A method and system for allocating ground attack tasks of UAV clusters based on improved particle swarm algorithm

Abstract

This invention discloses a method and system for allocating ground attack tasks for drone swarms based on an improved particle swarm algorithm. This method belongs to the field of intelligent optimization algorithms. Addressing the problem of allocating ground attack tasks for drone swarms, the invention analyzes existing research results, comprehensively considers target attack benefits and target attack costs, and analyzes two types of constraints: target-based constraints and drone-based constraints. This method establishes a mathematical model that maximizes the attack cost-effectiveness ratio. The specific steps are as follows: Step 1: Establish an objective function for ground attack task allocation that maximizes target attack benefits and minimizes target attack costs; Step 2: Analyze the constraints for ground attack task allocation; Step 3: Establish a mathematical model for ground attack task allocation based on the objective function and constraints; Step 4: Solve the mathematical model established in Step 3 using the improved particle swarm algorithm to obtain the final allocation result.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent optimization algorithms, and in particular relates to a method and system for allocating ground attack tasks of a cluster of unmanned aerial vehicles (UAVs) based on an improved particle swarm algorithm. Background Art

[0002] With the rapid development of network, control, and artificial intelligence technologies, major militaries around the world have conducted extensive basic theoretical research on the swarming use of drones, driving the implementation of related combat concepts. Drone swarm combat, supported by communications networks, involves the self-organization of a large number of low-cost, numerous, and autonomous drones. These systems combine spatial density and dispersion, operational planning and suddenness, and unidirectional and multi-directional attack directions to conduct continuous and parallel reconnaissance, electronic jamming, and firepower strikes against enemy targets.

[0003] Drone swarm combat has its own specific biological principles. In fact, swarming behavior is universal in the biological world. Wildebeests migrate in herds, ants flock to forage, and fish swim in groups. Within these swarms, individual perception and action capabilities are relatively simple, yet through complex collaborative behaviors, overall capabilities emerge. Drone swarms draw on this "autonomy + collaboration" behavior, achieving combat effectiveness through sheer volume and collaborative energy through the complex interactions of a large number of simple individuals.

[0004] Drone swarms can perform a variety of missions, generally speaking, including offensive and defensive missions. Offensive missions primarily include seizing air superiority and ground penetration attacks; defensive missions include defensive air interception and key point air defense. Furthermore, drone swarms can also perform support and assurance missions such as airborne early warning and detection, electronic jamming, and communications relay. The required level of autonomy for each of these missions varies. Generally speaking, the requirements for autonomy decrease in descending order from air combat to ground attack and support and assurance missions. Due to these varying levels of autonomy, drone swarms are currently less capable of conducting air combat missions, with offensive missions primarily focused on ground and sea attack missions.

[0005] Mission planning is key to swarm drone decision-making and control during ground attack missions. This process involves both pre-planning and online re-planning. Pre-planning involves developing a plan based on an analysis of the operational situation before the mission begins. Online re-planning involves restructuring and adjusting the plan based on changes in the operational situation caused by unexpected battlefield events during mission execution. Mission planning for ground attack drone swarms encompasses a comprehensive approach encompassing task allocation, route planning, communication link planning, and sensor planning, with task allocation being both a key and challenging aspect.

[0006] Extensive research has been conducted on the problem of allocating ground attack tasks for drone swarms, primarily focusing on modeling and solving them. Generally speaking, classic models for this problem include the Multiple Traveling Salesman Problem (MTSP), the Mixed Integer Linear Programming (MILP), the Cooperative Multiple Task Assignment Problem (CMTAP), and the Hybrid Binary Programming (HBP). Establishing the UAV swarm ground attack task allocation model as a classic model allows for the use of corresponding fast heuristic methods, resulting in optimal allocation results with minimal time cost. Solutions to this model primarily include optimization methods, intelligent optimization methods, and market mechanisms. Optimization methods include the Hungarian algorithm, branch-and-bound algorithm, and Lagrangian relaxation. However, these methods place high demands on the model and can only solve specific models. Intelligent optimization methods are algorithms designed to simulate human intelligence, the characteristics of biological populations, or natural laws. These include genetic algorithms (GAs), ant colony optimization (ACOs), artificial bee colony algorithms (ABCs), and wolf pack algorithms (WPAs). These algorithms offer the advantage of being less demanding on the model form, but suffer from poor timeliness and stability. Market mechanism methods primarily include contract network protocols and auction algorithms. These algorithms inherently employ distributed problem-solving architectures. While computationally intensive, they rely on frequent information exchange and negotiated decision-making. Furthermore, since the resulting solutions are compromises between all parties, the optimality of the solutions may be affected to some extent.

