Flight plan generation method and system for air traffic time-varying environment

Abstract

The invention is suitable for the technical field of aviation flight, and provides a flight plan generation method and system for an air traffic time-varying environment, and the method comprises the following steps: collecting data which comprises the origin-destination and plan time of a flight, the performance of an aircraft, the layout of waypoints and the airspace information of the waypoints; extracting features of an air traffic time-varying environment based on a space-time network; constructing a flight plan generation bilevel planning model considering the air traffic time-varying environment; designing a two-stage algorithm for solving a flight plan to generate a double-layer planning model; and evaluating the robustness of the solution. According to the invention, big data and artificial intelligence technologies are fused, a flight plan generation double-layer planning model considering a time-varying traffic environment and a two-stage solving algorithm thereof are established, and a robustness evaluation technology of a flight plan is discussed. A function of automatically generating an executable flight route point sequence and a corresponding flight path according to an air traffic time-varying environment is realized, and a technical support is provided for intelligent management of a flight plan by a daily dispatcher.

Description

Technical Field

[0001] This invention belongs to the field of aviation flight technology, and in particular relates to a method and system for generating flight plans in time-varying air traffic environments. Background Technology

[0002] Flight plan generation in a time-varying air traffic environment is a complex process that requires comprehensive consideration of multiple factors. Based on the origin and destination, combined with airspace restrictions, navigation facility distribution and meteorological conditions, the initial route is planned using aeronautical charts or professional software. Great circle routes are considered to shorten the flight distance, while avoiding no-fly zones, danger zones and air traffic congestion areas. Real-time weather forecast data, including wind direction, wind speed, temperature, air pressure, cloud cover, thunderstorms, etc., needs to be obtained to analyze their impact on flight. If necessary, the flight altitude or speed is adjusted, such as to avoid thunderstorm areas, and fuel quantity and flight time are adjusted according to headwind or tailwind conditions. Clearly, the main significance of flight plan generation in time-varying air traffic environments includes: considering time-varying environmental factors, enabling real-time avoidance of hazardous weather areas and air traffic congestion areas, reducing flight conflict and accident risks, and ensuring the safety of passengers, crew, and aircraft; optimizing routes, flight altitudes, and speeds based on real-time weather and traffic flow, which can shorten flight time, reduce fuel consumption, lower airline operating costs, improve flight punctuality, and enhance airline competitiveness; and rationally planning flight plans can enable fuller and more efficient use of airspace resources, reduce airspace congestion, improve the overall capacity and operational efficiency of the air traffic system, and achieve rational resource allocation.

[0003] Existing technologies optimize flight paths and scheduling schemes by establishing dynamic programming models and genetic algorithm models. However, it is rare to find the optimal flight plan by considering multiple time-varying factors. In particular, it ignores the correlation between flight plan and trajectory, which is one-sided and cannot be widely applied to real-world scenarios. Summary of the Invention

[0004] The purpose of this invention is to provide a method for generating flight plans in time-varying air traffic environments, aiming to solve the problems mentioned in the background art.

[0005] The present invention is implemented as follows: a flight plan generation method for time-varying air traffic environments includes the following steps:

[0006] Collect data, including flight origin and destination points and scheduled times, aircraft performance, waypoint layout and airspace information;

[0007] Based on spatiotemporal networks, features of the time-varying environment of air traffic are extracted;

[0008] Construct a two-level programming model for flight plan generation that takes into account the time-varying environment of air traffic;

[0009] Design a two-stage algorithm to solve the bi-level programming model for flight plan generation;

[0010] Evaluate the robustness of the solution.

[0011] Preferably, the step of collecting data, which includes the departure and arrival points and scheduled times of flights, aircraft performance, waypoint layout, and airspace information, specifically includes:

[0012] The departure airport of the flight is The airport ends The planned departure time is ;

[0013] Aircraft performance, including speed range fuel cost per unit mileage and maximum fuel volume ;

[0014] Waypoint layout and its airspace information, including node sets and flight segment collection Each segment The distance is ,in and .

[0015] Preferably, the step of extracting features of the time-varying air traffic environment based on a spatiotemporal network specifically includes:

[0016] Considering the safe operational performance of the aircraft, each flight segment airspace information Gridding, in total One grid;

[0017] For any two grids and Considering the time-varying air traffic environment at time t, determine whether it is a prohibited passage state. and ,like , If the '+' indicates passage; otherwise, , , then indicates stillness;

[0018] For any adjacent grid and Determine whether the flight is prohibited from passing at time t. Must meet ,like , then it means passage. and .

