Civil aviation autonomous operation efficiency evaluation method

Abstract

The invention relates to the technical field of operation efficiency evaluation, in particular to a civil aviation autonomous operation efficiency evaluation method, which comprises the following steps: acquiring operation information historical data which comprises operation information accumulated in the civil aviation operation process; multiple historical models are established based on the operation information historical data, each historical model is used for representing different autonomous operation scenes of the civil aviation, and each autonomous operation scene comprises a corresponding reference efficiency index; obtaining to-be-evaluated operation information, matching the to-be-evaluated operation information with a plurality of historical models, and obtaining a current autonomous operation scene; calculating an actual efficiency index corresponding to the current autonomous operation scene according to the to-be-evaluated operation information; performing visual comparison display on the actual efficiency index corresponding to the current autonomous operation scene and the reference efficiency index; the civil aviation operation efficiency can be comprehensively evaluated.

Description

Technical Field

[0001] This invention relates to the field of operational performance evaluation technology, and specifically to a method for evaluating the autonomous operational performance of civil aviation. Background Technology

[0002] With the continuous development of the air transport industry and the constant growth of air traffic volume, the existing air traffic management system faces increasingly severe safety and efficiency challenges. The traditional ground control model is ground-centric, with aircraft relying primarily on ground commands for path planning and adjustments throughout the flight, resulting in low crew involvement. While this model has a mature technological system for ensuring safety, it suffers from problems such as decision-making delays, high communication loads, and insufficient operational flexibility under complex weather conditions, multi-aircraft collaborative operations, and high-density airspace operations, making it difficult to meet the development needs of future intelligent air transport systems.

[0003] To adapt to the needs of future intelligent flight and efficient operation, the International Civil Aviation Organization (ICAO) and major aviation powers have successively proposed development visions based on Autonomous Operations. These visions aim to enable aircraft to make autonomous judgments, plans, and executions through integrated air-ground situational awareness sharing and collaborative decision-making. The integrated air-ground autonomous operation mode, while adhering to existing flight rules, centers on the aircraft and achieves real-time perception and dynamic decision-making of the surrounding operating environment through two-way situational awareness sharing between the airborne and ground systems. Its core objective is to fully leverage the aircraft's performance potential, improving operational efficiency and reducing energy consumption and air-ground workload while ensuring safety.

[0004] In this mode, aircraft can autonomously assess their flight status based on multi-source information fusion, including Automatic Dependent Surveillance-Broadcast (ADS-B), Navigation Satellite System (GNSS), weather radar, ground surveillance, and communication links. This allows the crew to conduct digital negotiations with ground control units, enabling autonomous operations such as adjusting flight intervals, optimizing routes, and correcting flight paths. Through this process, a new operational paradigm of limited autonomy and collaborative decision-making is formed between air and ground.

[0005] In response to the rapid development and complex application scenarios of the integrated air-ground autonomous operation mode, there is an urgent need to establish a scientific and systematic performance evaluation index system and evaluation method. This evaluation system should cover multiple dimensions, including autonomous operation capability, safety, operational efficiency, economy, environmental impact, and personnel workload, and comprehensively assess the overall benefits of the operation mode through a combination of quantitative and qualitative methods. Summary of the Invention

[0006] In view of the above problems, the present invention provides a method for evaluating the autonomous operation efficiency of civil aviation, which solves the technical problem that it is difficult to comprehensively evaluate the autonomous operation capability, safety, efficiency, economy, environmental impact and personnel load of civil aviation in the prior art.

[0007] This invention provides a method for evaluating the autonomous operation effectiveness of civil aviation, comprising the following steps: Step S1: Obtain historical operational information data. The historical operational information data includes operational information accumulated during civil aviation operations, including meteorological, airspace, ground operating conditions, flight plans, air-to-ground surveillance, and operational restriction information. Step S2: Based on the historical data of the operation information, establish multiple historical models. Each historical model is used to represent different autonomous operation scenarios of civil aviation. Each autonomous operation scenario includes corresponding benchmark performance indicators. Step S3: Obtain the operational information to be evaluated, match the operational information to be evaluated with multiple historical models, and obtain the current autonomous operation scenario; Step S4: Calculate the actual performance indicators corresponding to the current autonomous operation scenario based on the operational information to be evaluated; Step S5: Visualize and compare the actual performance indicators and benchmark performance indicators corresponding to the current autonomous operation scenario.

[0008] Preferably, step S2 specifically includes: Step S2-1: Establish multiple typical autonomous operation scenarios and determine the types of performance indicators for each autonomous operation scenario; Step S2-2: Classify the historical data of the operation information into the various typical autonomous operation scenarios to form various historical models; Step S2-3: Calculate the performance index corresponding to each historical model based on the historical data of the operation information, and perform post-processing to obtain the benchmark performance index.

[0009] Preferably, in step S2-1, the various typical autonomous operation scenarios specifically include: autonomous flight rerouting under severe weather conditions, straightening operations under flexible airspace use, single-aircraft trajectory-based operations, emergency response under the influence of strong convection along the route, autonomous wake separation operations in high-density scenarios, and autonomous decision-making operations for approach procedures.

[0010] Preferably, the step of determining the type of performance index for each autonomous operation scenario includes: (1) Determine the types of all performance indicators, including: safety performance evaluation indicators, efficiency performance evaluation indicators, economic performance index indicators, environmental benefit indicators, and the load of the unit and control personnel; (2) Establish different performance indicators for each autonomous operation scenario based on the scenario characteristics of the autonomous operation scenario. Specifically, for each autonomous operation scenario, establish corresponding performance indicator items for each type of performance indicator.

[0011] Preferably, step S2-2 specifically includes: obtaining the actual flight trajectory and planned route information of the flight based on the flight plan and air-to-ground surveillance information in the historical data of the operation information; and automatically completing the classification of the historical data of the operation information by judging the flight plan and air-to-ground surveillance information. Step S2-3 specifically includes: calculating the performance indicators corresponding to each piece of operational information in the historical data of each historical model, taking the average or clustering of the performance indicators to obtain the corresponding benchmark performance indicators.

[0012] Preferably, step S3 specifically includes: Based on the flight plan and air-to-ground surveillance information in the operational information to be evaluated, obtain the flight trajectory, flight plan, and operational environment characteristic parameters, and combine these parameters into a feature vector; A machine learning classification model is used to classify the feature vectors to obtain the corresponding current autonomous operation scenario.

