Methods, systems, equipment, media, and products for dynamic adjustment of airport flight schedules

Abstract

This application discloses a method, system, electronic device, readable storage medium, and computer program product for dynamically adjusting airport flight schedules. The method includes: acquiring a pre-planned historical flight schedule, a selected optimization range, and corresponding meteorological data; calculating departure capacity constraints for flights at different times within the optimization range based on the historical flight schedule and meteorological data, according to a pre-defined meteorological scoring rule base; constructing a single-airport flight schedule optimization model based on predefined constraints and departure capacity constraints; and iteratively calculating the single-airport flight schedule optimization model to obtain the optimized flight schedule. This method can solve the problems of complex flight schedule arrangement, low optimization efficiency, and poor adaptability, thereby improving flight on-time performance, airport operational efficiency, and passenger travel experience.

Description

Technical Field

[0001] This application relates to the field of air transport management technology, specifically to a method, system, electronic device, readable storage medium, and computer program product for dynamically adjusting airport flight schedules. Background Technology

[0002] Currently, the air transport industry is developing rapidly, and flight punctuality has become a core indicator for measuring airline service quality and operational efficiency. However, with the continuous growth in air transport demand, flight delays are becoming increasingly serious, especially during takeoff. In practice, it has been found that one of the main reasons for flight delays is the unreasonable allocation of airport slot resources, particularly at hub airports during peak hours, where flight takeoffs and landings are excessively concentrated, leading to airspace congestion and insufficient ground support capabilities. Traditional flight schedule scheduling mainly relies on fixed time intervals and manual adjustments based on experience, which suffers from low optimization efficiency and poor adaptability. This static scheduling method is ill-suited to dynamic operating environments such as weather changes and air traffic control, easily causing flight sequence conflicts and resource imbalances, which not only reduce flight punctuality but also affect airport operational efficiency and passenger travel experience. Summary of the Invention

[0003] In view of the above problems, this application provides a method, system, electronic device, readable storage medium and computer program product for dynamic adjustment of airport flight schedules, which can solve the problems of complex flight schedule arrangement, low optimization efficiency and poor adaptability, thereby improving flight on-time rate, airport operation efficiency and improving passenger travel experience.

[0004] Firstly, this application provides a method for dynamically adjusting airport flight schedules, including:

[0005] Obtain the pre-planned historical flight schedule, the selected optimization range, and the meteorological data corresponding to the historical flight schedule;

[0006] Based on the historical flight schedule and the meteorological data, the departure capacity constraints of flights at different times within the optimization range are calculated according to the preset meteorological scoring rule library.

[0007] Based on the predefined constraints and the departure capacity constraints, a single-airport flight schedule optimization model is constructed.

[0008] The single-airport flight timetable optimization model is iteratively calculated to obtain the optimized flight timetable.

[0009] In the above technical solution, this method can provide multi-dimensional data support for optimization by integrating historical operational data and real-time meteorological information, ensuring the comprehensiveness and dynamic adaptability of model input. Then, it combines a meteorological scoring rule base to dynamically evaluate the impact of airspace conditions (such as visibility, wind speed, etc.) on flight departure capacity, achieving accurate quantification of capacity constraints and solving the problem of the disconnect between traditional fixed capacity assumptions and the actual operating environment. Next, it transforms multi-dimensional constraints such as dynamic capacity constraints, ground support resources, and airspace conflicts into mathematical model constraints, forming a solvable optimization framework. Finally, it uses an iterative algorithm to globally search for the optimal solution, balancing flight punctuality rate, airport throughput, and resource utilization, thereby generating a flight schedule that can significantly reduce delay rates and adapt to dynamic scenarios such as air traffic control and sudden weather events.

[0010] Secondly, this application provides an airport flight schedule dynamic adjustment system, including:

[0011] The acquisition unit is used to acquire a pre-planned historical flight schedule, a selected optimization range, and meteorological data corresponding to the historical flight schedule;

[0012] The calculation unit is used to calculate the departure capacity constraints of flights at different times within the optimization range based on the historical flight schedule and the meteorological data, according to a preset meteorological scoring rule library.

[0013] The model framework unit is used to construct a single-airport flight timetable optimization model based on predefined constraints and the departure capacity constraints.

[0014] The iterative calculation unit is used to perform iterative calculations on the single-airport flight timetable optimization model to obtain the optimized flight timetable.

[0015] In the above technical solution, the system can comprehensively consider historical flight data and meteorological factors, dynamically adjust flight departure capacity constraints, and achieve intelligent optimization of timetables through model iteration, thereby effectively solving the problems of low efficiency and poor adaptability of traditional scheduling methods, and improving flight regularity, airport operation efficiency and passenger travel experience.

[0016] Thirdly, this application provides an electronic device including a memory and a processor, the memory storing a computer program, and the processor running the computer program to cause the electronic device to perform the airport flight schedule dynamic adjustment method described in any one of the first aspects.

[0017] Fourthly, this application provides a readable storage medium storing a computer program, which, when executed by a processor, performs the airport flight schedule dynamic adjustment method described in any one of the first aspects.

[0018] Fifthly, this application provides a computer program product, which includes a computer program that, when executed by a processor, performs the airport flight schedule dynamic adjustment method described in any one of the first aspects.

[0019] The beneficial effects of this application are as follows: it can achieve real-time response by combining dynamic capacity scoring with the dynamic impact of meteorological conditions, thereby breaking through the limitations of static capacity in traditional methods; at the same time, the particle swarm optimization algorithm can derive the optimal flight schedule arrangement and achieve rapid convergence, which is conducive to improving the efficiency of the algorithm; in addition, by using meteorological dynamic capacity constraints, improved optimization algorithms and single-airport optimization models, it is also possible to significantly reduce flight delay time and improve resource utilization efficiency. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating the method for dynamically adjusting airport flight schedules in some embodiments of this application;

[0022] Figure 2 This is a flowchart illustrating the meteorological score calculation method in some embodiments of this application;

[0023] Figure 3 This is a flowchart illustrating the particle swarm optimization algorithm solution method in some embodiments of this application;

[0024] Figure 4 The particle swarm optimization algorithm in some embodiments of this application is used to obtain the iterative convergence curve of the first international airport model;

