An aircraft hangar maintenance and hangar transfer collaborative scheduling method and device

Abstract

The application discloses an aircraft hangar maintenance and warehouse entry transfer collaborative scheduling method and device, relates to the technical field of scheduling optimization and aviation engineering management, and comprises the following steps: establishing a collaborative scheduling problem model; in the transfer scheduling stage, taking the minimization of the transfer time and the maintenance urgency proxy target as the optimization target, solving the aircraft warehouse entry transfer sequence and the actual entry time by using an intelligent optimization algorithm; in the maintenance scheduling stage, taking the actual entry time as the constraint and taking the maximization of the fleet wave availability as the optimization target, solving the hangar maintenance scheme and the maintenance completion time by using the intelligent optimization algorithm; feeding back the maintenance completion time to the transfer scheduling stage, repeatedly iterating until convergence, and outputting the converged aircraft warehouse entry transfer and hangar maintenance scheduling scheme. Through repeated execution of the cycle of "transfer-maintenance-feedback", the close coupling between the two sub-problems of transfer and maintenance is effectively solved, and the global optimality of the scheduling scheme is significantly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of scheduling optimization and aeronautical engineering management, in particular, to the field of computer-aided intelligent scheduling, and particularly relates to a method and device for collaborative scheduling of aircraft hangar maintenance and entry transfer. BACKGROUND

[0002] In large aircraft maintenance center (Maintenance, Repair, and Overhaul, MRO) and other scenarios, aircraft scheduling is a crucial support activity. Among them, transferring the aircraft from the parking area to the dedicated hangar for complex and long-period maintenance is the core link to ensure the health status of the aircraft fleet. This process naturally contains two closely coupled sub-problems: entry transfer scheduling of the aircraft and maintenance scheduling in the hangar. Transfer scheduling determines when the aircraft can arrive at the hangar to start maintenance, while maintenance scheduling directly affects the final completion time of the aircraft, and thus affects its subsequent availability. Related scheduling methods often have significant defects. Traditional manual scheduling relies heavily on the personal experience of the scheduler, and in the face of large-scale, multi-constrained complex scenarios, it is difficult to make globally optimal decisions, is low in efficiency and prone to errors. Some primary computer-aided scheduling systems usually treat transfer and maintenance as two independent and decoupled problems, planning transfer first and then planning maintenance. This fragmented approach ignores the deep internal relationship between the two, for example, a seemingly efficient transfer order may cause critical aircraft to be delayed due to waiting for maintenance resources, thereby seriously affecting the mission plan of the entire aircraft fleet. Although some technologies attempt to perform collaborative scheduling, their optimization objectives are often limited to traditional efficiency indicators such as minimizing total completion time or maximizing resource utilization. These indicators cannot directly reflect the support capability of the scheduling scheme for future flight mission plans. In particular, in large-scale mission applications, the ultimate purpose of scheduling is not just "fast", but to ensure that there are enough available aircraft at the predetermined future time point. Therefore, related technologies generally lack a collaborative scheduling method that can be driven by future task availability as the core and can effectively handle the dynamic feedback relationship between transfer and maintenance. SUMMARY

[0003] The purpose of the present application is to provide a method and device for collaborative scheduling of aircraft hangar maintenance and entry transfer, which divides the entire complex scheduling problem into a two-stage (transfer scheduling stage, maintenance scheduling stage) iterative optimization process, and realizes deep collaboration and global optimization of the two stages of transfer and maintenance through a two-stage iterative optimization framework.

[0004] To achieve the above purpose, the present application provides the following solutions:

[0005] In a first aspect, the present application provides a method for collaborative scheduling of aircraft hangar maintenance and entry transfer, comprising:

[0006] Based on the set of aircrafts to be dispatched, the set of hangar maintenance tasks, the set of aircrafts into hangar transfer tasks, and the set of preset dispatch waves, a collaborative scheduling problem model is established, and the collaborative scheduling problem model is decomposed into a process of iterative optimization of the transfer scheduling stage and the maintenance scheduling stage.

[0007] In the transfer scheduling stage, an intelligent optimization algorithm is used to solve the aircrafts into hangar transfer sequence and determine the actual arrival time of each aircraft, with the minimum transfer time and maintenance urgency proxy target as the optimization objective; the transfer time includes the maximum arrival time of all aircrafts and the total arrival time of aircrafts to be maintained; the maintenance urgency proxy target is a weighted delay penalty based on the maintenance completion time.

[0008] In the maintenance scheduling stage, an intelligent optimization algorithm is used to solve the hangar maintenance scheme and determine the maintenance completion time of each aircraft, with the actual arrival time as the constraint and the maximum fleet wave availability as the optimization objective; the fleet wave availability is the weighted average value of the ratio of the number of aircrafts performing each wave task to the total number of aircrafts planned to participate in each wave in the set of dispatch waves.

[0009] The maintenance completion time of the maintenance scheduling stage is fed back to the transfer scheduling stage to dynamically correct the maintenance urgency proxy target, and the iteration is repeated until convergence, and the converged aircrafts into hangar transfer and hangar maintenance scheduling scheme is output.

[0010] In an embodiment, an intelligent optimization algorithm is used to solve the aircrafts into hangar transfer sequence, with the minimum transfer time and maintenance urgency proxy target as the optimization objective, specifically including:

[0011] A first objective function is constructed for the set of aircrafts into hangar transfer tasks, with the minimum transfer time, transfer group load balancing degree, and maintenance urgency proxy target as the optimization objective.

[0012] An intelligent optimization algorithm is used to perform iterative search in multiple aircrafts into hangar transfer schemes according to the first objective function, to obtain the aircrafts into hangar transfer sequence that makes the first objective function reach the minimum value; wherein the iterative search process is: selecting the current aircrafts into hangar transfer sequence according to the first objective function value generated by the current iteration, and feeding back the current aircrafts into hangar transfer sequence to the next iteration to gradually approach the optimal solution.

[0013] The calculation formula of the first objective function is:

[0014] .

[0015] Wherein, is the first objective function; is the arrival time of aircraft . The subset of aircraft awaiting repair is a set A subset of; To ensure load balance of the dispatching group; For urgent maintenance targets; The preset normalized weighting coefficients satisfy... And its value range is [0, 1].

[0016] The formula for calculating the load balance of the dispatching group is:

[0017] .

[0018] in, Assemble the transport team. For the dispatch team personnel Total working hours; This represents the average working hours of the dispatch team members.

[0019] The formula for calculating the maintenance urgency proxy target is:

[0020] .

[0021] in, For the set of dispatch waves, For waves Importance weights To plan to participate in waves aircraft subset, The function represents the portion of the penalty value that is positive. For airplane Repair completion time, To plan to participate in waves The moment of preparation for deployment begins.

[0022] In one implementation, with actual arrival time as a constraint and maximizing the availability of aircraft fleet waves as the optimization objective, an intelligent optimization algorithm is used to solve the hangar maintenance plan, specifically including:

[0023] Using the actual arrival time as an input constraint, the earliest time when each aircraft can begin hangar maintenance is limited.

[0024] For the hangar maintenance task set, a second objective function is constructed with the optimization objectives of maximizing the availability of aircraft fleet waves and minimizing the load balancing of maintenance personnel.

[0025] Using intelligent optimization algorithms, a hangar maintenance scheme that minimizes the second objective function is searched in the feasible solution space.

