Improved wolf swarm-based heterogeneous aircraft cooperative mission planning method

Abstract

This invention relates to a cooperative mission planning method for heterogeneous aircraft based on an improved wolf-pack algorithm. The purpose of this invention is to address the problem of low accuracy in multi-task allocation for existing heterogeneous aircraft, and to propose a cooperative mission planning method for heterogeneous aircraft based on an improved wolf-pack algorithm. The specific process of the cooperative mission planning method based on the improved wolf-pack algorithm is as follows: Step 1, constructing an optimal task allocation model for heterogeneous aircraft; Step 2, optimizing the optimal task allocation model for heterogeneous aircraft using an improved wolf-pack optimization algorithm to obtain the optimal task allocation scheme. This invention is applicable to the field of cooperative mission planning for heterogeneous aircraft.

Description

Technical Field

[0001] This invention relates to a method for collaborative mission planning of heterogeneous aircraft. Background Technology

[0002] Existing technologies do not fully leverage the ability of aircraft to perform heterogeneous and diversified missions, lack in-depth research on related heterogeneous mission planning issues, and fail to adequately consider various constraints of similar problems.

[0003] The wolf pack algorithm is simple and easy to implement, and is suitable for solving task allocation problems. However, it is highly dependent on the initial population distribution and uses a fixed step size in its walking strategy, which makes its optimization efficiency unstable and prone to getting trapped in local optima.

[0004] In summary, existing heterogeneous aircraft have low accuracy in multi-mission allocation. Summary of the Invention

[0005] The purpose of this invention is to solve the problem of low accuracy in multi-task allocation for existing heterogeneous aircraft, and to propose a collaborative mission planning method for heterogeneous aircraft based on an improved wolf pack.

[0006] The specific process of the heterogeneous aircraft cooperative mission planning method based on improved wolf packs is as follows:

[0007] Step 1: Construct an optimal mission allocation model for heterogeneous aircraft;

[0008] Step 2: The improved wolf pack optimization algorithm is used to optimize the heterogeneous aircraft mission allocation model to obtain the optimal mission allocation scheme.

[0009] The beneficial effects of this invention are as follows:

[0010] This invention considers an aircraft with large payload, long range, and high speed, capable of carrying various payloads or configuring internal space for personnel rescue and material delivery missions. It proposes an aircraft cooperative mission planning method based on an improved wolf pack approach, establishing an optimal allocation model for heterogeneous aircraft performing rescue or delivery missions, including a capability model, a reward model, and a constraint model. Addressing the problem of traditional wolf pack algorithms easily getting trapped in local optima, this invention proposes chaotic mapping and back-learning to achieve uniform initialization of the population. Simultaneously, it introduces the Lévy flight strategy and proposes a variable step-size search strategy based on the Mantegna algorithm to escape local optima, fully leveraging the aircraft's ability to perform heterogeneous and diverse missions and improving the accuracy of multi-mission allocation for heterogeneous aircraft.

[0011] This invention relates to an improved wolf pack-based collaborative mission planning method for heterogeneous aircraft. Considering multiple aircraft with different mission execution capabilities, an optimal allocation model for heterogeneous collaborative flight missions is established. Furthermore, a population initialization method based on chaotic mapping and back-learning, and a variable step-size walking strategy based on Levy flight are proposed to form an improved wolf pack optimization algorithm. This fully leverages the ability of aircraft to perform heterogeneous and diverse missions, improving the accuracy of multi-mission allocation for heterogeneous aircraft.

[0012] 1. Key technical points of the present invention

[0013] (1) Optimal multi-task allocation model for heterogeneous aircraft

[0014] Consider an aircraft with large payload, long range, and high speed, which can carry multiple payloads or configure internal space for personnel rescue missions and material delivery missions respectively. An optimal allocation model for heterogeneous aircraft to perform rescue or delivery missions is established, including a capability model, a reward model, and a constraint model.

