Takeoff scheduling method, device and equipment for fixed-direction hybrid aircraft fleet based on whale algorithm

Through the take-off scheduling method of solid-line mixer group based on whale algorithm, a hybrid dispatch scheduling model is constructed and the dispatch sequence and position allocation are optimized, which solves the problem that traditional methods are difficult to deal with complex scheduling of solid-line mixer group, and improves the dispatch efficiency and quality.

CN115686066BActive Publication Date: 2024-11-19NAVAL AVIATION UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202211407385.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-11-09
Publication Date
2024-11-19
Estimated Expiration
2042-11-09

AI Technical Summary

Technical Problem

Traditional aircraft dispatching methods are difficult to effectively deal with the complex take-off position selection and dispatching process in solid-line hybrid aircraft groups, especially in the case of coexistence of fixed-wing aircraft and helicopters, resulting in limited dispatch efficiency and safety.

Method used

Using the take-off scheduling method of solid straight hybrid aircraft group based on whale algorithm, the whale population is initialized by constructing a hybrid dispatching model, and iteratively updates the dispatch priority and take-off position selection, optimizes the dispatch sequence and position allocation, and adapts to the discreteization of the hybrid dispatching model. Features.

Benefits of technology

It improves the take-off and dispatch efficiency and quality of the solid-line hybrid aircraft group, can quickly configure efficient hybrid dispatching solutions, adapt to complex aircraft types and take-off position distribution changes, and improves the optimization capabilities of dispatching.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115686066B_ABST
    Figure CN115686066B_ABST
Patent Text Reader

Abstract

The present application relates to a takeoff scheduling method, device and equipment for a mixed fleet of fixed-direction aircraft based on a whale algorithm. The method includes: constructing a mixed dispatch scheduling model for the dispatch priority and takeoff position selection of each aircraft in the mixed fleet; initializing a whale population according to the mixed dispatch mission parameters, updating the priority sequence of the current whale individual according to the differential information of the dispatch priority corresponding to the current whale individual and another whale individual in the initialized whale population, obtaining the updated current whale individual, iteratively updating each whale individual in the population, and obtaining a new whale population; iteratively updating the whale population, and when the pre-selected iteration stop condition is met, outputting the current mixed dispatch scheduling plan to perform takeoff dispatch scheduling for the mixed fleet of fixed-direction aircraft. The use of this method can quickly configure the mixed dispatch scheduling plan for the mixed fleet of fixed-direction aircraft, improve the quality of the optimal solution, and efficiently perform the takeoff dispatch of the mixed fleet of fixed-direction aircraft.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of resource scheduling, and in particular to a method, device and equipment for scheduling takeoff of a fixed-helicopter hybrid fleet based on a whale algorithm. Background Art

[0002] Aircraft operation is a cyclical process, including catapult takeoff, mission execution, return landing, offshore platform maintenance support, and catapult takeoff again, and so on. After completing their respective support work, the aircraft dispatched to the corresponding offshore platform position enters the aircraft dispatch and departure stage. This stage is relatively short in duration compared to the in-and-out transfer, but its space is smaller than the in-and-out transfer. On the flying offshore platform, it is necessary to complete the warm-up transfer and take-off position transfer of up to ten aircraft. During the transfer process, higher requirements are placed on the reasonable allocation of space resources and the collision avoidance safety of multiple aircraft taxiing. In addition, for small space and high-density transfer tasks, coupled with the preparation timing constraints of various dispatching procedures, the aircraft dispatch timing will have a greater impact on the formation's mission execution capability. Therefore, reasonable timing planning for the dispatch and departure of the fixed-direct hybrid fleet is an important foothold for improving aircraft dispatch capabilities.

[0003] However, the traditional method is only for fleets consisting of a single type of aircraft. When the mission requires the participation of both fixed-wing aircraft and helicopters, the dispatch process is different due to the different types of aircraft. When the fleet becomes a mixed fixed-wing and helicopter fleet, the take-off positions of the two types of aircraft are more dispersed. The aircraft layout of the initial parking position will affect the selection of subsequent take-off positions and the selection of dispatch processes. Changes in these two will change the interference of the path during dispatch and transportation. The traditional scheduling method is not suitable for this more complex problem. Summary of the invention

[0004] Based on this, it is necessary to provide a takeoff scheduling method, device and equipment for a fixed-direction hybrid fleet based on the whale algorithm to address the above technical problems.

[0005] A takeoff scheduling method for a fixed-direct hybrid aircraft fleet based on a whale algorithm, the method comprising:

[0006] Acquire mixed sortie mission parameters corresponding to a preset fixed-wing mixed aircraft group sortie mission; the mixed sortie mission parameters include the aircraft type of each aircraft in the mixed aircraft group, a first takeoff position set corresponding to the takeoff position of the fixed-wing aircraft, and a second takeoff position set corresponding to the takeoff position of the helicopter;

[0007] According to the preset constraints, taking the minimum sortie completion time of the fleet and the minimum taxiing time of the fixed-wing aircraft as the objective function, a mixed sortie scheduling model for the sortie priority and take-off position selection of each aircraft in the mixed fleet is constructed;

[0008] Initialize the whale population according to the mixed dispatch mission parameters, update the dispatch priority sequence of the current whale individual according to the differential information of the dispatch priority corresponding to the current whale individual and another whale individual in the initialized whale population, obtain the updated current whale individual, iteratively update each whale individual in the population, and obtain a new whale population;

[0009] Iteratively update the whale population, and when the pre-selected iteration stop condition is met, stop the iteration and output the current hybrid dispatch scheduling plan; the hybrid dispatch scheduling plan is used for takeoff dispatch scheduling of a fixed-direct hybrid fleet.

[0010] A takeoff scheduling device for a fixed-direct hybrid aircraft fleet based on a whale algorithm, the device comprising:

[0011] A parameter acquisition module is used to acquire mixed sortie mission parameters corresponding to a preset fixed-wing mixed aircraft group sortie mission; the mixed sortie mission parameters include the aircraft type of each aircraft in the mixed aircraft group, a first take-off position set corresponding to the take-off position of the fixed-wing aircraft, and a second take-off position set corresponding to the take-off position of the helicopter;

[0012] A model building module is used to build a mixed sortie scheduling model for sortie priority and takeoff position selection of each aircraft in a mixed fleet based on preset constraints and taking the minimum fleet sortie completion time and the minimum fixed-wing aircraft taxiing time as objective functions;

[0013] A model optimization module is used to initialize the whale population according to the mixed dispatch mission parameters, update the dispatch priority sequence of the current whale individual according to the differential information of the dispatch priority corresponding to the current whale individual and another whale individual in the initialized whale population, obtain the updated current whale individual, iteratively update each whale individual in the population, and obtain a new whale population;

[0014] The optimization output module is used to iteratively update the whale population. When the pre-selected iteration stop condition is met, the current hybrid dispatch scheduling plan is output; the hybrid dispatch scheduling plan is used to perform takeoff dispatch scheduling of a fixed-direct hybrid fleet.

[0015] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0016] Acquire mixed sortie mission parameters corresponding to a preset fixed-wing mixed aircraft group sortie mission; the mixed sortie mission parameters include the aircraft type of each aircraft in the mixed aircraft group, a first takeoff position set corresponding to the takeoff position of the fixed-wing aircraft, and a second takeoff position set corresponding to the takeoff position of the helicopter;

[0017] According to the preset constraints, taking the minimum sortie completion time of the fleet and the minimum taxiing time of the fixed-wing aircraft as the objective function, a mixed sortie scheduling model for the sortie priority and take-off position selection of each aircraft in the mixed fleet is constructed;

[0018] Initialize the whale population according to the mixed dispatch mission parameters, update the dispatch priority sequence of the current whale individual according to the differential information of the dispatch priority corresponding to the current whale individual and another whale individual in the initialized whale population, obtain the updated current whale individual, iteratively update each whale individual in the population, and obtain a new whale population;

[0019] Iteratively update the whale population, and when the pre-selected iteration stop condition is met, stop the iteration and output the current hybrid dispatch scheduling plan; the hybrid dispatch scheduling plan is used for takeoff dispatch scheduling of a fixed-direct hybrid fleet.

[0020] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0021] Acquire mixed sortie mission parameters corresponding to a preset fixed-wing mixed aircraft group sortie mission; the mixed sortie mission parameters include the aircraft type of each aircraft in the mixed aircraft group, a first takeoff position set corresponding to the takeoff position of the fixed-wing aircraft, and a second takeoff position set corresponding to the takeoff position of the helicopter;

[0022] According to the preset constraints, taking the minimum sortie completion time of the fleet and the minimum taxiing time of the fixed-wing aircraft as the objective function, a mixed sortie scheduling model for the sortie priority and take-off position selection of each aircraft in the mixed fleet is constructed;

[0023] Initialize the whale population according to the mixed dispatch mission parameters, update the dispatch priority sequence of the current whale individual according to the differential information of the dispatch priority corresponding to the current whale individual and another whale individual in the initialized whale population, obtain the updated current whale individual, iteratively update each whale individual in the population, and obtain a new whale population;

[0024] Iteratively update the whale population, and when the pre-selected iteration stop condition is met, stop the iteration and output the current hybrid dispatch scheduling plan; the hybrid dispatch scheduling plan is used for takeoff dispatch scheduling of a fixed-direct hybrid fleet.

