition-platform configuration into a two-layer optimization model for ammunition configuration.

3. The ammunition configuration optimization method based on a multi-layer optimization strategy according to claim 2, wherein: The upper-layer optimization model for target-ammunition configuration is as follows: Optimization objective: Constraint conditions: Where: Min TC1 represents the optimization objective of the upper-layer optimization model of the target-ammunition configuration, m represents the set of types of mission objectives, n represents the set of types of target precision-guided ammunition, j represents the j-th type of target precision-guided ammunition in the set of ammunition types, i represents the i-th type of mission objective in the set of target types, c i represents the quantity of the i-th type of mission objective, d j represents the quantity of the target precision-guided ammunition used to complete the combat mission in the set of ammunition types, Price ij represents the unit price of the target precision-guided ammunition used to complete the combat mission, a ij represents the matrix element in the target-ammunition quantitative mapping relationship matrix, A ij represents the recommended quantity of ammunition measurement; The lower-layer optimization model for ammunition-platform configuration is as follows: Optimization objective: Constraint conditions: Where: Min TC2 represents the optimization objective of the lower-layer optimization model of the ammunition-platform configuration, p represents the set of platform types of the ammunition-carrying platforms, k represents the k-th type of ammunition-carrying platform in the set of platform types, p k represents the number of ammunition-carrying platforms in the set of platform types for carrying the target precision-guided ammunition, c j represents the number of ammunitions of the target precision-guided ammunition that need to be carried by the ammunition-carrying platform, Price jk represents the unit price of the ammunition-carrying platform for carrying the target precision-guided ammunition, b jk represents the matrix element in the ammunition-platform quantization mapping relation matrix, B jk represents the number of ammunitions that can be successfully launched when the j-th type of target precision-guided ammunition is launched using the k-th type of ammunition-carrying platform.

4. The ammunition configuration optimization method based on a multi-layer optimization strategy according to claim 3, wherein: The two-layer optimization model for ammunition configuration is as follows: Optimization objective: Constraint conditions:

5. The ammunition configuration optimization method based on a multi-layer optimization strategy according to claim 4, characterized in that The step of solving the two-layer optimization model for ammunition configuration to obtain the optimal loading configuration plan of the target precision guided munitions includes the following steps: Use a stage optimization method based on an exact algorithm to solve the two-layer optimization model for ammunition configuration to obtain a first loading configuration plan of the target precision guided munitions; Use a generalized distance minimization method based on an exact algorithm to solve the two-layer optimization model for ammunition configuration to obtain a second loading configuration plan of the target precision guided munitions; Take the solution with the minimum total ammunition consumption among the first loading configuration solution and the second loading configuration solution as the optimal loading configuration solution.

6. The ammunition configuration optimization method based on a multi-layer optimization strategy according to claim 5, characterized in that The steps of using the stage optimization method based on the exact algorithm to solve the double-layer optimization model of ammunition configuration and obtaining the first loading configuration solution of the target precision-guided ammunition are as follows: Use the branch and bound method in the exact algorithm to solve the upper-layer optimization model of target-ammunition configuration in the double-layer optimization model of ammunition configuration, and obtain the quantity of the target precision-guided ammunition that needs to be carried by the ammunition carrying platform. Substitute the quantity of the target precision-guided ammunition that needs to be carried by the ammunition carrying platform into the lower-layer optimization model of ammunition-platform configuration in the double-layer optimization model of ammunition configuration. Use the branch and bound method to solve the lower-layer optimization model of ammunition-platform configuration, and obtain the first loading configuration solution of the target precision-guided ammunition.

7. The ammunition configuration optimization method based on a multi-layer optimization strategy according to claim 5, characterized in that The steps of using the generalized distance minimization method based on the exact algorithm to solve the double-layer optimization model of ammunition configuration and obtaining the second loading configuration solution of the target precision-guided ammunition are as follows: Adopt the generalized distance weighting method to assign the same weight to the objective functions of the upper-layer optimization model of target-ammunition configuration and the lower-layer optimization model of ammunition-platform configuration. Integrate the upper-layer optimization model of target-ammunition configuration and the lower-layer optimization model of ammunition-platform configuration based on the assignment of the weight to obtain an optimized integrated model, and the optimized integrated model is as follows: Optimization objective: Constraint conditions: Use the branch and bound method in the exact algorithm to solve the optimized integrated model, and obtain the second loading configuration solution of the target precision-guided ammunition.

8. The ammunition configuration optimization method based on a multi-layer optimization strategy according to claim 4, characterized in that The steps of solving the double-layer optimization model of ammunition configuration and obtaining the optimal loading configuration solution of the target precision-guided ammunition are as follows: Define the upper-layer chromosome encoding based on the optimization objective of the upper-layer optimization model of target-ammunition configuration, and define the lower-layer chromosome encoding based on the lower-layer optimization model of ammunition-platform configuration. Construct an upper-layer initial population that satisfies the constraint conditions in the upper-layer optimization model of target-ammunition configuration according to the upper-layer chromosome encoding by using the greedy algorithm, and take the upper-layer initial population as the target population. Execute the double-layer loop nested genetic algorithm by combining the target population and the lower-layer chromosome encoding until the number of iterations of the double-layer loop nested genetic algorithm reaches a preset first iteration number threshold, and obtain the optimal upper-layer individual and the optimal lower-layer individual output by the final iteration. Generate the optimal loading configuration solution of the target precision-guided ammunition by combining the optimal upper-layer individual and the optimal lower-layer individual output by the final iteration. The double-layer loop nested genetic algorithm specifically includes the following steps: Set the first fitness function values of all individuals in the target population based on the optimization objective of the upper-layer optimization model of target-ammunition configuration. Select upper-layer parent individuals and upper-layer maternal individuals from the target population, and perform crossover and mutation operations on the upper-layer parent individuals and the upper-layer maternal individuals to obtain the optimal upper-layer individual in the target population and the optimal first fitness function value of the optimal upper-layer individual. Combine the optimal upper-layer individual and the lower-layer chromosome encoding to construct a lower-layer initial population that satisfies the constraint conditions in the lower-layer optimization model of the ammunition-platform configuration, and use the lower-layer initial population as the sub-goal population; Execute a single-loop genetic algorithm based on the sub-goal population until the number of iterations of the single-loop genetic algorithm reaches a preset second iteration number threshold, and output the optimal second fitness function value of the optimal lower-layer individual in the sub-goal population; Take the sum of the optimal first fitness function value and the optimal second fitness function value as the global optimal fitness function value; Re-select the optimal upper-layer individual in the target population based on the global optimal fitness function value, and form the target population of the next generation with the re-selected optimal upper-layer individuals; The single-loop genetic algorithm specifically includes the following steps: Set the second fitness function values of all individuals in the sub-goal population based on the optimization goal of the lower-layer optimization model of the ammunition-platform configuration; Select lower-layer parent individuals and lower-layer mother individuals from the sub-goal population, and perform crossover and mutation operations on the lower-layer parent individuals and the lower-layer mother individuals to obtain the optimal lower-layer individual of the current generation, and form the sub-goal population of the next generation with the optimal lower-layer individuals of the current generation.

9. An ammunition configuration optimization system based on a multi-layer optimization strategy, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the ammunition configuration optimization method based on a multi-layer optimization strategy according to any one of claims 1 to 8.

10. A computer-readable storage medium having instructions stored thereon, characterized in that, When the instruction is executed by the processor, the processor is configured to execute the ammunition configuration optimization method based on a multi-layer optimization strategy according to any one of claims 1 to 8.

Images