Aviation aircraft autonomous guarantee intelligent decision implementation method and model

Abstract

The invention belongs to the technical field of electric data processing, and particularly relates to an aviation aircraft autonomous guarantee intelligent decision implementation method and model, and the method comprises the steps: S1, dividing all aircrafts into a plurality of batches according to an initial annual flight, and S2, according to the proportion of the available time of each aircraft to the total available time of all aircrafts of the batch, determining the available time of each aircraft; calculating the annual flight time of the airplane by combining the sum of the annual flight time of the batch; s3, taking annual flight time, monthly flight time limit, regular inspection and overhaul time windows and regular inspection and overhaul process duration of the aircrafts as constraints, taking minimization of the number of the aircrafts subjected to simultaneous overhaul or regular inspection as a target, solving to obtain a regular inspection or overhaul month, and further determining monthly flight time of each aircraft; and S4, according to the monthly flight time of each airplane, determining a weekly inspection, regular inspection or overhaul plan of the airplane in the current month, further determining the maximum number of simultaneous maintenance items in one week, the maintenance items of each airplane in each week and the weekly flight time of each airplane, and generating a flight plan.

Description

Technical Field

[0001] The present application belongs to the field of electrical data processing technology, and in particular relates to a method and model for implementing intelligent decision-making for autonomous aircraft support. Background Art

[0002] With the increasing complexity and performance of aircraft, the traditional manual and passive support methods such as mission planning, regular maintenance, fault diagnosis, and support resource coordination have seriously restricted the support efficiency of modern aircraft and affected the rapid formation of aircraft flight capabilities. How to use intelligent technology to build an autonomous support decision-making method for aircraft and realize the functions of automatic generation of aircraft support tasks and maintenance plans is an urgent problem to be solved and verified.

[0003] An autonomous support information system integrates information such as equipment status, mission planning, training, and maintenance support. Through comprehensive data analysis, it realizes functions such as maintenance task planning, comprehensive situation monitoring, and automatic fault diagnosis, which greatly reduces labor costs and human errors and improves equipment support efficiency. Autonomous support uses advanced technologies such as sensors, status monitoring, intelligent diagnosis, and open information system architecture to monitor the technical status of equipment in real time and predict equipment failures and lifespans, thereby determining maintenance decision plans. During the use of equipment, maintenance task preparation and maintenance resource allocation can be initiated in advance, improving the rapid response capability of maintenance support and achieving rapid and accurate support goals.

[0004] Features of existing aircraft support technology:

[0005] (1) The existing aircraft support is a human-centered management model, especially the formulation of maintenance plans and flight plans, which requires people to obtain data such as mission requirements and aircraft status, conduct manual screening and comparison, and make support decisions.

[0006] (2) The existing aircraft maintenance mainly relies on regular scheduled maintenance, which has a single maintenance method, high maintenance costs and is passive maintenance. Summary of the invention

[0007] In order to solve the above problems, the present application provides a method for realizing intelligent decision-making for autonomous aircraft support, including:

[0008] Step S1: when obtaining the initial annual flight of each aircraft, all aircraft are divided into multiple batches according to the initial annual flight, wherein the difference between the initial annual flight of each aircraft in the same batch is less than a preset value; and the difference between the sum of the initial annual flight of all aircraft in different batches is greater than a preset value;

[0009] Step S2: Calculate the annual flight time of each aircraft based on the proportion of the available time of each aircraft to the total available time of all aircraft in the batch and the sum of the annual flight time of the batch;

[0010] Step S3: Taking the annual flight hours and monthly flight hours of the aircraft, the time window for scheduled inspection and overhaul, and the duration of the scheduled inspection and overhaul process as constraints, and minimizing the number of aircraft that are overhauled or inspected at the same time as the goal, the month of scheduled inspection or overhaul is solved, and then the monthly flight hours of each aircraft are determined;

[0011] Step S4: According to the monthly flight time of each aircraft, determine the weekly inspection, scheduled inspection or overhaul plan of the aircraft in the current month, and then determine the maximum number of simultaneous maintenance items in a week, the weekly maintenance items of each aircraft and the weekly flight time of each aircraft, and finally arrange the aircraft flight plan and generate the flight plan.

