Target attack task allocation method with maximum target damage value

Abstract

The invention discloses a target attack task allocation method for maximizing a target damage value. The method comprises the following steps: S1, constructing a maximum attack damage value model; and S2, solving the maximum attack damage value model through an SA-PSO-TS optimization algorithm to realize target attack task allocation. By adopting the technical scheme of the invention, the target attack task distribution with the maximum target damage value can be realized.

Description

Technical Field

[0001] The invention belongs to the field of information processing technology, and in particular relates to a method for allocating target strike tasks with maximum target damage value. Background Art

[0002] In today's context of rapid development of information and network warfare, the complexity of the modern battlefield has increased significantly. Combat units not only face a changing tactical environment, but also have to deal with the rapid advancement of enemy technology and dynamic adjustments in tactics. All of this has made traditional combat theories and methods gradually appear inadequate. The armies of various countries must constantly adapt to changes in new technologies and changes in tactical requirements in the serialization, intelligence and systematization of unmanned weapon systems. With the rapid development of science and technology, new battlefield situations such as unmanned systems, network information technology and special operations have gradually emerged, greatly promoting the urgent need for the research and development of advanced weapons and ammunition, especially the rise of new weapon systems such as cruise missiles and low-cost combat drones.

[0003] The concept of cruise missiles was first proposed at the end of the last century. It organically combines drone technology with cruise missile technology to become an intelligent ammunition. This innovative weapon system has quickly attracted the attention of military experts from various countries with its unique functions and characteristics. Compared with traditional missiles, cruise missiles have the ability to stay in the air for a long time, can conduct reconnaissance and surveillance in the target area, and flexibly choose the best time to strike. This enables cruise missiles to not only perform a variety of combat missions such as reconnaissance and positioning, battlefield blockade, precision strikes and damage assessment, but also play multiple roles on the battlefield, such as wireless relay, target indication and air warning. For example, the US "Switchblade" and Israel's "Harop" cruise missiles have shown their unique combat advantages on the modern battlefield and can achieve efficient strikes at low cost.

[0004] In recent years, with the gradual maturity of technology, cruise missiles have become an indispensable combat unit in the modern battlefield. When facing a multi-target environment, how to reasonably and efficiently allocate and use cruise missiles has become a key issue that needs to be urgently resolved in combat command. This issue not only involves the strike capability of a single cruise missile, but also the coordinated combat effectiveness of the entire combat system.

[0005] The task allocation of cruise missiles aims to improve their utilization and strike effect through scientific and reasonable strategies. Its primary significance lies in improving the combat effectiveness of the entire battlefield. The modern battlefield environment is ever-changing, and the enemy's targets and threats change dynamically. Traditional task allocation often cannot quickly respond to such dynamic changes. For example, Ahner DK et al. used dynamic programming to allocate missile strike firepower in the paper "Optimal multi-stage allocation of weapons to targets using adaptive dynamic programming", and proved the optimality of dynamic programming for firepower allocation decisions. However, when facing medium and large-scale problems, the solution efficiency is too low and cannot cope with dynamic requirements. Wang Yongchun et al. used expert experience to construct a dynamic allocation decision judgment tree in the paper "Research on Firepower Allocation Model of Surface Ships and Aerial Targets", which can obtain a better allocation solution on a small scale, but in medium and large-scale and more complex scenarios, the allocation rules are difficult to accurately extract, and the applicability is greatly reduced. The traditional firepower allocation model based on human experience has problems such as limited applicability, poor objectivity and rationality of decision-making effects, and the efficiency limitations of dynamic programming are very large. Therefore, many scholars have begun to explore the use of heuristic search algorithms for firepower allocation decisions. For example, the invention patent "Anti-UAV firepower deployment method in open areas based on improved PSO algorithm" (publication number: CN111581878A) introduces in detail a firepower deployment solution for anti-UAV problems in open areas. Although this method improves the global search capability of the model by introducing a perturbation structure, and improves the defect of the traditional PSO algorithm that is prone to fall into local optimal solutions to a certain extent, it may still face problems of insufficient solution efficiency and adaptability in complex dynamic scenes. In the invention patent "Firepower allocation method based on ant colony algorithm" (publication number: CN106779210A), a firepower allocation solution based on an improved ant colony algorithm is introduced in detail. Although this method can effectively improve the decision-making efficiency and solution quality of firepower allocation to a certain extent, the classic ant colony algorithm still has problems such as slow convergence speed and easy to fall into local optimality. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide a method for allocating target strike tasks with the maximum target damage value.

