A method and system for predicting airport operational status based on digital twins

Abstract

This invention relates to the field of airport information processing technology, and provides a method and system for predicting airport operational status based on digital twins, comprising: deploying a twin space; wherein the twin space is used to represent a real airport geographical scene; loading at least one digital twin instance corresponding to coordinate information and entity objects into the twin space; wherein the coordinate information is the location information of the digital twin instance corresponding to the entity object; responding to a target scheduling instruction of the target digital twin instance, performing a hierarchical scheduling simulation of the target digital twin instance in the twin space to determine the operational status information of the target digital twin instance in the real airport geographical scene; wherein the hierarchical scheduling simulation includes a simulation space based on risk classification.

Description

Technical Field

[0001] This invention relates to the field of airport information processing technology, and in particular to a method and system for predicting airport operational status based on digital twins. Background Technology

[0002] Digital twins are a scenario simulation technology that constructs physical entities in virtual space to achieve precise mapping in digital transformation. Through two-way real-time interaction and driven by data, it enables full lifecycle management of the simulation scenario, simulates the operating mechanisms of scenario equipment, and achieves global and local control over the simulation scenario.

[0003] In terms of airport operation status analysis, existing technologies use big data technology to achieve airport scheduling and control. Digital twin technology, when applied to airport operations, is mainly used to monitor equipment status and analyze the rationality of airport scheduling. In terms of control precision, it can only determine whether there are scheduling conflicts after an aircraft has landed or during its movement by using the monitoring and sensing equipment installed at the airport.

[0004] Moreover, existing digital twin technology, in terms of the accuracy of digital twins, can only determine the location information of different aircraft, equipment or fixed facilities on the airport map to achieve global digital twin supervision. The computing power will be allocated to each piece of equipment, aircraft and fixed facilities on the airport map, which can only achieve global supervision. Single supervision of individual aircraft, equipment or fixed facilities will result in accuracy errors.

[0005] Therefore, it is not possible to perform scheduling analysis under the spatiotemporal reference of scenarios, aircraft, equipment, or fixed facilities. Consequently, it is impossible to determine whether there are risks based on aircraft scheduling instructions, and the degree of risk or accident that the risk situation may cause. Summary of the Invention

[0006] This application proposes a method for predicting airport operation status based on digital twins. By dynamically mapping twin instances and using a risk-level extrapolation space, this application embeds the risk dimension into the geographical extrapolation space, constructs a multi-level extrapolation, and outputs the micro-situation through instance-level extrapolation, thereby achieving high-precision prediction of airport operation status.

[0007] Firstly, this application proposes a method for predicting airport operational status based on digital twins, including:

[0008] Deploy a twin space; whereby the twin space is used to represent the real airport geographical scene;

[0009] Load at least one digital twin instance corresponding to an entity object and coordinate information into the twin space; wherein the coordinate information is the position information of the digital twin instance corresponding to the entity object;

[0010] In response to the target scheduling command of the target digital twin instance, a hierarchical scheduling simulation of the target digital twin instance is performed in the twin space to determine the operational status information of the target digital twin instance in the real airport geographical scenario; wherein, the hierarchical scheduling simulation includes a simulation space based on risk classification.

[0011] During airport operations, this application can achieve spatial location synchronization of multiple entities through twin space, and determine airport operation status information through virtual simulation under dynamic risk constraints, thereby reducing the probability of airport operation conflicts and delay time.

[0012] In conjunction with the first aspect, the twin space is equipped with computing nodes and geographic topology nodes; wherein, the computing nodes are used to process first data, which is non-pre-scheduled dynamic data representing entity objects in the locally processed scheduling data; the geographic topology nodes are used to determine the dynamic boundaries of the scheduling data based on the first data and entity modeling data; wherein, the entity modeling data is scene entities in real airport geographic information.

[0013] This application processes local dynamic data through computing nodes to prevent data delays, and sets the boundaries of entity objects through geographic topology results to prevent the virtual simulation from becoming disconnected from the spatial constraints of the real scene.

[0014] In conjunction with the first aspect, loading at least one digital twin instance corresponding to coordinate information and an entity object into the twin space includes:

[0015] In a real airport geographic scene, at least one entity object to be loaded is identified, and the entity dependency relationship of at least one entity object to be loaded in the real airport geographic scene is determined; wherein, the entity dependency relationship includes a first dependency relationship and a second dependency relationship, the first dependency relationship is used to characterize the geographic location information of the entity object to be loaded, and the second dependency relationship characterizes the three-dimensional layout information of the entity object to be loaded.

[0016] Based on entity dependencies, construct a composite coordinate system in the geographic scene and functional area to which at least one entity object to be loaded belongs;

[0017] Based on the first dependency relationship and the composite coordinate system, load the twin coordinate information of at least one entity object to be loaded into the twin space;

[0018] Based on the second dependency relationship and the composite coordinate system, three-dimensional layout information corresponding to the twin coordinate information is loaded into the twin space to form at least one digital twin instance.