[0012] Preferably, before step S1, overhauled aircraft are first eliminated, and the elimination method includes: obtaining the overhaul years of all aircraft, setting an index value, and eliminating overhauled aircraft by comparing the overhaul years with the index value.

[0013] Preferably, the index value is determined based on the lower limit of the overhaul time limit, and when the remaining flight hours of the aircraft not eliminated account for less than 40% of the total flight hours after the overhaul, the index value is manually set or the overhaul aircraft is manually designated.

[0014] Preferably, the mathematical model for dividing all aircraft into multiple batches according to the initial annual flight is as follows:

[0015] max k min

[0016]

[0017] Where N is the set of batches n, K l The remaining total flight hours of non-overhaul aircraft per year, The flight time allocated for batch n, is the current remaining total flight time of batch n, is the average flight time difference between batch n1 and batch n2, k min is the minimum value of the difference in flight time, The upper limit of the total flight time allocated for batch n, The lower bound of the total flight time allocated for batch n, Upper limit on the total flight time remaining for batch n.

[0018] Preferably, the calculation formula used in step S2 is:

[0019]

[0020] h i is the total annual flight time of the i-th batch, ti is the total available time, t ij is the available time of the i-th aircraft in the i-th batch.

[0021] Preferably, the mathematical model of the flight time in step S3 is as follows:

[0022] min Z total

[0023]

[0024] Variable Z total represents the sum of the differences in the monthly flight time of the aircraft, f is the aircraft code, x fn represents the flight time of aircraft f in the nth month, X fn represents the average flight time of aircraft f in month n, z fn represents the difference between the flight time of aircraft f in the nth month and the average flight time, Indicates the monthly flight time plan, represents the current flight time of aircraft f, represents the annual flight time allocated by f, x fn represents the flight time of aircraft f in the nth month, y fn Indicates whether aircraft f is scheduled for inspection in month n, α fn It represents the proportion of time that aircraft f does not undergo scheduled inspection or overhaul in month n. x fn It represents the lower limit of the monthly flight time of aircraft f in month n, It represents the upper limit of the monthly flight hours of aircraft f in the nth month.

[0025] Preferably, the aircraft flight plan includes:

[0026] Obtain the mission planning time. When the mission planning time is one week, the completion of the flight mission is taken as a constraint, the flight time of the aircraft that needs maintenance that week before maintenance is maximized and the aircraft flight time is as close as possible to the weekly flight time plan. The flight mission time does not overlap, the mission duration meets the flight time limit, and the spare aircraft is designated as constraints. A mixed integer linear programming mathematical model is established to solve and obtain the optimal solution, and then the aircraft that performs the flight mission is obtained, and a weekly flight plan and maintenance plan for multiple aircraft are generated.

[0027] An intelligent decision-making model for autonomous aircraft support, according to the intelligent decision-making implementation method for autonomous aircraft support, includes:

[0028] Batch division module: used to obtain the initial annual flight of each aircraft, and divide all aircraft into multiple batches according to the initial annual flight, wherein the difference between the initial annual flight of each aircraft in the same batch is less than the preset value; the difference between the sum of the initial annual flight of all aircraft in different batches is greater than the preset value;

[0029] Annual flight time calculation module: calculates the annual flight time of each aircraft based on the proportion of the available time of each aircraft to the total available time of all aircraft in the batch and the sum of the annual flight time of the batch;

[0030] Monthly flight time calculation module: With the annual flight time of the aircraft, the upper limit of the monthly flight time, the time window of scheduled inspection and overhaul, and the duration of the scheduled inspection and overhaul process as constraints, and with the goal of minimizing the number of aircraft that are overhauled or inspected at the same time, the month of scheduled inspection or overhaul is solved, and then the monthly flight time of each aircraft is determined;

[0031] Flight plan generation module: According to the monthly flight time of each aircraft, the weekly inspection, regular inspection or overhaul plan of the aircraft in the current month is determined, and then the maximum number of simultaneous maintenance items in a week, the weekly maintenance items of each aircraft and the weekly flight time of each aircraft are determined. Finally, the aircraft flight plan is arranged and the flight plan is generated.