[0026] The formula for calculating the second objective function is as follows:

[0027] .

[0028] in, The second objective function is... For fleet wave availability; For the load balancing of maintenance personnel; The weighting coefficients for multi-objective optimization have a value range of [0.01, 0.2].

[0029] The formula for calculating the availability of the aircraft fleet wavelets is as follows:

[0030] .

[0031] in, For the set of dispatch waves; For waves Importance weights, satisfying And for any two waves and ,like Prior to but ; The total number of aircraft; For airplane Repair completion time; For waves The moment preparations for deployment begin; This is a symbolic function, defined as follows: the function value is 1 when its input value is greater than zero, and 0 otherwise.

[0032] The formula for calculating the load balancing degree of maintenance personnel is:

[0033] .

[0034] in, Assemble the maintenance personnel; For maintenance personnel Total working hours; This represents the average working hours of maintenance personnel.

[0035] In one embodiment, during the maintenance scheduling phase, the constraints also include hangar resource constraints, specifically including: maintenance workstation space constraints and parallel operation constraints in the maintenance workshop.

[0036] The space constraint of the maintenance workstation is: at any time Assigned to any aircraft Used to perform a certain category of maintenance skills The number of maintenance personnel must not exceed the number of aircraft. The maintenance stop position is associated with the aforementioned maintenance skill category. the set available workstation space capacity .

[0037] the repair shop parallel operation constraint is that the number of repair tasks simultaneously performed in the repair shop that can be operated in parallel at any time should not exceed the maximum number of parallel operations set for the repair shop , wherein the maximum number of parallel operations of the repair shop is in the range [2, 10].

[0038] In an embodiment, the convergence condition uses a first convergence condition or a second convergence condition.

[0039] The first convergence condition is that in two consecutive iterations, let the fleet wave availability calculated in the i-th iteration and the (i+1)-th iteration be and respectively, and the improvement value satisfies , wherein is a preset convergence threshold, and the value range is [0.001, 0.01].

[0040] The second convergence condition is that the number of iterations reaches a preset maximum number of iterations , wherein the value range is [50, 200].

[0041] In an embodiment, the calculation formula of the repair completion time is:

[0042] .

[0043] , wherein is the repair completion time of the aircraft , is the hangar repair task set of the aircraft , is the start time of the repair task , and is the actual execution duration of the repair task . The second aspect of the application provides an aircraft hangar repair and warehouse transfer collaborative scheduling device, comprising: a problem modeling module, a transfer scheduling module, a repair scheduling module, and a collaborative optimization module.

[0044] The second aspect of the application provides an aircraft hangar repair and warehouse transfer collaborative scheduling device, comprising: a problem modeling module, a transfer scheduling module, a repair scheduling module, and a collaborative optimization module.

[0045] ​​​​The problem modeling module is configured to establish a collaborative scheduling problem model based on a set of aircrafts to be dispatched, a set of hangar maintenance tasks, a set of aircrafts to be transported into the hangar, and a set of preset dispatch waves, and decompose the collaborative scheduling problem model into a process of iterative optimization of the transportation scheduling stage and the maintenance scheduling stage.

[0046] The transportation scheduling module is configured to, in the transportation scheduling stage, solve a sequence of aircrafts to be transported into the hangar by using an intelligent optimization algorithm with an optimization objective of minimizing transportation time and maintenance urgency proxy target, and determine actual arrival times of each aircraft; the transportation time includes a maximum arrival time of all the aircrafts and a total arrival time of the aircrafts to be maintained; the maintenance urgency proxy target is a weighted delay penalty based on a maintenance completion time.

[0047] The maintenance scheduling module is configured to, in the maintenance scheduling stage, solve a hangar maintenance scheme by using an intelligent optimization algorithm with an optimization objective of maximizing fleet wave availability under a constraint of the actual arrival times, and determine a maintenance completion time of each aircraft; the fleet wave availability is a weighted average of a ratio of a number of the aircrafts performing each wave task to a total number of the aircrafts planned to participate in each wave in the set of dispatch waves.

[0048] The collaborative optimization module is configured to feed back the maintenance completion time of the maintenance scheduling stage to the transportation scheduling stage to dynamically correct the maintenance urgency proxy target, and repeatedly iterate until convergence, and output the converged aircraft transportation into the hangar and hangar maintenance scheduling scheme.

[0049] In a third aspect, the present application provides a computer device, comprising a memory, a processor, a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the steps of the aircraft hangar maintenance and transportation into the hangar collaborative scheduling method in any one of the above aspects.

[0050] In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the steps of the aircraft hangar maintenance and transportation into the hangar collaborative scheduling method in any one of the above aspects.

[0051] In a fifth aspect, the present application provides a computer program product comprising a computer program, and the computer program is executed by a processor to implement the steps of the aircraft hangar maintenance and transportation into the hangar collaborative scheduling method in any one of the above aspects.

[0052] According to the embodiments of the present application, the following technical effects are achieved:

[0053] The application provides an aircraft hangar maintenance and warehouse entry transfer collaborative scheduling method and device, establishes a collaborative scheduling problem model based on a set of aircrafts to be scheduled, a set of hangar maintenance tasks, a set of aircraft warehouse entry transfer tasks and a set of preset dispatch waves, and decomposes the collaborative scheduling problem model into a process of iterative optimization of the transfer scheduling stage and the maintenance scheduling stage; in the transfer scheduling stage, an efficient and reasonable aircraft warehouse entry transfer sequence is solved with the minimization of transfer time and maintenance urgency proxy target as the optimization target; in the maintenance scheduling stage, the actual entry time is taken as an input constraint, and a hangar maintenance scheme is solved with the maximization of fleet wave availability as the optimization target; the maintenance completion time of the maintenance scheduling stage is fed back to the transfer scheduling stage to dynamically correct the maintenance urgency proxy target, and the cycle of "transfer-maintenance-feedback" is repeatedly executed, each iteration is optimized on the basis of the previous iteration, and the converged aircraft warehouse entry transfer and hangar maintenance scheduling scheme is obtained, thereby effectively solving the close coupling between the transfer and maintenance two sub-problems and significantly improving the global optimality of the scheduling scheme. BRIEF DESCRIPTION OF DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0055] Figure 1 An application environment diagram of an aircraft hangar maintenance and warehouse entry transfer collaborative scheduling method in an embodiment of the present application;

[0056] Figure 2 A flowchart of an aircraft hangar maintenance and warehouse entry transfer collaborative scheduling method provided by an embodiment of the present application;

[0057] Figure 3 A functional module diagram of an aircraft hangar maintenance and warehouse entry transfer collaborative scheduling device provided by an embodiment of the present application;

[0058] Figure 4 A structural diagram of a computer device provided by an embodiment of the present application.

[0059] Reference signs:

[0060] 1-problem modeling module, 2-transfer scheduling module, 3-maintenance scheduling module, 4-collaborative optimization module. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work are within the protection scope of the present application.

[0062] The above purposes, features and advantages of the present application will be more obvious and easy to understand. The present application will be further described in detail below with reference to the drawings and specific embodiments.

[0063] The present application provides a method for collaborative optimization of aircraft hangar level deep maintenance and deck or apron warehouse transfer, which can directly link the scheduling target with future task demand, and through an innovative iterative optimization framework, realize deep collaboration and global optimization of the two stages of transfer and maintenance.