[0019] This application combines a single coordinate system and two-dimensional position mapping during the loading process of a digital twin instance to prevent incomplete structural restoration of three-dimensional entity objects in virtual space and positional deviations caused by inconsistent coordinates of entity objects in different functional areas.

[0020] In conjunction with the first aspect, loading at least one digital twin instance corresponding to coordinate information and an entity object into the twin space further includes:

[0021] Based on the location information of the entity object in the real airport geographical scene, determine the scheduling attributes of the entity object; among which, the scheduling attributes include fixed attributes and movable attributes;

[0022] Based on scheduling attributes, the scheduling instruction sets of entity objects are divided;

[0023] The synchronous response mechanism of the digital twin instance is configured in the twin space according to the scheduling instruction set; wherein, the synchronous response mechanism configures the operable instruction set that the digital twin instance can respond to according to the scheduling attributes and the real airport geographical scenario.

[0024] This application can prevent confusion between instructions for fixed entities and movable entities by using an instruction set and a synchronous response mechanism to ensure that twin instances only respond to their operable instructions.

[0025] In conjunction with the first aspect, the target scheduling instruction is the first instruction in the operable instruction set; wherein, the first instruction is a target instruction in which there is no instruction conflict between the target digital twin instance and another digital twin instance in the real-time twin space, and the target instruction generates a new operation for the current scheduling behavior when the target digital twin instance has scheduling behavior.

[0026] This application links instruction selection with real-time conflict detection to prevent static instruction selection from causing conflicts in real-world scenarios, and combines it with new operations to prevent instructions from failing to adapt to real-time changes during execution.

[0027] In conjunction with the first aspect, the hierarchical scheduling simulation includes:

[0028] In response to the simulation data of the target digital twin instance executing the target scheduling instruction, the first simulation sample data is obtained;

[0029] Based on the first inference sample data, the first inference space with spatiotemporal annotations is determined in the twin space;

[0030] By responding to the second scheduling instruction that is synchronously executed in the time period of each spatiotemporal marker in the twin space in the first simulation space, scheduling conflict determination is performed;

[0031] When there are no scheduling conflicts, the system outputs stable operational status information of the real airport geographical scenario.

[0032] When scheduling conflicts exist, the conflicting objects are identified, forming a second inference space based on the conflicting objects. The second inference space is used to form a third inference space according to the risk level.

[0033] This application addresses the issues of conflict detection and unclear spatiotemporal relationships in multi-instruction parallel processing through spatiotemporal annotation, and prevents the inability to accurately locate local risks after global conflict detection by hierarchical spatial extrapolation.

[0034] In conjunction with the first aspect, the third deduction space is used to replace the scheduling operation of the target digital twin instance in the twin space with the scheduling operation of the conflicting object, determine the scheduling conflict scenario, and the first conflict behavior that represents the scheduling conflict behavior in the twin space.

[0035] This application actively simulates conflict scenarios through replacement operations, which can solve the problem of conflict root cause location and convert the specific conflict behaviors into visual operations in twin space.

[0036] In conjunction with the first aspect, the second simulation space is also used to determine conflict instructions based on the conflict object, and to configure the risk level corresponding to the instruction source based on the instruction source of the conflict instruction; wherein, the risk level is matched with risk items and control items corresponding to the real airport geographical scenario, the risk items are used to determine the ontological risk value of the conflict object, and the control items are used to determine the diffusion risk value of the conflict object based on the ontological risk value, and the diffusion risk value is used as the target risk value for determining the risk level.

[0037] This application can solve the problems of homogenization of conflict risks caused by instructions from different sources and the problem of focusing only on local conflict scenarios while ignoring object characteristics and global impact.

[0038] In conjunction with the first aspect, the operational status information includes the potential risk vector of the target digital twin instance in the real airport geographical scenario, and through the potential risk vector; wherein, the potential risk vector is the target risk value of the second digital twin instance in the hierarchical scheduling simulation caused by the scheduling behavior of the target digital twin instance under the target scheduling instruction.

[0039] This application allows for the quantification of risks during its evolution.

[0040] Secondly, this application proposes an airport operation status prediction system based on digital twins, including:

[0041] Spatial Deployment Module: Used to deploy twin spaces; where twin spaces are used to represent real airport geographical scenarios;

[0042] Instance configuration module: used to load at least one digital twin instance in the twin space, which consists of coordinate information and an entity object; wherein, the coordinate information is the position information of the digital twin instance corresponding to the entity object;

[0043] The simulation and prediction module is used to respond to the target scheduling instructions of the target digital twin instance and perform hierarchical scheduling simulation of the target digital twin instance in the twin space to determine the operational status information of the target digital twin instance in the real airport geographical scenario; wherein, the hierarchical scheduling simulation includes a simulation space based on risk classification.

