NSGA-based flight ordering method, system, device, product and medium

Abstract

The invention relates to the technical field of aviation safety, and provides an NSGA-based flight ordering method, system, device, product and medium, and the method comprises the steps: obtaining the flight information of to-be-parked aircrafts, carrying out the random ordering of the to-be-parked aircrafts, and obtaining an initial population; calculating adaptive parameters so as to formulate optimization constraint conditions; under the constraint of an optimization constraint condition, performing multi-target optimization sorting on the initial population according to adaptive parameters, calculating the congestion degree of an approach sequence, performing elimination to obtain a first intermediate population, performing genetic algorithm screening to obtain a second intermediate population, and performing crossover variation to obtain a third intermediate population to obtain a target population; calculating a parking position selection parameter and a shortest taxiing path of the aircraft to be landed, thereby calculating a taxiway adaptability parameter; and calculating iteration adaptability parameters of the target population, and performing genetic algorithm iteration on the target population to obtain a target approach sequence. According to the invention, the scheduling efficiency of flight landing is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of aviation safety technology, and in particular to a flight sorting method, system, equipment, product and medium based on NSGA. Background Art

[0002] With the rapid development of the global air transport industry, air traffic has increased significantly, and airports are facing increasingly severe management pressure and operational challenges. Aircraft approach sorting, as a key link in air traffic management, directly affects the airport's operating efficiency and the on-time arrival rate of aircraft. Although the traditional FCFS (first come first serve) sorting method is simple and easy to implement, it fails to fully consider the diversity of aircraft and the complex operating environment, resulting in problems such as low aircraft approach efficiency, increased delay time, and increased fuel consumption. With the continuous increase in airport throughput, there is an urgent need for a more intelligent and efficient approach sorting method to improve the overall efficiency of air traffic management, reduce operating costs, and improve passenger satisfaction.

[0003] At present, the sorting of incoming flights is mainly done by controllers based on experience according to the flight plans and dynamic information of the flights. When the incoming flight traffic is large, this method makes the workload of the controllers heavy and easily causes a large number of flight delays. Therefore, in order to obtain a more scientific and reasonable sorting scheme for incoming flights, it is necessary to introduce an algorithm to calculate the order of flight arrival. In the problem of aircraft approach sorting, multiple optimization objectives need to be considered comprehensively, such as minimizing the number of delayed flights, minimizing average fuel consumption, and minimizing average delay time. Traditional algorithms often find it difficult to take all of these multi-objective problems into account. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the related art. To this end, the present invention provides a flight sequencing method, system, device, product and medium based on NSGA to achieve aircraft approach and taxiing.

[0005] The present invention provides a flight sorting method based on NSGA, comprising: S1: Acquire flight information of aircraft waiting to land, and randomly sort the aircraft waiting to land to obtain an initial population including multiple approach sequences; S2: obtaining safety restriction parameters, calculating adaptability parameters according to the flight information, and formulating optimization constraint conditions according to the flight information and the safety restriction parameters; S3: Under the constraints of the optimization constraints, the initial population is sorted by multi-objective optimization according to the adaptability parameters, and the congestion degree of the approach sequence is calculated, and the approach sequence in the initial population is eliminated according to the congestion degree to obtain a first intermediate population; S4: performing genetic algorithm screening on the first intermediate population to obtain a second intermediate population, performing crossover mutation on the second intermediate population to obtain a third intermediate population, and obtaining a target population through the third intermediate population; S5: Calculating the parking stand selection parameters and the shortest taxiing path of the aircraft waiting to land according to the target population, and obtaining taxiway adaptability parameters through the parking stand selection parameters and the shortest taxiing path; S6: calculating an iterative adaptability parameter of the target population, performing genetic algorithm iteration on the target population according to the iterative adaptability parameter and the taxiway adaptability parameter to obtain a target solution set, and selecting a target approach sequence from the target solution set.

[0006] According to the flight sorting method based on NSGA provided by the present invention, step S2 further includes: S21: Acquire the approach conditions of the airport, obtain the safety limit parameters according to the approach conditions, and obtain the adaptability parameters of each approach sequence according to the flight information, wherein the adaptability parameters include the number of delayed flights, average fuel consumption, and average delay time; S22: Formulate the optimization constraint conditions according to the flight information and the safety limit parameters, wherein the optimization constraint conditions include wake turbulence interval constraint, maximum allowable position exchange constraint and landing edge capacity constraint.

[0007] According to the flight sorting method based on NSGA provided by the present invention, step S3 further includes: S31: screening the approach sequences in the initial population according to the optimization constraint conditions, and performing multi-objective optimization sorting on the approach sequences in the initial population according to the adaptability parameters; S32: Calculating a fitness value according to the adaptability parameter, calculating the congestion of the approach sequence according to the fitness value, and eliminating the approach sequences in the initial population according to the congestion to obtain a first intermediate population.

