Airport stand control system and method based on airport surface dynamic regulation

Abstract

This invention relates to the field of air traffic management and intelligent control technology, specifically to an airport gate control system and method based on dynamic control of the airport surface; it includes the following steps: constructing a dynamic digital twin model capable of predicting future situations by real-time fusion of flight, surface surveillance, high-precision meteorological, and aircraft status data; predicting multi-dimensional operational conflicts, including weather mismatch and abnormal flight schedules, based on this model; intelligently generating and evaluating a coordinated control plan that integrates impact domain diffusion adjustment and fault-oriented safe gate strategies when receiving events such as sudden weather changes or aircraft malfunctions; parsing the optimal plan into differentiated instructions for roles such as control tower, apron, and ground services, and issuing them, tracking the execution status throughout the process; and finally, enabling the system rule base to self-optimize through a closed-loop feedback mechanism. This invention achieves efficient, coordinated, and early response to complex dynamic disturbances, improving the efficiency, safety, and resource utilization of airport ground operations.

Description

Technical Field

[0001] This invention relates to the field of air traffic management and intelligent control technology, specifically to an airport gate control system and method based on dynamic control of the airport surface. Background Technology

[0002] Airport gate resources are a core resource for ground operations, and the efficiency of their allocation and scheduling directly determines flight punctuality and airport operational capacity. Traditional gate allocation mainly relies on a static pre-allocation model based on flight schedules, which has inherent drawbacks: First, it has poor resilience to disturbances. When common dynamic events occur, such as flight delays, diversions, and especially sudden weather changes (airport weather or en route weather), the static plan cannot respond quickly, leading to gate conflicts and flight backlogs, often requiring manual intervention by air traffic controllers, which is inefficient and prone to errors. Second, the level of information integration is shallow. Existing systems fail to deeply integrate high-value dynamic data, especially refined meteorological forecast information (including impact range, intensity, and evolution trend) and real-time aircraft health status (such as fault reports) into decision-making models. For example, the system cannot predict that a certain aircraft stand area will be unavailable due to thunderstorms in 30 minutes, nor can it arrange for a flight to be moved to a maintenance-friendly stand in advance before landing due to a reported fault. Finally, decision-making is isolated and lacks coordination; adjustments are often limited to the aircraft stand itself, failing to simultaneously coordinate adjustments to ground support resources such as trailers, passenger boarding stairs, and refueling trucks and their travel routes, often leading to secondary conflicts or resource idleness.

[0003] While some studies have attempted to use optimization algorithms, they mostly focus on theoretical optimization under offline, single-objective, and ideal conditions. They have not yet formed a real-time collaborative intelligent control system that can operate online, provide closed-loop feedback, and coordinate multiple elements such as space, ground, air, and spacecraft. Summary of the Invention

[0004] To overcome the shortcomings of existing technologies, this invention proposes an airport gate control system and method based on dynamic control of the airport surface, which realizes real-time dynamic control of all elements of airport surface operation, and significantly improves operational safety, efficiency and resource utilization under complex and uncertain conditions.

[0005] The airport gate control method based on dynamic airport surface control described in this invention includes the following steps:

[0006] S1. Multi-source heterogeneous data fusion and dynamic digital twin construction: Real-time collection and fusion of flight operation data, airport surface surveillance data, high-precision meteorological forecast data and aircraft real-time status data to generate a spatiotemporally synchronized dynamic digital twin model of the airport surface that can predict future situations;

[0007] S2. Conflict prediction based on multidimensional dynamic constraints: Based on the dynamic digital twin model, the aircraft trajectory, gate occupancy, meteorological influence domain and facility status are comprehensively calculated to predict possible operational conflicts within a preset time period in the future;

[0008] S3. Intelligent control plan generation and evaluation integrating weather and abnormal impacts: When a conflict is predicted or a signal of sudden weather change or aircraft failure event is received, the plan analysis is triggered. Taking into account the single or combined impacts of local airport weather changes, flight schedule anomalies caused by airway weather, and aircraft failure special events, a collaborative control plan including gate reallocation, ground support resource rescheduling, and taxiing and towing path replanning is generated. The plan is then evaluated for multi-indicator effectiveness through simulation and output as the optimal plan.