[0032] Preferably, it also includes a feedback module, which feeds back the actual execution result of the flight plan to the aircraft autonomous support intelligent decision-making model as input for the next support decision.

[0033] Preferably, the actual execution results include: execution according to the decision plan, execution after adjustment, and data not executed according to the plan.

[0034] The advantages of this application include: This application establishes an autonomous support intelligent decision-making model based on a mixed integer linear programming algorithm, which can automatically decide on aircraft maintenance support plans and flight training plans, and can resolve task conflicts and dynamically adjust tasks. This method solves the problems existing in the existing human-dominated support plan formulation, and uses autonomous support decision-making methods to lay the foundation for the reform of maintenance support models. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a flowchart of the steps for implementing intelligent decision-making for autonomous aircraft protection in this application;

[0036] Figure 2 This is an architecture diagram of a scenario for the use of autonomous intelligent decision-making for aircraft in this application;

[0037] Figure 3 This is a flow chart of the process of building an intelligent decision-making model for autonomous security in this application. DETAILED DESCRIPTION

[0038] In order to make the technical solution and advantages of the present application clearer, the technical solution of the present application will be further described in detail in detail and in detail in conjunction with the accompanying drawings. It can be understood that the specific embodiments described here are only partial embodiments of the present application, which are only used to explain the present application, not to limit the present application. It should be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, and other related parts can refer to the general design. In the absence of conflict, the embodiments in the present application and the technical features in the embodiments can be combined with each other to obtain new embodiments.

[0039] An intelligent decision-making model for autonomous aircraft support in this application:

[0040] Batch division module: used to obtain the initial annual flight of each aircraft, and divide all aircraft into multiple batches according to the initial annual flight, wherein the difference between the initial annual flight of each aircraft in the same batch is less than the preset value; the difference between the sum of the initial annual flight of all aircraft in different batches is greater than the preset value;

[0041] Annual flight time calculation module: calculates the annual flight time of each aircraft based on the proportion of the available time of each aircraft to the total available time of all aircraft in the batch and the sum of the annual flight time of the batch;

[0042] Monthly flight time calculation module: With the annual flight time of the aircraft, the upper limit of the monthly flight time, the time window of scheduled inspection and overhaul, and the duration of the scheduled inspection and overhaul process as constraints, and with the goal of minimizing the number of aircraft that are overhauled or inspected at the same time, the month of scheduled inspection or overhaul is solved, and then the monthly flight time of each aircraft is determined;

[0043] Flight plan generation module: According to the monthly flight time of each aircraft, the weekly inspection, regular inspection or overhaul plan of the aircraft in the current month is determined, and then the maximum number of simultaneous maintenance items in a week, the weekly maintenance items of each aircraft and the weekly flight time of each aircraft are determined. Finally, the aircraft flight plan is arranged and the flight plan is generated.

[0044] The implementation method and usage scenarios of the above model include: aircraft autonomous support decision-making activities include equipment management decisions, maintenance decisions, planning decisions, resource scheduling decisions, wartime equipment support decisions, emergency decisions, training decisions, personnel decisions and other business activities, involving the optimization and decision-making of issues such as job scheduling, task allocation, and resource allocation. The ultimate goal is to achieve the coordinated arrangement of equipment resources, the reasonable division of maintenance tasks and the full utilization of support resources, so as to improve the efficiency of aircraft autonomous support.

[0045] This paper takes a scenario of autonomous aircraft support activities as an example, focusing on the research of maintenance plan decision-making and flight plan decision-making. The application scenarios of autonomous support intelligent decision-making in autonomous support activities are as follows: Figure 2 shown.