[0008] According to the flight sorting method based on NSGA provided by the present invention, step S4 further includes: S41: performing genetic algorithm screening on the first intermediate population by a tournament selection method to obtain a second intermediate population; S42: performing crossover on the second intermediate population by simulating a binary crossover method to obtain a progeny population, and performing mutation on the progeny population by a polynomial mutation method to obtain a third intermediate population; S43: merging the third intermediate population with the first intermediate population to obtain a temporary population, performing multi-objective optimization sorting on the temporary population and calculating the congestion degree to obtain a target population.

[0009] According to the flight sorting method based on NSGA provided by the present invention, step S5 further includes: S51: obtaining the taxiway route and parking stand distribution of the airport, formulating taxiway optimization constraint conditions according to the taxiway route and the parking stand distribution, and calculating the shortest taxiway path according to the taxiway optimization constraint conditions, the taxiway route, the target population and the parking stand distribution; S52: Calculating the parking stand selection parameter according to the parking stand distribution and the shortest taxiing path; calculating the average taxiing time through the shortest taxiing path, and using the parking stand selection parameter and the average taxiing time as the taxiway adaptability parameter.

[0010] According to the flight sorting method based on NSGA provided by the present invention, in step S1, priority aircraft waiting to land are determined according to the flight information, and the demand for the priority aircraft waiting to land is determined, and the aircraft waiting to land are randomly sorted according to the demand for the priority aircraft waiting to land.

[0011] The present invention also provides a flight sorting system based on NSGA, comprising: Initial population module: used to obtain flight information of aircraft waiting to land, randomly sort the aircraft waiting to land, and obtain an initial population including multiple approach sequences; Constraint condition module: used for obtaining safety restriction parameters, calculating adaptability parameters according to the flight information, and formulating optimization constraint conditions according to the flight information and the safety restriction parameters; A first intermediate population module: used for performing multi-objective optimization sorting on the initial population according to the adaptability parameters under the constraints of the optimization constraints, calculating the congestion degree of the approach sequence, and eliminating the approach sequence in the initial population according to the congestion degree to obtain a first intermediate population; Target population module: used for performing genetic algorithm screening on the first intermediate population to obtain a second intermediate population, performing crossover mutation on the second intermediate population to obtain a third intermediate population, and obtaining a target population through the third intermediate population; A taxiway planning module: used to calculate the parking position selection parameters and the shortest taxiing path of the aircraft to be landed according to the target population, and obtain the taxiway adaptability parameters through the parking position selection parameters and the shortest taxiing path; Target approach sequence module: used to calculate the iterative adaptability parameters of the target population, perform genetic algorithm iteration on the target population through the iterative adaptability parameters and the taxiway adaptability parameters to obtain a target solution set, and select a target approach sequence from the target solution set.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of any of the above-mentioned flight sorting methods based on NSGA are implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned flight sorting methods based on NSGA are implemented.

[0014] The present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can perform the steps of any of the above-mentioned NSGA-based flight sorting methods.

[0015] The above one or more technical solutions in the embodiments of the present invention have at least one of the following technical effects: The flight sorting method, system, equipment, product and medium based on NSGA provided by the present invention perform multi-objective optimization on the approach sequence of flights and the allocation of taxiways and parking stands through genetic algorithms, and adopt tournament selection, crossover and mutation operations to enhance the diversity and adaptability of the population and avoid premature convergence. The present invention fully considers the actual operational constraints such as aircraft wake intervals, maximum allowable position exchanges and sorting edge capacity restrictions to ensure the feasibility and safety of the scheme. By optimizing the approach sorting, aircraft delays and fuel consumption are reduced, and for large airports with more complex taxiway and parking stand layouts, reasonable taxiways and parking stands can be allocated to aircraft, thereby reducing operating costs, improving economic benefits and operational safety. It is suitable for airports of different sizes and complex air traffic conditions, and has broad application prospects.

[0016] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of the flight sorting method based on NSGA provided by the present invention.

[0019] Figure 2 It is a structural schematic diagram of the flight sorting system based on NSGA provided by the present invention.

[0020] Figure 3 It is a structural schematic diagram of a flight sorting device based on NSGA provided by the present invention.

[0021] Reference numerals: 100, initial population module; 200, constraint condition module; 300, first intermediate population module; 400, target population module; 500, taxiway planning module; 600, target approach sequence module; 810, processor; 820, communication interface; 830, memory; 840, communication bus. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme in the present invention will be clearly and completely described below. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present invention. The following embodiments are used to illustrate the present invention, but cannot be used to limit the scope of the present invention.

[0023] In the description of the embodiments of the present invention, it should be noted that the terms “first”, “second” and “third” are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0024] In the description of the embodiments of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances.

