Marine combat resource allocation optimization method and system based on particle swarm optimization algorithm

Abstract

The invention discloses a seaborne combat resource allocation optimization method and system based on a particle swarm optimization algorithm. The method comprises the following steps: initializing particle swarm optimization algorithm parameters, particle initial positions and speeds; constructing a fitness function, calculating a fitness value of each particle, and recording an individual optimal position and a global optimal position of the particle; iterating the particle swarm, calculating and recording a new fitness value, a new individual optimal position and a global optimal position of the particle after each iteration, stopping iteration when a termination condition is reached, and outputting an optimal solution at the moment; and outputting a corresponding marine combat resource allocation scheme according to the optimal solution, and allocating the marine combat resources. According to the method, the fitness function of the particle swarm optimization algorithm is constructed by comprehensively considering the marine combat resource demand, and the resource allocation scheme can be evaluated more comprehensively in combination with the actual demand; meanwhile, the adaptive inertia weight is introduced in the iteration process, the search capability of the particle swarm can be dynamically adjusted, and the convergence speed and the optimization effect of the algorithm are improved.

Description

Technical Field

[0001] The present invention relates to the field of maritime combat resource configuration optimization, and in particular to a maritime combat resource configuration optimization method and system based on a particle swarm optimization algorithm. Background Art

[0002] Traditional methods for optimizing maritime combat resource allocation primarily rely on rule-based approaches, linear programming, or dynamic programming, among other classical optimization algorithms. These methods can provide relatively feasible solutions in certain scenarios, particularly when the problem scale is small and the constraints are simple. They can often quickly and accurately find appropriate resource allocations. However, these traditional optimization methods often exhibit significant shortcomings when faced with more complex, larger-scale, and highly uncertain maritime combat resource allocation problems. First, rule-based methods typically set rules based on historical experience and prior knowledge. While effective in certain fixed scenarios, they lack flexibility and adaptability, making them difficult to adapt to complex and dynamic combat environments. Especially when dealing with highly uncertain combat missions, rule-based methods often fail to fully account for various changing factors, resulting in optimization results that may deviate from actual requirements. Second, while linear programming can provide effective solutions for some problems with clear linear relationships, due to the nonlinear characteristics of many factors involved in maritime combat resource allocation, linear programming algorithms often struggle to handle complex nonlinear constraints and adapt to complex synergies between resources and nonlinear relationships in coverage. Although dynamic programming performs well in solving multi-stage decision-making problems, its computational complexity increases exponentially with the increase in the scale of the problem, and its handling of constraints is relatively rigid, which greatly limits its application in large-scale resource allocation problems. Summary of the Invention

[0003] To address the deficiencies of the existing technology, the present invention provides a method and system for optimizing maritime combat resource configuration based on a particle swarm optimization algorithm, so as to quickly and accurately find the optimal or approximately optimal solution for maritime combat resource configuration while meeting the demand for maritime combat resources.

[0004] To this end, the technical solution adopted in the present invention is: The present invention provides a method for optimizing the configuration of maritime combat resources based on a particle swarm optimization algorithm, the method comprising: Initializing the particle swarm optimization algorithm parameters, initial particle positions and velocities; the particle swarm optimization algorithm parameters include particle swarm size, maximum number of iterations, inertia weight, and learning factor; A fitness function is constructed based on the demand for maritime combat resources. The fitness value of each particle is calculated based on the fitness function and the initial position of the particle. The individual optimal position of each particle and the global optimal position of the particle swarm are recorded based on the fitness value. Updating the particle swarm optimization algorithm parameters to iterate the particle swarm, calculating the new fitness value of the particle after each iteration and recording the new individual optimal position and the global optimal position, stopping the iteration when the termination condition is reached, and outputting the optimal solution at this time; the updating of the particle swarm optimization algorithm parameters is performed by introducing an adaptive inertia weight to update the particle swarm optimization algorithm parameters; the optimal solution is specifically the global optimal position of the particle swarm; According to the optimal solution output corresponding to the maritime combat resource allocation plan, maritime combat resources are configured.

