An intelligent system for matching ammunition with targets

Abstract

The present invention relates to an intelligent system for matching ammunition with targets, belonging to the technical field of combat targets. The present invention can allocate ammunition and targets under the constraints of maximum damage effectiveness and minimum ammunition value, and is a joint fire strike operation on multiple combat targets, featuring good reliability and high accuracy, and meeting the requirements of war complexity, accuracy and real-time performance.

Description

Technical Field

[0001] The present invention belongs to the technical field of combat targets, and particularly relates to an intelligent system for matching ammunition with targets. Background Art

[0002] It is very difficult to solve the problem of matching ammunition with targets. First of all, basically all the matching of ammunition with targets in battles is dynamic. Affected by the changeable factors on the battlefield, the types and quantities of available ammunition and targets are not fixed. More importantly, the striking efficiency of ammunition against targets also changes constantly, increasing the uncertainty of the problem of matching ammunition with targets that is difficult to estimate. Secondly, there are various connections among various types of ammunition and various types of targets, forming a complex decision-making system. Like combat effectiveness, some connections are time-varying, resulting in many connections being difficult to accurately quantify, and it is very difficult to make a decision on the optimal solution. Moreover, the requirements of combat missions are qualitative and difficult to quantify. Especially when the requirements of combat missions are not very clear or there are too many combat missions, how to meet the requirements of combat missions in the process of solving the problem of matching ammunition with targets is a difficult problem. Also, the core of the problem of matching ammunition with targets is to solve a large-scale non-linear integer programming model, which is proved to be an NP-hard combinatorial optimization problem, and there is still a lot of work to do on how to design a reasonable algorithm with high efficiency for solving it.

[0003] For a long time, the problem of matching ammunition with targets has been a research hotspot. Especially in terms of algorithms, a large number of solving methods have been proposed for different firepower distribution models to improve the solving speed and accuracy of the model, so as to meet the requirements of the complexity, accuracy and real-time nature of war. Summary of the Invention

[0004] (1) Technical Problems to be Solved

[0005] The technical problem to be solved by the present invention is: how to design an intelligent matching system for ammunition with targets with good reliability and high accuracy.

[0006] (2) Technical Solutions

[0007] To solve the above technical problems, the present invention provides an intelligent system for matching ammunition with targets, which is a system for realizing the intelligent matching of ammunition with targets, and includes:

[0008] A target value evaluation model establishment module, which is used to establish a target value evaluation model based on the principal component analysis method;

[0009] A target threat degree evaluation model establishment module, which is used to establish a target threat degree evaluation model;

[0010] An ammunition value evaluation model establishment module, which is used to establish an ammunition value evaluation model;

[0011] A projectile-target matching model building module, configured to build a projectile-target matching model based on the target value evaluation model, the target threat level evaluation model, and the ammunition value evaluation model;

[0012] A model solving module, configured to solve the projectile-target matching model using a genetic algorithm to obtain a projectile-target matching result.

[0013] Preferably, the target value evaluation model building module is specifically configured to evaluate the value of a target through a principal component analysis method according to the index data describing the target.

[0014] Preferably, the target value evaluation model building module builds a target threat level evaluation model in the following manner:

[0015] S11: Assume there are n targets, and each target is described by p indicators, and construct an index data matrix Z:

[0016]

[0017] S12: Use the Z-score method to perform a standardization transformation on the indicators;

[0018] S13: Calculate the correlation matrix R of the index data matrix Z:

[0019]

[0020] Where:

[0021]

[0022] S14: Solve for the p eigenvalues λ g , g = 1, 2,.., p, and each eigenvalue corresponds to an eigenvector (I g1 , I g2 , …, I gp ), and convert the standardized indicators into principal components:

[0023] F g = I g1 z1 + I 92 z2 + … + I gp z p

[0024] In the formula, F g is the gth principal component, and z p is the pth indicator of the target;

[0025] S15: Select q principal components such that the cumulative contribution rate reaches more than 85%:

[0026]

[0027] S16: Perform a weighted sum of the q principal components to obtain the final evaluation value of the target:

[0028]

[0029] Preferably, the target threat degree evaluation model establishment module is specifically configured to describe the threat degree by using the speed and distance of the target.