[0025] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0026] Combine the following Figures 1 to 3 Describing embodiments of the present invention: Figure 1 The figure is a flowchart of the flight sorting method based on NSGA. Among them, S1 is to obtain the flight information of the aircraft waiting to land and sort them randomly to obtain the initial population; S2 is to calculate the adaptability parameters and formulate the constraint optimization conditions; S3 is to perform multi-objective optimization sorting, calculate the congestion, and eliminate the initial population to obtain the first intermediate population; S4 is to screen the first intermediate population with genetic algorithm, and then obtain the target population through crossover mutation; S5 is to calculate the parking position selection parameters and the shortest taxiing path, and finally obtain the taxiway adaptability parameters; S6 is to iterate the target population and finally obtain the target approach sequence.

[0027] The flight sorting method based on NSGA provided by the present invention comprises: S1: Acquire flight information of aircraft waiting to land, and randomly sort the aircraft waiting to land to obtain an initial population including multiple approach sequences; Furthermore, the purpose of this stage is to obtain flight information including call signs, aircraft models, flight parameters and other data of the aircraft waiting to land, and to randomly sort the aircraft waiting to land, so as to generate an initial population including multiple approach sequences for the genetic algorithm. In step S1, the priority aircraft waiting to land is determined according to the flight information, and the demand for the priority aircraft waiting to land is determined, and the aircraft waiting to land is randomly sorted according to the demand for the priority aircraft waiting to land. The specific implementation method is as follows: In this embodiment, it is considered that the aircraft waiting to land can enter the landing procedure on time, there are no other circumstances that affect its entry into the landing procedure, and the good weather near the airport will not affect the normal landing. The aircraft waiting to land will not encounter any sudden situation on the runway that affects the landing of subsequent aircraft waiting to land, and the landing process of the aircraft waiting to land is regarded as uniform motion.

[0028] First, the aircraft waiting to land at the airport will send a request to the airport's air traffic control system. At this time, the transponder will automatically send its own status and call sign to the air traffic control system. The pilot and data transmitter of the aircraft waiting to land will also report their flight status to the air traffic control system. Therefore, we can determine the flight information of the aircraft waiting to land based on the pilot's report and the data sent by the transponder and data transmitter. Then, the call sign of each aircraft waiting to land is used as the name of each aircraft waiting to land and these aircraft waiting to land are randomly sorted to obtain an initial population including multiple approach sequences.

[0029] In addition, when flight information shows that an aircraft on standby has encountered some situations that require priority landing, such as an emergency patient or an organ waiting for transplantation, insufficient fuel, or a 7700 code indicating an emergency due to a malfunction, the aircraft on standby will be designated as a priority aircraft on standby, and the specific situation and needs of the priority aircraft on standby will be determined, so as to ensure that the priority aircraft on standby is in the front position in each approach sequence during the random sorting process. The specific way to be in the front position, such as always being in the first position of the approach sequence, always being in the first three positions of the approach sequence, etc., will be determined according to the specific situation and needs of the priority aircraft on standby.

[0030] S2: obtaining safety restriction parameters, calculating adaptability parameters according to the flight information, and formulating optimization constraint conditions according to the flight information and the safety restriction parameters; Furthermore, the purpose of this stage is to determine the safety limit parameters according to the conditions of the airport, calculate the adaptability parameters of the aircraft waiting to land according to the flight information, and determine the optimization constraints according to the safety limit parameters and the flight information, so as to provide constraints for the subsequent genetic algorithm optimization process and ensure that the optimization results are in line with reality. Specifically, step S2 further includes: S21: Acquire the approach conditions of the airport, obtain the safety limit parameters according to the approach conditions, and obtain the adaptability parameters of each approach sequence according to the flight information, wherein the adaptability parameters include the number of delayed flights, average fuel consumption, and average delay time; S22: Formulate the optimization constraint conditions according to the flight information and the safety limit parameters, wherein the optimization constraint conditions include wake turbulence interval constraint, maximum allowable position exchange constraint and landing edge capacity constraint.

[0031] With respect to the above steps, the specific implementation methods in this embodiment are as follows: First, the airport's approach conditions, that is, the airport's landing conditions, are determined based on the airport's surrounding terrain, the airport's weather on the day, the airport's environment and equipment. Then, the airport's safety restriction parameters can be determined based on the approach conditions, such as the maximum number of aircraft waiting to land that are allowed to exist simultaneously on the approach side during fifth leg flight, and the maximum number of times the air traffic control system allows the order of aircraft waiting to land to be swapped in the approach sequence.

[0032] Then, the adaptability parameters of each approach sequence are obtained based on the flight information, which is the target of multi-objective optimization in the subsequent genetic algorithm. The adaptability parameters include the number of delayed flights , average fuel consumption and average delay time , the calculation method of delayed flights is as follows: Where n is the total number of aircraft waiting to land, For the The time the aircraft waiting to land is delayed relative to the scheduled landing time. is the delay threshold. When the delay time relative to the scheduled landing time is greater than the delay threshold, the flight is considered to be delayed. () is the indicator function, that is, when the formula in the brackets is true, the indicator function takes the value of 1, otherwise it is 0.