[0025] Figure 5 The particle swarm optimization algorithm in some embodiments of this application is used to obtain the iterative convergence curve of the second international airport model;

[0026] Figure 6 The particle swarm optimization algorithm in some embodiments of this application is used to obtain the iterative convergence curve of the third international airport model;

[0027] Figure 7 The particle swarm optimization algorithm in some embodiments of this application is applied to the iterative convergence curve of the fourth airport model;

[0028] Figure 8This is a comparison chart of the number of flights taking off at the first airport before and after optimization in some embodiments of this application;

[0029] Figure 9 This is a comparison chart of peak-hour flight departures before and after optimization of the second airport in some embodiments of this application;

[0030] Figure 10 This is a comparison chart of the number of flights taking off at the third airport before and after optimization in some embodiments of this application;

[0031] Figure 11 This is a comparison chart of the number of flights taking off at the fourth airport before and after optimization in some embodiments of this application;

[0032] Figure 12 This is a flowchart illustrating the method for dynamically adjusting airport flight schedules in some embodiments of this application;

[0033] Figure 13 This is a schematic diagram of the structure of an airport flight schedule dynamic adjustment system in some embodiments of this application;

[0034] Figure 14 This is a schematic diagram of the structure of an electronic device in some embodiments of this application. Detailed Implementation

[0035] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0037] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more (including two), similarly, "multiple sets" refers to two or more sets (including two sets), and "multiple pieces" refers to two or more pieces (including two pieces) unless otherwise explicitly defined.

[0038] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0039] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0040] While the current air transport sector has adopted flight schedule scheduling technology based on static capacity constraints and empirical rules, achieving basic scheduling by fitting historical data with preset fixed intervals, existing technologies face the following problems in the face of new situations such as surging passenger traffic, frequent extreme weather, and a surge in demand for multi-entity collaboration: Static capacity assessment models cannot respond to dynamic weather changes in real time, causing hub airports to still release flights according to theoretical capacity in scenarios such as low visibility and excessive crosswinds; Traditional optimization algorithms lack global search capabilities, making it difficult to balance individual flight adjustments with overall operational efficiency under complex constraints of millions of variables, resulting in dense slot conflicts at high-traffic airports; Single-airport independent optimization models ignore regional synergy effects, failing to dynamically reconstruct the national flight network when local delays occur, leading to chain propagation of delays.

[0041] To address the aforementioned technical issues, this application provides a method for dynamically adjusting airport flight schedules. This method prioritizes acquiring historical flight schedule data and corresponding meteorological data from various airports, quantifies meteorological conditions into normalized scores using the ATMAP meteorological scoring algorithm, and generates dynamic capacity constraints. Based on the particle swarm optimization algorithm, a single-airport flight schedule optimization model is constructed, with the minimization of total delay time as the objective function. The optimized flight schedule is generated by combining flight uniqueness constraints, adjustment range constraints, and dynamic capacity constraints.

[0042] Compared with existing technologies, this method can overcome the limitations of static capacity and achieve real-time response through dynamic capacity scoring while considering the dynamic impact of meteorological conditions. At the same time, it finds a satisfactory flight schedule arrangement based on the particle swarm optimization algorithm and achieves faster convergence. In addition, through meteorological dynamic capacity constraints, improved optimization algorithms and single-airport optimization models, it can also significantly reduce delay time and improve resource utilization efficiency, thus making it of great engineering application value.

[0043] like Figure 1As shown, some embodiments of this application provide a method for dynamically adjusting airport flight schedules, which includes:

[0044] S101. Obtain the pre-planned historical flight schedule, the selected optimization range, and the meteorological data corresponding to the historical flight schedule;

[0045] S102. Based on historical flight schedules and meteorological data, calculate the departure capacity constraints of flights at different times within the optimization range according to the preset meteorological scoring rule library.

[0046] S103. Based on the predefined constraints and departure capacity constraints, construct a single-airport flight timetable optimization model;

[0047] S104. Iteratively calculate the single-airport flight timetable optimization model to obtain the optimized flight timetable.

[0048] In some embodiments, a pre-planned historical flight schedule refers to a static schedule pre-established by the airport or airline that contains information such as all scheduled flight departure / arrival times and flight numbers, serving as the basis for optimization.

[0049] In some embodiments, the selected optimization range refers to the time interval for which time adjustments are required (e.g., 6:00-22:00 on a certain day) or the set of flights (e.g., all departing flights), used to define the processing boundaries of the model.

[0050] In some embodiments, the meteorological data corresponding to the historical flight schedule refers to real-time airport meteorological observation data (such as visibility, wind speed, precipitation, etc.) that matches the flight schedule time, and is used to dynamically assess the impact of meteorology on flight capacity.

[0051] In some embodiments, the meteorological scoring rule base refers to an expert knowledge base, specifically including a predefined set of rules that map meteorological elements (such as visibility <800 meters, crosswind >10 meters / second) to numerical scores, with higher scores indicating worse meteorological conditions.

[0052] In some embodiments, the departure capacity constraint for flights at different times within the optimization range refers to the maximum number of departing flights that the airport can allow within each time slice (e.g., 5 minutes) dynamically calculated based on the weather score, with lower capacity for worse weather.

[0053] In some embodiments, predefined constraints refer to hard rules that the model must satisfy, including flight uniqueness (each flight is assigned only one time slot), maximum adjustment range (e.g., delays do not exceed 2 hours), and resource conflict avoidance.

[0054] In some embodiments, the single-airport flight schedule optimization model refers to a mathematical programming model that aims to minimize total delays, integrates meteorological capacity constraints and operational rules, and outputs an adjusted flight schedule.

[0055] In some embodiments, the optimized flight schedule refers to the adjusted schedule calculated by the model, which includes the new scheduled departure times for each flight and significantly reduces the risk of delays compared to the original schedule.

[0056] For example, since the single-airport flight schedule optimization problem involves a variety of complex and uncertain factors, to ensure the rigor and solvability of the problem, the following assumptions are made for the single-airport flight schedule optimization model based on meteorological factors:

[0057] Assumption 1: The flight schedule optimization problem uses 5-minute time slices, also known as flight slots. For example, if a departing flight at 08:00 is shifted by one slot after optimization, the flight will now depart at 08:05. Furthermore, the planned departure times between departing flights in the flight schedule can be quantified in 5-minute intervals. For example, Flight A is scheduled to depart at 07:00, Flight B at 07:10, and Flight C at 07:25.