[0025] The above-mentioned fixed-wing and helicopter hybrid takeoff scheduling method, device and equipment based on the whale algorithm constructs a mixed dispatch scheduling model for the takeoff of fixed-wing and helicopter hybrid fleets, performs time planning for the mixed dispatch of fixed-wing aircraft and helicopters, and discretizes the whale algorithm to make the whale algorithm adapt to the discretization characteristics of the mixed dispatch scheduling model, thereby optimizing the solution of the mixed dispatch scheduling model. In the discretization process, the dispatch priority sequence of the current whale individual is updated according to the differential information of the corresponding dispatch priority of the current whale individual and another whale individual in the initialized whale population, and the updated current whale individual is obtained, which improves the optimization ability of the algorithm, thereby performing takeoff scheduling of fixed-wing and helicopter hybrid fleets with high-quality optimal solutions. The embodiments of the present invention can improve the optimization efficiency, quickly configure the mixed dispatch scheduling plan of fixed-wing and helicopter hybrid fleets, and can improve the quality of the optimal solution, so as to efficiently perform the takeoff and dispatch of fixed-wing and helicopter hybrid fleets. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flowchart of a takeoff scheduling method for a fixed-direct hybrid aircraft fleet based on a whale algorithm in one embodiment;

[0027] Figure 2 A schematic diagram of a flow chart of a differential information cooperation mechanism in one embodiment;

[0028] Figure 3 Schematic diagram of the flow of an IWOA algorithm in one embodiment;

[0029] Figure 4 1. A schematic diagram of the change trend of optimization indicators for the dispatch and transfer scheduling of 12 aircraft in one embodiment, wherein (a) is a schematic diagram of the change trend of the completion time of the fleet dispatch, and (b) is a schematic diagram of the taxiing time and change trend of the fixed-wing aircraft;

[0030] Figure 5 A Gantt chart for scheduling a fleet of 12 machines in one embodiment;

[0031] Figure 6 A Gantt chart showing the occupancy of take-off positions for 12 aircraft in one embodiment;

[0032] Figure 7 It is a structural block diagram of a takeoff scheduling device for a fixed-direct hybrid aircraft fleet based on a whale algorithm in one embodiment;

[0033] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0035] The departure of fixed-wing aircraft mainly includes four stages:

[0036] Warm-up self-inspection stage: Due to the use requirements of fixed-wing aircraft engines, warm-up and self-inspection work must be performed before take-off to confirm whether the engine performance indicators are normal and whether there are any fault symptoms, and then the aircraft will proceed with the subsequent take-off process. This stage generally takes 2 to 3 minutes. However, due to the structural design characteristics of the offshore platform, some parking positions cannot perform warm-up self-inspection, otherwise the tail flame of the fixed-wing aircraft will cause ablation of the offshore platform structure. Therefore, some aircraft need to be warmed up and transported at this stage, and the aircraft will be transported from the non-warm-up position to the warm-up position.

[0037] Waiting stage after the deflector: After the aircraft completes the engine warm-up self-inspection, the aircraft can be transferred to the take-off position for take-off. However, if there is an aircraft waiting to take off at the target take-off position, the aircraft must first be transferred to the corresponding waiting position behind the target take-off position for take-off. After the aircraft at the target position takes off, the aircraft can enter the position to prepare for take-off. Since this stage involves offshore platform transfer, transfer collision avoidance constraints must be considered to prevent collisions caused by aircraft path interference.

[0038] Take-off preparation phase: When the aircraft enters the target take-off position, it can carry out corresponding pre-takeoff preparations according to the different take-off modes of the aircraft. In this phase, the pilot and maintenance personnel conduct a pre-takeoff inspection to ensure that the aircraft is in good condition.

[0039] Take-off phase: When the aircraft has completed all preparations, the pilot waits for the take-off order and completes the take-off.

[0040] The helicopter departure mainly includes two stages:

[0041] Take-off and transfer phase: After completing the maintenance and service support tasks, the helicopter can be transferred to the assigned take-off position for take-off. During this phase, it is necessary to consider the blockage of the transfer path, the interference of the parking position, and the collision avoidance during the transfer process. Depending on the situation, the helicopter will be hoisted to the corresponding take-off position when the transfer is possible. When there is an aircraft at the target parking position of the helicopter, it is necessary to wait at the original parking position.

[0042] Takeoff preparation and dispatch phase: When the helicopter taxis to the corresponding takeoff position, it is necessary to carry out pre-takeoff preparations, such as rotor deployment, navigation calibration, control system self-check, etc. After completing this series of work, the pilot waits for the takeoff command, and the helicopter takes off and leaves the airport. This phase takes about 5 minutes. Among them, fixed-wing aircraft and helicopters are in the wing-retracted state during the transfer phase, and the wings can only be deployed after the aircraft enters the takeoff position.

[0043] In one embodiment, Figure 1 As shown, a takeoff scheduling method for a fixed-direction hybrid aircraft fleet based on a whale algorithm is provided, comprising the following steps:

[0044] Step 102, obtaining the hybrid dispatching mission parameters corresponding to the pre-set solid-direct hybrid group dispatching mission.

[0045] The mixed sortie mission parameters include the aircraft type of each aircraft in the mixed fleet, a first take-off position set corresponding to the take-off position of the fixed-wing aircraft, and a second take-off position set corresponding to the take-off position of the helicopter.

[0046] Step 104, based on the preset constraints and mixed sortie mission parameters, with the minimum sortie completion time of the fleet and the minimum taxiing time of the fixed-wing aircraft as the objective function, a mixed sortie scheduling model for the sortie priority and take-off position selection of each aircraft in the mixed fleet is constructed.

[0047] The departure scheduling problem for fixed-wing aircraft and helicopter mixed fleet (DSPMF) is to optimize the timing and positions of each stage of the departure of fixed-wing aircraft and helicopter mixed fleet under complex constraints such as warm-up constraints, space resource constraints, operation process constraints, and take-off position selection constraints, so as to minimize the fleet completion time of each aircraft formation and the taxiing time of the offshore platform. In order to solve the DSPMF problem, the following assumptions are made: when a certain stage of operation begins, it cannot be stopped and must be executed until the end of that stage; this model is for static problems, and the tasks do not change during the fleet dispatch process.

[0048] In order to find the optimal plan for the departure of a mixed fixed-wing aircraft fleet, two types of optimization indicators, namely the fleet dispatch completion time and the fixed-wing aircraft taxiing time, are constructed respectively. While minimizing the fleet dispatch completion time, the fixed-wing aircraft transfer time is minimized as much as possible.

[0049] The objective function of the DSPMF model is as follows:

[0050] Minimize the time to complete the fleet dispatch: Since the aircraft fleet generally performs periodic operations when performing tasks, but the offshore platform is too narrow, the current wave of aircraft must be dispatched before the previous wave of aircraft lands. Therefore, only by completing the fleet dispatch and departure as soon as possible can we ensure that the aircraft that have completed the mission can be guaranteed as soon as possible and prepare for the next wave of dispatch. Minimize the time to complete the fleet dispatch:

[0051]

[0052] Minimize the taxiing time of fixed-wing aircraft: Since fixed-wing aircraft need to ignite the engine when taxiing from the warm-up position to the take-off position, the engine tail flame and wake are a threat to the safety of support personnel, support equipment and the aircraft at its tail during the transfer process. In addition, the taxiing process will cause fuel consumption. From the perspective of safety and resource conservation, the shorter the taxiing time of the fleet, the better. Minimize the taxiing time of fixed-wing aircraft and:

[0053]

[0054] The constraints of the DSPMF model are as follows:

[0055] Timing constraints of operation process: Whether it is a fixed-wing aircraft or a helicopter, its departure process includes multiple operation stages, and these stages are interconnected, and they contain timing relationships. For the transfer operation, the timing constraints are as follows:

[0056]

[0057] Among them, aircraft transfer or fixed-wing aircraft taxiing time ΔTz ij According to the parking positions in the previous and next two stages:

[0058]

[0059] For the guarantee operation, the timing constraints are:

[0060] E ij =Sw ij +dw j or

[0061] In order to achieve the connection between the transfer operation and the guarantee operation, the constraint relationship is expressed as follows:

[0062]

[0063]