[0033] The average fuel consumption is calculated as follows: in, Indicates The fuel consumption rate of the aircraft waiting to land during the cruise phase, Indicates The fuel consumption rate of the aircraft waiting to land during the descent phase, Indicates The fuel consumption rate of the aircraft waiting to land during the landing phase, Indicates The time that an aircraft waiting to land is in the cruising phase, Indicates The time that an aircraft waiting to land is in the descent phase, Indicates The fuel consumption rate can be determined based on the aircraft type in the flight information. In different approach sequences, the time occupied by the descent and landing phases of each aircraft waiting to land is relatively fixed. The main change is the cruising time, which can also be determined based on the aircraft type and the position of the aircraft waiting to land in the approach sequence.

[0034] The average delay time is calculated as follows: in, For the The actual landing time of the aircraft waiting to land, For the The scheduled landing time of the aircraft waiting to land, max () is the maximum value among the values ​​in brackets.

[0035] Then, the optimization constraints are formulated according to the flight information and safety limit parameters. The optimization constraints include wake turbulence interval constraint, maximum allowable position exchange constraint and landing edge capacity constraint. The wake turbulence interval constraint is: in, For the Frame, that is, The actual landing time of the waiting aircraft that landed after the waiting aircraft landed. Indicates The first aircraft to land and the The minimum landing time interval between two waiting aircraft. In this embodiment, the minimum landing time interval is determined based on the minimum safety interval specified by ICAO and the model of the waiting aircraft included in the flight information. In addition, the distance between the two waiting aircraft must be greater than the minimum safety interval to avoid the tail vortex of the previous waiting aircraft from affecting the safety of the next waiting aircraft. The specific minimum landing time interval and minimum safety interval are shown in Table 1: Table 1 Schematic diagram of the minimum landing time interval and minimum safety interval for aircraft waiting to land

[0036] When formulating the maximum allowable position exchange constraint, first generate a reference approach sequence according to the traditional first-come-first-served method, then calculate the change in the order of the waiting aircraft in each approach sequence relative to the position of the waiting aircraft in the reference approach sequence, and ensure that the position of the waiting aircraft in each approach sequence relative to the reference approach sequence will not change too much through constraints, so as to reduce the control difficulty of the air traffic control system. The maximum allowable position exchange constraint is as follows: in, For the The order of the aircraft waiting to land in the arrival sequence, For the The order of the aircraft waiting to land in the reference approach sequence, is the maximum allowed position exchange threshold determined according to the safety limit parameters.

[0037] The landing side capacity limit is the number of aircraft waiting to land that are allowed to exist simultaneously in the landing path of the airport in a time period determined according to the safety limitation parameters. The landing side capacity limit is as follows: Where m is the number of aircraft waiting to land that enter the airport airspace in a time period. Indicates the first aircraft waiting to land that enters the airport airspace. The actual landing time of the aircraft waiting to land, Indicates the start time of the time period. Indicates the end time of the time period. Indicates the number of waiting aircraft that are allowed to be on the landing path of the airport at the same time during the time period.

[0038] S3: Under the constraints of the optimization constraints, the initial population is sorted by multi-objective optimization according to the adaptability parameters, and the congestion degree of the approach sequence is calculated, and the approach sequence in the initial population is eliminated according to the congestion degree to obtain a first intermediate population; Furthermore, the purpose of this stage is to perform multi-objective optimization sorting on the initial population and calculate the congestion of each entry sequence, so as to ensure the diversity of the population in the subsequent genetic algorithm by eliminating sequences with lower congestion. Specifically, step S3 further includes: S31: screening the approach sequences in the initial population according to the optimization constraint conditions, and performing multi-objective optimization sorting on the approach sequences in the initial population according to the adaptability parameters; S32: Calculating a fitness value according to the adaptability parameter, calculating the congestion of the approach sequence according to the fitness value, and eliminating the approach sequences in the initial population according to the congestion to obtain a first intermediate population.

[0039] With respect to the above steps, the specific implementation methods in this embodiment are as follows: First, the approach sequences in the initial population are screened according to the optimization constraints to eliminate the approach sequences that do not meet the optimization constraints, and then the approach sequences are sorted by multi-objective optimization according to the adaptability parameters, that is, the optimization objectives of the genetic algorithm. Multi-objective optimization sorting is to perform non-dominated sorting on the approach sequences according to the adaptability parameters. Non-dominated sorting follows the idea of ​​NSGA (Non-dominated Sorting Genetic Algorithms). In order to coordinate the relationship between the various adaptability parameters in the approach sequence, the optimal approach sequence that makes each adaptability parameter obtain a relatively small value is found through the non-dominated sorting method, and the approach sequences are sorted according to the best approach sequence, the second best approach sequence, the third best approach sequence...the worst approach sequence. In this embodiment, the number of delayed flights, the average fuel consumption and the average delay time are all as small as possible.

