A method and system for constructing a comprehensive index system for airport safety operation diagnosis based on digital twinning

Abstract

This invention relates to the field of smart airport technology, specifically to a method and system for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins. This invention maps multi-source heterogeneous airport operational data to a unified data model within a digital twin, constructing a dual-view indicator system comprising a first safety operation object view and a second departmental responsibility performance view. Dynamic anomaly-safety composite weight parameters and refined departmental-business type multi-dimensional parameter matrices are configured for each view, enabling synchronous three-dimensional visualization and intelligent source tracing analysis of the fused calculation results of the indicator system. This invention solves the technical problems of data and scenario disconnect, fixed diagnostic dimensions, isolated alarms, and difficulty in spatially tracing anomalies in existing airport operation monitoring. It achieves scenario-based, spatial, and intelligent diagnostic processes, significantly improving the accuracy of airport safety situational awareness, the speed of anomaly location, and the efficiency of collaborative decision-making.

Description

Technical Field

[0001] This invention relates to the field of smart airport technology, and more specifically, to a method and system for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins. Background Technology

[0002] As complex transportation hubs and operational systems, the safe and efficient operation of modern airports relies on the close collaboration of multiple subsystems, including air traffic control, flight support, terminal services, and ground operations. With the deepening of smart airport construction, although the automation level of various business subsystems (such as air traffic control automation systems, flight information integration systems, and security management platforms) is constantly improving, the following fundamental technical bottlenecks still exist in terms of the overall and forward-looking diagnosis of operational safety:

[0003] First, the problems of data heterogeneity and scenario fragmentation are severe. Different subsystems use different data standards and have different interfaces, forming robust "data silos." More importantly, traditional monitoring dashboards can only display isolated data in chart form, lacking the ability to accurately and dynamically map data to the airport's three-dimensional physical space (such as runways, aprons, and terminals). Decision-makers struggle to understand data within a "scenario," unable to intuitively perceive the impact of congestion in a certain area or a malfunction in a piece of equipment on the overall picture—in other words, they lack "scenario-based perception" capabilities.

[0004] Secondly, the static nature of diagnostic logic and the difficulty in collaborative tracing are significant challenges. Existing assessments often rely on post-event statistical reports or simple alarms based on fixed rules, resulting in a single assessment dimension (e.g., focusing only on flight on-time performance). When anomalies occur, alarm information is scattered across various systems, lacking a mechanism that can intelligently correlate and visually trace the deterioration of the macro-level operational situation (e.g., "decreased overall airport operational efficiency") with micro-level departmental responsibilities (e.g., "flight support delays by the maintenance department") and specific spatial locations (e.g., "faulty boarding bridge at Gate 203"). This leads to time-consuming problem localization and inefficient collaborative handling.

[0005] Secondly, there is a lack of predictive control methods that allow for interaction between the virtual and real worlds. Most current systems are limited to recording and presenting events that have already occurred, and cannot simulate and evaluate the safety situation after adjustments to operational strategies (such as changing the taxiing route or adjusting support resources) in the digital space. In other words, they lack the "simulation and pre-playing" capability to optimize real-world decisions using virtual models, resulting in passive and lagging risk management.

[0006] Digital twin technology offers a new solution to the aforementioned problems. By creating a virtual image of a physical airport and enabling real-time data interaction between the virtual and real worlds, it provides an ideal platform for global perception. However, there is currently no mature solution for transforming the complex management objective of airport operational safety into a quantitative indicator system that can be effectively calculated, dynamically presented, and used to support decision-making within the digital twin. Existing technologies mostly use twins for 3D visualization and simple data overlay, and have not yet delved into the in-depth construction and intelligent application of multi-dimensional, configurable diagnostic indicator systems.

[0007] Therefore, there is an urgent need for an innovative technical solution that can deeply integrate the "virtual-real fusion" capability of digital twins with the "diagnosis and tracing" requirements of airport operation safety, and build a comprehensive indicator system that grows, operates, and feeds back into the physical world in the twin environment. Summary of the Invention

[0008] The purpose of this invention is to provide a method and system for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins, so as to solve the above-mentioned problems in the prior art.

[0009] This invention is achieved through the following technical solution: Firstly, a method for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins includes: Acquire heterogeneous operational data in the current airport physical space, and map the preprocessed heterogeneous operational data into the data model of the airport digital twin; Based on the data model, a set of logically related and complementary safety operation object view indicators and a set of departmental responsibility performance view indicators are constructed to form a comprehensive indicator system. Set composite weight coefficients for the first set of safety operation object view indicators, and set a multi-dimensional parameter matrix for the second set of departmental responsibility performance view indicators; Based on composite weight coefficients and multidimensional parameter matrices, the indicators in the comprehensive indicator system are quantitatively calculated and integrated to generate the airport operation health index and the department operation health index respectively. Based on the synchronous rendering and related display of the airport operation health index and the department operation health index, when an abnormal indicator of an abnormal index occurs, a diagnostic report is generated based on the entity association relationship in the digital twin, and the department to which the abnormal indicator belongs is highlighted.

