Method and system for optimizing taxiing path of aircraft
By constructing constraints and objective functions to improve the genetic algorithm, the aircraft taxiing path is optimized, solving the problems of long taxiing time and numerous conflicts in the existing technology, and achieving efficient and safe taxiing scheduling.
Patent Information
- Application Number
- CN202511571454.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-30
- Publication Date
- 2026-01-27
AI Technical Summary
Existing technologies lack improvements to genetic algorithms when optimizing aircraft taxiing scheduling. They fail to effectively consider objective taxiing conditions and economic costs, and fail to effectively utilize TTOT time for correction, resulting in long aircraft taxiing times, numerous conflicts, and impacting airport operational efficiency and safety.
The constraint function and objective function are constructed, and the initial solution of the genetic algorithm is improved by combining the aircraft type, wake separation and control rule parameters. The aircraft taxiing path is optimized by optimizing the genetic algorithm model, and the fitness function is used to correct the iteration and select the most suitable taxiing strategy.
It shortens aircraft taxiing time, reduces conflict points and time costs, provides a more scientific and efficient taxiing scheduling strategy, and improves airport operational efficiency and safety.
Smart Images
Figure CN121413435A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of taxiing scheduling technology, and in particular relates to a method and system for optimizing aircraft taxiing paths. Background Technology
[0002] Airport ground operations, as a crucial link in the overall airport system's operation, directly determine the safety and efficiency of airport operations. Many airports are large in scale, with numerous and complex taxiways, resulting in long aircraft taxiing times, heavy workloads for ground service vehicles, and an increased potential for conflicts between aircraft and ground vehicles. These conflicts not only create safety hazards but also consume significant time, manpower, and financial resources to resolve, impacting subsequent aircraft taxiing. Since aircraft taxi along specific routes, conflicts between aircraft and between aircraft and vehicles can be avoided by scientifically and rationally allocating boarding gates and planning aircraft taxiing routes.
[0003] Existing research mainly focuses on the taxiing scheduling problem for aircraft with given arrival / departure times, determining aircraft taxi routes, and directing different aircraft to pass through the same location at different times. Taxiing scheduling models can be classified according to their objectives, including total taxiing time, delay, and energy consumption. Tjahjono et al. (2014) identified conflicts between taxi routes and considered the delay time caused by avoiding conflicts. Benlic et al. (2016) proposed a method to simultaneously determine taxi routes and aircraft arrival and departure sequences on the runway. With the global trend towards green airports, airport energy conservation and emission reduction goals are receiving increasing attention.
[0004] Based on the above analysis, the existing technologies have the following problems that need to be addressed: Current research largely focuses on optimizing the total taxiing time, delays, and energy consumption of aircraft and ground support vehicles, with limited research considering objective taxiing conditions and economic costs to optimize taxiing scheduling for all aircraft. Furthermore, the application of genetic algorithms is limited to the initial parameter input stage, without targeted improvements to the algorithm itself, and lacks the utilization of time-to-over-time (TTOT) adjustments to adapt to the iterative processes of the genetic algorithm and achieve optimal aircraft taxiing scheduling allocation.
[0005] Therefore, how to consider the selection of subjective and objective constraints to construct the constraint function, and how to consider objective taxiing data and economic costs to construct the objective function for subsequent genetic algorithm improvement to obtain a model more suitable for aircraft taxiing scheduling and allocation, and how to perform relatively simple relation calculations to correct model iterations, are important problems faced in this field. To this end, an optimization method and system for aircraft taxiing paths is proposed. Summary of the Invention
[0006] To address the aforementioned technical problems, this invention proposes a method and system for optimizing aircraft taxiing paths.
[0007] In a first aspect of the invention, a method for optimizing an aircraft taxiing path is provided, the method comprising: Obtain the aircraft type parameters, wake separation parameters, and air traffic control rule parameters of the first taxiing aircraft to construct a constraint function; The objective function is to obtain the average taxiing time and average combined fuel consumption cost of the second taxiing aircraft. The takeoff parameters, handover point parameters, TTOT time of the first taxiing aircraft, and parking position characteristics of the second taxiing aircraft are input into the genetic algorithm. The genetic algorithm is iterated, and after the iteration is completed, the runway scheduling results of the first and second taxiing aircraft are output to the control console to optimize the taxiing path of the aircraft.