[0009] S4. Hierarchical Collaborative Instruction Issuance and Full-Process Tracking: The optimal plan is parsed into a set of differentiated executable instructions for different execution roles and issued, while the execution status of the instructions is tracked in real time and compared with the expected progress of the plan;

[0010] S5. Closed-loop feedback and knowledge base self-optimization: Based on the data of the entire execution process of the contingency plan and the final running effect, adaptively adjust the rule parameters and weights in the rule base on which the contingency plan generation depends.

[0011] Preferably, in S1, the high-precision meteorological forecast data includes at least airport terminal area weather forecasts, route-specific weather information, and real-time meteorological radar data; the real-time aircraft status data includes at least fault codes transmitted through the aircraft communication addressing and reporting system.

[0012] Preferably, in S2, the operational conflict includes meteorological condition mismatch conflict, and the prediction method is: to perform spatiotemporal superposition calculation of the spatial distribution data of future meteorological elements and the safety standard threshold of each operating area of ​​the airport, and identify the operating area where the safety conditions will be lower than the standard in a specific period of the future.

[0013] Preferably, S2 also includes the prediction of abnormal flight time conflicts: by integrating route weather forecasts and aircraft performance data, the estimated arrival time of the flight is dynamically corrected, and the corrected time is compared with the available time windows of various resources to be occupied to predict conflicts.

[0014] Preferably, in S3, when responding to changes in local airport weather, the contingency plan generation follows the principle of impact domain diffusion adjustment, including reallocating safe parking positions for directly affected flights and adjusting flights and resources in adjacent areas in advance to reserve buffer zones.

[0015] Preferably, in S3, when an aircraft malfunction signal is received, the contingency plan generates a fault-oriented safe parking position strategy that is immediately triggered, prioritizing parking positions that are close to the maintenance apron, have special support capabilities, and have unobstructed towing paths as target parking positions.

[0016] Preferably, in S4, the differentiated set of executable instructions includes: instruction texts containing suggested runways and taxi routes issued to the air traffic control tower; structured work orders containing specific towing tasks and route planning issued to the airport apron operations control center; and notifications containing changes in the location of support resources issued to the ground services agent.

[0017] Preferably, in S4, the real-time tracking of the instruction execution status and comparison with the expected process in the plan involves continuously acquiring real-time location and status data and comparing it with the expected spatiotemporal node sequence in the plan; when the execution deviation of the key action exceeds the dynamic threshold, a local alarm is automatically triggered and the subsequent process is re-evaluated.

[0018] Preferably, in S5, the adaptive adjustment is achieved by: establishing a historical case library marked with scene features, the rule chain adopted, and the final performance index; and optimizing the triggering conditions, priority order, and parameters of the rules in the rule library through feature association analysis.

[0019] The airport gate control system based on dynamic control of the airport surface includes: a data acquisition module, an early warning module, a contingency plan generation module, an instruction issuance and tracking module, and a knowledge base management and self-optimization module; all modules are interconnected.

[0020] The beneficial effects of this invention are as follows:

[0021] This invention integrates weather forecasts with real-time aircraft status, enabling the system to issue early warnings and generate contingency plans tens of minutes before a conflict occurs, achieving a fundamental shift from post-event response to pre-event prevention. The proposed strategies, such as influence domain diffusion adjustment and fault-oriented safe parking positions, ensure the integrated and coordinated adjustment of parking positions, routes, and support resources, avoiding global chain reactions caused by local adjustments.

[0022] 2. Through a closed-loop learning mechanism, the system can accumulate experience in handling different scenarios (such as operational characteristics under specific weather conditions), continuously optimize internal rules, and enhance the system's decision-making ability over time, thus possessing long-term vitality. Attached Figure Description

[0023] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0024] Figure 1 This is a flowchart of the method in this invention;

[0025] Figure 2 This is a flowchart of the system in this invention. Detailed Implementation

[0026] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0027] like Figures 1-2 As shown, the airport gate control method based on dynamic airport surface control of the present invention includes the following steps:

[0028] S1. Multi-source heterogeneous data fusion and dynamic digital twin construction: Real-time collection and fusion of flight operation data, airport surface surveillance data, high-precision meteorological forecast data, and aircraft real-time status data to generate a spatiotemporally synchronized dynamic digital twin model of the airport surface capable of predicting future situations; The system accesses flight plans (FPL), radar / ADS-B signals, surface surveillance video, meteorological grid forecast data (such as numerical weather prediction products), and aircraft ACARS messages; Through time, alignment, coordinate systems, and confidence-based data association algorithms, this information is integrated into a virtual digital model that strictly corresponds to the physical airport; This model not only displays the current position of aircraft and vehicles, but also predicts the geographical diffusion of rain areas, wind fields, and visibility at the airport within the next 30-120 minutes based on meteorological data, and corrects the estimated arrival time based on aircraft performance and route wind and temperature forecasts;

[0029] S2. Conflict Prediction Based on Multidimensional Dynamic Constraints: Based on the aforementioned dynamic digital twin model, the system comprehensively calculates aircraft trajectories, gate occupancy, meteorological influence domains, and facility status to predict potential operational conflicts within a preset time period. Based on the current state (position, speed, intent) and preset rules (safety interval, gate occupancy time) of objects (aircraft, vehicles) in the dynamic digital twin model, and combined with the spatiotemporal changes in the meteorological influence domain, the system calculates the possible movement trajectories and resource occupancy status of all objects within a future period and detects whether these states violate safety or efficiency constraints. For example, it can not only detect two aircraft potentially vying for a single jet bridge simultaneously, but also predict that an apron area will experience visibility below standard due to thunderstorms an hour later, coinciding with a flight scheduled to taxi through that area.

[0030] S3. Intelligent Control Plan Generation and Evaluation Integrating Weather and Anomaly Impacts: When a conflict is predicted or a signal of a sudden weather event or aircraft malfunction is received, contingency plan analysis is triggered. This analysis comprehensively considers the single or combined impacts of local airport weather changes, flight schedule anomalies caused by en-route weather, and aircraft malfunctions. A collaborative control plan is generated, including gate reallocation, ground support resource rescheduling, and taxiing and towing path replanning. Multi-indicator effectiveness is evaluated through simulation, and the optimal plan is output. When a conflict is predicted, the system does not provide a single solution but, like a Go AI, it simulates multiple possible strategies (i.e., contingency plans) in parallel. Each plan is a complete collaborative adjustment scheme. The system uses a built-in rule base containing hundreds of rules to generate prototypes of these plans. Then, in a simplified, rapid simulation environment, the impact of each plan's execution on operational indicators for the next hour is evaluated, such as changes in total delay time, jet bridge utilization, total towing distance, and safety risk level. The optimal plan with the highest comprehensive score is selected through a multi-objective evaluation function.

[0031] S4. Hierarchical Collaborative Instruction Issuance and Full-Process Tracking: The optimal contingency plan is parsed into differentiated executable instruction sets for different execution roles and issued. Simultaneously, the execution status of the instructions is tracked in real time and compared with the expected progress of the contingency plan. The optimal contingency plan is a high-level decision that needs to be accurately translated into instructions that are understandable and executable by personnel in different positions. The system decomposes tasks according to role responsibilities: generating control suggestion instructions for tower controllers (e.g., suggesting that CES5678 use runway 36L to land, taxiing via Q8 and B taxiways to T15 bridge), generating detailed work orders for apron controllers (e.g., dispatching tow truck DT-07 to the intersection of B and Q8 to perform the towing operation of CES5678 to T15 bridge; the path has been issued to the vehicle terminal), and generating resource scheduling notifications for ground services (e.g., CES5678 bridge position changed to T15; please dispatch the cleaning team and refueling truck to T15). After the instructions are issued, the system continuously tracks whether the aircraft taxis as suggested and whether the tow truck moves along the path through real-time data streams, achieving a closed loop.

[0032] S5. Closed-loop feedback and knowledge base self-optimization: Based on the data of the entire process of contingency plan execution and the final running effect, the system adaptively adjusts the rule parameters and weights in the rule base on which the contingency plan generation depends; after each event is handled, the system automatically generates a case report, recording the scene characteristics (weather type, fault code, conflict type), the rule chain adopted (which rules were used to generate the contingency plan), and the final effect (e.g., handling time, secondary delays caused, etc.); through the accumulation of a large number of cases, the system uses statistical analysis or machine learning methods to find that certain rules are not effective in specific scenarios, and thus automatically adjusts the priority, trigger threshold or parameters of these rules, making the system more and more efficient and accurate in dealing with similar scenarios;

[0033] For example, in a real-world scenario;

[0034] Suppose a thunderstorm is approaching the airport from the southwest, while a flight from Beijing reports a landing gear indicator light malfunction;

[0035] Fusion perception: The data fusion module overlays the movement trajectory of thunderstorm clouds onto the airport map, predicting that the area of ​​jet bridges 101-110 will be severely affected 40 minutes later; at the same time, it receives and parses the ACARS fault message of the faulty flight (flight number CCA101).