[0019] Preferably, the steps of constructing a two-level planning model for flight plan generation that considers the time-varying environment of air traffic specifically include:

[0020] In the upper-level model, considering real-world constraints, the origin and destination of the flight are... and Planned departure time Calculate the order of waypoints and actual departure time of the flight. The objective function is to minimize the total scheduling cost. ;

[0021] The constraints include: ,

[0022] ,

[0023] ,

[0024] ,

[0025] ;

[0026] in: Represents the set of waypoints. and It's weight. This is the largest deviation between the planned and actual departure time. and Each waypoint and Time, It is the time of departure. Indicates waypoints and The flight path mileage, This indicates fuel consumption per unit distance. This indicates the maximum fuel consumption. Indicates aircraft speed. Indicates whether the route passes through adjacent waypoints. and ;

[0027] In the lower-level model, when the upper-level model's When determined, according to calculate to divide each flight segment airspace information Grid-based approach, considering the spatiotemporal distribution of the time-varying air traffic environment network at time t, to calculate adjacent waypoints. At any moment Best route The objective function is: ;

[0028] The constraints include: ,

[0029] ,

[0030] ,

[0031] ;

[0032] in: Indicates waypoints and airspace A set of grids, and Different path grids and Time, waypoints Corresponding grid time, Indicates adjacent grids and distance, Indicates adjacent grids and In time The passage status, Indicates whether to pass through the grid. and Decision variables.

[0033] Preferably, the steps of designing a two-stage algorithm for solving the bi-level programming model for flight plan generation specifically include:

[0034] In the first phase, based on the airport of origin of the flight... The end of the airport is The order of waypoints for flights in the upper-level model is searched based on swarm intelligence algorithms. ;

[0035] In the second phase, based on the scheduled departure time of the flight... In the swarm intelligence algorithm, a greedy algorithm is embedded in the upper-level search model to execute flight operations at the starting airport. actual departure time for ;

[0036] In the second stage, when the upper-level model When determined, the A* algorithm is embedded in the swarm intelligence algorithm to calculate adjacent waypoints. At any moment Best route That is, whether the aircraft performing the flight passes through adjacent grids in sequence. and and through the grid The moment .

[0037] Preferably, the step of evaluating the robustness of the solution specifically includes:

[0038] Determine several adjacent grid sets for generating the aircraft plan. and reaching that arbitrary grid The moment ;

[0039] Setting the time range for safe flight of aircraft For any grid Considering the safe flight time window At any time within Traffic status Calculate the flight plan in any grid. robustness ;

[0040] The robustness of the flight plan is ,in It is a set The number of elements.

[0041] Another objective of this invention is to provide a flight plan generation system for time-varying air traffic environments, used to implement the aforementioned flight plan generation method for time-varying air traffic environments, including:

[0042] The data acquisition module is used to collect data, including the origin and destination points and scheduled times of flights, aircraft performance, waypoint layout and airspace information;

[0043] The feature extraction module is used to extract features of the time-varying environment of air traffic based on spatiotemporal networks;

[0044] The model building module is used to build a two-level planning model for flight plan generation that takes into account the time-varying environment of air traffic.

[0045] The computation module is used to design a two-stage algorithm for solving the bi-level programming model for flight plan generation;

[0046] The evaluation module is used to evaluate the robustness of the solution.

[0047] The flight plan generation method for time-varying air traffic environments provided in this invention integrates big data and artificial intelligence technologies, establishes a two-level programming model for flight plan generation considering time-varying traffic environments and its two-stage solution algorithm, and explores robustness evaluation techniques for flight plans.

[0048] Specifically, this invention considers the spatial layout of waypoints, rasterizes the airspace between adjacent waypoints based on GIS, and takes into account the time-varying air traffic environment such as turbulence, obstacles, and severe convective weather. Based on the origin and destination points and planned departure time of any flight, and while meeting realistic constraints such as the flight performance of the corresponding aircraft, it calculates the order of waypoints the flight passes through and the actual departure time, and determines the flight track of the flight at adjacent waypoints. This provides data support for the refined management of dynamically generating flight plans based on future changes in the air environment. Using this invention, an executable sequence of flight waypoints and its corresponding track can be automatically generated based on the time-varying air traffic environment, providing technical support for dispatchers to conduct intelligent flight plan management in daily operations. Attached Figure Description

[0049] Figure 1 A flowchart illustrating a method for generating flight plans in time-varying air traffic environments, as provided in an embodiment of the present invention.

[0050] Figure 2 This invention provides a two-layer planning flight plan planning model library and a flowchart of the solution process.