[0007] In short, as a hot topic in the research of military operations and UAV combat applications, the allocation of UAV swarm ground attack tasks is also an urgent problem that needs to be solved. Summary of the Invention

[0008] In order to solve the problem of allocating ground attack tasks among drone swarms, the present invention establishes a mathematical model based on the two aspects of attack benefit and attack cost, taking into account constraints such as target coverage, target damage effect, drone attack threshold, and drone range in ground attacks. The improved particle swarm optimization (IPSO) algorithm, which includes encoding and decoding rules, constraint processing rules, and iterative evolution rules, is used to solve the model, achieving good solution results.

[0009] In a first aspect, the present invention provides a method for optimizing blasting design parameters based on deep learning and deep neural networks, the optimization method comprising the following steps:

[0010] Step 1: For ground attack mission allocation, establish an objective function to maximize the target attack benefit and minimize the target attack cost;

[0011] Step 2: Analyze the constraints of ground attack mission allocation;

[0012] Step 3: Integrate the objective function and constraints of ground attack task allocation to establish a mathematical model for ground attack task allocation;

[0013] Step 4: Use the improved particle swarm algorithm to solve the mathematical model established in step 3 to obtain the final allocation result.

[0014] Furthermore, the objective function established in step 1 is as follows:

[0015] O=S / Q (6)

[0016] Among them, S represents the target attack benefit, and its expression is as follows:

[0017]

[0018] In the above, x mn represents the decision variable, d mn Indicates drone U m Target T n probability of damage;

[0019] Q represents the target attack cost, which is expressed as follows:

[0020]

[0021] In the above formula, For UAV U m The value of the variable related to the voyage cost, vU m is the platform value of the mth UAV, f(e1,e2) is a function of two variables e1 and e2, and f(e1,e2)=e1·e2 is defined. for

[0022]

[0023] Among them, c m For UAV U m The actual range of executing the target attack mission, cUm is the maximum range of the m-th UAV.

[0024] Furthermore, the specific steps of step 2 include:

[0025] Step 201: Target coverage is approximately, for any target T n , there should be at least one drone attacking it, that is:

[0026]

[0027] Step 202: Target damage effect constraint requires that the damage effect of all targets after being attacked reaches a certain threshold, that is:

[0028]

[0029] Step 203: The drone attack threshold constraint has a certain upper limit on the number of target attacks, namely:

[0030]

[0031] In the above formula, hT n The damage threshold that needs to be reached for the nth target;

[0032] Step 204: The actual range of the drone during the target attack mission cannot exceed the maximum range of the drone, that is:

[0033] c m ≤cU m , 1≤m≤M (10).

[0034] Furthermore, the mathematical model of ground attack distribution established by integrating the objective function and constraints in step 3 is:

[0035]

[0036] In formula (11), the first and second constraints are target constraints, and the third and fourth constraints are platform constraints.

[0037] Furthermore, in step 4, according to the characteristics of the UAV cluster ground attack task allocation, the encoding and decoding rules, constraint processing rules and particle updating rules of the particle swarm algorithm are designed to solve the mathematical model.

[0038] The specific steps of solving the problem using the improved particle swarm algorithm are as follows:

[0039] Step 401: Initialize the particle swarm. Each particle is an M*N matrix, where rows and columns represent drones and targets respectively. The elements in the matrix are real numbers that meet the coding rules, i.e., (0, 1.2].