[0010] Preferably, the secure operation object view indicator set includes a first top-level module and a first lower-level module; The first top-level module includes an airport safety operation comprehensive index that characterizes the overall operational status of the airport, and the first lower-level module includes object indicators that are dynamically linked to flight operations, passenger services, and energy management based on real-time calculations using twin data.

[0011] Preferably, the departmental responsibility performance view indicator set includes a second top-level module and a second lower-level module; The second top-level module includes the division of responsibility boundaries for the Airport Operations Control Center (AOC), Flight Area Operations Management Center (ROC), Terminal Area Operations Management Center (TOC), and Public Area Operations Management Center (POC). The second lower-level module includes business flow indicators that are dynamically decomposed into each department.

[0012] Preferably, the composite weighting coefficient includes an anomaly sensitivity coefficient and a steady-state protection coefficient. The quantitative calculation and fusion of the safe operation object view index set based on the composite weighting coefficient includes:

[0013] In the formula, The airport's operational health index The abnormal sensitivity coefficient, The score is normalized and aggregated to reflect global anomaly information. For steady-state protection coefficient, , The score is normalized and aggregated for global security information.

[0014] Preferably, the global anomaly information normalized aggregation score and the global security information normalized aggregation score include: The indicators in the safe operation object view indicator set are classified into anomaly information indicator set and safety information indicator set; Calculate the aggregated score for abnormal information and the aggregated score for security information for the indicators in the abnormal information indicator set and the security information indicator set, respectively. The aggregated scores of abnormal information and security information are aggregated a second time to obtain the normalized aggregated score of global abnormal information and the normalized aggregated score of global security information.

[0015] Preferably, the quantitative calculation and fusion of departmental responsibility performance view indicator sets based on multidimensional parameter matrices includes: Configure a multidimensional parameter matrix, which includes several matrix cells. The matrix cells store the aggregation method, indicator weights, and health thresholds of the current business in the current department. The department includes several types of business. The configuration tuples of matrix cells are obtained from the multidimensional parameter matrix. The atomic indicator data of business classification under each department are collected. The business score is calculated based on the aggregation method in the matrix cell. The departmental operational health index of the current indicator is output according to the business score and the calculation weight of each business.

[0016] Preferably, the business score calculated based on the aggregation method and atomic indicator data in the matrix cells includes: If the aggregation method is a weighted average, the business score includes:

[0017] In the formula, The weighted average business score, To configure tuples, As the indicator weight, For input data.

[0018] Preferably, if the aggregation method follows the weakest link principle, the business score includes:

[0019] In the formula, The score is based on the "weakest link" principle.

[0020] Preferably, if the aggregation method is a comprehensive evaluation of the matching degree of capacity supply and demand, the business score includes:

[0021] In the formula, To score business performance, To ensure the total effective supply of transportation capacity across multiple modes, To take into account the total passenger demand, To be A non-linear function mapped to the baseline score interval. This refers to a specific mode of transportation on the airport's landside, such as subway, airport bus, taxi, or ride-hailing service. The set of all modes of transportation participating in the assessment, i.e. , The penalty coefficient is... For real-time saturation of each mode, This represents the comfort threshold.

[0022] Secondly, the present invention also provides a method for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins, including the aforementioned method for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins, comprising: The data processing module is configured to acquire heterogeneous operational data in the current airport physical space, preprocess the heterogeneous operational data and map it to the data model of the airport digital twin; based on the data model, construct a set of logically related and complementary safety operation object view indicators and a set of departmental responsibility performance view indicators to form a comprehensive indicator system; set a composite weight coefficient for the first set of safety operation object view indicators and set a multi-dimensional parameter matrix for the second set of departmental responsibility performance view indicators; The calculation module is configured to quantify and integrate the indicators in the comprehensive indicator system based on composite weight coefficients and multidimensional parameter matrices, and generate the airport operation health index and the department operation health index respectively. Based on the airport operation health index and the department operation health index, synchronous rendering and associated display are performed. When an abnormal indicator of an abnormal index occurs, a diagnostic report is generated based on the entity association relationship in the digital twin, and the department to which the abnormal indicator belongs is highlighted.