[0015] (2) Improved Wolf Pack Algorithm Optimization Algorithm

[0016] We propose a population initialization method based on chaotic mapping and back learning, as well as a variable step size walking strategy based on Levy flight, to form an improved wolf pack optimization algorithm, which fully leverages the ability of the aircraft to perform heterogeneous and diversified tasks. Attached Figure Description

[0017] Figure 1 This is a flowchart of the improved wolf pack algorithm optimization algorithm of this invention. Detailed Implementation

[0018] Specific Implementation Method 1: This implementation method, based on an improved wolf pack-based heterogeneous aircraft cooperative mission planning method, specifically involves the following process:

[0019] Step 1: Construct an optimal multi-task allocation model for heterogeneous aircraft;

[0020] Step 2: The improved wolf pack optimization algorithm is used to optimize the multi-task optimal allocation model of heterogeneous aircraft to obtain the optimal task allocation scheme.

[0021] Specific Implementation Method Two: This implementation method differs from Specific Implementation Method One in that step one involves constructing a multi-task optimal allocation model for heterogeneous aircraft; the specific process is as follows:

[0022] (1) Suppose that N aircraft jointly perform M tasks;

[0023] The tasks are divided into rescue missions and deployment missions, denoted by K. i K indicates i =1 indicates a rescue mission, K i=2 indicates that the task is deployed, i = 1, 2, ..., M;

[0024] (2) The following assumptions are made regarding the aircraft mission allocation problem:

[0025] 1) It does not consider terrain obstacles and sudden threats;

[0026] 2) Spatial distance is represented by two-dimensional Euclidean distance;

[0027] 3) The destinations for each task remain stationary;

[0028] 4) The aircraft flies at a constant speed;

[0029] 5) The aircraft selects the mission closest to its current location as its next mission;

[0030] 6) The aircraft has no communication range or fuel limitations, and malfunction factors are not considered;

[0031] 7) Each mission must be carried out by exactly one aircraft;

[0032] (3) Establish the reward function for allocation (formulas (2) and (4)), considering:

[0033] 1) The aircraft swarm completes the mission the fastest;

[0034] 2) The aircraft cluster consumes the least total fuel;

[0035] Let the time taken for each rescue mission and deployment mission be T. save and T send ;

[0036] Let the time taken for each rescue mission and deployment mission be T. save and T send ;

[0037] Aircraft j needs to perform N save One rescue mission and N send There are N delivery tasks, where j = 1, 2, ..., N;

[0038] Total mission time T for aircraft j j for:

[0039]

[0040] Among them, T k-1:k T represents the time it takes for aircraft j to travel from the location of mission (k-1) to the location of mission k. 0:k This represents the time it takes for aircraft j to travel from its starting point to the location where it will perform mission k.

[0041] Based on the total mission time T of aircraft j jObtain the shortest time indicator for the entire aircraft cluster to complete its mission.

[0042] Because the aircraft flies at a constant speed, fuel consumption is directly proportional to the distance traveled.

[0043] Assuming fuel consumption per unit distance is 1, then the total mission distance D of aircraft j is... j for:

[0044]

[0045] in,

[0046] D k-1:k This represents the distance traveled by aircraft j from the location where mission (k-1) is performed to the location where mission k is performed;

[0047] D 0:k This represents the distance from the starting point to the location where task k is to be executed;

[0048] Based on the total mission distance D of aircraft j j To obtain the minimum fuel consumption index for the entire aircraft cluster to complete the final mission;

[0049] (4) Based on the shortest time index for the entire aircraft cluster to complete the task and the minimum fuel consumption index for the entire aircraft cluster to complete the task, the task allocation problem is obtained.

[0050] (5) In order to describe the heterogeneity of the mission, the ability of aircraft j to perform different missions is quantified by numbers between [0,1], j = 1,2,...,N;

[0051] If an aircraft carries detection and medical equipment but has limited cargo space, its rescue capability can be quantified as 0.9 and its delivery capability as 0.05; if an aircraft has a large internal space but no rescue equipment, its rescue capability can be quantified as 0.1 and its delivery capability as 0.9; if an aircraft combines rescue equipment and internal space, its rescue capability can be quantified as 0.6 and its delivery capability as 0.5.

[0052] Therefore, the aircraft performance matrix X is established;

[0053] At the same time, a lower limit for task capability requirements is set, and a capability lower limit matrix Y is established;

[0054] (6) Based on the aircraft performance matrix X and the capability lower limit matrix Y, construct the constraints for mission planning;

[0055] Thus, an integer programming problem model for time and fuel indicators and capacity constraints was established (Equations (1)-(8));

[0056] The other steps and parameters are the same as in Specific Implementation Method 1.