[0064] The aircraft hangar maintenance and warehouse transfer collaborative scheduling method provided by the embodiments of the present application can be applied to, for example Figure 1The application environment shown. Among them, the terminal 101 communicates with the server 102 through the network. The data storage system can store the data required by the server 102 to process. The data storage system can be set up separately, or integrated on the server 102, or placed on the cloud or other servers. The terminal 101 can send the set of aircrafts to be dispatched, the set of hangar maintenance tasks, the set of aircrafts into the hangar transfer tasks, and the set of preset dispatch waves to the server 102. The server 102 receives the set of aircrafts to be dispatched, the set of hangar maintenance tasks, the set of aircrafts into the hangar transfer tasks, and the set of preset dispatch waves, and the server 102 establishes a collaborative scheduling problem model; in the transfer scheduling stage, taking the minimization of the transfer time and the maintenance urgency proxy target as the optimization target, the intelligent optimization algorithm is used to solve the aircraft into the hangar transfer sequence, and the actual arrival time of each aircraft is determined; the transfer time includes the maximum arrival time of all aircrafts and the total arrival time of the aircrafts to be maintained; the maintenance urgency proxy target is a weighted delay penalty based on the maintenance completion time; in the maintenance scheduling stage, taking the actual arrival time as the constraint, taking the maximum fleet wave availability as the optimization target, using the intelligent optimization algorithm to solve the hangar maintenance scheme, and determining the maintenance completion time of each aircraft; the fleet wave availability is the weighted average value of the number of aircrafts executing each wave task in the set of dispatch waves and the total number of aircrafts planned to participate in each wave; the maintenance completion time of the maintenance scheduling stage is fed back to the transfer scheduling stage to dynamically correct the maintenance urgency proxy target, and the iteration is repeated until convergence, and the converged aircraft into the hangar transfer and hangar maintenance scheduling scheme is output. The server 102 can feed back the obtained aircraft into the hangar transfer and hangar maintenance scheduling scheme to the terminal 101. In addition, in some embodiments, the aircraft hangar maintenance and into the hangar transfer collaborative scheduling method can also be realized by the server 102 or the terminal 101 alone, such as the terminal 101 can directly perform aircraft hangar maintenance and into the hangar transfer collaborative scheduling processing, or the server 102 can obtain the set of aircrafts to be dispatched, the set of hangar maintenance tasks, the set of aircrafts into the hangar transfer tasks, and the set of preset dispatch waves from the data storage system, and perform aircraft hangar maintenance and into the hangar transfer collaborative scheduling processing.

[0065] Among them, the terminal 101 can be but not limited to various desktop computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices, and the Internet of Things devices can be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server 102 can be realized by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0066] In an exemplary embodiment, as Figure 2As shown, an aircraft hangar maintenance and warehouse transfer collaborative scheduling method is provided, which is executed by a computer device, specifically can be executed by a terminal or a server alone, or can be executed by a terminal and a server together. In the embodiments of the present application, the method is applied to Figure 1 The server 102 in the method is taken as an example for illustration, including the following steps 201-204. Wherein:

[0067] Step 201, based on the set of aircraft to be dispatched, the set of hangar maintenance tasks, the set of aircraft warehouse transfer tasks, and the set of preset dispatch waves, a collaborative scheduling problem model is established, and the collaborative scheduling problem model is decomposed into a process of iterative optimization of the transfer scheduling stage and the maintenance scheduling stage.

[0068] Step 202, in the transfer scheduling stage, the optimization objective is to minimize the transfer time and the maintenance urgency proxy target, the intelligent optimization algorithm is used to solve the aircraft warehouse transfer sequence, and the actual arrival time of each aircraft is determined; the transfer time includes the maximum arrival time of all aircraft and the total arrival time of aircraft to be maintained; the maintenance urgency proxy target is a weighted delay penalty based on the maintenance completion time.

[0069] Step 203, in the maintenance scheduling stage, the actual arrival time is used as a constraint, the optimization objective is to maximize the fleet wave availability, the intelligent optimization algorithm is used to solve the hangar maintenance scheme, and the maintenance completion time of each aircraft is determined; the fleet wave availability is the weighted average value of the ratio of the number of aircraft performing each wave task to the total number of aircraft planned to participate in each wave in the set of dispatch waves.

[0070] Step 204, the maintenance completion time of the maintenance scheduling stage is fed back to the transfer scheduling stage to dynamically correct the maintenance urgency proxy target, and the iteration is repeated until convergence, and the converged aircraft warehouse transfer and hangar maintenance scheduling scheme is output.

[0071] The steps 201 to 204 are implemented, and based on the set of aircrafts to be dispatched, the set of hangar maintenance tasks, the set of aircrafts to be transported into the hangar, and the set of preset wave sets, the application establishes a collaborative scheduling problem model, and decomposes the collaborative scheduling problem model into the process of iterative optimization of the transportation scheduling stage and the maintenance scheduling stage; in the transportation scheduling stage, the optimization target is to minimize the transportation time and the maintenance urgency proxy target, and an efficient and reasonable aircraft transportation sequence into the hangar is solved; in the maintenance scheduling stage, the actual arrival time is taken as an input constraint, and the optimization target is to maximize the availability of the wave set of the aircraft group, and the hangar maintenance scheme is solved; the maintenance completion time of the maintenance scheduling stage is fed back to the transportation scheduling stage to dynamically correct the maintenance urgency proxy target, and the cycle of “transportation-maintenance-feedback” is repeatedly executed, each iteration is optimized on the basis of the previous iteration, and the converged aircraft transportation into the hangar and hangar maintenance scheduling scheme is obtained, so that the close coupling between the transportation and the maintenance two sub-problems is effectively solved, and the global optimality of the scheduling scheme is significantly improved.

[0072] In step 201, a collaborative scheduling problem is defined: based on the set of aircrafts to be dispatched , the set of hangar maintenance tasks , the set of aircrafts to be transported into the hangar , and the set of preset wave sets , a collaborative scheduling problem model is established, and the primary optimization target is to maximize the availability of the wave set of the aircraft group.

[0073] In another exemplary embodiment of the application, the optimization target is to minimize the transportation time and the maintenance urgency proxy target, and the intelligent optimization algorithm is used to solve the aircraft transportation sequence into the hangar, which is replaced by the following steps 301 to 302:

[0074] Step 301, for the set of aircrafts to be transported into the hangar, a first objective function is constructed, and the optimization target is to minimize the transportation time, the load balancing degree of the transportation group and the maintenance urgency proxy target.

[0075] Step 302, the intelligent optimization algorithm is used to perform iterative search in a plurality of aircraft transportation schemes into the hangar according to the first objective function, and the aircraft transportation sequence into the hangar that makes the first objective function reach the minimum value is obtained; wherein the iterative search process is: the current aircraft transportation sequence into the hangar is selected according to the first objective function value generated in the current iteration, and the current aircraft transportation sequence into the hangar is fed back to the next iteration, so as to gradually approach the optimal solution.

[0076] The calculation formula of the first objective function is:

[0077] .

[0078] Wherein, is the first objective function; for the aircraft to enter the gate; for the subset of aircrafts to be maintained, is a subset of the set ; for the load balancing degree of the dispatch group; for the maintenance urgency proxy objective; for the preset normalized weight coefficient, satisfying , and the value range of each is [0, 1].