[0044] During airport operations, this application can achieve spatial location synchronization of multiple entities through twin space, and determine airport operation status information through virtual simulation under dynamic risk constraints, thereby reducing the probability of airport operation conflicts and delay time.

[0045] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0046] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0047] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0048] In the attached diagram:

[0049] Figure 1 This is an architecture diagram of the airport digital twin system in an embodiment of the present invention;

[0050] Figure 2 This is an architecture diagram of a traditional airport digital twin system.

[0051] Figure 3 This is a flowchart of the airport operation status prediction method based on digital twin in an embodiment of the present invention;

[0052] Figure 4 This is a diagram illustrating the loading process of a digital twin instance within the twin space in an embodiment of the present invention.

[0053] Figure 5 This is a processing diagram of the twin processing layer for digital twin instances in an embodiment of the present invention;

[0054] Figure 6 This is a scheduling and management diagram of the twin processing layer for digital twin instances in an embodiment of the present invention;

[0055] Figure 7 This is a diagram illustrating the hierarchical deduction process of the twin processing layer for digital twin instances in an embodiment of the present invention. Detailed Implementation

[0056] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0057] In the existing airport digital twin architecture, see Figure 2 It mainly targets different scenarios at airports, performs airport monitoring, collects flight data and aircraft location scheduling data, as well as ground handling management data, and realizes the construction of a digital twin space for the entire airport.

[0058] It should be understood that the key to building a digital twin space is the digital mapping of different physical objects in the airport. In the existing technology, the airport tower can only collect data on aircraft, ground staff, special vehicles, etc. based on the monitoring and sensing equipment inside the airport to achieve position simulation. However, aircraft monitoring and ground staff monitoring are two different independent data terminals and do not have the same spatiotemporal reference. Therefore, there are conflicts between elements of different control systems, and conflict prediction and control cannot be achieved.

[0059] Additionally, see Figure 2 Traditional digital twins can only monitor physical objects as a whole. The location information of the area can only be monitored through point twins. During the monitoring process, the conflicts can only be based on specific conflicts between the conflicting objects, such as sharing a runway and having the same arrival or departure position at the same time. Because the accuracy of traditional twin systems is insufficient, they cannot monitor and predict the unexpected conflicts that may occur between aircraft and special vehicles, aircraft and ground staff, special vehicles and ground staff, and the geographical environment of physical entities and aircraft under scheduling instructions. They also cannot judge the risk situation caused by different scheduling instructions.

[0060] Based on the above problems, this application provides the following solution;

[0061] Example 1:

[0062] See Figure 3 This application proposes a method for predicting airport operational status based on digital twins, including:

[0063] Step S100: Deploy the twin space; wherein, the twin space is used to represent the real airport geographical scene, and its function is to construct a virtual mapping environment corresponding to the real airport;

[0064] The twin space is a digital twin model. Based on the geographical information of the real airport, it forms a virtual three-dimensional space based on GIS+BIM. It integrates static scene data such as terrain, runways, and terminals. The twin space is a synchronous space for loading and simulating the operational status environment of digital twin instances.

[0065] Step S101: Load at least one digital twin instance corresponding to the entity object and coordinate information into the twin space; wherein, the coordinate information is the location information of the digital twin instance corresponding to the entity object; the digital twin instance is the mapping of the real airport entity object to the twin space;

[0066] Coordinate information is the specific information of entity objects. By modeling entity objects such as aircraft, ground support vehicles, and baggage systems as independent twins, and binding spatial coordinates and the three-dimensional structure and real-time behavior of the entity objects in real time, digital twin instances are generated. This allows for precise positioning of dynamic and static entity objects in virtual space, including spatial, temporal, and spatial occupancy. It enables the spatiotemporal synchronous distribution simulation of entities from different systems located in the same spatial area. Digital twin instances possess corresponding attribute information, including coordinates, speed, and fuel level, which is communicated through message queues, etc. The location information of the digital twin instances allows the twin space to reflect the real-time distribution of entity objects in the airport.

[0067] Step S102: In response to the target scheduling command of the target digital twin instance, perform a hierarchical scheduling simulation of the target digital twin instance in the twin space to determine the operational status information of the target digital twin instance in the real airport geographical scenario; wherein, the hierarchical scheduling simulation includes a simulation space based on risk classification. Hierarchical scheduling simulation predicts the real operational status through virtual simulation, which can reduce the computational cost of undifferentiated simulation across all scenarios, while improving the relevance of the prediction results.

[0068] Through target scheduling instructions, the scheduling behavior of any digital twin entity can be simulated, and simulation subspaces can be divided. Simulation simulations can be performed based on different simulation subspaces with different risk types and risk levels. Simulated events are injected into the subspaces, and the behavior path of the twin is calculated through a preset rule engine. Risk classification is mainly based on the specific simulation subspace settings.

