Intelligent scheduling method and system for aircraft jumping out of hangar

Abstract

The invention discloses an intelligent scheduling method and system for an aircraft jumping hangar. The method comprises the steps that the hangar obtains local aircraft flight operation data in real time; the hangar acquires stop request information of the jump flight aircraft in real time, performs data communication with the aircraft control center in real time according to the stop request information, acquires flight operation data of the aircraft, and performs data synchronization on the state of the aircraft and the hangar; acquiring real-time scene operation data of the hangar, and performing aircraft cluster scheduling according to the real-time scene operation data of the hangar; the state data of the hangar and the aircraft are obtained and synchronized in real time, deep reinforcement learning and mixed integer programming are combined, the scheduling strategy is dynamically adjusted, load balancing and optimal resource utilization are achieved, the problems of scheduling chaos and errors caused by communication faults in an existing hangar scheduling system are solved, and the scheduling efficiency is improved. The DRL model optimizes task allocation, ensures load balance and reduces waiting time by learning real-time states of an aircraft and a hangar.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent scheduling, and in particular to an intelligent scheduling method and system for aircraft hangar jump. Background Art

[0002] The current hangar scheduling system involves multi-aircraft cluster scheduling of local aircraft and roaming aircraft, which requires efficient communication and coordination between the aircraft cluster and multiple hangars. However, in the existing system, the communication link between the aircraft cluster and the hangar is prone to failure, resulting in unstable data transmission, which in turn causes scheduling confusion and errors. This communication problem will seriously affect the accuracy of cluster scheduling and the reliability of the system, thereby hindering the orderly operation of the hangar, increasing the risk of mission delays, and reducing overall operational efficiency. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent scheduling method and system for aircraft hangar jump, which combines deep reinforcement learning and mixed integer programming to dynamically adjust the scheduling strategy and optimize task allocation, load balancing and resource utilization.

[0004] The purpose of the present invention can be achieved through the following technical solutions: The present application provides an intelligent scheduling method for aircraft hangar jump, comprising: An intelligent scheduling method for aircraft hangar jump includes the following steps: The hangar obtains local aircraft flight operation data in real time; The hangar obtains the parking request information of the hopping aircraft in real time, communicates with the aircraft control center in real time according to the parking request information, obtains the flight operation data of the aircraft, and synchronizes the status of the aircraft with the hangar; Acquire the real-time scene operation data of the hangar, and perform aircraft cluster scheduling according to the real-time scene operation data of the hangar; the scene operation data includes operating sites, replenishment operation sites, take-off and landing operation sites, and idle operation sites; Among them, the method for scheduling aircraft clusters based on real-time scene operation data of the hangar includes: obtaining real-time position information of the first aircraft from the first hangar; sending the real-time position information of the first aircraft to the second hangar; when the first hangar receives the real-time position information of the third aircraft, sending a task instruction to the third aircraft, wherein the third aircraft is the aircraft in the second hangar.

[0005] Furthermore, the data synchronization of the aircraft status with the hangar is specifically used to obtain the aircraft's location information and task status in real time, generate and display a task allocation table, and the contents include: The aircraft control center receives a first data packet from a first aircraft, wherein the first data packet carries the current position information of the first aircraft and information about the currently executed mission; receives a second data packet from a third aircraft, wherein the second data packet carries the current position information of the third aircraft and information about the currently executed mission; generates a task allocation table based on the first data packet and the second data packet, wherein the task allocation table records the position information of each aircraft and information about the currently executed mission; and displays the task allocation table.

[0006] Furthermore, the flight operation data includes at least one of the following: aircraft position information, flight route, take-off and landing time, flight load, load information, heading information, speed information, remaining fuel information and status information.

[0007] Furthermore, before obtaining the real-time position information of the first aircraft from the first hangar, the method further includes: receiving a task request message from a user terminal, wherein the task request message carries identification information of the first aircraft.