[0058] Assumption 2: The input to this model is a pre-planned historical flight schedule, and it optimizes and adjusts all flights within the selected time range whose departure airport is within the airport.

[0059] Assumption 3: Flights landing within the airport will not affect flights taking off within the airport;

[0060] Assumption 4: The airport has 288 adjustable flight slots, which is the daily flight schedule, and there is a uniform adjustment time range for each flight at each airport.

[0061] Assumption 5: Meteorological reports within the airport have been acquired, parsed, and a meteorological matrix corresponding to the airport has been established.

[0062] After satisfying the above assumptions, constraints are imposed on airport flights:

[0063] (1) Flight execution uniqueness constraint, ensuring that each flight uses only one flight slot once within the adjusted time range, including the following formula:

[0064]

[0065] in, This is for all departing flights to gather at the airport. This is the set of all adjustable flight schedules within the selected time range;

[0066] (2) Maximum adjustment range constraint for time slots, which means that each flight to be adjusted cannot take off or leave early and can only be delayed, and each flight has the same maximum number of adjustable flight slots, including the following formula:

[0067] ;

[0068] in, This refers to the initial flight time number of the flight in the original flight timetable. The maximum number of adjustable time slots for all pending flights;

[0069] (3) Takeoff and departure dynamic capacity constraints, which indicate that the number of flights taking off from an airport within the adjusted time range shall not exceed the dynamic capacity of the flight at its departure time, including the following formulas:

[0070] ;

[0071] in, For the airport in flight schedule Normalized meteorological scores; That is, when the flight time A higher score indicates worse weather conditions at that moment, meaning that the departure frequency of flights cannot be executed according to the historically fixed flight slot capacity. The smaller the value, the lower the capacity of the fixed flight slot. The product of these values ​​results in the dynamic capacity of flight schedules, which varies with weather factors. The worse the weather conditions, the lower the dynamic capacity.

[0072] With minimizing the total delay time as the objective function, through The objective function measures the model and includes the following formula:

[0073] ;

[0074] in, The value is set to 5, which means 5 minutes per flight time. It is used to convert the unit of the objective function into minutes.

[0075] In the above embodiments, the method proposes a dynamic adjustment method for single-airport flight schedules based on meteorological factors. It can dynamically control airport capacity by combining meteorological reports, which greatly improves the efficiency and rationality of flight schedule arrangement. This solves the problem that existing technologies ignore the dynamic impact of meteorological conditions when optimizing flight schedules, and the optimization algorithm PSO can solve the problem of insufficient efficiency.

[0076] In some embodiments, obtaining a pre-planned historical flight schedule, a selected optimization range, and meteorological data corresponding to the historical flight schedule includes:

[0077] Obtain pre-planned historical flight schedules, selected optimization ranges, and METAR historical messages; the selected optimization ranges include all flights departing from the target airport within the selected time range.

[0078] Meteorological data corresponding to historical flight schedules are obtained from METAR historical messages; the meteorological data includes message release time, visibility, cloud base height, wind direction, wind speed, and temperature.

[0079] In some embodiments, this method can prioritize acquiring METAR messages from different airports at different times. These messages are primarily used by pilots, air traffic controllers, and dispatchers to assess real-time airport weather conditions. The content includes real-time meteorological observation data such as visibility, wind speed and direction, cloud base height, precipitation, temperature, and air pressure. Some reports also include short-term weather change information (such as the BECMG keyword). The message structure is fixed, beginning with "METAR" or "SPECI" (Special Report), and includes the airport code, UTC release time, and various meteorological elements.

[0080] In some embodiments, the METAR message is an internationally recognized routine meteorological report for aviation, which is issued regularly by airport meteorological observation stations to provide critical real-time meteorological information for aviation operations.

[0081] For example, this method can obtain raw data from authoritative meteorological websites through web crawlers, and after format conversion, invalid information removal, element parsing and structuring, form structured data that can be used for analysis, providing basic meteorological information support for flight operation decisions.

[0082] In the above embodiments, the method can accurately extract meteorological elements (such as visibility and wind speed) that are strongly correlated with flight times by integrating high-precision METAR historical message data, providing a reliable basis for dynamically assessing departure capacity constraints at different times, thereby improving the adaptability of flight timetables to complex weather scenarios.

[0083] In some embodiments, based on historical flight schedules and meteorological data, the departure capacity constraints for flights at different times within the optimization range are calculated according to a preset meteorological scoring rule base, including:

[0084] A meteorological matrix corresponding to the optimized range is constructed based on historical flight schedules and meteorological data;

[0085] The meteorological score is calculated based on expert knowledge and meteorological matrix in the preset meteorological scoring rule base.

[0086] The meteorological scores are normalized to obtain the target meteorological factors;

[0087] Departure capacity constraints for flights at different times within the optimization range are generated based on target meteorological factors.

[0088] In some embodiments, the method can normalize meteorological data to generate a meteorological score, which is then proportionally incorporated into the airport's dynamic capacity. The dynamic capacity is calculated by combining the airport's fixed departure capacity with the following formula:

[0089] ;

[0090] in, For the airport in flight schedule Normalized meteorological scores;

[0091] That is, when the flight time A higher score indicates worse weather conditions at that moment, meaning that the departure frequency of flights cannot be executed according to the historically fixed flight slot capacity. The smaller the value, the lower the capacity of the fixed flight slot. The product of these values ​​results in the dynamic capacity of flight schedules, which varies with weather factors. The worse the weather conditions, the lower the dynamic capacity.

[0092] In the above embodiments, the method can transform discrete meteorological data into quantifiable target meteorological factors by constructing a meteorological matrix and integrating expert scoring rules, thereby realizing dynamic and refined calculation of departure capacity constraints and improving the response capability of flight schedule optimization to variable weather conditions.