[0064] in, It means that for the support operation and transfer operation at the same stage, the former can only be carried out after the latter is completed; It means that the transfer operation can only start after the previous stage is completed. In addition, the fixed-wing aircraft needs to wait for the deflector plate to cool down and reset before entering the take-off position. The deflector plate cooling and reset time interval constraint for the fixed-wing aircraft is:

[0065]

[0066] Space resource constraints: This constraint mainly includes multi-machine transport collision avoidance constraints and the priority constraints of occupying the same space. The multi-machine transport collision avoidance constraints are:

[0067]

[0068]

[0069] The priority constraint of occupying the same space is mainly used to delay the aircraft transfer when there is interference between the aircraft transfer path and the fixed-wing aircraft takeoff and runway path, that is:

[0070]

[0071] Take-off position matching constraint: For fixed-wing aircraft, there is a corresponding waiting position behind each take-off position. When a fixed-wing aircraft selects a waiting position, its take-off position is also fixed, that is:

[0072]

[0073] Takeoff interval constraint: After a fixed-wing aircraft takes off, its takeoff wake will disturb the airflow field on the deck of the offshore platform, which will increase the risk of subsequent takeoffs, and the deflector behind the fixed-wing aircraft's takeoff position also needs to be reset and cooled. For helicopters, it takes a certain amount of time for the distance between the takeoff and the offshore platform to reach the safe distance for subsequent aircraft to take off. Therefore, after an aircraft takes off, it is necessary to wait for a period of time before the next aircraft takes off to ensure the safe departure of the aircraft. For fixed-wing aircraft, the wake time interval should be met between consecutive sorties, and for helicopters, the safe departure time interval should be met between consecutive takeoffs, that is:

[0074]

[0075] Takeoff configuration constraint: This constraint is for ski-jump takeoff. When the aircraft takeoff weight exceeds the limit, it must take off at a specific takeoff position with a longer runway distance to ensure that the aircraft meets the speed requirement when leaving the ship. Therefore, the takeoff position selection of fixed-wing aircraft must meet the weight requirement of the takeoff position, that is:

[0076]

[0077] Decision variable constraints: Yp ijegp , Yrijegr 、x ie They are all Boolean 0-1 decision variables, namely:

[0078]

[0079] Take-off position selection constraints: Since fixed-wing aircraft and helicopters have different corresponding take-off position types, constraints need to be imposed when selecting the take-off position. The take-off position selection constraints are:

[0080]

[0081] Among them, k is the take-off position number. When the dispatched aircraft is a fixed-wing aircraft, R can be 1, 2, or 3. When the dispatched aircraft is a helicopter, R can be 4, 5, 6, or 7.

[0082] The parameters used in the dispatching model of the hybrid fleet are defined as follows:

[0083] I represents the set of fixed-wing and helicopter mixed aircraft, I=I1∪I2={1,2,…,Nf}, Nf=Nf1+Nf2, the fixed-wing aircraft set I1={1,2,…,Nf1}, the helicopter set I2={1,2,…,Nf2};

[0084] Ψ j represents the set of parking stands that can be used for the j-th stage dispatch process;

[0085] P represents the parking stand set;

[0086] J represents the set of departure process stages, J = {0, 1, 2, 3, 4}, 0 is the initial stage, the first stage of the helicopter is equivalent to the second stage of the fixed-wing aircraft, that is, the departure stage, and the second stage of the helicopter is equivalent to the fourth stage of the fixed-wing aircraft, that is, the departure stage;

[0087] R represents the take-off position set;

[0088] O ij represents the j-th dispatching process of aircraft i;

[0089] TR(p,q,Ap t (p,q)) represents the time required for the aircraft to be transferred from the initial parking position p to the target parking position q at time t;

[0090] tx j Indicates the mooring and unmooring time;

[0091] dw j It indicates the time taken for the jth stage operation of the fixed-wing aircraft;

[0092] dh j It indicates the time taken for the helicopter to perform the jth phase of operation;

[0093] γ p represents the take-off position corresponding to the waiting position p, p∈Ψ2,γ p ∈Ψ3;

[0094] Φ p (p,q) represents the set of parking positions that interfere with the path from the initial position p to the target position q;

[0095] Φ r (p,q) represents the set of runways invaded by the path from the initial position p to the target position q;

[0096] δ i represents the wake turbulence interval time of the i-th fixed-wing aircraft or the safe departure time of the helicopter;

[0097] Δtb represents the cooling and reset time of the deflector plate;

[0098] m i represents the take-off weight of the i-th fixed-wing aircraft;

[0099] fm p It represents the maximum take-off weight at take-off position p;

[0100] The decision variables are defined as:

[0101] Sw ij represents the start time of operation phase j of aircraft i;

[0102] E ij represents the end time of operation phase j of aircraft i;

[0103] S ij represents the start time of the transfer of operation phase j of aircraft i;

[0104] Ez ij represents the end time of the transfer of operation phase j of aircraft i;

[0105] P ij represents the parking space occupied by aircraft i in operation phase j;

[0106]

[0107]

[0108]

[0109]

[0110] Traditional methods are only used for dispatching fixed-wing aircraft fleets. In a fixed-wing mixed fleet, the dispatching processes of fixed-wing aircraft and helicopters are different. The dispatching process of fixed-wing aircraft includes four stages, while the dispatching process of helicopters only includes two stages. The increase in the types of aircraft makes the dispatching process and various constraints more complicated. The DSPMF model constructed in the present invention can be applied to this more complicated problem.

[0111] Step 106, initialize the whale population according to the mixed dispatch mission parameters, update the dispatch priority sequence of the current whale individual according to the differential information of the dispatch priority corresponding to the current whale individual and another whale individual in the initialized whale population, obtain the updated current whale individual, iteratively update each whale individual in the population, and obtain a new whale population.

[0112] The design of the Whale Optimization Algorithm (WOA) is inspired by the behavior of humpback whales in hunting prey. In order to hunt krill or small fish close to the sea surface, the humpback whale population has evolved a unique bubble net foraging method. During the foraging process, the humpback whale creates bubbles on a circular or "9"-shaped path to trap the prey in the bubble for feeding. There are two bubble strategies, "upward spiral" and "double spiral". The whale optimization algorithm achieves the optimization purpose by simulating the spiral bubble net strategy. The whale optimization algorithm mainly includes shrinking and encircling foraging, bubble net foraging and random hunting. Shrinking and encircling foraging and bubble net foraging are group search. Group search is the process of approaching the optimal value, representing local search; while the approach target of random hunting is a random individual, so it represents the global search of the humpback whale. This behavior can also prevent the algorithm from falling into the local optimal value to a certain extent. In WOA, the process of shrinking and encircling foraging is defined as follows:

[0113]

[0114]

[0115] represents the distance between the individual and the prey, is the whale's position update formula, where t is the current iteration number, and is the coefficient vector, and are the position vector of the prey and the position vector of the whale, is the convergence factor, which decreases linearly from 2 to 0 as the number of iterations decreases. and The modulus of is a random number between [0,1]; bubble net foraging is a process that simulates the spiral movement of whale groups swimming towards prey; while the group is hunting, the humpback whales will also swim randomly according to each other's positions. Group search is the process of approaching the optimal value, representing a local search; and the approach target of random hunting is a random individual, so it represents the global search of the humpback whale. This behavior can also prevent the algorithm from falling into the local optimal value to a certain extent. The premise of this behavior is |A|>1.

[0116] The above-mentioned humpback whale foraging process is suitable for optimizing in a continuous area. Due to the discretization characteristics of DSPMF, the standard WOA algorithm is not applicable. Therefore, the present invention discretizes the WOA algorithm and proposes IWOA (Improve Whale Optimization Algorithm).

[0117] Step 108, iteratively update the whale population, and when the pre-selected iteration stop condition is met, stop the iteration and output the current hybrid dispatch scheduling plan; the hybrid dispatch scheduling plan is used to perform takeoff dispatch scheduling of a fixed-direct hybrid fleet.

[0118] Traditional algorithms only need to optimize the allocation of take-off positions and the dispatch sequence. However, when the fleet becomes a mixed fixed-wing and direct-wing fleet, on the original basis, it is also necessary to consider the selection of the initial parking position, because the dispatch process of helicopters is different from that of fixed-wing carrier-based aircraft, and the location distribution of their take-off positions is more dispersed. The aircraft layout of the initial parking position will affect the selection of subsequent take-off positions and the selection of the dispatch process. Changes in these two will lead to changes in the interference of paths during dispatch and transportation. The improved whale optimization algorithm designed in the present invention can simultaneously optimize the initial aircraft layout, the allocation of take-off positions and the dispatch sequence.

