Ship helicopter group wave power-off and recovery task planning and scheduling method and ship helicopter group wave power-off and recovery task planning and scheduling system

Abstract

The invention discloses a method and system for planning and scheduling a ship helicopter group wave-order dispatching recovery task, and relates to the field of task planning, and the method comprises the steps: building a ship helicopter group wave-order dispatching recovery task planning model; the ship helicopter group wave order starting recovery task planning model comprises a logic constraint, a resource constraint and a target function; the logic constraints are process constraints of six stages of the helicopter and time sequence constraints of each stage; obtaining a dispatching and recycling task demand; and based on the dispatching and recycling task demand, solving the starting time and the ending time of six stages of the helicopter by adopting a competitive particle swarm algorithm of a hybrid elite variation strategy by taking logic constraint and resource constraint as constraint conditions and taking the minimum target function value as a target, so as to obtain an optimal task planning and dispatching scheme. The deck resource utilization rate and the task response efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of mission planning, and in particular to a method and system for planning and scheduling the wave-based dispatch and recovery missions of a ship helicopter group. Background Art

[0002] The rapid deployment and efficient recovery capabilities of ship-based helicopter fleets are the key strategic support for the aviation mission system, and their importance is self-evident. However, when performing missions, current offshore platforms are faced with a prominent contradiction between dynamic mission requirements and limited deck resources: in the vertical dimension, ship-based helicopters need to go through multiple operation stages such as transportation, support, deployment, and recovery; in the horizontal dimension, the traditional aviation operation scheduling model has significant limitations due to the nonlinear layout characteristics of the narrow and long deck space and the dynamic occupancy mode of multiple aircraft positions.

[0003] After a comprehensive analysis of the relevant technical system, there are currently three major problems: First, the deck operation space presents a highly unstructured feature, and the traditional modeling method based on regular grids is difficult to accurately depict the dynamic occupancy relationship of the aircraft positions; second, there are differentiated timing constraints and resource requirements in each operation stage, and there is a lack of a collaborative optimization framework throughout the entire process; finally, the mainstream rotation scheduling mechanism adopts a fixed cycle operation mode, which is difficult to cope with the dynamic needs of sudden task insertion and priority adjustment in the modern battlefield. Especially in a high-intensity confrontation environment, traditional solutions are very likely to cause problems such as reduced deck resource utilization and poor timeliness of task response delays. Summary of the invention

[0004] The purpose of this application is to provide a method, system, equipment, medium and product for planning and scheduling the wave-based recovery mission of a ship helicopter group, which can improve the utilization rate of deck resources and the efficiency of mission response.

[0005] To achieve the above objectives, this application provides the following solutions.

[0006] In a first aspect, the present application provides a method for planning and scheduling a wave-based recovery mission for a ship helicopter group, comprising the following steps.

[0007] A planning model for the wave dispatch and recovery mission of a ship-borne helicopter fleet is established; the planning model for the wave dispatch and recovery mission of a ship-borne helicopter fleet includes: logical constraints, resource constraints and objective functions; the logical constraints are the process constraints of the six stages of the helicopter and the timing constraints of each stage; the six stages of the helicopter include: pre-dispatch transportation stage, maintenance service support stage, dispatch departure stage, mission flight stage, recovery on-site stage and post-recovery transportation stage; the resource constraints are the constraints on the transportation equipment, support personnel and supply resources required for the helicopter; the objective function is composed of the task window satisfaction rate of the helicopter dispatch mission and the helicopter's deck operation time on the ship.

[0008] Obtain the requirements of the sortie and recovery mission; the requirements of the sortie and recovery mission include: a set of mission waves, a set of helicopters participating in the operation for each wave, the earliest start time and the latest start time of each wave mission.

[0009] Based on the requirements of the sortie and recovery mission, with logical constraints and resource constraints as the constraint conditions, and with the minimum objective function value as the goal, use the competitive particle swarm optimization algorithm with a hybrid elite mutation strategy to solve the start time and end time of the six stages of the helicopter, and obtain the optimal mission planning and scheduling plan; the competitive particle swarm optimization algorithm with a hybrid elite mutation strategy is an algorithm improved based on the particle swarm optimization algorithm using a competitive hybrid elite mutation strategy.

[0010] In a second aspect, the present application provides a ship helicopter group wave sortie and recovery mission planning and scheduling system, including the following modules.

[0011] A model establishment module for establishing a ship helicopter group wave sortie and recovery mission planning model; the ship helicopter group wave sortie and recovery mission planning model includes: logical constraints, resource constraints, and an objective function; the logical constraints are the process constraints of the six stages of the helicopter and the timing constraints of each stage; the six stages of the helicopter include, in sequence: the pre-sortie transportation stage, the aircraft maintenance support stage, the sortie departure stage, the mission flight stage, the recovery arrival stage, and the post-recovery transportation stage; the resource constraints are the constraints of the transportation equipment, support personnel, and supply resources required by the helicopter; the objective function is composed of the mission window satisfaction rate of the helicopter sortie mission and the deck operation time of the helicopter on the ship.

[0012] An acquisition module for obtaining the requirements of the sortie and recovery mission; the requirements of the sortie and recovery mission include: a set of mission waves, a set of helicopters participating in the operation for each wave, the earliest start time and the latest start time of each wave mission.