[0079] The four components of the first objective function are respectively used for minimizing the maximum transfer completion time (i.e. the maximum entry time), preferentially processing the sum of entry times of aircrafts to be maintained, balancing the work load of the dispatch group, and reducing the risk of wave availability caused by maintenance delay. The optimization objective (i.e. the first objective function) focuses on the efficiency of the transfer stage and indirectly guides the transfer through the maintenance urgency proxy objective to improve the overall wave availability, focusing on the first-stage optimization process.

[0080] The load balancing degree of the dispatch group is measured by calculating the variance of the working time of the personnel of the dispatch group.

[0081] The calculation formula of the load balancing degree of the dispatch group is:

[0082] .

[0083] Wherein, is the set of personnel of the dispatch group; is the total working time of the personnel of the dispatch group ; is the average working time of the personnel of the dispatch group.

[0084] The calculation formula of the maintenance urgency proxy objective is:

[0085] .

[0086] Wherein, is the set of dispatched waves, is the importance weight of the wave , is the subset of aircrafts participating in the wave planned, the function indicates the part with a positive penalty value, is the maintenance completion time of the aircraft , is the start time of the dispatch preparation of the aircraft participating in the wave planned.

[0087] In step 202, the first stage of transfer scheduling optimization is performed: for the set of incoming transfer tasks , the optimization objective is to minimize the transfer time and maintenance urgency proxy, using intelligent optimization algorithms, based on pre-set transfer path rules, transportation resource constraints, and aircraft maintenance progress, to comprehensively evaluate and sort potential transfer tasks, to select the aircraft incoming transfer sequence that can minimize the optimization objective among multiple optional transfer schemes, rather than obtaining the sequence only by pre-initialization. This process is a dynamic programming optimization process, which iteratively solves the optimal transfer sequence according to the objective function value after each optimization, and feeds the result back to the next round of evaluation, and calculates the actual arrival time of each aircraft to the maintenance parking position of the hangar according to the transfer sequence ; the actual arrival time is the earliest time when the aircraft first stops at its designated maintenance parking position of the hangar and meets the conditions for starting maintenance after completing all necessary incoming transfer links. This time is the actual arrival time of each aircraft calculated independently. Its calculation formula is:

[0088] .

[0089] where, represents the time point when the aircraft completes all previous transfer operations and arrives at the designated maintenance parking position, considering the specific transfer path, transfer tool allocation and actual transfer duration; represents the earliest time when the designated maintenance parking position of the aircraft hangar changes from occupied state to available state. Considering the physical process of transfer and the actual accommodation capacity of the parking position, it ensures the rationality and accuracy of the arrival time, providing a reliable starting point for subsequent maintenance scheduling.

[0090] First, after defining the problem elements such as aircraft, tasks and pre-set sortie set, the method enters the first stage of transfer scheduling optimization. The goal of this stage is to generate an efficient and reasonable aircraft incoming transfer sequence. The optimization objective is composite, considering both the efficiency of transfer operations itself, such as minimizing the latest arrival time of all aircraft (i.e. maximum arrival time), and the workload balance of the transfer team, avoiding overwork of some personnel and idleness of others. More importantly, it will initially consider the urgency of the aircraft to be maintained to ensure that aircraft with serious faults or critical tasks can enter the hangar as soon as possible. The output of this stage is a specific transfer sequence and the accurate hangar arrival time of each aircraft calculated from it.

[0091] In another exemplary embodiment of this application, with the actual arrival time as a constraint and maximizing the availability of aircraft fleet waves as the optimization objective, an intelligent optimization algorithm is used to solve the hangar maintenance plan, which is replaced by the following steps 401 to 403:

[0092] Step 401: Using the actual arrival time as an input constraint, limit the earliest time when each aircraft can begin hangar maintenance.

[0093] Step 402: For the hangar maintenance task set, construct a second objective function with the optimization objectives of maximizing the availability of aircraft fleet waves and minimizing the load balancing of maintenance personnel.

[0094] Step 403: Using an intelligent optimization algorithm, search the feasible solution space for a hangar maintenance scheme that minimizes the second objective function.

[0095] The formula for calculating the second objective function is as follows:

[0096] .

[0097] in, The second objective function is... For fleet wave availability; For load balancing of maintenance personnel; The weighting coefficients for multi-objective optimization have a value range of [0.01, 0.2].

[0098] The formula for calculating the availability of the aircraft fleet wavelets is as follows:

[0099] .

[0100] in, For the set of dispatch waves; For waves Importance weights, satisfying And for any two waves and ,like Prior to but ; The total number of aircraft; For airplane Repair completion time; For waves The moment preparations for deployment begin; This is a symbolic function, defined as follows: the function value is 1 when its input value is greater than zero, and 0 otherwise.

[0101] Maintenance personnel load balancing It is measured by calculating the variance of the working hours of maintenance personnel.

[0102] The formula for calculating the maintenance personnel load balancing degree is:

[0103] .

[0104] Wherein, is the set of maintenance personnel; is the total working time of the maintenance personnel ; is the average working time of the maintenance personnel.

[0105] In step 203, the second stage of maintenance scheduling optimization is performed: receiving the actual aircraft entry time vector determined in step 202 as an input constraint, which limits the earliest time when each aircraft can start hangar maintenance. For the set of hangar maintenance tasks , this stage builds a maintenance task network model containing process dependency, resource demand, maintenance personnel skills, and hangar space layout, meets a series of hangar resource constraints such as maintenance workstation space constraints and maintenance workshop parallel operation constraints, and uses intelligent optimization techniques such as genetic algorithms to maximize the fleet wave availability and minimize the maintenance personnel load balancing degree as optimization objectives for multi-objective optimization solution. The solving process searches for the optimal solution in the feasible solution space through dynamic allocation of key resources such as maintenance personnel, maintenance equipment, and workstations and flexible arrangement of task timing, obtains a specific hangar maintenance operation timing scheme and maintenance resource allocation scheme, and calculates the maintenance completion time of each aircraft ; the maintenance completion time refers to the time when the aircraft completes all assigned hangar maintenance tasks and reaches the out-of-hangar state. This time is determined by analyzing all maintenance task processes of the aircraft , logically deducing and accumulating the start time, duration, and dependency relationship between the immediately preceding and immediately following processes of each process, and finally determining the end time of all maintenance tasks, i.e., the calculation formula of the maintenance completion time is:

[0106] .

[0107] Wherein, is the maintenance completion time of the aircraft , is the set of hangar maintenance tasks of the aircraft , is the start time of the maintenance task , is the maintenance task The actual execution time.

[0108] In another exemplary embodiment of this application, during the maintenance scheduling phase, the input constraints also include hangar resource constraints, specifically including: maintenance workstation space constraints and maintenance workshop parallel operation constraints.

[0109] The space constraint of the maintenance workstation is: at any time Assigned to any aircraft Used to perform a certain category of maintenance skills The number of maintenance personnel must not exceed the number of aircraft. The maintenance stop position is associated with the aforementioned maintenance skill category. The set available workstation space capacity .

[0110] The parallel operation constraint in the maintenance workshop is: at any given time... In a maintenance workshop where parallel operations are possible The number of maintenance tasks being performed simultaneously in the workshop shall not exceed the number of maintenance tasks being performed simultaneously in the workshop. Maximum number of parallel jobs set The repair workshop Maximum number of parallel jobs The value range is [2, 10].