[0051] Figure 3 A flowchart for implementing robustness assessment of flight plans provided in this embodiment of the invention;

[0052] Figure 4 A structural block diagram of a flight plan generation system for time-varying air traffic environments provided in an embodiment of the present invention;

[0053] Figure 5 A schematic diagram of a flight plan route provided for an embodiment of the present invention. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0055] The specific implementation of the present invention will be described in detail below with reference to specific embodiments.

[0056] like Figure 1 The diagram shown is a flowchart of a flight plan generation method for time-varying air traffic environments according to an embodiment of the present invention, including the following steps:

[0057] S1. Collect data, including the origin and destination points and scheduled times of flights, aircraft performance, waypoint layout and airspace information;

[0058] S2. Based on spatiotemporal networks, extract the features of the time-varying environment of air traffic;

[0059] S3. Construct a two-level programming model for flight plan generation that considers the time-varying environment of air traffic. The upper-level model calculates the order of waypoints and actual departure time of flights, while the lower-level model searches for the order of waypoints and actual departure time of flights.

[0060] S4. Design a two-stage algorithm to solve the bi-level programming model for generating flight plans;

[0061] S5. Evaluate the robustness of the solution.

[0062] like Figure 2 As shown, this embodiment of the invention provides a two-layer flight planning model based on operations research optimization, integrating big data and artificial intelligence methods, and combining functions such as data preparation, scheme generation and evaluation. It constructs a model under different scenarios, scheduling objectives and constraints, and provides a flowchart of the solution process. The main processes and steps include:

[0063] S1. Collect data, including flight origin and destination points and scheduled times, aircraft performance, waypoint layout and airspace information:

[0064] S11, the departure airport of the flight is The airport ends The planned departure time is ;

[0065] S12, Aircraft performance, including speed range fuel cost per unit mileage and maximum fuel volume ;

[0066] S13, Waypoint layout and its airspace information, including node sets and flight segment collection Each segment The distance is ,in and ;

[0067] S2. Based on spatiotemporal networks, extract features of the time-varying air traffic environment:

[0068] S21. Considering the safe operational performance of the aircraft, each flight segment... airspace information Gridding, in total One grid;

[0069] S22, For any grid and Considering the time-varying air traffic environment at time t, including turbulence, obstacles, severe convective weather, and dynamic control, determine whether passage is prohibited. and ,like , If the '+' indicates passage; otherwise, , , then indicates stillness;

[0070] S23, For any adjacent grid and Determine whether the flight is prohibited from passing at time t. Must meet ,like , then it means passage. and ;

[0071] S3. The process of constructing a two-level programming model for flight planning involves objective functions, constraints, and decision variables. Specifically, the upper-level model calculates the order of waypoints and actual departure times for flights, while the lower-level model searches for the same order of waypoints and actual departure times.

[0072] S31. In the upper-level model, considering realistic constraints such as the spatial distribution of waypoints and aircraft performance, the origin and destination of the flight are determined. and Planned departure time Calculate the order of waypoints and actual departure time of the flight. The objective function is to minimize the total scheduling cost. Pursuing delay deviation and fuel consumption costs Minimum weighting;

[0073] The constraints include:

[0074] Planned departure time and actual departure time The deviation between them does not exceed : ,

[0075] When the aircraft operating the flight passes through adjacent nodes in sequence and hour( ), at time Through nodes Then, at speed Travel time At the moment Through nodes : ,

[0076] The order in which flights pass through waypoints satisfies network flow relationships: ,

[0077] The aircraft operating the flight at the departure airport Departure time for : ,

[0078] Maximum fuel consumption constraints for flights: ;

[0079] in: Represents the set of waypoints. and It's weight. This is the largest deviation between the planned and actual departure time. and Each waypoint and Time, It is the time of departure. Indicates waypoints and The flight path mileage, This indicates fuel consumption per unit distance. This indicates the maximum fuel consumption. Indicates aircraft speed. Indicates whether the route passes through adjacent waypoints. and ;

[0080] In the lower-level model, when the upper-level model's When determined (i.e., when the flight's route through adjacent waypoints is determined), according to calculate Obviously, for the same ,when At the same time, They are also different, dividing each flight segment airspace information Grid-based analysis considers the spatiotemporal distribution of time-varying air traffic environmental factors such as turbulence, obstacles, severe convective weather, and dynamic control at time t, and calculates adjacent waypoints. At any moment Best route The objective function is: The goal is to minimize the time-varying flight path.