[0036] Conflict Prediction: The system predicts that there will be a weather conflict for the flight scheduled to dock at Bridge 105 in 45 minutes; Bridge 115, where flight CCA101 was originally scheduled to dock, does not have the conditions for complex fault inspection, resulting in a conflict in support capabilities.

[0037] Contingency Plan Generation: The system generates two contingency plans and simulates them; Plan A: All flights affected by thunderstorms will be relocated to the north side of the airport, and CCA101 will be moved to remote stand 205, which is adjacent to the maintenance area; Plan B: Only the three bridge stands closest to the thunderstorms will be relocated, and CCA101 will be moved to cargo stand 601, which has a canopy. According to the simulation evaluation, although Plan A involves more towing operations, it provides a larger buffer space for the uncertainty of thunderstorms, and stand 205 is more conducive to troubleshooting, so it has a higher overall score.

[0038] Command Issuance and Tracking: The system issues the following command: the tower instructs CCA101 to fly directly into a specific approach procedure; a high-level tow truck is arranged on standby at the apron to quickly tow it from the runway gate to position 205; the maintenance department receives the command and prepares to check the equipment at position 205 in advance; the system monitors the entire landing and towing process of CCA101.

[0039] Feedback Optimization: The handling time took 5 minutes longer than the initial system estimate because the tow truck had to detour to avoid other aircraft during the journey. The system will record this case and will automatically increase the weight of the path accessibility index when generating contingency plans involving long-distance towing to the maintenance area in the future, and may plan a better avoidance path in advance.

[0040] In one embodiment of the present invention, in S1, the high-precision meteorological forecast data includes at least airport terminal area weather forecasts, important weather information along air routes, and real-time meteorological radar data; the real-time aircraft status data includes at least fault codes transmitted through the aircraft communication addressing and reporting system.

[0041] As one embodiment of the present invention, in S2, the operational conflict includes meteorological condition mismatch conflict, and the prediction method is: to perform spatiotemporal superposition calculation of the spatial distribution data of future meteorological elements and the safety standard threshold of each operating area of ​​the airport, and identify the operating area where the safety conditions will be lower than the standard in a specific period of the future.

[0042] In this invention, meteorological conflict prediction transforms the physical constraint of meteorological conditions into temporal and air conditioning control of operational resource availability. The system internally stores safe operating standards for various operational resources, such as the maximum crosswind limit for the B737 aircraft, the minimum runway visual range requirement for a Category I instrument landing system, and the thunderstorm and strong wind cessation threshold for apron operations. The acquired refined meteorological grid data provides specific meteorological element values ​​(wind speed, wind direction, visibility, precipitation intensity, etc.) for each future time and geographical point.

[0043] The system periodically (e.g., every 5 minutes) performs a spatiotemporal overlay calculation. It divides the timeline of the next 60 minutes into multiple segments. For each time segment, it overlays the weather forecast field with the airport geographic information layer. By traversing each gate, each taxiway, and each holding point, the system determines whether the weather conditions at that location are below its safe operating standards within that time segment. If so, the resource is marked as weather unavailable for that time period and immediately compared with the flight schedule. Any flight or vehicle activity planned to use the resource within that time period will be marked as a weather condition incompatibility conflict.

[0044] For example, in a real-world scenario: A weather forecast indicates that the airport will be affected by strong winds in one hour, with a wind direction of 270 degrees and a speed of 25 knots (lasting 10 minutes). The system overlays this wind field data with the airport layout map and calculates that runways 05 / 23, running east-west, will be affected by crosswinds exceeding the 22-knot crosswind limit for B737 aircraft. Simultaneously, the E-series taxiways located west of the runways and the adjacent E1-E5 parking positions are in the wind's path, posing a high risk to ground vehicles and personnel. The system predicts two scenarios: one is that all B737 and smaller aircraft scheduled to land on runway 23 in one hour will face a land-based weather conflict; the other is that ground services scheduled for loading / unloading or refueling operations at E1-E5 parking positions in one hour will face an operational weather conflict. Based on this, the system triggers contingency plans in advance.