[0030] Preferably, the target threat degree evaluation model establishment module establishes the target threat degree evaluation model in the following manner:

[0031] S21: Let the speed of the target be v and the maximum speed be v max , then the speed threat degree of the target is:

[0032] w v = v / v max

[0033] S22: Let the distance between the target and our weapon be D, the maximum attack distance of our weapon be D w , the maximum attack distance of the target be D d , then the distance threat degree of the target is:

[0034]

[0035] Wherein, the weapon is the ammunition;

[0036] S23: The total threat degree of the target is expressed as:

[0037] W = (w v + M d ) / 2

[0038] Preferably, the ammunition value evaluation model establishment module is specifically configured to calculate the total ammunition value through the quantity matrix and value matrix of the ammunition.

[0039] Preferably, the ammunition value evaluation model establishment module establishes the ammunition value evaluation model in the following manner:

[0040] S31: Suppose there are n targets and m types of ammunition. The quantity matrix of each type of ammunition is expressed as C = [c1, c2,..., c m , and the value matrix is expressed as V = [v1, v2,..., v m , then the weapon - target allocation plan is expressed as:

[0041]

[0042] Wherein, x ij represents the quantity of the jth type of ammunition used for the ith target, i = 1, 2,..., n, j = 1, 2,..., m;

[0043] S32: The total value of all ammunition used is:

[0044]

[0045] v j is the value of the j-th type of ammunition.

[0046] Preferably, the warhead-target matching model establishment module is specifically configured to construct an objective function with the maximum damage efficiency and the minimum ammunition value as the objectives.

[0047] Preferably, the warhead-target matching model establishment module is specifically configured to establish a warhead-target matching model in the following manner:

[0048] S41: The kill probability of the j-th type of ammunition against the i-th target is e ij , according to the allocation plan X nm , the kill probability of using a certain number of the j-th type of ammunition to attack the i-th target is:

[0049]

[0050] Then the damage probability p i of all m types of ammunition against target i is:

[0051]

[0052] Then the damage efficiency is:

[0053]

[0054] where ω i is the total threat level of the i-th target calculated using step S2, and F i is the final evaluation value of the i-th target calculated using step S1;

[0055] S43: Establish a constrained optimization problem:

[0056]

[0057]

[0058]

[0059] Preferably, the model solving module is specifically configured to solve the objective function using the NAGA-II algorithm, including:

[0060] S51: Adopt decimal encoding, and each chromosome consists of weapon numbers arranged in the order of targets, representing a possible allocation plan;

[0061] S52: Initialize the parental population according to the target quantity and ammunition type;

[0062] S53: Perform fast non-dominated sorting on the parental population to obtain the Pareto ranks of all individuals, and calculate the crowding degree simultaneously;

[0063] S55: Generate the offspring population through crossover and mutation;

[0064] S56: Mix the parental population and the offspring population, and determine the Pareto ranks and crowding degrees of the individuals in the mixed population;

[0065] S57: Adopt the elitist strategy to select excellent individuals from the mixed population to generate a new parental population; the excellence of the mixed population is determined according to the preset index;

[0066] S58: Repeat steps S55 - S57 until the set number of evolutionary generations is reached, and finally obtain the ammunition-target matching result.

[0067] (III) Beneficial Effects

[0068] The present invention can allocate ammunition and targets with the maximum damage effectiveness and the minimum ammunition value as the constraint conditions, and is a joint fire strike operation on multiple combat targets, featuring good reliability and high accuracy, and meeting the requirements of the complexity, accuracy, and real-time nature of war. Description of the Drawings

[0069] Figure 1 It is the schematic diagram of the system implementation of the present invention. Detailed Embodiment

[0070] To make the objectives, content, and advantages of the present invention clearer, the following further describes in detail the specific embodiments of the present invention with reference to the drawings and embodiments.

[0071] As Figure 1 shown, a system for intelligent matching of ammunition and targets provided by the present invention includes:

[0072] A target value evaluation model establishment module for establishing a target value evaluation model based on the principal component analysis method;

[0073] A target threat degree evaluation model establishment module for establishing a target threat degree evaluation model;

[0074] An ammunition value evaluation model establishment module for establishing an ammunition value evaluation model;

[0075] An ammunition-target matching model establishment module for constructing an ammunition-target matching model based on the target value evaluation model, the target threat degree evaluation model, and the ammunition value evaluation model;

[0076] The model solution module is used to solve the projectile-target matching model using an improved genetic algorithm to obtain the projectile-target matching result.