[0040] Step 402 retains the current individual optimal and global optimal solutions. According to the decoding rules and constraint processing rules, feasible solutions are obtained and sorted. The best of all feasible solutions is the global optimal solution. All feasible solutions correspond to the individual optimal solutions of all particles at the current number of iterations.

[0041] Step 403: Particle swarm evolution. Entering the next iteration, the update formula of each particle's position matrix X and velocity matrix U is updated using the proposed particle update rule.

[0042] Step 404: Update the individual optimal solution and the global optimal solution. Determine whether the feasible solution corresponding to each particle at the current number of iterations is better than the corresponding individual optimal solution. If so, update the solution. Determine whether the optimal solution corresponding to the feasible solutions of all particles at the current number of iterations is better than the global optimal solution. If so, update the solution.

[0043] Furthermore, when the particle swarm algorithm is used to solve the mathematical model, the encoding and decoding rules adopt real number encoding, and the matrix G=(g mn ) M×N represents a population, where g mn The value range is (0,1.2], and the decoding method mainly uses the rounding down method, that is, for the 1 to N columns of the matrix G, Then let x mn =1.

[0044] Furthermore, the decision matrix obtained after encoding and decoding needs to be subjected to corresponding constraint processing. The specific operations are as follows:

[0045] (1) Determine whether all drones meet the constraints and record the serial numbers of all drones that do not meet the constraints;

[0046] (2) Process the drones that do not meet the constraints in order from low to high, and judge and cancel the attack on the target of the drone with the current sequence number according to the execution order until the third and fourth constraints of the mathematical model are met;

[0047] (3) Determine whether all targets satisfy the first and second constraints of the mathematical model, and record the serial numbers of all targets that do not meet the constraints;

[0048] (4) Process the targets that do not meet the constraints in descending order, and judge the current target from top to bottom and add drones to execute until the first and second constraints of the mathematical model are met; if the addition of a certain drone causes the third or fourth constraint of the mathematical model to no longer be met, the current drone will not be added, but the subsequent drones will continue to be judged;

[0049] After the decision matrix transformation, the penalty function method is further adopted. If the target number of a solution violating the constraint condition is δ (0≤δ≤N), the corresponding objective function is divided by δ+1.

[0050] Furthermore, the movement of particles mainly depends on the current position and velocity of the particles. The update formulas of the position matrix X and velocity matrix U are as follows:

[0051]

[0052] Among them, X and U are the position and velocity matrices before updating, X' and U' are the position and velocity matrices after updating, X G is the global optimal position under the current number of iterations, X L is the local optimal position under the current number of iterations, w is the inertia coefficient, c1 and c2 are learning factors, and rand1 and rand2 are random numbers in the range of (0,1).

[0053] In a first aspect, the present invention provides a UAV cluster ground attack task allocation system based on an improved particle swarm algorithm, the system comprising:

[0054] The first building block establishes the objective function of the UAV swarm ground attack mission based on battlefield environment information;

[0055] The second building block analyzes the constraints of target coverage, target damage effect, drone attack threshold, and drone range, and establishes a mathematical model for the allocation of drone swarm ground attack tasks based on the objective function.

[0056] The processing module is used to solve the mathematical model using the improved particle swarm algorithm.

[0057] Compared with the prior art, the present invention has the following advantages:

[0058] 1. This paper comprehensively considers the target attack benefits and costs, analyzes both target-based and drone-based constraints, and establishes a mathematical model that maximizes the attack cost-effectiveness ratio. This model is primarily solved using an improved particle swarm optimization algorithm. The algorithm's encoding and decoding rules and constraint processing rules are designed to address the model's discrete and multi-constrained nature. Multiple simulation experiments demonstrate that the proposed algorithm can effectively solve a multi-constrained ground attack task allocation model.

[0059] 2. Compared with the firefly algorithm and artificial bee colony algorithm, the improved particle swarm algorithm designed by the present invention has stronger optimization ability. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is the iterative evolution of the IPSO algorithm.

[0061] Figure 2 Iterative evolution of each comparison algorithm.

[0062] Figure 3 Iterative evolution of each comparison algorithm. DETAILED DESCRIPTION

[0063] The preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making a clearer and more precise definition of the protection scope of the present invention.