[0023] The technical solution of the present invention has at least the following advantages and beneficial effects: The method provided in this invention maps multi-source heterogeneous airport operational data to a unified data model within a digital twin, constructing a dual-view indicator system that includes a view of safe operation objects and a view of departmental responsibility and performance. Dynamic anomaly-safety composite weight parameters and refined departmental-business type multi-dimensional parameter matrices are configured for each view, enabling synchronous 3D visualization and intelligent traceability analysis of the fused calculation results of the indicator system. This method achieves "scenario-based" and "spatialized" diagnostics: by deeply embedding the indicator system into the digital twin, all indicator calculation results can be linked and visualized in real time with specific objects (runways, boarding bridges, vehicles), areas (terminal zones), or departmental jurisdictions in 3D space, transforming abstract "data" into intuitive "scenario situations," greatly improving the efficiency and accuracy of operational status perception.

[0024] A three-dimensional diagnostic closed loop of "macro-micro-spatial" was constructed: the innovative "dual-view" architecture was naturally integrated in the twin environment. A decline in macro health can be automatically linked to abnormal micro-department indicators, and further located in the three-dimensional scene to the specific physical location or device. This enables rapid, accurate, and visualized tracing of the source from the global situation to local responsibility and spatial root cause, significantly enhancing decision support capabilities.

[0025] This endows the indicator system with dynamic adaptability and strategy prediction capabilities: the combination of parameterized configuration models and a twin environment enables the indicator system to dynamically adjust according to real-time perceived operational patterns (such as weather changes). More importantly, managers can modify configuration parameters or simulate resource scheduling (static airport resources) in the twin environment and immediately see the changes in the safety situation after the simulation through the indicator system, thereby achieving predictive control through "trial before implementation" and improving the foresight of risk management.

[0026] The system's interpretability and human-machine collaboration have been enhanced: a visual parameter configuration interface, highlighted traceability paths in a 3D scene, and structured diagnostic reports make complex diagnostic logic transparent and understandable. This not only improves the system's credibility but also allows operation and management personnel to deeply participate in the diagnostic process, making more accurate and faster collaborative decisions. Attached Figure Description

[0027] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 A schematic diagram of the overall logical framework of the comprehensive index system construction method provided in the embodiments of the present invention; Figure 2 This is a schematic diagram of the core innovation of this invention, the "logical architecture of dual-view coupling"; Figure 3 This is a schematic diagram of the hierarchical structure of "First Logical View: Target Decomposition View"; Figure 4 This is a schematic diagram of the hierarchical structure of the "Second Logical View: Responsibility Tracing View"; Figure 5 This is a schematic diagram illustrating the steps and effects of the "Anomaly Collaborative Diagnosis and Source Tracing Analysis Process". Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0030] Please refer to Figures 1-5This invention provides a method for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins, comprising: S101: Obtain heterogeneous operational data in the current airport physical space, and map the heterogeneous operational data into the data model of the airport digital twin after preprocessing; The system collects heterogeneous operational data from air traffic control, flight support, surface surveillance, passenger services, and key equipment and facilities systems in the airport's physical space in real time. The data is then cleaned, aligned, and standardized, and the processed data is synchronously mapped to the unified data model of the airport's digital twin.

[0031] Data on key equipment and facilities systems includes the status of navigation lighting systems, the opening and closing status of check-in counters, the opening and closing status of security checkpoints, the failure rate of baggage sorting systems, and heat map data of terminal passenger flow density generated based on sensor data fusion.

[0032] S102: Based on the data model, construct a set of logically related and complementary safety operation object view indicators and a set of departmental responsibility performance view indicators in the situation awareness module to form a comprehensive indicator system; The safe operation object view indicator set is constructed using a top-down object-oriented architecture. Its first top-level module is the comprehensive airport safe operation index (also known as the airport overall operation health) that represents the overall operation status of the airport. The first lower-level module is dynamically associated with core business object indicators such as flight operation, passenger service, and energy management, which are calculated in real time based on twin data. The surface safety indicators in the safe operation object view indicator set include runway incursion risk probability indicators that belong to the flight operation support category and are calculated in real time using a conflict probability model based on surface surveillance data. The departmental responsibility performance view indicator set is constructed using a top-down departmental architecture. Its second top-level module is divided according to the responsibility boundaries of the Airport Operations Control Center (AOC), Flight Area Operations Management Center (ROC), Terminal Area Operations Management Center (TOC), and Public Area Operations Management Center (POC). The second lower-level module is dynamically decomposed into business flow indicators within each department.

[0033] The departmental performance view indicators focus on the business flow indicators of the AOC department, including flight departure on-time rate, transit flight on-time rate, gate turnover utilization rate, and runway takeoff and landing capacity.