[0077] Furthermore, the target value evaluation model establishment module is specifically used to evaluate the value of the target according to the index data describing the target through the principal component analysis method, specifically including:

[0078] S11: Suppose there are n targets, each target is described by p indicators, and an indicator data matrix Z is constructed.

[0079]

[0080] S12: Use the Z-score method to perform a standardized transformation on the indicators.

[0081] S13: Calculate the correlation matrix R of the indicator data matrix Z:

[0082]

[0083] Where:

[0084]

[0085] S14: Solve the p eigenvalues λ g (g = 1, 2,.., p), and each eigenvalue corresponds to an eigenvector (I g1 , I g2 , …, I gp ), and convert the standardized indicators into principal components:

[0086] F g = I g1 z1 + I 92 z2 + … + I gp z p

[0087] In the formula, F g is the gth principal component, and z p is the pth indicator of the target.

[0088] S15: Select q principal components so that the cumulative contribution rate reaches more than 85%:

[0089]

[0090] S16: Perform a weighted sum on the q principal components to obtain the final evaluation value of the target:

[0091]

[0092] Furthermore, the target threat level assessment model establishment module is specifically configured to describe the threat level by using the speed and distance of the target, specifically including:

[0093] S21: Let the speed of the target be v, and the maximum speed be v max , then the speed threat degree of the target is:

[0094] w v = v / v max

[0095] S22: Let the distance between the target and our weapon (i.e., ammunition) be D, the maximum attack distance of our weapon be D w , and the maximum attack distance of the target be D d , then the distance threat degree of the target is:

[0096]

[0097] S23: The total threat level of the target is expressed as:

[0098] W = (w v + w d ) / 2.

[0099] Furthermore, the ammunition value assessment model establishment module is specifically configured to calculate the total ammunition value through the quantity matrix and value matrix of the ammunition, specifically including:

[0100] S31: Suppose there are n targets and m types of ammunition. The quantity matrix of each type of ammunition is expressed as C = [c1, c2,..., c m , and the value matrix is expressed as V = [v1, v2,..., v m , then the weapon - target allocation plan is expressed as:

[0101]

[0102] Among them, x ij represents the quantity of the j - th type of ammunition used for the i - th target, i = 1, 2,..., n, j = 1, 2,..., m;

[0103] S32: The total value of all used ammunition is:

[0104]

[0105] v j is the value of the j - th type of ammunition.

[0106] Furthermore, the projectile - target matching model establishment module is specifically configured to construct an objective function with the maximum damage effectiveness and the minimum ammunition value as the objectives, specifically including:

[0107] S41: The kill probability of the j-th type of ammunition against the i-th target is e ij , according to the allocation scheme X nm , the kill probability of using a certain number of the j-th type of ammunition to attack the i-th target is:

[0108]

[0109] Then the damage probability p of all m types of ammunition against target i i is:

[0110]

[0111] Then the damage effectiveness is:

[0112]

[0113] Among them, ω i is the total threat level of the i-th target calculated using step S2, and F i is the final evaluation value of the i-th target calculated using step S1;

[0114] S43: Establish a constrained optimization problem:

[0115]

[0116]

[0117]

[0118] Furthermore, the model solving module is specifically used to solve the objective function using the NAGA-II algorithm, including:

[0119] S51: Adopt decimal coding. Each chromosome consists of weapon numbers arranged in the order of targets, representing a possible allocation scheme;

[0120] S52: Initialize the parental population according to the number of targets and types of ammunition;

[0121] S53: Perform fast non-dominated sorting on the parental population to obtain the Pareto ranks of all individuals, and calculate the crowding degree at the same time;

[0122] S55: Cross and mutate to obtain the offspring population;

[0123] S56: Mix the parental population and the offspring population, and determine the Pareto ranks and crowding degrees of the individuals in the mixed population;

[0124] S57: Adopt the elite strategy to select excellent individuals from the mixed population to generate a new parental population;

[0125] S58: Repeat steps S55 - S57 until the set number of evolutionary generations is reached, and finally obtain the missile - target matching result.

