Fixed-wing UAV swarm inspection task planning optimization method and system based on ICBBA-IGJO

Abstract

This invention belongs to the technical field of drone swarm inspection task planning, specifically to an ICBBA-IGJO-based fixed-wing drone swarm inspection task planning optimization method and system. This method first uses an improved consensus bundling algorithm to generate an optimal task allocation plan for a fixed-wing drone swarm. Then, with the goal of minimizing the total inspection cost of the fixed-wing drone swarm, it constructs a drone swarm inspection path optimization model. Based on the optimal task allocation plan, the improved golden jackal optimization algorithm is used to solve the drone swarm inspection path optimization model and obtain the optimal inspection path. This invention achieves the combined optimization of fixed-wing drone swarm task allocation and path planning, thereby improving the intelligent operation and maintenance level of fixed-wing drone swarms.

Description

Technical Field

[0001] The present invention belongs to the technical field of UAV swarm inspection task planning, and specifically relates to an ICBBA-IGJO-based fixed-wing UAV swarm inspection task planning optimization method, system, equipment and medium. Background Art

[0002] Traditional inspection methods include manual inspections and helicopter inspections. However, inspection tasks are often complex, covering a wide and dispersed area. Furthermore, the complex terrain and inconvenient transportation in urban and mountainous areas make manual inspections difficult and inefficient. Using helicopters is costly and not conducive to large-scale inspections. Meanwhile, drones, as a form of modern aviation equipment, have played a vital role in many fields. Their advantages, such as low price, high maneuverability, strong timeliness, high probability line-of-sight channels, and high positioning accuracy, perfectly match inspection needs. Currently, drones have found some application in power inspections, supporting a "drone-based, manual supplementary" inspection strategy, and gradually evolving towards fully unmanned inspections.

[0003] The paper "Three-Dimensional UAV Path Planning Based on an Improved A* Algorithm" plans three-dimensional UAV paths based on an improved A* algorithm. It utilizes a variable-step search to improve the algorithm's search efficiency and designs a variable-weight path evaluation function for enhanced optimization. However, this method only addresses single-UAV path planning and two-dimensional path search. The paper "Task Allocation Method for Multi-UAV Disaster Damage Inspection in Distribution Networks Based on an Improved Particle Swarm" utilizes biological intelligence methods for task allocation. This method is a centralized setup, and while its logic is simple, it is not suitable for large-scale task allocation. The paper "Distributed multirobot task assignment via consensus ADMM" introduces the alternating direction multiplier method for distributed task allocation and experimentally demonstrates that the proposed method can converge to the optimal solution in most cases. This method can quickly provide an acceptable task allocation solution, but it does not consider path planning. Therefore, there is an urgent need to develop an optimization method suitable for task allocation and path planning in UAV swarms. Summary of the Invention

[0004] The purpose of the present invention is to address the above-mentioned problems existing in the prior art and provide a method, system, device and medium for optimizing inspection task planning of fixed-wing UAV swarms based on ICBBA-IGJO, which is suitable for task allocation and path planning of UAV swarms.

[0005] To achieve the above objectives, the technical solutions of the present invention are as follows:

[0006] In a first aspect, the present invention provides an ICBBA-IGJO-based fixed-wing UAV group inspection task planning optimization method, the optimization method comprising:

[0007] An improved consensus bundling algorithm is used to generate the optimal task allocation scheme for fixed-wing UAV swarms;

[0008] With the goal of minimizing the total cost of fixed-wing UAV swarm inspection, a UAV swarm inspection path optimization model is constructed;

[0009] Based on the optimal task allocation scheme, the improved golden jackal optimization algorithm is used to solve the drone swarm inspection path optimization model and obtain the optimal inspection path.

[0010] The improved consensus bundling algorithm includes:

[0011] S1, task package construction phase: construct the data structure required by the algorithm for the UAVs in the fixed-wing UAV group, the data structure includes UAV mission package , Execution path list , Winners List , Winning Price List , the task package Indicates the assignment to A collection of drone missions. The tasks are arranged in the order in which they are added, and the execution path list Indicates the The mission execution path of the UAV, The tasks are arranged in the order of task execution, and the winner list Indicates storage The drone serial number set that the drone believes has won the mission, the winning price list Indicates the The set of bid prices of the drones that the drones believe will win the mission;

[0012] S2, Task selection stage: collect the total number of tasks Divide into valid task sets and invalid task collection , with the goal of maximizing the total benefit of the fixed-wing UAV swarm, based on the greedy strategy from the effective task set Select the task to add to the task package middle;

[0013] S3, redundancy removal phase: winner list Each task in the is tested for validity. If the validity check fails, the task Unable to reach consensus through the preset conflict resolution rules, the task Classify into invalid task set If the task If the validity test is passed, it means that a consensus can be reached through the conflict resolution rules and the winning price will be listed. The drone number corresponding to the task is added to the list of valid winners. , and the winning price list The drone bid price corresponding to this task is added to the valid winner price list , then enter S4;

[0014] The validity test is performed according to the following formula:

[0015] ;

[0016] In the above formula, 、 All are indicator functions; To judge the A UAV and its adjacent drone in the communication topology Targeted missions between drones Whether the winner or winning price can reach a local consensus through conflict resolution rules; Used to determine the mission between all drones and their adjacent drones in the communication topology Whether the winner or winning price can reach a local consensus through conflict resolution rules;

[0017] S4. Conflict resolution stage: When a drone receives communication data from a drone adjacent to it in the communication topology, it updates its own timestamp. and based on the list of valid winners , effective winner price , timestamp Update, reset, propagate, or default using conflict resolution rules, and then update the data structure;

[0018] S5. Return to step S2 and iterate the calculation until the total benefit of the fixed-wing UAV swarm is maximized.

[0019] The total benefit of the fixed-wing UAV swarm is the sum of the benefits of all UAVs, and the functional expression of the benefits of the UAVs is:

[0020] ;

[0021] ;

[0022] In the above formula, For the The benefits of drones; For the The drones follow the execution path list Arrival Mission the time required; For the List of execution paths executed by drones Medium Task The income value; List of execution paths Medium Task Discount factor; List of execution paths Clustering benefits; 、 Points ,point Cluster categories; for point with dot The Euclidean distance between for point with dot The Euclidean distance between the cluster centers; points Indicates a new task added to the execution path list from the task package. Click Indicates the last mission or drone slot in a mission package; 、 are the gain constant and the attenuation constant respectively.

