Method and device for obtaining digital twinborn bodies in airport flying area and medium

Abstract

The invention provides an airport flight area digital twinborn body obtaining method and device and a medium, and relates to the technical field of digital twinborn, and the method comprises the steps: obtaining physical facility data, device state data and operation data of a target airport flight area, building a three-dimensional geometric model based on the collected object facility data and device state data, and obtaining the digital twinborn body of the target airport flight area; and based on the three-dimensional geometric model, performing dynamic simulation on the operation data in the flight area, and determining a target digital twin model, thereby realizing automatic and efficient management of the aircraft flight area.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to a method, device and medium for acquiring a digital twin of an airport flight area. Background Art

[0002] As a key hub for air transportation, airports are growing in size and number, and their functions are becoming increasingly complex and diverse. Digital twin technology, as a key technology, has been applied in the airport field. Wang Jiamian studied the check-in service system of the airport terminal. He used digital twin technology to determine the key factors affecting check-in efficiency, establish a simulation model, and use an improved genetic algorithm for optimization to achieve the goal of minimizing queuing waiting time. Conde J et al. proposed an airport digital twin reference concept and data model based on FIWARE universal enabler and next-generation service interface-linked data standards to improve the efficiency of flight turnaround events.

[0003] Although digital twin technology is increasingly being used in the civil aviation field, its application in airport flight zones is still in its infancy and faces many challenges, such as the difficulty of technical implementation, low data utilization value, and unsatisfactory simulation software. Research on conflict detection and avoidance of aircraft in airport flight zones is of particular concern.

[0004] As the core area of ​​an airport, the airfield undertakes important functions such as aircraft take-off and landing, taxiing, parking, and ground traffic organization. Its complexity and importance require managers to master detailed and accurate geospatial information and the status of facilities and equipment. Traditional management methods often rely on two-dimensional drawings and manual inspections, which are difficult to meet the efficient and safe management needs of modern airports. Summary of the invention

[0005] In view of the above technical problems, the technical solution adopted by the present invention is: a method for obtaining a digital twin of an airport flight area, the method comprising the following steps: S100, obtaining physical facility data, equipment status data and operation data of the flight area of ​​the target airport; S200, creating a three-dimensional geometric model based on the collected physical facility data and equipment status data; S300, based on the 3D geometric model, dynamically simulates the operation data in the flight zone and generates a target digital twin model; Among them, the target digital twin model includes a target module, which performs the following steps to realize conflict detection of the target aircraft: S410, obtaining current flight data of the target aircraft flying at the current time node, wherein the current flight data at least includes: current position coordinates (x, y, z), current speed v, and current motion direction θ; wherein x is the value of the longitude and latitude values ​​of the position of the target aircraft at the current time node converted into the horizontal axis of the plane rectangular coordinate, y is the value of the longitude and latitude values ​​of the position of the target aircraft at the current time node converted into the vertical axis of the plane rectangular coordinate, and z is the flight altitude of the target aircraft flying at the current time node; S420, generating an initial protective cover based on the current flight data of the target aircraft, wherein the initial protective cover for predicting the target aircraft conflict is an initial polygon centered at the current position coordinates (x, y, z) and surrounding the target aircraft, wherein the i-th initial vertex A of the initial polygon is i Meet the following requirements: A i =(x+r i cos(θ+α i ), y+r i sin(θ+α i ), i ranges from 1 to m, where m is the number of initial vertices of the initial polygon; r i is the preset radius of the i-th initial vertex, and the i-th preset angle α i Yes A i The angle formed by connecting the origin in the specified rectangular coordinate system, wherein the specified rectangular coordinate system has the center of gravity of the target aircraft as the origin, the current direction of movement as the X-axis, and the current direction of movement rotated 90 degrees clockwise as the Y-axis; S430, inputting the current flight data and the initial protection cover of the target aircraft into the target machine learning model, obtaining an initial conflict result and obtaining a target conflict type based on the initial conflict result, wherein the target conflict type is a wake conflict, a head-on conflict or a cross conflict; S440, based on the initial collision result and the target collision type, obtaining the predicted collision position of the target aircraft and increasing the number of vertices of the initial protective cover corresponding to the predicted collision position, thereby obtaining an intermediate protective cover; wherein the shapes of the intermediate protective covers corresponding to different predicted collision positions are different; S450, input the current flight data and intermediate protection cover of the target aircraft into the target machine learning model to obtain the target conflict result.

[0006] According to another aspect of the present invention, a non-transitory computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the aforementioned method.

[0007] According to yet another aspect of the present invention, an electronic device is provided, comprising a processor and the aforementioned non-transitory computer-readable storage medium.