[0111] The above constraints are to achieve the goal of maximizing the availability of cluster waves. and minimize the load balancing of maintenance personnel The optimization objectives are a prerequisite. They limit the parallel execution of maintenance tasks, the scope and timing of resource allocation, and can affect the maintenance completion time of each aircraft. and the actual working hours of maintenance personnel Specifically, these constraints constitute the feasible solution space of the maintenance scheduling problem. Any scheduling scheme that violates these constraints will be considered invalid and thus avoided by the intelligent optimization algorithm during the optimization process, ensuring that the generated maintenance operation sequence plan is feasible in reality. By effectively satisfying these constraints, the optimization algorithm can find the optimal solution under realistic conditions, transforming the optimization objective into an operable resource allocation and timing arrangement.

[0112] The second phase of maintenance scheduling optimization begins. This phase uses the actual aircraft arrival times output from the previous phase as a fixed, inviolable start time constraint. Under this constraint, it prioritizes and allocates resources for all maintenance tasks within the hangar. This invention employs a strategy distinct from related technologies, prioritizing maximizing fleet availability as the primary optimization objective. This metric directly measures how many aircraft can complete maintenance and be available at each pre-set mission launch time, thus closely linking scheduling decisions to mission objectives. Simultaneously, this phase also considers the load balancing of maintenance personnel.

[0113] In step 204, iterative optimization is performed: the repair completion time calculated in step 203 is used as the basis for the optimization. Feedback is sent to step 202 to revise the maintenance urgency proxy target, the maintenance completion time. The relevance to the maintenance urgency proxy objective lies in its aim to assess and quantify the risk of each aircraft being unable to participate in a pre-set sortie wave on time due to maintenance delays. Specifically, maintenance completion time... It is a proxy target for calculating maintenance urgency. The key input. If the aircraft Repair completion time Later than the wave it should have participated in The moment of preparation for deployment begins If this happens, the aircraft will negatively impact the availability of that wave and increase its urgency level.

[0114] The maintenance urgency proxy target The calculation formula can be expressed as:

[0115] .

[0116] in, For the set of dispatch waves, For waves Importance weight, To plan to participate in waves A subset of aircraft The function represents the portion of the penalty value that is positive, i.e., the portion that exceeds the wave preparation time.

[0117] This calculation formula quantifies the wave availability loss caused by maintenance delays. The maintenance urgency proxy target... As an optimization objective in step 202 The correction term is used. Through this feedback mechanism, the first-stage transfer scheduling can dynamically adjust the priority and sequence of aircraft transfer into the hangar based on the actual completion status of the second-stage maintenance. Priority is given to aircraft with later maintenance completion times and greater impact on wave availability, ensuring they can enter maintenance earlier and thus improving overall coordination efficiency. Steps 202 and 203 are repeated until the preset iterative convergence condition is met, ultimately outputting a coordinated optimal aircraft transfer and maintenance scheduling scheme (i.e., the converged aircraft transfer and hangar maintenance scheduling scheme).

[0118] In another exemplary embodiment of this application, the convergence condition is a first convergence condition or a second convergence condition.

[0119] The first convergence condition is: in two consecutive iterations, let the... Second and third The availability of the cluster wavelets calculated in the next iteration are as follows: and Its improvement value satisfies ,in The preset convergence threshold has a value range of [0.001, 0.01].

[0120] The second convergence condition is: the number of iterations reaches the preset maximum number of iterations. ,in, The value range is [50, 200].

[0121] During iterative convergence, the first convergence condition and the second convergence condition are judged simultaneously, and the process stops when either the first convergence condition or the second convergence condition is satisfied.

[0122] The most critical innovation of this application lies in the iterative optimization mechanism established between the two phases. After the maintenance scheduling in the second phase is completed, the estimated final completion time (i.e., maintenance completion time) for each aircraft is obtained. This time information is not the final result, but is used as a precise feedback signal and transmitted back to the first phase. In the next iteration, the transfer scheduling in the first phase will use this feedback information to more accurately assess the maintenance urgency of each aircraft, potentially generating a better transfer sequence than the previous one. This "transfer-maintenance-feedback" loop will be repeated, with each iteration optimizing based on the previous one, until the core indicator of the scheduling scheme, namely the availability of aircraft waves, no longer shows significant improvement or reaches the preset iteration limit. At this point, the system outputs the final scheduling scheme after full collaborative optimization. This scheme achieves the best balance between transfer efficiency, resource load, and task availability from a global perspective.

[0123] The following will be described in combination with a specific civil aviation passenger plane maintenance application scenario, taking the process of aircraft hangar maintenance and in-hangar transfer coordination scheduling as an example.

[0124] S1. Define the coordination scheduling problem

[0125] In the application background of a large civil aviation maintenance center, it is assumed that there are three passenger planes, numbered as plane 1, plane 2 and plane 3 (i.e. the set of planes to be scheduled), which need to return to the maintenance hangar for deep maintenance after completing the flight task, and each plane corresponds to its own transfer task from the external parking apron to the maintenance hangar (i.e. the set of aircraft in-hangar transfer tasks). When being maintained, plane 1 needs to be overhauled for the engine and the interior of the passenger cabin; plane 2 needs to be overhauled for the landing gear and the flight control system; and plane 3 only needs to be checked regularly and the fuselage is partially painted (i.e. the set of hangar maintenance tasks). At the same time, according to the future flight plan of the airline, there are two important operation peaks: the first wave (peak 1) is planned to start at T+12 hours, and plane 1 and plane 2 need to be in a state of availability in order to perform important routes; the second wave (peak 2) is planned to start at T+20 hours, and plane 3 needs to be in a state of availability (i.e. the set of preset departure waves). The importance of peak 1 to the company's operation is higher than that of peak 2. In addition, the maintenance resources inside the hangar, such as maintenance technicians with specific skills, special tools, test equipment and maintenance workstations, are limited, and the ground support vehicle fleet responsible for aircraft towing (or transfer) is also limited. This embodiment needs to establish a coordination scheduling problem model with the primary optimization goal of maximizing the availability of the aircraft fleet in peak 1 and peak 2 in this complex situation, to ensure that the aircraft can serve the flight plan as soon as possible while meeting all maintenance and towing (or transfer) constraints.

[0126] S2. Perform the first-stage transfer scheduling optimization

[0127] In the first stage, the system will focus on the in-hangar transfer scheduling of the aircraft. At this time, planes 1, 2 and 3 are parked at the remote parking apron or the connection area of the airport and need to be towed (or transferred) to the maintenance parking spaces P1, P2 and P3 reserved for them in the maintenance hangar. It is assumed that the airport has only one aircraft towing (or transfer) fleet (i.e. the transfer group), which can only tow (or transfer) one aircraft at a time. Hangar parking spaces P1, P2 and P3 are not always immediately available, for example, P1 will be cleared and ready at T+1 hour, P2 will be available at T+0.5 hour, and P3 will be immediately available.

[0128] The current optimization objectives are to minimize the maximum aircraft arrival time, minimize the total arrival time of aircraft awaiting maintenance, and balance the workload of the towing convoy (or dispatching team). In the early stages of iteration, the system will also incorporate a maintenance urgency proxy objective based on historical maintenance data or preliminary estimates of subsequent maintenance tasks. The system will utilize intelligent optimization algorithms, such as genetic algorithms, to generate a preliminary aircraft towing (or dispatching) sequence after comprehensively considering factors such as aircraft type, towing (or transfer) path length, airport ground traffic control, available time windows for the towing (or transfer) convoy, and the actual capacity of the target parking positions. For example, although aircraft 1 may be physically closer to the towing (or transfer) convoy, if its corresponding hangar parking position P1 is not yet ready, and aircraft 2's maintenance task is more urgent and its parking position P2 is available, the system may prioritize the towing (or transfer) of aircraft 2, followed by aircraft 1, and finally aircraft 3.