[0119] In the above-mentioned takeoff scheduling method for a fixed-wing and helicopter hybrid fleet based on the whale algorithm, a mixed dispatch scheduling model for the takeoff of a fixed-wing and helicopter hybrid fleet is constructed, the mixed dispatch of fixed-wing aircraft and helicopters is time-planned, and the whale algorithm is discretized to adapt the whale algorithm to the discretization characteristics of the mixed dispatch scheduling model, thereby optimizing the solution of the mixed dispatch scheduling model. In the discretization process, the dispatch priority sequence of the current whale individual is updated according to the differential information of the corresponding dispatch priority of the current whale individual and another whale individual in the initialized whale population, and the updated current whale individual is obtained, which improves the optimization ability of the algorithm, thereby performing takeoff scheduling of a fixed-wing and helicopter hybrid fleet with a high-quality optimal solution. The embodiment of the present invention can improve the optimization efficiency, quickly configure the mixed dispatch scheduling plan of the fixed-wing and helicopter hybrid fleet, and can improve the quality of the optimal solution, so as to efficiently perform the takeoff and dispatch of the fixed-wing and helicopter hybrid fleet.

[0120] In one embodiment, the preset constraints include aircraft timing planning constraints, space resource constraints and take-off scheduling constraints for a mixed fleet; aircraft timing planning constraints include transfer operation timing constraints, support operation timing constraints, connection constraints between transfer operations and support operations, and deflector cooling and reset time interval constraints for fixed-wing aircraft; space resource constraints include multi-aircraft transfer collision avoidance constraints and priority constraints for occupying the same space; take-off scheduling constraints include take-off interval constraints, take-off position selection constraints, and waiting position and take-off position matching constraints and take-off configuration constraints for fixed-wing aircraft.

[0121] In one embodiment, the step of initializing a whale population according to mixed sortie mission parameters includes: allocating a corresponding take-off position to each aircraft according to the aircraft type, the first take-off position set and the second take-off position set of each aircraft in the mixed fleet to obtain a take-off position selection sequence; obtaining a sortie priority sequence according to the order in which each aircraft takes off; encoding the take-off position selection sequence and the sortie priority sequence to obtain whale individuals; and randomly generating multiple whale individuals to initialize the whale population.

[0122] In this embodiment, the warm-up position constraint requires that fixed-wing aircraft be transported for warm-up for certain parking positions that cannot complete engine warm-up. When no warm-up position is available, it is necessary to wait for other aircraft to leave the parking position before warm-up can be transported. Since the number of fixed-wing aircraft affected by the warm-up position constraint is relatively small, most of them can be warmed up on-site. Those that cannot be warmed up on-site can choose a warm-up position according to the nearest transfer rule. Helicopters do not need to be warmed up at the parking position. Therefore, in the coding stage, only the take-off position selection of each aircraft and the selection of the type of aircraft parked at the parking position are considered. The parking position occupied by the aircraft before dispatch is fixed, and the take-off position corresponding to the fixed-wing aircraft or the take-off position corresponding to the helicopter is allocated according to the aircraft type. The aircraft take-off position selection coding is adopted. represents the takeoff position selection sequence, where y j Indicates the takeoff position of the jth aircraft in the list code; the aircraft dispatch priority sequence is list-coded , where x j Indicates the priority of the jth aircraft in the list code, and the value range is x j ∈[1,Nf], the smaller the number, the higher the priority, then the encoding of the aircraft takeoff position selection and the corresponding takeoff sequence is:

[0123]

[0124] In one embodiment, the method further includes: pre-searching the situation where the parking position and the take-off position interfere with each other during the dispatch of each aircraft according to the dispatch priority sequence and the take-off position selection sequence corresponding to the randomly generated multiple whale individuals, and adjusting the dispatch priority sequence of the corresponding whale individuals according to the search results to complete the pre-constraint of the dispatch priority of the whale individuals. In this embodiment, since there is a situation where the parking position and the take-off position interfere with each other during the aircraft dispatch, when the algorithm generates a new individual, the individual sequence can be pre-searched according to the analysis of the transfer scheduling decoding, and the aircraft dispatch sequence can be pre-adjusted. For example: when there is an aircraft B in the interfering position corresponding to the take-off position of aircraft A, and the take-off sequence of A is before B, A can be moved to the next priority after B, so as to further reduce the effective search space.

[0125] In one embodiment, before updating the dispatch priority sequence of the current whale individual according to the differential information of the dispatch priority corresponding to the current whale individual and another whale individual in the initialized whale population, it includes: performing a decoding operation on each whale individual in the initialized population, and calculating the fitness function value of each whale individual according to the hybrid dispatch scheduling scheme and fitness function generated after the individual decoding, to obtain the optimal whale individual; the fitness function includes the fleet dispatch completion time and the fixed-wing aircraft taxiing time; the decoding operation includes: extracting the dispatch priority information and take-off position selection information corresponding to the current whale individual to initialize the to-be-scheduled set, and initializing the scheduled set and the executed process record; The execution process record is a matrix that records the executed processes of each aircraft to be scheduled in the initialized set to be scheduled; the aircraft type of the aircraft to be scheduled is determined according to the take-off position number corresponding to the current aircraft to be scheduled, and the corresponding departure process is executed according to the aircraft type; the next stage of the aircraft to be scheduled is selected according to the executed process, and when the aircraft to be scheduled completes the take-off and dispatching stage, the executed process record, the set to be scheduled and the scheduled set corresponding to the aircraft to be scheduled are updated; the executed process record, the set to be scheduled and the scheduled set are updated iteratively, and when the preset iteration termination condition is met, the iteration is stopped and a mixed dispatch scheduling plan is output; the mixed dispatch scheduling plan includes a mixed dispatch timing plan and a take-off position allocation plan.

[0126] In this embodiment, decoding is required to convert the coded takeoff position information and the dispatch timing priority sequence into a specific dispatch scheduling scheme. g , the scheduled set S g , first extract the integer part of the code to get the takeoff position information of the aircraft, then extract the decimal part of the code, and sort it from small to large according to the priority to get the takeoff sequence π. SL is defined as the record of the aircraft's executed process, where SL i The value is the number of process stages completed by machine i. The decoding process of dispatching and dispatching of a hybrid fleet of solid and direct-current machines is as follows:

[0127] Step 1: Initialize W g =π, SL=[0] 1×Nf ,index=1.

[0128] Step 2: When index>|W g |, go to step 6.

[0129] Step 3: Select the aircraft number i * =W g (index), corresponding to the take-off position If c * ≤3 means that the dispatched aircraft is a fixed-wing aircraft, and the dispatching process of fixed-wing aircraft Case 1 to Case 4 is executed. According to the completion status of the aircraft process, the next process is selected to continue to execute witch (SL i +1);

[0130] Case 1: Perform the fixed-wing aircraft warm-up self-test phase. In this phase, you must first determine i * Check whether the current parking position of the aircraft is a warm-up parking position. If so, warm up the aircraft for self-test directly and make Go to Case 2; otherwise, warm-up transfer is required first, and the aircraft is transferred to a warm-up parking position. Before warm-up transfer, first check whether there is an empty warm-up parking position. If so, select the position with the smallest sum of the transfer time from the empty warm-up parking position to the position and taxi from the position to the take-off position to perform warm-up transfer, and perform subsequent warm-up self-check, and make Go to Case 2; if there is no vacant warm-up parking position, check whether there is an aircraft that has completed the sortie. If so, retrieve the earliest time when the dispatched aircraft left the warm-up parking position and record its warm-up parking position. After the aircraft leaves the warm-up parking position, it can enter the position for warm-up self-inspection, and order Go to Case 2. If there is no aircraft that has been dispatched, the current aircraft cannot complete the warm-up self-test. Set index = index + 1 and go to step 2.

[0131] Case 2: A fixed-wing aircraft taxis into the take-off position or a waiting aircraft waits behind the deflector. Before taxiing, first determine whether there is an available path, that is, from the warm-up parking position To take-off position c * The interference position corresponding to the path library like If there is an aircraft that has not yet completed the sortie, then the aircraft cannot currently execute this stage, set index = index + 1, and go to step 2; if If all aircraft have completed their sorties, the earliest available time t1 of the search path is retrieved. Similarly, the set of takeoff runways that cause runway intrusions due to the taxiing path is queried. The earliest clearing time t2 of the takeoff runway after t1 is retrieved. This time is the earliest taxiing time. During the taxiing process, according to the transfer collision avoidance mechanism, the aircraft is delayed to avoid collisions and the actual taxiing start time t3 is determined. * If there is no aircraft ready to take off at the take-off position, then i * The aircraft taxis directly to the take-off position, and the waiting time after the deflector is 0. If there is an aircraft ready to take off, it taxis to c * The waiting position corresponding to the take-off position, and Proceed to Case 3.

[0132] Case 3: Prepare the fixed-wing aircraft for takeoff. This stage is only for fixed-wing aircraft in the waiting position. * After the aircraft is dispatched, the deflector plate is reset and cooled. After Δtb, the deflector plate is reset and cooled. The aircraft then taxis into position and prepares for takeoff. Proceed to Case 4.

