Method and device for determining nominal flight path of aircraft, computer equipment and medium

Abstract

The invention relates to a nominal flight path determination method and device of an aircraft, computer equipment and a medium. The method comprises the following steps: acquiring an initial scheme cluster; for each iteration process, determining the scheme fitness of the corresponding scheduling scheme according to the flight general situation information of each scheduling scheme in the target scheme cluster corresponding to the previous iteration process; according to the scheme fitness of each scheduling scheme, updating a target scheme cluster corresponding to the previous iteration process to obtain a target scheme cluster corresponding to the current iteration process; wherein the target scheme cluster corresponding to the first iteration process is an initial scheme cluster; and under the condition that the current iteration process meets the iteration termination condition, selecting a target scheduling scheme from the target scheme cluster obtained in the last iteration process. By adopting the method, flight conflicts among a plurality of aircrafts can be avoided, and the accuracy and rationality of determining the nominal flight path of the aircraft are further improved.

Description

Technical Field

[0001] This application relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to a method, apparatus, computer equipment, and medium for determining the nominal trajectory of an aircraft. Background Technology

[0002] The nominal track is the theoretically optimal flight path planned for an aircraft (such as a drone) after comprehensively considering performance, environment, and air traffic control requirements. It ensures the flight safety and efficiency of the aircraft in the aviation field. Therefore, it is crucial to determine the nominal track of an aircraft.

[0003] In traditional technologies, after obtaining the basic information of the aircraft, the Dijkstra algorithm or A* search algorithm is usually used to plan the route of the UAV, thereby obtaining the nominal track of the UAV.

[0004] While this method can complete the path planning for aircraft, the above algorithms are all based on the perspective of a single aircraft. When facing multi-aircraft scenarios, they lack the ability to coordinate planning to resolve flight conflicts and have the problem of not being able to perform nominal trajectory planning for a large number of aircraft. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer equipment, and medium for determining the nominal flight paths of multiple aircraft, which can plan the nominal flight paths of multiple aircraft, in order to address the above-mentioned technical problems.

[0006] In a first aspect, this application provides a method for determining the nominal trajectory of an aircraft, including:

[0007] Obtain an initial scheme cluster; wherein the initial scheme cluster includes at least one scheduling scheme; the scheduling scheme includes at least one nominal track of an aircraft in its flight airspace;

[0008] For each iteration, the fitness of the corresponding scheduling scheme is determined based on the flight profile information of each scheduling scheme in the target scheme cluster corresponding to the previous iteration.

[0009] Based on the fitness of each scheduling scheme, the target scheme cluster corresponding to the previous iteration is updated to obtain the target scheme cluster corresponding to the current iteration; among them, the target scheme cluster corresponding to the first iteration is the initial scheme cluster.

[0010] If the current iteration process meets the iteration termination condition, a target scheduling scheme is selected from the target scheme cluster obtained from the last iteration process.

[0011] In one embodiment, the target scheme cluster corresponding to the previous iteration is updated based on the scheme fitness of each scheduling scheme to obtain the target scheme cluster corresponding to the current iteration, including:

[0012] Based on the fitness of each scheduling scheme, at least one reference scheduling scheme is selected from the target scheme cluster corresponding to the previous iteration process.

[0013] Each reference scheduling scheme is derived and processed to update the reference scheduling scheme;

[0014] Based on the updated reference scheduling scheme, generate the target scheme cluster corresponding to this iteration process.

[0015] In one embodiment, a derivation process is performed on each reference scheduling scheme to update the reference scheduling scheme, including:

[0016] For each waypoint in each reference scheduling scheme, determine the number of conflicts in case of flight conflicts at the waypoint;

[0017] Path points with more than a preset conflict threshold are designated as derivative path points;

[0018] The reference scheduling scheme with derived path points is processed to update the reference scheduling scheme.

[0019] In one embodiment, a derivation process is performed on each reference scheduling scheme to update the reference scheduling scheme, including:

[0020] For each reference scheduling scheme, the scheme congestion degree is determined based on the flight conflict between different nominal tracks in the reference scheduling scheme.

[0021] Based on the congestion level of each reference scheduling scheme, at least two reference scheduling schemes are selected for cross-processing to update the reference scheduling scheme.

[0022] In one embodiment, each reference scheduling scheme undergoes a derivation process to update the reference scheduling scheme, including:

[0023] Determine the mutated random numbers for each reference scheduling scheme;

[0024] Based on the preset mutation threshold and the relationship between the size of the mutation random numbers of each reference scheduling scheme, at least one reference scheduling scheme is selected for mutation processing to update the reference scheduling scheme; wherein, the preset mutation threshold is determined based on the current iteration number and the mutation probability boundary value.

[0025] In one embodiment, each reference scheduling scheme undergoes a derivation process to update the reference scheduling scheme, including:

[0026] For each reference scheduling scheme, the reference scheduling scheme is perturbed to obtain the perturbed scheduling scheme corresponding to the reference scheduling scheme;

[0027] Based on the flight profile information of the disturbance scheduling scheme, determine the scheme adaptability of the disturbance scheduling scheme;

[0028] The degree of disturbance in the disturbance scheduling scheme is determined based on the scheme fitness of the disturbance scheduling scheme and the scheme fitness of the corresponding reference scheduling scheme.

[0029] Based on the degree of disturbance of each disturbance scheduling scheme, at least one disturbance scheduling scheme is selected to replace the corresponding reference scheduling scheme.

[0030] In one embodiment, the target scheme cluster corresponding to the current iteration process is generated based on the updated reference scheduling scheme, including:

[0031] For each reference scheduling scheme, the nominal tracks with flight conflicts are adjusted to update the reference scheduling scheme;

[0032] Based on the updated reference scheduling scheme, generate the target scheme cluster corresponding to this iteration process.

[0033] In one embodiment, the nominal track includes the aircraft's route and arrival time at waypoints; adjusting nominal tracks with flight conflicts to update the reference scheduling scheme includes at least one of the following:

[0034] Adjust the arrival time of the corresponding aircraft to the conflict path point in the nominal flight path where there is a flight conflict;

[0035] For aircraft whose nominal tracks conflict with each other, generate new nominal tracks;

[0036] Among them, the conflict waypoint is the waypoint reached by at least two aircraft corresponding to the nominal flight path of the flight conflict at the same time period.

[0037] In one embodiment, the fitness of the corresponding scheduling scheme is determined based on the flight profile information of each scheduling scheme in the target scheme cluster corresponding to the previous iteration, including:

[0038] For each scheduling scheme in the target scheme cluster corresponding to the previous iteration, the fitness weight is determined based on the airspace congestion degree corresponding to the scheduling scheme.

[0039] The fitness of the scheduling scheme is determined based on the fitness weights and flight profile information.

[0040] Secondly, this application also provides a nominal trajectory determination device for an aircraft, comprising:

[0041] The acquisition module is used to acquire an initial scheme cluster; wherein the initial scheme cluster includes at least one scheduling scheme; the scheduling scheme includes at least one nominal track of an aircraft in its flight airspace;

[0042] The determination module is used to determine the fitness of the corresponding scheduling scheme for each iteration process based on the flight profile information of each scheduling scheme in the target scheme cluster corresponding to the previous iteration process.

[0043] The update module is used to update the target scheme cluster corresponding to the previous iteration process based on the scheme fitness of each scheduling scheme to obtain the target scheme cluster corresponding to the current iteration process; wherein, the target scheme cluster corresponding to the first iteration process is the initial scheme cluster.

[0044] The selection module is used to select a target scheduling scheme from the target scheme cluster obtained in the last iteration process, provided that the iteration termination condition is met in the current iteration process.

[0045] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0046] Obtain an initial scheme cluster; wherein the initial scheme cluster includes at least one scheduling scheme; the scheduling scheme includes at least one nominal track of an aircraft in its flight airspace;

[0047] For each iteration, the fitness of the corresponding scheduling scheme is determined based on the flight profile information of each scheduling scheme in the target scheme cluster corresponding to the previous iteration.