[0040] After the approach sequences are sorted, the sorting results need to be layered according to the dominance relationship. In this embodiment, the dominance relationship is that, for two approach sequences, if all the adaptability parameters of one approach sequence are smaller than those of the other approach sequence, then this approach sequence is said to dominate the other approach sequence, and the other approach sequence is dominated by this approach sequence. Approach sequences dominated by the same number of other approach sequences are regarded as approach sequences of the same layer, thereby completing the layering of the approach sequences and completing the multi-objective optimization sorting.

[0041] Then, according to the needs of multi-objective optimization, a fitness function is selected to calculate the fitness value. In this application, a sigmoid function can be selected to map each fitness parameter to calculate the fitness value, and the distance between the fitness values ​​in each layer of the approach sequence is calculated to obtain the congestion of the approach sequence: in, is the congestion degree of the kth approach sequence, R is the number of fitness values, is the rth fitness value of the k+1th approach sequence, is the rth fitness value of the k-1th approach sequence. According to experience, a suitable crowding threshold is set for each layer of approach sequence, and approach sequences with crowding lower than the crowding threshold are eliminated to ensure the diversity of the population and obtain the first intermediate population.

[0042] S4: performing genetic algorithm screening on the first intermediate population to obtain a second intermediate population, performing crossover mutation on the second intermediate population to obtain a third intermediate population, and obtaining a target population through the third intermediate population; Furthermore, the purpose of this stage is to obtain a population with better performance, higher pertinence and richness through crossover mutation, and obtain the target population. Specifically, step S4 further includes: S41: performing genetic algorithm screening on the first intermediate population by a tournament selection method to obtain a second intermediate population; S42: performing crossover on the second intermediate population by simulating a binary crossover method to obtain a progeny population, and performing mutation on the progeny population by a polynomial mutation method to obtain a third intermediate population; S43: merging the third intermediate population with the first intermediate population to obtain a temporary population, performing multi-objective optimization sorting on the temporary population and calculating the congestion degree to obtain a target population.

[0043] With respect to the above steps, the specific implementation of this embodiment is as follows: First, according to the idea of ​​NSGA algorithm, the first intermediate population is screened by genetic algorithm to obtain the second intermediate population , the method chosen here is the tournament selection method: here, Indicates that each time a new sample is drawn from the first intermediate population P An entry sequence is used for tournament selection, and the second intermediate population can be obtained after multiple tournament selections.

[0044] Then the second intermediate population is crossovered by simulating binary crossover to obtain the offspring population: Among them, C represents the offspring population, SBX() represents the simulated binary crossover of the contents in the brackets, represents the empirically determined cross-distribution index.

[0045] Then the offspring population is mutated by polynomial mutation method to obtain the third intermediate population : in, Indicates polynomial mutation of the contents in brackets. is the empirically determined variation distribution index.

[0046] Then, the third intermediate population is merged with the first intermediate population to obtain a temporary population E. The approach sequences in the temporary population are sorted by multi-objective optimization and the congestion degree is calculated. After eliminating some approach sequences with excessive congestion, the first N approach sequences are taken to obtain the target population. ,The taxiway use order of the aircraft waiting to land using the taxiway can be determined according to the ,approach sequence included in the target population.

[0047] S5: Calculating the parking stand selection parameters and the shortest taxiing path of the aircraft waiting to land according to the target population, and obtaining taxiway adaptability parameters through the parking stand selection parameters and the shortest taxiing path; Furthermore, the purpose of this stage is to calculate the parking stand selection parameters of the aircraft waiting to land and obtain the shortest taxiing path to the parking stand, thereby obtaining the taxiway adaptability parameters, so that the allocation of taxiways and parking stands can be optimized after the aircraft lands. Specifically, step S5 further includes: S51: obtaining the taxiway route and parking stand distribution of the airport, formulating taxiway optimization constraint conditions according to the taxiway route and the parking stand distribution, and calculating the shortest taxiway path according to the taxiway optimization constraint conditions, the taxiway route, the target population and the parking stand distribution; S52: Calculating the parking stand selection parameter according to the parking stand distribution and the shortest taxiing path; calculating the average taxiing time through the shortest taxiing path, and using the parking stand selection parameter and the average taxiing time as the taxiway adaptability parameter.

[0048] With respect to the above steps, the specific implementation methods in this embodiment are as follows: First, the taxiway route and parking position distribution of the airport are obtained, and then the taxiway optimization constraint conditions are formulated according to the taxiway route and parking position distribution. In this embodiment, the taxiway constraint conditions are that the same parking position can only be used by one waiting aircraft at the same time; the taxiway is divided into several sections, and each taxiway section can only be used by one waiting aircraft at the same time; and there can only be one waiting aircraft at the intersection between each taxiway. Then, according to the taxiway route, parking position distribution and target population, the position of the waiting aircraft when it is about to enter the taxiway from the runway after landing is obtained, and under the premise of satisfying the taxiway optimization constraint conditions, the A* algorithm or Dijkstra algorithm that can find and plan the shortest path is used to calculate the shortest taxiing path for the waiting aircraft to reach the nearest available parking position.