[0045] As one embodiment of the present invention, S2 also includes the prediction of abnormal flight time conflicts: by integrating route weather forecasts and aircraft performance data, the estimated arrival time of the flight is dynamically corrected, and the corrected time is compared with the available time windows of various resources to be occupied to predict conflicts.

[0046] The scheduled arrival time of a flight is estimated based on standard routes and average weather conditions. In actual flight, strong tailwinds or headwinds, or detouring through thunderstorms, can significantly change the flight time. This invention dynamically integrates real-time route conditions with forecasted weather, combined with aircraft performance models, to achieve continuous rolling correction of the ETA, changing the prediction of gate availability time from fixed reservation to dynamic tracking.

[0047] The system maintains a dynamic arrival time for each flight in operation; it also integrates high-altitude wind and temperature forecasts and critical weather information along the flight path. When an aircraft enters the cruise phase, the system uses its ground speed, position, and wind and temperature forecasts along the route ahead to recalculate the remaining flight time based on a performance model. If weather conditions requiring detours are detected ahead, the system estimates the additional flight distance and time according to the detour plan. This dynamic arrival time is continuously updated. The system compares the updated arrival time with the planned time windows for occupied gates, jet bridges, and passenger boarding stairs. If the dynamic arrival time is more than a set threshold (e.g., 15 minutes) earlier or later than the planned time, the system determines that the flight has an abnormal time conflict with reserved resources, as the original resources may not have been released or may have been occupied by other flights.

[0048] For example, consider a real-world scenario: Flight CSN8888 flies from Guangzhou to Beijing with a scheduled arrival time (ETA) of 14:00. It plans to use gate 306 from 14:00 to 15:30. During the flight, the system detects, based on real-time weather data, that the flight is encountering unusually strong tailwinds in North China, with ground speeds 80 km / h higher than expected. Through dynamic calculation, its arrival time is revised to 13:38, 22 minutes earlier. The system immediately compares the revised arrival time (13:38) with the occupancy status of gate 306 and finds that the preceding flight, CSN7777, is scheduled to launch at 13:45. Therefore, the system predicts that CSN8888 will have a gate occupancy conflict with the yet-to-launch CSN7777 between 13:38 and 13:45, triggering an alert.

[0049] As one embodiment of the present invention, in S3, when dealing with changes in the local weather at the airport, the contingency plan generation follows the principle of influence domain diffusion adjustment, including reallocating safe parking positions for directly affected flights and adjusting flights and resources in adjacent areas in advance to reserve a buffer zone.

[0050] Traditional adjustments only target directly affected flights, which can easily lead to piecemeal solutions, spreading the problem to adjacent areas. The principle of this invention's impact domain diffusion adjustment is preventative spatial resource reorganization. When a region (such as the west apron) is predicted to be affected by weather, the system not only reallocates flights within that region but also assesses the uncertainty of weather movement and evolution, proactively relocating some non-emergency flights from adjacent buffer zones (such as the aircraft stands on both sides of the main taxiway connected to the west apron). The purposes of this are: first, to reserve safe alternate landing aircraft and towing lanes for aircraft that may need emergency diversions or transfers due to sudden weather changes; second, to prevent all affected flights from concentrating in a few safe areas, causing new congestion; and third, to facilitate the concentrated and efficient operation of ground support vehicles in safe areas. During implementation, the system dynamically calculates the required buffer zone clearance based on the intensity, speed, and uncertainty radius of the weather impact.

[0051] For example, in a real-world scenario: a thunderstorm cloud is predicted to cover cargo aprons 1-10 on the south side of the airport; the system initiates an adjustment to the spread of the impact area; the first step is to move all cargo flights scheduled to park at positions 1-10 to the north cargo apron; the second step is to make advance adjustments: the temporary cargo positions 11-15 on both sides of the main smooth lane G used for cargo vehicle passage, which is adjacent to positions 1-10, are also cleared, and flights at these positions are moved to more distant positions; in this way, when the thunderstorm arrives, even if a cargo plane needs to be detached or towed urgently, the smooth lane G and the area on both sides are free of aircraft and obstacles, becoming a safe emergency passage.