[0064] This embodiment specifically provides a method for allocating ground attack tasks of a drone cluster based on an improved particle swarm algorithm, which is introduced in detail from the following aspects.

[0065] 1. Definition of Task Allocation Problem Elements and Their Attributes

[0066] The problem of reassigning drone swarm ground attack missions primarily involves two key components: drones and targets. To simplify the problem, it is assumed that all drones launch from a certain initial position and attack ground targets, with varying platform values and mission execution capabilities. Changes in the drones' altitude are not considered; that is, they always move at the same altitude. Ground targets are assumed to be fixed, primarily including enemy command posts, important roads and bridges, radar sites, and missile launch sites. Relevant target information is already available through preliminary reconnaissance and detection.

[0067] (1) The set of UAVs is UAV={U1,U2,…,U M}, where M is the number of drones. m (1≤m≤M), let its initial position coordinates be (xU m ,yUm ), the platform value is vU m , the task execution threshold is hU m , the longest range is cU m .

[0068] (2) The target set is Target={T1,T2,…,T N}, where N is the number of targets. n (1≤n≤N), let its location coordinate be (xT n ,yT n ), the target value is vT n , the target expected damage effect threshold is hT n .

[0069] UAVU m Target T n The probability of damage is d mn , the damage probability of all drones to all targets forms a matrix D = (d mn ) M×N Target T n UAV m The threat size is r nm , the threat size of all targets to all drones constitutes the matrix R = (r nm ) N×M .

[0070] The decision matrix of the UAV swarm ground attack task allocation model is X = (x mn ) M×N , decision variable x mn Defined as

[0071]

[0072] 2. Modeling the Ground Attack Task Allocation Problem

[0073] The ground attack task allocation model primarily consists of two aspects: constraints and objective functions. First, the objective function of the task allocation model is analyzed. The principle of any combat operation is to maximize enemy damage while preserving the enemy's own capabilities. Therefore, the objective function of ground attack task allocation primarily consists of two aspects: maximizing the target attack benefit and minimizing the target attack cost.

[0074] (1) Target attack benefit. The target attack benefit is related to the target value and the probability of damage to the target after being attacked. The calculation formula for the target attack benefit is defined as:

[0075]

[0076] in, Target T n The probability of being damaged by one or more drones is defined as The calculation formula is:

[0077]

[0078] (3) Target attack cost. The target attack cost is related to the value of the UAV platform, the threat level of the target to the UAV, the actual range of the UAV mission, and the maximum range of the UAV. The calculation formula for the target attack cost Q is defined as:

[0079]

[0080] in, For UAV U m The value of the variable related to the voyage cost, vU m is the platform value of the mth UAV, f(e1,e2) is a function of two variables e1 and e2, and f(e1,e2)=e1·e2 is defined. for

[0081]

[0082] Among them, c m For UAV U m The actual range of executing the target attack mission, cUm is the maximum range of the m-th UAV.

[0083] In summary, the objective function O of the ground attack task allocation model is defined as:

[0084] O=S / Q (6)

[0085] Then, the constraints of the task allocation model are analyzed. The design of the constraints mainly considers the following aspects: the target must be attacked, the drone attack target has a certain upper limit, and the target attack must achieve a certain damage effect. The details are as follows:

[0086] (1) Target coverage constraint: To ensure the attack on all discovered targets, for any target T n , there should be at least one drone attacking it, that is:

[0087]

[0088] (2) Target damage effect constraint: To ensure the purpose of damaging all targets, the damage effect of all targets after being attacked must reach a certain threshold, that is:

[0089]

[0090] In the above formula, hT nThe damage threshold that needs to be reached for the nth target.

[0091] (3) UAV attack threshold constraint: Due to the limitation of payload, UAVs cannot attack an unlimited number of targets. There is a certain upper limit on the number of targets that can be attacked, namely:

[0092]

[0093] (4) UAV range constraint: Due to the limitation of fuel, the actual range of the UAV in performing the target attack mission cannot exceed the maximum range of the UAV, that is:

[0094] c m ≤cU m , 1≤m≤M (10).