[0034] S103: Set composite weight coefficients for the first safe operation object view indicator set, and set a multi-dimensional parameter matrix for the second departmental responsibility performance view indicator set; Among them, the composite weighting coefficient is used to independently adjust the degree of influence of negative events and positive status on the overall health assessment of the view, and can be dynamically adjusted according to the real-time operation mode perceived from the digital twin. In special weather or peak operation mode, the value of the abnormal information weight is automatically increased to enhance risk sensitivity.

[0035] The multidimensional parameter matrix is ​​used to set independent calculation rules and health judgment thresholds for indicators of different business types under different departments. It supports the preset of multiple configuration schemes according to typical operating scenarios and can be switched and loaded with one click in the visualization interface.

[0036] S104: Based on the composite weight coefficient and multidimensional parameter matrix, the indicators in the comprehensive indicator system are quantitatively calculated and integrated to generate the airport operation health index and the department operation health index respectively. Specifically, a dynamic weighted dual-path aggregation algorithm and a matrix-driven hierarchical aggregation algorithm are used to quantify and fuse the indicators in the comprehensive indicator system, generating the overall airport operational health index in the first view and the operational health indices of each department in the second view. The indices and their underlying indicator data are then synchronously rendered and displayed in conjunction with each other in the corresponding 3D scene and management panel of the digital twin visualization interface. S105: Based on the airport operation health index and the department operation health index, perform synchronous rendering and related display. When an abnormal indicator of an abnormal index occurs, generate a diagnostic report based on the entity association relationship in the digital twin, and highlight the department to which the abnormal indicator belongs.

[0037] Anomaly tracing and diagnostic report generation based on indicator association: When any health index or key indicator in the comprehensive indicator system becomes abnormal, based on the entity association relationship in the digital twin, collaborative association analysis is performed on the dual-view indicator set to automatically generate a diagnostic report, and the tracing path from the global anomaly to the specific responsible department and the root cause of the indicator is highlighted in the visualization interface.

[0038] Specifically, the diagnostic report simultaneously displays the historical trend of the health index in the form of visual charts, and presents the dynamic correlation path between abnormal indicators in the digital twin 3D scene through highlighting, connecting lines, or pulse animation. The method provided in this invention maps multi-source heterogeneous airport operational data to a unified data model within a digital twin, constructing a dual-view indicator system that includes a view of safe operation objects and a view of departmental responsibility and performance. Dynamic anomaly-safety composite weight parameters and refined departmental-business type multi-dimensional parameter matrices are configured for each view, enabling synchronous 3D visualization and intelligent traceability analysis of the fused calculation results of the indicator system. This method achieves "scenario-based" and "spatialized" diagnostics: by deeply embedding the indicator system into the digital twin, all indicator calculation results can be linked and visualized in real time with specific objects (runways, boarding bridges, vehicles), areas (terminal zones), or departmental jurisdictions in 3D space, transforming abstract "data" into intuitive "scenario situations," greatly improving the efficiency and accuracy of operational status perception.

[0039] An exemplary embodiment of the present invention aims to calculate the "overall airport operational health index" at the macro level. Its core feature is the introduction and dynamic application of an "anomaly-safety composite weight parameter," enabling the assessment to adapt to different operational scenarios. The composite weight coefficient includes an anomaly sensitivity coefficient and a steady-state assurance coefficient. The quantitative calculation and fusion of the set of safe operational object view indicators based on the composite weight coefficient includes:

[0040] In the formula, This is the airport operational health index (final output, value range 0-1 or 0-100). For abnormal sensitivity coefficient, satisfying , The score is normalized and aggregated to reflect global anomaly information. For steady-state protection coefficient, , The score is normalized and aggregated for global security information.

[0041] The normalized aggregate score for global anomaly information and the normalized aggregate score for global security information include: S201: Classify the indicators in the safe operation object view indicator set into an abnormal information indicator set and a safety information indicator set; From the unified data model of the digital twin, extract real-time data of all atomic indicators under the four preset dimensions (flight operation, passenger service, energy management, and transportation support) of the first view (safe operation object view).

[0042] Based strictly on the standardization results of step 1 and the view definition of step 2, each atomic indicator is classified into either anomaly information (negative) or security information (positive) indicator sets.

[0043] S202: Calculate the aggregated score of abnormal information and the aggregated score of security information for the indicators in the abnormal information indicator set and the security information indicator set, respectively;

[0044]

[0045] in, and These are the aggregated scores for abnormal information and the aggregated scores for security information, respectively. and These are the preset basic weights of the indicators. and These are indicators from the abnormal information indicator set and the security information indicator set, respectively. To convert the original index value Normalization functions that map to the [0,1] interval (such as min-max normalization or threshold-based piecewise functions).