[0008] The present invention has at least the following beneficial effects: obtaining physical facility data, equipment status data and operation data of the flight zone of the target airport, creating a three-dimensional geometric model based on the collected object facility data and equipment status data, dynamically simulating the operation data in the flight zone based on the three-dimensional geometric model, determining the target digital twin model, obtaining the current flight data of the target aircraft flying at the current time node, generating an initial protective cover based on the current flight data of the target aircraft, inputting the current flight data and the initial protective cover of the target aircraft into the target machine learning model, obtaining the initial conflict result and obtaining the target conflict type based on the initial conflict result, obtaining the predicted collision position of the target aircraft based on the initial conflict result and the target conflict type and increasing the number of vertices of the initial protective cover corresponding to the predicted collision position, thereby obtaining an intermediate protective cover, inputting the current flight data and the intermediate protective cover of the target aircraft into the target machine learning model, obtaining the target conflict result, and improving the accuracy of aircraft conflict identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A flowchart of a method for acquiring a digital twin of an airport flight area provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0011] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0012] The embodiment of the present invention provides a method for obtaining a digital twin of an airport flight area, such as Figure 1 As shown, the method comprises the following steps: S100, obtaining physical facility data, equipment status data and operation data of the flight area of ​​the target airport.

[0013] The physical facility data include: geographic information data of airfield runways, taxiways, aprons, aviation buildings, and parking lots; the physical facility data also include attribute data of boarding bridges, baggage handling equipment, aircraft, tractors and other facilities.

[0014] The device status information includes status information of pressure sensors, voltage sensors, current sensors, etc.

[0015] Among them, the operating data includes flight information data, traffic flow data, passenger flow data, etc. The flight information data includes flight schedule, flight dynamics (take-off time, landing time, boarding gate changes, etc.) data; the traffic flow data includes traffic flow, speed and driving path data of aircraft and ground vehicles (tractors, shuttle buses, luggage trucks, etc.).

[0016] S200, creating a three-dimensional geometric model based on the collected physical facility data and equipment status data.

[0017] Specifically, those skilled in the art know that any method of creating a three-dimensional geometric model based on data in the prior art falls within the scope of protection of the present invention, such as using CAD software or professional three-dimensional modeling software such as 3ds Max to create a three-dimensional geometric model.

[0018] S300, based on the three-dimensional geometric model, dynamically simulates the operating data in the flight zone to determine the target digital twin model.

[0019] In summary, the physical facility data, equipment status data and operation data of the target airport flight zone are obtained, and a three-dimensional geometric model is created based on the collected object facility data and equipment status data. Based on the three-dimensional geometric model, the operation data in the flight zone is dynamically simulated to determine the target digital twin model, thereby realizing automated and efficient management of the aircraft flight zone.

[0020] Among them, the target digital twin model includes a target module, which performs the following steps to realize conflict detection of the target aircraft: S410, obtaining the current flight data of the target aircraft currently flying at the current time node, wherein the current flight data at least includes: current position coordinates (x, y, z), current speed v, and current movement direction θ; wherein x is the value on the horizontal axis of the longitude and latitude values ​​of the position of the target aircraft at the current time node converted into plane rectangular coordinates, y is the value on the vertical axis of the longitude and latitude values ​​of the position of the target aircraft at the current time node converted into plane rectangular coordinates, and z is the flight altitude of the target aircraft currently flying at the current time node.

[0021] Specifically, the current flight data is acquired based on ADS-B broadcast. Those skilled in the art know that any method of converting longitude and latitude values ​​into rectangular coordinates in the prior art belongs to the protection scope of the present invention and will not be described in detail here.

[0022] S420, generating an initial protective cover based on the current flight data of the target aircraft, wherein the initial protective cover for predicting the target aircraft conflict is an initial polygon centered at the current position coordinates (x, y, z) and surrounding the target aircraft, wherein the i-th initial vertex A of the initial polygon is i Meet the following requirements: A i =(x+r i cos(θ+α i ), y+r i sin(θ+α i ), z), i ranges from 1 to m, where m is the number of initial vertices of the initial polygon; r i is the preset radius of the i-th initial vertex, and the i-th preset angle α i Yes A i The angle formed by connecting the origin in the specified rectangular coordinate system, wherein the specified rectangular coordinate system has the center of gravity of the target aircraft as the origin, the current direction of movement as the X-axis, and the current direction of movement rotated 90 degrees clockwise as the Y-axis.

[0023] Specifically, the aircraft model and the protective cover parameter data corresponding to the aircraft model are obtained, and the protective cover parameter data includes: the number of vertices, the preset radius corresponding to each vertex, and the preset angle corresponding to each vertex. By obtaining the model of the target aircraft, the protective cover parameter data m, α corresponding to the target aircraft are obtained. i and r i .

[0024] Specifically, the initial protection cover is a geometric area defined around the aircraft, which is used to represent the safety range of the aircraft. When other aircraft or objects enter the initial protection cover, it is considered that there is a risk of collision.

[0025] In one embodiment of the present invention, m=6. The hexagon can better fit the outline of the aircraft, especially when considering the extension range of the leading edge and the trailing edge of the wing of the aircraft. For example, the front and rear vertices of the hexagon can be determined according to the fuselage length and the safety buffer distance of the aircraft, while the vertices on the left and right sides can be set according to the wingspan and the safety buffer distance, and the oblique sides can consider the potential influence range of the leading edge and the trailing edge of the wing of the aircraft.