[0013] Preferably, in step S4, the crew and controller workload in the actual performance indicators includes the pilot workload indicator; The formula for calculating the pilot workload index is as follows:

[0014]

[0015]

[0016]

[0017]

[0018] in, Indicates in The total workload of pilots at all times Indicates in The coefficients of influencing factors at a given time. Represents the existence matrix of task units. These respectively represent the existence of visual input tasks, auditory input tasks, cognitive tasks, action output tasks, and language output tasks. This represents a matrix representing the single-task load values. These represent the single-task unit workload values ​​for visual input, auditory input, cognitive input, motor output, and language output channels, respectively. This represents the matrix of conflict coefficient values ​​for tasks within the same channel. These represent the task conflict coefficient values ​​for visual input, auditory input, cognitive input, motor output, and language output channels, respectively. This represents the multi-task load factor matrix. These represent the multitasking load coefficient values ​​for visual input, auditory input, cognitive input, motor output, and language output channels, respectively. This indicates the matrix transpose.

[0019] Preferably, the in Influencing factor coefficients at time points The method of obtaining the data is as follows: collect the subjective workload evaluation values ​​of the pilots under test at different flight stages, and perform regression calculation on the evaluation values ​​to obtain the coefficients of influencing factors; Single task load value matrix The acquisition method is as follows: Subjective workload evaluation values ​​of the tested pilots in different independent operating units are collected as... The single-task unit load value; Multi-task load factor matrix The acquisition method is as follows: collect the subjective workload evaluation values ​​of the pilots under test in different multi-task combination experiments, and obtain the multi-task workload coefficient matrix; Coupling coefficient matrix of tasks in the same channel The acquisition method is as follows: collect the subjective workload evaluation values ​​of the pilots under test in conflict mission experiments in different channels, and obtain the conflict coefficient value matrix of the same channel mission.

[0020] Preferably, step S5 specifically includes: Within the same user interface, radar charts, bar charts, or time series curves are used to display the actual performance indicators and benchmark performance indicators corresponding to the current autonomous operation scenario, thus completing the comparative display.

[0021] Compared with the prior art, the present invention has at least the following beneficial effects: (1) This invention extracts multi-dimensional operational information such as meteorology, airspace, ground operating conditions, flight plans, air-to-ground surveillance, and operational restrictions from laboratory integrated verification environments and flight test environments. Based on historical data, it constructs various autonomous operating scenario models to achieve accurate matching with the actual scenarios to be evaluated. By comparing historical models with current scenarios, the error caused by a single reference is effectively reduced, ensuring that the evaluation results are more scientific, objective, and in line with the actual operating environment.

[0022] (2) Based on the application background of air-ground information sharing and collaborative operation, this invention constructs an evaluation system covering five areas: safety, efficiency, economy, environment, and personnel workload. Through the calculation and visualization comparison of various performance indicators, the advantages and disadvantages of autonomous operation in different dimensions can be intuitively reflected, providing multi-angle and systematic decision support for improving the level of aviation operation management and promoting the comprehensive improvement of the autonomous operation efficiency of civil aviation.

[0023] (3) This invention identifies historical models most similar to the current operating environment from a large amount of historical data, giving the performance evaluation good scenario adaptability. Whether in daily operation or in special complex scenarios, it can quickly perform model matching and performance evaluation, greatly improving the versatility and practicality of the method, and providing strong technical support for optimizing civil aviation autonomous operation schemes and coping with complex operation challenges. Attached Figure Description

[0024] The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of the invention.

[0025] Figure 1 A flowchart of the civil aviation autonomous operation performance evaluation method provided by the present invention.

[0026] Figure 2 The schematic diagram of the principle structure of the civil aviation autonomous operation performance evaluation method provided by the present invention. Detailed Implementation

[0027] To better understand the above-described objectives, features, and advantages of the present invention, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments of the present invention and the features thereof can be combined with each other. Furthermore, the present invention can be implemented in other ways different from those described herein; therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0028] This invention first extracts autonomous operation scenarios and environments. The system extracts key operational information from measured samples obtained from laboratory integrated verification environments and flight test environments, including meteorological, airspace, ground operating conditions, flight plans, air-to-ground surveillance, and operational restrictions, to provide data support for subsequent matching and evaluation. Then, based on a typical day discrimination method, historical data is matched to identify the historical model closest to the current scenario. Matching with historical models provides a reference for performance evaluation. Finally, the background and typical scenarios of air-to-ground information sharing and collaboration are studied and summarized, constructing autonomous operation performance evaluation indicators from five areas: safety, efficiency, economy, environment, and personnel workload. Multiple performance indicators are then calculated by comparing historical and measured data.

[0029] To illustrate the effectiveness of the method proposed in this invention, the following detailed description of the above technical solution is provided through a specific embodiment. A specific embodiment of this invention is as follows: Figure 1 , Figure 2 As shown, a method for evaluating the autonomous operation efficiency of civil aviation is disclosed, and the specific implementation steps are as follows: Step S1: Obtain historical operational information data. The historical operational information data includes operational information accumulated during civil aviation operations, including meteorological, airspace, ground operating conditions, flight plans, air-to-ground surveillance, and operational restriction information. In this step, the present invention first establishes a historical database of civil aviation operation information. The historical database is obtained by aggregating and organizing the operation information of various civil aviation operation systems. The operation information includes meteorological, airspace, ground operation conditions, flight plans, air-to-ground surveillance, and operation restriction information.

[0030] In some embodiments, the operational information may come from airline ground support systems, meteorological observation systems, air traffic control and dispatch systems, automated monitoring systems, and airport operations control platforms, etc.

[0031] Specifically, the meteorological, airspace, ground operating conditions, flight plans, air-to-ground surveillance, and operational restrictions information are described in detail below.

[0032] Meteorological information includes values ​​for various meteorological elements such as temperature, air pressure, humidity, wind speed, wind direction, precipitation, and thunderstorms. Meteorological information can be further collected and extracted through meteorological observation systems.

[0033] Airspace information includes dynamic characteristics such as airspace type, structure, control rules, altitude and speed restrictions. Airspace information can be automatically synchronized with existing air traffic control and dispatch systems to obtain airspace type, boundaries, altitude layer divisions, control rules, and corresponding flight restrictions, reflecting real-time changes in airspace adjustments and usage.