[0048] Based on the fitness of each scheduling scheme, the target scheme cluster corresponding to the previous iteration is updated to obtain the target scheme cluster corresponding to the current iteration; among them, the target scheme cluster corresponding to the first iteration is the initial scheme cluster.

[0049] If the current iteration process meets the iteration termination condition, a target scheduling scheme is selected from the target scheme cluster obtained from the last iteration process.

[0050] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0051] Obtain an initial scheme cluster; wherein the initial scheme cluster includes at least one scheduling scheme; the scheduling scheme includes at least one nominal track of an aircraft in its flight airspace;

[0052] For each iteration, the fitness of the corresponding scheduling scheme is determined based on the flight profile information of each scheduling scheme in the target scheme cluster corresponding to the previous iteration.

[0053] Based on the fitness of each scheduling scheme, the target scheme cluster corresponding to the previous iteration is updated to obtain the target scheme cluster corresponding to the current iteration; among them, the target scheme cluster corresponding to the first iteration is the initial scheme cluster.

[0054] If the current iteration process meets the iteration termination condition, a target scheduling scheme is selected from the target scheme cluster obtained from the last iteration process.

[0055] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0056] Obtain an initial scheme cluster; wherein the initial scheme cluster includes at least one scheduling scheme; the scheduling scheme includes at least one nominal track of an aircraft in its flight airspace;

[0057] For each iteration, the fitness of the corresponding scheduling scheme is determined based on the flight profile information of each scheduling scheme in the target scheme cluster corresponding to the previous iteration.

[0058] Based on the fitness of each scheduling scheme, the target scheme cluster corresponding to the previous iteration is updated to obtain the target scheme cluster corresponding to the current iteration; among them, the target scheme cluster corresponding to the first iteration is the initial scheme cluster.

[0059] If the current iteration process meets the iteration termination condition, a target scheduling scheme is selected from the target scheme cluster obtained from the last iteration process.

[0060] The aforementioned method, apparatus, computer equipment, and medium for determining the nominal trajectory of an aircraft introduce a scheme fitness factor during the iteration process. This factor evaluates the adaptability of each aircraft's nominal trajectory within its respective airspace. By comprehensively considering the adaptability of different aircraft within their respective airspaces, the target scheme cluster corresponding to the previous iteration is iteratively updated. This improves the coordination between the nominal trajectories of different aircraft, causing the target scheme cluster to gradually approach the optimal solution set. From the target scheme cluster representing the optimal solution set obtained in the final iteration, a target scheduling scheme adapted to the current airspace is selected. This improves the adaptability of the aircraft to flight within its respective airspace, thereby avoiding flight conflicts between multiple aircraft and further improving the accuracy and rationality of determining the aircraft's nominal trajectory. Attached Figure Description

[0061] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1A A flowchart illustrating the nominal trajectory determination method for the first type of aircraft provided in this embodiment;

[0063] Figure 1B This embodiment provides a route network structure diagram for an aircraft.

[0064] Figure 2 This is a flowchart illustrating the first target scheme cluster determination step provided in this embodiment;

[0065] Figure 3 A flowchart illustrating the update steps of the first reference scheduling scheme provided in this embodiment;

[0066] Figure 4 This is a flowchart illustrating the update steps of the second reference scheduling scheme provided in this embodiment;

[0067] Figure 5 A flowchart illustrating the update steps of the third reference scheduling scheme provided in this embodiment;

[0068] Figure 6 This is a flowchart illustrating the second target scheme cluster determination step provided in this embodiment;

[0069] Figure 7 A flowchart illustrating the nominal trajectory determination method for the second type of aircraft provided in this embodiment;

[0070] Figure 8 This embodiment provides a structural block diagram of a nominal trajectory determination device for an aircraft.

[0071] Figure 9 This is an internal structural diagram of a computer device provided in this embodiment. Detailed Implementation

[0072] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0073] In one exemplary embodiment, such as Figure 1AAs shown, a method for determining the nominal trajectory of an aircraft is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0074] S110, Obtain the initial cluster.

[0075] The initial scheme cluster can be understood as the set of initial candidate schemes used to initiate the iteration process; the initial scheme cluster includes at least one scheduling scheme. A scheduling scheme can be understood as a flight plan set up under specific constraints to complete the flight missions of different aircraft within their respective airspaces; the scheduling scheme includes at least one nominal track of an aircraft in its airspace; the nominal track includes the aircraft's route and arrival time at waypoints. A route can be understood as the spatial trajectory or flight path planned by an aircraft during flight to complete its navigation mission from the takeoff point to the landing point; it should be noted that a route segment can consist of at least one waypoint and segments between waypoints. A waypoint can be understood as a pre-defined point in the route; a waypoint can be the aircraft's takeoff point, landing point, or waypoint.

[0076] In some embodiments, flight plan application information and airway network topology information of at least one aircraft are obtained; based on the flight plan application information and airway network topology information of each aircraft, an initial scheme cluster is generated under preset constraints.

[0077] Flight plan application information can be understood as a detailed set of data used to apply for flight permits and ensure flight safety and efficiency. Flight plan application information may include the aircraft's takeoff time, takeoff waypoint, arrival time, arrival waypoint, application time, aircraft type information, and flight mission type information.

[0078] In this context, airway network topology information can be understood as topological information formed by abstractly describing the connection relationships between waypoints and air segments, using waypoints and air segments as basic elements. For example, such as... Figure 1B The diagram shows the airway network structure. P1-P8 represent waypoints, and the black lines represent the air segments between two adjacent waypoints. Taking waypoints P1 and P3 as an example, the air segment formed by P1-P3 is the air segment connecting waypoints P1 and P3.

[0079] The preset constraints can include at least one of waypoint sequence constraints and waypoint arrival time constraints. Waypoint constraints can be understood as: based on the fixed departure and arrival waypoints according to the flight plan application information, the waypoints are arranged according to the route network topology information; waypoint arrival time constraints can be understood as: based on the fixed departure and arrival times according to the flight plan application information, the arrival time sequence of each waypoint is arranged according to a speed not exceeding the maximum speed of the aircraft or the route constraint.

[0080] For example, based on the flight plan application information and route network topology information of each aircraft, and under preset constraints, the initial scheme cluster is generated as follows: For each aircraft, an initial track is generated according to the route network topology information, starting from the aircraft's takeoff waypoint and ending at the aircraft's arrival waypoint; Based on the fixed takeoff and arrival times according to the corresponding flight plan application information of the aircraft, for each waypoint in the initial track, the arrival time of the aircraft to the corresponding waypoint is determined according to the aircraft's maximum flight speed and the topological order of the initial track; The takeoff time, arrival time, and arrival time of the aircraft to each waypoint in the initial track are updated to the corresponding waypoints in the initial track to obtain the nominal track of the aircraft; The nominal tracks of different aircraft are combined to obtain a scheduling scheme; An initial scheme cluster is constructed based on all scheduling schemes.

[0081] For example, the method for generating an initial track containing the aircraft's takeoff waypoint and arrival waypoint according to the route network topology information is as follows: Based on the route network topology information, sequentially select waypoints connected to the current waypoint as the next waypoint, until the selected next waypoint is the aircraft's arrival waypoint, thus completing the generation of the initial track. Specifically, during the initial selection of the next waypoint, the aircraft's takeoff waypoint is used as the current waypoint.

[0082] For example, the method for determining the arrival time of the aircraft to each waypoint in the initial path based on the maximum flight speed of the aircraft and the topological order of the initial track is as follows: select the current waypoint in sequence according to the order in which the aircraft arrives at each waypoint in the initial track, and take the ratio between the length of the segment between the current waypoint and the previous waypoint and the corresponding maximum speed of the aircraft as the flight time of the segment; add the corresponding flight time to the arrival time of the previous waypoint to obtain the arrival time of the current waypoint.