[0057] Specific Implementation Method 3: This implementation method differs from Specific Implementation Method 1 or 2 in that: in (3), the total mission time T based on aircraft j is... j Obtain the shortest time indicator for the entire aircraft cluster to complete its mission; the specific process is as follows:

[0058] The shortest time target for the entire aircraft cluster to complete its mission is:

[0059] min J time =max{T j |j=1,2...,N} (2)

[0060] Among them, J time This indicates the total mission time for the entire aircraft cluster.

[0061] Other steps and parameters are the same as in specific implementation method one or two.

[0062] Specific Implementation Method Four: This implementation method differs from one of the specific implementation methods one to three in that: in (3), the total mission distance D based on the aircraft j is... j Obtain the minimum fuel consumption index for the entire aircraft cluster to complete the final mission; the specific process is as follows:

[0063] The minimum fuel consumption target for the entire aircraft cluster to complete its mission is:

[0064]

[0065] Among them, J distance This represents the total mission distance of the entire aircraft cluster.

[0066] The other steps and parameters are the same as those in one of the specific implementation methods one to three.

[0067] Specific Implementation Method Five: This implementation method differs from Specific Implementation Methods One to Four in that: in (4), the task allocation problem is obtained based on the shortest time index for the entire aircraft cluster to complete the task and the minimum fuel consumption index for the entire aircraft cluster to complete the task; as shown below:

[0068] min J = aJ time +bJ distance

[0069]

[0070] in,

[0071] J represents the task assignment function;

[0072] a and b are the weighting coefficients for the equilibrium time and distance dimensions, respectively, satisfying a+b=1;

[0073] u ij This indicates whether the j-th spacecraft performs the i-th task; if it does, then u... ij =1, otherwise u ij =0;

[0074] u represents the discrimination matrix for whether the aircraft is performing a mission.

[0075] The other steps and parameters are the same as those in specific implementation methods one through four.

[0076] Specific Implementation Method Six: This implementation method differs from Specific Implementation Methods One to Five in that: In (5), the aircraft performance matrix X is established:

[0077]

[0078] in,

[0079] The first column represents the capability value of each aircraft to perform rescue missions;

[0080] The second column represents the capability value of each aircraft to perform delivery missions;

[0081] x 11 This represents the capability value of the first aircraft to perform a rescue mission, x. 21 This represents the capability value of the second aircraft to perform a rescue mission, x. N1 This represents the capability value of the Nth aircraft to perform a rescue mission;

[0082] x 12 This represents the capability value of the first aircraft to perform a delivery mission, x. 22 This represents the capability value of the second aircraft to perform the delivery mission, x. N2 This represents the capability value of the Nth aircraft to perform the delivery mission;

[0083] At the same time, a lower limit for task capability requirements is set, and a capability lower limit matrix Y is established:

[0084]

[0085] Among them, y i Let represent the lower limit of the required capability for the i-th task, where i = 1, 2, ..., M.

[0086] Different rescue or deployment missions have varying levels of difficulty and detail, thus requiring different minimum capability values ​​(y). i different.

[0087] The other steps and parameters are the same as those in specific implementation methods one through five.

[0088] Specific Implementation Method Seven: This implementation method differs from Specific Implementation Methods One through Six in that: in step (6), the constraints for mission planning are constructed based on the aircraft performance matrix X and the capability lower limit matrix Y; the specific process is as follows:

[0089] The constraints for task planning are expressed as follows:

[0090]

[0091] u ij =1 indicates that the j-th spacecraft performs the i-th mission, u ij When = 1, it represents the ability of aircraft j to perform rescue or deployment missions. It must be higher than the lower limit of the capability requirement for the i-th task. i ;

[0092] x represents j1 or x j2 ; j = 1, 2, ..., N.

[0093] The other steps and parameters are the same as those in one of the specific implementation methods one to six.

[0094] Specific Implementation Method Eight: This implementation method differs from Specific Implementation Methods One through Seven in that: in step two, an improved wolf pack optimization algorithm is used to optimize the multi-task optimal allocation model for heterogeneous aircraft to obtain the optimal task allocation scheme; the specific process is as follows:

[0095] The task allocation problem includes indicators, variables, and constraints; that is, under the constraints of Equation 8, we find u in Equation 5 such that J in Equation 5 is minimized.