[0129] Once the towing (or transfer) sequence is determined, the system can calculate the actual arrival time for each aircraft. This refers to the earliest time an aircraft, after completing all necessary towing (or transfer) procedures, first docks at its designated hangar maintenance bay and meets the conditions for commencing maintenance. Taking aircraft 2 as an example, assuming its towing (or transfer) completion time is T+1 hour, and designated bay P2 becomes available in T+0.5 hours, then the arrival time of aircraft 2 is... The larger of the two values ​​will be taken, which is T+1 hours. Similarly, the arrival times of aircraft 1 and aircraft 3... and This logic will also be used for precise calculations. These actual entry times will form a vector, serving as a key input for the next stage of maintenance scheduling.

[0130] S3. Perform the second phase of maintenance scheduling optimization.

[0131] In the second stage, the system receives the actual aircraft arrival time vector output from step S2. For example, assuming that after the initial iteration, aircraft 1 can only be maintained at T+2 hours, aircraft 2 can start at T+1 hours, and aircraft 3 can start at T+3 hours, these time points constitute the hard constraint of the earliest start time for each aircraft's maintenance task. For each set of maintenance tasks for each aircraft, this stage will construct a detailed maintenance task network model, which includes the sequential dependencies between various maintenance procedures, the required maintenance skill types, and the estimated time for each task.

[0132] The optimization goal of this phase is to maximize the overall fleet availability at the peak of the important flights (i.e. maximize fleet wave availability), i.e. to try to get aircraft 1 and 2 to catch peak 1, and aircraft 3 to catch peak 2, while also minimizing the load balancing of the maintenance personnel, to avoid some maintenance personnel being overworked while others are underworked. To do this, the system will use intelligent optimization techniques, such as improved genetic algorithms or priority rule based heuristic search, to perform maintenance scheduling while satisfying a series of hangar internal resource constraints. These constraints include maintenance bay space constraints, e.g. although a certain maintenance bay is allocated to aircraft 1 overall, its specific maintenance bay space, such as the area for cabin interior refurbishment, can only allow two interior technicians to operate simultaneously, even though theoretically more people could be working around the aircraft. Maintenance workshop parallel operation constraints further limit workshops that share equipment resources, e.g. a certain structure repair workshop can only handle two aircraft structure inspection or repair tasks at the same time, even if there are three aircraft waiting, and must queue according to the maximum parallel operation number of that workshop. By dynamically assigning maintenance tasks to the appropriate maintenance personnel, tools, and workshops, the system will generate a detailed hangar maintenance operation timing plan and maintenance resource allocation plan.

[0133] From this, the maintenance completion time for each aircraft can be calculated , i.e. the time at which the aircraft has completed all of its assigned hangar maintenance tasks and is in a state where it can be released from the hangar. For example, aircraft 1, due to the complexity of the procedures and the tightness of the resources, its maintenance completion time may be calculated as T+15 hours, aircraft 2 as T+10 hours, and aircraft 3 as T+18 hours.

[0134] S4. Iterative optimization

[0135] At the core of this collaborative scheduling, after the first execution of S3, the system has obtained the maintenance completion times for aircraft 1, 2, and 3 as T+15 hours, T+10 hours, and T+18 hours respectively. This information is now fed back to S2 to revise the maintenance urgency proxy goal in the first phase of transfer scheduling optimization goal. For example, the departure preparation start time for peak 1 is T+12 hours, T+15 hours, which is 3 hours late, while T+10 hours, which is 2 hours early. This delay information will be used to calculate the risk of each aircraft being unable to serve the flight plan on time due to maintenance delays. The urgency value of aircraft 1 will be significantly increased because its completion time far exceeds the requirement of peak 1, which can lead to flight delays or cancellations. This updated maintenance urgency proxy goal will be dynamically added as a weight coefficient to the optimization goal of step S2 In this way, the transport scheduling will give priority to the towing (or transport) of the aircraft whose maintenance completion time is later than the flight requirement and has a greater impact on the overall fleet availability in the next round of iteration, in addition to considering its own transport efficiency (i.e. trying to shorten the transport time and balance the towing (or transport) fleet load). For example, even if the towing (or transport) path of aircraft 2 is relatively complex in physics and the towing (or transport) time is longer, the system may adjust the transport sequence to make aircraft 1 enter the maintenance area earlier because the urgency of aircraft 1 to peak 1 is higher.

[0136] Subsequently, the system will repeatedly perform S2 and S3, and the new transport sequence will generate a new actual entry time, which in turn will cause the maintenance scheme to be adjusted and a new maintenance completion time to be generated, and so on. The iteration process will continue until the fleet wave availability improvement value calculated by two consecutive iterations is less than the preset convergence threshold (for example, 0.005), which means that the scheme has stabilized, or the number of iterations reaches the preset maximum number of iterations (for example, 100 times) to prevent infinite loop calculation. Finally, the system will output a plane towing (or transport) and maintenance scheduling scheme that has been optimized through multiple rounds of coordination, balancing towing (or transport) efficiency, maintenance progress, resource utilization, and fleet availability (i.e. the converged aircraft entry transport and hangar maintenance scheduling scheme), ensuring that the flight punctuality rate and overall operational efficiency are maximized in a complex and dynamic civil aviation operating environment.

[0137] The present application aims to solve the complex coupling scheduling problem of large-scale fleet deep maintenance and pre-transportation. The method establishes a two-stage iterative optimization framework. In the first stage, the entry transport is scheduled and optimized to minimize the transport time and maintenance urgency proxy target and balance the transport group load, generate an aircraft entry transport sequence, and determine the actual entry time. In the second stage, the actual entry time determined in the first stage is used as a constraint to perform hangar maintenance scheduling optimization, the core goal of which is to maximize the fleet wave availability of a series of future tasks while considering the load balancing of maintenance personnel. The key of the present application lies in establishing an iterative feedback mechanism between the two stages, feeding back the maintenance completion time of the aircraft calculated in the second stage to the first stage to dynamically correct the maintenance urgency proxy target of the transport decision, through cyclic iteration until convergence, and finally generating a synergistically optimal scheduling scheme. The present application improves the scheduling target from a simple efficiency indicator to a task-oriented aircraft availability, effectively solves the close coupling between the transport and maintenance sub-problems through an innovative iterative optimization framework, and significantly improves the global optimality of the scheduling scheme.

[0138] Based on the same inventive concept, the embodiments of the present application also provide an aircraft hangar maintenance and warehouse transfer collaborative scheduling device for implementing the aircraft hangar maintenance and warehouse transfer collaborative scheduling method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more aircraft hangar maintenance and warehouse transfer collaborative scheduling device embodiments provided below can be referred to the limitations of the aircraft hangar maintenance and warehouse transfer collaborative scheduling method described above, which will not be repeated here.