[0013] A mission planning and scheduling module for, based on the requirements of the sortie and recovery mission, with logical constraints and resource constraints as the constraint conditions, and with the minimum objective function value as the goal, using the competitive particle swarm optimization algorithm with a hybrid elite mutation strategy to solve the start time and end time of the six stages of the helicopter, and obtaining the optimal mission planning and scheduling plan; the competitive particle swarm optimization algorithm with a hybrid elite mutation strategy is an algorithm improved based on the particle swarm optimization algorithm using a competitive hybrid elite mutation strategy.

[0014] According to the specific embodiments provided by the present application, the present application has the following technical effects.

[0015] The present application provides a method and system for planning and scheduling the wave departure and recovery tasks of a shipborne helicopter group. Under the premise of resource constraints, through the process constraints of six stages of the helicopter and the timing constraints of each stage, the start and end times of each stage of the helicopter departure and recovery can be accurately constrained, so as to accurately calculate the start and end times of each stage of the helicopter. Then, by using the competitive particle swarm optimization algorithm with a hybrid elite mutation strategy, the start and end times of the six stages of the helicopter can be quickly solved, so as to obtain the mission window time of the helicopter departure mission and the time of the helicopter operating on the deck. At the same time, the competitive particle swarm optimization algorithm with a hybrid elite mutation strategy can accurately schedule the start and end times of the six stages of the helicopter, thereby improving the utilization rate of deck resources and the mission response efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] Figure 1 It is a schematic flowchart of a method for planning and scheduling the wave departure and recovery tasks of a shipborne helicopter group in an embodiment of the present application.

[0018] Figure 2 It is a schematic structural diagram of a system for planning and scheduling the wave departure and recovery tasks of a shipborne helicopter group in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0020] In the related art, traditional heuristic algorithms or single-stage optimization methods are adopted. Among them, traditional heuristic algorithms (such as genetic algorithms and simulated annealing) have certain applicability in solving complex optimization problems, but there are the following limitations: (1) High computational cost: Traditional heuristic algorithms usually require a large number of iterations and computational resources. Especially when dealing with large-scale multi-wave problems, the computational time may increase significantly; (2) Difficulty in handling complex constraints: For the multi-wave launch and recovery tasks of shipborne helicopter groups, it involves complex deck resource constraints, task time window constraints, and multi-stage operation logics. Traditional algorithms may be difficult to handle effectively. (3) Limited global optimization ability: Although algorithms such as genetic algorithms and simulated annealing have certain global search abilities, in complex task planning, they are prone to falling into local optimal solutions. Single-stage optimization methods (such as only optimizing the transportation or support stage) can improve efficiency in specific stages, but there are the following deficiencies: (1) Lack of global coordination: Single-stage optimization cannot consider the global constraints and mutual influences of the entire launch and recovery process, which may lead to low overall efficiency. (2) Inability to meet the requirements of the task time window: The satisfaction rate of the task time window is an important indicator for measuring the task planning of shipborne helicopter launch and recovery. Single-stage optimization is difficult to optimize the task time window globally. (3) Low resource utilization rate: Due to the lack of comprehensive optimization of the entire process, single-stage optimization may lead to unreasonable resource allocation, affecting the overall resource utilization rate.

[0021] The present application provides a method and system for planning and scheduling the multi-wave launch and recovery tasks of shipborne helicopter groups. Based on the requirements of the launch and recovery tasks, with logical constraints and resource constraints as the constraint conditions, and with the minimum objective function value as the goal, a competitive particle swarm algorithm with a hybrid elite mutation strategy is used to solve the start time and end time of the six stages of the helicopter, and an optimal task planning and scheduling scheme is obtained, which improves the deck resource utilization rate and task response efficiency.

[0022] In order to make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0023] In an exemplary embodiment, as Figure 1 shown, a method for planning and scheduling the multi-wave launch and recovery tasks of shipborne helicopter groups is provided. This method is executed by a computer device, and specifically, it can be executed independently by a computer device such as a terminal or a server, or jointly executed by a terminal and a server. In the embodiments of the present application, taking the application of this method to a server as an example for illustration, it includes the following steps 1 to step 3.

[0024] Step 1: Establish a mission planning model for the wave departure and recovery of shipborne helicopter groups; the mission planning model for the wave departure and recovery of shipborne helicopter groups includes: logical constraints, resource constraints, and objective functions; the logical constraints are the process constraints of the six stages of the helicopter and the timing constraints of each stage; the six stages of the helicopter include, in sequence: the pre-departure transportation stage, the maintenance and service support stage, the departure stage, the mission flight stage, the recovery approach stage, and the post-recovery transportation stage (i.e., the 1st stage to the 6th stage); the resource constraints are the constraints on the transportation equipment, support personnel, and supply resources required by the helicopter; the objective function is composed of the mission window satisfaction rate of the helicopter departure mission and the deck operation time of the helicopter on the ship.

[0025] Specifically, the logical constraints include: transportation stage constraints, maintenance and service support stage constraints, departure stage constraints, mission flight stage constraints, recovery approach stage constraints, and wave operation connection constraints.

[0026] Transportation stage constraints: This stage can be divided into the pre-departure transportation stage and the post-recovery transportation stage, but essentially it is a transfer from the initial parking position to the target parking position along a predetermined path. Since the path is composed of the pose at each moment, the transfer time is known when the path is determined. The constraints are expressed as follows.

[0027] .