[0026] S430, inputting the current flight data and the initial protection cover of the target aircraft into the target machine learning model, obtaining the initial conflict result and obtaining the target conflict type based on the initial conflict result, wherein the target conflict type is a wake conflict, a head-on conflict or a cross conflict. Specifically, the target machine learning model is a target support vector machine model.

[0027] Specifically, when the initial conflict result is in a conflict operation state, the target conflict type is obtained based on the conflict result. Further, if the movement directions of the two conflicting aircraft are the same and the rear aircraft enters the wake area of ​​the front aircraft, the target conflict type is determined to be a wake conflict; if the movement directions of the two conflicting aircraft are opposite and they are close to each other, the target conflict type is determined to be a head-on conflict; if the movement trajectories of the two conflicting aircraft intersect at a certain point, the target conflict type is determined to be a cross conflict.

[0028] Specifically, S430 also includes: when the initial conflict result is in a normal operation state, waiting for the next time node to execute S410.

[0029] S440, based on the initial collision result and the target collision type, obtain the predicted collision position of the target aircraft and increase the number of vertices of the initial protective cover corresponding to the predicted collision position, thereby obtaining an intermediate protective cover; wherein the shapes of the intermediate protective covers corresponding to different predicted collision positions are different. Specifically, after determining the predicted collision position and the number of increased vertices, in one embodiment of the present invention, the increased vertices are added to the predicted collision position according to a preset increase rule, thereby obtaining an intermediate protective cover. The preset increase rule can be determined according to actual conditions, for example, the increased vertices are evenly distributed based on (x, y).

[0030] S450, input the current flight data and intermediate protection cover of the target aircraft into the target machine learning model to obtain the target conflict result.

[0031] In summary, the current flight data of the target aircraft flying at the current time node is obtained, an initial protective cover is generated based on the current flight data of the target aircraft, the current flight data and the initial protective cover of the target aircraft are input into the target machine learning model, the initial conflict result is obtained, and the target conflict type is obtained based on the initial conflict result, based on the initial conflict result and the target conflict type, the predicted collision position of the target aircraft is obtained and the number of vertices of the initial protective cover corresponding to the predicted collision position is increased, so as to obtain an intermediate protective cover, the current flight data and the intermediate protective cover of the target aircraft are input into the target machine learning model, and the target conflict result is obtained. The present invention further determines the target conflict result by increasing the number of vertices of the initial protective cover corresponding to the predicted collision position, thereby improving the accuracy of aircraft conflict identification without increasing too much data.

[0032] Furthermore, S440 also includes: S441, when the target conflict type is a wake conflict and the predicted collision position of the target aircraft is the tail of the aircraft, the shape of the intermediate protective cover at the tail of the target aircraft is a first preset shape and the number of vertices n of the intermediate protective cover at the tail of the aircraft meets the following requirements: n=n0+ceil(k×v / av), wherein the first preset shape is determined based on the shape of the tail of the aircraft, n0 is the initial number of vertices of the initial protective cover at the tail of the aircraft, k is a speed influencing parameter, av is a preset average speed, and ceil() is a rounding-up function.

[0033] S442, when the target conflict type is a head-on conflict, the shape of the intermediate protective cover at the head of the target aircraft is a second preset shape and the number of vertices q of the intermediate protective cover at the head of the aircraft meets the following requirements: q=q0+ceil(k×v / av), wherein the second preset shape is determined based on the shape of the head of the aircraft, and q0 is the initial number of vertices of the initial protective cover at the head of the aircraft.

[0034] S443, when the target conflict type is an intersection conflict, the intersection angle φ of the target aircraft is obtained based on the current flight data, and the predicted collision position of the target aircraft is determined based on the intersection angle φ, the shape of the intermediate protective cover at the predicted collision position is a third preset shape and the number of vertices of the intermediate protective cover at the predicted collision position is greater than the initial number of vertices corresponding to the initial protective cover at the predicted collision position, wherein the third preset shape is determined based on the predicted collision position, wherein the intersection angle φ is the angle formed by the current flight direction of the target aircraft and the current flight direction of the conflicting aircraft, and the conflicting aircraft is the aircraft that conflicts with the target aircraft in the initial conflict result.

[0035] Furthermore, S441 also includes: the number p of vertices of the intermediate protective cover at the aircraft head meets the following requirement: p=q0-ceil(k×v / av).

[0036] In summary, when the target conflict type is wake conflict and the predicted collision position of the target aircraft is the tail of the aircraft, the number of vertices of the protective cover corresponding to the tail of the aircraft is increased, and the number of vertices of the protective cover corresponding to the tail of the aircraft is reduced; when the target conflict type is head-on conflict, the number of vertices of the protective cover corresponding to the head of the aircraft is increased; when the target conflict type is crossing conflict, the crossing angle φ of the target aircraft is obtained based on the current flight data, and the predicted collision position of the target aircraft is determined based on the crossing angle φ, and the number of vertices n of the protective cover corresponding to the predicted collision position is increased.

[0037] Furthermore, the time interval t between the next time node and the current time node satisfies the following condition: t=α / (β+γ×ED), wherein α is a preset basic time interval, β is a preset adjustment coefficient, γ is a preset event density influence coefficient, ED is the number of conflicts occurring to the target aircraft per unit time, and β<1, γ<1.