[0083] For example, taking three aircraft as an example, the scheduling scheme can be as follows (1-1). In this embodiment, only the nominal track 1 of aircraft 1 is described: the takeoff waypoint of aircraft 1 is P1, the takeoff time is 8:00; the transit point is P3, and the arrival time of transit point P3 is 8:05; finally, it lands at the transit point P5, and the arrival time is 8:20.

[0084] (1-1)

[0085] S120: For each iteration, the fitness of the corresponding scheduling scheme is determined based on the flight profile information of each scheduling scheme in the target scheme cluster corresponding to the previous iteration.

[0086] The target scheme cluster can be understood as a set of schemes that have undergone at least one iteration, used to characterize a set of high-quality scheduling schemes that require further iteration or are the final selection. Flight profile information can be understood as information characterizing the flight status of different aircraft in the scheduling scheme; optionally, flight profile information may include at least one of total flight time, total fuel consumption, and flight safety. Scheme fitness can be understood as a quantifiable evaluation of the merits of a scheduling scheme in terms of at least one flight profile requirement; for example, flight profile requirements may be minimizing total flight time, minimizing fuel consumption, and maximizing flight safety.

[0087] In one optional embodiment, for each scheduling scheme in the target scheme cluster corresponding to the previous iteration, flight indicators of the scheduling scheme in different dimensions are determined based on the flight profile information of the scheduling scheme; the sum of the flight indicators is used as the scheme fitness of the scheduling scheme. For example, based on the flight profile information of the scheduling scheme, the total flight time, total fuel consumption, and flight safety of the scheduling scheme are determined; the sum of the total flight time, total fuel consumption, and flight safety is used as the scheme fitness of the scheduling scheme.

[0088] In another optional embodiment, for each scheduling scheme in the target scheme cluster corresponding to the previous iteration, a fitness weight is determined based on the airspace congestion degree corresponding to the scheduling scheme; the scheme fitness is determined based on the fitness weight and flight profile information. The fitness weight includes safety weight, time weight, and fuel weight. The advantage of this setup is that by adjusting the fitness weight corresponding to the scheduling scheme, the priority of different flight profiles is dynamically optimized, significantly improving the flight safety of the scheduling scheme.

[0089] For example, the implementation method for determining the fitness weight based on the airspace congestion level corresponding to the scheduling scheme includes: taking the number of aircraft passing through the airspace in a unit of time as the current airspace congestion level of the scheduling scheme; taking the ratio between the current airspace congestion level and the preset maximum airspace capacity as the congestion index; determining the safety weight based on the congestion index and the preset safety weight boundary value; determining the time weight and fuel weight according to the safety weight and a preset ratio; and weighting the total flight time, time weight, total fuel consumption, fuel weight, flight safety, and safety weight in the flight overview information to obtain the fitness of the scheduling scheme.

[0090] For example, in this embodiment, the safety weight can be determined by the following formula (1-2) based on the congestion index and the preset safety weight boundary value.

[0091] (1-2)

[0092] in, Characterizing security weights, This represents the minimum value (e.g., 0.1) among the preset safety weight boundary values. C represents the maximum value among the preset safety weight boundary values ​​(e.g., 0.9), and C represents the current airspace congestion level. max This represents the maximum capacity of the spatial domain. It should be noted that, in this embodiment, the security weight... There is a positive correlation between the current airspace congestion level C and the safety weight; that is, the higher the current airspace congestion level C, the higher the safety weight. The larger the interval, the more it forces subsequent algorithms to prioritize generating scheduling schemes with larger safety intervals.

[0093] For example, taking a preset ratio of 5:3:2 between safety weight, time weight, and fuel weight as an example, if the safety weight is determined to be 0.5, the time weight is 0.3, and the fuel weight is 0.2. This application does not limit the specific preset ratio.

[0094] S130, based on the suitability of each scheduling scheme, update the target scheme cluster corresponding to the previous iteration process to obtain the target scheme cluster corresponding to the current iteration process.

[0095] Among them, the target scheme cluster corresponding to the first iteration process is the initial scheme cluster.

[0096] In some embodiments, the scheduling schemes are sorted in descending order of their fitness; the scheduling schemes with a preset ranking in the sorting results are retained to update the target scheme cluster corresponding to the previous iteration process, thereby obtaining the target scheme cluster corresponding to the current iteration process.

[0097] S140, if the current iteration process meets the iteration termination condition, select a target scheduling scheme from the target scheme cluster obtained in the last iteration process.

[0098] The iteration termination condition can be reaching a preset number of iterations (e.g., 100) or the fitness of the scheme does not improve after a preset number of consecutive algebras (e.g., 10). This application does not limit the specific iteration termination condition. The preset number of iterations and the preset number of algebras can be set based on human experience or can be experimental values ​​obtained through a large number of experiments. This embodiment does not limit them.

[0099] In one alternative implementation, if the current iteration process satisfies the iteration termination condition, the scheduling scheme with the highest fitness is selected from the target scheme cluster obtained in the last iteration process and used as the target scheduling scheme.

[0100] In another optional implementation, if the current iteration process meets the iteration termination condition, a scheme whose fitness exceeds a preset fitness threshold is selected from the target scheme cluster obtained in the last iteration process and used as the target scheduling scheme. The preset fitness threshold is set based on human experience or can be an experimental value obtained through numerous trials; this embodiment does not limit its implementation.

[0101] The aforementioned method for determining the nominal trajectory of an aircraft introduces a scheme fitness during the iteration process. This evaluates the adaptability of each aircraft's nominal trajectory within its respective airspace. By comprehensively considering the adaptability of different aircraft within their respective airspaces, the target scheme cluster corresponding to the previous iteration is iteratively updated. This improves the coordination between the nominal trajectories of different aircraft, causing the target scheme cluster to gradually approach the optimal solution set. From the target scheme cluster representing the optimal solution set obtained in the final iteration, a target scheduling scheme adapted to the current airspace is selected. This improves the adaptability of the aircraft to flight within its respective airspace, thereby avoiding flight conflicts between multiple aircraft and further improving the accuracy and rationality of determining the aircraft's nominal trajectory.

[0102] Based on the technical solutions of the above embodiments, this application also provides an optional embodiment. In this optional embodiment, the target scheme cluster determination step in S130 is refined. See [link to optional embodiment]. Figure 2 The steps for determining the target cluster shown include:

[0103] S210, based on the fitness of each scheduling scheme, select at least one reference scheduling scheme from the target scheme cluster corresponding to the previous iteration process.

[0104] The reference scheduling scheme can be understood as a feasible and referential scheduling scheme to be optimized that is generated during the iteration process.

[0105] In one embodiment, based on the fitness of each scheduling scheme, a scheduling scheme whose fitness exceeds a preset fitness threshold is selected from the target scheme cluster corresponding to the previous iteration process and used as a reference scheduling scheme.

[0106] In another alternative implementation, based on the Non-dominated Sorting Genetic Algorithm II (NSGA-II), the target scheme cluster corresponding to the previous iteration is selected and sorted according to the fitness of each scheduling scheme, resulting in a reference scheme set containing at least one reference scheduling scheme. It should be noted that for any two reference scheduling schemes in the reference scheduling scheme set, the first reference scheduling scheme must be superior to the second reference scheduling scheme in at least one dimension of flight profile information, and the first reference scheduling scheme must be inferior to the second reference scheduling scheme in at most one dimension of flight profile information.