[0005] According to the above scheme, the fitness function is calculated using the following formula: ; in, is the fitness function, is the comprehensive coverage function, is the coefficient of the penalty term; is the reward and punishment function; The comprehensive coverage function is calculated using the following formula: ; in, Representative The detection and perception resources are The first direction of attack Coverage of various types of incoming targets; Indicates the number of detection and sensing resources; Indicates the Intercept and strike resources against the The first direction of attack Coverage of various types of incoming targets; Indicates the number of interception and attack resources; Indicates the The weight factor of the overlapping area between the detection and interception range of different types of incoming targets; Indicates the total area of ​​the responsibility sector; is the number of attack directions to be considered. When only one attack direction is considered, When it is necessary to comprehensively consider multiple attack directions, that is, to optimize interception deployment with uncertain directions, ; For the Detection and perception resources A matching relationship between interception and attack resources. If the matching conditions are met, ;otherwise, .

[0006] According to the above scheme, the reward and punishment function is quantified by the importance and violation degree of the constraints; among them, the constraints include the synergistic relationship constraints between detection and perception resources and interception and strike resources, the combat capability limitation constraints of resources and the actual demand constraints of the battlefield environment.

[0007] According to the above scheme, the adaptive inertia weight is calculated using the following formula: ; in, Indicates the current iteration number, Indicates the maximum number of iterations set by the algorithm, Indicates the scaling factor.

[0008] According to the above scheme, the particle swarm optimization algorithm parameters are updated and the particle swarm is iterated using the following formula: ; ; in, , represents the dimension of the solution space; is the adaptive inertia weight; and is the learning factor, and They represent the learning ratio of the individual optimal position of the particle to the global optimal position of the entire particle swarm; and For range Random numbers within; is the particle velocity at the tth iteration; is the particle position at the tth iteration.

[0009] According to the above scheme, the new fitness value of the particle after each iteration is calculated and the new individual optimal position and the global optimal position are recorded. Specifically, When updating the particle swarm optimization algorithm to iterate the particle swarm, the new fitness value of each particle after each iteration is calculated; If the new fitness value is greater than the fitness value corresponding to the individual optimal position, the new particle position after this iteration is updated to the new individual optimal position; if the new fitness value is greater than the fitness value corresponding to the global optimal position, the new particle position after this iteration is updated to the new global optimal position.

[0010] According to the above scheme, the termination conditions specifically include: the number of iterations reaches the maximum number of iterations, the global optimal fitness value converges to a certain threshold, and the change in the global optimal fitness value in a certain number of consecutive iterations is less than a certain threshold; the global optimal fitness value is specifically the fitness value corresponding to the global optimal position.

[0011] The present invention also provides a maritime combat resource configuration optimization system based on a particle swarm optimization algorithm, the system comprising: An initialization module is used to initialize the parameters of the particle swarm optimization algorithm, the initial position and velocity of the particles; the parameters of the particle swarm optimization algorithm include the particle swarm size, the maximum number of iterations, the inertia weight, and the learning factor; A construction module is used to construct a fitness function according to the requirements of maritime combat resources, calculate the fitness value of each particle based on the fitness function and the initial position of the particle, and record the individual optimal position of each particle and the global optimal position of the particle swarm according to the fitness value; An iteration module updates the particle swarm optimization algorithm parameters to iterate the particle swarm, calculates the new fitness value of the particle after each iteration, and records the new individual optimal position and the global optimal position. When the termination condition is reached, the iteration is stopped and the optimal solution at that time is output. The particle swarm optimization algorithm parameters are updated by introducing an adaptive inertia weight. The optimal solution is specifically the global optimal position of the particle swarm. The output module is used to output the corresponding maritime combat resource configuration plan according to the optimal solution and configure the maritime combat resources.

[0012] According to the above scheme, the iteration module is specifically used to: calculate the new particle velocity after this iteration based on the adaptive inertia weight, the learning factor, and the particle position after the previous iteration; and calculate the new particle position after this iteration based on the new particle velocity and the particle position after the previous iteration.

[0013] The present invention also provides a computer storage medium storing a computer program executable by a processor, wherein the computer program executes the above-mentioned method for optimizing the configuration of maritime combat resources based on the particle swarm optimization algorithm.