[0028] Among them, is the end time of process , where is the th wave, the rd helicopter, in the th stage, and the th process; is the start time of process ; represents the th type and the th transportation equipment executing process , conversely , ; is the helicopter untethering time; is the time function for transporting the helicopter from parking position to parking position , corresponding to the selected path. Among them, is the initial parking position for executing process ; is the target parking position for executing process .

[0029] The collision avoidance problem during the transportation process can be regarded as an intersection problem of time and space. Given a fixed path, it is only necessary to ensure that the distance between the transportation helicopters at each moment is greater than the safety distance. The constraint is expressed as follows.

[0030] 。

[0031] Among them, is the function of the spatial occupancy point set of the th helicopter in the th wave at the moment; is the function of the spatial occupancy point set of the th helicopter in the th wave at the moment; is the preset safety distance, that is, the minimum distance that needs to be maintained during helicopter transportation.

[0032] Constraints in the aircraft maintenance support stage: The support can only start when the helicopter is located at the takeoff and landing area or the parking position in the parking area, and the support process has time sequence requirements and needs to be executed in a fixed order. The constraint is expressed as follows.

[0033] 。

[0034] 。

[0035] Among them, is the end time of process , where is the th helicopter in the th wave in the second stage of the th process; is the start time of process ; is the support time of process ; is the th helicopter in the th wave in the second stage of the th process. For , among them, is the set of immediate predecessor processes of process .

[0036] Constraints in the takeoff and departure stage: After the helicopter completes all operation supports at the takeoff and landing parking position, it can take off and leave according to the plan arrangement. No additional resource allocation is required in this stage. The constraint is expressed as follows.

[0037] 。

[0038] Among them, is the end time of process , where is the th wave th helicopter in the th process of the 3rd stage; is the start time of process ; is the departure time of the helicopter.

[0039] Task flight phase constraint: Only the established flight time needs to be considered in this phase, and the constraint is expressed as follows.

[0040] .

[0041] Among them, is the end time of process , where is the th wave th helicopter in the th process of the 4th stage; is the start time of process ; is the th wave helicopter flight time.

[0042] Recovery approach phase constraint: When the takeoff and landing apron is idle, the helicopter can recover and land on the ship. No additional resource allocation is required in this phase, and the constraint is expressed as follows.

[0043] .

[0044] Among them, is the end time of process , where is the th wave th helicopter in the th process of the 5th stage; is the start time of process ; is the helicopter recovery approach time.

[0045] Wave operation connection constraint: In one takeoff and recovery wave of the helicopter, it needs to go through six different phases, and the start and end times of each phase are strictly constrained by time sequence. If the helicopter is only guaranteed in the deck takeoff and landing area, it needs to execute each phase in sequence, and the constraint is expressed as follows.

[0046] .

[0047] Among them, is the process The end time; is the end time of the process , where is the th wave the th helicopter at the th process in the

[0048] In addition, since the helicopter's takeoff, recovery, and landing are all completed in the takeoff and landing area and cannot occupy the parking position at the same time, the takeoff and recovery times of adjacent wave helicopters need to be reasonably planned, and the constraints are expressed as follows.

[0049] .

[0050] Among them, is an arbitrary real number to ensure the inequality holds; means that after the th wave helicopter's 5th stage process is executed, then the th wave helicopter's 3rd stage process is executed; means the start time of the process , is in the special case of the th wave th helicopter at the 3rd stage of the th process, where is the th wave th helicopter at the stage of the th process.

[0051] Specifically, the resource constraints include: transportation equipment constraints, support personnel constraints, support equipment constraints, supply resource constraints, and resource allocation constraints.

[0052] Transportation equipment constraints: During the transportation process of the helicopter, it needs to be completed jointly with the tractor or elevator. Limited by the single traction capacity, after the transportation equipment completes one operation, it must be transferred to the parking position of the next helicopter to be transported, so as to start a new round of operations. The constraints are expressed as follows.

[0053] .

[0054] Among them, is the time for the th type of transportation equipment to transfer from the aircraft position to the aircraft position , , where For the initial position of the execution process ; Indicates the th th material handling equipment has completed the process and then executes the process , and vice versa , ; Is the start time of the process .

[0055] Personnel guarantee constraint: The execution of the guarantee process involves multiple professional fields and corresponding personnel configurations. The guarantee personnel need to complete a series of processes in a fixed order. Since this process may belong to different helicopters, after each process is completed, it needs to be transferred to the parking position where the next process is located. The constraint is expressed as follows.

[0056] .

[0057] Among them, Is the time for the th category of guarantee personnel to transfer from the position to the position . Among them, Is the target position for the execution of the process , Is the initial position for the execution of the process , Is the nd th helicopter in the th process in the second stage; Is the start time of the process ; Indicates that the process Is guaranteed by the th th guarantee personnel, otherwise .

[0058] In addition, due to the limited space carrying capacity of the guarantee workstations, only a certain number of guarantee personnel can work at the same time. The constraint is expressed as follows.

[0059] .

[0060] Among them, Is Indicates that the execution of the process Requires the th category of workstation space, otherwise ; Is the execution process The required number of support personnel for Category For the wave The number of support personnel that can be accommodated simultaneously in the work space of the th helicopter.

[0061] Support equipment constraint: The support equipment is deployed at a specific location on the deck and provides support services for the helicopters at the parking positions within its coverage area. The constraint is expressed as follows.

[0062] .

[0063] Among them, Indicates that the th support equipment of category executes process and then executes process , and vice versa ; Indicates that the parking position can be covered by the th support equipment of category , otherwise .