[0095] Combining the objective function and constraints of the model, the mathematical model of ground attack task allocation is established as follows:

[0096]

[0097] In formula (11), the first and second constraints are target constraints, and the third and fourth constraints are platform constraints.

[0098] 3. Ground attack task allocation based on improved particle swarm optimization algorithm

[0099] To solve the ground attack task allocation model shown in Equation (11), the IPSO algorithm is primarily used. The particle swarm optimization algorithm is a global optimization algorithm designed to simulate the foraging behavior of biological groups. It has the advantages of having few parameters, simple implementation, and strong optimization capabilities. The particle swarm optimization algorithm is primarily used to solve continuous domain optimization problems, but it can also be discretized to solve discrete domain optimization problems. Based on the characteristics of the problem of ground attack task allocation for drone swarms, this paper designs the algorithm's encoding and decoding rules, constraint processing rules, and particle update rules to solve Equation (11).

[0100] 3.1 Algorithm encoding and decoding rules

[0101] When using the IPSO algorithm to solve the problem shown in formula (11), the design of the encoding and decoding rules is very important. The encoding rule of the algorithm emphasizes simplicity and efficiency, that is, using less storage space to effectively represent the decision variables of the problem, and the encoding can adapt to the iterative operator of the algorithm without more conversion operations; the decoding rule of the algorithm emphasizes that the mapping to the problem solution space is unique and the mapping process is simple, which can ensure that the iterative operator of the encoding space is independent of the solution space. According to the constraints and other characteristics of the model, the encoding method adopted in this paper is real number encoding, using the matrix G = (g mn ) M×Nrepresents a population, where g mn The value range is (0,1.2], and the decoding method mainly uses the rounding down method, that is, for the 1 to N columns of the matrix G, Then let x mn =1.

[0102] Taking M=4 and N=5 as an example, a code G is randomly generated and the corresponding solution X obtained using the above decoding rule is as follows.

[0103]

[0104] According to the above decoding rules, the population can be decoded into a decision matrix. Such a decision matrix may not satisfy the constraints in Equation (11) and requires constraint processing. In fact, the calculation of the UAV range is also affected by the execution order of the attack mission. The main method is to sort the decimal parts of the elements with values greater than or equal to 1 in each row in ascending order to determine the execution order of the attack mission. Taking the above G as an example, the second row represents the second UAV U2. The decimal parts of the elements greater than or equal to 1 are 0.1441, 0.1896, and 0.1001, corresponding to T1, T4, and T5, respectively. Since 0.1001 < 0.1441 < 0.1896, the execution order of U2's attack mission is T5 → T1 → T4.

[0105] 3.2 Algorithm Constraint Processing Rules

[0106] After decoding, the decision matrix is obtained, but it cannot guarantee that the constraints in Equation (11) are satisfied, so appropriate constraint processing is required. For multi-constraint optimization problems, constraint processing rules mainly include penalty function method, decision matrix transformation method, multi-objective optimization method, feasibility rule method, and ε constraint method, which need to be selected based on the characteristics of the problem to be solved. Considering that the proportion of feasible solutions in the solution space is relatively small, this paper mainly adopts a method that combines the decision matrix transformation method and the penalty function method.

[0107] The decision matrix transformation method changes the values of the decision variables in the decision matrix so that the decision matrix can satisfy all constraints. To satisfy the UAV-class constraints and target-class constraints in Equation (11), the following constraint processing operations are performed.

[0108] (1) Determine whether all drones meet the constraints and record the serial numbers of all drones that do not meet the constraints;

[0109] (2) Process the drones that do not meet the constraints in order from low to high, and judge and cancel the attack on the target of the drone with the current sequence number according to the execution order until the third and fourth constraints of the mathematical model are met;

[0110] (3) Determine whether all targets satisfy the first and second constraints of the mathematical model, and record the serial numbers of all targets that do not meet the constraints;

[0111] (4) The targets that do not meet the constraints are processed in order from low to high, and the current target number is judged from top to bottom to add drones for execution until the first and second constraints of the mathematical model are met; if the third or fourth constraint of the mathematical model is no longer met after adding a certain drone, the current drone is not added, but the subsequent drones are judged.