[0014] The beneficial effects of the present invention are as follows: by comprehensively considering the demand for maritime combat resources to construct a fitness function of the particle swarm optimization algorithm, the present invention can more comprehensively evaluate the pros and cons of resource allocation schemes in combination with actual needs and ensure that its optimization results meet combat needs; at the same time, by introducing adaptive inertia weights in the parameter update of the particle swarm optimization algorithm in the iterative process, the search capability of the particle swarm can be dynamically adjusted, thereby significantly improving the convergence speed and optimization effect of the algorithm, and improving the accuracy of the obtained optimal solution. The present invention has strong robustness and adaptability, can cope with changes in different combat scenarios and mission requirements, and provides reliable technical support for the scientific allocation of maritime combat resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 1 is a flow chart of a method for optimizing maritime combat resource allocation based on a particle swarm optimization algorithm according to an embodiment of the present invention; Figure 2 Schematic diagram of how the optimal fitness value changes with the number of iterations according to an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] Example 1 The essence of the maritime combat resource allocation optimization problem is how to rationally allocate and schedule maritime combat resources to maximize combat objectives while satisfying multiple constraints (such as resource quantity, coverage, and response time). The constraints involved in this problem are extremely complex and, in practical applications, highly dynamic and uncertain, making traditional optimization methods difficult to address. Conventional maritime combat resource allocation optimization methods typically rely on rule-based methods, linear programming, dynamic programming, and other algorithms. While these methods can provide feasible solutions in certain simple scenarios, they often fall short when dealing with large-scale, multi-objective, and multi-constrained resource allocation problems. Especially when considering multiple variables, dynamic environmental factors, and complex constraints simultaneously, these traditional methods suffer from low computational efficiency and difficulty finding a global optimal solution. Furthermore, traditional methods lack adaptability and cannot flexibly adjust to complex and changing combat environments, resulting in an inability to fully utilize existing resources and thus reducing combat effectiveness. Therefore, embodiments of the present invention provide a maritime combat resource allocation optimization method based on a particle swarm optimization algorithm to address the limitations of traditional methods, such as high computational complexity, insufficient ability to handle nonlinear constraints, and a tendency to fall into local optimal solutions. Figure 1 As shown, the method includes: S1. Initialize the particle swarm optimization algorithm parameters, initial particle positions and velocities; the particle swarm optimization algorithm parameters include particle swarm size, maximum number of iterations, inertia weight, and learning factor.

[0018] S2. Construct a fitness function based on the demand for maritime combat resources, calculate the fitness value of each particle based on the fitness function and the initial position of the particle, and record the individual optimal position of each particle and the global optimal position of the particle swarm according to the fitness value.

[0019] S3, updating the particle swarm optimization algorithm parameters to iterate the particle swarm, calculating the new fitness value of the particle after each iteration and recording the new individual optimal position and the global optimal position, stopping the iteration when the termination condition is reached, and outputting the optimal solution at this time; the updating of the particle swarm optimization algorithm parameters is performed by introducing an adaptive inertia weight to update the particle swarm optimization algorithm parameters; the optimal solution is specifically the global optimal position of the particle swarm.

[0020] S4. Output the corresponding maritime combat resource allocation plan based on the optimal solution and allocate the maritime combat resources.

[0021] Specifically, the parameters of the particle swarm optimization algorithm include particle swarm size N, maximum number of iterations T, inertia weight w, individual learning factor and social learning factors .

[0022] Among them, the size of the particle swarm The number of particles involved in the optimization is determined by the complexity of the problem and the limitation of computing resources. A larger particle swarm size can enhance the comprehensiveness and diversity of the search, but it will also increase the computing overhead. Therefore, it is necessary to find a balance between efficiency and effect. It controls the running time of the algorithm. The more iterations, the more opportunities the algorithm has to search and adjust, but it also means an increase in computing time. Therefore, it is necessary to make a trade-off between optimization effect and computing efficiency based on actual needs. It is an important parameter in particle swarm optimization. Its role is to balance the ability of particles to search globally and locally during the search process. A larger inertia weight helps particles maintain their original state of motion, thereby conducting a wider global search and avoiding falling into a local optimal solution. A smaller inertia weight will promote particles to conduct a more detailed local search, making it easier to accurately find the optimal solution to the problem. Therefore, the adjustment of the inertia weight directly affects the efficiency and results of the search strategy. and social learning factors They represent the degree to which the particle learns from its own historical optimal position and the global historical optimal position, respectively. Usually, the values ​​of these two factors range from 1 to 4. A larger learning factor means that the particle is more inclined to refer to its own or the global optimal solution's experience, thereby promoting faster convergence of the optimization process; however, an excessively large factor value may cause the particle to over-rely on historical information and ignore the current search status, thereby affecting the diversity of the search.