[0038] Optional, α=0.1, β=0.05, γ=0.01.

[0039] Specifically, the target machine learning model is obtained through the following steps: S001, obtaining sample flight data of several sample aircraft and the actual conflict results corresponding to the sample flight data, wherein the sample flight data at least includes: sample position coordinates (x0, y0, z0), sample speed v0, and sample motion direction θ0. Among them, x0 is the value on the horizontal axis of the longitude and latitude values ​​of the sample aircraft at the sample time node converted into the plane rectangular coordinates, y0 is the value on the vertical axis of the longitude and latitude values ​​of the sample aircraft at the sample time node converted into the plane rectangular coordinates, and z is the flight altitude of the sample aircraft at the sample time node.

[0040] S002, based on the sample flight data of the sample aircraft, a sample protection cover is generated, wherein the sample protection cover is a sample polygon surrounding the target aircraft based on the sample position coordinates (x0, y0, z0), and the jth sample vertex B of the sample polygon j Meet the following requirements: B j =(x0+r 0j cos(θ0+α 0j ), y0+r 0j sin(θ0+α 0j )、z0);r 0j is the preset radius of the i-th sample vertex, and the i-th preset angle α 0j It is B j The angle formed by connecting the origin in the rectangular coordinates of the plane. The value of j ranges from 1 to n, where n is the number of sample vertices.

[0041] Specifically, based on the aircraft model and the protective cover parameter data corresponding to the aircraft model, the protective cover parameter data n, α corresponding to the sample aircraft are obtained. 0j and r 0j .

[0042] S003, construct a machine learning model, and use sample flight data, sample protection cover and actual conflict results to train the constructed machine learning model to obtain sample training results.

[0043] S004: If the sample training results meet the preset training requirements, the trained machine learning model is used as the target machine learning model.

[0044] Specifically, the preset training requirements can be set according to actual needs.

[0045] In summary, sample flight data of several sample aircraft and actual conflict results corresponding to the sample flight data are obtained, and a sample protective cover is generated based on the sample flight data of the sample aircraft to construct a machine learning model. The constructed machine learning model is trained using the sample flight data, the sample protective cover, and the actual conflict results to obtain sample training results. If the sample training results meet the preset training requirements, the trained machine learning model is used as the target machine learning model.

[0046] In a specific embodiment of the present invention, the specific implementation strategy after the conflict occurs includes: In a wake conflict, when one of the two aircraft enters the section, the aircraft acts as the master aircraft. When the second aircraft enters the section, the distance between the second aircraft and the first aircraft is detected in real time. When the distance is less than the safe distance, the second aircraft slows down and stops until the distance is greater than the safe distance. The second aircraft starts to move forward until one of the two aircraft leaves the wake monitoring area and the monitoring ends. When multiple aircraft are following at the same time, the nearest master aircraft controls the following aircraft; when a wake conflict is detected, the following aircraft needs to accurately calculate the safe deceleration range based on factors such as the distance from the leading aircraft, the model of the leading aircraft, and the current meteorological conditions. For example, if the leading aircraft is a large passenger aircraft, the wake vortex it generates is stronger, and the following aircraft may need to decelerate more significantly. In general, the deceleration range of the following aircraft can be between 5 and 15 knots. The specific value is obtained through the wake intensity calculation model, which comprehensively considers the influence of the wingspan, engine thrust, flight altitude and other parameters of the leading aircraft on the wake intensity. During the deceleration process, the following aircraft should maintain a stable deceleration rate to avoid other risks caused by sudden braking or excessive deceleration. At the same time, the distance to the front aircraft is continuously monitored. Once the distance returns to a safe range, the following aircraft can gradually resume normal taxiing speed. The speed recovery rate also needs to be controlled according to airport regulations and actual conditions, generally not exceeding 5 knots per second.

[0047] In a head-on collision, when one of the two aircraft enters the road section, the aircraft acts as the master aircraft and monitors the second aircraft in real time to see if it is too close to the monitored road section. When the distance is less than a certain threshold, the second aircraft slows down and stops until the master aircraft leaves the monitoring area. The monitoring ends and the second aircraft is released. When multiple aircraft collide head-on at the same time, the master aircraft controls all subsequent aircraft and queues up to pass through the road section.

[0048] In a crossing conflict, when one of the two aircraft enters the section, the aircraft acts as the master aircraft and monitors in real time whether the second aircraft is too close to the monitored section. When the distance is less than a certain threshold, the second aircraft slows down and stops until the master aircraft leaves the monitoring area, then the monitoring ends and the second aircraft is released. When multiple aircraft encounter a crossing conflict at the same time, the master aircraft controls all subsequent aircraft to queue up to pass through the section. In particular, due to the shortness of some taxiways, intersections may merge, and the two intersections will be treated as one intersection, making them exclusive. When a head-on conflict or a crossing conflict occurs, the relevant aircraft or vehicles must stop immediately or slow down to the minimum safe speed. For example, when an aircraft conflicts near the intersection of a runway and a taxiway, the speed should be reduced to 0 knots or maintained at an extremely low idle speed (such as less than 5 knots) in the shortest time to ensure that no collision occurs in the conflict area. The decision to stop or slow down is based on the relative position of the conflicting parties, the speed vector, and the safety threshold set in advance by the airport. Through precise calculation models, the conflict risk is evaluated in real time, and once the risk exceeds the safety threshold, a stop or deceleration instruction is immediately triggered.