[0064] In addition, according to the equipment characteristics, the support equipment can also be divided into two categories: shared and exclusive. For shared equipment, during the support period, it can provide services for all the processes that require this equipment for this helicopter. The constraint is expressed as follows.

[0065] .

[0066] Among them, is the number of support equipment of category required for executing process .

[0067] For exclusive equipment or shared equipment that provides support services for different helicopters, it can only provide services for a single process, i.e., plug-and-play, and needs to be reset after each use to ensure subsequent processes. The constraint is expressed as follows.

[0068] .

[0069] Among them, is the time when the interface of the support equipment of category transfers from the parking position to the parking position ; is; is the start time of process ; Indicates Class Ensure that the equipment completes the process Post-execution process ,on the contrary .

[0070] Supply resource constraints: The normal operation of the support equipment is inseparable from the corresponding supply resources. Although it is assumed that there are sufficient resources on board, the instantaneous supply capacity of resources is limited, that is, at the same time, the support equipment can be as follows.

[0071] .

[0072] in, Indicates Class Each protection device needs to consume Class supply resources, otherwise ; For the The maximum number of processes that a supply resource can guarantee simultaneously.

[0073] Resource allocation constraints: During deck operations, it is necessary to configure and use resources such as transportation equipment, support personnel, and support equipment to ensure that process requirements and resource supply are accurately matched. The constraints are expressed as follows.

[0074] .

[0075] .

[0076] .

[0077] in, For the Class Each transport equipment performs the process ,on the contrary , ; Indicates the process By Class A security personnel guarantee, otherwise ; Indicates the process By Class A guarantee device guarantee, otherwise .

[0078] Mission time window satisfaction rate and deck operation time: In helicopter sortie missions, the mission time window satisfaction rate is a key performance indicator that measures the ability of a helicopter sortie mission to be completed within a predetermined time window. This goal reflects sortie efficiency and the reliability of the plan, denoted by as follows.

[0079] On the premise of ensuring the mission completion rate, the helicopter sortie rate and mission response speed of the ship should be increased as much as possible, and the deck operation time of the fleet should be reduced. Considering that in the operation process of each wave, only the three stages of pre-sortie transportation, aircraft maintenance support, and post-recovery transportation require decision-making, therefore, the deck operation time can be expressed as the sum of the time required for these three stages in all waves, denoted by as follows.

[0080] To comprehensively consider the two goals, a linear weighting method is adopted to combine them into a single objective function, enabling the optimization algorithm to find the best trade-off solution during the search process, denoted by as follows. Each stage of each helicopter includes multiple processes; the calculation formula of the objective function is as follows.

[0081] .

[0082] .

[0083] .

[0084] .

[0085] .

[0086] Among them, is the objective function value; and are both weight values; is the maximum value of the mission window satisfaction rate of the helicopter sortie mission; is the minimum value of the mission window satisfaction rate of the helicopter sortie mission; is the mission window satisfaction rate of the helicopter sortie mission; is the deck operation time of the helicopter on the ship; is the maximum value of the deck operation time of the helicopter on the ship; is the minimum value of the deck operation time of the helicopter on the ship; is the mission window satisfaction condition for the th wave. If is within the mission window, it is defined as meeting the mission time window, the mission window satisfaction rate; is the set of mission waves; is the earliest start time of the wave mission; is the start time of the th helicopter in the th process of the 4th stage; is the latest start time of the wave mission; is the end time of the th helicopter in the th process of the 2nd stage; is the start time of the th helicopter in the th process of the 1st stage; is the end time of the th helicopter in the th process of the 6th stage; is the start time of the th helicopter in the

[0087] th process of the 6th stage.

[0087] Step 2: Obtain the mission requirements for takeoff and recovery; the mission requirements for takeoff and recovery include: a set of mission waves, a set of helicopters participating in the operation for each wave, the earliest start time and the latest start time of each wave mission. In addition, the mission requirements for takeoff and recovery also include: a set of processes for each helicopter in six stages; a set of processes that can be guaranteed by the deck parking area; a path library between different parking positions; the operation time of each process; a set of resource types and quantities required for each process; the safe distance for transportation; a set of transportation equipment types and the quantity of each type; a set of support personnel types and the quantity of each type; a set of support equipment types and the quantity of each type; a set of supply resource types and the maximum quantity for guaranteeing processes; a set of station space types; the earliest start time and the latest start time of each wave mission.

[0088] Step 3: Based on the mission requirements for takeoff and recovery, with logical constraints and resource constraints as the constraint conditions, and with the minimum objective function value as the goal, use the competitive particle swarm optimization algorithm with a hybrid elite mutation strategy to solve the start time and end time of the six stages of the helicopter, and obtain the optimal mission planning and scheduling scheme; the competitive particle swarm optimization algorithm with a hybrid elite mutation strategy is an algorithm improved based on the particle swarm optimization algorithm using a competitive hybrid elite mutation strategy. Each wave includes multiple helicopters. Step 3 specifically includes the following steps 31 to 37.

[0089] Step 31: Use random numbers to encode each process in the pre-mobilization transportation stage, each process in the aircraft maintenance support stage, and each process in the post-recovery transportation stage of the mobilization and recovery mission requirements, obtaining multiple encoded individuals, and the multiple encoded individuals form an initial population.

[0090] Step 32: Determine the priority of each encoded individual according to the size of the random number.