[0052] As one embodiment of the present invention, in S3, when an aircraft malfunction signal is received, a contingency plan is generated to immediately trigger a fault-oriented safe parking position strategy, prioritizing parking positions that are close to the maintenance apron, have special support capabilities, and have unobstructed towing paths as target parking positions.

[0053] The key to aircraft malfunction handling is the optimal matching of time and space; this mainly involves immediately translating malfunction information into a demand for specific aircraft stand attributes and achieving optimal resource matching. When the system receives a clear malfunction code (such as ENG1OILPRESSLOW) via ACARS or voice communication, it immediately queries the stand-support capability database in the background. This database records whether each stand has the following attributes: large power supply vehicle, air conditioning vehicle, hydraulic oil vehicle interface, proximity to hangar or maintenance apron, and wide and unobstructed towing path. Based on the malfunction type, the system matches the demand with the stand attributes, prioritizing the stand with the shortest overall towing distance, the easiest access to support resources, and the least impact on subsequent operations.

[0054] For example, in a real-world scenario: An A330 aircraft reports a suspected malfunction in its nose landing gear steering system. Upon receiving the code, the system triggers a fault-oriented safe parking position strategy. The rule base defines that such malfunctions require: a spacious parking position for inspection; proximity to the maintenance apron for potential major overhauls; and a towing path that avoids sharp bends. The system filters out a suitable target parking position: remote parking position 801 (close to the maintenance apron, spacious, and with a straight towing path). Simultaneously, the system automatically generates a supporting plan: instructs a tow truck (which must be a high-powered tow truck) to be in place in advance, and notifies the maintenance department to bring the A330 nose landing gear inspection equipment to parking position 801 to wait. The entire process is arranged before the flight lands.

[0055] As one embodiment of the present invention, in S4, the differentiated set of executable instructions includes: instruction texts containing suggested runways and taxi routes issued to the air traffic control tower; structured work orders containing specific towing tasks and route planning issued to the airport apron operations control center; and notifications containing changes in the location of support resources issued to the ground services agent.

[0056] As one embodiment of the present invention, in S4, the real-time tracking of the instruction execution status and comparison with the expected process in the plan is achieved by continuously acquiring real-time location and status data and comparing it with the expected spatiotemporal node sequence in the plan; when the execution deviation of the key action exceeds the dynamic threshold, a local alarm is automatically triggered and the subsequent process is re-evaluated.

[0057] Different positions require different granularities and perspectives of information; the control tower focuses on air sequence and macro-paths; apron control focuses on the details of ground movement of specific vehicles and aircraft; ground services focus on the location and timing of support resources; the system needs to translate high-level decisions into instructions that are adapted to the work interfaces and responsibilities of each role; at the same time, issuing instructions does not mean the task is completed, and it is necessary to monitor whether the actual execution deviates from the plan in order to intervene in a timely manner.

[0058] The system has a built-in instruction template library; for the control tower, instructions are formatted into concise standard air-to-ground communication suggestion phrases and displayed via digital broadcasts or prompt boxes; for apron control, instructions are converted into structured data containing origin and destination points, waypoints, task type, executing vehicle ID, and time nodes, which can be imported into the airfield monitoring system or a dedicated tablet for graphical display; for ground services, instructions are dispatched to specific support teams in the form of work orders through the resource scheduling system; all instructions have a unique task ID for easy tracking; the system predefines an expected sequence of multiple key spatiotemporal nodes for each critical task (such as towing an aircraft from point A to point B); for example, node 1: the tow truck and aircraft docking is completed (time T1, position P1); Point 2: Begin moving (T2); Node 3: Pass through critical intersection C (T3, position P3)...; During mission execution, the data fusion module continuously provides the real-time positions of the aircraft and vehicles; the tracking module compares the real-time positions with the expected node sequence; if the aircraft has not reached position P3 by time T3 and the deviation exceeds a threshold dynamically calculated based on the current scene activity density (e.g., a static threshold of 3 minutes, which can be relaxed to 5 minutes during dynamic busy periods), the system determines that the mission has derailed and triggers a yellow alarm; the alarm will prompt the controller to pay attention and automatically initiate a lightweight follow-up process reassessment to determine whether the delay will affect subsequent flights; if the deviation is extremely large, the system may directly trigger a new fine-tuning contingency plan generation process;