[0023] The total inspection cost of the fixed-wing UAV swarm includes the total flight length cost, average flight altitude cost, total time consumption cost, and total power consumption cost of the fixed-wing UAV swarm. The calculation formula for the total inspection cost of the fixed-wing UAV swarm is:

[0024] ;

[0025] ;

[0026] ;

[0027] ;

[0028] ;

[0029] ;

[0030] ;

[0031] In the above formula, is the total inspection cost of fixed-wing UAV swarm; is the total flight length cost of the fixed-wing UAV swarm; is the average flight altitude cost of a fixed-wing UAV swarm; is the total time consumption cost of the fixed-wing UAV swarm; is the total power consumption cost of the fixed-wing UAV swarm; 、 、 、 are the weight coefficients of the corresponding costs; For the drones, , is the total number of drones in the fixed-wing drone swarm; For the task To the task flight path; For the task To the task The Euclidean distance of For path The number of waypoints in ; is a binary decision variable, when the task and tasks All are drones The value is 1 when the task sequence is set, otherwise the value is 0; 、 Respectively represent the path Middle , The Z-axis coordinate of each path point; is the distance conversion coefficient; For drones Total flight distance; Assigned to drones after completing the task The number of tasks; For drones Total flight time; is the total number of missions for a single UAV; For drones Power consumption; is the power per unit distance of the UAV;

[0032] The constraints of the drone swarm inspection path optimization model include:

[0033] Safety distance constraints:

[0034] ;

[0035] In the above formula, For the drones, , Indicates drone With drones The distance between the drones With obstacles the distance between them; is the distance safety threshold.

[0036] The improved golden jackal optimization algorithm includes: firstly determining the positions of male and female jackals according to fitness values, wherein the male jackal is the jackal with the highest fitness value in the golden jackal population, and the female jackal is the jackal with the second highest fitness value in the golden jackal population; then determining the positions of male and female jackals according to the prey escape energy value; Determine the position update strategy, if the prey escapes energy satisfy , then the exploration strategy is used to update the relative positions of all jackal individuals and prey, otherwise the utilization strategy is used to update the relative positions of all jackal individuals and prey;

[0037] The prey escape energy The calculation formula is:

[0038] ;

[0039] ; ;

[0040] In the above formula, 、 are the escape random factor and the iteration number attenuation factor respectively; is a random value in (0, 1); is a constant; is the current iteration number; is the maximum number of iterations.

[0041] The relative position update formula in the exploration strategy is:

[0042] ;

[0043] ;

[0044] ;

[0045] ;

[0046] In the above formula, 、 Respectively represent male jackals and female jackals in the The relative position vector with the prey at the iteration; 、 Respectively represent male jackals and female jackals in the The position vector at the iteration; Indicates that the prey is Position vector at iteration ; represents the escape coefficient of the prey; represents a random number vector based on Levy distribution; For the golden jackal individual The relative position vector with the prey at the iteration; is the proportional balance factor; is a constant; is a random value in (0, 1).

[0047] The relative position update formula of the utilization strategy is improved by using the golden jackal observation strategy. The improved relative position update formula of the utilization strategy is:

[0048] ;

[0049] ;

[0050] ;

[0051] ;

[0052] ;

[0053] ;

[0054] ;

[0055] In the above formula, 、 Respectively represent male and female jackals in the The relative position vector with the prey at the iteration; 、 Respectively represent male jackals and female jackals in the The position vector at the iteration; 、 Respectively represent the position vectors of the male and female jackals after observation; 、 are the upper and lower bounds of the position respectively; is the attenuation factor; is the maximum number of iterations; is a random number that obeys the normal distribution; is a random number uniformly distributed between 0 and 1; For the golden jackal individual The relative position vector with the prey at the iteration; is the proportional balance factor; is a constant; is a random value in (0, 1).

[0056] In a second aspect, the present invention provides a fixed-wing UAV swarm inspection task planning optimization system based on ICBBA-IGJO, wherein the optimization system includes a task allocation module, a model building module, and a path optimization module;

[0057] The task allocation module is used to generate an optimal task allocation plan for the fixed-wing UAV group using an improved consensus bundling algorithm;

[0058] The model building module is used to build a drone swarm inspection path optimization model with the goal of minimizing the total inspection cost of the fixed-wing drone swarm;

[0059] The path optimization module is used to solve the drone group inspection path optimization model based on the optimal task allocation plan using the improved golden jackal optimization algorithm to obtain the optimal inspection path.

[0060] The task allocation module includes a task package construction submodule, a task selection submodule, a redundancy removal submodule, and a conflict resolution submodule;

[0061] The task package construction submodule is used to construct the data structure required by the algorithm for the UAVs in the fixed-wing UAV group, and the data structure includes the first UAV mission package , Execution path list , Winners List , Winning Price List , the task package Indicates the assignment to A collection of drone missions. The tasks are arranged in the order in which they are added, and the execution path list Indicates the The mission execution path of the UAV, The tasks are arranged in the order of task execution, and the winner list Indicates storage The drone serial number set that the drone believes has won the mission, the winning price list Indicates the The set of bid prices of the drones that the drones believe will win the mission;

[0062] The task selection submodule is used to set the total task Divide into valid task sets and invalid task collection , with the goal of maximizing the total benefit of the fixed-wing UAV swarm, based on the greedy strategy from the effective task set Select the task to add to the task package middle;

[0063] The redundancy removal submodule is used to list the winners Each task in the is tested for validity. If the validity check fails, the task Unable to reach consensus through the preset conflict resolution rules, the task Classify into invalid task set If the task If the validity test is passed, it means that a consensus can be reached through the conflict resolution rules and the winning price will be listed. The drone number corresponding to the task is added to the list of valid winners. , and the winning price list The drone bid price corresponding to this task is added to the valid winner price list ; The formula for the validity test is:

[0064] ;

[0065] In the above formula, 、 All are indicator functions; To judge the A UAV and its adjacent drone in the communication topology Targeted missions between drones Whether the winner or winning price can reach a local consensus through conflict resolution rules; Used to determine the mission between all drones and their adjacent drones in the communication topology Whether the winner or winning price can reach a local consensus through conflict resolution rules;

[0066] The conflict resolution submodule is used in the When a drone receives communication data from a drone adjacent to it in the communication topology, it updates its own timestamp. and based on the list of valid winners , effective winner price , timestamp The conflict resolution rules are used to update, reset, replace the propagation or keep the default operation, and then the data structure is updated. The updated data structure is input into the task selection submodule to continue iterative calculation until the total benefit of the fixed-wing UAV swarm is maximized.