[0046] S203: Perform a second aggregation on the aggregated scores of abnormal information and the aggregated scores of security information to obtain the normalized aggregated scores of global abnormal information and global normalized aggregated scores of security information.

[0047]

[0048]

[0049] In the formula, and These are the preset importance weights of the indicators in the abnormal information indicator set and the security information indicator set for the overall assessment.

[0050] Apply dynamic weights and generate an index: Obtain real-time weights: Based on the real-time operating mode perceived from the digital twin (such as "thunderstorm weather" or "peak hour"), invoke the rules preset in step S103 to determine the currently applicable weights. value.

[0051] Substitute into the core formula for calculation: , , , Substituting into the core calculation formula, we get .

[0052] Health status assessment: Compared with the preset global threshold, it is mapped to three states: "healthy (green)", "warning (yellow)" and "abnormal (red)".

[0053] An exemplary embodiment of the present invention, which quantifies and integrates a set of departmental responsibility performance view indicators based on a multidimensional parameter matrix, includes: Configure a multi-dimensional parameter matrix, which includes several matrix cells. Each matrix cell stores the aggregation method, indicator weights, and health thresholds for the current business in the current department. The department includes several types of business. Obtain the configuration tuples of the matrix cells from the multi-dimensional parameter matrix, collect the atomic indicator data of the business classification under each department, calculate the business score based on the aggregation method in the matrix cell, and output the department's operational health index for the current indicator based on the business score and the calculated weight of each business.

[0054] Specifically, data input includes real-time values ​​of all atomic business metrics belonging to each department (AOC, ROC, TOC, POC).

[0055] Rule input: "Department-Business Type Multidimensional Parameter Matrix". The matrix cells store the aggregation methods, indicator weights, and health thresholds configured for specific business types (security, efficiency, service, resources) under a specific department.

[0056] Step 1.1: Read Matrix Configuration: Retrieve the configuration tuple of the cells from the matrix. ,in, , , These are the aggregation method, indicator weights, and health thresholds, respectively.

[0057] Step 1.2: Collection and Classification: Collect all business-related data and classify them into categories. Atomic index data , For the department, For business purposes, Data generated for business purposes.

[0058] Step 1.3: Execute the specified aggregation: based on Perform the calculation to obtain the business type score. .

[0059] The business score, calculated based on the aggregation method and atomic indicator data in the matrix cells, includes: If the aggregation method is a weighted average, the business score includes:

[0060] In the formula, The weighted average business score, To configure tuples, As the indicator weight, The input data is the k-th data generated by the business.

[0061] If the aggregation method follows the weakest link principle, the business score includes:

[0062] In the formula, The score is based on the "weakest link" principle.

[0063] If the aggregation method is a veto method, the business score includes:

[0064] in, This is a pre-defined set of veto criteria.

[0065] If the aggregation method is a comprehensive evaluation of the matching degree of capacity supply and demand, the business score includes:

[0066] In the formula, To score business performance, This refers to a specific mode of transportation on the airport's landside, such as subway, airport bus, taxi, or ride-hailing service. The set of all modes of transportation participating in the assessment, i.e. , The penalty coefficient is... For real-time saturation of each mode, This represents the comfort threshold.

[0067] This represents the total effective transportation capacity supply across multiple modes (persons / hour). For real-time available capacity, As the benchmark weight, Based on turnaround time The efficiency decay function.

[0068] The total passenger demand (in persons) is calculated by combining the GTC's forecast of arriving / departing passengers and the current number of stranded passengers. For the field resistance coefficient, For the number of arrivals, For the number of people departing, This refers to the number of people stranded.

[0069] To adjust the overall supply and demand ratio A non-linear function that maps to a baseline score range (e.g., 60-100 points).

[0070] This is an unbalanced penalty term. For real-time saturation of each mode, For comfort threshold, This is the penalty coefficient.

[0071] final Scores need to be cropped to ensure the value range is [0, 100].

[0072] Weighted aggregation: This involves combining departments Scores for all business types Aggregation is typically performed using a weighted average, with weights... This reflects the importance of each business type to the overall performance of the department (configurable at the department level).

[0073]

[0074] Overall health assessment of the department: By comparing with the overall threshold at the department level, the overall status of the department can be obtained.

[0075] The above algorithms have the following visualization features in digital twins: First view presentation: The numerical values ​​and status drive the overall color scheme of the global dashboard and 3D scene.

[0076] Second view presentation: Each and Drive the department performance panel and, through spatial mapping relationships, drive the color highlighting of each department's responsibility area in the 3D scene (such as changing the color of the TOC area), to achieve "data-scene" linkage.