[0008] Furthermore, when generating the task allocation table, deep reinforcement learning is used to optimize the task allocation, including: Define the state vector s as the current state of the aircraft and hangar; the state vector s is expressed as: ; in, Indicates the real-time position coordinates of the 1st to nth aircraft; Indicates the real-time speed of the 1st to nth aircraft; Indicates the remaining fuel of the 1st to nth aircraft; Indicates the real-time mission status of the hangar; Define action a as a scheduling decision, including ,in represents the scheduling action for the i-th aircraft; Design a reward function R to evaluate the quality of each action; Specific Where T(s,a) represents the task completion time, S(s,a) represents the safety index, and U(s,a) represents the resource utilization rate. is the weight coefficient; Define state value function and action value function to quantify the value of each state and action; Use the loss function of the DQN algorithm for training, update the network weight θ and select the optimal action value function; The loss function is expressed as: , where y represents the target Q value; is the value estimate of the current network for taking action a in state s; θ is the current network parameter, Represents the expected value, which is used to represent the statistical average of a sample; The trained DRL model is deployed to the scheduling system, and the optimal scheduling decision is output in real time according to the current state s.

[0009] Furthermore, in the process of optimizing task allocation, the mixed integer programming model is used to deal with constraints and optimization problems, including: According to the action space of the DRL model, the decision variables of the MIP model are defined, and the decision of assigning tasks to each aircraft is represented as a binary variable , where i represents the index of the aircraft and j represents the index of the mission; Combine the reward function of the DRL model to construct the objective function of the MIP model; The specific objective function is expressed as: ;in represents the accumulation of the costs of all aircraft i and all tasks j, is the weight coefficient of task completion time, represents the safety index of aircraft i when performing mission j, is the weight coefficient of resource utilization, represents the resource utilization rate when aircraft i performs mission j, is the decision variable; Add constraints to the MIP model based on the real-time status of the aircraft and hangar; Use a mathematical optimization solver to solve the MIP model and find the optimal solution that satisfies all constraints; Analyze the solution results, apply the optimization results to actual aircraft scheduling, and adjust the model parameters according to the actual operation conditions.

[0010] Furthermore, the constraints of the MIP model include: task allocation constraints, each task is assigned to exactly one aircraft, expressed as: ; Aircraft capacity constraint: the load of an aircraft must not exceed its maximum capacity, expressed as: ;in represents the resource requirement of mission j for aircraft i, represents the resource capacity of aircraft i; Time window constraint: the take-off and landing time of the aircraft must be within a specific time window, expressed as: ;in represents the time when aircraft i starts to perform mission j, and They represent the earliest and latest take-off and landing times of aircraft i respectively; Safety constraints, which ensure safe distances or other safety standards between aircraft, are expressed as: ,in Indicates the safety threshold.

[0011] Furthermore, the method also includes real-time collision detection: when it is detected that there is a risk of collision between the first aircraft and the third aircraft, an avoidance instruction is sent to the third aircraft so that the third aircraft avoids the area where the first aircraft is located.

[0012] An intelligent scheduling system for aircraft hangar jumps includes a data synchronization and communication module, a real-time scene analysis module and an intelligent scheduling decision module. The data synchronization and communication module is used to obtain the flight operation data of the local aircraft in real time, obtain the parking request information of the hopping aircraft, and communicate data with the aircraft control center to synchronize the status of the aircraft and the hangar data; The real-time scene analysis module is used to obtain the real-time scene operation data of the hangar, obtain the real-time position information of the first aircraft from the first hangar, and send the information to the second hangar, receive the real-time position information of the third aircraft, and send a task instruction; The intelligent scheduling decision module makes intelligent scheduling decisions through a deep reinforcement learning unit and a mixed integer programming unit, sends mission instructions to the aircraft, and adjusts the flight route.

[0013] Furthermore, the deep reinforcement learning unit uses the DRL algorithm to optimize task allocation, trains the DRL model, updates the network weights to select the optimal action value function, deploys the trained DRL model to the scheduling system, and outputs the optimal scheduling decision in real time according to the current state; The mixed integer programming unit defines the decision variables of the MIP model, represents the decision of assigning tasks to each aircraft as a binary variable, constructs the objective function of the MIP model, adds the constraints of the MIP model, and then uses a mathematical optimization solver to solve the MIP model to find the optimal solution that meets all constraints.