[0093] In some embodiments, a meteorological score is calculated based on expert knowledge and a meteorological matrix in a preset meteorological scoring rule base to obtain a meteorological score, including:

[0094] The meteorological matrix is ​​quantified into multiple meteorological classification data;

[0095] The meteorological score is obtained by performing multi-category meteorological scoring based on expert knowledge in the pre-set meteorological scoring rule base and multiple meteorological classification data;

[0096] Among them, expert knowledge includes at least the scoring rules for visibility and cloud base height, wind, precipitation, icing conditions, and hazardous weather phenomena.

[0097] In some embodiments, the method may use the ATMAP algorithm to perform multi-class meteorological scoring based on expert knowledge in a preset meteorological scoring rule base and multiple meteorological classification data to obtain a meteorological score.

[0098] In some embodiments, the ATMAP algorithm (Air Traffic Management Adaptive Optimization Algorithm) is an intelligent algorithm designed specifically for flight schedule optimization and traffic management in complex airspace environments. Its core objective is to achieve a comprehensive improvement in flight punctuality, operational efficiency, and resource utilization by dynamically adapting to multi-dimensional constraints such as weather, traffic flow, and airspace restrictions.

[0099] In some embodiments, the ATMAP algorithm was jointly developed by experts from multiple fields, including meteorology, air traffic control, airport operators, airlines, and mathematicians, within the European Union organization, and is primarily applied to:

[0100] (1) Conduct unified measurements of weather conditions at airports across Europe;

[0101] (2) To objectively and comprehensively measure the intensity and duration of weather phenomena that may make ANS and airport airside operations more difficult;

[0102] (3) Divide the operating days into two categories to enable higher-dimensional analysis. This algorithm helps air traffic managers make decisions to optimize flight scheduling and ground operations and improve the overall operational efficiency of the airport by analyzing the impact of weather conditions on airport operating efficiency.

[0103] In some embodiments, the ATMAP algorithm can quantify airport meteorological data into five categories: visibility, wind, precipitation, icing conditions, and hazardous weather. Each category has a severity level and provides coefficients to reflect the different severity levels under different meteorological conditions. For each specified severity level code, a value called the summary score coefficient is given, which enables the description of the non-linear behavior of several weather events.

[0104] For example, the visibility and cloud base height scores in the ATMAP rating are shown in Table 1 below.

[0105] Table 1: Scoring Rules for Visibility and Cloud Base Height

[0106]

[0107] An airport's ANS performance (runway throughput, delays) varies with visibility levels. In low visibility, airport performance depends on the Instrument Landing System (ILS) or other approach aids. Reduced visibility affects both takeoffs and landings. Under the same weather conditions, the decline in airport ANS performance in poor visibility will vary depending on the aids used (ILS, MLS, satellite-aided systems, multilateral ground motion radar, etc.) and the approved air traffic control procedures employed.

[0108] In the visibility and cloud base high score examples, the METAR message provides the visibility value (VIS), the runway visible range value (RVR), and three sets of cloud values ​​(CLD_base, CLD_type, CLD_cover). Code 1, Code 2, Code 3, and Code 4 correspond to the limit values ​​under non-precision approach runway conditions, Category I precision approach runway conditions, Category II precision approach runway conditions, and Category III precision approach runway conditions, respectively. The score for each category is set according to the flight interval, operational complexity, and error probability under different landing procedures.

[0109] Regarding wind, a meteorological element, it has multiple effects on airport operational performance, as shown in Table 2.

[0110] Table 2: Scoring Rules for Wind

[0111]

[0112] When wind speeds increase to 15 KT / S or higher, airport operations become more difficult, whether it's crosswinds or headwinds. At the same wind speed, gusts also increase the difficulty of aircraft landing, so one point is added to the score for each gust.

[0113] Regarding precipitation, a meteorological element, it directly affects runway friction. Increased precipitation reduces aircraft taxiing speed, leading to increased runway occupancy time. As shown in Table 3, the METAR report infers the runway friction coefficient based on precipitation amount and type. Different scores are assigned based on the precipitation type in the report code; higher precipitation amounts tend to reduce runway friction levels, thus causing flight delays.

[0114] Table 3: Precipitation Scoring Rules

[0115]

[0116] Regarding the meteorological element of icing conditions, these conditions are determined by both humidity and temperature. Icing not only affects the runway friction coefficient but also increases the need for pre-flight de-icing checks and runway clearing, leading to delays in takeoff times. The impact of this condition varies depending on the region and season; for example, icing is more likely to occur in northern winters, while the situation is less severe in the south. The rating given here is based on general conditions but can be adjusted based on historical data compiled by airports during use.

[0117] The scoring rules for freezing conditions are shown in Table 4. When the temperature is above 3°C, the presence of visible humidity will not lead to freezing. When the temperature is below 3°C and there is a small amount of precipitation, the freezing condition is mild. When the temperature is below 3°C and the snowfall is small, the freezing condition is moderate. When the temperature is below 3°C and there is heavy snowfall or the temperature is below -15°C and there is any form of visible humidity, the freezing condition is severe.

[0118] Table 4: Scoring Rules for Icing Condition

[0119]

[0120] In the meteorological element of hazardous weather phenomena, hazardous weather phenomena include all observed weather conditions that threaten the safety of aircraft operations. These mainly include cumulonimbus clouds (CB), vertically developing cumulonimbus clouds (TCU), thunderstorms (TS), hail (GS), tornadoes (FC), and dust storms (DS). Scores are assigned based on the degree of delay caused by these weather phenomena. Some examples are shown in Table 5.

[0121] Table 5: Example of scoring rules for hazardous weather phenomena

[0122]

[0123] based on Figure 2 The flowchart illustrating the meteorological scoring calculation method shows that after reading the CSV file containing METAR reports using the pandas library in Python, the system parses and extracts information on wind speed, visibility and cloud base height, precipitation, icing status, and hazardous weather phenomena from the reports. Then, scores are calculated based on different weather elements and their severity, and the results are stored in a new CSV file.

[0124] In the above embodiments, the method can transform complex meteorological conditions into quantifiable comprehensive scoring indicators by integrating expert scoring rules of multiple meteorological elements, providing a fine-grained meteorological impact assessment basis for departure capacity constraints.

[0125] In some embodiments, the constraints include flight execution uniqueness constraints, maximum time period adjustment constraints, and takeoff and departure dynamic capacity constraints;

[0126] The flight execution uniqueness constraint means that each flight uses only one flight slot within the adjusted time range, and the use of that flight slot is executed only once.