[0077] This invention provides a digital twin-based airport safety operation diagnostic system for implementing the above-described method, comprising a processor, a memory, and a computer program. The system includes: The digital twin construction and driving module is used to build and drive a 3D model that is synchronized with the physical entity of the airport and maintain its unified data model. The comprehensive indicator system construction and situational awareness module is communicatively connected to the digital twin construction and driving module, and is used to perform dynamic construction, parameterized configuration, fusion diagnosis and anomaly tracing of the comprehensive indicator system; The visualization interaction and diagnostic presentation module is used to render and display the digital twin 3D scene, and integrate and display the dual-view indicators, health index and diagnostic report output by the comprehensive indicator system construction and situational awareness module.

[0078] Based on the above, the present invention provides a specific example to further explain and illustrate the above content: Step 1: Multi-source data fusion and twin synchronization The data acquisition and governance module connects to the Air Traffic Control CDM system, Flight Information Integration System (FIMS), surface surveillance radar, video analytics platform, Baggage Handling System (BHS), and Building Automation System (BAS) via adapters. It acquires real-time data from these heterogeneous sources, including flight schedules, radar trajectories, vehicle positions, equipment alarms, and passenger density. After standardized cleaning (such as unified time reference, coordinate transformation, and data format normalization), this data is used as attributes or events via a twin data bus to drive and update the corresponding virtual objects in the digital twin. For example, radar target position data is synchronized to the aircraft model on the twin runway, and BHS fault alarms are synchronized to the baggage carousel model in the twin terminal. This step establishes a vibrant "data soil" upon which the indicator system depends.

[0079] Step 2: Dynamic Construction of a Comprehensive Indicator System Driven by Dual Views In the situational awareness module, the dual-view indicator construction engine works in parallel: 1) Constructing the First View (Safe Operation Object View): The engine extracts data from the twin data model. The calculation of the top-level "Airport Safe Operation Comprehensive Index" relies on multiple core object indicators at the lower level, such as the "Runway Safety Index." A key sub-indicator of this index—"Runway Intrusion Risk Probability"—is dynamically calculated based on real-time updated surface surveillance data (aircraft and vehicle positions and speeds) in the twin, using a built-in conflict probability model, and is directly associated with specific runway objects in the 3D scene.

[0080] 2) Constructing a Second View (Departmental Responsibility Performance View): The engine calculates metrics by filtering entity data belonging to the responsibilities of each department from the twin data model based on a pre-defined departmental responsibility matrix (e.g., AOC is responsible for flight operations, TOC is responsible for the terminal). For example, the "AOC Flight Departure On-Time Rate" metric is derived from the status of all flight entities associated with AOC's responsibilities in the twin. Each department's metric set can be highlighted in the visualization interface in conjunction with the physical area under that department's responsibility (e.g., a certain area of ​​the terminal under TOC's jurisdiction) in the 3D scene.

[0081] Step 3: Dynamic configuration of indicator system parameters The parameterized management configuration module provides a graphical interface. Users can access it from the digital twin system management backend: For the first view, drag the slider to adjust the anomaly-safety composite weight parameter. , The system can be preset with rules, for example, when "thunderstorm" weather is detected from the meteorological system interface, it can automatically... The value was increased by 20%, making the overall health assessment more sensitive to abnormal information such as delays and alarms.

[0082] The parameters are defined as follows: (Abnormal Sensitivity Coefficient) adjusts the impact weight of negative information such as alarms, violations, and delays; (Steady-state assurance coefficient), adjusting the weighting of positive information such as normal operation rate and availability rate. Constraints: + = 1.

[0083] For the second view, parameters are configured for different business types in different departments within a parameter matrix table. For example, a more lenient passenger queuing time threshold can be set for the "Passenger Services" business in the "TOC" department, while a very strict security check pass rate threshold can be set for the "Security and Compliance" business. These parameters are stored directly in the twin's configuration database for the calculation engine to access.

[0084] The matrix construction involves creating a 4 (departments: AOC, ROC, TOC, POC) × 4 (business type: security, efficiency, service, resource) configurable parameter matrix. An example of fine-grained cell configuration is shown below: (AOC, Efficiency Category): The aggregation method used is "weighted average," assigning weights (W1, W2, …Wn) to each subordinate indicator. For example, flight on-time departure rate (0.4), gate turnaround rate (0.3), and runway capacity utilization rate (0.3). The overall score = Σ(indicator value) i × W i Health thresholds are set as follows: [Green ≥ 90, Yellow 80-90, Red < 80].