[0067] The total benefit of the fixed-wing UAV swarm is the sum of the benefits of all UAVs, and the functional expression of the benefits of the UAVs is:

[0068] ;

[0069] ;

[0070] In the above formula, For the The benefits of drones; For the The drones follow the execution path list Arrival Mission the time required; For the List of execution paths executed by drones Medium Task The income value; List of execution paths Medium Task Discount factor; List of execution paths Clustering benefits; 、 Points ,point Cluster categories; for point with dot The Euclidean distance between for point with dot The Euclidean distance between the cluster centers; points Indicates a new task added to the execution path list from the task package. Click Indicates the last mission or drone slot in a mission package; 、 are the gain constant and the attenuation constant respectively.

[0071] The total inspection cost of the fixed-wing UAV swarm includes the total flight length cost, average flight altitude cost, total time consumption cost, and total power consumption cost of the fixed-wing UAV swarm. The calculation formula for the total inspection cost of the fixed-wing UAV swarm is:

[0072] ;

[0073] ;

[0074] ;

[0075] ;

[0076] ;

[0077] ;

[0078] ;

[0079] In the above formula, is the total inspection cost of fixed-wing UAV swarm; is the total flight length cost of the fixed-wing UAV swarm; is the average flight altitude cost of a fixed-wing UAV swarm; is the total time consumption cost of the fixed-wing UAV swarm; is the total power consumption cost of the fixed-wing UAV swarm; 、 、 、 are the weight coefficients of the corresponding costs; For the drones, , is the total number of drones in the fixed-wing drone swarm; For the task To the task flight path; For the task To the task The Euclidean distance of For path The number of waypoints in ; is a binary decision variable, when the task and tasks All are drones The value is 1 when the task sequence is set, otherwise the value is 0; 、 Respectively represent the path Middle , The Z-axis coordinate of each path point; is the distance conversion coefficient; For drones Total flight distance; Assigned to drones after completing the task The number of tasks; For drones Total flight time; is the total number of missions for a single UAV; For drones Power consumption; is the power per unit distance of the UAV;

[0080] The constraints of the drone swarm inspection path optimization model include:

[0081] Safety distance constraints:

[0082] ;

[0083] In the above formula, For the drones, , Indicates drone With drones The distance between the drones With obstacles the distance between them; is the distance safety threshold.

[0084] The improved golden jackal optimization algorithm includes: firstly determining the positions of male and female jackals according to fitness values, wherein the male jackal is the jackal with the highest fitness value in the golden jackal population, and the female jackal is the jackal with the second highest fitness value in the golden jackal population; then determining the positions of male and female jackals according to the prey escape energy value; Determine the position update strategy, if the prey escapes energy satisfy , then the exploration strategy is used to update the relative positions of all jackal individuals and prey, otherwise the utilization strategy is used to update the relative positions of all jackal individuals and prey;

[0085] The prey escape energy The calculation formula is:

[0086] ;

[0087] ; ;

[0088] In the above formula, 、 are the escape random factor and the iteration number attenuation factor respectively; is a random value in (0, 1); is a constant; is the current iteration number; is the maximum number of iterations.

[0089] The relative position update formula in the exploration strategy is:

[0090] ;

[0091] ;

[0092] ;

[0093] ;

[0094] In the above formula, 、 Respectively represent male jackals and female jackals in the The relative position vector with the prey at the iteration; 、 Respectively represent male jackals and female jackals in the The position vector at the iteration; Indicates that the prey is Position vector at iteration ; represents the escape coefficient of the prey; represents a random number vector based on Levy distribution; For the golden jackal individual The relative position vector with the prey at the iteration; is the proportional balance factor; is a constant; is a random value in (0, 1).

[0095] The path optimization module is further used to improve the relative position update formula of the utilization strategy using the golden jackal observation strategy. The improved relative position update formula of the utilization strategy is:

[0096] ;

[0097] ;

[0098] ;

[0099] ;

[0100] ;

[0101] ;

[0102] ;

[0103] In the above formula, 、 Respectively represent male and female jackals in the The relative position vector with the prey at the iteration; 、 Respectively represent male jackals and female jackals in the The position vector at the iteration; 、 Respectively represent the position vectors of the male and female jackals after observation; 、 are the upper and lower bounds of the position respectively; is the attenuation factor; is the maximum number of iterations; is a random number that obeys the normal distribution; is a random number uniformly distributed between 0 and 1; For the golden jackal individual The relative position vector with the prey at the iteration; is the proportional balance factor; is a constant; is a random value in (0, 1).

[0104] In the third aspect, the present invention also provides a fixed-wing UAV group inspection task planning optimization device based on ICBBA-IGJO, the optimization device including a memory and a processor; the memory is used to store computer program code and transfer the computer program code to the processor; the processor is used to execute the aforementioned optimization method according to the instructions in the computer program code.

[0105] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the aforementioned optimization method when executed by a processor.

[0106] Compared with the prior art, the present invention has the following beneficial effects:

[0107] 1. The present invention describes an ICBBA-IGJO-based fixed-wing UAV swarm inspection task planning optimization method. The method first uses an improved consensus bundling algorithm to generate an optimal task allocation plan for the fixed-wing UAV swarm. Then, with the goal of minimizing the total inspection cost of the fixed-wing UAV swarm, a UAV swarm inspection path optimization model is constructed. Based on the optimal task allocation plan, the improved golden jackal optimization algorithm is used to solve the UAV swarm inspection path optimization model to obtain the optimal inspection path. The above method achieves the combined optimization of task allocation and path planning for the fixed-wing UAV swarm, thereby improving the intelligent operation and maintenance level of the fixed-wing UAV swarm. Therefore, the present invention can achieve the combined optimization of task allocation and path planning for the fixed-wing UAV swarm, improving the intelligent operation and maintenance level of the fixed-wing UAV swarm.

[0108] 2. The present invention describes an ICBBA-IGJO-based fixed-wing UAV swarm inspection task planning optimization method. In the traditional consensus bundling algorithm, a redundancy removal stage is added to the task package construction stage. Each task in the winner list is tested for validity. Tasks that fail the validity test are divided from the valid task set to the invalid task set, thereby avoiding the continued processing of invalid tasks in the task selection stage in subsequent iterations, saving computing and communication bandwidth resources, reducing consensus costs, and accelerating algorithm convergence. Therefore, the present invention reduces consensus costs and accelerates algorithm convergence through the redundancy removal stage in task allocation optimization.

[0109] 3. The ICBBA-IGJO-based fixed-wing UAV swarm inspection task planning optimization method described in this invention utilizes a category-based reward system to improve the functional expression of UAV efficiency. In this category-based reward system, rewards are designed based on whether the new task added to the execution path list from the task package and the last task point or UAV slot in the task path list belong to the same cluster. This can prevent UAVs from adding distant tasks due to greedy strategies, which reduces the total efficiency of the fixed-wing UAV swarm and increases the total path length and total task time. Therefore, the present invention can ensure the total efficiency of the fixed-wing UAV swarm while reducing the total path length and total task time in task allocation optimization.