[0069] Finally, the simulation results generate structured data such as airport traffic heat maps, conflict point warnings, and resource scheduling suggestions, extending digital twin technology from industrial scenarios to airport geographical scenarios and solving the technical problem of synchronizing the spatial locations of multiple entities; this can significantly reduce the probability of airport operational conflicts and delays.

[0070] Example 2:

[0071] See Figure 4 and Figure 1The twin space of this application deploys computing nodes 2010 and geographic topology nodes 2020, which are distributed computing units deployed in the twin space's server; computing nodes 2010 and geographic topology nodes 2020 belong to the twin processing layer 20. Computing nodes 2010 and geographic topology nodes 2020 have node division of labor functions to improve the parallel processing capability of the twin space.

[0072] First, entity modeling is performed, as in step S1001: obtaining entity modeling data. Computation node 2010 first determines the specific modeling data of the physical entities to be modeled through geographic topology node 2020;

[0073] Specifically, computing node 2010 is used to process the first data, which is non-pre-scheduled dynamic data representing entity objects in the locally processed scheduling data (data not generated by operations that should be performed in the regular plan); the scheduling data includes pre-scheduled data and non-pre-scheduled data, where pre-scheduled data is data in the plan such as planned taxiing time and fixed routes.

[0074] For example, in step S1002: Based on the entity modeling data, the non-pre-scheduled dynamic data of the modeled entity is determined in the local scheduling data, and the first data is generated. The computing node 2010 processes the non-pre-scheduled dynamic data in the local scheduling data, which can quickly respond to emergencies in real airports. Because it does not involve cloud data processing and external servers, there is no delay.

[0075] Non-pre-scheduled dynamic data refers to the unpre-scheduled dynamic data generated during airport operations under unexpected circumstances, such as sudden equipment failures or weather and terrain damage. Its purpose is to provide sample data for the prediction process.

[0076] The geographic topology node 2020 is used to determine the dynamic boundaries of scheduling data based on the first data and entity modeling data. The entity modeling data consists of scene entities in the real airport geographic information (scene entities include geographic entities, equipment entities, and building entities). For example, in step S1003: the scene entities of the modeling entities and the dynamic boundaries of the scene entities in the twin space are determined. The geographic topology node 2020 performs entity modeling based on the non-pre-scheduled dynamic data appearing in the real airport environment, calculates the influence range through spatial topological relationships, and determines the subspace range for simulation based on the non-pre-scheduled dynamic data, thus limiting the scope of the simulation and preventing conflicts between the simulation results and the real space.

[0077] Example 3:

[0078] See Figure 5 and Figure 1 This application loads at least one digital twin instance in the twin space, consisting of coordinate information and an entity object, including:

[0079] The instance configuration module 202 receives data on fixed and mobile entities in the scene from the spatial deployment module 201, determines the entity objects to be loaded, and then performs instance deployment through the spatial deployment module 201. It identifies at least one entity object to be loaded in a real airport geographical scene and determines the entity dependencies of at least one entity object in the real airport geographical scene; wherein, the entity dependencies include a first dependency and a second dependency, the first dependency representing the geographical location information of the entity object to be loaded, and the second dependency representing the three-dimensional layout information of the entity object to be loaded.

[0080] The first dependency relationship is constructed based on the coordinate data of entity objects corresponding to geographic location information. The second dependency relationship achieves high-precision measurement between different entities through the relative spatial relationships between entities and the height hierarchy in three-dimensional space, such as the vertical distance between a taxiway and a runway. The combination of the two realizes the unique topological constraint of entities in three-dimensional space, and neither can be omitted. In terms of the accuracy of the twin model, it can achieve centimeter-level spatial distribution misalignment determination.

[0081] Based on entity dependencies, construct a composite coordinate system in the geographic scene and functional area to which at least one entity object to be loaded belongs;

[0082] The composite coordinate system is a spatiotemporal reference system that integrates geographical scenes (runway area, apron area) and entity dependencies (aircraft taxiing function), and synchronously processes the absolute position and relative deployment of equipment.

[0083] Based on the first dependency relationship and the composite coordinate system, load the twin coordinate information of at least one entity object to be loaded into the twin space; the twin coordinate information accurately maps the planar position of the entity object in the real scene to the twin space, so that the planar position of the digital twin instance is completely consistent with the real entity object.

[0084] Based on the first dependency relationship, twin coordinate information can be loaded to enable the configuration of spatial anchor points for entity objects;

[0085] Based on the second dependency relationship and the composite coordinate system, 3D layout information corresponding to the twin coordinate information is loaded into the twin space to form at least one digital twin instance. The 3D layout information maps the 3D structure of entity objects in the real scene to the twin space, enabling the 3D structure to also be mapped into the twin space, improving the fidelity of the real scene corresponding to the digital twin instance in the twin space. It constructs the spatial relationship network of entity objects, realizing a full-dimensional mapping from physical entities to digital twins.