[0127] The maximum adjustment range for a time slot means that each flight to be adjusted cannot take off or leave early and can only be delayed, and each flight has the same maximum number of adjustable flight slots;

[0128] The dynamic capacity constraint for takeoff and departure means that within the adjusted time range, the number of flights taking off at an airport must not exceed the dynamic capacity of the flight slot at the time of departure.

[0129] In the above embodiments, the method can ensure the uniqueness, controllability and real-time matching with the dynamic capacity of the airport by coordinating the control of multi-dimensional constraints, thereby maximizing the efficiency of time slot resource utilization while ensuring operational safety.

[0130] In some embodiments, the single-airport flight schedule optimization model includes at least the set of all flights to be adjusted at the target airport, the set of flights departing from the target airport, the initial flight time sequence number of the flights in the original flight schedule, the set of all adjustable flight times within the selected time range, the flight times allocated during optimization, the weather score of the target airport at each flight time, the fixed departure capacity of the target airport, the maximum number of adjustable time slices for all flights to be adjusted, and preset unit conversion parameters.

[0131] The single-airport flight schedule optimization model takes minimizing total delay time as its objective function.

[0132] In some embodiments, the method aims to construct a flight schedule optimization model based on meteorological factors to better reflect weather and other factors considered in actual operations, thereby enabling early warning of weather impacts and flexible scheduling of flight plans.

[0133] For example, the parameters in the flight timetable optimization model based on meteorological factors are defined as shown in Table 6.

[0134] Table 6: Definitions of parameters in the flight timetable optimization model

[0135]

[0136] In the above embodiments, the method can achieve global collaborative optimization of flight schedules by constructing a refined optimization model that includes multi-dimensional operating parameters and dynamic meteorological factors, with the goal of minimizing total delays. This significantly improves the rationality of schedule resource allocation and overall operating efficiency in complex operating environments.

[0137] In some embodiments, the single-airport flight timetable optimization model is iteratively calculated to obtain an optimized flight timetable, including:

[0138] Obtain the configuration parameters for the particle swarm optimization algorithm; the configuration parameters should include at least the maximum number of iterations, the number of particles, the social learning rate, the cognitive learning rate, and the inertia weight.

[0139] Based on the configuration parameters and objective function, the single-airport flight timetable optimization model is subjected to particle swarm optimization iteration to obtain the particle swarm iteration optimization results.

[0140] The optimized flight schedule is generated based on the particle swarm optimization results.

[0141] In some embodiments, the parameter configuration can be as shown in Table 7 below.

[0142] Table 7: Particle Swarm Optimization Algorithm Parameter Configuration

[0143]

[0144] After adjusting the parameters according to Table 7, particle swarm iteration can be performed to find the optimal position.

[0145] In the above embodiments, the method can achieve rapid convergence and high-quality solution generation for the flight timetable optimization problem by introducing the efficient global search capability of the particle swarm optimization algorithm and combining iterative parameter configuration with dynamic adjustment, thereby significantly improving optimization efficiency and global optimality of the timetable under complex constraints.

[0146] In some embodiments, a particle swarm optimization iteration is performed on the single-airport flight timetable optimization model according to configuration parameters and an objective function to obtain the particle swarm iteration optimization result, including:

[0147] Initialize particle position and particle velocity based on historical flight schedules and particle count;

[0148] Calculate the new velocity and new position of each particle based on its position and velocity.

[0149] Calculate the new fitness value for each particle based on its new velocity and new position;

[0150] Update the individual extreme value and the population extreme value based on the new fitness value of each particle and the objective function;

[0151] Update the optimal position of each particle's function based on the individual extreme value and the group extreme value;

[0152] The global optimal solution of the population is updated based on the functional optimal position of each particle;

[0153] When the maximum number of iterations is reached, the final updated global optimal solution is determined as the result of particle swarm optimization.

[0154] In some embodiments, Particle Swarm Optimization (PSO) is a heuristic optimization algorithm proposed in 1995, simulating group behaviors such as flocks of birds foraging and schools of fish swimming. Originally a simulation of the "group decision-making process" in social psychology, it was later abstracted into an optimization algorithm, searching for the optimal solution to a problem by simulating the cooperation and competition among individuals within a group. Compared to evolutionary algorithms such as Genetic Algorithms (GA), PSO avoids complex operations like crossover and mutation, has fewer parameters, and is simpler to implement. Each particle represents a candidate solution in the solution space. Each particle starts from a starting point and reaches a random position at a random speed, generating a new solution. Then, each particle calculates and records its current fitness value. Subsequently, each particle sets off again to a new location, continuously adjusting its position and speed guided by its own historical best solution and the best solution among the group's particles. This process of "generating a new solution → calculating fitness value → updating the individual's optimal position and the population's optimal position → updating the optimal fitness value" is repeated until the global optimum is found.

[0155] For example, such as Figure 3 As shown, the steps for solving the problem using the particle swarm optimization algorithm can be as follows:

[0156] (1) The initial position of each particle is the historical flight schedule;

[0157] (2) Each particle arrives at a different location according to the velocity and position update formula, which generates a new solution, including the following formula:

[0158]

[0159] in, and These are individual learning factors and group learning factors, respectively. and A random decimal number between [0,1]. The inertial weight of the particle during its movement. and Particles At any moment Individual Optimum and Group exist The optimal time for a group to be together.

[0160]

[0161] in, For particles At any moment new location, For particles At any moment Historical position, For particles At any moment A new speed.

[0162] The fitness value is calculated based on the new position of each particle, which involves calculating the objective function value and comparing it with the previous value. If the objective function value is better, the fitness value is updated; otherwise, the previous fitness value is retained. Simultaneously, the optimal position of the individual particle and the optimal position of the population are updated.

[0163] (3) Repeat the steps to perform iterative updates;

[0164] (4) Determine whether the set number of iterations has been reached. If it has, end the optimization. If it has not, continue the iterative optimization.

[0165] In the above embodiments, the method can achieve global optimal search and fast convergence of flight timetables under multidimensional constraints by combining the dynamic iteration mechanism of particle swarm optimization algorithm with a particle initialization strategy driven by historical flight data. This effectively balances computational efficiency and optimization accuracy, and improves the rationality of time resource allocation in complex scenarios.