[0091] Step 33: Sort each encoded individual according to the priority of each encoded individual, obtaining multiple sorted encoded individuals.

[0092] Specifically, the method of using priority encoding is as follows: Each encoded individual is divided into multiple waves, each wave is three-segment encoding, and all three segments of encoding use priorities. The smaller the number, the higher the priority.

[0093] The first segment of encoding is the pre-mobilization transportation priority encoding of the helicopter, expressed as a vector , indicating the th wave, the th helicopter, and the priority of the th process in the pre-mobilization transportation stage.

[0094] The second segment of encoding is the aircraft maintenance support priority encoding of the helicopter, which is a vector , indicating the th wave, the th helicopter, and the priority of the th process in the aircraft maintenance support stage.

[0095] The third segment of encoding is the post-recovery transportation priority, which is a vector , indicating the th wave, the th helicopter, and the priority of the th process in the post-recovery transportation stage.

[0096] In the above formula, indicates the number of helicopters participating in the operation in the th wave. For example, indicates the number of helicopters participating in the operation in the 1st wave; indicates the th wave, the th aircraft, and the number of processes in the th stage (i.e., the six stages of the helicopter). For example, indicates the number of processes of the th aircraft in the 2nd stage (i.e., the aircraft maintenance support stage) in the 1st wave. The vector composed of the three segments of encoding is an encoded individual.

[0097] Step 34: With logical constraints and resource constraints as constraints, a serial scheduling mechanism is used to decode each sorted coded individual to obtain multiple task planning and scheduling schemes; the task planning and scheduling schemes include: the start and end time of the pre-dispatch transportation phase, the start and end time of the maintenance and service support phase, and the start and end time of the post-recovery transportation phase; each task planning and scheduling scheme corresponds to a decoding individual, and multiple decoding individuals form a first population. Step 34 specifically includes the following steps 341 to 343.

[0098] Step 341: Based on the earliest start time of each wave, calculate the planned dispatch operation end time and planned recovery operation start time of each wave, and arrange them in ascending order by time to generate an operation set; the dispatch operation includes: pre-dispatch transportation stage, maintenance service support stage and dispatch departure stage; the recovery operation includes: recovery on-site stage and post-recovery transportation stage.

[0099] Specifically, based on the earliest execution time of the wave task To calculate the end time of the planned dispatch operation of the wave and the scheduled recycling job start time , and generate a job set by arranging the job time of each wave in ascending order .

[0100] In chronological order For each dispatch operation, the actual dispatch operation end time of the wave is determined by executing the dispatch operation decoding in step 342. and the actual recycling operation start time ,like If the scheduling order of the job is changed, update For the recovery operation, update the decision variables and When it is a recovery operation, it is necessary to first decide the transportation area of ​​the helicopter after recovery according to the subsequent operation type, that is, the helicopter that needs to perform the mission again can park directly in the take-off and landing area, otherwise it must leave the take-off and landing area, and then execute the recovery operation decoding in step 342 to update the decision variables and Step 342 is repeated until all jobs are scheduled.

[0101] Step 342: In the order of priority of each coded individual, with logical constraints and resource constraints as constraints, decode each process of each stage in the dispatching operation and recycling operation of each coded individual, and determine the start time and end time of each stage in the dispatching operation and recycling operation of each decoded individual.

[0102] Specifically, for the dispatch operation decoding, it is divided into three steps in total. The first step: Define the time variable , the scheduled set , the process index flag ; The second step: Ascendingly sort the two-layer encoding and in the dispatch operation stage to generate the set ; The third step: Select the process with the highest priority from , and calculate its wave number , helicopter number , process number and stage . If this process meets the scheduling conditions (that is, all its preceding processes have been scheduled and there is no blocked path during the pre-dispatch transportation stage), then determine the earliest feasible time that meets all the constraints of its stage, and update the decision variables of each stage of each helicopter in each wave number and . Repeat this process until all processes have been scheduled.

[0103] Specifically, for the recovery operation decoding, it is divided into three steps in total. The first step is to define the time variable , the scheduled set , the process index flag ; The second step is to ascendingly sort the encoding in the recovery operation stage to generate the set ; The third step is to select the process with the highest priority from , calculate its wave number , helicopter number , process number and stage . If this process meets the scheduling conditions (that is, all its preceding processes have been scheduled and there is no blocked path during the post-recovery transportation stage), then determine the earliest feasible time that meets all the constraints of its stage, and then update the decision variables of each stage of each helicopter in each wave number and . Repeat this process until all processes have been scheduled.

[0104] Step 343: According to the start time and end time of each stage in the dispatch operation and recovery operation of each decoded individual, determine the task planning and scheduling scheme corresponding to each decoded individual, and obtain multiple task planning and scheduling schemes.

[0105] Step 35: Calculate the start time and end time of the departure stage, the start time and end time of the mission flight stage, and the start time and end time of the recovery approach stage based on the start time and end time of the pre-deployment transportation stage, the start time and end time of the aircraft maintenance support stage, and the start time and end time of the post-recovery transportation stage.

[0106] Step 36: Calculate the objective function value of each decoded individual based on the start time and end time of the mission flight stage, the start time and end time of the pre-deployment transportation stage, the start time and end time of the aircraft maintenance support stage, and the start time and end time of the post-recovery transportation stage.