[0014] The beneficial effects of the present invention are: The present invention acquires and synchronizes the status data of the hangar and the aircraft in real time, combines deep reinforcement learning and mixed integer programming, dynamically adjusts the scheduling strategy, realizes load balancing and optimal resource utilization, and solves the scheduling confusion and error problems caused by communication failures in the existing hangar scheduling system. The DRL model optimizes task allocation by learning the real-time status of the aircraft and the hangar, ensures load balancing, reduces waiting time, and improves work efficiency. At the same time, the MIP model processes constraints, such as aircraft capacity and time window, to ensure scheduling under the premise of meeting all constraints; in addition, the real-time collision detection function avoids the risk of collision between aircraft by sending avoidance instructions, thereby enhancing the safety of the system. This method not only improves the intelligence and efficiency of the scheduling system, but also enhances its flexibility and robustness, effectively responds to the dynamically changing operating environment, and shows a strong application potential in complex aviation scheduling problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] For better understanding and implementation, the technical solution of the present application is described in detail below with reference to the accompanying drawings.

[0016] Figure 1 A schematic diagram of a flow chart of an intelligent scheduling method for aircraft hangar jump provided in Example 1 of the present application; Figure 2 A flowchart of an intelligent scheduling method for aircraft hangar jumps provided in Example 1 of the present application for optimizing task allocation through deep reinforcement learning; Figure 3 A mixed integer programming model of an intelligent scheduling method for aircraft hangar jump provided in Example 1 of the present application is used to process constraints and optimization problems. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects taken by the present invention to achieve the predetermined invention purpose, exemplary embodiments will be described in detail here, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of methods and systems consistent with some aspects of the present application as detailed in the attached claims.

[0018] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0019] The specific implementation methods, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0020] Example 1 See also Figure 1-Figure 3 ,This embodiment provides an intelligent scheduling method and system for aircraft hangar jump, which combines deep reinforcement learning and mixed integer programming to dynamically adjust the scheduling strategy and optimize task allocation, load balancing and resource utilization.

[0021] The present invention provides an intelligent scheduling method for aircraft hangar jump, comprising the following steps: S1. The hangar obtains local aircraft flight operation data in real time; S2. The hangar obtains the parking request information of the hopping aircraft in real time, communicates data with the aircraft control center in real time according to the parking request information, obtains the flight operation data of the aircraft, and synchronizes the status of the aircraft with the hangar; S3. Obtain the real-time scene operation data of the hangar, and perform aircraft cluster scheduling according to the real-time scene operation data of the hangar; Among them, the method for scheduling aircraft clusters based on real-time scene operation data of the hangar includes: obtaining real-time position information of the first aircraft from the first hangar; sending the real-time position information of the first aircraft to the second hangar; when the first hangar receives the real-time position information of the third aircraft, sending a task instruction to the third aircraft, wherein the third aircraft is the aircraft in the second hangar.

[0022] The scenario operation data includes operating sites, supply operating sites, take-off and landing operating sites, and idle operating sites, etc.; This invention can globally control the operating status of the target hangar scene and form a reasonable, efficient and orderly aircraft cluster intelligent scheduling method.

[0023] Furthermore, the data synchronization of the aircraft status with the hangar is specifically used to obtain the aircraft's location information and task status in real time, generate and display a task allocation table, and the contents include: The aircraft control center receives a first data packet from a first aircraft, wherein the first data packet carries the current position information of the first aircraft and information about the currently executed mission; receives a second data packet from a third aircraft, wherein the second data packet carries the current position information of the third aircraft and information about the currently executed mission; generates a task allocation table based on the first data packet and the second data packet, wherein the task allocation table records the position information of each aircraft and information about the currently executed mission; and displays the task allocation table.

[0024] Furthermore, the flight operation data includes at least one of the following: aircraft position information, flight route, take-off and landing time, flight load, load information, heading information, speed information, remaining fuel information and status information.

[0025] Furthermore, before obtaining the real-time position information of the first aircraft from the first hangar, the method further includes: receiving a task request message from a user terminal, wherein the task request message carries identification information of the first aircraft.

[0026] Furthermore, when generating task allocation tables, deep reinforcement learning can be used to optimize task allocation, ensure load balancing of aircraft, reduce waiting time, and improve overall operational efficiency.

[0027] Specific content includes: S11. Define the state vector s as the current state of the aircraft and the hangar; include: ; in, Indicates the real-time position coordinates of the 1st to nth aircraft; Indicates the real-time speed of the 1st to nth aircraft; Indicates the remaining fuel of the 1st to nth aircraft; Indicates the real-time mission status of the hangar, including mission type, mission priority, mission completion and other information.