[0086] This application associates entity dependencies with subdivided planar and solid structures to prevent incomplete reconstruction of 3D entity objects in twin space. It also combines a composite coordinate system and integrates multi-source coordinate references to enable mapping of entity objects with different functions even when coordinates are not uniform, without resulting in positional deviations.

[0087] Example 4:

[0088] See Figure 6 and Figure 1 This application loads at least one digital twin instance corresponding to coordinate information and an entity object in the twin space, and further includes:

[0089] Based on the location information of the entity object in the real airport geographical scene, determine the scheduling attributes of the entity object; among which, the scheduling attributes include fixed attributes and movable attributes;

[0090] The location information of entity objects in the real airport geographical scene, including whether the entity object is a long-term fixed entity or an entity that depends on a power system for movement, is classified according to scheduling attributes (fixed equipment or mobile equipment). Under the attribute classification, erroneous instructions for object entities within the twin space are prevented, and the targeting of instructions is improved.

[0091] Entities with fixed attributes are immovable entities such as walkways, control towers, and some fixed equipment.

[0092] The movable attribute represents movable objects such as airplanes, ground support vehicles, and engineers. Through the scheduling attribute, we can first verify the accuracy of scheduling instructions, and secondly, determine the location and boundaries of movement for each entity.

[0093] Based on scheduling attributes, the scheduling instruction sets of entity objects are divided;

[0094] The scheduling instruction set consists of exclusive control instructions for each type of entity object. Fixed attribute objects only respond to status query instructions, while movable attribute objects need to respond to path planning instructions. It can filter out irrelevant instructions and eliminate illegal operations. At the same time, it can also prevent instruction set redundancy to a certain extent and reduce computational load.

[0095] The synchronous response mechanism of the digital twin instance is configured in the twin space according to the scheduling instruction set; wherein, the synchronous response mechanism configures the operable instruction set that the digital twin instance can respond to according to the scheduling attributes and the real airport geographical scenario.

[0096] The synchronous response mechanism sets dynamic response rules in the twin space (e.g., when the synchronous response mechanism is based on the MQTT protocol, when the real device receives an instruction, the twin instance synchronously triggers the inference of the same instruction). It limits the range of operable instructions based on scheduling attributes and constrains the validity of instructions according to the real geographical scenario. This allows the instruction set to dynamically shrink / expand with the entity's location, reducing response latency from seconds to milliseconds, and ensuring that the twin instance only responds to its operable instructions. Furthermore, in the twin space, there will be no distortion of inference results due to irrelevant instructions.

[0097] Example 5:

[0098] See Figure 6 and Figure 1 The target scheduling instruction in this application is the first instruction in the operable instruction set; wherein, the first instruction is a target instruction in which there is no instruction conflict between the target digital twin instance and another digital twin instance in the real-time twin space, and the target instruction generates a new operation for the current scheduling behavior when the target digital twin instance has scheduling behavior.

[0099] The first instruction is a pre-selected valid instruction from the operable instruction set. This first instruction must not conflict with another digital twin instance in the real-time twin space. When the target instruction is a scheduling action, a new operation for the current action will be generated, achieving a balance between instruction security and resource optimization. The operable instruction set is a dedicated instruction set configured based on scheduling attributes. The first instruction is the instruction preferentially selected from this dedicated instruction set, ensuring that the target scheduling instruction matches the scheduling attributes of the digital twin instance. In actual implementation, if two aircraft use the same taxiway, it constitutes an instruction conflict. By real-time detection of the instruction targets of both (such as taxiway occupancy time and path), it is determined whether there is a conflict (such as time overlap or spatial overlap), and only the conflict-free instruction is selected as the first instruction. When the target digital twin instance executes a scheduling action (such as the aircraft starting to taxi), the original instruction may need to be adjusted due to real-time scene changes (such as sudden obstacles). The new operation is a dynamic supplement to the original instruction. By obtaining real-time inference feedback from the twin space (such as collision warning), the generation of the new operation is triggered, preventing static instructions from being unsuitable for scene changes.

[0100] Example 6:

[0101] See Figure 7 and Figure 1 The twin space of this application can perform hierarchical scheduling deduction, including:

[0102] In response to the simulation data of the target digital twin instance executing the target scheduling instruction, the first simulation sample data is obtained;

[0103] When the target digital twin instance (aircraft) executes the target command (taxiing to any parking area), simulation data is generated. The first simulation sample data is the simulation process data based on the target instance executing the target command. It can generate an initial simulation data set, which can ensure that the simulation process is based on dynamic data of real scheduling behavior and prevent simulation deviations due to actual data.

[0104] Based on the first inference sample data, the first inference space with spatiotemporal annotations is determined in the twin space;

[0105] The first simulation space is a virtual simulation environment with spatiotemporal labels built in the twin space based on simulation data. Spatiotemporal labeling adds labels in the time and space dimensions to the first simulation sample data. The first simulation space is a virtual environment built based on the labeled labels, which simulates the overlap of multiple scheduling instructions in time and space, making the spatiotemporal correlation visible, showing the execution trajectory of multiple instructions, and providing a clear analysis scenario for conflict determination.