[0166] In some embodiments, the method further includes: validating the optimization model and evaluating metrics.

[0167] For example, this method is performed in the following hardware and software environment: the processor is an Intel® Core™ i5-7500 (3.40 GHz) equipped with an NVIDIA Quadro GP100 accelerated graphics card; the operating system is Ubuntu 18.04; the development tool is PyCharm; and the programming language is Python.

[0168] Based on this, and using statistical analysis of historical flight schedule data for each airport, this example selected the day with the longest delay for each airport as the target for optimization: September 15, 2020, International Airport 1 (387 flights departing / departing, delay time 4566 minutes); September 18, 2020, International Airport 2 (249 flights departing / departing, delay time 630 minutes); October 28, 2020, International Airport 3 (171 flights departing / departing, delay time 2551 minutes); and May 14, 2021, International Airport 4 (63 flights departing / departing, delay time 560 minutes). A comparison of the flight schedules before and after optimization for each airport is detailed in Tables 8 to 11. Simultaneously, by collecting and analyzing the full-day METAR weather reports for each airport, and using the flight number as the primary key, the weather data was fused with the flight schedule data for that day. The encoded flight schedules and meteorological matrices for each airport were then used as inputs to a single-airport flight schedule optimization model based on meteorological factors, in order to verify the effectiveness of the model in responding to meteorological factors in actual operation and its practical value in optimizing flight scheduling.

[0169] Table 8: Comparison of Flight Schedules Before and After Optimization at the First International Airport

[0170]

[0171] Table 9: Comparison of Flight Schedules Before and After Optimization at the Second International Airport

[0172]

[0173] Table 10: Comparison of Flight Schedules Before and After Optimization at the Third International Airport

[0174]

[0175] Table 11: Comparison of Flight Schedules Before and After Optimization at the Fourth Airport

[0176]

[0177] In the above embodiments, this method overcomes the limitations of static capacity, as traditional models ignore the dynamic impact of meteorological conditions. Simultaneously, it achieves real-time response through dynamic capacity scoring; furthermore, it can quickly converge based on particle swarm optimization algorithms, finding satisfactory flight schedule arrangements.

[0178] For example, the particle swarm optimization algorithm is applied to the iterative convergence graph of each airport model, such as... Figures 4 to 7 As shown ( Figure 4 The convergence curve of the model for the first international airport. Figure 5 The convergence curve of the second international airport model. Figure 6 The convergence curve of the third international airport model. Figure 7(Convergence curve of the fourth airport model). Figures 4 to 7 The horizontal axis represents the number of iterations, and the vertical axis represents the delay time of each airport, i.e., the objective function of the flight timetable optimization model for each single airport. The red horizontal dashed line represents the original delay time of each airport on that day. Figures 4 to 7 It is evident that the delay time decreases rapidly in the early stages of iteration and then stabilizes in the later stages, verifying that the algorithm converges stably after a certain number of iterations.

[0179] For example, the method also shows a comparison of evaluation indicators before and after optimization for each airport in Table 12.

[0180] Table 12: Comparison of Evaluation Indicators Before and After Optimization for Each Airport

[0181]

[0182] The evaluation metrics included total delay time, average delay time per flight, and number of overcapacity flight slots. The results showed that total delay time and average delay time per flight were significantly reduced at airports one, two, three, and four, and no airports experienced overcapacity flight slots.

[0183] In the above embodiments, delay times at the first airport were reduced by 21.59% and 21.62%, respectively; at the third airport by 51% and 51.01%, respectively; and at the fourth airport by 73.50% and 73.45%, respectively, with no overcapacity flight slots. These results validate the effectiveness of the single-airport flight schedule optimization model based on meteorological factors in reducing delays.

[0184] For example, after iterating the single-airport flight schedule optimization model based on meteorological factors using the PSO optimization algorithm, the delay time of each single airport decreased, and the number of flights per hour at the corresponding airport was also adjusted. The specific flight schedules during peak hours before and after the adjustment for each airport are shown in the following figure. Figures 8 to 11 As shown ( Figure 8 A comparison chart of flight departures at the First Airport before and after optimization, showing the departure times for certain periods. Figure 9 A comparison chart of peak-hour flight departures before and after optimization for the second airport. Figure 10 A comparison chart of flight departures before and after optimization at the third airport during certain time periods. Figure 11 (Comparison chart of flight departures before and after optimization of the fourth airport during certain time periods).

[0185] In summary, the proposed single-airport flight schedule optimization model based on meteorological factors takes minimizing single-airport delay time as the objective function, and considers flight uniqueness, the range of adjusted flight times for each flight, and dynamic capacity constraints for departure flight times.

[0186] Based on the analysis results, the following airports were selected as optimization targets: the first airport on September 15, 2020; the second airport on September 18, 2020; the third airport on October 28, 2020; and the fourth airport on May 14, 2021. The particle swarm optimization algorithm was then applied to solve the optimization models of these four single airports.

[0187] The results show that, compared with the historical flight schedules that have been implemented, the delay time of each airport and the average delay time per flight have both decreased significantly, improving resource utilization efficiency. At the same time, it also provides effective assistance for the arrangement and optimization of flight schedules at each airport, and has broad engineering application value.

[0188] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below. In some embodiments, such as Figure 12 As shown, the airport's dynamic flight schedule adjustment methods include:

[0189] S201. Obtain historical flight schedule data and corresponding meteorological data, and construct a meteorological matrix.

[0190] S202. Based on the ATMAP algorithm, new feature data with expert knowledge is generated from the METAR message data to form a meteorological score.

[0191] S203. Calculate the dynamic capacity score for each flight time based on the meteorological matrix and generate dynamic capacity constraints.

[0192] S204. Construct a single-airport flight timetable optimization model with the objective function of minimizing total delay time, and define the following constraints: flight execution uniqueness constraint; maximum time slot adjustment constraint; takeoff and departure dynamic capacity constraint.

[0193] S205. The particle swarm optimization algorithm is used to iteratively solve the model, construct a single-airport flight timetable optimization model based on meteorological factors, and generate the optimized flight timetable.