[0107] For example, if scheduling scheme 1 has a total flight time of 10 minutes, total fuel consumption of 50, and flight safety of 30; scheduling scheme 2 has a total flight time of 8 minutes, total fuel consumption of 60, and flight safety of 50; scheduling scheme 3 has a total flight time of 20 minutes, total fuel consumption of 100, and flight safety of 10; and scheduling scheme 4 has a total flight time of 5 minutes, total fuel consumption of 40, and flight safety of 60, it is obvious that scheduling scheme 3 is inferior to scheduling schemes 1, 2, and 4 in all three dimensions of flight profile information (total flight time, total fuel consumption, and flight safety). Therefore, scheduling scheme 3 cannot be used as a reference scheduling scheme. Similarly, scheduling scheme 4 is superior to scheduling schemes 1, 2, and 3 in all three dimensions of flight profile information (total flight time, total fuel consumption, and flight safety). Therefore, scheduling scheme 4 cannot be used as a reference scheduling scheme. Regarding scheduling scheme 1 and scheduling scheme 2, although scheduling scheme 1 is better than scheduling scheme 2 in terms of total fuel consumption, it is inferior to scheduling scheme 2 in terms of total flight time and flight safety. Therefore, both scheduling scheme 1 and scheduling scheme 2 can be used as reference scheduling schemes.

[0108] S220, perform derivative processing on each reference scheduling scheme to update the reference scheduling scheme.

[0109] In this context, derivation processing can be understood as the process of generating a new reference scheduling scheme by transforming, expanding, or optimizing the nominal trajectories of each aircraft in the reference scheduling scheme during the iteration process. Optionally, derivation processing may include at least one of cross-processing, transformation processing, disturbance processing, and annealing simulation processing.

[0110] In one alternative implementation, for each reference scheduling scheme, the nominal track of at least one aircraft in the reference scheduling scheme is extended to obtain a new reference scheduling scheme.

[0111] In another optional implementation embodiment, for each waypoint in each reference scheduling scheme, the number of conflicts in flight conflict situations at the waypoint is determined; waypoints with a conflict number greater than a preset conflict threshold are designated as derivative waypoints; the reference scheduling scheme with derivative waypoints is subjected to derivative processing to update the reference scheduling scheme. Here, a flight conflict can be understood as a conflict that occurs between an aircraft and another aircraft during flight; a flight conflict can include at least one of arrival time conflict and flight collision conflict; an arrival time conflict can be understood as at least two aircraft arriving at the same waypoint at the same time with the same or similar arrival times (e.g., within ±5 minutes); a flight collision conflict can be understood as at least two aircraft overlapping in position at the same time point or the distance between their positions being less than a preset distance threshold (e.g., minimum collision avoidance distance). It should be noted that the preset conflict threshold and preset distance threshold can be set manually based on experience, or they can be experimental values ​​obtained through numerous experiments; this application does not impose any limitations on these. The advantage of this setup is that it selects waypoints with a conflict count greater than a preset conflict threshold, uses these high-conflict waypoints as derivative waypoints, and performs derivative processing on the reference scheduling scheme with derivative waypoints. This prioritizes reducing the probability of flight conflicts at high-conflict waypoints, thereby reducing the number of conflicts at high-conflict waypoints and further improving the accuracy and rationality of the reference scheduling scheme update.

[0112] For example, the method for determining the number of flight conflicts at a waypoint can be as follows: the number of times the arrival time conflicts occur between aircraft at the waypoint is taken as the first conflict number; the number of times the aircraft collide with each other within a preset range (excluding the area to which the waypoint belongs) is taken as the second conflict number; and the number of flight conflicts at the waypoint is determined based on the first conflict number and / or the second conflict number. The preset range can be set based on human experience or it can be an experimental value obtained through numerous experiments; this embodiment does not limit this.

[0113] It should be noted that in this embodiment, the first number of collisions may be taken as the number of flight collisions occurring at the waypoint, or the second number of collisions may be taken as the number of flight collisions occurring at the waypoint, or the sum of the first number of collisions and the second number of collisions may be taken as the number of flight collisions occurring at the waypoint. This embodiment does not limit the specific implementation method.

[0114] For example, the method of determining the number of times that the aircraft arrive at the waypoint conflict with each other as the first conflict count is as follows: obtain the arrival time of each aircraft at the waypoint; determine whether there are aircraft with the same arrival time at the waypoint; if there are aircraft with the same arrival time, determine the number of aircraft with the same arrival time as the first conflict count. For example, if there are three aircraft that all arrive at waypoint 1 at 8:10, then the first conflict count for waypoint 1 is determined to be 3.

[0115] For example, the method of using the number of collisions between aircraft within a preset range (excluding the area to which the waypoint belongs) as the second conflict count is as follows: convert the flight trajectories of each aircraft within the preset range (excluding the area to which the waypoint belongs) into a time point sequence; determine the second conflict count based on the number of time point overlaps and / or the number of time point sequences whose nearest distance is less than a preset distance threshold. For example, only the number of time point overlaps can be used as the second conflict count, or only the number of time point sequences whose nearest distance is less than the preset distance threshold can be used as the second conflict count; or the sum of the number of time point overlaps and the number of time point sequences whose nearest distance is less than the preset distance threshold can be used as the second conflict count. The specific implementation method is not limited in this embodiment.

[0116] For example, the implementation of a reference scheduling scheme with derived path points to update the reference scheduling scheme can be as follows: For a reference scheduling scheme with derived path points, perform derived processing on the derived path points in the reference scheme to update the reference scheduling scheme.

[0117] S230: Based on the updated reference scheduling scheme, generate the target scheme cluster corresponding to this iteration process.

[0118] In one alternative implementation, the updated reference scheduling schemes can be directly merged to obtain the target scheme cluster corresponding to this iteration.

[0119] In another optional implementation, based on the updated reference scheduling scheme, it is determined whether there are still flight conflicts in the reference scheduling scheme; reference scheduling schemes without flight conflicts are merged to obtain the target scheme cluster corresponding to this iteration process.

[0120] In this embodiment, at least one reference scheduling scheme is selected from the target scheme cluster corresponding to the previous iteration process for derivation processing to update the reference scheduling scheme and enhance its adaptability and richness. Based on the updated reference scheduling scheme, a more reasonable target scheme cluster is generated, which provides data support for the subsequent selection of target scheduling schemes from the target scheme cluster, and further improves the accuracy and rationality of the target scheduling scheme determination.

[0121] Based on the technical solutions of the above embodiments, this application also provides an optional embodiment. In this optional embodiment, the reference scheduling scheme update step in S220 is refined. See [link to optional embodiment]. Figure 3 The reference scheduling scheme update steps shown include:

[0122] S310, for each reference scheduling scheme, determines the scheme congestion degree based on the flight conflict between different nominal tracks in the reference scheduling scheme.

[0123] Among them, the congestion level of the scheme can be understood as the airspace conflict risk of each nominal track in the reference scheduling scheme.

[0124] In some embodiments, for each reference scheduling scheme, it is determined whether there are arrival time conflicts and / or flight collision conflicts between different nominal tracks in the reference scheduling scheme; the scheme congestion degree of the reference scheduling scheme is determined based on the number of first conflicts that occur and / or the number of second conflicts that occur.

[0125] For example, in this embodiment, only the first number of conflicts can be used as the congestion level of the solution, or only the second number of conflicts can be used as the congestion level of the solution; or the sum of the first number of conflicts and the second number of conflicts can be used as the congestion level of the solution. The specific implementation method is not limited in this embodiment.

[0126] S320: Based on the congestion level of each reference scheduling scheme, select at least two reference scheduling schemes for cross-processing to update the reference scheduling schemes.

[0127] In some embodiments, the average congestion level among the congestion levels of all reference scheduling schemes is determined; for each reference scheduling scheme, the crossover probability of the reference scheduling scheme is determined based on its scheme congestion level, average congestion level, and a preset crossover probability boundary value; reference scheduling schemes with crossover probabilities greater than a preset probability threshold are selected; and crossover processing is performed on the selected reference scheduling schemes to update the reference scheduling schemes. The preset crossover probability boundary value can be set based on human experience or it can be an experimental value obtained through numerous trials; this embodiment does not limit this.

[0128] For example, based on the reference scheduling scheme, the average congestion level, and the preset crossover probability boundary value, the crossover probability of the reference scheduling scheme is determined by the following formula (1-3).