[0034] Ground operations information includes basic airport information, runway conditions, navigation facilities, signs and markings, and air traffic control services. This information can be comprehensively collected through airline ground support systems combined with airport announcements, airport capacity data, and ground traffic flow data.

[0035] Flight plan information includes information such as departure and arrival airports, routes, and track matching. Flight plan information can be obtained by analyzing flight schedules and other data provided by airline operating systems and air traffic control systems.

[0036] Air-to-ground surveillance information includes the flight path data of the aircraft and other aircraft, flight traffic, and airspace density. Flight path data includes latitude, longitude, altitude, speed, and heading. Air-to-ground surveillance information can be collected by automated surveillance systems.

[0037] Operational restrictions include weather restrictions, airport operational restrictions, aircraft performance restrictions, and flight rule constraints, which can be obtained through airport operations control platforms, etc.

[0038] Step S2: Based on the historical data of the operation information, establish multiple historical models. Each historical model is used to represent different autonomous operation scenarios of civil aviation. Each autonomous operation scenario includes corresponding benchmark performance indicators. In this step, the present invention first establishes six typical autonomous operation scenarios, determines the types of performance indicators for each autonomous operation scenario, then classifies the historical data of operation information into these six typical autonomous operation scenarios to form six historical models, and finally calculates the performance indicators corresponding to each historical model based on the historical data of operation information, and performs post-processing to obtain the benchmark performance indicators.

[0039] Step S2-1: Establish multiple typical autonomous operation scenarios and determine the types of performance indicators for each autonomous operation scenario.

[0040] In this step, the various typical autonomous operation scenarios of the present invention include: autonomous rerouting operation under severe weather conditions, straightening operation under flexible airspace use, single-aircraft trajectory-based operation (single-aircraft TBO), emergency response under the influence of strong convection along the route, autonomous wake separation operation in high-density scenarios, and autonomous decision-making operation for approach procedures.

[0041] To scientifically and comprehensively evaluate the performance of different autonomous operation scenarios, a complete performance indicator system is first constructed in the specific embodiments of this invention. This system systematically defines various evaluation indicators from five dimensions: safety, efficiency, economy, environment, and personnel workload, forming a complete indicator library required for evaluation.

[0042] In this step, the present invention defines the types of performance indicators, including: safety performance evaluation indicators, efficiency performance evaluation indicators, economic performance index indicators, environmental benefit indicators, and the load on the unit and control personnel.

[0043] Each performance indicator includes several specific indicators. Among them, the safety performance evaluation indicators specifically include: Accident / Incident Rate, Separation Violation Rate, Situational Awareness Consistency Rate (SACR), Perception Loss Rate (PLR), Potential Conflict Detection Rate (PCDR), Successful Conflict Resolution Rate (SCRR), Emergency Response Delay (ERD), and Safety Redundancy Coverage (SRC).

[0044] Efficiency and performance evaluation indicators specifically include: Flight Density, Peak Traffic Load, Average Traffic Load, Airspace Utilization Rate, Temporary Route Availability (UR), Temporary Route Potential Availability (PUR), Number of Flights Using Temporary Routes (RUS), Number of Flights Using Temporary Routes Potentially (PRUS), Temporary Route Actual Utilization Rate (RAU), Route Length Utilization Rate, and Delay Rate.

[0045] The specific indicators of the economic efficiency index include: total miles saved (FER), average miles saved (PFE), potential total miles saved (FEL), flight economy contribution (FEO), potential miles saved ratio (RFEL), actual flight efficiency (AFE), and total fuel savings (TFS).

[0046] The specific environmental benefit indicators include: pollutant gas emission benefit (PGB), noise pollution benefit (NPB), total CO2 emission reduction (TCR), potential CO2 emission reduction (PCR), potential CO2 emission reduction ratio (RPCR), and potential mileage saving ratio (RFEL).

[0047] The specific loads of the crew and controllers include: influencing factor coefficient K, task unit load value B, multitasking coefficient D, task conflict value C, traffic density load index, communication load index, interface interaction compliance index, and time characteristic load index.

[0048] The above are all the performance indicators provided by this invention. Based on the core operational characteristics, key performance objectives, and main potential risks of each autonomous operation scenario, this invention selectively filters and combines indicators from the aforementioned indicator library to construct a dedicated set of evaluation indicators highly matched to the scenario. This selection criterion ensures the accuracy and relevance of the evaluation. Different types of performance indicators are provided for each autonomous operation scenario, described in detail below.

[0049] (1) For autonomous flight rerouting operations under severe weather conditions, the indicators include: Safety performance indicators: air-to-ground situational consistency rate, minimum separation maintenance violation rate, and effective avoidance rate; Efficiency and performance indicators: delay rate, route length utilization rate; Economic efficiency indicators: Total fuel savings and actual flight benefits; Environmental benefit indicators: Total CO2 emission reduction; Personnel workload index: Pilot workload.

[0050] (2) For flexible use of airspace and straightening of curves, the indicators include: Safety performance indicators: actual utilization rate of temporary routes, utilization rate of route length, and utilization rate of airspace; Economic efficiency indicators: total mileage savings, average mileage savings, total fuel savings, and potential total mileage savings; Environmental benefit indicator: Total CO2 emission reduction.

[0051] (3) For single-aircraft trajectory-based operations (single-aircraft TBO), the metrics include: Safety performance indicators: Minimum interval violation rate; Efficiency and performance indicators: Delay rate; Economic efficiency indicator: Total fuel savings.

[0052] (4) For emergency response to severe convective weather along flight routes, the indicators include: Safety performance indicators: emergency response delay, effective avoidance rate, and air-to-ground situational consistency rate; Efficiency and performance indicators: Delay rate.

[0053] (5) For autonomous wake interval operation in high-density scenarios, the indicators include: Safety performance indicators: Minimum interval violation rate; Efficiency and performance indicators: peak traffic flow, traffic density, airspace utilization, and delay rate.

[0054] (6) For the autonomous decision-making operation of the entry procedure, the indicators include: Efficiency and performance indicators: Route length utilization rate; Economic efficiency indicator: Total fuel savings; Environmental benefit indicators: noise pollution benefit, total CO2 emission reduction; Personnel workload index: Pilot workload.