[0139] In an exemplary embodiment, as shown in Figure 3 , an aircraft hangar maintenance and warehouse transfer collaborative scheduling device is provided, comprising: a problem modeling module 1, a transfer scheduling module 2, a maintenance scheduling module 3, and a collaborative optimization module 4.

[0140] The problem modeling module 1 is configured to establish a collaborative scheduling problem model based on a set of aircrafts to be scheduled, a set of hangar maintenance tasks, a set of aircraft warehouse transfer tasks, and a set of preset wave sets, and decompose the collaborative scheduling problem model into a process of iterative optimization of the transfer scheduling stage and the maintenance scheduling stage.

[0141] The transfer scheduling module 2 is configured to, in the transfer scheduling stage, take minimizing the transfer time and the maintenance urgency proxy target as the optimization target, solve the aircraft warehouse transfer sequence by using an intelligent optimization algorithm, and determine the actual arrival time of each aircraft; the transfer time includes the maximum arrival time of all aircrafts and the total arrival time of the aircrafts to be maintained; the maintenance urgency proxy target is a weighted delay penalty based on the maintenance completion time.

[0142] The transfer scheduling module 2 focuses on the maximum arrival time, the sum of the arrival times of the aircrafts to be maintained, and the balanced load of the transfer group, and indirectly guides the wave availability by accessing the maintenance urgency proxy target. Specifically, the module solves the aircraft warehouse transfer sequence that meets the current optimization target by using heuristic rules, and accurately calculates the arrival time of each aircraft to be maintained at the hangar maintenance parking space according to the transfer sequence and the parking space availability. .

[0143] The maintenance scheduling module 3 is configured to, in the maintenance scheduling stage, take the actual arrival time as the constraint, take maximizing the fleet wave availability as the optimization target, solve the hangar maintenance scheme by using an intelligent optimization algorithm, and determine the maintenance completion time of each aircraft; the fleet wave availability is the weighted average value of the ratio of the number of aircrafts performing each wave task to the total number of aircrafts planned to participate in each wave in the set of wave sets.

[0144] The maintenance scheduling module 3 receives the calculated aircraft arrival time vector provided by the transfer scheduling module 2 ​As a hard constraint for the start of maintenance, the maintenance scheduling can be optimized based on fine time information. The module further maximizes the fleet wave availability and minimizes the maintenance personnel load balancing degree as optimization objectives, dynamically generates the hangar maintenance job timing and resource allocation scheme (i.e. hangar maintenance scheme), and calculates the maintenance completion time .

[0145] The collaborative optimization module 4 is used to feed back the maintenance completion time of the maintenance scheduling phase to the transfer scheduling phase to dynamically correct the maintenance urgency proxy objective, and iterates repeatedly until convergence, and outputs the converged aircraft warehouse transfer and hangar maintenance scheduling scheme.

[0146] The collaborative optimization module 4 realizes the iteration process by controlling the information feedback and cyclic call between the transfer scheduling module 2 and the maintenance scheduling module 3, and judges whether the iteration is terminated according to the convergence condition, and finally outputs the collaborative optimal scheduling scheme. Specifically, the module feeds back the aircraft maintenance completion time calculated by the maintenance scheduling module 3 to the transfer scheduling module 2. This feedback is used by the transfer scheduling module 2 to dynamically correct the maintenance urgency proxy objective in its optimization objective, so that the transfer scheduling can prioritize the processing of those aircrafts that are crucial to the overall fleet wave availability in the next iteration. This targeted and fine feedback mechanism greatly improves the efficiency and convergence speed of collaborative optimization, ensuring that the system can quickly converge to the optimal or near-optimal scheduling scheme in a complex dynamic environment.

[0147] The aircraft hangar maintenance and warehouse transfer collaborative scheduling device of the present application automatically executes the collaborative scheduling process through modular functional design, and outputs high-quality and reliable scheduling scheme.

[0148] In an exemplary embodiment, a computer device, which can be a server or a terminal, is provided, and an internal structure diagram thereof can be as shown in Figure 4As shown in the figure. The computer device includes a processor, a memory, an Input / Output (I / O) interface, and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. 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, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store aircraft hangar maintenance and warehouse transfer collaborative scheduling data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement an aircraft hangar maintenance and warehouse transfer collaborative scheduling method.

[0149] Those skilled in the art can understand that, Figure 4 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0150] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in each of the method embodiments described above.

[0151] In one exemplary embodiment, a computer readable storage medium is provided, storing a computer program, which is executed by a processor to implement the steps in each of the method embodiments described above.

[0152] In one exemplary embodiment, a computer program product is provided, including a computer program, which is executed by a processor to implement the steps in each of the method embodiments described above.

[0153] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use, and processing of related data need to comply with relevant regulations.

[0154] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to a memory, a database or other medium used in the embodiments provided in the present application can include at least one of a non-volatile and a volatile memory. The non-volatile memory can include a read-only memory (ROM), a magnetic tape, a floppy disk, a flash memory, an optical storage, a high-density embedded non-volatile memory, a resistive random access memory (ReRAM), a magnetoresistive random access memory (MRAM), a ferroelectric random access memory (FRAM), a phase change memory (PCM), a graphene memory, etc. The volatile memory can include a random access memory (RAM) or an external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), etc.

[0155] The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0156] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combinations of the technical features do not exist contradictory, they should be considered as the scope of the present application.

[0157] The principles and implementation modes of the present application are described by applying specific examples in the present application. The above-mentioned embodiments are only used to help understand the method and its core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range can be changed. In conclusion, the content of the present application should not be understood as a limitation.

Claims

1. An aircraft hangar maintenance and in-hangar transfer collaborative scheduling method, characterized in that, The method comprises the steps of: establishing a collaborative scheduling problem model based on a set of aircrafts to be dispatched, a set of hangar maintenance tasks, a set of aircrafts to be transported into the hangar, and a set of preset wave sets, and decomposing the collaborative scheduling problem model into an iterative optimization process of a transportation scheduling stage and a maintenance scheduling stage; in the transportation scheduling stage, an intelligent optimization algorithm is used to solve the aircraft transportation sequence into the hangar and determine the actual arrival time of each aircraft, with the minimum transportation time and maintenance urgency proxy target as the optimization objective; the transportation time comprises the maximum arrival time of all aircrafts and the total arrival time of the aircrafts to be maintained; the maintenance urgency proxy target is a weighted delay penalty based on the maintenance completion time; The aircraft in-transit sequence is solved by using an intelligent optimization algorithm with the optimization objective of minimizing the in-transit time and the maintenance urgency proxy objective, and specifically includes: a first objective function with the optimization objective of minimizing the in-transit time, the load balancing degree of the transport group and the maintenance urgency proxy objective is constructed for the in-transit task set; the intelligent optimization algorithm is used to perform iterative search in multiple aircraft in-transit schemes according to the first objective function, and the aircraft in-transit sequence that makes the first objective function reach the minimum value is obtained; wherein the iterative search process is: the current aircraft in-transit sequence is selected according to the first objective function value generated by the current iteration, and the current aircraft in-transit sequence is fed back to the next iteration to gradually approach the optimal solution; the calculation formula of the first objective function is: ; wherein, is the first objective function; is the arrival time of the aircraft ; is the aircraft subset to be maintained, which is a subset of the set ; is the load balancing degree of the transport group; is the maintenance urgency proxy objective; is a preset normalized weight coefficient, which satisfies , and the value range is [0, 1]; the calculation formula of the load balancing degree of the transport group is: ; wherein, is the transport group personnel set; is the total working time of the transport group personnel ; is the average working time of the transport group personnel; the calculation formula of the maintenance urgency proxy objective is: ; wherein, is the set of dispatched wave sets, is the importance weight of the wave , is the aircraft subset participating in the wave , is a function indicating that the penalty value is positive, is the maintenance completion time of the aircraft , is the start time of the dispatch preparation of the aircraft participating in the wave . in the maintenance scheduling stage, an intelligent optimization algorithm is used to solve the hangar maintenance scheme with the actual arrival time as the constraint and the maximum wave set availability of the aircraft group as the optimization objective; the wave set availability of the aircraft group is a weighted average value of the ratio of the number of aircrafts performing each wave set task to the total number of aircrafts planned to participate in each wave set in the set of wave sets; and the maintenance completion time of each aircraft is determined; the maintenance completion time of the maintenance scheduling stage is fed back to the transportation scheduling stage to dynamically correct the maintenance urgency proxy target, and the iteration is repeated until convergence, and the converged aircraft transportation into the hangar and hangar maintenance scheduling scheme is output.