[0008] Furthermore, the runway scheduling result includes the first initial taxiing time feature vector and the first runway threshold feature vector of the first taxiing aircraft, and also includes the second initial taxiing time feature vector and the second runway threshold feature vector of the second taxiing aircraft.
[0009] Furthermore, the initial solution input to the genetic algorithm is obtained by improving it using a rule-based algorithm.
[0010] Furthermore, the initial solution input to the genetic algorithm also includes the TTOT time of the first taxiing aircraft, which is determined by the expiry date closeness factor, the expiry date range factor, and the setting time severity factor.
[0011] Furthermore, the forward-looking parameter is calculated using the due date range factor, and the scaling parameter is calculated using the due date tightness factor and the setting time severity factor.
[0012] Furthermore, the fitness function of the genetic algorithm is constructed using the constraint function and the objective function.
[0013] Furthermore, the constraint function is constructed from the aircraft type parameters, wake separation parameters, and control rule parameters of the first taxiing aircraft.
[0014] Furthermore, the objective function of the second taxiing aircraft is obtained by multiplying the average taxiing time and the average combined cost of fuel consumption. In this invention, both parameters are better the smaller they are for the taxiing aircraft. Therefore, in order to calculate the value of the fitness function in the subsequent calculation, a simple positive linear calculation is used to obtain it.
[0015] A system for optimizing aircraft taxiing paths is also provided, comprising an airport aircraft data acquisition module, a taxiway topology model construction module, an initial solution improvement calculation module, a taxiway optimal runway scheduling genetic algorithm module, and a taxiway terminal control module, characterized in that: The airport aircraft data acquisition module acquires the takeoff parameters, handover point parameters, TTOT time of the first taxiing aircraft, and parking position characteristics of the second taxiing aircraft. It also acquires the aircraft type parameters, wake separation parameters, and air traffic control rule parameters of the first taxiing aircraft. Furthermore, it acquires the average taxiing time and average combined fuel consumption cost of the second taxiing aircraft. The taxiway topology model construction module: obtains the aircraft type parameters, wake separation parameters, and control rule parameters of the first taxiing aircraft to construct constraint function; Obtain the objective function for the average taxiing time and average combined cost of fuel consumption of the second taxiing aircraft; The initial solution improvement calculation module: uses a rule-based algorithm to improve the initial solution of the input genetic algorithm; The optimal runway scheduling genetic algorithm module for taxiways: constructs the fitness function of the genetic algorithm using the constraint function and the objective function, and terminates the iteration of the genetic algorithm based on the fitness function; The taxiway terminal control module outputs the runway scheduling results of the first and second taxiways after iteration to the console to optimize the taxiway paths of the aircraft.
[0016] This invention considers the selection of objective parameters such as specific aircraft parameters and subjective constraints such as control rules to construct a constraint function. It then considers objective taxiing data and economic costs to form an objective function for subsequent genetic algorithm improvements, resulting in a model more suitable for aircraft taxiing scheduling. Furthermore, it improves the initial solution of the genetic algorithm using a rule-based algorithm to accelerate its iterative improvement in aircraft taxiing scheduling. It also utilizes influence to construct a fitness function model, and the calculation of the conventional fitness function in this genetic algorithm corrects the model iteration. By optimizing the genetic algorithm model for computation and solving, it selects the most suitable constraint conditions to shorten the time cost incurred during taxiing. It calculates the variable taxiing time for aircraft under different parking positions and external conditions, feeding back into the apron operation management system and providing apron control departments with a more scientific and efficient aircraft taxiing scheduling strategy.
[0017] Further embodiments and improvements of the present invention will be described in conjunction with the accompanying drawings and specific examples. Attached Figure Description
[0018] Figure 1This is a flowchart of an aircraft taxiing path optimization method according to the present invention; Figure 2 This is a schematic diagram of an aircraft taxiing path optimization system according to the present invention; Figure 3 This is a schematic diagram of the port entry datum in this invention; Figure 4 These are schematic diagrams before and after optimization of the improved genetic algorithm in this invention; Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation
[0019] The invention will now be further described in conjunction with the accompanying drawings and specific embodiments.