[0055] For autonomous flight detours in adverse weather conditions, the key lies in whether the aircraft can safely and efficiently complete its flight in a dynamic and complex environment after deviating from its planned route. Therefore, air-to-ground situational awareness rate and effective avoidance rate are selected to measure its safety assurance capability after deviation. At the same time, flight detours inevitably lead to changes in flight path and time, so delay rate and route length utilization rate are selected to quantify their impact on operational efficiency. The economic and environmental benefits are assessed by total fuel savings and total CO2 emission reductions, while pilot workload is used to assess the impact on personnel under abnormal conditions.

[0056] For scenarios involving flexible airspace use and straightening off-traffic routes, the core objective is to shorten flight distances through temporary routes, thereby improving economy and efficiency. Therefore, the selection of indicators focuses heavily on quantifying benefits, directly using economic indicators such as total mileage savings and total fuel savings, and environmental indicators such as total CO2 emission reduction, to measure its main benefits. Indicators such as the actual utilization rate of temporary routes and airspace utilization rate are used to evaluate the actual performance of this strategy in improving airspace resource utilization efficiency.

[0057] For autonomous wake separation operations in high-density scenarios, the essence is to improve airspace capacity and operational efficiency by shortening the intervals while ensuring safety. Therefore, the most important aspect of safety assessment is maintaining a low violation rate for minimum intervals to monitor core risks. Its operational benefits are directly reflected in indicators such as peak traffic flow, traffic density, and delay rate, which directly reflect the effectiveness of capacity improvement.

[0058] Using the above method, this invention selects the most representative performance items based on the key operational risk points, operational efficiency requirements, and practical application value corresponding to each scenario, forming a combination of performance evaluation indicators that match different scenarios, thereby achieving a scientific, systematic, and targeted evaluation of performance under various autonomous and complex operating environments.

[0059] Step S2-2: Classify the historical data of the operation information into the various typical autonomous operation scenarios to form various historical models.

[0060] In this step, the historical data of the operation information is classified and divided into these 6 typical autonomous operation scenarios, thereby obtaining the historical data of the operation information corresponding to the 6 autonomous operation scenarios.

[0061] In some embodiments, the original information of the historical operation information data already records the operation scenario at that time, and the historical operation information data can be classified according to the original information; In some embodiments, information such as the actual flight trajectory and planned route of a flight can be obtained from flight plans, air-to-ground surveillance, and other information in the historical operational information data. By judging the flight plans and air-to-ground surveillance, the classification of the historical operational information data can be automatically completed.

[0062] Step S2-3: Calculate the performance index corresponding to each historical model based on the historical data of the operation information, and perform post-processing to obtain the benchmark performance index.

[0063] In this step, the performance indicators corresponding to each piece of operational information in the historical data of each historical model can be specifically calculated. The performance indicators can be averaged or clustered to obtain the corresponding benchmark performance indicators.

[0064] In some embodiments, after completing the data classification in step S2-2, performance indicators are batch calculated and statistically analyzed for the six scenario-specific historical model databases formed above. First, based on the performance indicator types preset for each scenario in step S2-1, the corresponding calculation formulas are called. Taking the historical model database of "autonomous wake turbulence interval operation in high-density scenarios" as an example, each historical time segment in the database can be traversed to extract data such as traffic flow and aircraft intervals within that time period, and formulas such as "peak traffic flow" and "minimum interval maintenance violation rate" are applied for calculation to obtain a series of discrete raw performance indicator values. After completing the calculation for all historical data points in a scenario database, statistical post-processing is performed on the historical data points.

[0065] Specifically, this involves calculating the mean, median, standard deviation, and key percentiles (such as the 75th and 90th percentiles) for each performance indicator, or performing clustering operations on each performance indicator. This ultimately forms a multi-dimensional set of benchmark performance indicators. For example, for the indicator "delay rate," the benchmark value may not be a single numerical value, but rather a comprehensive reference system that includes "historical average delay rate," "historical delay rate fluctuation range (defined by the standard deviation)," and "historical high delay level (defined by the 90th percentile)." The benchmark performance indicators obtained in this way not only objectively reflect the historical average performance in this scenario but also provide a quantitative understanding of performance stability and historical extreme cases, thus establishing a reference benchmark for subsequent comparative evaluation with real-time operating scenarios.

[0066] Step S3: Obtain the operational information to be evaluated, match the operational information to be evaluated with multiple historical models, and obtain the current autonomous operation scenario; In this step, the present invention acquires the operational information to be evaluated and the feature information of various historical models, compares and matches them based on the feature information, and finally determines the current autonomous operation scenario corresponding to the operational information to be evaluated.

[0067] In some embodiments, a series of key feature parameters, such as flight trajectory, flight plan, and operating environment, can be obtained from the flight plan, air-to-ground surveillance, and other information in the operational information to be evaluated, and these parameters can be combined into a real-time feature vector representing the current operational status.

[0068] The matching process of this invention employs a pre-built and trained scene classification model. This classification model can be a machine learning-based model, such as a Support Vector Machine (SVM), Gradient Boosting Decision Tree, or Deep Neural Network (DNN).

[0069] In some embodiments, during the training phase of the classification model, the model can learn a large number of feature vectors and their corresponding scene labels from the historical database of six typical scenarios in step S2-2. During the evaluation phase, the real-time scene matching engine takes the newly generated real-time feature vectors as input, and the model calculates the probability or confidence score of the real-time feature vector belonging to each typical autonomous operation scenario based on its internally learned decision boundaries or patterns. Finally, the engine selects the scenario category with the highest probability or a confidence score exceeding a preset threshold as the autonomous operation scenario matched to the current operational information to be evaluated. For example, if the real-time feature vector has high weights for features such as "high traffic density," "small aircraft spacing," and "specific approach procedures," the classification model will identify it as "autonomous wake turbulence interval operation in a high-density scenario" with a very high probability. Through this matching mechanism based on feature vectorization and machine learning classifiers, this invention can achieve rapid, accurate, and automated scene identification of current complex operational situations.

[0070] Step S4: Calculate the actual performance indicators corresponding to the current autonomous operation scenario based on the operational information to be evaluated; In this step, the present invention calculates the current operational information to be evaluated, and obtains the specific values ​​of the actual performance indicators corresponding to the current autonomous operation scenario. As described in step S1, the operational information to be evaluated includes the current meteorological, airspace, ground operation conditions, flight plan, air-to-ground surveillance, and operational restriction information.

[0071] The calculation methods for all the various performance indicators of this invention are described in detail below.