[0096] Wolf packs rely on teamwork to hunt and obtain food, and are divided into alpha wolves, scout wolves, and predator wolves according to their individual roles.

[0097] There is competition within a wolf pack, which gradually eliminates inferior individuals. The main mechanisms are as follows:

[0098] 1) Alpha Wolf Generation: Individuals with the optimal objective function value are randomly selected if there are ties for first place. The alpha wolf is reselected in each iteration or replaced by other individuals during the hunting process.

[0099] 2) Wandering mechanism: Except for the alpha wolf, Q, which has a better objective function t Sekiro is a scout wolf, using a roaming stride length of S. t Wandering, among which Q t It is a random integer;

[0100] Wandering stride length S t Summoning Step S m Siege stride length S w It's a relative value, like S.t =2,S w =1,S m =3;

[0101] If the objective function value of the scout wolf exceeds that of the alpha wolf during the roaming process, the scout wolf becomes the new alpha wolf and performs the summoning action; otherwise, it continues to roam until the maximum number of roams is reached.

[0102] 3) Summoning behavior: After the alpha wolf issues the command, Q m Only a fierce wolf summons stride length S m Approach the alpha wolf. If the target function value of the wolf exceeds that of the alpha wolf during the approach, the wolf becomes the new alpha wolf and initiates a siege. Otherwise, continue approaching until the summoning distance threshold is reached.

[0103] 4) Encirclement and attack behavior: Detective wolves and ferocious wolves surround and attack with a stride length of S. w Explore around the alpha wolf and update the positions of the scout wolf and the ferocious wolf based on the criterion that the objective function values ​​of the scout wolf and the ferocious wolf are better.

[0104] 5) Elimination mechanism: Individuals with poor objective function values ​​will be eliminated and then redistributed to the solution space to form a new search group to participate in the next hunt. The number of eliminations is a random integer R. The more individuals are eliminated, the more the algorithm tends to random search and converges more slowly. Otherwise, the wolf pack tends to be stable and is prone to getting trapped in local optima.

[0105] like Figure 1 Based on the above description, an improved wolf pack algorithm optimization is proposed:

[0106] 1) Chaotic reverse learning initialization;

[0107] 2) Divide the wolf pack:

[0108] Calculate the task assignment function value for each individual wolf in the entire wolf pack and sort them in ascending order;

[0109] The wolf with the smallest task assignment function value is the alpha wolf. If there is a tie for first place, a wolf is randomly selected as the alpha wolf.

[0110] Except for the alpha wolf, the task allocation function value Q is smaller. t Sekiro's individual form is the Wolf Scout, Q t It is a random positive integer;

[0111] Apart from the alpha wolf and the scout wolf, all the others are fierce wolves;

[0112] There are at least 1 alpha wolf, at least 1 scout wolf, and at least 1 fierce wolf.

[0113] 3) Wandering behavior:

[0114] The alpha wolf gives the roaming command, and the scout wolves move with a stride of S. tThe roaming wolf scout determines whether its task allocation function value is less than that of the alpha wolf during the roaming process.

[0115] If the scout wolf's task allocation function value is less than that of the lead wolf during its roaming process, then the scout wolf replaces the lead wolf as the new lead wolf and immediately stops its roaming behavior, and executes step 4);

[0116] If the scout wolf's task allocation function value is greater than or equal to that of the lead wolf during its movement, then the scout wolf continues to move at a step length S. t Wander until the maximum number of wanders is reached, then execute step 4);

[0117] Here, the Mantegna algorithm is used to simulate Levi's flight, forming a flight pattern with a step size of S. t for:

[0118]

[0119] Among them, S t Let represent the roaming step size of the wolf, β be a random number between [0,2], round means rounding to the nearest integer, and μ and v be random numbers following a Gaussian distribution with variances σ and σ, respectively. μ and σ v :

[0120]

[0121] σ v =1

[0122] Where γ represents the gamma distribution;

[0123] 4) Summoning behavior:

[0124] The alpha wolf issues a summoning command, and the wolves summon with a stride length of S. m The wolf charges toward the alpha wolf, and during the charge, it checks whether the wolf's task allocation function value is less than that of the alpha wolf.