[0085] (TOC, Service Category): The aggregation method uses the "weakest link rule" (taking the minimum value of the index in this category), and the comprehensive score = Min(index value 1, index value 2, ... index value n), for example, Min(average passenger waiting time, first baggage on-time rate, ..., baggage opening rate), which reflects the strict requirement of no weak links in service; the threshold is set to be more stringent [green ≥ 90, yellow 80-90, red < 80].

[0086] (ROC, Security Category): The aggregation method is set to "one-vote veto". If any core security indicator (such as a confirmed runway intrusion) is abnormal, the score for this category will be directly reduced to zero (red).

[0087] (POC, Resource Category): The aggregation method is set to "Comprehensive Assessment of Capacity Supply and Demand Matching Degree", which comprehensively calculates the capacity matching achievement rate of each mode of transportation, such as comprehensively calculating AC capacity data and GTC passenger flow data; the health threshold is set to [Green ≥90, Yellow 80-90, Red <80].

[0088] The application of matrices in the diagnostic process is as follows: 1. Strategy solidification stage: Through a graphical matrix interface, operation management experts translate management requirements for different departments and business areas (such as "AOC emphasizes efficiency", "TOC has no service shortcomings" and "ROC has zero tolerance for security") into specific aggregation methods and thresholds, and save them as different "scenario solutions" (such as "daily mode" and "Spring Festival travel mode").

[0089] 2. Real-time Calculation Phase: During system runtime, the health calculation engine in the second view (department responsibility performance view) queries and loads the currently effective matrix configuration in real time. For each department, the engine traverses its corresponding four business type cells and, like executing a "recipe," strictly follows the rules set in each cell to calculate the score and determine the status.

[0090] 3. Dynamic Adjustment Phase: When a significant change occurs in the operational scenario (such as switching from routine to the Spring Festival travel rush), the administrator can switch to the preset "Spring Festival Travel Rush Mode" matrix scheme with a single click. The health assessment standards for all departments in the system will be updated immediately according to the new scheme, achieving a second-level global switch of the assessment strategy.

[0091] Step 4: Integrated Diagnosis and Visualization Based on the Indicator System The health score calculation module performs calculations periodically (e.g., every minute) or triggered automatically. The calculation results are pushed to the visualization module. Users can simultaneously view the results on the main interface. The left side shows a 3D twin scene of the airport, where the colors of key areas (such as runways and boarding gates) change dynamically according to the health status of their associated indicators (e.g., green for healthy and red for abnormal).

[0092] The right side features a dual-view indicator panel, displaying the "Overall Airport Health" and the health and key indicator values ​​of various departments such as "AOC" and "TOC" in the form of dashboards, trend charts, and lists. Clicking on an abnormal area in the 3D scene will automatically focus on and expand the right panel to show the relevant department and indicator details for that area, enabling deep interaction between the scene and the data.

[0093] Step 5: Anomaly tracing and diagnostic report generation based on indicator correlation When the "Overall Airport Health" indicator on the visualization interface changes from green to yellow, the early warning and source tracing analysis module automatically activates. It first analyzes the first view and finds that a decline in the "Flight Operation Index" is the primary cause. Next, it correlates with the second view, locating a simultaneous decline in "AOC Health" and an anomaly in its subordinate "Gate Turnover Rate" indicator. Further, the module retrieves twin data, finding the anomalies concentrated in the "West Area Remote Gates." Finally, the system generates a diagnostic report stating: "The overall health decline is mainly attributed to the excessively low turnover rate of the West Area remote gates managed by the AOC. Correlation analysis reveals frequent GPS signal loss for ground vehicles in this area during the same period, suspected to be causing a decrease in operational efficiency." Simultaneously, in the 3D scene, a highlighted animated path sequentially illuminates the entire airport model, from the West Area remote gates to the specific operational vehicle trajectories, visually demonstrating the complete source tracing chain.

[0094] As can be seen from the above embodiments, the present invention successfully transforms the comprehensive indicator system from a static "management table" into a dynamic, visual, and intelligent "sensory nerve" and "diagnostic brain" in a digital twin environment, realizing a deeper and more agile understanding and control of the airport's safe operation status.

[0095] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0096] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. This computer software product, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0097] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins, characterized in that, include: Acquire heterogeneous operational data in the current airport physical space, and map the preprocessed heterogeneous operational data into the data model of the airport digital twin; Based on the data model, a set of logically related and complementary safety operation object view indicators and a set of departmental responsibility performance view indicators are constructed to form a comprehensive indicator system. Set composite weight coefficients for the first set of safety operation object view indicators, and set a multi-dimensional parameter matrix for the second set of departmental responsibility performance view indicators; Based on composite weight coefficients and multidimensional parameter matrices, the indicators in the comprehensive indicator system are quantitatively calculated and integrated to generate the airport operation health index and the department operation health index respectively. Based on the synchronous rendering and related display of the airport operation health index and the department operation health index, when an abnormal indicator of an abnormal index occurs, a diagnostic report is generated based on the entity association relationship in the digital twin, and the department to which the abnormal indicator belongs is highlighted.