[0023] In addition, initialize the position of each particle and speed When swarming particles, it is necessary to ensure that they are randomly distributed within the solution space. This random initialization not only ensures that the particle swarm covers the entire search space but also avoids bias in the early search process, allowing the algorithm to fully explore all regions of the solution space, thereby increasing the probability of finding the global optimal solution. In practical applications, through reasonable parameter settings and initialization of particle positions and velocities, the particle swarm optimization algorithm can effectively solve complex optimization problems.

[0024] Specifically, the fitness function is obtained by subtracting the product of the reward and punishment function and the penalty term coefficient from the comprehensive coverage function; wherein, the comprehensive coverage function is calculated based on the coverage range of detection and perception resources, the number of detection and perception resources, the coverage range of interception and strike resources, the number of interception and strike resources, the total area of ​​resource responsibility sectors, the number of incoming directions, and the matching relationship between detection and perception resources and interception and strike resources.

[0025] In addition, the reward and punishment function is quantified by the importance and violation degree of the constraints; wherein, the constraints include the synergistic relationship constraints between detection and perception resources and interception and strike resources, the combat capability limitation constraints of resources, and the actual demand constraints of the battlefield environment.

[0026] Specifically, the adaptive inertia weight is calculated according to the current number of iterations, the maximum number of iterations, and the scaling factor.

[0027] Specifically, updating the particle swarm optimization algorithm parameters to iterate the particle swarm specifically includes: Calculate the new particle velocity after this iteration based on the adaptive inertia weight, learning factor, and particle position after the previous iteration; The new particle position after this iteration is calculated based on the new particle velocity and the particle position after the last iteration.

[0028] Specifically, calculate the new fitness value of the particle after each iteration and record the new individual optimal position and the global optimal position Specifically include: When updating the particle swarm optimization algorithm to iterate the particle swarm, the new fitness value of each particle after each iteration is calculated; If the new fitness value is greater than the fitness value corresponding to the individual optimal position, the new particle position after this iteration is updated to the new individual optimal position; if the new fitness value is greater than the fitness value corresponding to the global optimal position, the new particle position after this iteration is updated to the new global optimal position.

[0029] In the particle swarm optimization algorithm, when initially exploring the solution space, particles are often far away from the optimal solution. At this time, the particles need to have strong flight capabilities so that they can approach the optimal solution more quickly. However, in the later stages of the algorithm, when the particles approach the optimal solution, an excessively large flight step may cause the particles to exceed the optimal value, resulting in oscillation near the optimal value, affecting the convergence of the algorithm. Therefore, in this embodiment, an adaptive inertia weight is introduced into the particle swarm optimization algorithm. The adaptive inertia weight w can be specifically expressed as:

[0030] in, Indicates the current iteration number, Indicates the maximum number of iterations set by the algorithm, Indicates the scaling factor.

[0031] The update formula of the particle swarm optimization algorithm can be specifically expressed as:

[0032]

[0033] in, , represents the dimension of the solution space, d represents the d-th dimension of the solution space. For example, D=3 means that the space where the particle velocity and position are located is three-dimensional, and d can take three values: 1, 2, and 3. The adaptive inertia weight of particle flight; and is the learning factor, and They represent the learning ratio of the individual optimal position of the particle to the global optimal position of the entire particle swarm; and For range Random numbers within; is the particle velocity at the tth iteration; is the particle position at the tth iteration.

[0034] In this embodiment, after calculating the fitness value of each particle, the individual optimal fitness value and individual optimal position of each particle are recorded. And the global optimal fitness value and global optimal position of the entire particle swarm ; When the particle swarm optimization algorithm iterates the particle swarm, the new fitness value of each particle after each iteration is calculated; if the new fitness value is greater than the individual optimal fitness value, the new fitness value and the particle position are updated to the individual optimal fitness value and the individual optimal position; if the new fitness value is greater than the global optimal fitness value, the new fitness value and the particle position are updated to the global optimal fitness value and the global optimal position.