[0106] The first simulation space responds to the second scheduling instruction, which is executed synchronously within the time period of each spatiotemporal marker in the digital twin space, to determine scheduling conflicts. The second scheduling instruction is the scheduling instruction of other digital twin instances within the same time period. Through the spatiotemporal markers of the first simulation space, the execution process of these instructions is simulated synchronously to detect whether there are conflicts with time overlap (such as simultaneous occupation of the same taxiway) or spatial overlap (such as path intersection). Conflict determination is a parallel conflict detection of multiple instructions to avoid missed conflict detection caused by sequential execution detection.

[0107] Specifically, when there is no scheduling conflict, the stable operation status information of the real airport geographical scene is output; if all second scheduling instructions and target scheduling instructions do not overlap in time and space, the stable operation status information of the real airport is output.

[0108] When scheduling conflicts exist, the conflicting objects are identified, forming a second inference space based on the conflicting objects. The second inference space is used to form a third inference space according to the risk level.

[0109] The tiered conflict handling mechanism in this application involves: locating conflicting objects (e.g., conflicting aircraft A and ground support vehicle B); constructing a second simulation space (a sandbox dedicated to each conflicting object); and finally generating a third simulation space based on risk level (e.g., simulating collision consequences in high-risk scenarios). In this tiered conflict handling mechanism, in the absence of conflict, stable operational status information can be directly output. In the presence of conflict, conflict handling is performed according to subspaces. These subspaces are highly correlated with risk level and risk type, enabling high-precision simulations with low computing power.

[0110] Example 7:

[0111] See Figure 7The third deduction space of this application is used to replace the scheduling operation of the target digital twin instance in the twin space with the scheduling operation of the conflict object, determine the scheduling conflict scenario, and the first conflict behavior that represents the scheduling conflict behavior in the twin space.

[0112] In the second simulation space, conflicting objects (such as the target digital twin instance A and conflicting object B) have been identified. In the third simulation space, the scheduling operation replacement mechanism of this application replaces the scheduling operations of the target digital twin instance with those of the conflicting objects. For example, the landing command of aircraft A is replaced with the movement command of ground support vehicle B. Through simulation of the replaced operations, the scheduling conflict scenario is determined. Finally, the first conflict behavior is dynamically generated in the twin space. The focus of this application is to actively construct the conflict scenario and extrapolate micro-behaviors to locate the root cause and reason for the conflict. The scheduling conflict scenario refers to the specific spatiotemporal conditions under which the conflict occurs. By recording the execution process of the replaced scheduling operations and combining spatiotemporal annotations, the third simulation space can determine detailed conflict scenario information, transforming the abstract conflict into observable and analyzable behavior.

[0113] Example 8:

[0114] See Figure 7 The second deduction space of this application is also used to determine the conflict command based on the conflict object, and to configure the risk level corresponding to the command source based on the command source of the conflict command; wherein, the risk level is matched with the risk item and control item corresponding to the real airport geographical scenario, the risk item is used to determine the ontological risk value of the conflict object, and the control item is used to determine the diffusion risk value of the conflict object based on the ontological risk value, and the diffusion risk value is used as the target risk value for determining the risk level.

[0115] Based on the conflicting objects, identifying the conflicting instructions allows for the tracing of these instructions' origins. Through source analysis, the risk level can be determined, the inherent risk value of the conflicting object can be calculated, and the diffusion risk value can be derived from this inherent risk value. Finally, the diffusion risk value serves as the target risk value, driving the risk level update. By analyzing the historical scheduling records and real-time simulation data of the conflicting objects, the instructions directly causing the conflict can be located. The instruction source refers to the issuing entity (e.g., ground dispatch system, tower control system) or type of the conflicting instruction. Different instruction sources have varying authority and scope of influence, thus requiring different risk levels for differentiated risk assessment. Risk items are risk factors related to the inherent attributes of the conflicting objects themselves. The inherent risk value quantifies these risk factors, avoiding a focus solely on the conflict scenario while ignoring the object's characteristics. Object characteristics can lead to small risk events resulting in significant consequences. Control items are factors in the airport operating environment that influence risk diffusion (e.g., traffic density at the conflict site, availability of backup taxiways, and response time of rescue resources). The diffusion risk value quantifies the factors influencing risk diffusion, and the target risk value is the diffusion risk value—the final risk level determination based on the combination of the inherent risk value and control items.

[0116] Example 9:

[0117] See Figure 7 The operational status information of this application includes the potential risk vector of the target digital twin instance in the real airport geographical scenario, and the potential risk vector is the target risk value of the second digital twin instance in the hierarchical scheduling simulation caused by the scheduling behavior of the target digital twin instance under the target scheduling instruction.