[0129] (1-3)

[0130] Where, p c p represents the crossover probability of the reference scheduling scheme. Cminp represents the minimum value among the preset crossover probability boundary values ​​(e.g., 0.6); Cmax Characterizes the maximum value (e.g., 0.9) among the preset crossover probability boundary values; d (i) The congestion level of the i-th reference scheduling scheme is represented by d. avg(i) It is the average congestion level of the cluster where the i-th reference scheduling scheme is located.

[0131] For example, the method for selecting a reference scheduling scheme with a crossover probability greater than a preset probability threshold is as follows: Select a reference scheduling scheme with a crossover probability greater than a preset probability threshold; determine the number of selected reference scheduling schemes; if the number of schemes is even, directly execute the subsequent step of crossover processing on each selected reference scheduling scheme to update the reference scheduling scheme; if the number of schemes is odd, randomly select any reference scheduling scheme from the target scheme cluster corresponding to the previous iteration process, so that the number of selected reference scheduling schemes is even, and then execute the subsequent step of crossover processing on each selected reference scheduling scheme to update the reference scheduling scheme.

[0132] For example, when there are no derived waypoints in the reference scheduling scheme, the selected reference scheduling schemes are cross-processed to update the reference scheduling scheme. The implementation method is as follows: the nominal tracks of the same aircraft in the two reference scheduling schemes are randomly cross-processed to update the reference scheduling scheme. For example, the nominal track 1 of aircraft 1 in reference scheduling scheme 1 and the nominal track 2 of aircraft 2 in reference scheduling scheme 2 are cross-processed. Only the arrival times in nominal track 1 and nominal track 2 can be swapped; only the waypoints in nominal track 1 and nominal track 2 can be swapped; or nominal track 1 and nominal track 2 can be swapped completely. The specific implementation method is not limited in this embodiment.

[0133] For example, when there are derived waypoints in the reference scheduling scheme, the cross-processing of the selected reference scheduling schemes to update the reference scheduling scheme is carried out as follows: determine the flight conflict situation of the derived waypoints in the reference scheduling scheme; when the flight conflict situation is an arrival time conflict, cross-process the route paths of the derived waypoints in each reference scheduling scheme that all have arrival time conflicts to update the reference scheduling scheme; when the flight conflict situation is a flight collision conflict, cross-process the arrival times of the derived waypoints in each reference scheduling scheme that all have flight collision conflicts to update the reference scheduling scheme; when the flight conflict situation includes both arrival time conflicts and flight collision conflicts, cross-process the nominal tracks of the derived waypoints in each reference scheduling scheme that all have arrival time conflicts and flight collision conflicts to update the reference scheduling scheme.

[0134] For example, in the case of a flight conflict involving arrival time conflict, the takeoff time of aircraft 1 corresponding to reference scheduling scheme 1 is 8:00, and the route path is 1-2-4-5; the takeoff time of aircraft 2 corresponding to reference scheduling scheme 2 is 8:00, and the route path is 3-4. Therefore, the route paths of aircraft 1 and aircraft 2 can be swapped to obtain that the takeoff time of aircraft 1 corresponding to reference scheduling scheme 1' is 8:00, and the route path is 3-4; the takeoff time of aircraft 2 corresponding to reference scheduling scheme 2' is 8:00, and the route path is 1-2-4-5.

[0135] For example, in the case of a flight conflict that is a flight collision conflict, the takeoff time of aircraft 1 corresponding to reference scheduling scheme 3 is 9:00 and the route is 1-2-4; the takeoff time of aircraft 2 corresponding to reference scheduling scheme 4 is 9:30 and the route is 1-2-4. Therefore, the takeoff times of aircraft 1 and aircraft 2 can be swapped to obtain that the takeoff time of aircraft 1 corresponding to reference scheduling scheme 3' is 9:30 and the route is 1-2-4; the takeoff time of aircraft 2 corresponding to reference scheduling scheme 4' is 9:00 and the route is 1-2-4.

[0136] In this embodiment, the congestion degree of the reference scheduling scheme is introduced. Based on the congestion degree of each reference scheduling scheme, the selected reference scheduling schemes are cross-processed to guide the algorithm to prioritize the resolution of reference scheduling schemes with more severe conflicts. This reduces the probability of flight conflicts in the reference scheduling schemes, reduces the number of flight conflicts in the updated reference scheduling schemes, and further improves the accuracy and rationality of the reference scheduling scheme updates.

[0137] Based on the technical solutions of the above embodiments, this application also provides an optional embodiment. In this optional embodiment, the reference scheduling scheme update step in S220 is refined. See [link to optional embodiment]. Figure 4 The reference scheduling scheme update steps shown include:

[0138] S410, determine the mutated random numbers for each reference scheduling scheme.

[0139] In some embodiments, for each reference scheduling scheme, a random number is randomly generated based on the reference scheduling scheme, and this random number is used as a variant random number of the reference scheduling scheme.

[0140] S410, based on the preset mutation threshold and the relationship between the size of the mutation random numbers of each reference scheduling scheme, select at least one reference scheduling scheme for mutation processing to update the reference scheduling scheme.

[0141] The preset variation threshold can be set based on human experience or it can be a test value obtained through a large number of experiments. This embodiment does not limit this.

[0142] In some embodiments, for each reference scheduling scheme, the mutation probability of the reference scheduling scheme is determined based on a preset mutation threshold and the current iteration number; a reference scheduling scheme with a mutation probability greater than the mutation random number is selected as the scheduling scheme to be mutated; the scheduling scheme to be mutated is mutated to update the reference scheduling scheme.

[0143] For example, based on the preset mutation threshold and the current iteration number, the mutation probability of the reference scheduling scheme is determined by the following formula (1-4).

[0144] (1-4)

[0145] Where, p M Characterizing the mutation probability of the reference scheduling scheme; p Mmin Characterizes the minimum value among the preset variation thresholds (e.g., 0.01); p Mmax The maximum value among the preset mutation thresholds (e.g., 0.1) is represented by `iter`; `iter` represents the current iteration number, and `Max` represents the maximum value among the preset mutation thresholds. iter Represents the maximum number of iterations.

[0146] For example, the method of modifying the proposed mutated scheduling scheme to update the reference scheduling scheme can be as follows: Either any nominal track in the proposed mutated scheduling scheme can be modified randomly to update the reference scheduling scheme. Alternatively, the derived waypoints in the proposed mutated scheduling scheme can be modified based on the flight conflict situations corresponding to the derived waypoints to update the reference scheduling scheme.

[0147] For example, if the flight conflict corresponding to the derived waypoint in the scheduling scheme to be modified is an arrival time conflict, the arrival time of the aircraft to the derived waypoint is modified to update the reference scheduling scheme; if the flight conflict corresponding to the derived waypoint in the scheduling scheme to be modified is a flight collision conflict, the derived waypoint is modified to update the reference scheduling scheme.

[0148] For example, in the case of a flight conflict involving arrival time conflict, if both aircraft 1 and aircraft 2 arrive at derivative waypoint 1 at 8:00, then only the arrival time of aircraft 1 at derivative waypoint 1 can be changed to 8:05; or only the arrival time of aircraft 2 at derivative waypoint 1 can be changed to 8:05; or the arrival time of aircraft 1 at derivative waypoint 1 can be changed to 8:01; or the arrival time of aircraft 1 at derivative waypoint 1 can be changed to 8:05. The specific change method is not specifically limited in this embodiment.

[0149] For example, the mutation process can also be performed by mutating the selected reference scheduling scheme according to the mutated random number using the following formula (1-5).

[0150] (1-5)

[0151] Where, x new Characterizes the reference scheduling scheme after mutation processing; x old The reference scheduling scheme before mutation processing is represented by α; α represents the preset variable time length, and rand represents the mutation random number. It should be noted that the preset variable time length can be set based on human experience or it can be an experimental value obtained through a large number of experiments. This embodiment does not limit this.