[0035] Specifically, the termination conditions include: the number of iterations reaches the maximum number of iterations, the global optimal fitness value converges to a certain threshold, and the change in the global optimal fitness value in a certain number of consecutive iterations is less than a certain threshold; wherein the global optimal fitness value is specifically the fitness value corresponding to the global optimal position.

[0036] When the termination condition is met, the global optimal position is output Corresponding maritime combat resource allocation plan.

[0037] like Figure 2 The following table shows the experimental results of the embodiment of the present invention. The hardware environment used is CPU i7-7700HQCPU @ 2.80GHz, memory 16G; the software environment is: Python = 3.7.1. The algorithm parameters selected for the experiment of this embodiment are shown in the following table:

[0038] In addition, the following table shows a comparison of the results of the algorithm used in this embodiment and the traditional algorithm:

[0039] As can be seen from the table above, the particle swarm optimization algorithm has significant advantages in computational efficiency compared to the exhaustive search algorithm. Under the same number of iterations, the particle swarm optimization algorithm based on adaptive inertia weight of the present invention can reach a better solution earlier. Specifically, at the 100th iteration, the optimal solution of the algorithm has exceeded the optimal solution of the exhaustive search algorithm at the 500th iteration, indicating that the particle swarm optimization algorithm can find a solution closer to the global optimal solution in a shorter time, significantly improving computational efficiency. This result fully demonstrates that the optimization method proposed by the present invention can achieve more efficient and accurate resource allocation with fewer computing resources and iterations when dealing with complex optimization problems.

[0040] In addition, if Figure 2 The graph shows how the optimal fitness value changes with the number of iterations. It can be seen that the optimal fitness value of the particle swarm optimization algorithm gradually stabilizes with increasing iterations, and its convergence speed is significantly superior to traditional exhaustive search methods. The curve in the figure clearly shows that the algorithm quickly approaches the optimal solution in the first few iterations, while in subsequent iterations, it gradually refines the search, further improving the accuracy and stability of the solution. This iterative process demonstrates the particle swarm optimization algorithm's powerful balance between global and local search capabilities. This is particularly effective in addressing multi-constraint and multi-objective maritime combat resource allocation problems, effectively avoiding the pitfalls of traditional methods that often fall into local optimal solutions.

[0041] In addition, an embodiment of the present invention further provides a system for optimizing the configuration of maritime combat resources based on a particle swarm optimization algorithm, which is used in the above-mentioned method for optimizing the configuration of maritime combat resources based on a particle swarm optimization algorithm in an embodiment of the present invention. The system includes: An initialization module is used to initialize the parameters of the particle swarm optimization algorithm, the initial position and velocity of the particles; the parameters of the particle swarm optimization algorithm include the particle swarm size, the maximum number of iterations, the inertia weight, and the learning factor; A construction module is used to construct a fitness function according to the requirements of maritime combat resources, calculate the fitness value of each particle based on the fitness function and the initial position of the particle, and record the individual optimal position of each particle and the global optimal position of the particle swarm according to the fitness value; An iteration module updates the particle swarm optimization algorithm parameters to iterate the particle swarm, calculates the new fitness value of the particle after each iteration, and records the new individual optimal position and the global optimal position. When the termination condition is reached, the iteration is stopped and the optimal solution at that time is output. The particle swarm optimization algorithm parameters are updated by introducing an adaptive inertia weight. The optimal solution is specifically the global optimal position of the particle swarm. The output module is used to output the corresponding maritime combat resource configuration plan according to the optimal solution and configure the maritime combat resources.

[0042] The iteration module is specifically used to: calculate the new particle velocity after this iteration based on the adaptive inertia weight, the learning factor, and the particle position after the previous iteration; and calculate the new particle position after this iteration based on the new particle velocity and the particle position after the previous iteration.

[0043] The various modules or mechanisms of the system are mainly used to implement the various steps of the above method embodiments, which will not be described in detail here.