[0107] Step 37: Determine whether the current iteration round has reached the preset maximum iteration round; if so, determine the decoded individual with the minimum objective function value as the optimal mission planning and scheduling scheme; if not, optimize the first population using a particle swarm with a hybrid elite mutation strategy to obtain a subpopulation, re-decode the subpopulation, and calculate the objective function value of each encoded individual in the subpopulation.

[0108] In an exemplary example, optimizing the first population using a particle swarm with a hybrid elite mutation strategy in Step 37 to obtain a subpopulation specifically includes the following Steps 371 to 376.

[0109] Step 371: Randomly generate a certain number of particles and add them to the first population to obtain a second population; one particle is an encoded individual.

[0110] Specifically, randomly generate a certain number of particles, each particle being an individual representing a potential solution and having attributes of position (i.e., a random number) and velocity (i.e., the change amount used to calculate the random number). The position represents the parameter value of the solution, and the velocity determines the moving direction and step size of the particle in the solution space. Update the velocity and position of each particle based on the particle's own experience and the experience of the group, and then generate new offspring. The velocity update formula is as follows.

[0111] 。

[0112] Among them, is the velocity of particle in the th iteration and the th dimension; is the velocity of particle in the th iteration and the th dimension; is the inertia weight; and are learning factors; and is a random weight; is a particle at the dimensional historical optimal position; is a particle at the th iteration, the dimensional position; is the global optimal position of the entire population at the dimensional. The position update formula is as follows.

[0113] .

[0114] Among them, is a particle at the th iteration, the dimensional position; is a particle at the th iteration, the dimensional position.

[0115] Step 372: Randomly match the encoded individuals in the second population to obtain particle pairs; a particle pair includes: two encoded individuals.

[0116] Step 373: Calculate the objective function values of the two encoded individuals in the particle pair respectively to obtain the objective function values of each encoded individual in the particle pair.

[0117] Step 374: Evolve the encoded individual with the lower objective function value in each particle pair using the reverse mutation strategy to obtain the mutated encoded individual.

[0118] Specifically, the encoded individuals generated in the second population are randomly assigned to particle pairs, and each particle pair contains two encoded individuals. In each particle pair, the individual with the lower objective function value undergoes reverse mutation strategy evolution, and the individual with the higher objective function value learns from the individual with the lower objective function value, thereby generating new offspring population individuals. Reverse mutation strategy: Generate another encoded individual through reverse learning. The specific operation is: According to the current encoded individual position, calculate its reverse position. The expression of the mutated encoded individual is as follows.

[0119] .

[0120] Among them, is the random number of the mutated encoded individual; is the random number of the encoded individual with the lower objective function value among the objective function values of the first encoded individual and the second encoded individual.

[0121] Step 375: Perform particle learning on the encoding individual with a higher objective function value among each pair of particles to obtain the learned encoding individual.

[0122] Specifically, the particle learning process: Calculate the difference vector between the two encoding individuals, and update the position of the encoding individual with a smaller objective function value to the weighted sum of the position of the individual with a larger objective function value and the difference vector. The expression of the learned encoding individual is as follows.

[0123] 。

[0124] Among them, is the random number of the learned encoding individual; is the random number of the encoding individual with a higher objective function value among the objective function values of the first encoding individual and the second encoding individual; is the learning step coefficient; is the random number of the encoding individual with a lower objective function value among the objective function values of the first encoding individual and the second encoding individual.

[0125] Step 376: Based on the mutated encoding individual and the learned encoding individual, form the offspring population.

[0126] The beneficial effects of a ship helicopter group wave departure and recovery mission planning and scheduling method proposed in this application are mainly manifested in the following aspects.

[0127] (1) The ship helicopter group wave departure and recovery mission planning model established in this application details the wave mission into six stages: pre-departure transportation, maintenance support, departure from the ship, mission flight, recovery approach, and post-recovery transportation. A non-linear integer programming model is established, comprehensively considering logical constraints and resource constraints, so as to accurately calculate the start and end times of each stage of helicopter departure and recovery, accurately calculate the start and end times of the helicopter's mission execution, ensure the start and end times of personnel work, ensure the activation and deactivation times of equipment, and the start and end times of transportation equipment, and obtain the mission window time of the helicopter departure mission and the time of the helicopter's operation on the deck, providing accurate time for subsequent mission planning and scheduling.

[0128] (2) This application uses a competitive particle swarm algorithm with a hybrid elite mutation strategy to solve the start time and end time of the six stages of the helicopter. Compared with traditional intelligent algorithms, the elite mutation and competition mechanisms in the algorithm can balance the exploration and exploitation capabilities, and at the same time improve the convergence speed, and can obtain the solution results faster.

[0129] Based on the same inventive concept, an embodiment of the present application further provides a ship helicopter group sortie launch and recovery mission planning and scheduling system. The implementation solutions provided by this system for solving problems are similar to those described in the above method. Therefore, the specific limitations in one or more embodiments of the ship helicopter group sortie launch and recovery mission planning and scheduling system provided below can refer to the limitations on the ship helicopter group sortie launch and recovery mission planning and scheduling method in the foregoing, and will not be repeated here.

[0130] In an exemplary embodiment, as Figure 2 shown, a ship helicopter group sortie launch and recovery mission planning and scheduling system is provided, which includes the following modules.