[0020] In a first aspect of the invention, a method for optimizing an aircraft taxiing path is provided, the method comprising: Obtain the aircraft type parameters, wake separation parameters, and air traffic control rule parameters of the first taxiing aircraft to construct a constraint function; The objective function is to obtain the average taxiing time and average combined fuel consumption cost of the second taxiing aircraft. The takeoff parameters, handover point parameters, TTOT time of the first taxiing aircraft, and parking position characteristics of the second taxiing aircraft are input into the genetic algorithm. The genetic algorithm is iterated, and after the iteration is completed, the runway scheduling results of the first and second taxiing aircraft are output to the control console to optimize the taxiing path of the aircraft.
[0021] Furthermore, the runway scheduling result includes the first initial taxiing time feature vector and the first runway threshold feature vector of the first taxiing aircraft, and also includes the second initial taxiing time feature vector and the second runway threshold feature vector of the second taxiing aircraft.
[0022] Furthermore, the initial solution input to the genetic algorithm is obtained by improving it using a rule-based algorithm, the formula of which is as follows:
[0023] In the formula, This represents the priority index of the first taxiing aircraft with task number j completing the task at the current time t. The weight representing job number j is determined and set by those skilled in the art. The processing time for task number j refers to the ground taxiing time of the first taxiing aircraft for task number j. In Take the maximum value between 0 and 0. The takeoff time of the first taxiing aircraft with operation sequence number j. Forward parameters, These scaling parameters are used for dynamic adjustment of the initial glide solution and are settings determined by those skilled in the art. For average scheduling processing time, To set the adjustment time for the average, The setting time of the first taxiing aircraft with job sequence number j is the index l immediately following the most recently completed job. In this invention, the higher the priority index, the greater the importance of the job sequence number. By sorting the priority indices of each job from largest to smallest, the job priorities can be sorted from high to low, thereby prioritizing the taxiing of the first taxiing aircraft based on its starting job sequence number.
[0024] Rule-based algorithms can be used to improve the initial solution of genetic algorithms, thereby accelerating the iterative improvement of aircraft taxiing scheduling. In this embodiment, the initial solution, namely the initial taxiing operation sequence number and taxiway of the aircraft, is selected as the optimal initial solution. This can reduce the number of iterations required by the genetic algorithm, reduce model consumption, and enable the model to obtain aircraft taxiing strategies more efficiently.
[0025] Furthermore, the initial solution input to the genetic algorithm also includes the TTOT time of the first taxiing aircraft, wherein the TTOT time is determined by the expiration date closeness factor, the expiration date range factor, and the setting time severity factor.
[0026] In the formula, The due date urgency factor is an indicator used to quantify the urgency of a target object's due date and current time. R is the due date range factor, which is a quantitative indicator that classifies urgency levels based on the number of days remaining before the due date. It is used to dynamically adjust task priorities or resource allocation strategies. The time severity factor provides an adaptive decision-making basis for complex systems by quantifying the dynamic relationship between time and task attributes.
[0027] Furthermore, the maturity date tightness factor is:
[0028] The expiration date range factor is:
[0029] The time severity factor is set as follows:
[0030] In the formula, For the tightness factor of the due date, The average cutoff date for aircraft. This represents the total number of assignments by sequence number. For average scheduling processing time, To set the adjustment time for the average, The time correlation coefficient is the coefficient of variation, which changes with n, and ≤1, For the range of due dates, The maximum operation deadline, in this scheme, refers to the latest takeoff time of the second taxiing aircraft. The minimum operation deadline, in this scheme, refers to the earliest takeoff time of the second taxiing aircraft. Set the time severity factor.
[0031] Furthermore, the forward-looking parameter is calculated using the maturity date range factor:
[0032] The scaling parameters are calculated using the due date tightness factor and the setting time severity factor:
[0033] In the formula, Let R be the forward-looking parameter, and R be the maturity date range factor. The scaling parameter, For the tightness factor of the due date, Set the time severity factor.
[0034] Furthermore, the fitness function of the genetic algorithm is constructed using the constraint function and the objective function:
[0035] In the formula, the fitness function for the target is... To eliminate dimensional differences, in the formula To construct a constraint function based on the aircraft type parameters, wake separation parameters, and air traffic control rule parameters of the first taxiing aircraft, The objective function is the average taxiing time and average combined cost of fuel consumption for the second taxiing aircraft. When the fitness function value reaches a certain threshold, the starting taxiing time and selected runway gate of the first taxiing aircraft, as well as the starting taxiing time and selected runway gate of the second taxiing aircraft, are output.