[0125] If the wolf's task allocation function value is less than that of the alpha wolf during its charge towards the alpha wolf, then the wolf replaces the alpha wolf as the new alpha wolf and immediately stops the summoning behavior, and executes step 5);

[0126] If the wolf's task allocation function value is greater than or equal to that of the alpha wolf during its charge towards the alpha wolf, then the wolf continues with a summoning step length S. m Charge toward the alpha wolf until the distance between the wolf and the alpha wolf is less than the summoning distance threshold, then execute step 5.

[0127] 5) Besieging behavior:

[0128] The alpha wolf issues the command to attack, and the scout wolves and the main wolves attack with a stride length of S. wExplore around the alpha wolf, and update the positions of the scout wolves and the ferocious wolves based on the smaller task allocation function value of the scout wolves and the fierce wolves. After the scout wolves and the fierce wolves update their positions, execute step 6).

[0129] 6) Elimination process:

[0130] Calculate the task assignment function value for each wolf, sort the task assignment function values ​​from smallest to largest, and eliminate the R wolves at the bottom of the list; R is a random integer.

[0131] 7) Repeat steps 2)-6) until the maximum number of iterations is reached to obtain the optimal task allocation function value, and obtain the optimal allocation scheme based on the optimal task allocation function value.

[0132] The optimal allocation model forms the foundation for the initial steps. Based on this, optimization algorithms are developed to solve for the optimal allocation scheme. For example, the allocation model identifies the optimization variables and indicators. The optimization variables represent the state of the wolf pack in the optimization algorithm. Each individual wolf corresponds to one indicator, and the optimal solution obtained by the entire wolf pack is the maximization / minimization of the corresponding indicator. The wolf pack continuously updates its own state, gradually improving the indicators—this is the optimization process.

[0133] The task allocation problem includes a reward (or indicator) (the reward is the task allocation function J in equation (5), a position (the discrimination matrix u of whether the aircraft performs the task in equation (5), and a constraint (equation 8); that is, under the constraint of equation 8, we find u in equation 5 so that J in equation (5) is minimized.

[0134] The other steps and parameters are the same as those in specific implementation methods one through seven.

[0135] Specific Implementation Method Nine: This implementation method differs from Specific Implementation Methods One through Eight in that: 1) Chaotic reverse learning initialization is performed; the specific process is as follows:

[0136] 1a) Generate a Tent random sequence:

[0137] For a scenario where N aircraft jointly perform M tasks, given a random number r1 between [0,1], the recursive method for the Tent random sequence is as follows:

[0138]

[0139] Where n represents the random number index, n = 1, 2, ..., Q / 2; ζ is a random number between [0, 0.1]; r n+1 Represents the (n+1)th random number; r n Represents the nth random number;

[0140] 1b) Population initialization;

[0141] 1c) Check constraints;

[0142] 1d) Determine the parameters: maximum number of iterations, maximum number of walks, summoning distance threshold, wolf pack update ratio, and summoning step size S. m and the siege stride length S w .

[0143] The other steps and parameters are the same as those in specific implementation methods one through eight.

[0144] Specific Implementation Method Ten: This implementation method differs from Specific Implementation Methods One through Nine in that: in 1b), population initialization:

[0145] 1b1) Considering the wolf pack size is Q, an initial wolf pack consisting of Q / 2 wolf individuals is generated based on the Tent random sequence, and the Q / 2 wolf individuals correspond to Q / 2 allocation results;

[0146] The wolf pack includes the position and reward (or indicator) of each individual wolf. The position of each individual wolf is the discrimination matrix u in Equation (5) indicating whether the aircraft is performing a task, and the reward is the task allocation function J in Equation (5).

[0147] The Q / 2 allocation results include Q / 2 discriminant matrices u for determining whether an aircraft performs a mission and Q / 2 mission allocation functions J;

[0148] Q / 2 u correspond to u1, u2, ..., u Q / 2 u1 is the discrimination matrix for whether the first spacecraft performs the mission, u2 is the discrimination matrix for whether the second spacecraft performs the mission, u Q / 2 Let Q / 2 be the discrimination matrix for determining whether the Q / 2th spacecraft performs its mission.