[0028] Specifically, the state vector s represents the current state information of the aircraft, reflecting the real-time data of the aircraft, including: the position information is the position of the aircraft, which can be used as a part of the state vector to represent the current physical position of the aircraft; the velocity vector is the velocity of the aircraft and is also an important part of the state vector, describing the dynamic characteristics of the aircraft. The real-time speed is a key parameter required for the aircraft during navigation and mission execution; the mission information is that the state vector should also include the mission status of the aircraft (such as whether it is in the process of executing a mission, mission priority, etc.); the state vector s is actually a multi-dimensional information vector that integrates the real-time data of the aircraft.

[0029] S12. Define action a as a scheduling decision, including ,in Represents the scheduling action for the i-th aircraft, such as assigning tasks, adjusting flight routes, issuing avoidance instructions, etc.; Specifically, action a is the decision made by the system on the state of the aircraft. The action may include the following: Position adjustment action Based on the current position and speed of the aircraft (provided by the state vector), the action can determine the next movement direction or speed adjustment of the aircraft. For example, based on the distance between the real-time position of the aircraft and the target mission point, the action will guide its movement path; Task allocation action involves the allocation decision of specific tasks, especially based on the real-time priority of the task and the current mission state of the aircraft, the order of task execution can be dynamically changed to ensure the best use of resources.

[0030] S13. Design a reward function R to evaluate the quality of each action, including indicators such as task completion time, safety, and resource utilization. Specific Where T(s,a) represents the task completion time, S(s,a) represents the safety index, and U(s,a) represents the resource utilization rate. is the weight coefficient.

[0031] S14. Define the state value function and the action-value function , quantify the value of each state and action, and help the intelligent scheduling system make the best decision.

[0032] Specific ; ,in represents the cumulative reward after taking action a in state s.

[0033] S15. Use the loss function of the DQN algorithm for training, update the network weight θ and select the optimal action value function; The specific calculation target Q value y: , where r is the immediate reward received after taking action a at time step t; γ is a discount factor that measures the current value of future rewards; is the state of the environment at time step t+1; is in state The best action among all possible actions; is a set of network parameters other than the current action a, used to calculate the next state The expected reward.

[0034] The loss function is expressed as: ,in is the value estimate of the current network for taking action a in state s; θ is the current network parameter, Represents the expected value, which is used here to represent the statistical mean of the sample.

[0035] Specifically, by minimizing the loss function L(θ), the network parameter θ can be adjusted to make the network's estimate of the action value closer to the target Q value y, thereby improving the accuracy of the model's prediction.

[0036] S16. Deploy the trained DRL model to the scheduling system and output the optimal scheduling decision in real time based on the current state s , .

[0037] The DRL model can learn to make optimal scheduling decisions in a complex dynamic environment, thereby achieving aircraft load balancing, reducing waiting time, and improving overall work efficiency. By optimizing task allocation through deep reinforcement learning (DRL), real-time analysis and decision-making of aircraft and hangar status are achieved, significantly improving the intelligence and efficiency of the work process. By defining detailed state vectors and flexible action spaces, the system can make accurate scheduling decisions based on the real-time position, speed, fuel volume of the aircraft and the task status of the hangar. The design of a reasonable reward function further ensures the efficiency and safety of task allocation. At the same time, the introduction of state value function and action value function provides a mathematical basis for learning decision-making for the DRL model. Through the training of the DQN algorithm, the model learns how to choose the optimal action under various states to minimize task completion time, maximize safety, and optimize resource utilization. Finally, the deployed DRL model can continuously learn and adapt in a dynamically changing environment, provide a load-balanced scheduling solution for aircraft, effectively reduce waiting time, improve overall work efficiency, and show strong practical application potential.

[0038] Furthermore, in the process of optimizing task allocation, the mixed integer programming model is used to deal with constraints and optimization problems, including: S21. Based on the action space of the DRL model, define the decision variables of the MIP model, and represent the decision of assigning tasks to each aircraft as a binary variable , where i represents the index of the aircraft and j represents the index of the mission; S22. Combine the reward function of the DRL model to construct the objective function of the MIP model. The objective function may aim to minimize the task completion time, improve safety and resource utilization; The specific objective function is expressed as: ;in represents the accumulation of the costs of all aircraft i and all tasks j, is the weight coefficient of task completion time, indicating the importance of task completion time in the total cost. represents the safety index of aircraft i when performing mission j, is the weight coefficient of resource utilization, indicating the importance of resource utilization in the total cost. represents the resource utilization rate when aircraft i performs mission j, is the decision variable, which is a binary variable indicating whether aircraft i performs task j (1 means execution, 0 means no execution).