[0110] 4. The present invention describes an ICBBA-IGJO-based fixed-wing UAV swarm inspection mission planning optimization method. In an improved golden jackal optimization algorithm, the position update strategy is first determined based on the prey's escape energy, enabling adaptive adjustment of the search range to avoid falling into local optima and improve search accuracy. Secondly, a proportional balance factor is introduced into the position update formula to randomly adjust the contribution ratio of male and female jackals during each update process, providing more jump possibilities and preventing all individuals in the population from converging to the same solution, thereby reducing the risk of falling into local optima. Furthermore, a dynamic migration mechanism and a dynamic feedback migration mechanism are introduced into the relative position update formula of the utilization strategy to further enhance the population's ability to escape local optima. Therefore, the present invention can avoid falling into local optima during path planning optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0111] Figure 1 The figure is a flow chart of the optimization method of the present invention.

[0112] Figure 2 This is the path optimization result of the optimization method proposed in this invention.

[0113] Figure 3 This is a structural block diagram of the optimization system described in the present invention.

[0114] Figure 4 This is a structural block diagram of the optimization device described in the present invention. DETAILED DESCRIPTION

[0115] The present invention will be further described in detail below with reference to specific embodiments and the accompanying drawings.

[0116] Example 1:

[0117] See also Figure 1 ,A fixed-wing UAV swarm inspection task planning optimization method based on ICBBA-IGJO, follows the following steps in sequence:

[0118] Step 1: Generate an optimal task allocation plan for a fixed-wing UAV swarm using an improved consensus bundling algorithm (ICBBA). The traditional consensus bundling algorithm (CBBA) is divided into two phases: the first phase is the task package construction phase, and the second phase is the conflict resolution phase. The improved consensus bundling algorithm of the present invention first adds a redundancy removal phase after the first phase to eliminate potential non-conflicting tasks in advance; secondly, it uses a category-based reward system to improve the UAV benefit function; finally, in the conflict resolution phase, a new conflict resolution rule is established to achieve task allocation. The improved consensus bundling algorithm includes:

[0119] S1, task package construction phase: construct the data structure required by the algorithm for the UAVs in the fixed-wing UAV group, the data structure includes UAV mission package , Execution path list , Winners List , Winning Price List , the task package Indicates the assignment to A collection of drone missions. The tasks are arranged in the order in which they are added, and the execution path list Indicates the The mission execution path of the UAV, The tasks are arranged in the order of task execution, and the winner list Indicates storage The set of drone serial numbers that the drones believe to have won the mission is of size The matrix, The winning price list is the number of tasks currently being assigned. Indicates the The bid price set of the drone that the drone believes will win the task, and its elements are Corresponding; Example: Suppose there are currently 5 tasks being assigned {T1, T2, T3, T4, T5}, the winner list is [2, 1, 3, 5, 4], then is 5, and the drone numbers of each mission winner are 2, 1, 3, 5, and 4 respectively;

[0120] S2, Task selection stage: collect the total number of tasks Divide into valid task sets and invalid task collection , the UAV selects from the effective task set based on the greedy strategy Select the task to add to the task package In order to maximize the total benefit of the fixed-wing UAV swarm, the total benefit of the fixed-wing UAV swarm is the sum of the benefits of all UAVs. In order to prevent UAVs from adding distant tasks due to greedy strategies, reducing the total benefit of the fixed-wing UAV swarm and increasing the total path length and total task time, a category-based reward system is used to improve the functional expression of UAV benefits. In the category-based reward system, the task points and UAV nests are clustered indiscriminately using the Kmeans algorithm. The clustering results are used to determine whether the new task added from the task package to the execution path list and the last task point in the task path list belong to the same cluster. If the task path list is empty, it is determined whether the new task added from the task package to the execution path list and the UAV slot belong to the same category. The functional expression of the UAV benefit is:

[0121] ;

[0122] ;

[0123] In the above formula, For the The benefits of drones; For the The drones follow the execution path list Arrival Mission the time required; For the List of execution paths executed by drones Medium Task The income value; List of execution paths Medium Task Discount factor; List of execution paths Clustering benefits; 、 Points ,point The clustering category, Indicates a point with dot The cluster categories are the same, otherwise, Indicates a point with dot The cluster categories are different; for point with dot The Euclidean distance between for point with dot The Euclidean distance between the cluster centers; points Indicates a new task added to the execution path list from the task package. Click Indicates the last mission or drone slot in a mission package; 、 are gain constant and attenuation constant respectively;

[0124] S3, redundancy removal stage: The winner list is sorted according to the following formula Each task in is tested for validity:

[0125] ;

[0126] In the above formula, 、 All are indicator functions; To judge the A UAV and its adjacent drone in the communication topology Targeted missions between drones Whether the winner or winning price can reach a local consensus through conflict resolution rules; Used to determine the mission between all drones and their adjacent drones in the communication topology Whether the winner or winning price can reach a local consensus through conflict resolution rules;

[0127] If the task If the validity check fails, the task Unable to reach consensus through the preset conflict resolution rules, the task From the set of valid tasks Classify into invalid task set , and add it to the invalid task collection The end of the task selection phase in subsequent iterations can avoid continuing to process such invalid tasks, saving computing and communication bandwidth resources, avoiding unnecessary information transmission, and accelerating the convergence of the algorithm; invalid tasks include but are not limited to the following situations: 1. The resources required for the task, such as time and priority, cannot be met under the current conditions; 2. The execution order or dependency between tasks is not met; 3. The flight capability of the drone cannot meet the task; To ensure that all tasks can be assigned, invalid tasks may still be converted into valid tasks in subsequent iterations, and be included in the valid task set again and re-participate in the assignment; invalid tasks may be converted into valid tasks Situations include but are not limited to: 1. A task may become valid again when its status or conditions change, for example, the priority between tasks is met in this validity check; 2. A task was previously invalid due to reasons such as insufficient drone flight capability or task constraint conflict, and now due to the completion or cancellation of other tasks or changes in drone status, resources are released, which may allow the previously invalid task to become valid again; 3. The execution conditions of a task become more suitable for the current drone's capabilities, such as the task time window is adjusted or the distance between the task and the drone becomes suitable for allocation, at which point the task can be converted from invalid to valid;