[0149] Q / 2 task allocation functions J correspond to J1, J2, ..., J..., respectively. Q / 2 J1 is the first task allocation function, J2 is the second task allocation function, J Q / 2 Assign a function to the Q / 2th task;

[0150] 1b2) Using a reverse learning strategy, the inverse solution is obtained for each wolf in the initial wolf pack consisting of Q / 2 wolf individuals generated in 1b1), resulting in Q / 2 inverse solutions, which correspond to Q / 2 allocation results;

[0151] The Q / 2 allocation results include Q / 2 discriminant matrices u for determining whether an aircraft performs a mission and Q / 2 mission allocation functions J;

[0152] Q / 2 u respectively correspond to u Q / 2+1 ,u Q / 2+2 ,…,u Q u Q / 2+1 Let u be the discrimination matrix for determining whether the Q / 2+1th spacecraft performs a mission.Q / 2+2 Let u be the discrimination matrix for determining whether the Q / 2+2th spacecraft performs its mission. Q Let be the discrimination matrix for whether the Q-th aircraft performs its mission;

[0153] Q / 2 task allocation functions J respectively correspond to J Q / 2+1 J Q / 2+2 ,…,J Q J Q / 2+1 Assign a function to the first task, J Q / 2+2 Assign a function to the second task, J Q Assign a function to the Q / 2th task.

[0154] The constraint check in 1c) is as follows:

[0155] Check the constraints; if u1, u2, ..., u Q If constraint (8) is satisfied, execute 2); otherwise, execute 1a) to 1b) until u1, u2, ..., u Q It satisfies constraint (8).

[0156] The other steps and parameters are the same as those in specific implementation methods one through nine.

[0157] This invention may have other embodiments. Without departing from the spirit and essence of this invention, those skilled in the art can make various corresponding changes and modifications according to this invention, but these corresponding changes and modifications should all fall within the protection scope of the appended claims.

Claims

1. A heterogeneous aircraft cooperative mission planning method based on improved wolf pack, characterized in that: The specific process of the method is as follows: Step 1: Construct an optimal mission allocation model for heterogeneous aircraft; Step 2: Optimize the heterogeneous spacecraft mission allocation model using an improved wolf pack optimization algorithm to obtain the optimal mission allocation scheme; Step one involves constructing an optimal mission allocation model for heterogeneous aircraft; the specific process is as follows: (1) Set M tasks are performed by the aircraft together; The task is divided into a rescue task and a drop task, and the type is indicated by , indicates a rescue task, indicates a drop task, ; (2) The following assumptions are made regarding the aircraft mission allocation problem: 1) It does not consider terrain obstacles and sudden threats; 2) Spatial distance is represented by two-dimensional Euclidean distance; 3) The destinations for each task remain stationary; 4) The aircraft flies at a constant speed; 5) The aircraft selects the mission closest to its current location as its next mission; 6) The aircraft has no communication range or fuel limitations, and malfunction factors are not considered; 7) Each mission must be carried out by exactly one aircraft; (3) Establish the reward function for allocation, considering: 1) The aircraft swarm completes the mission the fastest; 2) The aircraft cluster consumes the least total fuel; Let the time consumption of each rescue task and drop task be and respectively Aircraft Need to perform One rescue mission and One drop mission, wherein ; Aircraft total mission time is: （1） in, Indicates aircraft From executing tasks Fly to the location of the mission The place and time Indicates aircraft From the starting point to the execution of the task The location and time; Based on aircraft Total task time Obtain the shortest time indicator for the entire aircraft cluster to complete its mission. Assuming fuel consumption per unit distance is 1, then the aircraft Total mission route for: （3） in, Indicates aircraft From executing tasks Fly to the location to carry out the mission The distance to the location; Indicates the time from the starting point to the execution of the task. The distance to the location; Based on aircraft Total mission route To obtain the minimum fuel consumption index for the entire aircraft cluster to complete the final mission; (4) Based on the shortest time index for the entire aircraft cluster to complete the task and the minimum fuel consumption index for the entire aircraft cluster to complete the task, the task allocation problem is obtained. (5) The aircraft The ability to perform different tasks is quantified using numbers between [0,1]. ; Establish the aircraft performance matrix ; At the same time, a lower limit for task capability requirements is set, and a capability lower limit matrix Y is established; (6) Based on the aircraft performance matrix Using the lower limit matrix Y, we construct the constraints for task planning; This established a model for an integer programming problem with time, fuel, and capacity constraints.