[0039] Specifically, the objective function can be interpreted as: for each pair of aircraft and mission, a cost that is a weighted combination of mission completion time, safety, and resource utilization is calculated, and then these costs are accumulated through decision variables to find the aircraft-to-mission allocation scheme that minimizes the total cost Z.

[0040] In practical applications, the objective function will be combined with a series of constraints, such as ensuring that each mission is assigned to exactly one vehicle, or the flight path and load constraints of the vehicle, to form a complete MIP model and solve it using a mathematical optimization solver.

[0041] S23. Add constraints of the MIP model according to the real-time status of the aircraft and the hangar; Specifically include: task allocation constraints, each task is assigned to exactly one aircraft, expressed as: ; Aircraft capacity constraint: the load of an aircraft must not exceed its maximum capacity, expressed as: ;in represents the resource requirement of mission j for aircraft i, represents the resource capacity of aircraft i; Time window constraint: the take-off and landing time of the aircraft must be within a specific time window, expressed as: ;in represents the time when aircraft i starts to perform mission j, and They represent the earliest and latest take-off and landing times of aircraft i respectively; Safety constraints, which ensure safe distances or other safety standards between aircraft, are expressed as: ,in Indicates the safety threshold.

[0042] S24. Use a mathematical optimization solver to solve the MIP model and find the optimal solution that satisfies all constraints. S25. Analyze the solution results to ensure the feasibility and effectiveness of the solution, apply the optimization results to the actual aircraft scheduling, and adjust the model parameters according to the actual operation conditions to improve future scheduling decisions.

[0043] Specifically, by combining deep reinforcement learning (DRL) with mixed integer programming (MIP), the decision-making ability of DRL and the advantages of MIP in dealing with complex constraints are fully utilized in the process of optimizing task allocation. The action space of the DRL model guides the definition of decision variables of MIP, while the reward function of DRL inspires the construction of MIP objective function to minimize task completion time and improve safety and resource utilization. The MIP model ensures the feasibility of the solution through a series of constraints such as task allocation, aircraft capacity, time window and safety standards. The MIP model is solved using a mathematical optimization solver to find the optimal solution that satisfies all constraints, and these solutions are applied to actual aircraft scheduling, thereby achieving load balancing, reducing waiting time, and improving overall operational efficiency. In addition, by analyzing the solution results and adjusting the model parameters according to the actual operation situation, the scheduling decision can be continuously improved, making the system more adaptable to the dynamically changing operating environment. This method not only improves the intelligence level of task allocation, but also enhances the flexibility and robustness of the system, showing a strong application potential in complex aviation scheduling problems.

[0044] It should be noted that in applications that combine deep reinforcement learning (DRL) with mixed integer programming (MIP), DRL is responsible for learning and exploring in continuous decision spaces, while MIP deals with the optimization of discrete decisions. Specifically, DRL can be used to initially explore and evaluate various possible scheduling decisions, which can be continuous, such as flight path selection or priority of task assignment. These continuous decisions can then be quantized or discretized to fit the needs of the MIP model. For example, the DRL model can assign a priority score to each task, which is then converted into binary decision variables (such as whether the task is assigned to a specific aircraft). In this way, the soft decisions provided by DRL can be converted into hard decisions in the MIP model, allowing MIP to optimize task assignment and scheduling strategies while satisfying all discrete constraints. In this way, the flexibility of DRL and the constraint satisfaction ability of MIP are combined to jointly realize an efficient and reliable intelligent scheduling system.

[0045] Furthermore, the method also includes real-time collision detection: when it is detected that there is a risk of collision between the first aircraft and the third aircraft, an avoidance instruction is sent to the third aircraft so that the third aircraft avoids the area where the first aircraft is located.

[0046] Example 2 This embodiment provides an intelligent scheduling system for aircraft jump hangars, which acquires and synchronizes the status information of the aircraft and the hangar in real time through a data synchronization and communication module; uses a real-time scene analysis module to monitor the hangar scene and transmit the aircraft location information; the intelligent scheduling decision module combines deep reinforcement learning (DRL) and mixed integer programming (MIP) to optimize task allocation and flight routes, achieve load balancing, reduce waiting time, and improve work efficiency and resource utilization. DRL optimizes the decision strategy, and MIP uses a mathematical solver to find the optimal solution under multiple constraints to ensure the safe and efficient completion of the task.