[0128] If the task If the validity test is passed, it means that a consensus can be reached through the conflict resolution rules and it is necessary to continue to participate in subsequent communications. At this time, the winning price list will be The drone number corresponding to the task is added to the list of valid winners. , and the winning price list The drone bid price corresponding to this task is added to the valid winner price list , then enter S4;

[0129] S4. After removing redundant tasks, each drone will use the list of valid winners , effective winner price , timestamp Task information is propagated through conflict resolution rules; the conflict resolution phase is as follows:

[0130] First, when the When a drone receives communication data from a drone adjacent to it in the communication topology, it updates its own timestamp. :

[0131] ;

[0132] In the above formula, The time when the information was received; Indicates the communication matrix Rank The element value of the column is The first drone (recipient) and the The communication quality between two drones (senders). A larger value indicates more communication loss. The communication matrix The minimum value of the row, set the minimum value to point to drones; Indicates the communication matrix The timestamp pointed to by the maximum value of the row, let the maximum value point to the drone, then Indicates that the drone is received The communication data sent is from the drone timestamp;

[0133] Then, based on the list of valid winners , effective winner price , timestamp Update, reset, replace propagation, or retain by default through conflict resolution rules to propagate task information and subsequently update the data structure;

[0134] The conflict resolution rules are as shown in Table 1, where:

[0135] renew: ; ; 、 UAVs , drones Think Task The valid winner of 、 UAVs , drones Think Task The effective winner price of

[0136] Reset: ; ;

[0137] Replacement propagation: by drones As a sender;

[0138] Default retention: ; And wait for other drone senders to send information;

[0139] Table 1 Conflict resolution rules

[0140]

[0141] in 、 Respectively, upon receiving Communication data drone , drones timestamp;

[0142] S5. Return to step S2 and iterate the calculation until the total benefit of the fixed-wing UAV swarm is maximized;

[0143] Step 2: With the goal of minimizing the total inspection cost of fixed-wing UAV swarm, a UAV swarm inspection path optimization model is constructed. When the fixed-wing UAV swarm performs the inspection task, the allocation of its collaborative tasks is mainly affected by five factors, which are expressed as ;in Indicates the distribution network inspection task environment, the drone swarm in the environment Execute tasks in is the three-dimensional coordinate; For a given fixed-wing UAV swarm, in Indicates the drones; Represents the UAV mission set. Each UAV has a mission set. The mission set of a UAV can be expressed as , Indicates the total number of missions for a single UAV; Indicates the type of mission that the fixed-wing UAV swarm needs to perform; Indicates the UAV power, The power of a UAV is expressed as ;

[0144] The UAV swarm inspection path optimization model includes an objective function and a safety distance constraint. The objective function is to minimize the total inspection cost of the fixed-wing UAV swarm. The total inspection cost of the fixed-wing UAV swarm includes the total flight length cost, average flight altitude cost, total time consumption cost, and total power consumption cost of the fixed-wing UAV swarm. The calculation formula for the total inspection cost of the fixed-wing UAV swarm is:

[0145] ;

[0146] In the above formula, is the total inspection cost of fixed-wing UAV swarm; is the total flight length cost of the fixed-wing UAV swarm; is the average flight altitude cost of a fixed-wing UAV swarm; is the total time consumption cost of the fixed-wing UAV swarm; is the total power consumption cost of the fixed-wing UAV swarm; 、 、 、 are the weight coefficients of the corresponding costs;

[0147] During fixed-wing drone swarm inspections, shorter flight paths can save more energy and time, and stable flight altitudes can reduce the probability of multiple drones colliding with obstacles. 、 It can be expressed as:

[0148] ;

[0149] ;

[0150] In the above formula, For the drones, , is the total number of drones in the fixed-wing drone swarm; For the task To the task flight path; For the task To the task The Euclidean distance of For path The number of waypoints (i.e., tasks) in the game; is a binary decision variable, when the task and tasks All are drones The value is 1 when the task sequence is set, otherwise the value is 0; 、 Respectively represent the path Middle , The Z-axis coordinate of each path point;

[0151] Since each mission has a time limit, it is necessary to limit the inspection time of the drone; It can be expressed as:

[0152] ;

[0153] ;

[0154] In the above formula, is the distance conversion coefficient; For drones Total flight length; Assigned to drones after completing the task The number of tasks; For drones Total flight time; is the total number of missions for a single UAV;

[0155] Considering the power limitation of UAV, it is necessary to constrain the power consumption of UAV; It can be expressed as:

[0156] ;

[0157] ;

[0158] In the above formula, For drones Power consumption; is the power per unit distance of the UAV;

[0159] The safety distance constraint is:

[0160] ;

[0161] In the above formula, For the drones, ; Indicates drone With drones The distance between the drones With obstacles the distance between them; is the distance safety threshold;

[0162] Step 3: Based on the optimal task allocation plan, the improved golden jackal optimization algorithm (IGJO) is used to solve the drone swarm inspection path optimization model to obtain the optimal inspection path;

[0163] The improved golden jackal optimization algorithm includes: firstly determining the positions of male and female jackals according to fitness values, wherein the male jackal is the jackal with the highest fitness value in the golden jackal population, and the female jackal is the jackal with the second highest fitness value in the golden jackal population; then determining the positions of male and female jackals according to the prey escape energy value; Determine the position update strategy, adaptively adjust the search range, avoid falling into local optimality and improve search accuracy; if the prey escapes energy satisfy , then the exploration strategy is used to update the relative positions of all jackal individuals and prey. The exploration strategy tends to jump over a larger range, so that the jackal individuals tend to search farther areas, thus avoiding the population from falling into a local extreme value. If the prey can escape, , then the relative positions of all jackal individuals and prey are updated by using the strategy, and the strategy is used to make the jackal individual conduct a more detailed search near the current position, thereby improving the accuracy of the local solution; the prey escape energy The calculation formula is:

[0164] ;

[0165] ; ;

[0166] In the above formula, 、 are the escape random factor and the iteration number attenuation factor respectively; is a random value in (0, 1); is a constant; is the current iteration number; is the maximum number of iterations;

[0167] The relative position update formula in the exploration strategy is:

[0168] ;

[0169] ;

[0170] ;

[0171] ;

[0172] In the above formula, 、 Respectively represent male jackals and female jackals in the The relative position vector with the prey at the iteration; 、 Respectively represent male jackals and female jackals in the The position vector at the iteration; Indicates that the prey is Position vector at iteration ; represents the escape coefficient of the prey; represents a random number vector based on Levy distribution; For the golden jackal individual The relative position vector with the prey at the iteration; is the proportional balance factor; is a constant; is a random value in (0, 1);

[0173] The relative position update formula of the utilization strategy is improved by using the golden jackal observation strategy. The improved relative position update formula of the utilization strategy is:

[0174] ;

[0175] ;

[0176] ;

[0177] ;

[0178] ;

[0179] ;

[0180] ;

[0181] In the above formula, 、 Respectively represent male and female jackals in the The relative position vector with the prey at the iteration; 、 Respectively represent male jackals and female jackals in the The position vector at the iteration; 、 Respectively represent the position vectors of the male and female jackals after observation; 、 are the upper and lower bounds of the position respectively; is the attenuation factor; is the maximum number of iterations; is a random number that obeys the normal distribution; is a random number uniformly distributed between 0 and 1; For the golden jackal individual The relative position vector with the prey at the iteration; is the proportional balance factor; is a constant; is a random value in (0, 1);

[0182] In the exploration strategy and the relative position update formula of the utilization strategy, the proportional balance factor is introduced , so that during each update 、 The contribution ratio is random, which provides more jump possibilities. Even in the optimization within a small range, global exploration can be carried out through the guidance of suboptimal solutions, increasing the diversity of solutions and avoiding the situation where all individuals in the population tend to the same solution, thereby reducing the risk of falling into local optimality.

[0183] In the relative position update formula of the utilization strategy, 、 They represent the dynamic migration mechanism and the dynamic feedback migration mechanism respectively; the dynamic migration mechanism is used to guide golden jackal individuals to move from the local optimal area to other wider areas, so as to explore more solution space and prevent golden jackal individuals from staying near the local optimal solution for a long time; the dynamic feedback migration mechanism is to adjust the search strategy by feedbacking the current search effect during the optimization process, so that golden jackal individuals can more easily leave the current local optimal solution at the right time and search towards the direction of the global optimal solution; by introducing these two mechanisms, the ability of the population to jump out of the local optimal value is enhanced.

[0184] Performance Verification:

[0185] The optimization method proposed in this invention is compared with particle swarm optimization, mixed integer linear programming, ant colony algorithm, and reinforcement learning to calculate the total inspection cost of fixed-wing UAV swarm. The results are shown in Table 2:

[0186] Table 2 Comparison of total inspection costs of fixed-wing drone swarms

[0187]

[0188] As shown in Table 2, the total cost of fixed-wing UAV group inspection by the optimization method proposed in this invention is the lowest. Compared with particle swarm optimization, mixed integer linear programming, ant colony algorithm and reinforcement learning, it is 8454, 6005, 5992 and 4001 ahead respectively. The results show that the optimization method proposed in this invention can significantly reduce the total cost of UAV inspection. The path optimization results of the optimization method proposed in this invention are shown in Figure 2. Figure 2 As shown by Figure 2 It can be seen that the flight length of each UAV first increases and then shortens during the iterative process, and the iteration is completed in about two hundred times. The results show that the optimization method proposed in the present invention can effectively shorten the length of the UAV inspection path.

[0189] Example 2:

[0190] See also Figure 3 A fixed-wing UAV swarm inspection task planning and optimization system based on ICBBA-IGJO includes a task allocation module, a model building module, and a path optimization module; the task allocation module is used to generate an optimal task allocation plan for the fixed-wing UAV swarm using an improved consensus bundling algorithm; the model building module is used to construct a UAV swarm inspection path optimization model with the goal of minimizing the total inspection cost of the fixed-wing UAV swarm; the path optimization module is used to solve the UAV swarm inspection path optimization model based on the optimal task allocation plan using an improved golden jackal optimization algorithm to obtain the optimal inspection path;

[0191] Specifically, the task allocation module includes a task package construction submodule, a task selection submodule, a redundancy removal submodule, and a conflict resolution submodule; the task package construction submodule is used to construct the data structure required by the algorithm for the UAVs in the fixed-wing UAV group, and the data structure includes the first UAV mission package , Execution path list , Winners List , Winning Price List , the task package Indicates the assignment to A collection of drone missions. The tasks are arranged in the order in which they are added, and the execution path list Indicates the The mission execution path of the UAV, The tasks are arranged in the order of task execution, and the winner list Indicates storage The drone serial number set that the drone believes has won the mission, the winning price list Indicates the The set of bid prices of the drones that the drones believe will win the mission;

[0192] The task selection submodule is used to set the total task Divide into valid task sets and invalid task collection , with the goal of maximizing the total benefit of the fixed-wing UAV swarm, based on the greedy strategy from the effective task set Select the task to add to the task package The total benefit of the fixed-wing UAV group is the sum of the benefits of all UAVs, and the functional expression of the benefit of the UAV is:

[0193] ;

[0194] ;

[0195] In the above formula, For the The benefits of drones; For the The drones follow the execution path list Arrival Mission the time required; For the List of execution paths executed by drones Medium Task The income value; List of execution paths Medium Task Discount factor; List of execution paths Clustering benefits; 、 Points ,point Cluster categories; for point with dot The Euclidean distance between for point with dot The Euclidean distance between the cluster centers; points Indicates a new task added to the execution path list from the task package. Click Indicates the last mission or drone slot in a mission package; 、 are gain constant and attenuation constant respectively;

[0196] The redundancy removal submodule is used to list the winners Each task in the is tested for validity. If the validity check fails, the task Unable to reach consensus through the preset conflict resolution rules, the task Classify into invalid task set If the task If the validity test is passed, it means that a consensus can be reached through the conflict resolution rules and the winning price will be listed. The drone number corresponding to the task is added to the list of valid winners. , and the winning price list The drone bid price corresponding to this task is added to the valid winner price list ; The formula for the validity test is:

[0197] ;

[0198] In the above formula, 、 All are indicator functions; To judge the A UAV and its adjacent drone in the communication topology Targeted missions between drones Whether the winner or winning price can reach a local consensus through conflict resolution rules; Used to determine the mission between all drones and their adjacent drones in the communication topology Whether the winner or winning price can reach a local consensus through conflict resolution rules;

[0199] The conflict resolution submodule is used in the When a drone receives communication data from a drone adjacent to it in the communication topology, it updates its own timestamp. and based on the list of valid winners , effective winner price , timestamp Update, reset, replace propagation or default preservation through conflict resolution rules, then update the data structure, and input the updated data structure into the task selection submodule to continue iterative calculation until the total benefit of the fixed-wing UAV swarm is maximized;

[0200] Specifically, the drone swarm inspection path optimization model constructed by the model construction module includes an objective function and constraints. The objective function is to minimize the total inspection cost of the fixed-wing drone swarm. The total inspection cost of the fixed-wing drone swarm includes the total flight length cost, average flight altitude cost, total time consumption cost, and total power consumption cost of the fixed-wing drone swarm. The calculation formula for the total inspection cost of the fixed-wing drone swarm is:

[0201] ;

[0202] ;

[0203] ;

[0204] ;

[0205] ;

[0206] ;

[0207] ;

[0208] In the above formula, is the total inspection cost of fixed-wing UAV swarm; is the total flight length cost of the fixed-wing UAV swarm; is the average flight altitude cost of a fixed-wing UAV swarm; is the total time consumption cost of the fixed-wing UAV swarm; is the total power consumption cost of the fixed-wing UAV swarm; 、 、 、 are the weight coefficients of the corresponding costs; For the drones, , is the total number of drones in the fixed-wing drone swarm; For the task To the task flight path; For the task To the task The Euclidean distance of For path The number of waypoints in ; is a binary decision variable, when the task and tasks All are drones The value is 1 when the task sequence is set, otherwise the value is 0; 、 Respectively represent the path Middle , The Z-axis coordinate of each path point; is the distance conversion coefficient; For drones Total flight distance; Assigned to drones after completing the task The number of tasks; For drones Total flight time; is the total number of missions for a single UAV; For drones Power consumption; is the power per unit distance of the UAV;

[0209] The constraints include safety distance constraints:

[0210] ;

[0211] In the above formula, For the drones, , Indicates drone With drones The distance between the drones With obstacles the distance between them; is the distance safety threshold;

[0212] Specifically, the improved golden jackal optimization algorithm includes: first determining the positions of male and female jackals according to fitness values, wherein the male jackal is the jackal with the highest fitness value in the golden jackal population, and the female jackal is the jackal with the second highest fitness value in the golden jackal population; then determining the positions of male and female jackals according to the prey escape energy value; Determine the position update strategy, if the prey escapes energy satisfy , then the exploration strategy is used to update the relative positions of all jackal individuals and prey, otherwise the utilization strategy is used to update the relative positions of all jackal individuals and prey;

[0213] The prey escape energy The calculation formula is:

[0214] ;

[0215] ; ;

[0216] In the above formula, 、 are the escape random factor and the iteration number attenuation factor respectively; is a random value in (0, 1); is a constant; is the current iteration number; is the maximum number of iterations;

[0217] The relative position update formula in the exploration strategy is:

[0218] ;

[0219] ;

[0220] ;

[0221] ;

[0222] In the above formula, 、 Respectively represent male jackals and female jackals in the The relative position vector with the prey at the iteration; 、 Respectively represent male jackals and female jackals in the The position vector at the iteration; Indicates that the prey is Position vector at iteration ; represents the escape coefficient of the prey; represents a random number vector based on Levy distribution; For the golden jackal individual The relative position vector with the prey at the iteration; is the proportional balance factor; is a constant; is a random value in (0, 1);

[0223] Specifically, the path optimization module is further configured to utilize the golden jackal observation strategy to improve the relative position update formula of the utilization strategy. The improved relative position update formula of the utilization strategy is:

[0224] ;

[0225] ;

[0226] ;

[0227] ;

[0228] ;

[0229] ;

[0230] ;

[0231] In the above formula, 、 Respectively represent male and female jackals in the The relative position vector with the prey at the iteration; 、 Respectively represent male jackals and female jackals in the The position vector at the iteration; 、 Respectively represent the position vectors of the male and female jackals after observation; 、 are the upper and lower bounds of the position respectively; is the attenuation factor; is the maximum number of iterations; is a random number that obeys the normal distribution; is a random number uniformly distributed between 0 and 1; For the golden jackal individual The relative position vector with the prey at the iteration; is the proportional balance factor; is a constant; is a random value in (0, 1).

[0232] Example 3:

[0233] See also Figure 4 , a fixed-wing UAV group inspection task planning and optimization device based on ICBBA-IGJO, including a memory and a processor; the memory is used to store computer program code and transmit the computer program code to the processor; the processor is used to execute the optimization method described in Example 1 according to the instructions in the computer program code.

[0234] Example 4:

[0235] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the optimization method described in Example 1.

[0236] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0237] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0238] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0239] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0240] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. An ICBBA-IGJO-based fixed-wing UAV swarm inspection task planning optimization method is characterized by: The optimization method comprises: An improved consensus bundling algorithm is used to generate the optimal task allocation scheme for fixed-wing UAV swarms; With the goal of minimizing the total cost of fixed-wing UAV swarm inspection, a UAV swarm inspection path optimization model is constructed; Based on the optimal task allocation scheme, the improved golden jackal optimization algorithm is used to solve the drone swarm inspection path optimization model and obtain the optimal inspection path; The improved golden jackal optimization algorithm includes: firstly determining the positions of male and female jackals according to fitness values, wherein the male jackal is the jackal with the highest fitness value in the golden jackal population, and the female jackal is the jackal with the second highest fitness value in the golden jackal population; then determining the positions of male and female jackals according to the prey escape energy value; Determine the position update strategy, if the prey escapes energy satisfy , then the exploration strategy is used to update the relative positions of all jackal individuals and prey, otherwise the utilization strategy is used to update the relative positions of all jackal individuals and prey; The prey escape energy The calculation formula is: ； ； ； In the above formula, 、 are the escape random factor and the iteration number attenuation factor respectively; is a random value in (0, 1); is a constant; is the current iteration number; is the maximum number of iterations; The relative position update formula in the exploration strategy is: ； ； ； ； In the above formula, 、 Respectively represent male jackals and female jackals in the The relative position vector with the prey at the iteration; 、 Respectively represent male jackals and female jackals in the The position vector at the iteration; Indicates that the prey is Position vector at iteration ; represents the escape coefficient of the prey; represents a random number vector based on Levy distribution; For the golden jackal individual The relative position vector with the prey at the iteration; is the proportional balance factor; is a constant; is a random value in (0, 1).