2. The heterogeneous aircraft cooperative mission planning method based on improved wolf packs according to claim 1, characterized in that: The aircraft-based (3) mentioned above Total task time Obtain the shortest time indicator for the entire aircraft cluster to complete its mission; the specific process is as follows: The shortest time target for the entire aircraft cluster to complete its mission is: （2） in, This indicates the total mission time for the entire aircraft cluster.

3. The heterogeneous aircraft cooperative mission planning method based on improved wolf packs according to claim 2, characterized in that: The aircraft-based (3) mentioned above Total mission route Obtain the minimum fuel consumption index for the entire aircraft cluster to complete the final mission; the specific process is as follows: The minimum fuel consumption target for the entire aircraft cluster to complete its mission is: （4） in, This represents the total mission distance of the entire aircraft cluster.

4. The heterogeneous aircraft cooperative mission planning method based on improved wolf packs according to claim 3, characterized in that: The task allocation problem is obtained in (4) based on the shortest time index for the entire aircraft cluster to complete the task and the minimum fuel consumption index for the entire aircraft cluster to complete the task; it is expressed as follows: （5） in, This represents the task allocation function; and The weighting coefficients, respectively, for equilibrium time and distance, satisfy the following conditions: ; Indicates the first Does the aircraft execute the first...? One task, if executed... ,otherwise ; The discrimination matrix indicates whether the aircraft is performing a mission.

5. The heterogeneous aircraft cooperative mission planning method based on improved wolf packs according to claim 4, characterized in that: The aircraft performance matrix is ​​established in (5). : （6） in, The first column represents the capability value of each aircraft to perform rescue missions; The second column represents the capability value of each aircraft to perform delivery missions; This indicates the capability value of the first aircraft to perform a rescue mission. This indicates the capability value of the second aircraft to perform a rescue mission. Indicates the first The capability value of each aircraft to perform rescue missions; This indicates the capability value of the first aircraft to perform the delivery mission. This indicates the capability value of the second aircraft to perform the delivery mission. Indicates the first The capability value of an individual aircraft to perform a delivery mission; At the same time, a lower limit for task capability requirements is set, and a capability lower limit matrix Y is established: （7） in, Indicates the first The minimum required capabilities for each task .

6. The heterogeneous aircraft cooperative mission planning method based on improved wolf packs according to claim 5, characterized in that: The aircraft performance matrix mentioned in (6) Based on the capability lower limit matrix Y, the constraints for task planning are constructed; the specific process is as follows: The constraints for task planning are expressed as follows: （8） Indicates the first The aircraft performed the first One task, At that time, the aircraft Ability value for performing rescue or deployment missions It is higher than the first Minimum required capabilities for each task ; express or ; .