[0081] The constraints include:

[0082] Network flow constraints on the trajectory: ,

[0083] When the aircraft performing the flight pass through adjacent grids in sequence and hour( ), at time Through the grid Then, at speed Travel time At the moment Through nodes : ,

[0084] Aircraft operating flights only fly in safe airspace: ,

[0085] Departure time of the aircraft operating the flight from its origin. for : ;

[0086] in: Indicates waypoints and airspace A set of grids, and Different path grids and Time, waypoints Corresponding grid time, Indicates adjacent grids and distance, Indicates adjacent grids and In time The passage status, Indicates whether to pass through the grid. and Decision variables;

[0087] S4. Two-stage algorithm based on swarm intelligence algorithm (e.g., genetic algorithm) to solve the coding design of bi-level programming model;

[0088] S5. Generate the initial population for the swarm intelligence algorithm;

[0089] S6. The next generation of population generation, selection, and evolution in swarm intelligence algorithms:

[0090] S61. In the first phase, based on the airport of origin of the flight... The end of the airport is The order of waypoints for flights in the upper-level model is searched based on swarm intelligence algorithms. ;

[0091] S62. In the second phase, based on the scheduled departure time of the flight... In the swarm intelligence algorithm, a greedy algorithm is embedded in the upper-level search model to execute flight operations at the starting airport. actual departure time for ;

[0092] In the second stage, when the upper-level model When the adjacent waypoints of a flight are determined, the A* algorithm is embedded in the swarm intelligence algorithm to calculate the adjacent waypoints. At any moment Best route That is, whether the aircraft performing the flight passes through adjacent grids in sequence. and ( ), and through the grid The moment ;

[0093] S7, Output Flight Plan.

[0094] like Figure 3 The flowchart shown is an embodiment of the present invention that provides a method for evaluating the robustness of a flight plan solution and determining its feasibility in response to changes in traffic conditions over a certain period of time. The main processes and steps include:

[0095] S1. Set up several adjacent grid sets for the aircraft plan to be evaluated. and reaching that arbitrary grid The moment ;

[0096] S2. Set the time range for safe flight of aircraft. ;

[0097] S3, For any grid Considering the safe flight time window At any time within Traffic status ;

[0098] S4. During the safe flight window Within, calculate the flight plan in any grid. robustness ;

[0099] S5. Taking into account all grids along the flight plan route, assess the overall robustness of the flight plan. ,in It is a set The number of elements.

[0100] like Figure 4 The diagram shown illustrates the structural block diagram of a flight plan generation system for time-varying air traffic environments, provided in an embodiment of the present invention. The system includes:

[0101] The data acquisition module 100 is used to collect data, including the origin and destination points and scheduled times of flights, aircraft performance, waypoint layout and airspace information;

[0102] The feature extraction module 200 is used to extract features of the time-varying environment of air traffic based on the spatiotemporal network.

[0103] Model building module 300 is used to build a two-level planning model for flight plan generation that takes into account the time-varying environment of air traffic.

[0104] Calculation module 400 is used to design a two-stage algorithm for solving the bi-level programming model for flight plan generation;

[0105] Evaluation module 500 is used to evaluate the robustness of the solution.

[0106] Taking a flight departing from airport S and arriving at airport E as an example, its scheduled departure time is 7:00. Figure 5 As shown, the flight plan route calculated using the upper-level model is S-P1-P4-E, with an actual departure time of 7:30 and the times of passing through each waypoint being 7:30-8:00-8:30-9:00 respectively.

[0107] Using the lower-level model, the relevant airspace grids of flight segments S-P1, P1-P4, and P4-E at three times (7:30, 8:00, and 8:30) are solved, and their trajectories S-N1-N2-P1, P1-N3-N4-P4, and P4-N5-N6-E are calculated. Based on this, the flight trajectory of the complete flight S-N1-N2-P1-N3-N4-P4-N5-N6-E is obtained.

[0108] according to =10min interval, as shown in Table 1. According to the solution process described above, calculate the values ​​of S, N1, N2, P1, N3, N4, P4, N5, N6, and E respectively. The values ​​are 0.5, 0.3, 0.6, 0.5, 0.3, 0.6, 0.5, 0.3, 0.6, and 0.6 respectively. Based on this, the robustness of the flight plan is obtained as follows: = (0.5 + 0.3 + 0.6 + 0.5 + 0.3 + 0.6 + 0.5 + 0.3 + 0.6 + 0.6) / 10:

[0109] Table 1

[0110]

[0111] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for generating flight plans in time-varying air traffic environments, characterized in that, Includes the following steps: Collect data, including flight origin and destination points and scheduled times, aircraft performance, waypoint layout and airspace information; Based on spatiotemporal networks, features of the time-varying environment of air traffic are extracted; Construct a two-level programming model for flight plan generation that takes into account the time-varying environment of air traffic; Design a two-stage algorithm to solve the bi-level programming model for flight plan generation; Evaluate the robustness of the solution.