2. The method for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins as described in claim 1, characterized in that, The secure operation object view indicator set includes a first top-level module and a first lower-level module; The first top-level module includes an airport safety operation comprehensive index that characterizes the overall operational status of the airport, and the first lower-level module includes object indicators that are dynamically linked to flight operations, passenger services, and energy management based on real-time calculations using twin data.

3. The method for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins as described in claim 1, characterized in that, The departmental responsibility performance view indicator set includes a second top-level module and a second lower-level module; The second top-level module includes the division of responsibility boundaries for the Airport Operations Control Center (AOC), Flight Area Operations Management Center (ROC), Terminal Area Operations Management Center (TOC), and Public Area Operations Management Center (POC). The second lower-level module includes business flow indicators that are dynamically decomposed into each department.

4. The method for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins as described in claim 1, characterized in that, The composite weighting coefficient includes an anomaly sensitivity coefficient and a steady-state protection coefficient. The quantitative calculation and fusion of the safety operation object view index set based on the composite weighting coefficient includes: In the formula, The airport's operational health index The abnormal sensitivity coefficient, The score is normalized and aggregated to reflect global anomaly information. For steady-state protection coefficient, , The score is normalized and aggregated for global security information.

5. The method for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins according to claim 4, characterized in that, The normalized aggregate score for global anomaly information and the normalized aggregate score for global security information include: The indicators in the safe operation object view indicator set are classified into anomaly information indicator set and safety information indicator set; Calculate the aggregated score for abnormal information and the aggregated score for security information for the indicators in the abnormal information indicator set and the security information indicator set, respectively. The aggregated scores of abnormal information and security information are aggregated a second time to obtain the normalized aggregated score of global abnormal information and the normalized aggregated score of global security information.

6. The method for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins as described in claim 5, characterized in that, The quantitative calculation and fusion of departmental responsibility performance view indicator sets based on multidimensional parameter matrices includes: Configure a multidimensional parameter matrix, which includes several matrix cells. The matrix cells store the aggregation method, indicator weights, and health thresholds of the current business in the current department. The department includes several types of business. The configuration tuples of matrix cells are obtained from the multidimensional parameter matrix. The atomic indicator data of business classification under each department are collected. The business score is calculated based on the aggregation method in the matrix cell. The departmental operational health index of the current indicator is output according to the business score and the calculation weight of each business.

7. The method for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins as described in claim 6, characterized in that, The business score calculated based on the aggregation method and atomic indicator data in the matrix cells includes: If the aggregation method is a weighted average, the business score includes: In the formula, The weighted average business score, To configure tuples, As the indicator weight, For input data.

8. The method for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins as described in claim 7, characterized in that, If the aggregation method follows the weakest link principle, the business score includes: In the formula, The score is based on the "weakest link" principle.

9. The method for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins as described in claim 7, characterized in that, If the aggregation method is a comprehensive evaluation of the matching degree of capacity supply and demand, the business score includes: In the formula, To score business performance, To ensure the total effective supply of transportation capacity across multiple modes, To take into account the total passenger demand, To be A non-linear function mapped to the baseline score interval. A specific mode of transportation for airport landside transport. A collection of modes of transportation. The penalty coefficient is... For real-time saturation of each mode, This represents the comfort threshold.

10. A method for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins, comprising the method for constructing a comprehensive indicator system for airport safety operation diagnosis based on digital twins as described in any one of claims 1-9, characterized in that, include: The data processing module is configured to acquire heterogeneous operational data in the current airport physical space, and preprocess the heterogeneous operational data before mapping it to the data model of the airport digital twin; Based on the data model, a set of logically related and complementary safety operation object view indicators and a set of departmental responsibility performance view indicators are constructed to form a comprehensive indicator system; a composite weight coefficient is set for the first set of safety operation object view indicators, and a multi-dimensional parameter matrix is ​​set for the second set of departmental responsibility performance view indicators; The calculation module is configured to perform quantitative calculations and integration of each indicator in the comprehensive indicator system based on composite weight coefficients and multidimensional parameter matrices, and generate the airport operation health index and the department operation health index respectively. Based on the synchronous rendering and related display of the airport operation health index and the department operation health index, when an abnormal indicator of an abnormal index occurs, a diagnostic report is generated based on the entity association relationship in the digital twin, and the department to which the abnormal indicator belongs is highlighted.

Images