[0059] For example, in a real-world scenario: The system instructs tow truck TV-10 to tow aircraft B-1234 from bridge 215 to maintenance apron M2, with an estimated time of 12 minutes. The system's critical milestone is that it should pass through the intersection of taxiways T5 and T6 by the 5th minute. Real-time tracking reveals that at the 7th minute, B-1234 is still stopped 50 meters before the intersection (due to refueling operations ahead). This deviation of 2 minutes exceeds the threshold (1.5 minutes for the current time period). The system triggers an alarm, and the task is highlighted in yellow on the apron controller's interface. Simultaneously, the system quickly assesses that this delay will postpone another task scheduled to be performed using the tow truck. The system automatically generates a minor adjustment suggestion: informing the ground service team of the subsequent task flight that their support start time is expected to be delayed by 5 minutes.

[0060] As one embodiment of the present invention, in S5, the adaptive adjustment is achieved by: establishing a historical case library marked with scene features, rule chains adopted and final performance indicators, and optimizing the triggering conditions, priority order and parameters of rules in the rule library through feature association analysis;

[0061] The system treats each complete handling process as a case study; by analyzing the relationship between scene characteristics, actions taken, and outcomes in a large number of cases, the system can discover which rules are more effective under what conditions, thereby optimizing decision-making logic.

[0062] The system automatically generates structured records for each handling case; scene features are encoded as feature vectors, such as: [weather type = thunderstorm, affected area = west apron, time period = evening peak, fault type = none]; the rule chain used is recorded as a rule ID sequence; performance indicators include multiple dimensions, such as: total handling time, total number of minutes of additional delay caused, extra mileage of tow trucks, etc.; these cases constitute a historical case library; periodically (e.g., weekly), the self-optimization module runs the analysis program; for example, using association rule mining (e.g., the Apriori algorithm), it was found that when the scene features include [weather type = heavy snow, time period = morning peak], if rule R32 (prioritizing wide-body aircraft docking at the bridge) is frequently used, the average additional delay index is generally high; this indicates that rule R32 may be too rigid in the morning peak heavy snow scenario; the system may then automatically adjust: when the condition [weather type = heavy snow, time period = morning peak] is met, reduce the priority weight of rule R32, or add an additional constraint condition (e.g., only triggered when no narrow-body aircraft is scheduled to use the bridge in the following hour).

[0063] Taking a real-world scenario as an example: Initially, the system was set up so that when a flight was delayed by more than 30 minutes, rule R105, which reassigns the flight to an adjacent gate of the same airline, had a higher weight, aiming to facilitate ground service support. However, after several months of operation, the learning module analyzed cases and found that, during nighttime hours, while applying this rule reduced the distance ground service personnel had to travel, it often led to jet bridge utilization issues (the concentration of gates of the same airline resulted in some jet bridges being idle while others were congested). Therefore, the system automatically added a time decay function to rule R105: during nighttime (22:00-06:00), the weight of this rule was automatically halved, making the system more inclined to adopt the global optimization rule of using the nearest and most efficient jet bridges at night, rather than the company clustering rule.

[0064] The airport gate control system based on dynamic airport surface control includes: a data acquisition module, an early warning module, a contingency plan generation module, an instruction issuance and tracking module, and a knowledge base management and self-optimization module. These modules are interconnected. This system serves as the physical and software carrier of the method. The data acquisition module corresponds to a data server and access gateway; the early warning and contingency plan generation modules correspond to application servers running core algorithms; the instruction issuance and tracking module corresponds to a communication server and various terminal interfaces; and the knowledge base management and self-optimization module corresponds to a database server and a machine learning platform. These modules are interconnected through an internal high-speed network and interact via API calls and a data bus in the software, collaboratively completing all the functions of the airport gate control method based on dynamic airport surface control. Through modular design, complex intelligent control tasks are decomposed into different specialized processing units and then integrated.