[0049] Specifically, when the conflict cannot be resolved by speed adjustment, the system quickly starts path replanning. The replanned path selection is based on a comprehensive analysis of the real-time traffic conditions of the entire airport flight area, including the location, movement direction, speed of other aircraft and vehicles, and the occupancy of runways and taxiways. Using the Dijkstra algorithm or A Advanced path planning algorithms, such as the ROI algorithm, search for alternative paths in the airport's topological map. These algorithms take into account factors such as the length of the path, the degree of congestion, and the intersection with other traffic flows to find the optimal conflict-free path. For example, during peak hours, paths with less traffic and higher taxiway grades are given priority to improve taxiing efficiency. Path replanning must strictly follow the airport's facility layout and operating rules. For example, avoid directing aircraft to taxiways that are under maintenance or closed, and ensure that navigation facilities and signs on the path are complete and available. For special areas, such as runway end safety zones and clear space protection zones, path planning must ensure that aircraft and vehicles stay away from these areas to prevent threats to airport operation safety.

[0050] Furthermore, emergency flights such as medical rescue flights and firefighting flights are always given the highest priority. These flights enjoy unconditional right of way during the conflict resolution process, and other aircraft and vehicles must immediately give way to them to ensure that emergency tasks can be carried out quickly. The system quickly identifies emergency flights through real-time information interaction with the airport emergency command center and air traffic control department, and sets special identification and priority processing mechanisms for them.

[0051] Large passenger aircraft are usually given higher priority in conflict resolution due to their large number of passengers and large occupation of airport resources. Departing flights are also given priority because they involve flight punctuality and subsequent air traffic flow management. For large passenger aircraft, according to their aircraft models and the distribution of boarding bridge resources at the airport, they are given priority to use parking spaces close to the terminal and equipped with well-equipped boarding bridges to reduce passenger boarding time and the use of airport shuttle buses. Departing flights will reasonably arrange taxiing paths and conflict resolution sequences based on their estimated take-off times and the sequencing requirements of air traffic control.

[0052] Furthermore, for aircraft or vehicles that have been waiting for a long time on the taxiway or apron, their priority will be appropriately increased when the conflict is resolved. Through real-time monitoring and statistics of waiting time, when the waiting time exceeds a certain threshold (such as 15 minutes), the system automatically adjusts its priority to reduce its stay time on the ground and improve the overall utilization of airport resources. This priority adjustment helps to balance the fairness of services for different objects in the airport and avoid a series of subsequent problems caused by long waiting times for certain flights or vehicles, such as passenger dissatisfaction and crew fatigue.

[0053] In the case of resource constraints, such as limited boarding bridges, refueling equipment and other resources, priority is given to aircraft or vehicles that can quickly release resources for conflict resolution. For example, flights that are about to complete the boarding procedure are given priority to taxi to the runway to free up boarding bridge resources for subsequent flights; vehicles that have completed refueling are given priority to leave the refueling area to improve the turnover rate of refueling facilities.

[0054] In another specific embodiment of the present invention, the target digital twin model also includes: a speed rule curve model of the aircraft. The speed rule curve model is mainly divided into take-off phase curve fitting, landing phase curve fitting and taxiing outbound and inbound phase linear fitting. The take-off phase curve model of the aircraft can be fitted according to the position, height and speed information of ADS-B through algorithms such as polynomial regression and spline interpolation. The landing phase curve fitting fits the braking and deceleration phase through an exponential decay function or uses a piecewise function to fit the entire landing process. Use a linear method to fit the aircraft taxiing motion speed curve.

[0055] Specifically, polynomial regression is a commonly used curve fitting method. For the takeoff acceleration phase, the change of aircraft speed over time can be approximated by a polynomial function. For example, through methods such as least squares, these coefficients are solved according to the speed and time information in the collected ADS-B data to obtain a fitting curve. The polynomial regression method is simple and intuitive, and can provide a good fitting effect for a relatively smooth acceleration process. It can select the appropriate polynomial degree according to the characteristics of the data. For example, if the acceleration process is more complicated, a higher-order polynomial may be needed to better capture the speed change.

[0056] Spline interpolation is a method of constructing a smooth curve between data points. It fits the curve using a low-order polynomial (usually a cubic spline) between adjacent data points, and ensures that the curve has continuous first-order and second-order derivatives at the data points, making the curve smoother. Spline interpolation can better adapt to situations where speed changes are more complex, especially during takeoff when the aircraft may have different acceleration stages, such as initial acceleration, engine thrust adjustment, etc. It can more accurately describe the speed change trend and avoid the overfitting or underfitting problems that may occur in polynomial regression.