[0049] Then, the shortest glide path can be used to calculate the Taxi time for aircraft waiting to land : in, is the length of the bth taxiway in the shortest taxiway path, For the The taxiing speed of the aircraft waiting to land. This data is usually determined by the model of the aircraft waiting to land. is the average waiting time of aircraft waiting to land at the cth intersection, which can be obtained based on the historical data of the statistical airport.

[0050] Then the parking space selection parameter H can be calculated: in, is the first parking stand selection coefficient determined based on experience, is the second parking stand selection coefficient determined based on experience, is the third parking stand selection coefficient determined empirically and can be a negative value. For the The number of potential conflicts between the parking stand reached by the aircraft waiting to land when occupying the shortest taxiing path and other flights. Whether a potential conflict occurs can be set based on the experience and needs of the airport. For example, when an aircraft waiting to land with a relatively low passenger load occupies a parking stand with a large passenger reception capacity, and there may be other aircraft waiting to land with a relatively large passenger load that will land and need to use the parking stand, it can be determined that a potential conflict has occurred; The parking stand indication coefficient is used to indicate the Whether the parking stand reached by the aircraft waiting to land on the shortest taxiing path is a specific parking stand of priority, such as whether it is a dedicated parking stand for the airline to which it belongs; When the parking stand reached by the shortest taxiing path is the preferred parking stand for an aircraft waiting to land, is 1 if the value is true, otherwise it is 0.

[0051] The average glide time G can also be calculated based on the shortest glide path: Finally, the average taxi time and parking stand selection parameters are used as taxiway adaptability parameters, and the smaller the average taxi time and parking stand selection parameters are, the better.

[0052] S6: calculating an iterative adaptability parameter of the target population, performing genetic algorithm iteration on the target population according to the iterative adaptability parameter and the taxiway adaptability parameter to obtain a target solution set, and selecting a target approach sequence from the target solution set.

[0053] Furthermore, the purpose of this stage is to iterate the target population using a genetic algorithm, thereby obtaining a target solution set and selecting a target approach sequence therefrom to complete the planning of flight landing and parking space allocation. Specifically, first, the adaptability parameters of the approach sequence in the target population are calculated, and then used as the iterative adaptability parameters of the approach sequence in the target population. Then, the iterative adaptability parameters and the taxiway adaptability parameters are used as new adaptability parameters to perform multi-objective optimization sorting, calculate fitness values ​​and congestion and perform elimination, genetic algorithm screening, crossover mutation, calculate taxiway adaptability parameters and other steps, that is, execute the steps from step S3 to step S6 up to the calculation of iterative adaptability parameters to iterate the target population until the number of iterations reaches the predetermined number of iterations or the change in fitness values ​​between the target populations in two iterations is less than a threshold set based on experience, and the iteration of the target population can be considered completed. Finally, a number of approach sequences that are not dominated by other approach sequences are selected from the target population as the target solution set. : Among them, GetNondominatedSet() means taking the non-dominated solution set in the brackets, and then selecting an approach sequence from the target solution set as the target approach sequence as needed, so as to complete the acquisition of the approach sequence.

[0054] The present invention uses genetic algorithms for iteration and comprehensively considers factors such as the number of delayed flights, fuel consumption, allocation of taxiways and parking spaces, etc., thereby effectively improving the airport's scheduling capabilities, reducing the fuel consumption of aircraft during landing and taxiing phases, and reducing flight delays.

[0055] The flight sequencing device based on NSGA provided by the present invention is described below. The flight sequencing device based on NSGA described below and the flight sequencing method based on NSGA described above can correspond to each other.

[0056] Figure 2 The structural diagram of the flight sorting system based on NSGA is shown as follows: Figure 2 As shown, the flight sorting method based on NSGA as described above includes: The initial population module 100 is used to obtain flight information of aircraft waiting to land, and randomly sort the aircraft waiting to land to obtain an initial population including multiple approach sequences; Constraint condition module 200: used to obtain safety restriction parameters, calculate adaptability parameters according to the flight information, and formulate optimization constraint conditions according to the flight information and the safety restriction parameters; The first intermediate population module 300 is used to perform multi-objective optimization sorting on the initial population according to the adaptability parameters under the constraints of the optimization constraints, calculate the congestion degree of the approach sequence, and eliminate the approach sequence in the initial population according to the congestion degree to obtain the first intermediate population; Target population module 400: used for performing genetic algorithm screening on the first intermediate population to obtain a second intermediate population, performing crossover mutation on the second intermediate population to obtain a third intermediate population, and obtaining a target population through the third intermediate population; The taxiway planning module 500 is used to calculate the parking position selection parameters and the shortest taxiing path of the waiting aircraft according to the target population, and obtain the taxiway adaptability parameters through the parking position selection parameters and the shortest taxiing path; The target approach sequence module 600 is used to calculate the iterative adaptability parameters of the target population, perform genetic algorithm iteration on the target population through the iterative adaptability parameters and the taxiway adaptability parameters to obtain a target solution set, and select a target approach sequence from the target solution set.