[0133] Case 4: Execute fixed-wing aircraft takeoff. After the fixed-wing aircraft in front of the offshore platform takes off, wait for its wake to disappear. After the helicopter in front takes off, wait for it to fly to a safe distance. Take this moment as the earliest time the aircraft can take off, t1. Take this moment as the starting moment, retrieve the time t2 when the takeoff runway interference parking position corresponding to the takeoff position is cleared. This moment is the takeoff time of the aircraft, and let W g =W g -{i *},S g =S g ∪{i *}, set index = 1, and go to step 2.

[0134] If c * ≥4 means the dispatched aircraft is a helicopter, and the helicopter dispatching process Case 2 and Case 4 are executed. The next stage of operation is selected according to the completed stage. Switch (SL i +2);

[0135] Case 2: The helicopter is transferred to the take-off position. Before starting the transfer, first determine whether there is an available path, that is, from the parking position To take-off position c * The interference position corresponding to the path library like If there is an aircraft that has not yet completed the sortie, then the aircraft cannot currently execute this stage, set index = index + 1, and go to step 2; if If all aircraft have completed their sorties, the earliest available time t1 of the search path is retrieved. Similarly, the set of takeoff runways that cause runway intrusions due to the taxiing path is queried. Retrieve the earliest clearing time t2 of the takeoff runway after time t1, which is the earliest taxiing time. During the taxiing process, according to the transfer collision avoidance mechanism, the aircraft is delayed to avoid collisions and the actual taxiing start time t3 is determined. Proceed to Case 4.

[0136] Case 4: Execute takeoff preparation and dispatch. After the helicopter is in position, it immediately begins to prepare for takeoff, such as unfolding the rotor, and its preparation completion time is t1; after retrieving time t1, after the fixed-wing aircraft in front of the offshore platform takes off, wait for its wake to disappear, and after the helicopter in front of the same takeoff position takes off, wait for it to fly to a safe distance, and use this time as the earliest time the aircraft can take off t2; using this time as the starting time, retrieve the time t3 when the takeoff interference parking position corresponding to the takeoff position is cleared, which is the takeoff time of the aircraft, and let W g =W g -{i *},S g =S g ∪{i *}, set index = 1, and go to step 2.

[0137] Step 4: After the deployment is completed, output the deployment plan and calculate the objective function value.

[0138] Step 5: The fixed-wing aircraft warm-up process is shifted to the right. In the decoding process of the present invention, in order to complete each process as early as possible, the start time is the earliest possible start time. For fixed-wing aircraft, they generally start taxiing into position directly after warming up, rather than starting warming up immediately when the aircraft is in a parking position that can be warmed up as in the current decoding, which will cause the engine to wait for a long time and waste fuel. Therefore, the start time of the fixed-wing aircraft engine warm-up process is postponed so that its end time is exactly the start time of taxiing into position to avoid unnecessary standby time.

[0139] The individual fitness function value is calculated as follows:

[0140]

[0141] in, is the weight coefficient of the aircraft taxiing time.

[0142] In one embodiment, the dispatching priority sequence of the current whale individual is updated according to the differential information of the dispatching priorities corresponding to the current whale individual and another whale individual in the initialized whale population, and the step of obtaining the updated current whale individual includes: determining the foraging method of the current whale individual according to the size relationship between the random number and the preset foraging method selection threshold; the foraging methods include shrinking and surrounding foraging, bubble net foraging and random hunting; if the foraging method of the current whale individual is shrinking and surrounding foraging, obtaining the optimal whale individual of the initialized whale population, using the first collaborative participation degree to obtain the differential information of the dispatching priorities corresponding to the current individual and the optimal individual, and updating the dispatching priority sequence of the current individual according to the differential information to obtain the updated current whale individual; if the foraging method of the current whale individual is bubble net foraging, obtaining the initialized The optimal whale individual of the whale population after the acquisition, the differential information of the dispatching priorities corresponding to the current individual and the optimal individual is obtained by using the second collaborative participation degree, and the dispatching priority sequence of the current individual is updated according to the differential information to obtain the updated current whale individual; if the foraging method of the current whale individual is random hunting, the differential information of the dispatching priorities corresponding to the current individual and the random individual is obtained by using the first collaborative participation degree, and the dispatching priority sequence of the current individual is updated according to the differential information to obtain the updated current whale individual; updating the dispatching priority sequence of the current whale individual according to the differential information to obtain the updated current whale individual includes: updating the dispatching priority sequence of the current whale individual according to the differential information, and recombining the updated dispatching priority sequence with the take-off position selection sequence corresponding to the current whale individual to obtain the updated current whale individual.

[0143] In this embodiment, on the basis of maintaining the original framework of the whale optimization algorithm, the three optimization processes of shrinking encirclement foraging, bubble net foraging and random swimming foraging are redesigned, and the differential information cooperation mechanism is adopted to calculate the optimal process of the two random individuals in the population. and Extract the corresponding dispatch priority sequence and Using the difference information of the two with the collaborative participation degree F, we can get the priority sequence of guiding individuals Then with the original takeoff position information Recombination to obtain new individuals The specific operations are as follows:

[0144]

[0145] The above formula mainly includes the following two steps:

[0146] Step 1: Get humpback whale individual Z with the first collaborative participation r1 ,Z r2 The difference information:

[0147]

[0148] For each dimension, the principle is as follows:

[0149]

[0150] Among them, rand(·) is a random number uniformly distributed on (0,1), F is the first collaborative participation degree, D′ max for The dimension is the number of aircraft dispatched, α is the learning dimension, s′ is the learning factor, t is the current iteration number, T is the maximum iteration number, and [·] is the rounding operation.

[0151] Step 2: Use differential information to update the individual's own priority sequence:

[0152]

[0153] For each dimension, the principle is as follows:

[0154]

[0155] in, refers to individuals Using differential information Δ i After moving, the priority code originally located at position j.

[0156] In step 1, a learning factor mechanism is introduced to determine the individual learning dimension in the subsequent discretized whale optimization algorithm. α determines the value of the first collaborative participation in the discretized design, and is also used to determine the maximum dimension of the effect of some operations on individuals in the population restart mechanism. Since there is a blocking relationship between parking spaces when aircraft are dispatched, the primary factor affecting the fitness of the scheduling sequence is the order of aircraft scheduling. When the learning dimension is small, the individual retains more self-information, which is helpful for global search. When the learning dimension is large, the individual retains less self-information and approaches the learning individual faster, which is helpful for local search. The learning dimension α determines the maximum individual dimension that can be acted on in the shrinking surround foraging, random hunting, and field re-insertion and field reversal operations in the population restart mechanism of the IWOA algorithm. According to this feature, as the number of iterations increases, let α gradually increase from 1 to [s′·D′ max +1], in order to effectively balance the global exploration ability and local development ability of the algorithm, α is increased using an exponential function.

[0157] like Figure 2 As shown, a schematic diagram of the differential information cooperation mechanism is provided. The subscript vector at the corresponding position is The subscript vector after shifting using the differential information is In ascending order Sort the subscripts in Extracted from according to Subscript exchange sequence is synchronously rearranged to obtain Will and Recombination can be obtained If the sorting process If the same subscript appears in the , the subscript that was on the left before sorting will be on the right after sorting to ensure the feasibility and diversity of the operation.

[0158] Shrinking and surrounding foraging: for the current individual And the optimal individual of the population exist:

[0159]

[0160] Bubble Network Foraging: For the current individual And the optimal individual of the population exist:

[0161]

[0162] Among them, F′ is the second collaborative participation degree, F′=|[D′ max ·e bl ·cos(2πl)]|, D′ max represents the maximum dimension of an individual, b is a constant used to define the shape of the spiral, l is a random number in (-1,1), [·] represents rounding, and |·| represents the absolute value.

[0163] Random hunting: For the current individual and random individuals in the population exist:

[0164]

[0165] First, the threshold size relationship is selected according to the random number and the foraging method to decide whether to choose bubble net foraging. Secondly, when |A|≤1, the algorithm performs convergent encirclement foraging. When |A|>1, the algorithm performs random hunting. These two foraging methods are the specific embodiment of local search and global search. The value of is determined by the convergence factor Control, that is The change of controls the balance between the global search capability and the local search capability of the algorithm. Therefore, the present invention adjusts the convergence factor The decreasing method is improved as follows:

[0166]

[0167] In the algorithm iteration process, an exponential function is used to decay Through this operation, the convergence factor presents nonlinear dynamic changes, which can effectively balance the global search and local search.