[0112] As can be seen from the above steps, the decision matrix transformation method can fully satisfy the UAV constraints, but it cannot fully satisfy the target constraints. Therefore, after the decision matrix transformation, a penalty function method is further applied. If the number of targets that violate the constraints of a solution is δ (0≤δ≤N), the corresponding objective function is divided by δ+1.

[0113] 3.3 Particle Update Rules

[0114] In the IPSO algorithm, particle movement mainly depends on the current position and velocity of the particle. The update formula of the position matrix and velocity matrix is shown in Equation (12).

[0115]

[0116] Among them, X and U are the position and velocity matrices before updating, X' and U' are the position and velocity matrices after updating, X G is the global optimal position under the current number of iterations, X L is the local optimal position under the current number of iterations, w is the inertia coefficient, c1 and c2 are learning factors, and rand1 and rand2 are random numbers in the range of (0,1).

[0117] The specific steps of solving the problem using the improved particle swarm algorithm are as follows:

[0118] Step 401: Initialize the particle swarm. Each particle is an M*N matrix, where rows and columns represent drones and targets respectively. The elements in the matrix are real numbers that meet the coding rules, i.e. (0, 1.2].

[0119] Step 402: Retain the current individual optimal and global optimal solutions. Obtain feasible solutions according to the decoding rules and constraint processing rules, and sort the feasible solutions. The best of all feasible solutions is the global optimal solution. All feasible solutions correspond to the individual optimal solutions of all particles at the current number of iterations.

[0120] Step 403: Particle swarm evolution. Entering the next iteration, the update formula of each particle's position matrix X and velocity matrix U is updated using the proposed particle update rule.

[0121] Step 404: Update the individual optimal solution and the global optimal solution. Determine whether the feasible solution corresponding to each particle at the current number of iterations is better than the corresponding individual optimal solution. If so, update the solution. Determine whether the optimal solution corresponding to the feasible solutions of all particles at the current number of iterations is better than the global optimal solution. If so, update the solution.

[0122] Simulation results analysis

[0123] To verify the effectiveness and superiority of the IPSO algorithm in solving the model shown in Equation (11), relevant simulation comparison experiments were carried out using MATLAB R2021a on a computer equipped with a core frequency of 2.27GHz processor. Among them, simulation experiment 1 verifies the effectiveness of the IPSO algorithm, that is, the IPSO algorithm can solve a feasible solution that satisfies all constraints, and verifies the superiority of the IPSO algorithm compared to the Glowworm Swarm Optimization (GSO) and Artificial Bee Colony (ABC) algorithm in a set of typical scenarios; simulation experiment 2 verifies the superiority of the IPSO algorithm compared to the GSO algorithm and ABC algorithm in random scenarios.

[0124] In terms of scenario setting, the number of drones in the drone cluster is 30, the initial positions of the drones are randomly distributed in a 100*100 square area, the drone value is a random number in the range of [0.1, 0.7], the drone's threshold for performing ground attack missions is a random integer in the range of [3, 6], and the drone's maximum range is 300, 400, 500, 600, or 700; the number of various targets to be attacked is 40, the target positions are randomly distributed in a 100*100 square area, the target value is a random number in the range of [0.3, 0.9], and the target expected damage probability is a random number in the range of [0.5, 0.8]; the drone's damage probability to the target is a random number in the range of [0.2, 0.9], and the target's threat size to the drone is a random number in the range of [0.1, 0.8].

[0125] Simulation Experiment 1: The scenario settings are a set of typical scenarios under the aforementioned values. Table 1 shows the drone's initial position, value, ground attack mission threshold, and maximum range. Table 2 shows the target's position, value, and expected damage probability. For the IPSO algorithm, the population size is set to 50 and the number of iterations is set to 200.

[0126] Table 1 UAV attributes

[0127]

[0128]

[0129] Table 2 Target attribute table

[0130]

[0131] Under the above parameter input, the IPSO algorithm is used to solve equation (11). Figure 1 As shown in Figure 1, it is the iterative evolution of the IPSO algorithm.