[0057] on the other hand, Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the flight sorting method based on NSGA, and the method includes: S1: Acquire flight information of aircraft waiting to land, and randomly sort the aircraft waiting to land to obtain an initial population including multiple approach sequences; S2: obtaining safety restriction parameters, calculating adaptability parameters according to the flight information, and formulating optimization constraint conditions according to the flight information and the safety restriction parameters; S3: Under the constraints of the optimization constraints, the initial population is sorted by multi-objective optimization according to the adaptability parameters, and the congestion degree of the approach sequence is calculated, and the approach sequence in the initial population is eliminated according to the congestion degree to obtain a first intermediate population; S4: performing genetic algorithm screening on the first intermediate population to obtain a second intermediate population, performing crossover mutation on the second intermediate population to obtain a third intermediate population, and obtaining a target population through the third intermediate population; S5: Calculating the parking stand selection parameters and the shortest taxiing path of the aircraft waiting to land according to the target population, and obtaining taxiway adaptability parameters through the parking stand selection parameters and the shortest taxiing path; S6: calculating an iterative adaptability parameter of the target population, performing genetic algorithm iteration on the target population according to the iterative adaptability parameter and the taxiway adaptability parameter to obtain a target solution set, and selecting a target approach sequence from the target solution set.

[0058] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0059] On the other hand, the present invention also provides a computer program product, the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, when the program instructions are executed by a computer, the computer can execute the flight sorting method based on NSGA provided by the above methods, the method includes S1: Acquire flight information of aircraft waiting to land, and randomly sort the aircraft waiting to land to obtain an initial population including multiple approach sequences; S2: obtaining safety restriction parameters, calculating adaptability parameters according to the flight information, and formulating optimization constraint conditions according to the flight information and the safety restriction parameters; S3: Under the constraints of the optimization constraints, the initial population is sorted by multi-objective optimization according to the adaptability parameters, and the congestion degree of the approach sequence is calculated, and the approach sequence in the initial population is eliminated according to the congestion degree to obtain a first intermediate population; S4: performing genetic algorithm screening on the first intermediate population to obtain a second intermediate population, performing crossover mutation on the second intermediate population to obtain a third intermediate population, and obtaining a target population through the third intermediate population; S5: Calculating the parking stand selection parameters and the shortest taxiing path of the aircraft waiting to land according to the target population, and obtaining taxiway adaptability parameters through the parking stand selection parameters and the shortest taxiing path; S6: calculating an iterative adaptability parameter of the target population, performing genetic algorithm iteration on the target population according to the iterative adaptability parameter and the taxiway adaptability parameter to obtain a target solution set, and selecting a target approach sequence from the target solution set.

[0060] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the flight sorting method based on NSGA provided by the above methods, the method comprising: S1: Acquire flight information of aircraft waiting to land, and randomly sort the aircraft waiting to land to obtain an initial population including multiple approach sequences; S2: obtaining safety restriction parameters, calculating adaptability parameters according to the flight information, and formulating optimization constraint conditions according to the flight information and the safety restriction parameters; S3: Under the constraints of the optimization constraints, the initial population is sorted by multi-objective optimization according to the adaptability parameters, and the congestion degree of the approach sequence is calculated, and the approach sequence in the initial population is eliminated according to the congestion degree to obtain a first intermediate population; S4: performing genetic algorithm screening on the first intermediate population to obtain a second intermediate population, performing crossover mutation on the second intermediate population to obtain a third intermediate population, and obtaining a target population through the third intermediate population; S5: Calculating the parking stand selection parameters and the shortest taxiing path of the aircraft waiting to land according to the target population, and obtaining taxiway adaptability parameters through the parking stand selection parameters and the shortest taxiing path; S6: calculating an iterative adaptability parameter of the target population, performing genetic algorithm iteration on the target population according to the iterative adaptability parameter and the taxiway adaptability parameter to obtain a target solution set, and selecting a target approach sequence from the target solution set.