[0047] Specific content includes: Data synchronization and communication module, used to obtain local aircraft flight operation data in real time, obtain the parking request information of the hopping aircraft, and communicate data with the aircraft control center to synchronize the aircraft status and hangar data; The real-time scene analysis module is used to obtain the real-time scene operation data of the hangar, including the operation site, the supply operation site, the take-off and landing operation site, and the idle operation site, etc., obtain the real-time position information of the first aircraft from the first hangar, and send the information to the second hangar, receive the real-time position information of the third aircraft, and send the task instruction; The intelligent scheduling decision module makes intelligent scheduling decisions through deep reinforcement learning units and mixed integer programming units, sends mission instructions to the aircraft, adjusts the flight route, and ensures the implementation of the scheduling strategy.

[0048] Furthermore, the deep reinforcement learning unit uses the DRL algorithm to optimize task allocation, ensure load balancing of the aircraft, reduce waiting time, and improve overall operation efficiency. It trains the DRL model, updates the network weights to select the optimal action value function, deploys the trained DRL model to the scheduling system, and outputs the optimal scheduling decision in real time according to the current status.

[0049] The mixed integer programming unit defines the decision variables of the MIP model, represents the decision of assigning tasks to each aircraft as binary variables, and constructs the objective function of the MIP model, aiming to minimize the task completion time, improve safety and resource utilization, add constraints of the MIP model, such as task allocation constraints, aircraft capacity constraints, time window constraints, safety constraints, etc., and then use the mathematical optimization solver to solve the MIP model to find the optimal solution that meets all constraints.

[0050] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An intelligent scheduling method for aircraft hangar jump, characterized in that: The steps include: The hangar obtains local aircraft flight operation data in real time; The hangar obtains the parking request information of the hopping aircraft in real time, communicates with the aircraft control center in real time according to the parking request information, obtains the flight operation data of the aircraft, and synchronizes the status of the aircraft with the hangar; Obtain the real-time scene operation data of the hangar, and perform aircraft cluster scheduling based on the real-time scene operation data of the hangar; The scenario operation data includes operating sites, supply operating sites, take-off and landing operating sites, and idle operating sites; Among them, the method for scheduling aircraft clusters based on real-time scene operation data of the hangar includes: obtaining real-time position information of the first aircraft from the first hangar; sending the real-time position information of the first aircraft to the second hangar; when the first hangar receives the real-time position information of the third aircraft, sending a task instruction to the third aircraft, wherein the third aircraft is the aircraft in the second hangar.

2. The intelligent scheduling method for aircraft hangar jump according to claim 1 is characterized in that: The data synchronization between the aircraft status and the hangar is specifically used to obtain the aircraft's location information and mission status in real time, generate and display a task allocation table, and the contents include: The aircraft control center receives a first data packet from a first aircraft, wherein the first data packet carries the current position information of the first aircraft and information about the currently executed mission; receives a second data packet from a third aircraft, wherein the second data packet carries the current position information of the third aircraft and information about the currently executed mission; generates a task allocation table based on the first data packet and the second data packet, wherein the task allocation table records the position information of each aircraft and information about the currently executed mission; and displays the task allocation table.

3. The intelligent scheduling method for aircraft hangar jump according to claim 1 is characterized in that: The flight operation data includes at least one of the following: aircraft position information, flight route, take-off and landing time, flight load, load information, heading information, speed information, remaining fuel information and status information.

4. The intelligent scheduling method for aircraft hangar jump according to claim 1 is characterized in that: Before obtaining the real-time position information of the first aircraft from the first hangar, the method further includes: receiving a task request message from a user terminal, wherein the task request message carries identification information of the first aircraft.