[0036] Furthermore, the constraint function is constructed from the aircraft type parameters, wake separation parameters, and control rule parameters of the first taxiing aircraft, using the following formula:
[0037] In the formula, The constraint function is... For the aircraft type parameters of the first taxiing aircraft, this invention specifically considers only the weight parameter of the taxiing aircraft, therefore Specifically, for aircraft weight, since the weight parameter is on a much larger scale than other parameters, a logarithmic function is used to reduce the value to obtain a more suitable constraint function for fitness function calculation.
[0038] For example, aircraft weight is measured in tons, while airplanes generally weigh over 40 tons. If the calculation here uses kilograms, the data volume can reach 40,000 kilograms. The wake separation parameter for taxiing aircraft is generally around 10 km, and the taxiing speed limit in the control rules is also on this order of magnitude. The aircraft weight parameter mentioned above is three orders of magnitude different from the latter two parameters.
[0039] The wake separation parameter for the first taxiing aircraft is the minimum safe distance that aircraft must maintain during flight. Its purpose is to prevent following aircraft from entering the wake turbulence zone generated by the preceding aircraft, thus preventing dangers such as loss of flight attitude and engine failure. It is generally taken as a value of 11 km or higher. Dimension elimination processing is performed, and the control rule parameter in this invention is the coasting speed limit, generally taken as below 15 km / h. This is also utilized here. Perform dimensionless processing.
[0040] Furthermore, the objective function of the second taxiing aircraft is obtained by multiplying the average taxiing time and the average combined cost of fuel consumption. In this invention, both parameters are better the smaller they are for the taxiing aircraft. Therefore, in order to calculate the value of the fitness function in the subsequent calculation, a simple positive linear calculation is used to obtain it.
[0041] A system for optimizing aircraft taxiing paths is also provided, comprising an airport aircraft data acquisition module, a taxiway topology model construction module, an initial solution improvement calculation module, a taxiway optimal runway scheduling genetic algorithm module, and a taxiway terminal control module, characterized in that: The airport aircraft data acquisition module acquires the takeoff parameters, handover point parameters, TTOT time of the first taxiing aircraft, and parking position characteristics of the second taxiing aircraft. It also acquires the aircraft type parameters, wake separation parameters, and air traffic control rule parameters of the first taxiing aircraft. Furthermore, it acquires the average taxiing time and average combined fuel consumption cost of the second taxiing aircraft. The taxiway topology model construction module: obtains the aircraft type parameters, wake separation parameters, and control rule parameters of the first taxiing aircraft to construct constraint function; Obtain the objective function for the average taxiing time and average combined cost of fuel consumption of the second taxiing aircraft; The initial solution improvement calculation module: uses a rule-based algorithm to improve the initial solution of the input genetic algorithm; The optimal runway scheduling genetic algorithm module for taxiways: constructs the fitness function of the genetic algorithm using the constraint function and the objective function, and terminates the iteration of the genetic algorithm based on the fitness function; The taxiway terminal control module outputs the runway scheduling results of the first and second taxiways after iteration to the console to optimize the taxiway paths of the aircraft.
[0042] Based on the improvements made to the genetic algorithm in this embodiment, based on Figure 4 It can be seen that the conflict point index decreased from 0.296 to 0.222, a decrease of 25%; the taxiing + queuing time decreased from 37.477 to 30.486, a decrease of 18.65%.
[0043] This invention considers the selection of objective parameters such as specific aircraft parameters and subjective constraints such as control rules to construct a constraint function. It then considers objective taxiing data and economic costs to form an objective function for subsequent genetic algorithm improvements, resulting in a model more suitable for aircraft taxiing scheduling. Furthermore, it improves the initial solution of the genetic algorithm using a rule-based algorithm to accelerate its iterative improvement in aircraft taxiing scheduling. It also utilizes influence to construct a fitness function model, and the calculation of the conventional fitness function in this genetic algorithm corrects the model iteration. By optimizing the genetic algorithm model for computation and solving, it selects the most suitable constraint conditions to shorten the time cost incurred during taxiing. It calculates the variable taxiing time for aircraft under different parking positions and external conditions, feeding back into the apron operation management system and providing apron control departments with a more scientific and efficient aircraft taxiing scheduling strategy.