[0132] Table 3 shows the final distribution of UAV ground attack tasks obtained by the IPSO algorithm. The actual damage probabilities of all targets are 0.85, 0.88, 0.86, 0.64, 0.88, 0.87, 0.87, 0.89, 0.88, 0.88, 0.58, 0.84, 0.82, 0.90, 0.85, 0.88, 0.90, 0.85, 0.89, 0.89, 0.88, 0.86, 0.87, 0.90, 0.89, 0.82, 0.90, 0.88, 0.80, 0.88, 0.88, 0.74, 0.83, 0.87, 0.63, 0.81, 0.88, and 0.90, which all meet the expected damage probabilities and meet the target class constraints. The actual ranges of all drones are 24.91, 74.35, 76.33, 0, 35.10, 47.99, 67.83, 0, 92.98, 106.04, 74.11, 66.51, 83.64, 13.42, 84.68, 119.32, 13.51, 7.49, 0, 99.27, 41.40, 176.94, 35.35, 63.14, 85.63, 202.21, 85.70, 89.93, 49.74, and 158.44, which are all less than their maximum ranges, and the actual number of missions performed is less than their respective mission thresholds, which meets the drone category constraints.

[0133] Table 3 IPSO algorithm solves the generated task allocation results

[0134]

[0135] The scenario is still set to a set of typical scenarios under the above values, and the number of iterations of the IPSO algorithm, GSO algorithm and ABC algorithm is set to 200. Figure 2 As shown in Figure 1, it is the iterative evolution of the three algorithms: PSO algorithm, GSO algorithm and ABC algorithm. Figure 2It can be seen that in this typical scenario, the optimization ability of the PSO algorithm is stronger than that of the GSO algorithm and the ABC algorithm, and the algorithm convergence is stronger than that of the ABC algorithm.

[0136] Simulation experiment 2: The scenario is set as a set of random scenarios under the above values. All parameters are set randomly. The IPSO algorithm, GSO algorithm and ABC algorithm are run 20 times respectively. Figure 3 As shown in Figure 2, the box-and-whisker plots of the objective function values of each comparison algorithm are run 20 times.

[0137] Among them, the mean value of the objective function of the IPSO algorithm is 18.2212, the median value of the objective function value is 18.5020, and the variance value of the objective function value is 3.1221; the mean value of the objective function of the GSO algorithm is 14.9028, the median value of the objective function value is 14.7334, and the variance value of the objective function value is 1.7668; the mean value of the objective function of the ABC algorithm is 16.2795, the median value of the objective function value is 16.0471, and the variance value of the objective function value is 3.4773.

[0138] It can be seen that the IPSO algorithm has the strongest optimization ability, but its stability is inferior to the GSO algorithm and better than the ABC algorithm.

[0139] Conclusion: To address the problem of allocating ground attack tasks for drone swarms, this paper, based on an analysis of existing research results, comprehensively considers both the target attack benefit and target attack cost, and analyzes both target-based and drone-based constraints to establish a mathematical model that maximizes the attack cost-effectiveness ratio. This model is primarily solved using an improved particle swarm optimization algorithm. The algorithm's encoding and decoding rules and constraint processing rules are designed to address the model's discrete and multi-constrained nature. Multiple simulation experiments demonstrate that the proposed algorithm can effectively solve the multi-constrained ground attack task allocation model. Compared to the firefly algorithm and artificial bee colony algorithm, the improved particle swarm optimization algorithm exhibits stronger optimization capabilities and a stability intermediate between the two.

[0140] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the essence and scope of the technical solutions of the present invention.