[0046] Application scenario description:

[0047] (1) Before preparing for an aircraft training mission, it is necessary to select aircraft that can meet the mission requirements based on the health status of the fleet aircraft. The autonomous support intelligent decision-making model can automatically decide on the flight training plan and maintenance support work plan based on information such as aircraft training requirements and aircraft health status data;

[0048] (2) After the mission is confirmed, the maintenance personnel will carry out pre-flight preparations, including pre-flight inspection, equipment configuration verification, mission data upload and confirmation, etc.;

[0049] (3) During the flight training execution phase, the aircraft prediction and health management system (PHM) monitors the aircraft health status in real time, diagnoses aircraft faults, and automatically transmits health status data. The autonomous support intelligent decision-making model receives the health status data, combines the support process management data to make intelligent decisions, and generates support decision-making plans, such as maintenance items, maintenance personnel and other information, to prepare for the next mission before the aircraft lands.

[0050] (4) When the aircraft status affects the next mission, early warning information is given and fed back to the autonomous support intelligent decision-making model, which will affect the formulation of the next flight training plan;

[0051] (5) After the maintenance plan decision is generated, the maintenance personnel will conduct a comprehensive analysis, initiate the work order, and issue it to the support site to implement the maintenance work;

[0052] (6) After the maintenance task is completed, the maintenance activities are registered and technical summaries are conducted to realize the informatization of the support process activities. The data is used to support (1) the next support decision-making activity.

[0053] The autonomous support intelligent decision-making activity is a closed-loop system and the core technology in aircraft support activities. It establishes an intelligent decision-making model by comprehensively analyzing flight mission plan requirements, aircraft health status, fault information, equipment life control information and other data information, automatically making decisions on aircraft scheduled inspections, overhauls and other maintenance support plans, and automatically making decisions on flight training plans. It supports multiple aircraft flights and continuous flights on a flight day. When an aircraft failure occurs, it can automatically resolve conflicts and dynamically adjust flight training scheduling tasks. Through data verification, this method can effectively improve the autonomous support capabilities of aircraft.

[0054] The present invention relates to a method for realizing intelligent decision-making for autonomous support of an aircraft. First, all parameters are preset: the preset parameters are the parameters and data required by the autonomous support intelligent decision-making model. The data can be imported from the aircraft support business information system or obtained through data simulation.

[0055] Aircraft basic status: aircraft number, number of take-offs and landings, calendar time, flight hours; flight time plan: total annual flight hours, total monthly flight hours;

[0056] Aircraft health status: aircraft number, health status; maintenance control information: object, maintenance item, time limit, maintenance time, maximum advance time, maximum delay time;

[0057] Restriction parameters: overhaul time limit, overhaul quantity, whether maintenance is done on holidays, monthly minimum flight time, monthly maximum flight time, annual flight time upper limit, annual flight time lower limit, daily flight time upper limit, number of aircraft in a batch;

[0058] Fault information: aircraft number, status, date, maintenance days;

[0059] Flight mission records: flight mission number, number of days since the last mission;

[0060] Flight mission requirements: flight mission number, date, mission type, planned start time, planned end time, number of aircraft required, mission flight time, and number of take-offs and landings.

[0061] These parameters are also the basis for establishing objective functions and constraints in subsequent steps.

[0062] Step S1: when obtaining the initial annual flight of each aircraft, all aircraft are divided into multiple batches according to the initial annual flight, wherein the difference between the initial annual flight of each aircraft in the same batch is less than a preset value; and the difference between the sum of the initial annual flight of all aircraft in different batches is greater than a preset value;

[0063] The specific implementation methods corresponding to step S1 include:

[0064] Aircraft that need to be overhauled can be selected based on the obtained lower limit of the overhaul time limit. If the indicator value results in the inability to meet the 40% indicator of the remaining aircraft's overhaul time limit, the value will be prompted.

[0065] If the indicator value is not manually entered, the aircraft to be overhauled will be automatically selected.

[0066] For example, without specifying an aircraft for overhaul, the calculated aircraft No. 254 can enter overhaul on December 1, 2023.