[0072] Accident / Incident Rate

[0073] in, This indicates the number of accidents or accident precursors that occurred within the statistical period. This represents the total flight hours (in hours) within the statistical period. You can specifically choose as (Mid-air collision risk event) (Controlled flight collision risk event) (Runway incursion incident) (Out-of-control incident) (Events directly related to autonomous decision-making), unit: number of events / 100,000 flight hours.

[0074] Separation Violation Rate (MSV) Separation Violation Rate

[0075] in, This indicates the number of events within a statistical period whose actual horizontal or vertical interval is less than the minimum value stipulated by regulations. This represents the total number of potential encounters between aircraft within a statistical period, with a minimum horizontal separation of 5 nautical miles and a minimum vertical separation of 1,000 feet.

[0076] Situational Awareness Consistency Rate (SACR) Definition: The percentage of situations in which airborne aircraft and ground air traffic control make the same situational assessment of the same target at the same time.

[0077]

[0078] in, This indicates the number of times the air-ground situation assessment is consistent. This represents the number of all comparable situation assessments.

[0079] Perception Loss Rate (PLR) Definition: The proportion of necessary situational information that an autonomous system fails to perceive.

[0080]

[0081] in, This indicates the number of key objectives that were missed. This indicates the number of targets that should theoretically be detected.

[0082] Potential Conflict Detection Rate (PCDR) Definition: The ratio of the number of potential conflicts detected by the system to the number of actual conflicts.

[0083]

[0084] in, This indicates the number of times potential conflicts were correctly detected. This indicates the number of known potential conflicts, which can be calculated based on the actual potential conflicts generated by the simulator or the conflict determination criteria.

[0085] Successful Conflict Resolution Rate (SCRR) Definition: The ratio of the number of times the system successfully avoids and evades a conflict to the total number of all events that trigger aircraft avoidance.

[0086]

[0087] in, This indicates the number of times conflict was successfully avoided. This indicates the total number of events that trigger avoidance.

[0088] Emergency Response Delay (ERD) Definition: The time difference between a system recognizing a conflict and executing an avoidance operation.

[0089]

[0090] in, Indicates the total number of events. This indicates the actual start time of the response action. This indicates that the system identifies the first An abnormal time.

[0091] Safety Redundancy Coverage (SRC) Definition: The percentage of information (such as target location) that has two or more redundant sources.

[0092]

[0093] in, This indicates the amount of situational information with at least two redundant sources (such as ADS-B + radar). This represents the total number of all perceived situational information.

[0094] Flight Density Definition: Flight density refers to the number of flights per unit airspace area per unit time.

[0095]

[0096] in, This indicates the number of flights within the statistical period. Indicates the airspace area. Indicates the duration of the statistics.

[0097] Peak Traffic Load Definition: Peak traffic flow refers to the number of aircraft counted minute by minute within a statistical period, taking the maximum value.

[0098]

[0099] in, This indicates taking the maximum value. This indicates the number of flights per unit of time.

[0100] Average Traffic Load Definition: Traffic density refers to the number of aircraft per unit airspace area.

[0101]

[0102] in, This indicates the number of aircraft in the airspace per unit of time. Indicates the area of ​​the airspace.

[0103] Airspace utilization rate Airspace utilization rate refers to the ratio of actual flight traffic to airspace capacity, reflecting the airspace usage situation.

[0104]

[0105] in, Indicates the actual number of flights. This represents the theoretical spatial capacity.

[0106] Temporary route availability (UR) Temporary route availability UR represents the average number of hours a temporary route is available within a specific time period PrdA.

[0107]

[0108] in, This indicates the number of hours the temporary flight route is open from UTC 0400 to UTC 2200. This indicates the number of hours the temporary route is open from UTC2200 to UTC0400.

[0109] Potential availability (PUR) of temporary routes The Temporary Route Potential Availability Rate (PUR) represents the percentage of time within a specific period (PrdA) during which a temporary route meets the conditions for opening but is not actually opened.

[0110]

[0111] This indicates the number of times during which temporary routes within PrdA meet the conditions for opening but are not yet open.

[0112] Using temporary route flights (RUS) The Use of Temporary Route Flights (RUS) metric is a metric for a specific temporary route (TPAR). It refers to the number of flights that used the TPAR within a certain time period (PrdB) instead of fully utilizing the original regular route.

[0113] It should be noted that the scope of meaning for calculating and using RUS, as well as all the operational performance evaluation indicators described below, must be clearly defined. Generally, these operational performance evaluation indicators are for a specific time period and a specific temporary route, but their scope can be expanded or narrowed according to actual evaluation needs.

[0114] Utilizing potential flight slots (PRUS) on temporary routes Potential Flight Utilization (PRUS) is an indicator of a specific temporary route's Total Participating Rate (TPAR). It refers to the number of flights that could have been used within a given timeframe (PrdB) but were not. The use of temporary routes is triggered under certain conditions, and using temporary routes may result in mileage savings or improved airspace safety. Therefore, the PRUS figure reflects the utilization rate of temporary routes to some extent.

[0115] Temporary route utilization rate (RAU) Temporary route actual utilization rate (RAU) is an indicator for a specific time period (PrdB) and a particular temporary route (TPAR). It refers to the ratio of the number of aircraft actually using the TPAR (RUS) to the number of potential users (PU) of the temporary route.

[0116]

[0117]

[0118] Route Length Utilization Rate Route length utilization rate refers to the ratio of the actual flight route length to the theoretical shortest route length.

[0119]

[0120] in, Indicates the actual flight path length. This represents the theoretically shortest flight path length.

[0121] Delay Rate The delay rate refers to the proportion of delayed flights to the total number of flights.

[0122]

[0123] in, Indicates the number of delayed flights. This indicates the total number of flights.

[0124] Total miles saved (FER) Total mileage savings (FER) is defined for a specific temporary route (TPAR) and is the expected mileage savings from using TRAP for all aircraft (let S be the set of aircraft and ARFL be the number of elements in the set) with flight plans on TRAP within a certain time period (PrdB).

[0125]

[0126] ARFL represents the number of elements in the set of all aircraft with flight plans on TRAP. This indicates the average number of miles saved.

[0127] Average mileage savings (PFE) Average mileage savings (PFE) are defined for a specific temporary route (TPAR) and are the average mileage savings achieved by all aircraft with flight plans on the TRAP during a specific time period (PrdB) due to the use of the TRAP.

[0128]

[0129] SRI represents the length of the temporary route, and SR6 represents the length of the backup route; both are in kilometers.