[0065] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. An airport gate control method based on dynamic control of the airport surface, characterized in that, Includes the following steps: S1. Multi-source heterogeneous data fusion and dynamic digital twin construction: Real-time collection and fusion of flight operation data, airport surface surveillance data, high-precision meteorological forecast data and aircraft real-time status data to generate a spatiotemporally synchronized dynamic digital twin model of the airport surface that can predict future situations; S2. Conflict prediction based on multidimensional dynamic constraints: Based on the dynamic digital twin model, the aircraft trajectory, gate occupancy, meteorological influence domain and facility status are comprehensively calculated to predict possible operational conflicts within a preset time period in the future; S3. Intelligent control plan generation and evaluation integrating weather and abnormal impacts: When a conflict is predicted or a signal of sudden weather change or aircraft failure event is received, the plan analysis is triggered. Taking into account the single or combined impacts of local airport weather changes, flight schedule anomalies caused by airway weather, and aircraft failure special events, a collaborative control plan including gate reallocation, ground support resource rescheduling, and taxiing and towing path replanning is generated. The plan is then evaluated for multi-indicator effectiveness through simulation and output as the optimal plan. S4. Hierarchical Collaborative Instruction Issuance and Full-Process Tracking: The optimal plan is parsed into a set of differentiated executable instructions for different execution roles and issued, while the execution status of the instructions is tracked in real time and compared with the expected progress of the plan; S5. Closed-loop feedback and knowledge base self-optimization: Based on the data of the entire execution process of the contingency plan and the final running effect, adaptively adjust the rule parameters and weights in the rule base on which the contingency plan generation depends.

2. The airport gate control method based on dynamic control of the airport surface as described in claim 1, characterized in that, In S1, the high-precision meteorological forecast data includes at least airport terminal area weather forecasts, important weather information along air routes, and real-time meteorological radar data; the real-time aircraft status data includes at least fault codes transmitted through the aircraft communication addressing and reporting system.

3. The airport gate control method based on dynamic control of the airport surface as described in claim 1, characterized in that, In S2, the operational conflict includes meteorological condition mismatch conflict, and its prediction method is: to perform spatiotemporal superposition calculation of the spatial distribution data of future meteorological elements and the safety standard threshold of each operating area of ​​the airport, and identify the operating area where the safety conditions will be lower than the standard in a specific period of the future.

4. The airport gate control method based on dynamic control of the airport surface as described in claim 3, characterized in that, The S2 also includes the prediction of abnormal flight schedule conflicts: by integrating route weather forecasts and aircraft performance data, the estimated arrival time of the flight is dynamically corrected, and the corrected time is compared with the available time windows of various resources to be occupied to predict conflicts.

5. The airport gate control method based on dynamic control of the airport surface as described in claim 1, characterized in that, In S3, when dealing with changes in local airport weather, the contingency plan is generated in accordance with the principle of impact domain diffusion adjustment, including reallocating safe parking positions for directly affected flights and adjusting flights and resources in adjacent areas in advance to reserve buffer zones.

6. The airport gate control method based on dynamic control of the airport surface according to claim 1, characterized in that, In S3, when an aircraft malfunction signal is received, the contingency plan is generated and immediately triggers the fault-oriented safe parking position strategy, prioritizing parking positions that are close to the maintenance apron, have special support capabilities, and have unobstructed towing paths as target parking positions.

7. The airport gate control method based on dynamic control of the airport surface according to claim 1, characterized in that, In S4, the differentiated set of executable instructions includes: instruction texts containing suggested runways and taxi routes issued to the air traffic control tower; structured work orders containing specific towing tasks and route planning issued to the airport apron operations control center; and notifications containing changes in the location of support resources issued to ground service agents.

8. The airport gate control method based on dynamic control of the airport surface according to claim 7, characterized in that, In S4, the real-time tracking of the instruction execution status and comparison with the expected process in the plan are achieved by continuously acquiring real-time location and status data and comparing it with the expected spatiotemporal node sequence in the plan; when the execution deviation of the key action exceeds the dynamic threshold, a local alarm is automatically triggered and the subsequent process is re-evaluated.

9. The airport gate control method based on dynamic control of the airport surface according to claim 1, characterized in that, In S5, the adaptive adjustment is achieved by: establishing a historical case library marked with scene features, rule chains adopted, and final performance indicators; and optimizing the triggering conditions, priority order, and parameters of rules in the rule library through feature association analysis.

10. An airport gate control system based on dynamic airport surface control, applicable to the airport gate control method based on dynamic airport surface control as described in any one of claims 1-9, characterized in that, include: The system includes a data acquisition module, an early warning module, a contingency plan generation module, an instruction issuance and tracking module, and a knowledge base management and self-optimization module. Communication connections between modules.

Images