[0067] To calculate the annual flight time of an aircraft, the aircraft except those that are undergoing overhaul will be divided into multiple batches. The flight time of aircraft in the same batch is relatively close, while the flight time difference between different batches is large. By widening the difference in flight time between different batches, it is convenient for aircraft in the same batch to enter the repair state. After batch division and optimization of the echelon, the annual flight time plan for each aircraft can be calculated. This part allocates the flight time of each batch with the goal of maximizing the difference in flight time between batches. The mixed integer linear programming mathematical model is as follows:

[0068] max k min

[0069]

[0070] In formula ②, N is the set of batches n, K l The remaining total flight hours of non-overhaul aircraft per year, The flight time allocated for batch n, is the current remaining total flight time of batch n, is the average flight time difference between batch n1 and batch n2, k min is the minimum value of the difference in flight time, The upper limit of the total flight time allocated for batch n, The lower bound of the total flight time allocated for batch n, Upper limit on the total flight time remaining for batch n.

[0071] Step S2: Calculate the annual flight time of each aircraft based on the proportion of the available time of each aircraft to the total available time of all aircraft in the batch and the sum of the annual flight time of the batch;

[0072] The specific implementation methods corresponding to step S2 include:

[0073] After obtaining the flight time of each batch, calculate the annual flight time plan for each aircraft. If the total annual flight time of the i-th batch is h i , the total available time is t i , the available time of the i-th aircraft in the i-th batch is t ij , the aircraft's annual flight hours are:

[0074]

[0075] After calculating the annual flight time plan for each batch of aircraft, an aircraft utilization plan can be generated as the basis for formulating aircraft flight training plans and maintenance support plans.

[0076] A tiered usage plan is generated based on the annual planned flight hours and actual flight hours.

[0077] Step S3: Taking the annual flight hours and monthly flight hours of the aircraft, the time window for scheduled inspection and overhaul, and the duration of the scheduled inspection and overhaul process as constraints, and minimizing the number of aircraft that are overhauled or inspected at the same time as the goal, the month of scheduled inspection or overhaul is solved, and then the monthly flight hours of each aircraft are determined;

[0078] The specific implementation methods corresponding to step S3 include:

[0079] After calculating the annual flight hours of each aircraft in the above steps, the annual flight time plan can be used to predict the aircraft that will enter scheduled inspection this year and the number of flight hours that will be completed. By adding constraints on the total annual flight time of the aircraft, the upper limit constraints on the monthly flight time, the time window for scheduled inspection and overhaul, and the time constraints for the scheduled inspection and overhaul processes, the months for scheduled inspection or overhaul are solved with the goal of minimizing the number of aircraft that are overhauled or inspected at the same time. After determining the scheduled inspection plan, it is necessary to optimize the monthly flight time of each aircraft so that the flight time of the aircraft that is scheduled to be inspected is within the scheduled inspection time limit, and the monthly flight time of other aircraft is distributed as evenly as possible. The mixed integer linear programming mathematical model is established as follows:

[0080] min Z total

[0081]

[0082] Variable Z total , represents the sum of the difference in monthly flight time of the aircraft, x fn represents the flight time of aircraft f in the nth month, X fn represents the average flight time of aircraft f in month n, z fn represents the difference between the flight time of aircraft f in the nth month and the average flight time, Indicates the monthly flight time plan, represents the current flight time of aircraft f, represents the annual flight time allocated by f, x fn represents the flight time of aircraft f in the nth month, y fn Indicates whether aircraft f is scheduled for inspection in month n, α fn It represents the proportion of time that aircraft f does not undergo scheduled inspection or overhaul in month n. x fn It represents the lower limit of the monthly flight time of aircraft f in month n, It represents the upper limit of the monthly flight hours of aircraft f in the nth month.

[0083] After calculating the monthly flight hours of each aircraft, it can be determined whether the aircraft needs weekly inspection, regular inspection or overhaul in the current month.

[0084] For example, it is calculated that aircraft No. 264 can undergo regular inspection from December 4, 2023 to January 19, 2024, and aircraft No. 281 can undergo weekly inspection from December 4, 2023 to December 8, 2023.