[0057] For landing phase curve fitting, the speed usually shows an exponential decay trend during the braking and deceleration phase after the aircraft touches down. An exponential decay function can be used for fitting. By fitting the speed and time information of the braking and deceleration phase in the ADS-B data, the values ​​of and are determined. The exponential decay function can well describe the process of rapid speed drop and conform to the physical law of braking and deceleration. It can accurately reflect the performance and deceleration effect of the braking system based on actual data. At the same time, by comparing the fitting parameters under different aircraft or different landing conditions, the working condition of the braking system and the impact of runway conditions on deceleration can be evaluated.

[0058] The landing process includes different stages such as approach, touchdown, and braking and deceleration, and the speed change law is different in each stage. A piecewise function can be used to fit the speed curve of the entire landing process. For example, a constant function can be used to represent the relatively stable speed in the approach stage, a linear function can be used to represent the transition of speed from approach speed to touchdown speed in the touchdown stage, and an exponential decay function is used in the braking and deceleration stage. The piecewise function can more accurately describe the complex speed changes in the landing process, taking into account the physical characteristics and actual conditions of different stages.

[0059] For the taxiway motion speed curve fitting method, since the speed of the aircraft on the taxiway is relatively low and relatively stable, a linear function can usually be used to fit the change of speed over time. Where is the initial speed, is the slope, and represents the rate of change of speed. In most cases, the value of is small because the taxiing speed does not change much. The linear fitting method is simple and has a small amount of calculation. It can provide sufficiently accurate fitting results for the relatively stable speed conditions on the taxiway. It can quickly obtain the trend of speed changes over time, and can analyze some basic characteristics of the taxiing process, such as average speed, speed fluctuation, etc., based on the fitting results. By analyzing the slope and intercept of the fitting curve, it is also possible to understand the speed changes of the aircraft during the taxiing departure process and whether it meets the taxiing speed requirements specified by the airport.

[0060] The fitted motion curve needs to be verified and evaluated. Indicators such as root mean square error (RMSE) and mean absolute error (MAE) can be used to measure the closeness of the fitted curve to the actual data to ensure that the fitted curve can accurately reflect the aircraft's taxiing motion. The fitted motion curve is integrated into the simulation model. This requires converting the mathematical expression of the motion curve into a form that the simulation model can recognize and process. According to the motion curve, set the aircraft's motion parameters such as speed, acceleration, and steering angle at different stages. For example, in the take-off phase, set the aircraft's acceleration process according to the motion curve; in the taxiing phase, set the appropriate taxiing speed and steering logic.

[0061] In another specific embodiment of the present invention, the target digital twin model also includes: a simulation time management algorithm and a simulation optimization algorithm.

[0062] The simulation time management algorithm uses various events in the airport flight zone as trigger points to advance the simulation time. It ensures accuracy by dynamically adjusting the time step, uses distributed clock synchronization technology to ensure time synchronization of each module, and accurately synchronizes real-time data with simulation time. The time advancement algorithm uses various events that occur in the airport flight zone (such as aircraft takeoff and landing, taxiing, vehicle driving, etc.) as trigger points for time advancement. When an event occurs, the system updates the system status according to the event type and related rules, and dynamically adjusts the time step according to the busyness of the airport operation and the density of events. During peak hours with large traffic flow and frequent events, a smaller time step (such as 0.1 second) is used to accurately capture details. During periods with small traffic and few events, the time step (such as 1 second) is appropriately increased to improve simulation efficiency while ensuring that important information is not lost. The system monitors the operating status of the simulation environment in real time and automatically adjusts the time step. For example, when aircraft are waiting to take off on the runway, it switches to a small step, thereby accurately simulating the airport operation scene and making the simulation process consistent with the actual operation in terms of time logic. The time synchronization algorithm ensures time synchronization between different modules in the simulation system (such as aircraft motion model, vehicle motion model, conflict detection module, etc.). Distributed clock synchronization technology (such as the Network Time Protocol (NTP) or the Precision Time Protocol (PTP)) is used to synchronize the clocks of each module, and timestamp information is transmitted between modules to ensure the processing order and time consistency of events in different modules. For example, after the aircraft motion model updates the aircraft position, the position information with timestamp is transmitted to the conflict detection module to ensure that the detection result accurately corresponds to the actual position of the aircraft at the same time point. When processing real-time data updates, an accurate timestamp is added to each piece of real-time data collected (consistent with the time accuracy of the simulation system, such as microseconds). Through timestamp matching and calibration, the real-time data is accurately integrated into the simulation system. The real-time data timestamp and simulation time are regularly compared and calibrated, and the synchronization lock mechanism is used to avoid data conflicts to ensure the accuracy and reliability of the coordinated work of various modules in the system. The time scheduling algorithm is responsible for the reasonable scheduling of various events in the simulation process. It determines the execution order and timing of events based on factors such as event priority, time sequence, and availability of system resources. For example, events related to emergency mission flights (such as medical rescue flights, firefighting flights, etc.) are given the highest priority to ensure their priority execution; for events of other regular flights, they are scheduled according to predetermined rules (such as first come first served, according to the importance of the flight, etc.). At the same time, the event scheduling algorithm also needs to consider the allocation of system resources to avoid event execution being blocked or errors due to resource conflicts. Through reasonable event scheduling, it is ensured that the simulation process can accurately reflect various situations in the actual operation of the airport, and improve the authenticity and effectiveness of the simulation.