[0131] A model establishment module, configured to establish a ship helicopter group sortie launch and recovery mission planning model; the ship helicopter group sortie launch and recovery mission planning model includes: logical constraints, resource constraints, and an objective function; the logical constraints are the process constraints of the six stages of the helicopter and the timing constraints of each stage; the six stages of the helicopter sequentially include: the pre-launch transportation stage, the aircraft maintenance support stage, the launch departure stage, the mission flight stage, the recovery approach stage, and the post-recovery transportation stage; the resource constraints are the constraints on the transportation equipment, support personnel, and supply resources required by the helicopter; the objective function is composed of the mission window satisfaction rate of the helicopter launch mission and the deck operation time of the helicopter on the ship.

[0132] An acquisition module, configured to acquire the sortie launch and recovery mission requirements; the sortie launch and recovery mission requirements include: a mission wave set, a helicopter set participating in the operation for each wave, the earliest start time and the latest start time of each wave mission.

[0133] A mission planning and scheduling module, configured to, based on the sortie launch and recovery mission requirements, with the logical constraints and resource constraints as the constraint conditions, and with the minimum objective function value as the goal, use a competitive particle swarm optimization algorithm with a hybrid elite mutation strategy to solve the start time and end time of the six stages of the helicopter, and obtain an optimal mission planning and scheduling scheme; the competitive particle swarm optimization algorithm with a hybrid elite mutation strategy is an algorithm improved based on the particle swarm optimization algorithm by adopting a competitive hybrid elite mutation strategy.

[0134] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0135] In this article, specific examples are used to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application. At the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for planning and scheduling the recovery mission of a group of ship-based helicopters in waves, characterized in that: The method for planning and scheduling the recovery mission of a ship-to-ship helicopter group wave dispatch includes: A planning model for the wave dispatch and recovery mission of a ship helicopter group is established; the planning model for the wave dispatch and recovery mission of a ship helicopter group includes: logical constraints, resource constraints and objective functions; the logical constraints are the process constraints of the six stages of the helicopter and the timing constraints of each stage; the six stages of the helicopter include: the pre-dispatch transportation stage, the maintenance service support stage, the dispatch departure stage, the mission flight stage, the recovery on-site stage and the post-recovery transportation stage; the resource constraints are the constraints on the transportation equipment, support personnel and supply resources required for the helicopter; the objective function is composed of the task window satisfaction rate of the helicopter dispatch mission and the helicopter's deck operation time on the ship; Obtaining the recovery mission requirements; the recovery mission requirements include: a mission wave set, a helicopter set participating in each wave, and the earliest start time and the latest start time of each wave mission; Based on the requirements of the sortie and recovery mission, with logical constraints and resource constraints as constraints, and with the minimum objective function value as the goal, the competitive particle swarm algorithm with a hybrid elite mutation strategy is used to solve the start and end times of the six stages of the helicopter to obtain the optimal mission planning and scheduling solution; the competitive particle swarm algorithm with a hybrid elite mutation strategy is an improved algorithm based on the particle swarm algorithm using a competitive hybrid elite mutation strategy.

2. The method for planning and scheduling the recovery mission of a ship-to-ship helicopter group in waves according to claim 1 is characterized in that: The logical constraints include: transportation phase constraints, maintenance and service phase constraints, dispatch and departure phase constraints, mission flight phase constraints, return and return phase constraints and wave operation connection constraints.

3. The method for planning and scheduling the recovery mission of a ship-to-ship helicopter group in waves according to claim 1 is characterized in that: The resource constraints include: transportation equipment constraints, support personnel constraints, support equipment constraints, supply resource constraints and resource allocation constraints.

4. The method for planning and scheduling the recovery mission of a ship-to-ship helicopter group in waves according to claim 1 is characterized in that: Each stage of each helicopter includes multiple processes; the calculation formula of the objective function is: ； ； ； ； ； in, is the objective function value; and All are weight values; The maximum value of the mission window satisfaction rate of the helicopter dispatch mission; The minimum value of the mission window satisfaction rate of the helicopter dispatch mission; The mission window satisfaction rate for helicopter sortie missions; The time the helicopter spends operating on the ship's deck; The maximum time that a helicopter can operate on the deck of a ship; The minimum time for a helicopter to operate on the deck of a ship; For the The task window of the wave meets the conditions; It is a collection of task waves; For the The earliest start time of the wave task; For the Wave sequence The helicopter is in the fourth stage The start time of the process; For the The latest start time of the wave task; For the Wave sequence The helicopter was in the second phase The end time of the process; For the Wave sequence Helicopters in Phase 1 The start time of the process; For the Wave sequence The helicopter is in the 6th stage The end time of the process; For the Wave sequence The helicopter is in the 6th stage The start time of a process.