[0168] In one embodiment, Figure 3 As shown, a flowchart of an IWOA algorithm flowchart is provided, and the method also includes: when the optimal whale individual of the whale population has not been updated for L generations, a multi-strategy hierarchical reconstruction mechanism is adopted to restart the population; the multi-strategy hierarchical reconstruction mechanism includes: obtaining the number of individuals in the whale population, and dividing the whale individuals in the whale population into multiple layers; obtaining the optimal whale individual of the whale population under the current number of iterations and the historical optimal solution of each whale individual; performing mutation operations on the take-off position selection sequence and the dispatching priority sequence in the optimal whale individual, and reorganizing the mutated take-off position selection sequence and the dispatching priority sequence to update the whale individuals in the odd layers; performing mutation operations on the take-off position selection sequence and the dispatching priority sequence in the historical optimal solution of each whale individual, and reorganizing the mutated take-off position selection sequence and the dispatching priority sequence to update the whale individuals in the even layers; and obtaining a new population according to the updated whale individuals.

[0169] In this embodiment, during the algorithm iteration process, when the optimal solution of the population has not been updated for L generations, a population restart mechanism is introduced. This mechanism obtains a new population by performing corresponding operations on the historical optimal solution of the individual and the optimal solution of the population. The specific operations are shown in the following table:

[0170] Table 1 Population restart

[0171]

[0172] In the pseudo code of Table 1, sizepop is the number of individuals in the population, floor is the function of rounding to negative infinity, is the historical optimal solution of individual i, corresponding to and is the optimal solution for the population, corresponding to and is the reorganized individual of individual i. In Table 1, the field re-insertion operation includes: for the take-off position selection sequence and dispatch priority sequence of an individual, randomly select a field with a length not greater than α at any position, extract it and reinsert it into any position of the remaining fields, where α is the individual learning dimension; the two-point crossover operation includes: for the take-off position selection sequence and dispatch priority sequence of an individual, randomly select two different positions in the field, and exchange the data of the two positions; the field reversal operation includes: for the take-off position selection sequence and dispatch priority sequence of an individual, randomly select a field with a length not greater than α at any position, and reverse the order of the selected sequence.

[0173] In this mechanism, a multi-strategy hierarchical reconstruction mechanism is adopted, and when reconstructing the population, the individual In and Then they are reorganized to form new individuals. This operation successfully changes the initial layout of the aircraft and the corresponding take-off sequence, making the initial parking layout and dispatch sequence of helicopters and fixed-wing aircraft more diversified, and fully considering the factors affecting fitness. Since each initial layout has its own optimal dispatch sequence, this involves two-layer optimization, that is, the optimization of the upper initial layout and the optimization of the dispatch sequence under certain layout conditions in the lower layer. Through this restart mechanism, the algorithm can fully optimize the solution space.

[0174] In a specific embodiment, Figure 3 As shown, a flowchart of an IWOA algorithm is provided, which includes population initialization, pre-constraint retrieval, prey hunting and random hunting, and population restart. First, the take-off position selection and dispatch priority of each aircraft to be transferred are encoded, and multiple whale individuals are randomly generated according to the encoding method to initialize the whale population. Pre-constrained retrieval is performed on each whale individual in the current whale population, and the whale individuals with interference between the parking position and the take-off position are optimized and adjusted, which can reduce the effective search space; then, the encoding operation is performed on each whale individual to perform population evaluation, and the fitness function value of each whale individual is obtained, and the individual historical optimal and the global historical optimal are saved; then, the foraging method is selected to optimize the dispatch priority of the aircraft to be transferred. When the generated random number is greater than or equal to the foraging method selection threshold, the bubble net foraging method is selected. Otherwise, when the modulus value of A is less than 1, the shrinkage encirclement foraging is selected. When the modulus value of A is greater than or equal to 1, the random hunting method is selected for foraging. If the optimal solution of the population is still not updated after L generations, the take-off position selection and dispatch priority are optimized by restarting the population at the same time, so as to optimize the initial arrangement. When t>T, the mixed dispatch scheduling scheme corresponding to the current optimal whale individual is output to perform the take-off scheduling of the mixed aircraft group.

[0175] In a specific embodiment, in order to verify the model and optimization algorithm for the DSPMF problem proposed in the present invention, the parking positions of the offshore platform used for simulation are parking positions A1-A16 and parking positions P1-P7. In the case of 12 aircraft dispatch, the parking position set is specified as Ω 12 =[A1, A6, A7, A8, A9, A10, A11, A12, A13, A14, A15, A16]. The parking spaces in this set are selected because any parking space in the set can complete the warm-up operation of the fixed-wing aircraft. In the DSPMF simulation experiment, the aircraft mooring / unmooring time is 30s, and according to the safety requirements of shipboard transportation, the aircraft transportation speed does not exceed 3.6km / h. In order to adjust the algorithm parameters, the present invention adopts L 16 (3 4 ) The orthogonal table was used to conduct optimization tests on the algorithm parameters, and the optimal solution was obtained as follows: population size Np = 100, learning factor s′ = 1, foraging mode selection threshold p = 0.5, and population restart threshold L = 10. The algorithm parameter settings of the above optimal solution were selected, and the algorithm iteration termination condition was set to 20,000 scheduling evaluation times. Three cases of 8 aircraft, 12 aircraft, and 16 aircraft were simulated and optimized. Each case involved four helicopters. Figure 4 As shown in the figure, a schematic diagram of the change trend of the optimization index of the 12-aircraft dispatch transfer scheduling is provided, where (a) is a schematic diagram of the change trend of the fleet dispatch completion time, and (b) is a schematic diagram of the change trend of the fixed-wing aircraft taxiing time. The fleet dispatch completion time converges to the optimal value C max =13.96min, fixed-wing aircraft taxiing time and TT = 22.85min. Figure 5 Gantt chart for fleet scheduling under the optimal plan for 12 aircraft dispatching. Figure 6 This is the Gantt chart of take-off position occupancy under the optimal plan for 12 aircraft deployment. Figure 5 In the figure, each row of Gantt bars represents an aircraft, and its number is shown on the vertical axis, and the horizontal axis is time. Jj in the Gantt box represents the dispatch operation stage j. When the second stage of the fixed-wing aircraft takes a very short time, it is not displayed. The transfer taxiing process of the aircraft in the figure is represented by a military gray Gantt box. The starting parking position and the target parking position are marked on the left and right ends of the gray Gantt box. Figure 6 In the figure, each row of Gantt bars represents a take-off position, and its number is shown on the vertical axis. The numbers in the Gantt box mean the aircraft number-the dispatch operation phase number. Combining the two Gantt charts, it can be seen that the scheduling process is consistent with the model constraints.

[0176] In summary, when the number of aircraft in the fleet is small and the dispatch process basically does not involve the warm-up and transportation of fixed-wing aircraft, both dispatch modes can be used. However, when the fleet is large and the aircraft types are complex, the mixed dispatch mode of fixed-wing aircraft and helicopters is more efficient than the current solution.

[0177] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in the present invention, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0178] In one embodiment, Figure 7 As shown, a takeoff scheduling device for a fixed-direction hybrid aircraft fleet based on a whale algorithm is provided, comprising: a parameter acquisition module 702, a model construction module 704, a model optimization module 706 and an optimization output module 708, wherein:

[0179] The parameter acquisition module 702 is used to acquire the mixed sortie mission parameters corresponding to the preset fixed-wing mixed aircraft group sortie mission; the mixed sortie mission parameters include the aircraft type of each aircraft in the mixed aircraft group, the first take-off position set corresponding to the take-off position of the fixed-wing aircraft, and the second take-off position set corresponding to the take-off position of the helicopter;

[0180] The model building module 704 is used to build a mixed sortie scheduling model for sortie priority and takeoff position selection of each aircraft in the mixed fleet according to preset constraints and mixed sortie mission parameters, with the minimum fleet sortie completion time and the minimum fixed-wing aircraft taxiing time as the objective function;

[0181] The model optimization module 706 is used to initialize the whale population according to the mixed dispatching mission parameters, update the priority sequence of the current whale individual according to the differential information of the dispatching priority of the current whale individual and another whale individual in the initialized whale population, obtain the updated current whale individual, iteratively update each whale individual in the population, and obtain a new whale population;

[0182] The optimization output module 708 is used to iteratively update the whale population and output the current hybrid dispatch scheduling plan when the pre-selected iteration stop condition is met; the hybrid dispatch scheduling plan is used to perform takeoff dispatch scheduling of a fixed-direct hybrid fleet.