[0085] Step S4: According to the monthly flight time of each aircraft, determine the weekly inspection, scheduled inspection or overhaul plan of the aircraft in the current month, and then determine the maximum number of simultaneous maintenance items in a week, the weekly maintenance items of each aircraft and the weekly flight time of each aircraft, and finally arrange the aircraft flight plan and generate the flight plan.

[0086] After the above steps are calculated, the maximum number of simultaneous maintenance items in a week, the maintenance items per aircraft per week, and the flight time per aircraft per week are obtained, and then the daily and weekly plans of the aircraft can be arranged. If the mission plan time length is one week, it is a weekly plan; if the mission time length is one day, it is a daily plan. If a mission plan for a week is given, the completion of the flight mission is the constraint, and the optimization goal is to maximize the flight time of the aircraft that needs maintenance that week before maintenance and to keep the aircraft flight time as close to the weekly flight time plan as possible. When making decisions, consider the constraints of non-overlapping flight mission time, mission duration meeting flight time restrictions, and specifying spare aircraft. A mixed integer linear programming mathematical model is established to solve the optimal solution, that is, the aircraft that can meet the conditions to perform the flight mission.

[0087] Plan execution and implementation result feedback

[0088] After the calculations in the above steps are completed, the autonomous support intelligent decision-making model has generated a maintenance plan and a weekly flight plan. The maintenance plan includes weekly maintenance activities, regular inspection plans, and overhaul plans. The flight plan is automatically arranged according to mission requirements to maximize the mission completion rate of the aircraft.

[0089] In the actual flight support process, the plan is executed after manual review. After the execution is completed, the actual execution results (including data such as execution according to the decision plan, execution after adjustment, and failure to execute according to the plan) are fed back to the autonomous support intelligent decision-making model as input for the next support decision.

[0090] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for realizing intelligent decision-making for autonomous aircraft support, characterized in that: include: Step S1: when obtaining the initial annual flight of each aircraft, all aircraft are divided into multiple batches according to the initial annual flight, wherein the difference between the initial annual flight of each aircraft in the same batch is less than a preset value; and the difference between the sum of the initial annual flight of all aircraft in different batches is greater than a preset value; Step S2: Calculate the annual flight time of each aircraft based on the proportion of the available time of each aircraft to the total available time of all aircraft in the batch and the sum of the annual flight time of the batch; Step S3: Taking the annual flight hours and monthly flight hours of the aircraft, the time window for scheduled inspection and overhaul, and the duration of the scheduled inspection and overhaul process as constraints, and minimizing the number of aircraft that are overhauled or inspected at the same time as the goal, the month of scheduled inspection or overhaul is solved, and then the monthly flight hours of each aircraft are determined; Step S4: According to the monthly flight time of each aircraft, determine the weekly inspection, scheduled inspection or overhaul plan of the aircraft in the current month, and then determine the maximum number of simultaneous maintenance items in a week, the weekly maintenance items of each aircraft and the weekly flight time of each aircraft, and finally arrange the aircraft flight plan and generate the flight plan.

2. The method for realizing intelligent decision-making for autonomous aircraft support as claimed in claim 1, characterized in that: Before step S1, overhauled aircraft are first eliminated. The elimination method includes: obtaining the overhaul years of all aircraft, setting an index value, and eliminating overhauled aircraft by comparing the overhaul years with the index value.

3. The method for realizing intelligent decision-making for autonomous aircraft support as claimed in claim 2, characterized in that: The index value is determined based on the lower limit of the overhaul time limit. When the remaining flight hours of the aircraft not eliminated account for less than 40% of the total flight hours after the overhaul, the index value is manually set or the overhaul aircraft is manually designated.

4. The method for realizing intelligent decision-making for autonomous aircraft support as claimed in claim 1, characterized in that: The mathematical model for dividing all aircraft into multiple batches according to their initial annual flight is as follows: max k min Where N is the set of batches n, K l The remaining total flight hours of non-overhaul aircraft per year, The flight time allocated for batch n, is the current remaining total flight time of batch n, is the average flight time difference between batch n1 and batch n2, k min is the minimum value of the difference in flight time, The upper limit of the total flight time allocated for batch n, The lower bound of the total flight time allocated for batch n, Upper limit on the total flight time remaining for batch n.