[0007] To achieve the above object, the present invention adopts the following technical solution:

[0008] A method for allocating strike tasks for targets with the greatest target damage value, comprising:

[0009] Step S1, constructing a maximum strike damage value model;

[0010] Step S2: Solve the maximum strike damage value model through the SA-PSO-TS optimization algorithm to achieve target strike task allocation.

[0011] As a preferred embodiment, the maximum strike damage value model is:

[0012]

[0013] Among them, the firepower allocation decision variable matrix is ​​[x ij ] N×M , the matrix has N rows and M columns, N is the number of cruise missiles, M is the number of targets to be hit, if the i-th cruise missile hits the j-th target, then x ij =1, otherwise x ij =0, p ij is the damage probability of the i-th XFD hitting the j-th target in one attack, dist ij is the distance between the i-th cruise missile and the j-th target, v j is the value of the jth target, and max_distace is the maximum flight distance limit of XFD.

[0014] Preferably, in step S2, firstly, the value and threat level of the target are obtained, and the algorithm parameters are initialized; secondly, the particle swarm is initialized, and a set of solutions is randomly generated for each particle; then the initial solution is sent to the particle swarm + simulated annealing + taboo search algorithm for optimization, firstly, an optimization is performed according to the initialized particle swarm, and the optimal solution in the particle swarm is taken out, and the optimal solution is used as the initial solution of the simulated annealing algorithm, and then the index is calculated according to the initial solution, and several neighborhood solutions are randomly exchanged. If the generated new solution meets the constraint conditions, the solution is accepted and included in the taboo table. If the calculated index is better than the original solution or meets the Metropolis criterion, the existing solution is replaced. If the generated new solution does not meet the constraint conditions, the solution is continued to be generated until the generated solution meets the constraint conditions. If the calculated new solution index is better than the historical best index, the optimal solution is updated. Then the optimal solution generated by this round of iteration is stored as the optimal solution of the particle swarm, and then the next iteration is performed until termination. The optimization process ends when the number of iterations ends or the temperature is less than the minimum temperature.

[0015] The present invention integrates the advantages of particle swarm optimization (PSO), simulated annealing (SA) and taboo search (TS), and effectively improves the problems of insufficient global search ability, easy to fall into local optimum, slow convergence speed of ant colony algorithm, and insufficient adaptability to complex dynamic scenes in traditional particle swarm methods. The algorithm uses PSO to quickly explore the whole world to obtain the initial solution, combines the random perturbation of simulated annealing and the Metropolis criterion to jump out of the local optimum, and avoids repeated search and exploration of potential space through taboo search, which enhances the particle swarm's ability to find the best solution in the global scope, and comprehensively improves the quality of solution and optimization efficiency. At the same time, the algorithm effectively improves the adaptability and processing ability of constraints in complex dynamic scenes through dynamic temperature control and real-time verification of constraints, and provides an efficient and reliable optimization solution for problems such as firepower allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0017] Figure 1 This is a flow chart of a target strike task allocation method according to an embodiment of the present invention;

[0018] Figure 2 Flowchart of SA-PSO-TS optimization algorithm;

[0019] Figure 3 Iterate the mission process for maximum strike damage value;

[0020] Figure 4 Assign results to the firepower. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0023] Embodiment 1:

[0024] Firepower allocation is to analyze the importance of the target and evaluate the threat level of the target to the defender based on the key situation information of the target. On this basis, according to the firepower resources of the attacker, the cruise missile-target firepower allocation plan is optimized under specific attack criteria, and the plan results are distributed to the corresponding cruise missile launch system. After determining the target to be hit, the cruise missile launch system calculates and binds the launch parameters, and the cruise missile achieves precise strikes on the target under the control of the guidance program. Therefore, the effectiveness of the strike on the enemy camp depends largely on the results of the firepower allocation plan.