[0183] In one embodiment, the model optimization module 706 is further used to perform a decoding operation on each whale individual in the initialized population, and calculate the fitness function value of each whale individual according to the hybrid dispatch scheduling scheme and fitness function generated after the individual decoding, so as to obtain the optimal whale individual; the fitness function includes the fleet dispatch completion time and the fixed-wing aircraft taxiing time; the decoding operation includes: extracting the dispatch priority information and take-off position selection information corresponding to the current whale individual to initialize the set to be scheduled, and initialize the scheduled set and the executed process record; the executed process record is a record of each to-be-scheduled set in the initialized set to be scheduled The invention discloses a matrix of executed procedures of the aircraft to be scheduled; according to the take-off position number corresponding to the current aircraft to be scheduled, the aircraft type of the aircraft to be scheduled is determined, and the corresponding departure process is executed according to the aircraft type; the next stage of the aircraft to be scheduled is selected according to the executed process, and when the aircraft to be scheduled completes the take-off and dispatching stage, the executed process record, the to-be-scheduled set and the scheduled set corresponding to the aircraft to be scheduled are updated; the executed process record, the to-be-scheduled set and the scheduled set are updated iteratively, and when the preset iteration termination condition is met, the iteration is stopped, and a mixed dispatch scheduling plan is output; the mixed dispatch scheduling plan includes a mixed dispatch timing plan and a take-off position allocation plan.

[0184] In one embodiment, the model optimization module 706 is also used to determine the foraging method of the current whale individual according to the size relationship between the random number and the preset foraging method selection threshold; the foraging methods include shrinking and encircling foraging, bubble net foraging and random hunting; if the foraging method of the current whale individual is shrinking and encircling foraging, the optimal whale individual of the initialized whale population is obtained, and the differential information of the dispatching priority corresponding to the current individual and the optimal individual is obtained by using the first collaborative participation degree, and the priority sequence of the current individual is updated according to the differential information to obtain the updated current whale individual; if the foraging method of the current whale individual is bubble net foraging, the optimal whale individual of the initialized whale population is obtained, and the differential information of the dispatching priority corresponding to the current individual and the optimal individual is obtained by using the second collaborative participation degree, and the priority sequence of the current individual is updated according to the differential information to obtain the updated current whale individual; if the foraging method of the current whale individual is random hunting, the differential information of the dispatching priority corresponding to the current individual and the random individual is obtained by using the first collaborative participation degree, and the priority sequence of the current individual is updated according to the differential information to obtain the updated current whale individual.

[0185] In one of the embodiments, the model optimization module 706 is also used to allocate a corresponding take-off position to each aircraft in the mixed fleet according to the aircraft type, the first take-off position set and the second take-off position set of each aircraft to obtain a take-off position selection sequence; obtain a priority sequence according to the order in which each aircraft takes off; encode the take-off position selection sequence and the priority sequence to obtain whale individuals; and randomly generate multiple whale individuals to initialize the whale population.

[0186] In one embodiment, the model optimization module 706 is also used to update the dispatch priority sequence of the current whale individual according to the differential information, and reorganize the updated dispatch priority sequence and the take-off position selection sequence corresponding to the current whale individual to obtain an updated current whale individual.

[0187] In one of the embodiments, the model optimization module 706 is also used to use a multi-strategy hierarchical reconstruction mechanism to restart the population when the optimal whale individual of the whale population has not been updated for L generations; the multi-strategy hierarchical reconstruction mechanism includes: obtaining the number of individuals in the whale population, and dividing the whale individuals in the whale population into multiple layers; obtaining the optimal whale individual of the whale population under the current number of iterations and the historical optimal solution of each whale individual; performing mutation operations on the take-off position selection sequence and the dispatch priority sequence in the optimal whale individual, and reorganizing the mutated take-off position selection sequence and the dispatch priority sequence to update the whale individuals in the odd layers; performing mutation operations on the take-off position selection sequence and the dispatch priority sequence in the historical optimal solution of each whale individual, and reorganizing the mutated take-off position selection sequence and the dispatch priority sequence to update the whale individuals in the even layers; and obtaining a new population based on the updated whale individuals.

[0188] In one of the embodiments, the model optimization module 706 is also used to pre-search the situation where there is interference between parking positions and take-off positions during the dispatch of each aircraft based on the dispatch priority sequences and take-off position selection sequences corresponding to multiple randomly generated whale individuals, and adjust the dispatch priority sequence of the corresponding whale individual based on the search results to complete the pre-constraint of the dispatch priority of the whale individual.

[0189] In one embodiment, the model building module 704 is also used to preset constraints including aircraft timing planning constraints, space resource constraints and take-off scheduling constraints for a mixed fleet; aircraft timing planning constraints include transfer operation timing constraints, support operation timing constraints, connection constraints between transfer operations and support operations, and deflector cooling and reset time interval constraints for fixed-wing aircraft; space resource constraints include multi-aircraft transfer collision avoidance constraints and priority constraints for occupying the same space; take-off scheduling constraints include take-off interval constraints, take-off position selection constraints, and waiting position and take-off position matching constraints and take-off configuration constraints for fixed-wing aircraft.

[0190] For the specific limitations of the takeoff scheduling device for a fleet of fixed-wing and direct-aircraft hybrids based on the whale algorithm, please refer to the limitations of the takeoff scheduling method for a fleet of fixed-wing and direct-aircraft hybrids based on the whale algorithm above, which will not be repeated here. Each module in the above-mentioned takeoff scheduling device for a fleet of fixed-wing and direct-aircraft hybrids based on the whale algorithm can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0191] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for scheduling the take-off of a fixed-direction hybrid aircraft fleet based on a whale algorithm is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0192] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0193] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method in the above embodiment when executing the computer program.

[0194] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method in the above embodiment are implemented.

[0195] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0196] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, 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, they should be considered to be within the scope of this specification.

[0197] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A takeoff scheduling method for a fixed-direct hybrid fleet based on a whale algorithm, characterized in that: The method comprises: Acquire mixed sortie mission parameters corresponding to a preset fixed-wing mixed aircraft group sortie mission; the mixed sortie mission parameters include the aircraft type of each aircraft in the mixed aircraft group, a first takeoff position set corresponding to the takeoff position of the fixed-wing aircraft, and a second takeoff position set corresponding to the takeoff position of the helicopter; According to the preset constraints, taking the minimum sortie completion time of the fleet and the minimum taxiing time of the fixed-wing aircraft as the objective function, a mixed sortie scheduling model for the sortie priority and take-off position selection of each aircraft in the mixed fleet is constructed; Initialize the whale population according to the mixed dispatch mission parameters, update the dispatch priority sequence of the current whale individual according to the differential information of the dispatch priority corresponding to the current whale individual and another whale individual in the initialized whale population, obtain the updated current whale individual, iteratively update each whale individual in the population, and obtain a new whale population; Iteratively update the whale population, and when the pre-selected iteration stop condition is met, stop the iteration and output the current hybrid dispatch scheduling plan; the hybrid dispatch scheduling plan is used for the takeoff dispatch scheduling of the fixed-direct hybrid aircraft group; Before updating the dispatching priority sequence of the current whale individual according to the differential information of the dispatching priority corresponding to the current whale individual and another whale individual in the initialized whale population, it includes: Perform a decoding operation on each whale individual in the initialized population, and calculate the fitness function value of each whale individual according to the hybrid dispatch scheduling scheme and fitness function generated after individual decoding to obtain the optimal whale individual; the fitness function includes the fleet dispatch completion time and the fixed-wing aircraft taxiing time; The decoding operation includes: Extract the dispatch priority information and take-off position selection information corresponding to the current whale individual to initialize the set to be scheduled, and initialize the scheduled set and the executed process record; the executed process record is a matrix that records the executed process of each aircraft to be scheduled in the initialized set to be scheduled; According to the take-off position number corresponding to the current aircraft to be scheduled, the aircraft type of the aircraft to be scheduled is determined, and the corresponding departure process is executed according to the aircraft type; Selecting the next stage of the aircraft to be scheduled according to the executed process, and updating the executed process record, the to-be-scheduled set and the scheduled set corresponding to the aircraft to be scheduled after the aircraft to be scheduled completes the take-off and dispatching stage; Iteratively update the executed process record, the to-be-scheduled set and the scheduled set, and when a preset iteration termination condition is met, stop the iteration and output a hybrid dispatch scheduling plan; the hybrid dispatch scheduling plan includes a hybrid dispatch timing plan and a take-off position allocation plan; The step of updating the dispatching priority sequence of the current whale individual according to the differential information of the dispatching priority corresponding to the current whale individual and another whale individual in the initialized whale population to obtain the updated current whale individual includes: Determine the foraging mode of the current individual whale according to the relationship between the random number and the preset foraging mode selection threshold; the foraging mode includes shrinking and encircling foraging, bubble net foraging and random hunting; If the foraging mode of the current whale individual is the shrinking and encircling foraging, the optimal whale individual of the initialized whale population is obtained, and the differential information of the dispatching priority corresponding to the current whale individual and the optimal whale individual is obtained by using the first collaborative participation degree, and the dispatching priority sequence of the current whale individual is updated according to the differential information to obtain the updated current whale individual; the mathematical model of the shrinking and encircling foraging is: in, for The dispatch priority sequence, is the current whale individual, for The dispatch priority sequence, is the optimal whale individual, F is the first collaborative participation degree, D′ max is the individual maximum dimension, α is the learning dimension, s′ is the learning factor, t is the current iteration number, T is the maximum iteration number, and [·] is the rounding operation; If the foraging method of the current whale individual is the bubble net foraging, the optimal whale individual of the initialized whale population is obtained, and the differential information of the dispatching priority corresponding to the current whale individual and the optimal whale individual is obtained by using the second collaborative participation degree, and the dispatching priority sequence of the current whale individual is updated according to the differential information to obtain the updated current whale individual; the mathematical model of the shrinking and encircling foraging is: Among them, F′ is the second collaborative participation degree, F′=|[D′ max ·e bl ·cos(2πl)]|, b is a constant used to define the shape of the spiral, l is a random number in (-1,1), [·] indicates rounding, and |·| indicates the absolute value; If the foraging mode of the current whale individual is the random hunting, the differential information of the dispatching priorities of the current whale individual and the random whale individual is obtained by using the first collaborative participation degree, and the dispatching priority sequence of the current whale individual is updated according to the differential information to obtain the updated current whale individual; the mathematical model of the shrinking and encircling foraging is: in, for The dispatch priority sequence, is a random whale individual; The step of initializing the whale population according to the mixed sortie mission parameters comprises: According to the aircraft type of each aircraft in the mixed aircraft group, the first take-off position set and the second take-off position set, a corresponding take-off position is allocated to each aircraft to obtain a take-off position selection sequence; According to the order in which each aircraft takes off, the dispatch priority sequence is obtained; Encoding the take-off position selection sequence and the dispatching priority sequence to obtain individual whales; Multiple whale individuals are randomly generated to initialize the whale population.