5. The method for realizing intelligent decision-making for autonomous aircraft support as claimed in claim 1, characterized in that: The calculation formula used in step S2 is: h i is the total annual flight time of the i-th batch, t i is the total available time, t ij is the available time of the i-th aircraft in the i-th batch.

6. The method for realizing intelligent decision-making for autonomous aircraft support as claimed in claim 1, characterized in that: The mathematical model of the monthly flight time in step S3 is as follows: mins from total Variable Z total represents the sum of the differences in the monthly flight time of the aircraft, f is the aircraft code, x fn represents the flight time of aircraft f in the nth month, X fn represents the average flight time of aircraft f in month n, z fn represents the difference between the flight time of aircraft f in the nth month and the average flight time, Indicates the monthly flight time plan, represents the current flight time of aircraft f, represents the annual flight time allocated by f, x fn represents the flight time of aircraft f in the nth month, y fn Indicates whether aircraft f is scheduled for inspection in month n, α fn It represents the proportion of time that aircraft f does not undergo scheduled inspection or overhaul in month n. x fn It represents the lower limit of the monthly flight time of aircraft f in month n, It represents the upper limit of the monthly flight hours of aircraft f in the nth month.

7. The method for realizing intelligent decision-making for autonomous aircraft support as claimed in claim 1, characterized in that: Aircraft flight planning includes: Obtain the mission planning time. When the mission planning time is one week, the completion of the flight mission is taken as a constraint, the flight time of the aircraft that needs maintenance that week before maintenance is maximized and the aircraft flight time is as close as possible to the weekly flight time plan. The flight mission time does not overlap, the mission duration meets the flight time limit, and spare aircraft are designated as constraints. A mixed integer linear programming mathematical model is established to solve and obtain the optimal solution, and then the aircraft that performs the flight mission is obtained, and weekly flight plans and maintenance plans for multiple aircraft are generated.

8. An intelligent decision-making model for autonomous aircraft support, according to the method for realizing intelligent decision-making for autonomous aircraft support as claimed in claims 1 to 7, characterized in that: include: Batch division module: used to obtain the initial annual flight of each aircraft, and divide all aircraft into multiple batches according to the initial annual flight, wherein the difference between the initial annual flight of each aircraft in the same batch is less than the preset value; the difference between the sum of the initial annual flight of all aircraft in different batches is greater than the preset value; Annual flight time calculation module: calculates the annual flight time of each aircraft based on the proportion of the available time of each aircraft to the total available time of all aircraft in the batch and the sum of the annual flight time of the batch; Monthly flight time calculation module: With the annual flight time of the aircraft, the upper limit of the monthly flight time, the time window of scheduled inspection and overhaul, and the duration of the scheduled inspection and overhaul process as constraints, and with the goal of minimizing the number of aircraft that are overhauled or inspected at the same time, the month of scheduled inspection or overhaul is solved, and then the monthly flight time of each aircraft is determined; Flight plan generation module: According to the monthly flight time of each aircraft, the weekly inspection, regular inspection or overhaul plan of the aircraft in the current month is determined, and then the maximum number of simultaneous maintenance items in a week, the weekly maintenance items of each aircraft and the weekly flight time of each aircraft are determined. Finally, the aircraft flight plan is arranged and the flight plan is generated.

9. The method for realizing intelligent decision-making for autonomous aircraft support as claimed in claim 7, characterized in that: It also includes a feedback module, which feeds back the actual execution result of the flight plan to the aircraft autonomous support intelligent decision-making model as an input for the next support decision.

10. The method for realizing intelligent decision-making for autonomous aircraft support as claimed in claim 9, characterized in that: The actual execution results include: execution according to the decision plan, execution after adjustment, and data not executed according to the plan.

Images