2. The ICBBA-IGJO-based fixed-wing UAV swarm inspection task planning optimization method according to claim 1 is characterized by: The improved consensus bundling algorithm includes: S1, task package construction phase: construct the data structure required by the algorithm for the UAVs in the fixed-wing UAV group, the data structure includes UAV mission package , Execution path list , Winners List , Winning Price List , the task package Indicates the assignment to A collection of drone missions. The tasks are arranged in the order in which they are added, and the execution path list Indicates the The mission execution path of the UAV, The tasks are arranged in the order of task execution, and the winner list Indicates storage The drone serial number set that the drone believes has won the mission, the winning price list Indicates the The set of bid prices of the drones that the drones believe will win the mission; S2, Task selection stage: collect the total number of tasks Divide into valid task sets and invalid task collection , with the goal of maximizing the total benefit of the fixed-wing UAV swarm, based on the greedy strategy from the effective task set Select the task to add to the task package middle; S3, redundancy removal phase: winner list Each task in the is tested for validity. If the validity check fails, the task Unable to reach consensus through the preset conflict resolution rules, the task Classify into invalid task set If the task If the validity test is passed, it means that a consensus can be reached through the conflict resolution rules and the winning price will be listed. The drone number corresponding to the task is added to the list of valid winners. , and the winning price list The drone bid price corresponding to this task is added to the valid winner price list , then enter S4; perform validity check according to the following formula: ； In the above formula, 、 All are indicator functions; To judge the A UAV and its adjacent drone in the communication topology Targeted missions between drones Whether the winner or winning price can reach a local consensus through conflict resolution rules; Used to determine the mission between all drones and their adjacent drones in the communication topology Whether the winner or winning price can reach a local consensus through conflict resolution rules; S4. Conflict resolution stage: When a drone receives communication data from a drone adjacent to it in the communication topology, it updates its own timestamp. and based on the list of valid winners , effective winner price , timestamp Update, reset, propagate, or default using conflict resolution rules, and then update the data structure; S5. Return to step S2 and iterate the calculation until the total benefit of the fixed-wing UAV swarm is maximized.

3. The ICBBA-IGJO-based fixed-wing UAV swarm inspection task planning optimization method according to claim 2 is characterized by: The total benefit of the fixed-wing UAV swarm is the sum of the benefits of all UAVs, and the functional expression of the benefits of the UAVs is: ； ； In the above formula, For the The benefits of drones; For the The drones follow the execution path list Arrival Mission the time required; For the List of execution paths executed by drones Medium Task The income value; List of execution paths Medium Task Discount factor; List of execution paths Clustering benefits; 、 Points ,point Cluster categories; for point with dot The Euclidean distance between for point with dot The Euclidean distance between the cluster centers; points Indicates a new task added to the execution path list from the task package. Click Indicates the last mission or drone slot in a mission package; 、 are the gain constant and the attenuation constant respectively.

4. The ICBBA-IGJO-based fixed-wing UAV swarm inspection task planning optimization method according to claim 1 is characterized by: The total inspection cost of the fixed-wing UAV swarm includes the total flight length cost, average flight altitude cost, total time consumption cost, and total power consumption cost of the fixed-wing UAV swarm. The calculation formula for the total inspection cost of the fixed-wing UAV swarm is: ； ； ； ； ； ； ； In the above formula, is the total inspection cost of fixed-wing UAV swarm; is the total flight length cost of the fixed-wing UAV swarm; is the average flight altitude cost of a fixed-wing UAV swarm; is the total time consumption cost of the fixed-wing UAV swarm; is the total power consumption cost of the fixed-wing UAV swarm; 、 、 、 are the weight coefficients of the corresponding costs; For the drones, , is the total number of drones in the fixed-wing drone swarm; For the task To the task flight path; For the task To the task The Euclidean distance of For path The number of waypoints in ; is a binary decision variable, when the task and tasks All are drones The value is 1 when the task sequence is set, otherwise the value is 0; 、 Respectively represent the path Middle , The Z-axis coordinate of each path point; is the distance conversion coefficient; For drones Total flight distance; Assigned to drones after completing the task The number of tasks; For drones Total flight time; is the total number of missions for a single UAV; For drones Power consumption; is the power per unit distance of the UAV; The constraints of the drone swarm inspection path optimization model include: Safety distance constraints: ； In the above formula, For the drones, , Indicates drone With drones The distance between the drones With obstacles the distance between them; is the distance safety threshold.

5. The ICBBA-IGJO-based fixed-wing UAV swarm inspection task planning optimization method according to claim 1 is characterized by: The relative position update formula of the utilization strategy is improved by using the golden jackal observation strategy. The improved relative position update formula of the utilization strategy is: ； ； ； ； ； ； ； In the above formula, 、 Respectively represent male and female jackals in the The relative position vector with the prey at the iteration; 、 Respectively represent male jackals and female jackals in the The position vector at the iteration; 、 Respectively represent the position vectors of the male and female jackals after observation; 、 are the upper and lower bounds of the position respectively; is the attenuation factor; is the maximum number of iterations; is a random number that obeys the normal distribution; is a random number uniformly distributed between 0 and 1; For the golden jackal individual The relative position vector with the prey at the iteration; is the proportional balance factor; is a constant; is a random value in (0, 1).

6. The ICBBA-IGJO-based fixed-wing UAV swarm inspection mission planning and optimization system is characterized by: The optimization system includes a task allocation module, a model building module, and a path optimization module; The task allocation module is used to generate an optimal task allocation plan for the fixed-wing UAV group using an improved consensus bundling algorithm; The model building module is used to build a drone swarm inspection path optimization model with the goal of minimizing the total inspection cost of the fixed-wing drone swarm; The path optimization module is used to solve the drone group inspection path optimization model based on the optimal task allocation plan using the improved golden jackal optimization algorithm to obtain the optimal inspection path; The improved golden jackal optimization algorithm includes: firstly determining the positions of male and female jackals according to fitness values, wherein the male jackal is the jackal with the highest fitness value in the golden jackal population, and the female jackal is the jackal with the second highest fitness value in the golden jackal population; then determining the positions of male and female jackals according to the prey escape energy value; Determine the position update strategy, if the prey escapes energy satisfy , then the exploration strategy is used to update the relative positions of all jackal individuals and prey, otherwise the utilization strategy is used to update the relative positions of all jackal individuals and prey; The prey escape energy The calculation formula is: ； ； ； In the above formula, 、 are the escape random factor and the iteration number attenuation factor respectively; is a random value in (0, 1); is a constant; is the current iteration number; is the maximum number of iterations; The relative position update formula in the exploration strategy is: ； ； ； ； In the above formula, 、 Respectively represent male jackals and female jackals in the The relative position vector with the prey at the iteration; 、 Respectively represent male jackals and female jackals in the The position vector at the iteration; Indicates that the prey is Position vector at iteration ; represents the escape coefficient of the prey; represents a random number vector based on Levy distribution; For the golden jackal individual The relative position vector with the prey at the iteration; is the proportional balance factor; is a constant; is a random value in (0, 1).

7. ICBBA-IGJO-based fixed-wing UAV swarm inspection mission planning and optimization equipment, characterized by: The optimization device includes a memory and a processor; the memory is used to store computer program code and transmit the computer program code to the processor; the processor is used to execute the optimization method according to any one of claims 1 to 5 according to instructions in the computer program code.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the optimization method according to any one of claims 1 to 5.

Images