2. The flight plan generation method for time-varying air traffic environments according to claim 1, characterized in that, The steps for collecting data, including flight origin and destination points and scheduled times, aircraft performance, waypoint layouts, and airspace information, specifically include: The departure airport of the flight is The airport ends The planned departure time is ; Aircraft performance, including speed range fuel cost per unit mileage and maximum fuel volume ; Waypoint layout and its airspace information, including node sets and flight segment collection Each segment The distance is ,in and .

3. The flight plan generation method for time-varying air traffic environments according to claim 2, characterized in that, The steps for extracting features of the time-varying air traffic environment based on spatiotemporal networks specifically include: Considering the safe operational performance of the aircraft, each flight segment airspace information Gridding, in total One grid; For any two grids and Considering the time-varying air traffic environment at time t, determine whether it is a prohibited passage state. and ,like , If the '+' indicates passage; otherwise, , , then indicates stillness; For any adjacent grid and Determine whether the flight is prohibited from passing at time t. Must meet ,like , then it means passage. and .

4. The flight plan generation method for time-varying air traffic environments according to claim 3, characterized in that, The steps for constructing a two-level programming model for flight plan generation that considers the time-varying environment of air traffic include: In the upper-level model, considering real-world constraints, the origin and destination of the flight are... and Planned departure time Calculate the order of waypoints and actual departure time of the flight. The objective function is to minimize the total scheduling cost. ; The constraints include: , 、 、 、 ； in: Represents the set of waypoints. and It's weight. This is the largest deviation between the planned and actual departure time. and Each waypoint and Time, It is the time of departure. Indicates waypoints and The flight path mileage, This indicates fuel consumption per unit distance. This indicates the maximum fuel consumption. Indicates aircraft speed. Indicates whether the route passes through adjacent waypoints. and ; In the lower-level model, when the upper-level model's When determined, according to calculate to divide each flight segment airspace information Grid-based approach, considering the spatiotemporal distribution of the time-varying air traffic environment network at time t, to calculate adjacent waypoints. At any moment Best route The objective function is: ; The constraints include: , 、 、 ； in: Indicates waypoints and airspace A set of grids, and Different path grids and Time, waypoints Corresponding grid time, Indicates adjacent grids and distance, Indicates adjacent grids and In time The passage status, Indicates whether to pass through the grid. and Decision variables.

5. The flight plan generation method for time-varying air traffic environments according to claim 4, characterized in that, The steps for designing a two-stage algorithm to solve the bi-level programming model for flight plan generation specifically include: In the first phase, based on the airport of origin of the flight... The end of the airport is The order of waypoints for flights in the upper-level model is searched based on swarm intelligence algorithms. ; In the second phase, based on the scheduled departure time of the flight... In the swarm intelligence algorithm, a greedy algorithm is embedded in the upper-level search model to execute flight operations at the starting airport. actual departure time for ; In the second stage, when the upper-level model When determined, the A* algorithm is embedded in the swarm intelligence algorithm to calculate adjacent waypoints. At any moment Best route That is, whether the aircraft performing the flight passes through adjacent grids in sequence. and and through the grid The moment .

6. The flight plan generation method for time-varying air traffic environments according to claim 5, characterized in that, The steps for evaluating the robustness of a solution include: Determine several adjacent grid sets for generating the aircraft plan. and reaching that arbitrary grid The moment ; Setting the time range for safe flight of aircraft For any grid Considering the safe flight time window At any time within Traffic status Calculate the flight plan in any grid. robustness ; The robustness of the flight plan is ,in It is a set The number of elements.

7. A flight plan generation system for time-varying air traffic environments, used to implement the flight plan generation method for time-varying air traffic environments as described in any one of claims 1-6, characterized in that, include: The data acquisition module is used to collect data, including the origin and destination points and scheduled times of flights, aircraft performance, waypoint layout and airspace information; The feature extraction module is used to extract features of the time-varying environment of air traffic based on spatiotemporal networks; The model building module is used to build a two-level planning model for flight plan generation that takes into account the time-varying environment of air traffic. The computation module is used to design a two-stage algorithm for solving the bi-level programming model for flight plan generation; The evaluation module is used to evaluate the robustness of the solution.

Images