[0063] The simulation optimization algorithm covers intelligent optimization algorithms, deep learning model optimization, and multi-agent reinforcement learning motion model optimization. Through the synergistic effect of various technical means, the efficiency of airport resource allocation, the accuracy of traffic prediction, and the optimization of traffic management strategies are improved. Intelligent optimization algorithms include genetic algorithms, particle swarm optimization, ant colony algorithms, simulated annealing, etc., which are often used to solve complex optimization problems. In the airport digital twin, particle swarm optimization is suitable for handling real-time scheduling in a dynamic environment, such as flight scheduling and resource allocation, and can converge quickly; genetic algorithms perform well in dealing with complex multi-objective optimization problems (such as passenger flow management and facility layout optimization) and can explore a wider solution space. Taking boarding gate allocation as an example, the genetic algorithm encodes boarding gates and flights as genetic elements to construct chromosomes, selects excellent individuals through fitness functions (comprehensively considering factors such as passenger walking distance, flight delay costs, and boarding gate facility utilization), generates new solutions through crossover and mutation operations, and optimizes the boarding gate allocation plan for multiple iterations. For airport ground vehicle scheduling, the particle swarm optimization algorithm regards vehicles as particles. According to their position, speed and fitness function (such as minimizing total driving time, reducing energy consumption, and improving task completion rate), the particle collaboration and competition find the optimal driving path and task execution order, thereby improving airport operation efficiency. It can also be widely used in ground traffic flow management, resource allocation optimization and other issues, support airport emergency management, and promote the intelligent development of airports. The deep learning optimization algorithm optimizes tasks such as airport traffic forecasting by building a deep learning model that combines the advantages of convolutional neural networks (CNN) and recurrent neural networks (RNN). CNN extracts airport spatial layout features (such as runway, taxiway layout and facility distribution), RNN processes time series data (such as flight takeoffs and landings and passenger flow changes), and adjusts network layer parameters (convolution kernel size, number, number of RNN hidden units, etc.) to improve model fitting ability. When training the model, an adaptive learning rate strategy is used. A larger learning rate is used to accelerate parameter updates in the early stage, and a lower learning rate is used in the later stage to avoid oscillation, ensuring convergence to the global optimal or near-optimal solution. At the same time, regularization techniques (such as L2 regularization) are used to add penalty terms to the loss function to constrain the size of parameters, prevent overfitting, improve the generalization ability of the model in complex operating environments, accurately predict airport traffic under different circumstances, and provide strong support for operational management. The reinforcement learning motion model optimization algorithm uses the deep Q network (DQN) and its improved strategy to optimize the multi-agent (aircraft and ground vehicle) motion model. DQN uses deep neural networks to process the complex state space (position, speed, heading combination of aircraft and vehicles, etc.) and action space (various operating actions) of airport scene traffic. By introducing the experience replay mechanism, the experience data of the interaction between the agent and the environment is stored in the buffer, and samples are randomly selected for learning, breaking the sample correlation and improving learning efficiency; the target network update strategy is used to stabilize the Q value estimation results and accelerate model convergence.Based on a carefully designed reward function (balancing individual goals with the overall operational needs of the airport, such as reducing aircraft taxiing time, avoiding collisions and maximizing runway utilization, and collaboration between vehicles and aircraft to ensure seamless traffic), the intelligent agent selects actions based on the real-time environmental status of the airport, explores the optimal movement strategy in continuous interaction with the environment, and adapts to complex situations such as dynamic changes in flights and emergencies to ensure orderly and efficient operation of airport traffic. For example, it can still make reasonable decisions in bad weather or peak hours, adapt to the operating characteristics of new equipment or new aircraft, and improve surface traffic management.

[0064] An embodiment of the present invention also provides a non-transitory computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to implementing a method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the method provided in the above embodiment.

[0065] An embodiment of the present invention further provides an electronic device, comprising a processor and the aforementioned non-transitory computer-readable storage medium.

[0066] Although some specific embodiments of the present invention have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are only for illustration, not for limiting the scope of the present invention. It should also be understood by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention.