[0194] S206. Verify and optimize the model, and evaluate the indicators.

[0195] Figure 13 This diagram illustrates the structure of an airport flight schedule dynamic adjustment system. It should be understood that this system is related to... Figure 1 The method executed in the middle corresponds to the steps involved in the aforementioned method. The specific functions and effects of the system can be found in the description above. To avoid repetition, detailed descriptions are omitted here.

[0196] The airport's dynamic flight schedule adjustment system includes:

[0197] The acquisition unit 310 is used to acquire the pre-planned historical flight schedule, the selected optimization range, and the meteorological data corresponding to the historical flight schedule;

[0198] The calculation unit 320 is used to calculate the departure capacity constraints of flights at different times within the optimization range based on historical flight schedules and meteorological data, according to a preset meteorological scoring rule library.

[0199] Model framework unit 330 is used to construct a single-airport flight timetable optimization model based on predefined constraints and departure capacity constraints;

[0200] The iterative calculation unit 340 is used to perform iterative calculations on the single-airport flight timetable optimization model to obtain the optimized flight timetable.

[0201] In some embodiments, the acquisition unit 310 is specifically used to acquire a pre-planned historical flight schedule, a selected optimization range, and METAR historical messages; the selected optimization range includes all flights that depart from the target airport within a selected time range.

[0202] The acquisition unit 310 is also used to acquire meteorological data corresponding to historical flight schedules based on METAR historical messages; the meteorological data includes message release time, visibility, cloud base height, wind direction, wind speed and temperature.

[0203] In some embodiments, the computing unit 320 includes:

[0204] Subunit 321 is constructed to build a meteorological matrix corresponding to the optimization range based on historical flight schedules and meteorological data.

[0205] The calculation subunit 322 is used to calculate the meteorological score based on the expert knowledge and meteorological matrix in the preset meteorological scoring rule base and obtain the meteorological score;

[0206] Normalization subunit 323 is used to normalize the meteorological score to obtain the target meteorological factor;

[0207] The first generation subunit 324 is used to generate departure capacity constraints for flights at different times within the optimization range based on the target meteorological factors.

[0208] In some embodiments, the calculation subunit 322 is specifically used to quantify the meteorological matrix into multiple meteorological classification data; perform multi-class meteorological scoring based on expert knowledge in a preset meteorological scoring rule base and multiple meteorological classification data to obtain a meteorological score;

[0209] Among them, expert knowledge includes at least the scoring rules for visibility and cloud base height, wind, precipitation, icing conditions, and hazardous weather phenomena.

[0210] In some embodiments, the constraints include flight execution uniqueness constraints, maximum time period adjustment constraints, and takeoff and departure dynamic capacity constraints;

[0211] The flight execution uniqueness constraint means that each flight uses only one flight slot within the adjusted time range, and the use of that flight slot is executed only once.

[0212] The maximum adjustment range for a time slot means that each flight to be adjusted cannot take off or leave early and can only be delayed, and each flight has the same maximum number of adjustable flight slots;

[0213] The dynamic capacity constraint for takeoff and departure means that within the adjusted time range, the number of flights taking off at an airport must not exceed the dynamic capacity of the flight slot at the time of departure.

[0214] In some embodiments, the single-airport flight schedule optimization model includes at least the set of all flights to be adjusted at the target airport, the set of flights departing from the target airport, the initial flight time sequence number of the flights in the original flight schedule, the set of all adjustable flight times within the selected time range, the flight times allocated during optimization, the weather score of the target airport at each flight time, the fixed departure capacity of the target airport, the maximum number of adjustable time slices for all flights to be adjusted, and preset unit conversion parameters.

[0215] The single-airport flight schedule optimization model takes minimizing total delay time as its objective function.

[0216] In some embodiments, the iterative calculation unit 340 includes:

[0217] Acquire subunit 341 to acquire configuration parameters for the particle swarm optimization algorithm; the configuration parameters include at least the maximum number of iterations, the number of particles, the social learning rate, the cognitive learning rate, and the inertia weight;

[0218] Iteration subunit 342 is used to perform particle swarm optimization iteration on the single airport flight timetable optimization model according to the configuration parameters and objective function, and obtain the particle swarm iterative optimization result.

[0219] The second generating subunit 343 is used to generate an optimized flight timetable based on the particle swarm optimization results.

[0220] In some embodiments, the iterative subunit 342 is specifically configured to initialize particle positions and particle velocities based on historical flight schedules and particle numbers; calculate new velocities and new positions for each particle based on particle positions and particle velocities; calculate new fitness values ​​for each particle based on new velocities and new positions; update individual and swarm extreme values ​​based on the new fitness values ​​and objective function; update the optimal position of each particle based on individual and swarm extreme values; update the global optimal solution of the swarm based on the optimal position of each particle; and when the maximum number of iterations is reached, determine the finally updated global optimal solution as the particle swarm iterative optimization result.

[0221] like Figure 14 As shown, this application provides an electronic device 400, which includes a processor 401 and a memory 402. The processor 401 and the memory 402 are interconnected and communicate with each other through a communication bus 403 and / or other forms of connection mechanism (not shown). The memory 402 stores a computer program that can be executed by the processor 401. When the computing device is running, the processor 401 executes the computer program to perform the method in any of the aforementioned optional implementations.

[0222] This application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the method in any of the aforementioned optional implementations.

[0223] The computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0224] This application provides a computer program product, which includes a computer program that, when run by a processor, executes the method in any of the aforementioned optional implementations.