[0152] In the above embodiments, based on the preset mutation threshold and the relationship between the size of the mutation random numbers of each reference scheduling scheme, at least one reference scheduling scheme is selected for mutation processing. Priority is given to mutating reference scheduling schemes with more serious conflicts, thereby reducing the probability of flight conflicts in the reference scheduling scheme, reducing the number of flight conflicts in the updated reference scheduling scheme, and further improving the accuracy and rationality of the reference scheduling scheme update.

[0153] Based on the technical solutions of the above embodiments, this application also provides an optional embodiment. In this optional embodiment, the reference scheduling scheme update step in S220 is refined. See [link to optional embodiment]. Figure 5 The reference scheduling scheme update steps shown include:

[0154] S510: For each reference scheduling scheme, the reference scheduling scheme is perturbed to obtain the perturbed scheduling scheme corresponding to the reference scheduling scheme.

[0155] Disturbance handling can be understood as the process of optimizing a reference scheduling scheme by introducing controllable random changes or disturbances.

[0156] In some embodiments, for each reference scheduling scheme, the reference scheduling scheme is subjected to artificial perturbation processing or random noise perturbation processing to obtain the perturbation scheduling scheme corresponding to the reference scheduling scheme.

[0157] S520 determines the suitability of a disturbance scheduling scheme based on the flight profile information of the disturbance scheduling scheme.

[0158] In some embodiments, the method of determining the fitness of a disturbance scheduling scheme based on the flight profile information of the disturbance scheduling scheme is the same as or similar to the method of determining the fitness of the corresponding scheduling scheme based on the flight profile information of each scheduling scheme in the target scheme cluster corresponding to the previous iteration process in the above embodiments. The specific implementation method has been described in detail in the above embodiments, and will not be repeated here.

[0159] S530, based on the fitness of the disturbance scheduling scheme and the fitness of the corresponding reference scheduling scheme, determine the disturbance degree of the disturbance scheduling scheme.

[0160] The degree of disturbance can be understood as a numerical value that quantifies the extent to which the disturbance scheduling scheme handles disturbances.

[0161] In some embodiments, the difference between the fitness of the perturbation scheduling scheme and the fitness of the corresponding reference scheduling scheme is taken as the perturbation degree of the perturbation scheduling scheme.

[0162] S540, based on the degree of disturbance of each disturbance scheduling scheme, select at least one disturbance scheduling scheme to replace the corresponding reference scheduling scheme.

[0163] In some embodiments, for each perturbation scheduling scheme, the reception probability of the perturbation scheduling scheme is determined based on the perturbation degree of the perturbation scheme and the current temperature preset in the current iteration. If the reception probability is greater than a preset probability threshold, the perturbation scheduling scheme replaces the corresponding reference scheduling scheme. The preset probability threshold can be set based on human experience or it can be an experimental value obtained through numerous experiments; this embodiment does not limit this. It should be noted that the current temperature gradually decreases with the number of iterations. Each iteration can decrease the temperature by a fixed value or a random value; the specific degree of temperature reduction is not limited in this embodiment.

[0164] For example, based on the degree of disturbance of the disturbance scheduling scheme and the current temperature preset in the current iteration, the reception probability of the disturbance scheduling scheme is determined by the following formula (1-6).

[0165] (1-6)

[0166] Where P represents the reception probability of the perturbation scheduling scheme; T represents the degree of disturbance in the disturbance scheduling scheme; T represents the preset current temperature in the current iteration process.

[0167] In this embodiment, by perturbing the reference scheduling scheme, the balance in the target scheme cluster corresponding to the previous iteration is broken, thereby improving the convergence speed and distribution uniformity of the reference scheduling scheme in the target scheme cluster, avoiding the occurrence of local optima in the target scheme cluster, assisting the algorithm in exploring the global optimum, and further improving the accuracy and rationality of the reference scheduling scheme update.

[0168] Based on the technical solutions of the above embodiments, this application also provides an optional embodiment. In this optional embodiment, the target scheme cluster determination step in S230 is refined. See [link to optional embodiment]. Figure 6 The steps for determining the target cluster shown include:

[0169] S610 adjusts the nominal tracks with flight conflicts for each reference scheduling scheme to update the reference scheduling scheme.

[0170] In some embodiments, adjusting nominal tracks with flight conflicts to update the reference scheduling scheme may include at least one of the following: adjusting the arrival time of the corresponding aircraft to the conflicting waypoint in the nominal tracks with flight conflicts; generating a new nominal track for the aircraft corresponding to the nominal tracks with flight conflicts; wherein the conflicting waypoint is a waypoint reached by at least two aircraft corresponding to the nominal tracks with flight conflicts during the same time period. The advantage of this setup is that by optimizing the arrival time and route path in the nominal tracks, the adjustment efficiency of the nominal tracks is significantly improved, further enhancing the planning efficiency of the reference scheduling scheme.

[0171] For example, when there are nominal flight paths with flight conflicts in the reference scheduling scheme, the arrival time of the aircraft to the conflict path point is extended by a preset time (e.g., ±10 seconds) to avoid flight conflicts in the nominal flight path. The preset time can be set based on human experience or based on experimental values ​​obtained from numerous experiments. For instance, if the arrival time of both aircraft 1 and aircraft 2 to the conflict path point is 8:00:00, the arrival time of only aircraft 1 can be extended (e.g., 8:00:10); the arrival time of only aircraft 2 can be extended (e.g., 8:00:10); the arrival time of both aircraft 1 and aircraft 2 can also be extended (e.g., 7:59:50). The specific implementation method for extending the arrival time is not limited in this embodiment.

[0172] For example, when there are conflicting nominal tracks in the reference scheduling scheme, the conflicting waypoints in the nominal tracks are replaced to avoid flight conflicts in the nominal tracks. For instance, if the arrival time of both aircraft 1 and aircraft 2 at the conflicting waypoint P2 is 9:00, the conflicting waypoint P2 in nominal track 1 corresponding to aircraft 1 can be replaced only with the conflicting waypoint P3; or the conflicting waypoint P2 in nominal track 2 corresponding to aircraft 2 can be replaced only with the conflicting waypoint P4; or the conflicting waypoint P2 in nominal track 1 corresponding to aircraft 1 can be replaced with the conflicting waypoint P3, and the conflicting waypoint P2 in nominal track 2 corresponding to aircraft 2 can be replaced with the conflicting waypoint P4. The specific implementation method of replacing the conflicting waypoints in the nominal tracks is not limited in this embodiment.

[0173] For example, when there are nominal flight paths with flight conflicts in the reference scheduling scheme, it is determined whether the flight conflict can be avoided by extending the arrival time; if it is determined that the flight conflict can be avoided by extending the arrival time, the arrival time of the aircraft to the conflict path point is extended by a preset time to update the reference scheduling scheme; it is determined whether there are still conflict path points in the updated reference scheduling scheme; if there are no conflict path points in the updated reference scheduling scheme, the update of the reference scheduling scheme is ended; if it is determined that the flight conflict cannot be avoided by extending the arrival time, or if there are still conflict path points in the updated reference scheduling scheme, the conflict path points in the nominal flight paths are replaced, and the reference scheduling scheme is updated again.

[0174] For example, such as Figure 1BThe route network diagram shown is illustrated using a reference scheduling scheme with two aircraft as an example. Aircraft 1's nominal track 1 is [(P1, 8:00:00), (P3, 8:05:00), (P5, 8:20:00)], and aircraft 2's nominal track 2 is [(P1, 8:00:00), (P3, 8:05:00), (P1, 8:25:00)]. Clearly, waypoint P3 is a conflict waypoint. Therefore, in this embodiment, the arrival time of aircraft 1 at waypoint P3 can be preferentially extended by -10 seconds, and the arrival time of aircraft 2 at waypoint P3 can be extended by +10 seconds to avoid flight conflicts in the scheduling scheme. If the adjusted nominal track 1 fails to meet the preset constraints mentioned in S110, it proves that the arrival time of aircraft 1 cannot be adjusted at this time. Therefore, the conflicting waypoints can only be replaced (e.g., replacing the conflicting waypoint P3 in nominal track 1 with waypoint P2), thereby updating the reference scheduling scheme. The updated reference scheduling scheme includes nominal track 1 of aircraft 1 as [(P1,8:00:00),(P3,8:05:10),(P5,8:20:00)], and nominal track 2 of aircraft 2 as [(P1,8:00:00),(P2,8:04:50),(P1,8:25:00)].