5. The intelligent scheduling method for aircraft hangar jump according to claim 2 is characterized in that: When generating the task allocation table, deep reinforcement learning is used to optimize task allocation, including: Define the state vector s as the current state of the aircraft and hangar; the state vector s is expressed as: ; in, Indicates the real-time position coordinates of the 1st to nth aircraft; Indicates the real-time speed of the 1st to nth aircraft; Indicates the remaining fuel of the 1st to nth aircraft; Indicates the real-time mission status of the hangar; Define action a as a scheduling decision, including ,in represents the scheduling action for the i-th aircraft; Design a reward function R to evaluate the quality of each action; Specific Where T(s,a) represents the task completion time, S(s,a) represents the safety index, and U(s,a) represents the resource utilization rate. is the weight coefficient; Define state value function and action value function to quantify the value of each state and action; Use the loss function of the DQN algorithm for training, update the network weight θ and select the optimal action value function; The loss function is expressed as: , where y represents the target Q value; is the value estimate of the current network for taking action a in state s; θ is the current network parameter, Represents the expected value, which is used to represent the statistical average of a sample; The trained DRL model is deployed to the scheduling system, and the optimal scheduling decision is output in real time according to the current state s.

6. The intelligent scheduling method for aircraft hangar jump according to claim 5 is characterized in that: In the process of optimizing task allocation, mixed integer programming models are used to deal with constraints and optimization problems, including: According to the action space of the DRL model, the decision variables of the MIP model are defined, and the decision of assigning tasks to each aircraft is represented as a binary variable , where i represents the index of the aircraft and j represents the index of the mission; Combine the reward function of the DRL model to construct the objective function of the MIP model; The specific objective function is expressed as: ;in represents the accumulation of the costs of all aircraft i and all tasks j, is the weight coefficient of task completion time, represents the safety index of aircraft i when performing mission j, is the weight coefficient of resource utilization, represents the resource utilization rate when aircraft i performs mission j, is the decision variable; Add constraints to the MIP model based on the real-time status of the aircraft and hangar; Use a mathematical optimization solver to solve the MIP model and find the optimal solution that satisfies all constraints; Analyze the solution results, apply the optimization results to actual aircraft scheduling, and adjust the model parameters according to the actual operation conditions.

7. The intelligent scheduling method for aircraft hangar jump according to claim 6 is characterized in that: The constraints of the MIP model include: The task assignment constraint is that each task is assigned to exactly one aircraft, expressed as: ; Aircraft capacity constraint: the load of an aircraft must not exceed its maximum capacity, expressed as: ;in represents the resource requirement of mission j for aircraft i, represents the resource capacity of aircraft i; Time window constraint: the take-off and landing time of the aircraft must be within a specific time window, expressed as: ;in represents the time when aircraft i starts to perform mission j, and They represent the earliest and latest take-off and landing times of aircraft i respectively; Safety constraints, which ensure safe distances or other safety standards between aircraft, are expressed as: ,in Indicates the safety threshold.

8. The intelligent scheduling method for aircraft hangar jump according to claim 1 is characterized by: The method further includes real-time collision detection: when it is detected that there is a collision risk between the first aircraft and the third aircraft, an avoidance instruction is sent to the third aircraft so that the third aircraft avoids the area where the first aircraft is located.

9. An aircraft hangar intelligent scheduling system, applied to an aircraft hangar intelligent scheduling method as claimed in any one of claims 1 to 8, characterized in that: Including data synchronization and communication module, real-time scene analysis module and intelligent scheduling decision module, The data synchronization and communication module is used to obtain the flight operation data of the local aircraft in real time, obtain the parking request information of the hopping aircraft, and communicate data with the aircraft control center to synchronize the status of the aircraft and the hangar data; The real-time scene analysis module is used to obtain the real-time scene operation data of the hangar, obtain the real-time position information of the first aircraft from the first hangar, and send the information to the second hangar, receive the real-time position information of the third aircraft, and send a task instruction; The intelligent scheduling decision module makes intelligent scheduling decisions through a deep reinforcement learning unit and a mixed integer programming unit, sends mission instructions to the aircraft, and adjusts the flight route.

10. The intelligent dispatching system for aircraft hangar jump according to claim 9, characterized in that: The deep reinforcement learning unit uses the DRL algorithm to optimize task allocation, trains the DRL model, updates the network weights to select the optimal action value function, deploys the trained DRL model to the scheduling system, and outputs the optimal scheduling decision in real time according to the current state; The mixed integer programming unit defines the decision variables of the MIP model, represents the decision of assigning tasks to each aircraft as a binary variable, constructs the objective function of the MIP model, adds the constraints of the MIP model, and then uses a mathematical optimization solver to solve the MIP model to find the optimal solution that meets all constraints.

Images