[0118] Operational status information is a comprehensive representation of the airport's operational status;

[0119] The potential risk vector quantifies the risk impact of the target instance's behavior on associated entities, representing the potential risk of the target digital twin instance;

[0120] The risk transmission mechanism is that the scheduling behavior of the target instance causes the second digital twin instance (related entity) to generate a target risk value in the simulation (such as flight delays causing subsequent flight delays), preventing only focusing on the direct conflict object and ignoring the indirect risks of the target scheduling behavior to other instances.

[0121] Example 10:

[0122] See Figure 1This application proposes an airport operation status prediction system based on digital twins. The system includes a tower dispatch layer 10, a twin processing layer 20, and a data acquisition layer 30. The data acquisition layer 30 is used to collect object instances and real airport geographical scene data and upload them to the twin processing layer 20. The tower dispatch layer 10 is used to receive the hierarchical simulation data from the twin processing layer 20 and issue dispatch instructions to the twin processing layer 20 to assist in real-time simulation.

[0123] The core processing module of the digital twin airport operation status prediction system, configured within the twin processing layer 20, specifically includes:

[0124] Spatial Deployment Module 201: Used to deploy twin space; wherein, twin space is used to represent the real airport geographical scene, and its function is to construct a virtual mapping environment corresponding to the real airport;

[0125] The twin space is a digital twin model. Based on the geographical information of the real airport, it forms a virtual three-dimensional space based on GIS+BIM. It integrates static scene data such as terrain, runways, and terminals. The twin space is a synchronous space for loading and simulating the operational status environment of digital twin instances.

[0126] Instance configuration module 202: used to load at least one digital twin instance corresponding to an entity object and coordinate information into the twin space; wherein, the coordinate information is the location information of the digital twin instance corresponding to the entity object; the digital twin instance maps the real airport entity object to the twin space;

[0127] Coordinate information is the specific information of entity objects. By modeling entity objects such as aircraft, ground support vehicles, and baggage systems as independent twins, and binding spatial coordinates and the three-dimensional structure and real-time behavior of the entity objects in real time, digital twin instances are generated. This allows for precise positioning of dynamic and static entity objects in virtual space, including spatial, temporal, and spatial occupancy. It enables the spatiotemporal synchronous distribution simulation of entities from different systems located in the same spatial area. Digital twin instances possess corresponding attribute information, including coordinates, speed, and fuel level, which is communicated through message queues, etc. The location information of the digital twin instances allows the twin space to reflect the real-time distribution of entity objects in the airport.

[0128] The simulation and prediction module 203 is used to respond to the target scheduling instructions of the target digital twin instance and perform hierarchical scheduling simulation of the target digital twin instance in the twin space to determine the operational status information of the target digital twin instance in the real airport geographical scenario. The hierarchical scheduling simulation includes a simulation space based on risk classification. Hierarchical scheduling simulation predicts the real operational status through virtual simulation, which can reduce the computational cost of undifferentiated simulation across all scenarios while improving the specificity of the prediction results.

[0129] Through target scheduling instructions, the scheduling behavior of any digital twin entity can be simulated, and simulation subspaces can be divided. Simulation simulations can be performed based on different simulation subspaces with different risk types and risk levels. Simulated events are injected into the subspaces, and the behavior path of the twin is calculated through a preset rule engine. Risk classification is mainly based on the specific simulation subspace settings.

[0130] Finally, the simulation results generate structured data such as airport traffic heatmaps, conflict point warnings, and resource scheduling suggestions, extending digital twin technology from industrial scenarios to airport geographical scenarios and solving the technical problem of synchronizing the spatial locations of multiple entities. This can significantly reduce the probability of airport operational conflicts and delays. Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for predicting airport operational status based on digital twins, characterized in that, include: Deploy a twin space; whereby the twin space is used to represent the real airport geographical scene; Load at least one digital twin instance corresponding to an entity object and coordinate information into the twin space; wherein the coordinate information is the position information of the digital twin instance corresponding to the entity object; In response to the target scheduling command of the target digital twin instance, a hierarchical scheduling simulation of the target digital twin instance is performed in the twin space to determine the operational status information of the target digital twin instance in a real airport geographical scenario; wherein, the hierarchical scheduling simulation includes a simulation space based on risk classification; wherein, The hierarchical scheduling simulation includes: In response to the simulation data of the target digital twin instance executing the target scheduling instruction, the first simulation sample data is obtained; Based on the first inference sample data, the first inference space with spatiotemporal annotations is determined in the twin space; By responding to the second scheduling instruction that is synchronously executed in the time period of each spatiotemporal marker in the twin space in the first simulation space, scheduling conflict determination is performed; When there are no scheduling conflicts, the system outputs stable operational status information of the real airport geographical scenario. When scheduling conflicts exist, the conflicting objects are identified, forming a second inference space based on the conflicting objects. The second inference space is used to form a third inference space according to the risk level.