[0175] S620 generates the target scheme cluster corresponding to this iteration process based on the updated reference scheduling scheme.

[0176] In some embodiments, the implementation method of generating the target scheme cluster corresponding to the current iteration process according to the updated reference scheduling scheme in this embodiment is the same as or similar to the implementation method of generating the target scheme cluster corresponding to the current iteration process according to the updated reference scheduling scheme in the above embodiment S230. The specific implementation method has been described in detail in the above embodiments, and will not be repeated here.

[0177] In this embodiment, nominal tracks with flight conflicts are adjusted to reduce the probability of flight conflicts in the reference scheduling scheme, thereby reducing the number of flight conflicts in the updated reference scheduling scheme and further improving the accuracy and rationality of the reference scheduling scheme update. Furthermore, by performing local replanning only on a portion of the nominal tracks in the reference scheduling scheme, the complexity of the reference scheduling scheme update is reduced, ensuring the algorithm's real-time performance and efficiency.

[0178] To facilitate understanding of this solution by those skilled in the art, the method for determining the nominal trajectory of the aircraft provided in this application is described in detail. See [link to relevant documentation]. Figure 7 The method for determining the nominal trajectory of the aircraft shown includes:

[0179] S710, obtain the initial cluster plan.

[0180] The initial scheme cluster includes at least one scheduling scheme; the scheduling scheme includes at least one nominal track of an aircraft in its flight airspace.

[0181] S720: For each iteration, the fitness weight of the corresponding scheduling scheme is determined based on the airspace congestion degree of each scheduling scheme in the target scheme cluster corresponding to the previous iteration.

[0182] Among them, the target scheme cluster corresponding to the first iteration process is the initial scheme cluster.

[0183] S730 determines the fitness of each scheduling scheme based on the fitness weight of each scheme and flight profile information.

[0184] S740: Based on the fitness of each scheduling scheme, select at least one reference scheduling scheme from the target scheme cluster corresponding to the previous iteration process.

[0185] S750 performs derivative processing on each reference scheduling scheme to update the reference scheduling scheme.

[0186] In one optional embodiment, the reference scheduling schemes are subjected to derivative processing to update the reference scheduling schemes, including: for each reference scheduling scheme, determining the scheme congestion degree of the reference scheduling scheme based on the flight conflict between different nominal tracks in the reference scheduling scheme; and selecting at least two reference scheduling schemes for cross processing based on the scheme congestion degree of each reference scheduling scheme to update the reference scheduling schemes.

[0187] In another optional embodiment, a derivation process is performed on each reference scheduling scheme to update the reference scheduling scheme, including: determining the mutation random number of each reference scheduling scheme; selecting at least one reference scheduling scheme for mutation processing according to a preset mutation threshold and the size relationship of the mutation random numbers of each reference scheduling scheme to update the reference scheduling scheme; wherein, the preset mutation threshold is determined based on the current iteration number and the mutation probability boundary value.

[0188] In another optional embodiment, a derivation process is performed on each reference scheduling scheme to update the reference scheduling scheme, including: for each reference scheduling scheme, a perturbation process is applied to the reference scheduling scheme to obtain a perturbation scheduling scheme corresponding to the reference scheduling scheme; the scheme fitness of the perturbation scheduling scheme is determined based on the flight profile information of the perturbation scheduling scheme; the perturbation degree of the perturbation scheduling scheme is determined based on the scheme fitness of the perturbation scheduling scheme and the scheme fitness of the corresponding reference scheduling scheme; and at least one perturbation scheduling scheme is selected to replace the corresponding reference scheduling scheme based on the perturbation degree of each perturbation scheduling scheme.

[0189] It should be noted that the derivation processing of each reference scheduling scheme in this embodiment includes at least one of the following: cross-processing, mutation processing, and perturbation processing. In this embodiment, only one of the cross-processing, mutation, or perturbation processing methods can be performed on each reference scheduling scheme individually to update the reference scheduling scheme; any two of the cross-processing, mutation, or perturbation processing methods can be selected to update the reference scheduling scheme; or all of the cross-processing, mutation, or perturbation processing methods can be selected to update the reference scheduling scheme. Where at least two derivation processing methods are selected to update the reference scheduling scheme, this application does not limit the order in which the derivation processes are performed.

[0190] S760 adjusts the nominal tracks with flight conflicts for each reference scheduling scheme to update the reference scheduling scheme.

[0191] In some embodiments, adjusting the nominal tracks with flight conflicts to update the reference scheduling scheme includes at least one of the following: adjusting the arrival time of the corresponding aircraft to the conflict waypoint in the nominal tracks with flight conflicts; generating a new nominal track for the aircraft corresponding to the nominal tracks with flight conflicts; wherein the conflict waypoint is the waypoint reached by at least two aircraft corresponding to the nominal tracks with flight conflicts in the same time period.

[0192] S770 generates the target scheme cluster corresponding to this iteration process based on the updated reference scheduling scheme.

[0193] S780: If the current iteration process meets the iteration termination condition, select a target scheduling scheme from the target scheme cluster obtained from the last iteration process.

[0194] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0195] Based on the same inventive concept, this application also provides a nominal trajectory determination device for implementing the nominal trajectory determination method for the aforementioned aircraft. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations of one or more nominal trajectory determination device embodiments for aircraft provided below can be found in the limitations of the nominal trajectory determination method for aircraft described above, and will not be repeated here.

[0196] In one exemplary embodiment, such as Figure 8 As shown, a nominal trajectory determination device for an aircraft is provided, comprising: an acquisition module 10, a determination module 20, an update module 30, and a selection module 40, wherein:

[0197] The acquisition module 810 is used to acquire an initial scheme cluster; wherein, the initial scheme cluster includes at least one scheduling scheme; the scheduling scheme includes at least one nominal track of an aircraft in its flight airspace;

[0198] The determination module 820 is used to determine the fitness of the corresponding scheduling scheme for each iteration process based on the flight profile information of each scheduling scheme in the target scheme cluster corresponding to the previous iteration process.

[0199] The update module 830 is used to update the target scheme cluster corresponding to the previous iteration process based on the scheme fitness of each scheduling scheme to obtain the target scheme cluster corresponding to the current iteration process; wherein, the target scheme cluster corresponding to the first iteration process is the initial scheme cluster.

[0200] Module 840 is selected to select a target scheduling scheme from the target scheme cluster obtained in the last iteration process, provided that the iteration termination condition is met in the current iteration process.

[0201] In some embodiments, the update module 830 includes: a reference selection unit, configured to select at least one reference scheduling scheme from the target scheme cluster corresponding to the previous iteration process based on the scheme fitness of each scheduling scheme; a reference update unit, configured to perform derivation processing on each reference scheduling scheme to update the reference scheduling scheme; and a target determination unit, configured to generate the target scheme cluster corresponding to the current iteration process based on the updated reference scheduling scheme.

[0202] In some embodiments, the reference update unit is further configured to determine the number of flight conflicts at each waypoint in each reference scheduling scheme; designate waypoints with a number of conflicts greater than a preset conflict threshold as derivative waypoints; and perform derivative processing on reference scheduling schemes with derivative waypoints to update the reference scheduling scheme.

[0203] In some embodiments, the reference update unit is further configured to determine the congestion level of each reference scheduling scheme based on the flight conflict between different nominal tracks in the reference scheduling scheme; and to select at least two reference scheduling schemes for cross-processing based on the congestion level of each reference scheduling scheme in order to update the reference scheduling scheme.