2. The method according to claim 1, characterized in that The updating of the dispatching priority sequence of the current whale individual according to the differential information to obtain the updated current whale individual includes: The dispatching priority sequence of the current individual whale is updated according to the differential information, and the updated dispatching priority sequence and the take-off position selection sequence corresponding to the current individual whale are recombined to obtain the updated current individual whale.

3. The method according to claim 2, characterized in that The method further comprises: When the optimal whale individuals of the whale population have not been updated for L generations, a multi-strategy hierarchical reconstruction mechanism is used to restart the population; The multi-strategy hierarchical reconstruction mechanism includes: Obtain the number of individuals in the whale population, and divide the whale individuals in the whale population into multiple layers; Obtain the optimal whale individual of the whale population under the current number of iterations and the historical optimal solution of each whale individual; Perform mutation operations on the take-off position selection sequence and the dispatching priority sequence in the optimal whale individual respectively, and reorganize the mutated take-off position selection sequence and the dispatching priority sequence to update the whale individuals in the odd layers; Perform mutation operations on the take-off position selection sequence and the dispatching priority sequence in the historical optimal solution of each individual whale, reorganize the mutated take-off position selection sequence and the dispatching priority sequence, and update the whale individuals in the even-numbered layers; Based on the updated whale individuals, a new population is obtained.

4. The method according to claim 3, characterized in that The method further comprises: According to the dispatch priority sequences and take-off position selection sequences corresponding to the randomly generated multiple whale individuals, the situation of interference between the parking position and the take-off position during the dispatch of each aircraft is pre-searched, and the dispatch priority sequence of the corresponding whale individual is adjusted according to the search result to complete the pre-constraint of the dispatch priority of the whale individual.

5. The method according to claim 1, characterized in that The preset constraints include aircraft timing planning constraints, space resource constraints and take-off and dispatch scheduling constraints of the mixed fleet; The aircraft timing planning constraints include the transport operation timing constraints, the support operation timing constraints, the connection constraints between the transport operation and the support operation, and the deflector cooling and resetting time interval constraints for fixed-wing aircraft; The space resource constraints include multi-machine transport collision avoidance constraints and priority constraints for occupying the same space; The take-off dispatch scheduling constraints include take-off interval constraints, take-off position selection constraints, and waiting position and take-off position matching constraints for fixed-wing aircraft and take-off configuration constraints.

6. A takeoff scheduling device for a fixed-direct hybrid fleet based on a whale algorithm, characterized in that: The device comprises: A parameter acquisition module is used to acquire mixed sortie mission parameters corresponding to a preset fixed-wing mixed aircraft group sortie mission; the mixed sortie mission parameters include the aircraft type of each aircraft in the mixed aircraft group, a first take-off position set corresponding to the take-off position of the fixed-wing aircraft, and a second take-off position set corresponding to the take-off position of the helicopter; A model building module is used to build a mixed sortie scheduling model for sortie priority and takeoff position selection of each aircraft in a mixed fleet based on preset constraints and taking the minimum fleet sortie completion time and the minimum fixed-wing aircraft taxiing time as objective functions; A model optimization module is used to initialize the whale population according to the mixed dispatch mission parameters, update the dispatch priority sequence of the current whale individual according to the differential information of the dispatch priority corresponding to the current whale individual and another whale individual in the initialized whale population, obtain the updated current whale individual, iteratively update each whale individual in the population, and obtain a new whale population; The optimization output module is used to iteratively update the whale population and output the current hybrid dispatch scheduling plan when the pre-selected iteration stop condition is met; the hybrid dispatch scheduling plan is used to perform takeoff dispatch scheduling of a fixed-direct hybrid fleet; The model optimization module is also used to perform a decoding operation on each whale individual in the initialized population, and calculate the fitness function value of each whale individual according to the hybrid dispatch scheduling scheme and fitness function generated after the individual decoding, so as to obtain the optimal whale individual; the fitness function includes the fleet dispatch completion time and the fixed-wing aircraft taxiing time; the decoding operation includes: extracting the dispatch priority information and take-off position selection information corresponding to the current whale individual to initialize the set to be scheduled, and initialize the scheduled set and the executed process record; the executed process record is a matrix that records the executed process of each aircraft to be scheduled in the initialized set to be scheduled; based on According to the take-off position number corresponding to the current aircraft to be scheduled, the aircraft type of the aircraft to be scheduled is judged, and the corresponding departure process is executed according to the aircraft type; the next stage of the aircraft to be scheduled is selected according to the executed process, and when the aircraft to be scheduled completes the take-off and dispatching stage, the executed process record, the to-be-scheduled set and the scheduled set corresponding to the aircraft to be scheduled are updated; the executed process record, the to-be-scheduled set and the scheduled set are updated iteratively, and when the preset iteration termination condition is met, the iteration is stopped, and a mixed dispatch scheduling plan is output; the mixed dispatch scheduling plan includes a mixed dispatch timing plan and a take-off position allocation plan; The model optimization module is also used to determine the foraging method of the current whale individual according to the size relationship between the random number and the preset foraging method selection threshold; the foraging methods include shrinking and encircling foraging, bubble net foraging and random hunting; if the foraging method of the current whale individual is the shrinking and encircling foraging, the optimal whale individual of the initialized whale population is obtained, and the differential information of the dispatching priority corresponding to the current whale individual and the optimal whale individual is obtained by using the first collaborative participation degree, and the dispatching priority sequence of the current whale individual is updated according to the differential information to obtain the updated current whale individual; the mathematical model of shrinking and encircling foraging is: in, for The dispatch priority sequence, is the current whale individual, for The dispatch priority sequence, is the optimal whale individual, F is the first collaborative participation degree, D′ max is the individual maximum dimension, α is the learning dimension, s′ is the learning factor, t is the current iteration number, T is the maximum iteration number, and [·] is the rounding operation; if the foraging method of the current whale individual is the bubble net foraging, the optimal whale individual of the initialized whale population is obtained, and the differential information of the dispatching priority corresponding to the current whale individual and the optimal whale individual is obtained by using the second collaborative participation degree, and the dispatching priority sequence of the current whale individual is updated according to the differential information to obtain the updated current whale individual; the mathematical model of the shrinking encirclement foraging is: Among them, F′ is the second collaborative participation degree, F′=|[D′ max ·e bl ·cos(2πl)]||, b is a constant used to define the shape of the spiral, l is a random number in (-1,1), [·] represents rounding, and |·| represents the absolute value; if the foraging mode of the current whale individual is the random hunting, the first collaborative participation degree is used to obtain the differential information of the dispatching priority corresponding to the current whale individual and the random whale individual, and the dispatching priority sequence of the current whale individual is updated according to the differential information to obtain the updated current whale individual; the mathematical model of the shrinking encirclement foraging is: in, for The dispatch priority sequence, is a random whale individual; The model optimization module is also used to assign a corresponding take-off position to each aircraft in the mixed fleet according to the aircraft type of each aircraft, the first take-off position set and the second take-off position set to obtain a take-off position selection sequence; obtain a dispatch priority sequence according to the order in which each aircraft takes off; encode the take-off position selection sequence and the dispatch priority sequence to obtain whale individuals; and randomly generate multiple whale individuals to initialize the whale population.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.