7. The heterogeneous aircraft cooperative mission planning method based on improved wolf packs according to claim 6, characterized in that: In step two, an improved wolf pack optimization algorithm is used to optimize the heterogeneous spacecraft mission allocation model to obtain the optimal mission allocation scheme; the specific process is as follows: 1) Chaotic reverse learning initialization; 2) Divide the wolf pack: Calculate the task assignment function value for each individual wolf in the entire wolf pack and sort them in ascending order; The wolf with the smallest task assignment function value is the alpha wolf. If there is a tie for first place, a wolf is randomly selected as the alpha wolf. Except for the alpha wolf, the task allocation function values ​​are relatively small. Sekiro is a lone wolf. It is a random positive integer; Apart from the alpha wolf and the scout wolf, all the others are fierce wolves; 3) Wandering behavior: The alpha wolf gives the command to roam, and the scout wolves move according to their stride length. The roaming wolf scout determines whether its task allocation function value is less than that of the alpha wolf during the roaming process. If the scout wolf's task allocation function value is less than that of the lead wolf during its roaming process, then the scout wolf replaces the lead wolf as the new lead wolf and immediately stops its roaming behavior, and executes step 4); If the scout wolf's task allocation function value is greater than or equal to that of the lead wolf during its movement, then the scout wolf continues to move at a certain step size. Wander until the maximum number of wanders is reached, then execute step 4); Wandering stride for: （10） in, Indicates the roaming stride length of a wolf. It is a random number between [0, 2]. This indicates rounding to the nearest integer. and It is a random number that follows a Gaussian distribution. and The variances are respectively and : （11） in, Indicates the gamma distribution; 4) Summoning behavior: The alpha wolf issues a summoning command, and the other wolves respond with a summoning stride. The wolf charges toward the alpha wolf, and during the charge, it checks whether the wolf's task allocation function value is less than that of the alpha wolf. If the wolf's task allocation function value is less than that of the alpha wolf during its charge towards the alpha wolf, then the wolf replaces the alpha wolf as the new alpha wolf and immediately stops the summoning behavior, and executes step 5); If the wolf's task allocation function value is greater than or equal to that of the alpha wolf during its charge towards the alpha wolf, then the wolf continues with the summoning stride length. Charge toward the alpha wolf until the distance between the wolf and the alpha wolf is less than the summoning distance threshold, then execute step 5. 5) Besieging behavior: The alpha wolf issues the command to attack, and the scout wolves and the main wolves attack in formation. Explore around the alpha wolf, and update the positions of the scout wolves and the ferocious wolves based on the smaller task allocation function value of the scout wolves and the fierce wolves. After the scout wolves and the fierce wolves update their positions, execute step 6). 6) Elimination process: Calculate the task assignment function value for each individual wolf, sort the task assignment function values ​​from smallest to largest, and eliminate those ranked lower. Individual wolf; It is a random integer; 7) Repeat steps 2)-6) until the maximum number of iterations is reached to obtain the optimal task allocation function value, and obtain the optimal allocation scheme based on the optimal task allocation function value.

8. The heterogeneous aircraft cooperative mission planning method based on improved wolf packs according to claim 7, characterized in that: The chaotic reverse learning initialization in step 1) is specifically as follows: 1a) Generate a Tent random sequence: for The two aircraft jointly carried out The scenario for each task is to first provide a random number between [0, 1]. The recursive method for the Tent random sequence is as follows: （9） in, The number representing the random number. ; It is a random number between [0, 0.1]. Representing the A random number; Representing the A random number; 1b) Population initialization; 1c) Check constraints; 1d) Determine the parameters: maximum number of iterations, maximum number of walks, summoning distance threshold, wolf pack update ratio, and summoning step size. and siege stride .

9. The heterogeneous aircraft cooperative mission planning method based on improved wolf packs according to claim 8, characterized in that: Population initialization in 1b): 1b1) Considering the size of the wolf pack as Generated based on Tent random sequence The initial wolf pack consisted of individual wolves. Each wolf corresponds to One allocation result; The wolf pack includes the position and reward of each individual wolf. The position of each individual wolf is the discrimination matrix in equation (5) indicating whether the aircraft is performing a mission. The reward is the task allocation function in equation (5). ; The allocation results include The discrimination matrix for determining whether an aircraft is performing a mission. and Task allocation function ; indivual Corresponding to , This is the discrimination matrix for determining whether the first spacecraft performs a mission. This is the discrimination matrix for determining whether the second spacecraft performs the mission. For the first A matrix for determining whether an aircraft is performing a mission; Task allocation function Corresponding to , Assign a function to the first task. Assign a function to the second task. For the first Task allocation function; 1b2) Using a reverse learning strategy to analyze the data generated in 1b1) In the initial wolf pack consisting of ... An inverse solution, Each inverse solution corresponds to One allocation result; The allocation results include The discrimination matrix for determining whether an aircraft is performing a mission. and Task allocation function ; indivual Corresponding to , For the first A matrix for determining whether an aircraft is performing a mission. For the first A matrix for determining whether an aircraft is performing a mission. For the first A matrix for determining whether an aircraft is performing a mission; Task allocation function Corresponding to , Assign a function to the first task. Assign a function to the second task. For the first Task allocation function; The constraint check in 1c) is as follows: Check the constraints, if If constraint (8) is satisfied, execute 2); otherwise, execute 1a) to 1b) until... It satisfies constraint (8).

Images