[0204] In some embodiments, the reference update unit is further configured to determine the mutation random number of each reference scheduling scheme; and select at least one reference scheduling scheme for mutation processing according to a preset mutation threshold and the relationship between the size of the mutation random numbers of each reference scheduling scheme, so as to update the reference scheduling scheme; wherein, the preset mutation threshold is determined based on the current iteration number and the mutation probability boundary value.

[0205] In some embodiments, the reference update unit is further configured to: perform disturbance processing on each reference scheduling scheme to obtain a disturbance scheduling scheme corresponding to the reference scheduling scheme; determine the scheme fitness of the disturbance scheduling scheme based on the flight profile information of the disturbance scheduling scheme; determine the disturbance degree of the disturbance scheduling scheme based on the scheme fitness of the disturbance scheduling scheme and the scheme fitness of the corresponding reference scheduling scheme; and select at least one disturbance scheduling scheme to replace the corresponding reference scheduling scheme based on the disturbance degree of each disturbance scheduling scheme.

[0206] In some embodiments, the target determination unit is further configured to adjust the nominal tracks with flight conflicts for each reference scheduling scheme to update the reference scheduling scheme; and generate a target scheme cluster corresponding to the current iteration process based on the updated reference scheduling scheme.

[0207] In some embodiments, the target determination unit is further configured to adjust the arrival time of the corresponding aircraft to the conflict path point in the nominal track with flight conflict; and generate a new nominal track for the aircraft corresponding to the nominal track with flight conflict; wherein the conflict path point is the path point reached by at least two aircraft corresponding to the nominal track with flight conflict in the same time period.

[0208] In some embodiments, the determining module 820 is further configured to, for each scheduling scheme in the target scheme cluster corresponding to the previous iteration process, determine the fitness weight based on the airspace congestion degree corresponding to the scheduling scheme; and determine the scheme fitness of the scheduling scheme based on the fitness weight and flight profile information.

[0209] The modules in the nominal trajectory determination device of the aforementioned aircraft can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0210] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When executed by the processor, the computer program implements a method for determining the nominal trajectory of an aircraft.

[0211] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0212] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0213] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0214] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0215] It should be noted that the data involved in this application (including but not limited to data used for analysis, data stored, data displayed, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0216] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0217] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0218] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining the nominal trajectory of an aircraft, characterized in that, The method includes: Obtain an initial scheme cluster; wherein the initial scheme cluster includes at least one scheduling scheme; the scheduling scheme includes at least one nominal track of an aircraft in its flight airspace; For each iteration, the fitness of the corresponding scheduling scheme is determined based on the flight profile information of each scheduling scheme in the target scheme cluster corresponding to the previous iteration. Based on the fitness of each scheduling scheme, the target scheme cluster corresponding to the previous iteration is updated to obtain the target scheme cluster corresponding to the current iteration; wherein, the target scheme cluster corresponding to the first iteration is the initial scheme cluster. If the current iteration process meets the iteration termination condition, a target scheduling scheme is selected from the target scheme cluster obtained from the last iteration process.

2. The method according to claim 1, characterized in that, The step of updating the target scheme cluster corresponding to the previous iteration process based on the scheme fitness of each of the scheduling schemes to obtain the target scheme cluster corresponding to the current iteration process includes: Based on the fitness of each scheduling scheme, at least one reference scheduling scheme is selected from the target scheme cluster corresponding to the previous iteration process; Each of the aforementioned reference scheduling schemes is subjected to derivative processing to update the reference scheduling scheme; Based on the updated reference scheduling scheme, generate the target scheme cluster corresponding to this iteration process.

3. The method according to claim 2, characterized in that, The step of performing derivative processing on each of the reference scheduling schemes to update the reference scheduling scheme includes: For each waypoint in each reference scheduling scheme, determine the number of conflicts in the flight conflict situation at the waypoint; The path points with a conflict count greater than a preset conflict threshold are designated as derived path points; The reference scheduling scheme with the aforementioned derivative path points is subjected to derivative processing to update the reference scheduling scheme.

4. The method according to claim 2 or 3, characterized in that, The step of performing derivative processing on each of the reference scheduling schemes to update the reference scheduling scheme includes: For each reference scheduling scheme, the scheme congestion degree is determined based on the flight conflict between different nominal tracks in the reference scheduling scheme. Based on the congestion level of each reference scheduling scheme, at least two reference scheduling schemes are selected for cross-processing to update the reference scheduling schemes.

5. The method according to claim 2 or 3, characterized in that, Each of the aforementioned reference scheduling schemes undergoes a derivative process to update the reference scheduling scheme, including: Determine the mutated random number for each of the aforementioned reference scheduling schemes; Based on the preset mutation threshold and the relationship between the size of the mutation random numbers of each reference scheduling scheme, at least one reference scheduling scheme is selected for mutation processing to update the reference scheduling scheme; wherein, the preset mutation threshold is determined based on the current iteration number and the mutation probability boundary value.

6. The method according to claim 2 or 3, characterized in that, Each of the aforementioned reference scheduling schemes undergoes a derivative process to update the reference scheduling scheme, including: For each of the reference scheduling schemes, the reference scheduling schemes are perturbed to obtain the perturbed scheduling schemes corresponding to the reference scheduling schemes. Based on the flight profile information of the disturbance scheduling scheme, determine the scheme fitness of the disturbance scheduling scheme; The degree of disturbance of the disturbance scheduling scheme is determined based on the scheme fitness of the disturbance scheduling scheme and the scheme fitness of the corresponding reference scheduling scheme. Based on the degree of disturbance of each disturbance scheduling scheme, at least one disturbance scheduling scheme is selected to replace the corresponding reference scheduling scheme.

7. The method according to claim 2, characterized in that, The step of generating the target scheme cluster corresponding to this iteration process based on the updated reference scheduling scheme includes: For each of the aforementioned reference scheduling schemes, the nominal tracks with flight conflicts are adjusted to update the reference scheduling scheme; Based on the updated reference scheduling scheme, generate the target scheme cluster corresponding to this iteration process.

8. The method according to claim 7, characterized in that, The nominal track includes the aircraft's flight path and arrival time at waypoints; adjusting the nominal track with flight conflicts to update the reference scheduling scheme includes at least one of the following: Adjust the arrival time of the corresponding aircraft to the conflict path point in the nominal flight path where there is a flight conflict; For aircraft whose nominal tracks conflict with each other, generate new nominal tracks; The conflict waypoints are the waypoints reached by at least two aircraft at the same time period corresponding to the nominal flight paths of the flight conflict.

9. The method according to claim 1, characterized in that, The step of determining the fitness of a scheduling scheme based on the flight profile information of each scheduling scheme in the target scheme cluster corresponding to the previous iteration includes: For each scheduling scheme in the target scheme cluster corresponding to the previous iteration, the fitness weight is determined based on the airspace congestion degree corresponding to the scheduling scheme. The fitness of the scheduling scheme is determined based on the fitness weight and the flight profile information.

10. A device for determining the nominal trajectory of an aircraft, characterized in that, The device includes: An acquisition module is used to acquire an initial scheme cluster; wherein the initial scheme cluster includes at least one scheduling scheme; the scheduling scheme includes at least one nominal track of an aircraft in its flight airspace; The determination module is used to determine the fitness of the corresponding scheduling scheme for each iteration process based on the flight profile information of each scheduling scheme in the target scheme cluster corresponding to the previous iteration process. The update module is used to update the target scheme cluster corresponding to the previous iteration process according to the scheme fitness of each of the scheduling schemes, so as to obtain the target scheme cluster corresponding to the current iteration process; wherein, the target scheme cluster corresponding to the first iteration process is the initial scheme cluster. The selection module is used to select a target scheduling scheme from the target scheme cluster obtained in the last iteration process, provided that the iteration termination condition is met in the current iteration process.

11. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

Images