[0130] Potential total miles saved (FEL) Potential Total Mileage Savings (FEL) is defined for a temporary route (TPAR) and is the amount of mileage savings lost by not using the TRAP for all aircraft (let the set of aircraft be S, and the number of elements in the set be ANRF) that could have used the TRAP during a certain time period (PrdB) but did not use the TRAP and instead used its backup route.

[0131]

[0132] ANRF represents the number of elements in the set of all aircraft that did not use TRAP but fully utilized its backup routes. This indicates the average number of miles saved.

[0133] Flight Economic Contribution (FEO) Flight Economic Contribution (FEO) is defined for a temporary route (TPAR) and a specific time period (PrdB), representing the maximum total flight mileage savings that the TPAR can generate within the PrdB period.

[0134]

[0135] Potential Mileage Savings Ratio (RFEL) Potential mileage savings ratio is an indicator for a specific temporary route's TPAR and a specific time period's PrdB.

[0136]

[0137] Actual Flight Benefits (AFE) Actual Flight Benefit (AFE) is for a specific temporary route (TPAR), referring to the total mileage savings achieved by aircraft that actually use TRAP within a certain time period (PrdB) (let this set of aircraft be denoted as , and the number of elements in this set be UR).

[0138]

[0139] in, This indicates the mileage savings achieved by flight fl due to the actual use of TRAP. This represents the set of aircraft that actually use TRAP.

[0140] Total fuel savings (TFS) Total fuel savings (TFS) refers to the fuel savings achieved by aircraft using TRAP (Travel over Temporary Route) during a specific time period (PrdB) when flying on a temporary route instead of the original route.

[0141]

[0142] in, Indicates flight Fuel consumption.

[0143] Pollutant emission benefit (PGB) The pollution gas emission benefit refers to the reduction in pollution gas emissions of all flights using the TPAR within a certain time period (PrdB) due to the use of the temporary route.

[0144]

[0145] in, Indicates flight For polluting gases The emission index is defined as the amount of polluting gases generated per unit of oil consumed.

[0146] This indicates a group of flights using temporary routes.

[0147] Indicates flight Fuel consumption.

[0148] Indicates flight Pollutant gas emission factors.

[0149] Noise pollution benefit (NPB) The Noise Pollution Benefit (NPB) reflects the reduction in noise pollution for ground residents due to the provision of temporary air routes. This indicator is defined for a specific temporary air route (TPART) for arrival and departure (the noise impact of flights on other temporary air routes on the ground is negligible). It is defined as the distance of the noise reduction route segment (the air route segment with a significant noise impact on ground residential areas) for all flights flying on TPART within a certain time period (PrdB) due to the use of TRAPT.

[0150] Total CO2 emission reduction (TCR) Total CO2 emission reduction refers to the reduction in carbon dioxide emissions of all flights using TPARs within a certain time period (PrdB) due to the use of temporary routes.

[0151]

[0152] in, This indicates the amount of carbon dioxide emitted per unit of fuel consumed by a flight. Potential CO2 emission reduction (PCR) Potential CO2 emission reduction refers to the reduction in carbon dioxide emissions lost by all flights that could have used the temporary route but did not use the temporary route within a certain period of time (PrdB).

[0153]

[0154] in, This indicates all flights that could have been used but did not utilize TPAR.

[0155] Potential CO2 emission reduction ratio (RPCR) The potential fuel savings from CO2 emission reductions reflect the potential to improve current total CO2 emission reductions, i.e., the potential for increased total emission reduction (TCR).

[0156]

[0157] in, This represents the theoretical CO2 emission reduction. This represents the actual CO2 emission reduction.

[0158] Potential Mileage Savings Ratio (RFEL) The measure of fuel efficiency improvement (i.e., fuel waste compared to the baseline route) achieved by airlines through the use of temporary routes (TPAR) reflects the extent to which temporary routes improve fuel efficiency. The higher the value (closer to 1), the more significant the temporary routes have in reducing fuel efficiency losses, indicating a clear optimization effect.

[0159]

[0160] in, This indicates the fuel efficiency loss along the baseline route.

[0161] This indicates the fuel efficiency loss of temporary routes.

[0162] Pilot workload indicators The formula for calculating the pilot's workload index is as follows:

[0163]

[0164]

[0165]

[0166]

[0167] in, Indicates in The total workload of pilots at all times Indicates in The coefficients of influencing factors at a given time. Represents the existence matrix of task units. These respectively represent the existence of visual input tasks, auditory input tasks, cognitive tasks, action output tasks, and language output tasks. This represents a matrix representing the single-task load values. These represent the single-task unit workload values ​​for visual input, auditory input, cognitive input, motor output, and language output channels, respectively. This represents the matrix of conflict coefficient values ​​for tasks within the same channel. These represent the task conflict coefficient values ​​for visual input, auditory input, cognitive input, motor output, and language output channels, respectively. This represents the multi-task load factor matrix. These represent the multitasking load coefficient values ​​for visual input, auditory input, cognitive input, motor output, and language output channels, respectively. This indicates the matrix transpose.

[0168] This invention provides a specific implementation of a mission-based pilot workload prediction model. The model is constructed as a multi-module matrix calculation framework, designed to comprehensively evaluate a pilot's workload at a specific moment. Its core calculation model utilizes a comprehensive formula. To achieve this, the formula integrates the functions of the influencing factors module, task unit module, conflict task module, and multi-task module. The model first decomposes the tasks performed by the pilot into five independent processing channels based on Wickens' multi-resource theory: visual perception (v), auditory perception (a), cognition (c), action output (k), and language output (s), laying the foundation for subsequent matrix calculations.

[0169] In this embodiment, the computational input of the model consists of five key matrices. First is the task unit existence matrix A(t) = [ , , , ], where each element is a binary value (0 or 1). , , , These are used to characterize in real time whether a task exists in the five channels (visual, auditory, cognitive, motor, and language) at time t. Next is the single-task load value matrix B(t), a diagonal matrix whose diagonal elements [ , , , ] represents the base load value of a single task unit on each channel; if a channel has no task, its load value is replaced by a unit value of 1 to ensure the effectiveness of matrix operations.