[0025] However, due to the complex and ever-changing battlefield situation, in order to meet different strategic goals and tactical requirements, the embodiment of the present invention combines distance and damage value to establish a mathematical model that combines maximum damage value and shortest distance. The shortest distance combat plan maintains the initiative on the battlefield by quickly completing combat missions, reducing enemy reaction time and our exposure risk; the maximum strike damage value plan focuses on maximizing the destructive effect and weakening the enemy's combat capability by accurately striking key enemy facilities under limited resources. Combining the two can make the allocation result take into account both the path and the damage value to achieve the desired strike effect.

[0026] like Figure 1 As shown, an embodiment of the present invention provides a method for allocating a target strike task with the maximum target damage value, comprising:

[0027] Step S1, constructing a maximum strike damage value model;

[0028] Step S2: Solve the maximum strike damage value model based on the SA-PSO-TS optimization algorithm to achieve target strike task allocation.

[0029] As an implementation method of the present invention, in step S1, the maximum strike damage value model is expected to maximize the damage value of the enemy target group to minimize the combat effectiveness of the enemy and minimize the distance that the XFD strikes the target. In this combat mode, the firepower allocation decision variable matrix is ​​defined as [x ij ] N×M , the matrix has N rows and M columns, N is the number of cruise missiles, M is the number of targets to be hit, if the i-th cruise missile hits the j-th target, then x ij =1, otherwise x ij =0. ij is the damage probability of the i-th XFD hitting the j-th target in one attack, dist ij is the distance between the i-th cruise missile and the j-th target, v j is the value of the jth target, max_distace is the maximum flight distance limit of XFD, then,

[0030]

[0031] As an implementation method of an embodiment of the present invention, in step S2, the simulated annealing algorithm (SA) is a random optimization algorithm based on the principles of thermodynamics, which is inspired by the solid annealing process. By gradually reducing the system temperature, the simulated annealing algorithm performs a random search in the solution space to achieve the global optimal solution. Particle swarm optimization (PSO) is an optimization algorithm based on swarm intelligence, proposed by Kennedy and Eberhart in 1995. PSO simulates the foraging behavior of a flock of birds, and achieves the optimal solution through the collaboration of individuals in the group; the algorithm principle is: PSO consists of a group of individuals called particles, each particle represents a potential solution, and the particle updates its position and velocity in the solution space according to its own experience and group experience. Taboo search (TS) is a heuristic algorithm for solving optimization problems, proposed by Glover in 1986. TS uses a taboo table to prevent the search from returning to a solution that has been visited, thereby jumping out of the local optimum.

[0032] Furthermore, the problem of firepower allocation is an important part of multi-missile coordinated operations. When multiple missiles attack multiple targets, they must be reasonably allocated to multiple targets to maximize the attack efficiency. Firepower allocation is an optimization NP problem, and the size of its solution space grows exponentially with the increase of the problem scale. Therefore, in the embodiment of the present invention, an improved particle swarm algorithm, namely, SA-PSO-TS optimization algorithm, is used to optimize firepower allocation. The SA algorithm is introduced into the particle swarm algorithm to accept suboptimal solutions with a certain probability during the optimization process, thereby overcoming the problem that the typical PSO algorithm is prone to "premature maturity". However, since the simulated annealing algorithm has randomness in the process of generating new solutions, it may be repeated with the previous solution, so the taboo search idea (TS) is added to the algorithm. The optimization result of PSO is used as the initial population of the simulated annealing algorithm. After iterative optimization of the simulated annealing algorithm, a better PSO particle is explored in the vicinity of the original particle, and a taboo table is added in the iterative process of the simulated annealing algorithm to avoid circuitous search and enhance the local search ability of PSO, thereby improving the global convergence. Its specific steps can be summarized as follows:

[0033] (1) Initialize algorithm parameters and initialize particle population;

[0034] (2) Update particles, check the legitimacy of particle encoding, and record local and global optimal particles;

[0035] (3) Further apply the simulated annealing algorithm to generate new particles based on the particles updated in the previous step, and check whether the constraints are met and whether the generated new solution is in the taboo table. If not, continue to generate new solutions based on the solutions generated by the particle swarm in the simulated annealing part until they are met, and then determine whether to accept the new particles generated this time, and complete the iterative update of the local and global optimal particles at the same time;

[0036] (4) Steps (2) and (3) are continuously repeated until the algorithm termination condition is met, the optimal fitness value is output, and the optimal firepower allocation plan is decoded.