[0044] In addition, an embodiment of the present invention further provides a computer storage medium storing a computer program executable by a processor, which executes the method for optimizing maritime combat resource configuration based on the particle swarm optimization algorithm described above in an embodiment of the present invention.

[0045] The embodiments of the present invention provide a method and system for optimizing the allocation of maritime combat resources based on a particle swarm optimization algorithm. By comprehensively considering the requirements for maritime combat resources, the fitness function of the particle swarm optimization algorithm is constructed. This method can more comprehensively evaluate the advantages and disadvantages of resource allocation schemes in combination with actual requirements and ensure that the optimization results meet combat needs. At the same time, an adaptive inertia weight is introduced into the parameter update of the particle swarm optimization algorithm in the iterative process. This method can dynamically adjust the search capability of the particle swarm to adapt to the search requirements of different stages and avoid falling into local optimality. It can also significantly improve the convergence speed and optimization effect of the algorithm. The method has strong robustness and adaptability, can cope with changes in different combat scenarios and mission requirements, and provides reliable technical support for the scientific allocation of maritime combat resources.

[0046] Example 2 Based on Example 1, this embodiment of the present invention provides a method for optimizing the configuration of maritime combat resources based on a particle swarm optimization algorithm, wherein the fitness function described in step S2 can be specifically expressed as follows:

[0047] in, is the coefficient of the penalty term; is the reward and punishment function.

[0048] Among them, the comprehensive coverage function can be specifically expressed as:

[0049] in, represents the comprehensive coverage rate; Representative The detection and perception resources are The first direction of attack Coverage of various types of incoming targets; Indicates the number of detection and sensing resources; Indicates the Intercept and strike resources against the The first direction of attack Coverage of various types of incoming targets; Indicates the number of interception and attack resources; Indicates the The weight factor of the overlapping area between the detection and interception range of different types of incoming targets; Indicates the total area of ​​the responsibility sector; is the number of attack directions to be considered. When only one attack direction is considered, When it is necessary to comprehensively consider multiple attack directions, that is, to optimize interception deployment with uncertain directions, ; For the Detection and perception resources A matching relationship between interception and attack resources. If the matching conditions are met, ;otherwise, For the single resource deployment optimization problem, without considering the constraints of other types of resources, the model Can be simplified to or When optimizing the joint deployment of two types of resources, select and The overlapping area is regarded as the effective coverage area.

[0050] The fitness function comprehensively considers factors such as coverage, response time, and resource utilization of maritime combat resources to evaluate the performance of each particle's deployment plan. Specifically, coverage is a crucial component of the fitness function, reflecting the sea area that the resource deployment plan can effectively support. The size of the coverage is directly related to the geographic scope requirements of the combat mission and is typically quantified based on the size, shape, and strategic importance of the target sea area. For example, for wide-area patrol missions, coverage may need to be maximized, while for key area defense missions, coverage needs to be concentrated in a specific sea area. Response time is a core metric for measuring the effectiveness of resource deployment plans. It measures the time efficiency from receiving a mission order to the actual deployment of resources, reflecting the rapid response capability of combat resources. Optimizing response time is particularly important for maritime operations, as the maritime battlefield environment is complex and volatile, and rapid response often determines the success or failure of an operation. The calculation of response time requires consideration of factors such as resource deployment location, mobility, and the efficiency of mission order delivery. Resource utilization is an essential element of the fitness function, evaluating the efficiency of the resource deployment plan in utilizing various resources. Resource utilization is directly related to the economic viability and sustainability of combat missions. Excessively low utilization can lead to resource waste, while excessively high utilization can lead to over-concentration of resources, impacting overall combat effectiveness. The calculation of resource utilization requires comprehensive consideration of the allocation of multiple resources, including manpower, equipment, and supplies, and dynamic adjustments based on mission requirements. The design of the fitness function also requires customization based on specific combat missions and objectives. For example, in emergency rescue missions, response time may be given a higher weight; in long-term patrol missions, resource utilization and coverage may be more important. By rationally designing the fitness function, the particle swarm optimization algorithm can find optimal or near-optimal resource allocation solutions in complex maritime combat environments, providing a scientific basis for command decision-making and improving overall combat effectiveness.