[0170] To accurately model load variations during multi-task parallel processing, this implementation introduces a task conflict coefficient matrix C(t) and a multi-task load coefficient matrix D(t). C(t) is a row vector. , , represent the task conflict coefficients on each channel, used to quantify the additional load caused by multiple tasks occurring simultaneously (i.e., conflicting tasks) within the same channel. Their coefficient values ​​reflect the nonlinear superposition effect of the load; the coefficient value for conflict-free channels is 1. D(t) is a column vector. , respectively, represent the task coefficient matrix on each channel, used to quantify the impact of resource allocation and parallel operation on the total load when tasks on different channels are executed simultaneously (i.e., multitasking). The coefficient value characterizes the relationship between the multitasking load and the arithmetic sum of the individual task loads. The coefficient value of the channel where no multitasking occurs is 1.

[0171] To incorporate situational factors such as the external environment and pilot condition, the model also includes an influencing factor coefficient K(t). This coefficient is a scalar used to correct and adjust the baseline workload value calculated based on the mission. The influencing factors broadly cover four aspects: flight mission characteristics (e.g., normal / abnormal conditions, time pressure, flight phase), flight environment (e.g., weather, terrain, aircraft type), cockpit human-machine interface (e.g., visual cleanliness, operational logic), and individual pilot factors (e.g., fatigue, total flight time). Through this coefficient, the model can dynamically reflect workload fluctuations under different situations.

[0172] In this implementation, all key coefficients and load values ​​were obtained through a series of hierarchically designed experiments, and a database was established. For example, the flight phase coefficient in the influencing factor coefficient K(t) was obtained by controlling the flight phase as a single variable in simulated flight, having pilots perform the same tasks, and evaluating it using a 1-10 workload subjective evaluation scale. Regression analysis was then used to obtain the coefficient values ​​of each phase (e.g., takeoff 0.834, approach 1.257) relative to the baseline. Similarly, the task unit load value B(t) (e.g., "monitoring altitude" 3.73), the task conflict coefficient C(t) (e.g., visual conflict coefficient 1.14), and the multi-task coefficient D(t) (e.g., visual-operation combined task coefficient) were all measured and calibrated through carefully designed single-task, same-channel conflict task, and different-channel multi-task experiments, combined with subjective evaluation scales and regression analysis methods, thereby ensuring the effectiveness and practical application value of the entire prediction model. Single-task load value matrix. The acquisition method is as follows: Subjective workload evaluation values ​​of the tested pilots in different independent operating units are collected as... Single-task unit load value; multi-task load factor matrix The acquisition method is as follows: Subjective workload evaluation values ​​of the tested pilots in different multi-task combination experiments are collected to obtain a multi-task workload coefficient matrix; and a matrix of co-channel task conflict coefficient values ​​are also obtained. The acquisition method is as follows: collect the subjective workload evaluation values ​​of the pilots under test in conflict mission experiments in different channels, and obtain the conflict coefficient value matrix of the same channel mission.

[0173] Traffic density load index

[0174] It reflects the characteristics of traffic flow within the airspace and is an important indicator for measuring workload.

[0175]

[0176] in, This indicates the number of aircraft entering controlled airspace per unit of time, reflecting the overall traffic flow level. This indicates the maximum number of aircraft per minute within the statistical period, reflecting the instantaneous load limit. This indicates the number of aircraft per unit airspace area, reflecting the concentration of spatial distribution. This represents the historical peak number of aircraft entering controlled airspace per unit of time. This indicates the historical peak number of aircraft per minute within the statistical period. This represents the threshold for the volume of a unit of airspace area. , , The weighting coefficient is determined through expert evaluation or the AHP method.

[0177] Communication load indicators

[0178] It is used to quantify the amount and complexity of language interactions between controllers and pilots, reflecting the controllers' cognitive and operational workload in communication.

[0179]

[0180] in, This indicates the number of communications between air traffic controllers and pilots per unit of time, reflecting the intensity of communication. This indicates the average duration of each call, reflecting the amount of information conveyed or the difficulty of coordination in a single interaction. This indicates the diversity of control instructions per unit of time, reflecting the complexity of the communication content. This indicates the maximum number of communications between the controller and the pilot within a given time period. Indicates the longest duration of the call. This indicates the maximum category of instructions issued by the controller per unit of time.

[0181] User interface interaction meets the criteria

[0182] It is used to quantify the interaction efficiency and compliance between controllers and monitoring interfaces. Combining interaction frequency and operational complexity, it reflects whether the interface design is optimized and meets human factors engineering requirements.

[0183]

[0184] in, This indicates that the user interface meets the metrics. Indicates the frequency of mouse clicks. Indicates the window switching frequency. Indicates the length of the operation path.

[0185] Time-characteristic load index

[0186] It is used to quantify the distribution characteristics of controller tasks over time and the impact of emergency tasks on workload, reflecting the rationality of task scheduling and time pressure.

[0187]

[0188] in, Indicates the maximum allowed continuous working time. Indicates the actual continuous working time. This indicates the percentage of urgent tasks. This indicates the uniformity of task distribution.

[0189] The above content lists the specific calculation formulas for all performance indicators provided by this invention. In this step, this invention calculates the actual performance indicators corresponding to the current autonomous operation scenario based on the current meteorological, airspace, ground operation conditions, flight plan, air-to-ground surveillance, and operational restriction information to be evaluated.

[0190] Step S5: Visualize and compare the actual performance indicators and benchmark performance indicators corresponding to the current autonomous operation scenario.

[0191] In some embodiments, the actual performance index data corresponding to the current autonomous operation scenario obtained in step S4 can be acquired, and the corresponding benchmark performance index data can be extracted from the historical model matched in step S2. The performance indicators may include parameters from multiple dimensions such as flight on-time performance, airspace utilization, flight time deviation, fuel consumption efficiency, carbon emissions, runway capacity utilization, taxiing time, waiting time, number of conflict resolutions, and safety margin. These actual performance indicators and benchmark performance indicators are paired to ensure that each actual performance indicator can find a corresponding benchmark performance indicator for comparison.

[0192] In some embodiments, radar charts, bar charts, time series curves, etc., can be used to compare and display the performance indicators.

[0193] In some embodiments, a multi-dimensional comprehensive comparison view is provided. Within the same user interface, the system combines and displays various visualizations, such as a radar chart at the top for overall performance comparison, a bar chart in the middle for detailed numerical comparison, and a time-series curve at the bottom for trend analysis. The system can also provide a dashboard-style comprehensive performance score display, calculating a comprehensive score by weighting multiple performance indicators. It calculates both the actual performance score and the benchmark score, visually displaying the difference between the two using dashboard pointers. The dashboard can be configured with different color zones, such as green for excellent, yellow for good, orange for areas needing improvement, and red for areas with risk, allowing users to quickly assess the current operational status.