[0037] Further, if Figure 2 As shown in the figure, the task of solving the maximum strike damage value is as follows: according to the initial battlefield situation, obtain the target value v j , the cruise missile's ability to strike various targets ij 、The distance between the cruise missile and the target ij Then initialize the number of particle swarms, and then initialize an initial solution for each particle to ensure that the initial solution of each particle meets the constraints. Then select the global optimal initial solution as the initial solution of simulated annealing based on the initial particle swarm, and obtain the value v of each cruise missile to hit the target based on the initial solution. j , the strike capability of cruise missile i against target j p ij 、The distance between cruise missile i and target j is dist ij， The initial allocation scheme is sent to the maximum damage value model, the damage value of the initial allocation scheme is calculated, and the records are saved. Then, several neighborhoods of the solution are randomly exchanged to generate a new solution. If the new solution meets the constraints and is not in the taboo table, the solution is stored in the taboo table. The new solution is sent to the maximum damage value mathematical model to calculate the damage value of the new solution. If the damage value calculated by the new solution is greater than the damage value of the initial solution or the damage value of the new solution is less than the damage value of the initial solution and satisfies the Metropolis criterion, the new solution becomes the initial solution and the optimal solution, and the temperature is updated. Until the temperature is lower than the initial set temperature or the number of iterations is reached, the simulated annealing is exited. Then the optimal solution obtained by simulated annealing is marked as the global optimal solution, and the solution of each particle is updated according to the global optimal solution. If the updated solution does not meet the encoding format of the allocation scheme, it is rounded and the allocation range is limited to ensure the rationality of the encoding. Then the optimal solution is selected according to the update of the particle group and sent to the simulated annealing, and this is repeated until the outermost iteration number is reached. The resulting firepower allocation plan can achieve maximum damage to the target.

[0038] The parameter settings of the SA-PSO-TS optimization algorithm are shown in Table 1, including key parameters such as population size, number of iterations, initial temperature, and length of the taboo table.

[0039] Table 1

[0040]

[0041] After testing 13 cruise missiles against 6 targets, the optimization process and firepower allocation scheme for this case were obtained; the iterative process and allocation results are shown in Figure 3 , 4 shown.

[0042] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for allocating strike tasks to targets with the greatest target damage value, characterized in that: include: Step S1, constructing a maximum strike damage value model; Step S2: Solve the maximum strike damage value model through the SA-PSO-TS optimization algorithm to achieve target strike task allocation.

2. The method for allocating target strike tasks with the greatest target damage value as claimed in claim 1, characterized in that: The maximum damage value model is: Among them, the firepower allocation decision variable matrix is ​​[x ij ] N×M , the matrix has N rows and M columns, N is the number of cruise missiles, M is the number of targets to be hit, if the i-th cruise missile hits the j-th target, then x ij =1, otherwise x ij =0, p ij is the damage probability of the i-th XFD hitting the j-th target in one attack, dist ij is the distance between the i-th cruise missile and the j-th target, v j is the value of the jth target, and max_distace is the maximum flight distance limit of XFD.

3. The method for allocating target strike tasks with the greatest target damage value as claimed in claim 2, characterized in that: In step S2, firstly, the value of the target, the threat level and the distance matrix between the cruise missile and the target are obtained, and the algorithm parameters are initialized; secondly, the particle swarm is initialized, and a set of solutions is randomly generated for each particle; then the initial solution is sent to the particle swarm + simulated annealing + taboo search algorithm for optimization. First, an optimization is performed according to the initialized particle swarm, and the optimal solution in the particle swarm is taken out, and the optimal solution is used as the initial solution of the simulated annealing algorithm. Then, the index is calculated according to the initial solution, and several neighborhood solutions are randomly exchanged. If the generated new solution meets the constraint conditions and the new solution is not in the taboo table, the solution is accepted and included in the taboo table. If the calculated index is better than the original solution or meets the Metropolis criterion, the existing solution is replaced. If the generated new solution does not meet the constraint conditions, the solution is continued to be generated until the generated solution meets the constraint conditions. If the calculated new solution index is better than the historical best index, the optimal solution is updated. Then the optimal solution generated by this round of iteration is stored as the optimal solution of the particle swarm, and then the next iteration is performed until termination. The optimization process ends when the number of iterations ends or the temperature is less than the minimum temperature.

Images