2. The airport operation status prediction method based on digital twin as described in claim 1, characterized in that, The twin space is equipped with computing nodes and geographic topology nodes. The computing nodes are used to process first data, which is non-pre-scheduled dynamic data representing entity objects in the locally processed scheduling data. The geographic topology nodes are used to determine the dynamic boundaries of the scheduling data based on the first data and entity modeling data. The entity modeling data is scene entities in real airport geographic information.

3. The airport operation status prediction method based on digital twin as described in claim 1, characterized in that, Loading at least one digital twin instance corresponding to coordinate information and an entity object into the twin space includes: In a real airport geographic scene, at least one entity object to be loaded is identified, and the entity dependency relationship of at least one entity object to be loaded in the real airport geographic scene is determined; wherein, the entity dependency relationship includes a first dependency relationship and a second dependency relationship, the first dependency relationship is used to characterize the geographic location information of the entity object to be loaded, and the second dependency relationship characterizes the three-dimensional layout information of the entity object to be loaded. Based on entity dependencies, construct a composite coordinate system in the geographic scene and functional area to which at least one entity object to be loaded belongs; Based on the first dependency relationship and the composite coordinate system, load the twin coordinate information of at least one entity object to be loaded into the twin space; Based on the second dependency relationship and the composite coordinate system, three-dimensional layout information corresponding to the twin coordinate information is loaded into the twin space to form at least one digital twin instance.

4. The airport operation status prediction method based on digital twin as described in claim 3, characterized in that, The step of loading at least one digital twin instance corresponding to coordinate information and entity objects into the twin space further includes: Based on the location information of the entity object in the real airport geographical scene, determine the scheduling attributes of the entity object; among which, the scheduling attributes include fixed attributes and movable attributes; Based on scheduling attributes, the scheduling instruction sets of entity objects are divided; The synchronous response mechanism of the digital twin instance is configured in the twin space according to the scheduling instruction set; wherein, the synchronous response mechanism configures the operable instruction set that the digital twin instance can respond to according to the scheduling attributes and the real airport geographical scenario.

5. The airport operation status prediction method based on digital twin as described in claim 4, characterized in that, The target scheduling instruction is the first instruction in the operable instruction set; wherein, the first instruction is a target instruction in which there is no instruction conflict between the target digital twin instance and another digital twin instance in the real-time twin space, and the target instruction generates a new operation for the current scheduling behavior when the target digital twin instance has scheduling behavior.

6. The airport operation status prediction method based on digital twin as described in claim 1, characterized in that, The third inference space is used to replace the scheduling operation of the target digital twin instance in the twin space with the scheduling operation of the conflict object, determine the scheduling conflict scenario, and the first conflict behavior that represents the scheduling conflict behavior in the twin space.

7. The airport operation status prediction method based on digital twin as described in claim 1, characterized in that, The second simulation space is also used to determine conflict instructions based on the conflict object, and to configure the risk level corresponding to the instruction source based on the instruction source of the conflict instruction; wherein, the risk level is matched with risk items and control items corresponding to the real airport geographical scenario, the risk items are used to determine the ontological risk value of the conflict object, and the control items are used to determine the diffusion risk value of the conflict object based on the ontological risk value, and the diffusion risk value is used as the target risk value for determining the risk level.

8. The airport operation status prediction method based on digital twin as described in claim 7, characterized in that, The operational status information includes the potential risk vector of the target digital twin instance in the real airport geographical scenario, and through the potential risk vector; wherein, the potential risk vector is the target risk value of the second digital twin instance in the hierarchical scheduling simulation caused by the scheduling behavior of the target digital twin instance under the target scheduling instruction.

9. An airport operation status prediction system based on digital twins, characterized in that, include: Spatial Deployment Module: Used to deploy twin spaces; where twin spaces are used to represent real airport geographical scenarios; Instance configuration module: used to load at least one digital twin instance in the twin space, which consists of coordinate information and an entity object; wherein, the coordinate information is the position information of the digital twin instance corresponding to the entity object; The simulation and prediction module is used to respond to the target scheduling instructions of the target digital twin instance and perform hierarchical scheduling simulations of the target digital twin instance in the twin space to determine the operational status information of the target digital twin instance in the real airport geographical scenario. The hierarchical scheduling simulation includes a simulation space based on risk classification. The hierarchical scheduling simulation includes: In response to the simulation data of the target digital twin instance executing the target scheduling instruction, the first simulation sample data is obtained; Based on the first inference sample data, the first inference space with spatiotemporal annotations is determined in the twin space; By responding to the second scheduling instruction that is synchronously executed in the time period of each spatiotemporal marker in the twin space in the first simulation space, scheduling conflict determination is performed; When there are no scheduling conflicts, the system outputs stable operational status information of the real airport geographical scenario. When scheduling conflicts exist, the conflicting objects are identified, forming a second inference space based on the conflicting objects. The second inference space is used to form a third inference space according to the risk level.

Images