[0194] Through the above-mentioned various visualization and comparison methods, the system can comprehensively, intuitively, and clearly compare the actual performance indicators and benchmark performance indicators corresponding to the current autonomous operation scenario, helping operation managers and decision-makers to quickly understand the current operating status, identify performance advantages and disadvantages, and provide strong support for operation optimization and decision-making.

[0195] While the specific embodiments of the present invention depict actions or steps in a particular order, this should be understood as requiring such actions or steps to be performed in the specific order shown or in sequential order, or requiring all illustrated actions or steps to be performed to achieve the desired result. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single implementation. Conversely, various features described in the context of a single implementation may also be implemented individually or in any suitable sub-combination in multiple implementations.

[0196] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for evaluating the autonomous operation efficiency of civil aviation, characterized in that, Includes the following steps: Step S1: Obtain historical operational information data. Historical operational information data includes operational information accumulated during civil aviation operations, including meteorological, airspace, ground operating conditions, flight plans, air-to-ground surveillance, and operational restriction information. Step S2: Based on the historical data of the operation information, establish multiple historical models. Each historical model is used to represent different autonomous operation scenarios of civil aviation. Each autonomous operation scenario includes corresponding benchmark performance indicators. Step S3: Obtain the operational information to be evaluated, match the operational information to be evaluated with multiple historical models, and obtain the current autonomous operation scenario; Step S4: Calculate the actual performance indicators corresponding to the current autonomous operation scenario based on the operational information to be evaluated; Step S5: Visualize and compare the actual performance indicators and benchmark performance indicators corresponding to the current autonomous operation scenario.

2. The method for evaluating the autonomous operation efficiency of civil aviation according to claim 1, characterized in that, Step S2 specifically includes: Step S2-1: Establish multiple typical autonomous operation scenarios and determine the types of performance indicators for each autonomous operation scenario; Step S2-2: Classify the historical data of the operation information into the various typical autonomous operation scenarios to form various historical models; Step S2-3: Calculate the performance index corresponding to each historical model based on the historical data of the operation information, and perform post-processing to obtain the benchmark performance index.

3. The method for evaluating the autonomous operation efficiency of civil aviation according to claim 2, characterized in that, In step S2-1, the various typical autonomous operation scenarios specifically include: autonomous flight rerouting under severe weather conditions, straightening operations under flexible airspace use, single-aircraft trajectory-based operations, emergency response under strong convective weather along the route, autonomous wake separation operations in high-density scenarios, and autonomous decision-making operations for approach procedures.

4. The method for evaluating the autonomous operation efficiency of civil aviation according to claim 3, characterized in that, The steps for determining the types of performance indicators for each autonomous operation scenario include: (1) Determine the types of all performance indicators, including: safety performance evaluation indicators, efficiency performance evaluation indicators, economic performance index indicators, environmental benefit indicators, and the load of the unit and control personnel; (2) Establish different performance indicators for each autonomous operation scenario based on the scenario characteristics of the autonomous operation scenario. Specifically, for each autonomous operation scenario, establish corresponding performance indicator items for each type of performance indicator.

5. The method for evaluating the autonomous operation efficiency of civil aviation according to claim 4, characterized in that, Step S2-2 specifically includes: obtaining the actual flight trajectory and planned route information of the flight based on the flight plan and air-to-ground surveillance information in the historical data of the operation information; and automatically completing the classification of the historical data of the operation information by judging the flight plan and air-to-ground surveillance information. Step S2-3 specifically includes: calculating the performance indicators corresponding to each piece of operational information in the historical data of each historical model, taking the average or clustering of the performance indicators to obtain the corresponding benchmark performance indicators.

6. The method for evaluating the autonomous operation efficiency of civil aviation according to claim 5, characterized in that, Step S3 specifically includes: Based on the flight plan and air-to-ground surveillance information in the operational information to be evaluated, obtain the flight trajectory, flight plan, and operational environment characteristic parameters, and combine these parameters into a feature vector; A machine learning classification model is used to classify the feature vectors to obtain the corresponding current autonomous operation scenario.

7. The method for evaluating the autonomous operation efficiency of civil aviation according to claim 6, characterized in that, In step S4, the actual performance indicators include the workload of the crew and air traffic controllers, which includes the workload of pilots. The formula for calculating the pilot workload index is as follows: in, Indicates in The total workload of pilots at all times Indicates in The coefficients of influencing factors at a given time. Represents the existence matrix of task units. These respectively represent the existence of visual input tasks, auditory input tasks, cognitive tasks, action output tasks, and language output tasks. This represents a matrix representing the single-task load values. These represent the single-task unit workload values ​​for visual input, auditory input, cognitive input, motor output, and language output channels, respectively. This represents the matrix of conflict coefficient values ​​for tasks within the same channel. These represent the task conflict coefficient values ​​for visual input, auditory input, cognitive input, motor output, and language output channels, respectively. This represents the multi-task load factor matrix. These represent the multitasking load coefficient values ​​for visual input, auditory input, cognitive input, motor output, and language output channels, respectively. This indicates the matrix transpose.

8. The method for evaluating the autonomous operation efficiency of civil aviation according to claim 7, characterized in that, The above Influencing factor coefficients at time point The method of obtaining the data is as follows: collect the subjective workload evaluation values ​​of the pilots under test at different flight stages, and perform regression calculation on the evaluation values ​​to obtain the coefficients of influencing factors; Single task load value matrix The acquisition method is as follows: Subjective workload evaluation values ​​of the tested pilots in different independent operating units are collected as... The single-task unit load value in the data; Multi-task load factor matrix The acquisition method is as follows: collect the subjective workload evaluation values ​​of the pilots under test in different multi-task combination experiments, and obtain the multi-task workload coefficient matrix; Coupling coefficient matrix of tasks in the same channel The acquisition method is as follows: collect the subjective workload evaluation values ​​of the pilots under test in conflict mission experiments in different channels, and obtain the conflict coefficient value matrix of the same channel mission.

9. The method for evaluating the autonomous operation efficiency of civil aviation according to claim 8, characterized in that, Step S5 specifically includes: Within the same user interface, radar charts, bar charts, or time series curves are used to display the actual performance indicators and benchmark performance indicators corresponding to the current autonomous operation scenario, thus completing the comparative display.

Images