5. The method for planning and scheduling the recovery mission of a ship-to-ship helicopter group in waves according to claim 1 is characterized in that: Each wave includes multiple helicopters; each stage of each helicopter includes multiple processes; Based on the requirements of the recovery mission, with logical constraints and resource constraints as constraints, and the minimum objective function value as the goal, the competitive particle swarm algorithm with a hybrid elite mutation strategy is used to solve the start and end times of the six stages of the helicopter, and the optimal mission planning and scheduling scheme is obtained, which specifically includes: A random number is used to encode each process in the pre-dispatch transportation stage, each process in the maintenance support stage, and each process in the post-recovery transportation stage in the dispatch recovery mission requirements, and multiple encoded individuals are obtained, and multiple encoded individuals form an initialization population; Determine the priority of each coded individual according to the size of the random number; Sorting each coded individual according to the priority of each coded individual to obtain a plurality of sorted coded individuals; Taking the logic constraint and the resource constraint as the constraint conditions, a serial scheduling mechanism is used to decode each sorted coding individual to obtain multiple task planning scheduling schemes; the task planning scheduling schemes include: the start time and end time of the pre-dispatch transportation phase, the start time and end time of the maintenance service support phase, and the start time and end time of the post-recovery transportation phase; each task planning scheduling scheme corresponds to a decoding individual, and multiple decoding individuals form a first population; According to the start and end time of the pre-dispatch transportation phase, the start and end time of the maintenance service support phase, and the start and end time of the post-recovery transportation phase, calculate the start and end time of the departure phase, the start and end time of the mission flight phase, and the start and end time of the recovery phase; Calculate the objective function value of each decoding individual according to the start and end time of the mission flight phase, the start and end time of the pre-dispatch transportation phase, the start and end time of the maintenance support phase, and the start and end time of the post-recovery transportation phase; Determine whether the current iteration round has reached the preset maximum iteration round; If so, the decoding individual with the smallest objective function value is determined as the optimal task planning and scheduling solution; If not, a particle swarm with a hybrid elite mutation strategy is introduced to optimize the first population to obtain a child population, which is then re-decoded and the objective function value of each encoded individual in the child population is calculated.

6. The method for planning and scheduling the recovery mission of a ship-to-ship helicopter group according to claim 5 is characterized in that: With logical constraints and resource constraints as constraints, a serial scheduling mechanism is used to decode each sorted coded individual to obtain multiple task planning and scheduling schemes, including: Based on the earliest start time of each wave, the planned dispatching operation end time and the planned recovery operation start time of each wave are calculated, and the operation set is generated by arranging them in ascending order according to time; the dispatching operation includes: pre-dispatch transportation stage, maintenance service support stage and dispatch departure stage; the recovery operation includes: recovery on-site stage and post-recovery transportation stage; According to the priority order of each coded individual, with logic constraints and resource constraints as constraints, each process of each stage in the dispatching operation and recycling operation of each coded individual is decoded, and the start time and end time of each stage in the dispatching operation and recycling operation of each decoded individual are determined; According to the start time and end time of each stage in the dispatching operation and recovery operation of each decoding individual, the task planning and scheduling scheme corresponding to each decoding individual is determined, and multiple task planning and scheduling schemes are obtained.

7. The method for planning and scheduling the recovery mission of a ship-to-ship helicopter group according to claim 5 is characterized in that: The particle swarm with hybrid elite mutation strategy is introduced to optimize the first population and obtain the offspring population, including: A certain number of particles are randomly generated and added to the first population to obtain a second population; one particle is a coding individual; Randomly match the coded individuals in the second population to obtain particle pairs; a particle pair includes: two coded individuals; Calculate the objective function values ​​of the two coding individuals in the particle pair respectively, and obtain the objective function value of each coding individual in the particle pair; The coding individual with the lower objective function value in each coding individual of the particle pair is subjected to reverse mutation strategy evolution to obtain the mutated coding individual; Perform particle learning on the coding individual with a higher objective function value in each coding individual of the particle pair to obtain the learned coding individual; The offspring population is composed of the mutated coding individuals and the learned coding individuals.

8. The method for planning and scheduling the recovery mission of a ship-to-ship helicopter group according to claim 7 is characterized in that: The expression of the mutated coding individual is: ； in, is the random number of the coded individual after mutation; The random number of the encoding individual which is the lower of the objective function value of the first encoding individual and the objective function value of the second encoding individual.

9. The method for planning and scheduling the recovery mission of a ship-to-ship helicopter group in waves according to claim 7 is characterized in that: The expression of the learned encoding individual is: ； in, is the random number of the coded individual after learning; A random number of a coding individual which is a higher one of the objective function value of the first coding individual and the objective function value of the second coding individual; is the learning step size coefficient; The random number of the encoding individual which is the lower of the objective function value of the first encoding individual and the objective function value of the second encoding individual.

10. A ship helicopter group wave dispatch recovery mission planning and scheduling system, characterized in that: The ship helicopter group wave dispatch recovery mission planning and scheduling system includes: The model building module is used to establish a ship helicopter group wave dispatch recovery mission planning model; the ship helicopter group wave dispatch recovery mission planning model includes: logical constraints, resource constraints and objective functions; the logical constraints are the process constraints of the six stages of the helicopter and the timing constraints of each stage; the six stages of the helicopter include: pre-dispatch transportation stage, maintenance service support stage, dispatch departure stage, mission flight stage, recovery on-site stage and post-recovery transportation stage; the resource constraints are the constraints on the transportation equipment, support personnel and supply resources required for the helicopter; the objective function is composed of the task window satisfaction rate of the helicopter dispatch mission and the helicopter deck operation time on the ship; An acquisition module is used to acquire the recovery mission requirements; the recovery mission requirements include: a mission wave set, a helicopter set participating in each wave, and the earliest start time and the latest start time of each wave mission; The task planning and scheduling module is used to solve the start and end times of the six stages of the helicopter based on the requirements of the dispatch and recovery task, with logical constraints and resource constraints as constraints, and with the minimum objective function value as the goal, using a competitive particle swarm algorithm with a hybrid elite mutation strategy to obtain the optimal task planning and scheduling solution; the competitive particle swarm algorithm with a hybrid elite mutation strategy is an improved algorithm based on the particle swarm algorithm using a competitive hybrid elite mutation strategy.

Images