Claims

1. A method for allocating ground attack tasks of UAV clusters based on an improved particle swarm algorithm, characterized in that: The allocation method includes the following steps: Step 1: For ground attack mission allocation, establish an objective function to maximize the target attack benefit and minimize the target attack cost; Step 2: Analyze the constraints of ground attack mission allocation; Step 3: Integrate the objective function and constraints of ground attack task allocation to establish a mathematical model for ground attack task allocation; Step 4: Use the improved particle swarm algorithm to solve the mathematical model established in step 3 to obtain the final allocation result; In step 3, the mathematical model of ground attack distribution is established by integrating the objective function and constraints: （11） In formula (11), the first and second constraints are target constraints, and the third and fourth constraints are platform constraints. Target attack benefit, The target attack cost, is the decision variable, is the number of drones, is the target number, Target The probability of being damaged by one or more drones, For the n The damage threshold that needs to be reached for each target. is the task execution threshold, For the longest voyage; In step 4, according to the characteristics of the UAV cluster ground attack task allocation, the encoding and decoding rules, constraint processing rules and particle update rules of the particle swarm algorithm are designed to solve the mathematical model; When using particle swarm optimization to solve mathematical models, the encoding and decoding rules use real number encoding and matrix represents a population, where The value range is , the decoding method mainly adopts the rounding down method, that is, the matrix of Column, for , then let ; The decision matrix obtained after encoding and decoding needs to be processed with corresponding constraints. The specific operations are as follows: (1) Determine whether all drones meet the constraints and record the serial numbers of all drones that do not meet the constraints; (2) Process the drones that do not meet the constraints in order from low to high, and judge the expected attack targets of the drone with the current sequence number according to the execution order and cancel the attack until the third and fourth constraints of the mathematical model are met; (3) Determine whether all targets meet the first and second constraints of the mathematical model, and record the serial numbers of all targets that do not meet the constraints; (4) Process the targets that do not meet the constraints in descending order, and judge the current target from top to bottom and add drones to execute until the first and second constraints of the mathematical model are met; if the addition of a drone causes the third or fourth constraint of the mathematical model to no longer be met, the current drone will not be added, but the subsequent drones will continue to be judged; After the decision matrix transformation, the penalty function method is further adopted. If a solution violates the target number of constraints, , then in the corresponding objective function, divide by .

2. The method for allocating ground attack tasks of a UAV cluster based on an improved particle swarm algorithm according to claim 1 is characterized in that: The objective function established in step 1 is as follows: （6） in, It represents the target attack benefit, and its expression is as follows: （2） （3） Among the above, represents the decision variable, is the target value, Indicates drone Towards the target probability of damage; It represents the target attack cost, which is expressed as follows: （4） In the above formula, For drones The value of the variable related to the voyage cost, For the m The platform value of a drone, Target drones The size of the threat, It is a two-variable and The function that constitutes ,definition for （5） in, For drones The actual range of the target attack mission, For the m The maximum flight range of a drone.

3. The method for allocating ground attack tasks of a UAV cluster based on an improved particle swarm algorithm according to claim 2 is characterized in that: The specific steps of step 2 include: Step 201: Target coverage is approximately, for any target , there should be at least one drone attacking it, that is: （7） Step 202: Target damage effect constraint requires that the damage effect of all targets after being attacked reaches a certain threshold, that is: （8） In the above formula, For the n The damage threshold that needs to be reached for each target; Step 203: The drone attack threshold constraint has a certain upper limit on the number of target attacks, namely: （9） Step 204: The actual range of the drone during the target attack mission cannot exceed the maximum range of the drone, that is: （10）。 4. The method for allocating ground attack tasks of a UAV cluster based on an improved particle swarm algorithm according to claim 1 is characterized in that: The movement of particles mainly depends on the current position and velocity of the particles. The position matrix and the velocity matrix The update formula is as follows: （12） in, and are the position and velocity matrices before updating, and are the updated position and velocity matrices, is the global optimal position under the current number of iterations, is the local optimal position under the current number of iterations, is the inertia coefficient, and is the learning factor, and The value range is A random number.

5. A system for allocating UAV swarm ground attack tasks based on an improved particle swarm algorithm according to any one of claims 1 to 4, the system comprising: The first building block establishes the objective function of the UAV swarm ground attack mission based on battlefield environment information; The second building block analyzes the constraints of target coverage, target damage effect, drone attack threshold, and drone range, and establishes a mathematical model for the allocation of drone swarm ground attack tasks based on the objective function. The processing module is used to solve the mathematical model using the improved particle swarm algorithm.

Images