[0044] Of course, it is understood that each embodiment of the present invention can achieve one of the effects on its own, and the combination of multiple embodiments of the present invention can achieve all the above effects. However, it is not required that each embodiment of the present invention achieve all the above advantages and effects, because each embodiment of the present invention can constitute a separate technical solution and make one or more contributions to the prior art.
[0045] For any module structures not specifically defined in this invention, the existing technical specifications shall prevail. The existing technical specifications mentioned in the foregoing background and specific embodiments sections are considered part of this invention and are used to understand the meaning of certain technical features or parameters. The scope of protection of this invention is determined by the actual contents of the claims.
Claims
1. A method for optimizing an aircraft taxiing path, characterized in that, The method includes: Obtain the aircraft type parameters, wake separation parameters, and air traffic control rule parameters of the first taxiing aircraft to construct a constraint function; The objective function is to obtain the average taxiing time and average combined fuel consumption cost of the second taxiing aircraft. The takeoff parameters, handover point parameters, TTOT time of the first taxiing aircraft, and parking position characteristics of the second taxiing aircraft are input into the genetic algorithm. The genetic algorithm is iterated, and after the iteration is completed, the runway scheduling results of the first and second taxiing aircraft are output to the control console to optimize the taxiing path of the aircraft.
2. The method for optimizing an aircraft taxiing path as described in claim 1, characterized in that: The runway scheduling result includes the first initial taxiing time feature vector and the first runway threshold feature vector of the first taxiing aircraft, and also includes the second initial taxiing time feature vector and the second runway threshold feature vector of the second taxiing aircraft.
3. The method for optimizing an aircraft taxiing path as described in claim 1, characterized in that: The initial solution of the genetic algorithm is obtained by improving it using a rule-based algorithm.
4. The method for optimizing an aircraft taxiing path as described in claim 3, characterized in that: The initial solution input to the genetic algorithm also includes the TTOT time of the first taxiing aircraft, which is determined by the expiry date closeness factor, the expiry date range factor, and the setting time severity factor.
5. The method for optimizing an aircraft taxiing path as described in claim 4, characterized in that: The forward-looking parameter is calculated using the due date range factor, and the scaling parameter is calculated using the due date tightness factor and the setting time severity factor.
6. The method for optimizing an aircraft taxiing path as described in claim 1, characterized in that: The fitness function of the genetic algorithm is constructed using the constraint function and the objective function.
7. The method for optimizing an aircraft taxiing path as described in claim 6, characterized in that: The constraint function is constructed from the aircraft type parameters, wake separation parameters, and control rule parameters of the first taxiing aircraft.
8. The method for optimizing an aircraft taxiing path as described in claim 7, characterized in that: The objective function of the second taxiing aircraft is obtained by multiplying the average taxiing time and the average combined cost of fuel consumption.
9. An optimization system for aircraft taxiing paths, comprising an airport aircraft data acquisition module, a taxiway topology model construction module, an initial solution improvement calculation module, a taxiway optimal runway scheduling genetic algorithm module, and a taxiway terminal control module, characterized in that: The airport aircraft data acquisition module acquires the takeoff parameters, handover point parameters, TTOT time of the first taxiing aircraft and the parking position characteristics of the second taxiing aircraft, as well as the aircraft type parameters, wake separation parameters and control rule parameters of the first taxiing aircraft. It is also used to acquire the average taxiing time and average combined fuel consumption cost of the second taxiing aircraft. The taxiway topology model construction module: obtains the aircraft type parameters, wake separation parameters, and control rule parameters of the first taxiing aircraft to construct constraint function; Obtain the objective function for the average taxiing time and average combined cost of fuel consumption of the second taxiing aircraft; The initial solution improvement calculation module: uses a rule-based algorithm to improve the initial solution of the input genetic algorithm; The optimal runway scheduling genetic algorithm module for taxiways: constructs the fitness function of the genetic algorithm using the constraint function and the objective function, and terminates the iteration of the genetic algorithm based on the fitness function; The taxiway terminal control module outputs the runway scheduling results of the first and second taxiways after iteration to the console to optimize the taxiway paths of the aircraft.