[0051] Furthermore, the optimization process of the particle swarm optimization algorithm is constrained by constraints, which cover the synergistic relationship between detection and perception resources and interception and strike resources, the operational capability limitations of these resources, and the actual requirements of the battlefield environment. The matching relationship between detection and perception resources and interception and strike resources is a key constraint. It requires that the detection and perception system provide the interception and strike system with timely and accurate target information to ensure the effectiveness of interception operations. This matching relationship not only involves the quantitative ratio of resources but also the timeliness and accuracy of information transmission. The near and far interception ranges of interception and strike resources for different incoming targets are also a core constraint. The near interception range determines the resource's ability to quickly respond to close-range threats, while the far interception range reflects the resource's deterrence and strike capabilities against distant targets. The setting of these two ranges requires comprehensive consideration based on the characteristics of the incoming target, the performance of the interception weapon, and the characteristics of the battlefield environment. The detection range of detection and perception resources for various incoming targets is another key constraint. The size of the detection range directly affects the ability to conduct early warning and target tracking. Different types of detection equipment may have significant differences in their detection capabilities for air, surface, and underwater targets, so they need to be appropriately configured according to mission requirements. Constraints on the guidance capabilities of detection and perception resources further limit their effectiveness in complex battlefield environments, such as limitations on multi-target tracking, anti-interference capabilities, and target recognition accuracy. The limitation on the number of firepower channels for interception and strike resources is also a significant constraint, determining the ability to simultaneously intercept multiple targets.

[0052] During the optimization process, only resource deployment plans that meet the constraints are retained; otherwise, the overall value function is penalized through a reward and penalty function. The design of the reward and penalty function requires quantifying the importance and degree of violation of the constraints. This allows the algorithm to gradually eliminate plans that do not meet the requirements during the search process, ensuring that the final optimized plan not only meets operational requirements but also complies with the actual constraints. This constraint-based optimization approach not only improves the operability of resource allocation plans but also provides a more scientific and reliable basis for command decision-making.

[0053] Preferably, in this embodiment, when the interception distance of the interception unit to the target is The following reward and punishment function can be constructed:

[0054] in, Indicates interception unit With the goal The Euclidean distance.

[0055] It should be pointed out that, according to the needs of implementation, the various steps / components described in this application can be split into more steps / components, or two or more steps / components or partial operations of steps / components can be combined into new steps / components to achieve the purpose of the present invention.

[0056] The size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0057] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes should fall within the scope of protection of the appended claims of the present invention.

Claims

1. A method for optimizing maritime combat resource allocation based on particle swarm optimization algorithm, characterized in that: The method comprises: Initializing the particle swarm optimization algorithm parameters, initial particle positions and velocities; the particle swarm optimization algorithm parameters include particle swarm size, maximum number of iterations, inertia weight, and learning factor; A fitness function is constructed based on the demand for maritime combat resources. The fitness value of each particle is calculated based on the fitness function and the initial position of the particle. The individual optimal position of each particle and the global optimal position of the particle swarm are recorded based on the fitness value. Updating the particle swarm optimization algorithm parameters to iterate the particle swarm, calculating the new fitness value of the particle after each iteration and recording the new individual optimal position and the global optimal position, stopping the iteration when the termination condition is reached, and outputting the optimal solution at this time; the updating of the particle swarm optimization algorithm parameters is performed by introducing an adaptive inertia weight to update the particle swarm optimization algorithm parameters; the optimal solution is specifically the global optimal position of the particle swarm; According to the optimal solution output corresponding to the maritime combat resource allocation plan, maritime combat resources are configured.

2. The method for optimizing maritime combat resource allocation based on particle swarm optimization algorithm according to claim 1, characterized in that: The fitness function is calculated using the following formula: ； in, is the fitness function, is the comprehensive coverage function, is the coefficient of the penalty term; is the reward and punishment function; The comprehensive coverage function is calculated using the following formula: ； in, Representative The detection and perception resources are The first direction of attack Coverage of various types of incoming targets; Indicates the number of detection and sensing resources; Indicates the Intercept and strike resources against the The first direction of attack Coverage of various types of incoming targets; Indicates the number of interception and strike resources; Indicates the The weight factor of the overlapping area between the detection and interception range of different types of incoming targets; Indicates the total area of ​​the responsibility sector; is the number of attack directions to be considered. When only one attack direction is considered, When it is necessary to comprehensively consider multiple attack directions, that is, to optimize interception deployment with uncertain directions, ; For the Detection and perception resources A matching relationship between interception and attack resources. If the matching conditions are met, ;otherwise, .