[0061] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0062] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0063] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The flight sorting method based on NSGA is characterized by: include: S1: Acquire flight information of aircraft waiting to land, and randomly sort the aircraft waiting to land to obtain an initial population including multiple approach sequences; S2: obtaining safety restriction parameters, calculating adaptability parameters according to the flight information, and formulating optimization constraint conditions according to the flight information and the safety restriction parameters; S3: Under the constraints of the optimization constraints, the initial population is sorted by multi-objective optimization according to the adaptability parameters, and the congestion degree of the approach sequence is calculated, and the approach sequence in the initial population is eliminated according to the congestion degree to obtain a first intermediate population; S4: performing genetic algorithm screening on the first intermediate population to obtain a second intermediate population, performing crossover mutation on the second intermediate population to obtain a third intermediate population, and obtaining a target population through the third intermediate population; S5: Calculating the parking stand selection parameters and the shortest taxiing path of the aircraft waiting to land according to the target population, and obtaining taxiway adaptability parameters through the parking stand selection parameters and the shortest taxiing path; S6: calculating an iterative adaptability parameter of the target population, performing genetic algorithm iteration on the target population according to the iterative adaptability parameter and the taxiway adaptability parameter to obtain a target solution set, and selecting a target approach sequence from the target solution set.

2. The flight sorting method based on NSGA according to claim 1, characterized in that: Step S2 further comprises: S21: Acquire the approach conditions of the airport, obtain the safety limit parameters according to the approach conditions, and obtain the adaptability parameters of each approach sequence according to the flight information, wherein the adaptability parameters include the number of delayed flights, average fuel consumption, and average delay time; S22: Formulate the optimization constraint conditions according to the flight information and the safety limit parameters, wherein the optimization constraint conditions include wake turbulence interval constraint, maximum allowable position exchange constraint and landing edge capacity constraint.

3. The flight sorting method based on NSGA according to claim 1, characterized in that: Step S3 further comprises: S31: screening the approach sequences in the initial population according to the optimization constraint conditions, and performing multi-objective optimization sorting on the approach sequences in the initial population according to the adaptability parameters; S32: Calculating a fitness value according to the adaptability parameter, calculating the congestion of the approach sequence according to the fitness value, and eliminating the approach sequences in the initial population according to the congestion to obtain a first intermediate population.

4. The flight sorting method based on NSGA according to claim 1, characterized in that: Step S4 further comprises: S41: performing genetic algorithm screening on the first intermediate population by a tournament selection method to obtain a second intermediate population; S42: performing crossover on the second intermediate population by simulating a binary crossover method to obtain a progeny population, and performing mutation on the progeny population by a polynomial mutation method to obtain a third intermediate population; S43: merging the third intermediate population with the first intermediate population to obtain a temporary population, performing multi-objective optimization sorting on the temporary population and calculating the congestion degree to obtain a target population.

5. The flight sorting method based on NSGA according to claim 1, characterized in that: Step S5 further comprises: S51: obtaining the taxiway route and parking stand distribution of the airport, formulating taxiway optimization constraint conditions according to the taxiway route and the parking stand distribution, and calculating the shortest taxiway path according to the taxiway optimization constraint conditions, the taxiway route, the target population and the parking stand distribution; S52: Calculating the parking stand selection parameter according to the parking stand distribution and the shortest taxiing path; calculating the average taxiing time through the shortest taxiing path, and using the parking stand selection parameter and the average taxiing time as the taxiway adaptability parameter.

6. The flight sorting method based on NSGA according to claim 1, characterized in that: In step S1, priority aircraft waiting to land are determined according to the flight information, and the demand for the priority aircraft waiting to land is determined, and the aircraft waiting to land are randomly sorted according to the demand for the priority aircraft waiting to land.

7. A flight sorting system based on NSGA, used to execute the flight sorting method based on NSGA as claimed in any one of claims 1 to 6, characterized in that: include: Initial population module: used to obtain flight information of aircraft waiting to land, randomly sort the aircraft waiting to land, and obtain an initial population including multiple approach sequences; Constraint condition module: used for obtaining safety restriction parameters, calculating adaptability parameters according to the flight information, and formulating optimization constraint conditions according to the flight information and the safety restriction parameters; A first intermediate population module: used for performing multi-objective optimization sorting on the initial population according to the adaptability parameters under the constraints of the optimization constraints, calculating the congestion degree of the approach sequence, and eliminating the approach sequence in the initial population according to the congestion degree to obtain a first intermediate population; Target population module: used for performing genetic algorithm screening on the first intermediate population to obtain a second intermediate population, performing crossover mutation on the second intermediate population to obtain a third intermediate population, and obtaining a target population through the third intermediate population; A taxiway planning module: used to calculate the parking position selection parameters and the shortest taxiing path of the aircraft to be landed according to the target population, and obtain the taxiway adaptability parameters through the parking position selection parameters and the shortest taxiing path; Target approach sequence module: used to calculate the iterative adaptability parameters of the target population, perform genetic algorithm iteration on the target population through the iterative adaptability parameters and the taxiway adaptability parameters to obtain a target solution set, and select a target approach sequence from the target solution set.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the flight sorting method based on NSGA are implemented as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the flight sorting method based on NSGA as described in any one of claims 1 to 6 are implemented.

10. A computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, characterized in that: When the program instructions are executed by a computer, the computer can perform the steps of the flight sequencing method based on NSGA as described in any one of claims 1 to 6.

Images