[0225] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and not to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and they should all be covered within the scope of the claims and specification of this application. In particular, as long as there is no conflict, the various technical features mentioned in the embodiments can be combined in any way. This application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for dynamically adjusting airport flight schedules, characterized in that, include: Obtain the pre-planned historical flight schedule, the selected optimization range, and the meteorological data corresponding to the historical flight schedule; Based on the historical flight schedule and the meteorological data, the departure capacity constraints for flights at different times within the optimization range are calculated according to a preset meteorological scoring rule library; the departure capacity constraint refers to the maximum number of departing flights allowed by the current airport. Based on the predefined constraints and the departure capacity constraints, a single-airport flight schedule optimization model is constructed. The single-airport flight timetable optimization model is iteratively calculated to obtain the optimized flight timetable; The step of calculating the departure capacity constraints for flights at different times within the optimization range based on the historical flight schedule and the meteorological data, according to a preset meteorological scoring rule base, includes: Construct a meteorological matrix corresponding to the optimization range based on the historical flight schedule and the meteorological data; A meteorological score is obtained by calculating the meteorological score based on the expert knowledge in the preset meteorological scoring rule base and the meteorological matrix; The meteorological scores are normalized to obtain the target meteorological factors; Based on the target meteorological factors, departure capacity constraints for flights at different times within the optimization range are generated; The single-airport flight schedule optimization model includes at least the set of all flights to be adjusted at the target airport, the set of flights departing from the target airport, the initial flight time sequence number of the flights in the original flight schedule, the set of all adjustable flight times within the selected time range, the flight times allocated during optimization, the weather score of the target airport at each flight time, the fixed departure capacity of the target airport, the maximum number of adjustable time slices for all flights to be adjusted, and preset unit conversion parameters. The single-airport flight timetable optimization model takes minimizing total delay time as its objective function.

2. The method for dynamically adjusting airport flight schedules according to claim 1, characterized in that, The process of obtaining the pre-planned historical flight schedule, the selected optimization range, and the meteorological data corresponding to the historical flight schedule includes: Obtain the pre-planned historical flight schedule, the selected optimization range, and METAR historical messages; the selected optimization range includes all flights departing from the target airport within the selected time range. Meteorological data corresponding to the historical flight schedule is obtained from the METAR historical messages; the meteorological data includes message release time, visibility, cloud base height, wind direction, wind speed, and temperature.

3. The method for dynamically adjusting airport flight schedules according to claim 1, characterized in that, The step of calculating a meteorological score based on expert knowledge in a preset meteorological scoring rule base and the meteorological matrix, including: The meteorological matrix is ​​quantified into multiple meteorological classification data; Based on expert knowledge in a pre-set meteorological scoring rule base and multiple meteorological classification data, a multi-category meteorological score is obtained. The expert knowledge mentioned includes at least the scoring rules for visibility and cloud base height, wind, precipitation, icing conditions, and hazardous weather phenomena.

4. The method for dynamically adjusting airport flight schedules according to claim 1, characterized in that, The constraints include flight execution uniqueness constraints, maximum time period adjustment constraints, and takeoff and departure dynamic capacity constraints. The flight execution uniqueness constraint means that each flight uses only one flight slot within the adjusted time range, and the use of that flight slot is executed only once; The maximum adjustment range constraint for the time period means that each flight to be adjusted cannot take off or leave the airport early and can only be delayed, and each flight has the same maximum number of adjustable flight slots; The aforementioned takeoff and departure dynamic capacity constraint means that within the adjusted time range, the number of flights taking off from an airport must not exceed the dynamic capacity of the flight slot at the time of takeoff.

5. The method for dynamically adjusting airport flight schedules according to claim 1, characterized in that, The iterative calculation of the single-airport flight timetable optimization model to obtain the optimized flight timetable includes: Obtain the configuration parameters of the particle swarm optimization algorithm; the configuration parameters include at least the maximum number of iterations, the number of particles, the social learning rate, the cognitive learning rate, and the inertia weight; Based on the configuration parameters and the objective function, the single-airport flight timetable optimization model is subjected to particle swarm optimization iteration to obtain the particle swarm iteration optimization result. The optimized flight schedule is generated based on the particle swarm optimization results.

6. The method for dynamically adjusting airport flight schedules according to claim 5, characterized in that, The step of performing particle swarm optimization iteration on the single-airport flight timetable optimization model based on the configuration parameters and the objective function to obtain the particle swarm iteration optimization result includes: Initialize particle position and particle velocity based on the historical flight schedule and the particle count; Calculate the new velocity and new position of each particle based on the particle position and particle velocity; Calculate the new fitness value for each particle based on its new velocity and new position; Update the individual extreme value and the population extreme value based on the new fitness value of each particle and the objective function; Update the optimal position of each particle's function based on the individual extreme value and the group extreme value; The global optimal solution of the population is updated based on the functional optimal position of each particle; When the maximum number of iterations is reached, the final updated global optimal solution is determined as the particle swarm optimization result.

7. An airport flight schedule dynamic adjustment system, characterized in that, The airport flight schedule dynamic adjustment system includes: The acquisition unit is used to acquire a pre-planned historical flight schedule, a selected optimization range, and meteorological data corresponding to the historical flight schedule; The calculation unit is used to calculate the departure capacity constraint of flights at different times within the optimization range based on the historical flight schedule and the meteorological data, according to a preset meteorological scoring rule library; the departure capacity constraint refers to the maximum number of departing flights allowed by the current airport. The model framework unit is used to construct a single-airport flight timetable optimization model based on predefined constraints and the departure capacity constraints. An iterative calculation unit is used to perform iterative calculations on the single-airport flight timetable optimization model to obtain the optimized flight timetable. The computing unit includes: Construct sub-units to build a meteorological matrix corresponding to the optimization range based on historical flight schedules and meteorological data; The calculation subunit is used to calculate the meteorological score based on the expert knowledge and meteorological matrix in the preset meteorological scoring rule base. The normalization sub-unit is used to normalize the meteorological score to obtain the target meteorological factor. The first generation sub-unit is used to generate departure capacity constraints for flights at different times within the optimization range based on the target meteorological factors. The single-airport flight schedule optimization model includes at least the set of all flights to be adjusted at the target airport, the set of flights departing from the target airport, the initial flight time sequence number of the flights in the original flight schedule, the set of all adjustable flight times within the selected time range, the flight times allocated during optimization, the weather score of the target airport at each flight time, the fixed departure capacity of the target airport, the maximum number of adjustable time slices for all flights to be adjusted, and preset unit conversion parameters. The single-airport flight schedule optimization model takes minimizing the total delay time as its objective function.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to cause the electronic device to perform the airport flight schedule dynamic adjustment method according to any one of claims 1 to 6.

9. A readable storage medium, characterized in that, The readable storage medium stores a computer program, which, when executed by a processor, performs the airport flight schedule dynamic adjustment method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, performs the airport flight schedule dynamic adjustment method as described in any one of claims 1 to 6.

Images