Claims

1. A method for obtaining a digital twin of an airport flight area, characterized in that: The method comprises the following steps: S100, obtaining physical facility data, equipment status data and operation data of the flight area of ​​the target airport; S200, creating a three-dimensional geometric model based on the collected physical facility data and equipment status data; S300, based on the 3D geometric model, dynamically simulates the operation data in the flight zone and generates a target digital twin model; Among them, the target digital twin model includes a target module, which performs the following steps to realize conflict detection of the target aircraft: S410, obtaining current flight data of the target aircraft flying at the current time node, wherein the current flight data at least includes: current position coordinates (x, y, z), current speed v, and current motion direction θ; wherein x is the value of the longitude and latitude values ​​of the position of the target aircraft at the current time node converted into the horizontal axis of the plane rectangular coordinate, y is the value of the longitude and latitude values ​​of the position of the target aircraft at the current time node converted into the vertical axis of the plane rectangular coordinate, and z is the flight altitude of the target aircraft flying at the current time node; S420, generating an initial protective cover based on the current flight data of the target aircraft, wherein the initial protective cover for predicting the target aircraft conflict is an initial polygon centered at the current position coordinates (x, y, z) and surrounding the target aircraft, wherein the i-th initial vertex A of the initial polygon is i Meet the following requirements: A i =(x+r i cos(θ+α i ), y+r i sin(θ+α i ), z), i ranges from 1 to m, where m is the number of initial vertices of the initial polygon; r i is the preset radius of the i-th initial vertex, and the i-th preset angle α i Yes A i The angle formed by connecting the origin in the specified rectangular coordinate system, wherein the specified rectangular coordinate system has the center of gravity of the target aircraft as the origin, the current direction of movement as the X-axis, and the current direction of movement rotated 90 degrees clockwise as the Y-axis; S430, inputting the current flight data and the initial protection cover of the target aircraft into the target machine learning model, obtaining an initial conflict result and obtaining a target conflict type based on the initial conflict result, wherein the target conflict type is a wake conflict, a head-on conflict or a cross conflict; S440, based on the initial collision result and the target collision type, obtaining the predicted collision position of the target aircraft and increasing the number of vertices of the initial protective cover corresponding to the predicted collision position, thereby obtaining an intermediate protective cover; wherein the shapes of the intermediate protective covers corresponding to different predicted collision positions are different; S450, input the current flight data and intermediate protection cover of the target aircraft into the target machine learning model to obtain the target conflict result.

2. The method for obtaining the digital twin of an airport flight area according to claim 1, characterized in that: The physical facility data includes: geographic information data of the airfield runway, taxiway, apron, aviation building, and parking lot.

3. The method for obtaining the digital twin of an airport flight area according to claim 1, characterized in that: S430 also includes: when the initial conflict result is in a normal operating state, waiting for the next time node to execute S410.

4. The method for obtaining the digital twin of an airport flight area according to claim 1, characterized in that: The S440 also includes: S441, when the target conflict type is a wake conflict, and the predicted collision position of the target aircraft is the tail of the aircraft, the shape of the intermediate protective cover at the tail of the target aircraft is a first preset shape and the number of vertices n of the intermediate protective cover at the tail of the aircraft meets the following requirements: n=n0+ceil(k×v / av), wherein the first preset shape is determined based on the shape of the tail of the aircraft, n0 is the initial number of vertices of the initial protective cover at the tail of the aircraft, k is a speed influence parameter, av is a preset average speed, and ceil() is a rounding up function; S442, when the target conflict type is a head-on conflict, the shape of the intermediate protective cover at the head of the target aircraft is a second preset shape and the number of vertices q of the intermediate protective cover at the head of the aircraft meets the following requirement: q=q0+ceil(k×v / av), wherein the second preset shape is determined based on the shape of the head of the aircraft, and q0 is the initial number of vertices of the initial protective cover at the head of the aircraft; S443, when the target conflict type is an intersection conflict, the intersection angle φ of the target aircraft is obtained based on the current flight data, and the predicted collision position of the target aircraft is determined based on the intersection angle φ, the shape of the intermediate protective cover at the predicted collision position is a third preset shape and the number of vertices of the intermediate protective cover at the predicted collision position is greater than the initial number of vertices corresponding to the initial protective cover at the predicted collision position, wherein the third preset shape is determined based on the predicted collision position, wherein the intersection angle φ is the angle formed by the current flight direction of the target aircraft and the current flight direction of the conflicting aircraft, and the conflicting aircraft is the aircraft that conflicts with the target aircraft in the initial conflict result.

5. The method for obtaining the digital twin of an airport flight area according to claim 4, characterized in that: S441 also includes: the number p of vertices of the intermediate protective cover at the aircraft head meets the following requirement: p=q0-ceil(k×v / av).

6. The method for obtaining the digital twin of an airport flight area according to claim 3, characterized in that: The time interval t between the next time node and the current time node satisfies the following condition: t=α / (β+γ×ED), where α is the preset basic time interval, β is the preset adjustment coefficient, γ is the preset event density influence coefficient, ED is the number of conflicts occurring to the target aircraft per unit time, and β<1, γ<1.

7. The method for obtaining the digital twin of an airport flight area according to claim 6, characterized in that: α=0.1, β=0.05, γ=0.

01.

8. The method for acquiring the digital twin of an airport flight area according to claim 1, characterized in that: The target machine learning model is a target support vector machine model.

9. A non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the storage medium, characterized in that: The at least one instruction or the at least one program is loaded and executed by the processor to implement the method for acquiring the digital twin of the airport flight area as described in any one of claims 1-8.

10. An electronic device, characterized in that: The invention comprises a processor and the non-transitory computer-readable storage medium as claimed in claim 9.

Images