3. The method for optimizing maritime combat resource allocation based on particle swarm optimization algorithm according to claim 2, characterized in that: The reward and punishment function is obtained by quantifying the importance and violation degree of the constraints; among them, the constraints include the synergistic relationship constraints between detection and perception resources and interception and strike resources, the combat capability limitation constraints of resources, and the actual demand constraints of the battlefield environment.

4. The method for optimizing maritime combat resource allocation based on particle swarm optimization algorithm according to claim 1, characterized in that: The adaptive inertia weight is calculated using the following formula: ； in, Indicates the current iteration number, Indicates the maximum number of iterations set by the algorithm, Indicates the scaling factor.

5. The method for optimizing maritime combat resource allocation based on particle swarm optimization algorithm according to claim 1, characterized in that: Update the particle swarm optimization algorithm parameters and iterate the particle swarm using the following formula: ； ； in, , represents the dimension of the solution space; is the adaptive inertia weight; and is the learning factor, and They represent the learning ratio of the individual optimal position of the particle to the global optimal position of the entire particle swarm; and For range Random numbers within; is the particle velocity at the tth iteration; is the particle position at the tth iteration.

6. The method for optimizing maritime combat resource allocation based on particle swarm optimization algorithm according to claim 1 or 5, characterized in that: Calculate the new fitness value of the particle after each iteration and record the new individual optimal position and the global optimal position. Specifically include: When updating the particle swarm optimization algorithm to iterate the particle swarm, the new fitness value of each particle after each iteration is calculated; If the new fitness value is greater than the fitness value corresponding to the individual optimal position, the new particle position after this iteration is updated to the new individual optimal position; if the new fitness value is greater than the fitness value corresponding to the global optimal position, the new particle position after this iteration is updated to the new global optimal position.

7. The method for optimizing maritime combat resource allocation based on particle swarm optimization algorithm according to claim 1, characterized in that: The termination conditions specifically include: the number of iterations reaches the maximum number of iterations, the global optimal fitness value converges to a certain threshold, and the change in the global optimal fitness value in a certain number of consecutive iterations is less than a certain threshold; the global optimal fitness value is specifically the fitness value corresponding to the global optimal position.

8. A maritime combat resource allocation optimization system based on particle swarm optimization algorithm, characterized in that: The system comprises: An initialization module is used to initialize the parameters of the particle swarm optimization algorithm, the initial position and velocity of the particles; the parameters of the particle swarm optimization algorithm include the particle swarm size, the maximum number of iterations, the inertia weight, and the learning factor; A construction module is used to construct a fitness function according to the requirements of maritime combat resources, calculate the fitness value of each particle based on the fitness function and the initial position of the particle, and record the individual optimal position of each particle and the global optimal position of the particle swarm according to the fitness value; An iteration module updates the particle swarm optimization algorithm parameters to iterate the particle swarm, calculates the new fitness value of the particle after each iteration, and records the new individual optimal position and the global optimal position. When the termination condition is reached, the iteration is stopped and the optimal solution at that time is output. The particle swarm optimization algorithm parameters are updated by introducing an adaptive inertia weight. The optimal solution is specifically the global optimal position of the particle swarm. The output module is used to output the corresponding maritime combat resource configuration plan according to the optimal solution and configure the maritime combat resources.

9. The maritime combat resource allocation optimization system based on particle swarm optimization algorithm according to claim 8 is characterized in that: The iteration module is specifically used to: calculate the new particle velocity after this iteration based on the adaptive inertia weight, the learning factor, and the particle position after the previous iteration; and calculate the new particle position after this iteration based on the new particle velocity and the particle position after the previous iteration.

10. A computer storage medium, characterized in that A computer program executable by a processor is stored therein, and the computer program executes the method for optimizing the configuration of maritime combat resources based on the particle swarm optimization algorithm according to any one of claims 1 to 7.

Images