2. The method of claim 1, wherein, In the maintenance scheduling stage, an intelligent optimization algorithm is used to solve the hangar maintenance scheme with the actual arrival time as the constraint and the maximum wave set availability of the aircraft group as the optimization objective, specifically comprising: the actual arrival time is used as an input constraint to limit the earliest time at which each aircraft can start hangar maintenance; a second objective function is constructed for the set of hangar maintenance tasks, with the maximum wave set availability of the aircraft group and the minimum maintenance personnel load balancing degree as the optimization objectives; an intelligent optimization algorithm is used to search for a hangar maintenance scheme in the feasible solution space that makes the second objective function minimum; the calculation formula of the second objective function is: ； wherein, is a second objective function, is fleet wave availability; is maintenance personnel load balancing degree; is a multi-objective optimization weight coefficient, and its value range is [0.01, 0.2]; the calculation formula of the wave set availability of the aircraft group is: ； wherein, is the set of dispatched wave; is the wave importance weight, satisfying and for any two waves and , if precedes then ; is the total number of aircrafts; is the aircraft maintenance completion time; is the start time of the dispatch preparation of the wave ; is the symbol function, which is defined as: when the input value is greater than zero, the function value is 1, otherwise 0; the calculation formula of the maintenance personnel load balancing degree is: ； wherein, total work time for the service personnel; total work time for the service personnel average work time for the service personnel. average work time for the service personnel.

3. The method of claim 1, wherein, in the maintenance scheduling stage, the constraint further comprises a hangar resource constraint, specifically comprising: a maintenance workstation space constraint and a maintenance workshop parallel operation constraint; The maintenance station space constraint is that at any time , the number of maintenance personnel assigned to any aircraft , for performing a certain maintenance skill category , cannot exceed the available station space capacity , set for the maintenance skill category , associated with the maintenance stand where the aircraft is located. The repair shop parallel operation constraint is that the number of repair tasks simultaneously performed in the repair shop at any time cannot exceed the maximum number of parallel operations set for the repair shop . The maximum number of parallel operations set for the repair shop is in the range [2, 10] . The maximum number of parallel operations for the repair shop 4. The method of claim 1, wherein, the convergence condition adopts a first convergence condition or a second convergence condition; The first convergence condition is: in two continuous iterations, let the fleet wave availability calculated in the first and the second iterations be and respectively, and the improvement value satisfies , wherein is a preset convergence threshold, and the value range of the convergence threshold is [0.001, 0.01]. The second convergence condition is that the number of iterations reaches a preset maximum number of iterations wherein, The value range of the parameter is [50, 200].

5. The method of claim 1, wherein, the calculation formula of the maintenance completion time is: ； in, For airplane Repair completion time, For airplane A collection of hangar maintenance tasks. For maintenance tasks The start time, For maintenance tasks The actual execution time.

6. An aircraft hangar maintenance and in-hangar transfer co-scheduling device, characterized in that, The method comprises the steps of: a problem modeling module is configured to establish a collaborative scheduling problem model based on a set of aircrafts to be dispatched, a set of hangar maintenance tasks, a set of aircrafts to be transported into the hangar, and a set of preset wave sets, and decompose the collaborative scheduling problem model into an iterative optimization process of a transportation scheduling stage and a maintenance scheduling stage; a transportation scheduling module is configured to use an intelligent optimization algorithm to solve the aircraft transportation sequence into the hangar and determine the actual arrival time of each aircraft in the transportation scheduling stage, with the minimum transportation time and maintenance urgency proxy target as the optimization objective; the transportation time comprises the maximum arrival time of all aircrafts and the total arrival time of the aircrafts to be maintained; the maintenance urgency proxy target is a weighted delay penalty based on the maintenance completion time; The aircraft in-transit sequence is solved by using an intelligent optimization algorithm with the optimization objective of minimizing the in-transit time and the maintenance urgency proxy objective, and specifically includes: a first objective function with the optimization objective of minimizing the in-transit time, the load balancing degree of the transport group and the maintenance urgency proxy objective is constructed for the in-transit task set; the intelligent optimization algorithm is used to perform iterative search in multiple aircraft in-transit schemes according to the first objective function, and the aircraft in-transit sequence that makes the first objective function reach the minimum value is obtained; wherein the iterative search process is: the current aircraft in-transit sequence is selected according to the first objective function value generated by the current iteration, and the current aircraft in-transit sequence is fed back to the next iteration to gradually approach the optimal solution; the calculation formula of the first objective function is: ; wherein, is the first objective function; is the arrival time of the aircraft ; is the aircraft subset to be maintained, which is a subset of the set ; is the load balancing degree of the transport group; is the maintenance urgency proxy objective; is a preset normalized weight coefficient, satisfying , and the value range thereof is [0, 1]; the calculation formula of the load balancing degree of the transport group is: ; wherein, is the transport group personnel set; is the total working time of the transport group personnel ; is the average working time of the transport group personnel; the calculation formula of the maintenance urgency proxy objective is: ; wherein, is the set of dispatched wave sets, is the importance weight of the wave , is the aircraft subset participating in the wave , the function represents the part with a positive penalty value, is the maintenance completion time of the aircraft , is the start time of the dispatch preparation of the aircraft participating in the wave . The maintenance scheduling module is configured to, in the maintenance scheduling stage, solve a hangar maintenance scheme by using an intelligent optimization algorithm with an actual entry time as a constraint and maximizing a fleet wave availability as an optimization target, and determine a maintenance completion time of each aircraft; the fleet wave availability is a weighted average of a ratio of a number of aircrafts performing each wave task to a total number of aircrafts planned to participate in each wave in a set of dispatched waves; The collaborative optimization module is configured to feed back the maintenance completion time of the maintenance scheduling stage to the transfer scheduling stage to dynamically correct a maintenance urgency proxy target, repeatedly iterate until convergence, and output a converged aircraft hangar transfer and hangar maintenance scheduling scheme.

7. A computer device comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that the processor executes the computer program to implement the aircraft hangar maintenance and hangar transfer collaborative scheduling method of any one of claims 1-5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the aircraft hangar maintenance and hangar transfer collaborative scheduling method of any one of claims 1-5.

9. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the aircraft hangar maintenance and hangar transfer collaborative scheduling method of any one of claims 1-5.

Images