[0126] The above - mentioned is only the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the technical principle of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent system for matching ammunition with a target, characterized in that, The system is a system for realizing intelligent matching of ammunition and targets, including: A target value evaluation model establishment module, which is used to establish a target value evaluation model based on the principal component analysis method; A target threat degree evaluation model establishment module, which is used to establish a target threat degree evaluation model; An ammunition value evaluation model establishment module, which is used to establish an ammunition value evaluation model; A projectile-target matching model establishment module, which is used to construct a projectile-target matching model based on the target value evaluation model, the target threat degree evaluation model, and the ammunition value evaluation model; A model solving module, which is used to solve the projectile-target matching model using the genetic algorithm to obtain a projectile-target matching result; The projectile-target matching model establishment module is specifically used to establish a projectile-target matching model in the following manner: S41: The kill probability of the j-th type of ammunition against the i-th target is e ij , according to the allocation plan X nm , the kill probability of using a certain number of the j-th type of ammunition to attack the i-th target is: Then the damage probability p of all m types of ammunition against target i i is as follows: Then the damage effectiveness is: where ω i is the total threat level of the i-th target calculated using step S2, and F i is the final evaluation value of the i-th target calculated using step S1; S42: Establish a constrained optimization problem:

2. The system according to claim 1, wherein The target value evaluation model establishment module is specifically used to evaluate the value of the target through the principal component analysis method according to the index data describing the target.

3. The system according to claim 2, wherein The target threat degree evaluation model establishment module is specifically used to establish a target threat degree evaluation model in the following manner: S11: Suppose there are n targets, and each target is described by p items of indicators, and construct an index data matrix Z: S12: Use the Z-score method to perform a standardized transformation on the indicators; S13: Calculate the correlation matrix R of the index data matrix Z: Where: S14: Solve for the p eigenvalues λ of the correlation matrix R g , g = 1, 2,.., p, and each eigenvalue corresponds to an eigenvector (I g1 , I g2 , …, I gp ), and convert the standardized indicators into principal components: F g = I g1 z1 + I g2 z2 + … + I gp z p where F g is the g-th principal component, and z p is the p-th index of the target; S15: Select q principal components so that the cumulative contribution rate reaches more than 85%; S16: Perform a weighted sum on the q principal components to obtain the final evaluation value of the target:

4. The system according to claim 3, wherein The target threat degree evaluation model establishment module is specifically used to describe the threat degree by using the speed and distance of the target.

5. The system according to claim 4, wherein The target threat degree evaluation model establishment module is specifically used to establish a target threat degree evaluation model in the following manner: S21: Let the speed of the target be v and the maximum speed be v max , then the speed threat level of the target is: w v = v / v max S22: Let the distance between the target and our weapon be D, and the maximum attack distance of our weapon be D w , and the maximum attack distance of the target be D d , then the distance threat level of the target is as follows: Among them, the weapon is the ammunition; S23: The total threat degree of the target is expressed as: W = (w v + w d ) / 2。 6. The system according to claim 5, wherein The ammunition value evaluation model establishment module is specifically used to calculate the total ammunition value through the ammunition quantity matrix and the value matrix.

7. The system according to claim 6, wherein The ammunition value evaluation model establishment module establishes an ammunition value evaluation model in the following manner: S31: There are n targets and m types of ammunition. The quantity matrix of each type of ammunition is represented as C = [c1, c2, …, c m , and the value matrix is represented as V = [v1, v2, …, v m . Then the weapon-target assignment plan is represented as: where x ij represents the quantity of the j-th type of ammunition used by the i-th target, where i = 1, 2, …, n and j = 1, 2, …, m; S32: The total value of all used ammunition is: v j is the value of the j-th type of ammunition.

8. The system according to claim 7, wherein The projectile-target matching model establishment module is specifically used to construct an objective function with the maximum damage effectiveness and the minimum ammunition value as the goals.

9. The system according to claim 8, wherein The model solving module is specifically used to solve the objective function using the NAGA-II algorithm, including: S51: Adopt decimal coding, and each chromosome consists of weapon numbers arranged in the order of targets, representing a possible allocation scheme; S52: Initialize the parental population according to the number of targets and the types of ammunition; S53: Perform a fast non-dominated sorting on the parental population to obtain the Pareto ranks of all individuals, and calculate the crowding degree at the same time; S55: Cross and mutate to obtain the offspring population; S56: Mix the parental population and the offspring population, and determine the Pareto ranks and crowding degrees of the individuals in the mixed population; S57: Adopt an elite strategy to select excellent individuals from the mixed population to generate a new parental population; the excellence of the mixed population is judged according to a preset index; S58: Repeat steps S55 to S57 until the set number of evolution generations is reached, and finally obtain the projectile-target matching result.

Images