A human-machine function allocation method, a driving platform and an aircraft based on scenario factors

Abstract

The present invention relates to a human-machine function allocation method, a driving platform and an aircraft based on scenario factors, including: S1. Divide the scenario dimensions of the flight process, determine the scenario factors and corresponding human-machine function allocation coefficients under different scenario dimensions; S2. Decompose the flight tasks to obtain interaction tasks and the reference time required to complete each interaction task; S3. Identify the current scenario factors, calculate in real time the human-machine function allocation coefficients coupled with the scenario factors, obtain the real-time human-machine interaction evaluation value, compare the real-time human-machine interaction evaluation value with the corresponding human-machine function allocation threshold, and construct a real-time dynamic human-machine function allocation mechanism. The present invention efficiently and safely solves the problem of unreasonable load distribution of operators in complex task scenarios of complex systems, optimizes the degree of human participation in the system, dynamically and real-time evaluates the matching degree of the three elements of human, machine and environment, enables the human-machine system to match and coordinate with each other, so as to achieve the real-time optimum of the human-machine system and ensure operation safety.

Description

Technical Field

[0001] The present invention relates to the field of flight control, and particularly to a human-machine function allocation method, a driving platform and an aircraft based on scenario factors. Background Art

[0002] Human-machine function allocation refers to the process of rationally allocating various functions of a system to humans and machines on the basis of analyzing the characteristics of humans and machines in order to achieve the best match of a human-machine system and give full play to the potential of humans and machines.

[0003] One of the existing technologies is to adopt a comparison of human and machine dominant capabilities, use the analytic hierarchy process to determine the weight coefficients of each element in the set of dominant capabilities, and determine the automation level of static human-machine function allocation in the cockpit.

[0004] Another existing technology is to adopt a static human-machine function allocation method. First, a comparison of human and machine dominant capabilities is carried out to form sets of human and machine dominant capabilities; then, the fuzzy analytic hierarchy process is used to determine the weight coefficients of each element in the sets of human and machine dominant capabilities; after dividing the automation level of the civil aircraft cockpit system, the range of the automation level is determined by comparing human and machine dominant capabilities; finally, a multi-attribute group decision-making method based on an interval two-tuple semantic operator is used to determine the automation level of function allocation.

[0005] However, existing human-machine function allocations are all static allocation methods that directly divide functions by using the relative advantages of humans and machines. It will not change regardless of the scenario in which the pilot and the aircraft are located. On the one hand, in an emergency scenario, the pilot needs to quickly respond to and handle the faults generated by the aircraft, and at the same time needs to operate or monitor the current attitude of the aircraft, thus generating a relatively high workload; on the other hand, during a long-term normal cruise, the pilot is in a low-load task of monitoring the aircraft attitude, heading, etc. for a long time, which may cause inattention and slack monitoring. Both states will affect flight safety. Summary of the Invention

[0006] The purpose of the present invention is to solve the disadvantages existing in the prior art. The present invention aims to provide a human-machine function allocation method, a driving platform and an aircraft based on scenario factors, which can realize real-time dynamic allocation operations according to different scenario factors and is used to solve the above problems existing in the prior art.

[0007] The above technical object of the present invention will be achieved by the following technical solutions.

[0008] A human-machine function allocation method based on scenario factors includes the steps:

[0009] S1. Divide the scenario dimensions of the flight process, determine the scenario factors under different scenario dimensions and assign values, and couple the scenario factors to obtain the human-machine function allocation coefficient corresponding to the determined scenario;

[0010] S2. Decompose the flight tasks to obtain the underlying interaction tasks, determine the interaction task set corresponding to the scenario factors, and measure the benchmark time required to complete each of the said interaction tasks;

[0011] S3. Identify the current scenario factors, calculate in real time the human-machine function allocation coefficient in the scenario of multi-scenario factor coupling, perform fuzzy evaluation using parameters such as the human-machine function allocation coefficient and the benchmark time, obtain the real-time evaluation value of human-machine interaction, compare the real-time evaluation value of human-machine interaction with the human-machine function allocation threshold corresponding to the scenario factors, and construct a real-time dynamic human-machine function allocation mechanism.

[0012] In the aspect and any possible implementation manner as described above, a further implementation manner is provided. The scenario dimensions in S1 include weather, flight phase, pilot status, flight status, and / or route / terminal area conditions.

[0013] In the aspect and any possible implementation manner as described above, a further implementation manner is provided. The weather scenario dimension includes: visibility, precipitation, temperature, relative humidity, sky cover, surface wind / route wind, or special weather;

[0014] The flight phase scenario dimension includes: flight plan, pre-flight preparation, pushback / tow and start, taxi out, takeoff, climb, en-route climb, cruise, descent, hold, approach, landing, taxi in, post-flight, end of flight, ground service, or ground maintenance;

[0015] The pilot status scenario dimension includes: normal, fatigued, or incapacitated;

[0016] The flight status scenario dimension includes: normal, engine failure, flight control system failure, landing gear system failure, navigation system failure, or air conditioning system failure;

[0017] The route / terminal area condition scenario dimension includes: runway status, airport altitude, or terminal area busyness status.

[0018] In the aspect and any possible implementation manner as described above, a further implementation manner is provided. Each of the said scenario factors can be further divided until it can be evaluated by the pilot.

[0019] For the aspects and any possible implementation manners described above, a further implementation manner is provided. The coupling of the scenario factors to obtain the human-machine function allocation coefficient corresponding to the determined scenario includes: based on the coupling of scenario factors in different dimensions, an evaluation or simulation training method is used to comprehensively evaluate the human-machine function allocation coefficient corresponding to the scenario factors with different values.

[0020] For the aspects and any possible implementation manners described above, a further implementation manner is provided. In S2, the determination of the reference time required to complete each of the interaction tasks includes: using a measurement method to determine the reference time required to complete each of the interaction tasks.

[0021] For the aspects and any possible implementation manners described above, a further implementation manner is provided. In S3, the current scenario factors are comprehensively judged by the aircraft altitude, speed, attitude, system status, and / or air traffic control information obtained in real time, and the human-machine function allocation coefficient is calculated.

[0022] For the aspects and any possible implementation manners described above, a further implementation manner is provided. The interaction tasks include stabilizing the aircraft attitude, adjusting the target altitude, and / or disconnecting the autopilot.

[0023] For the aspects and any possible implementation manners described above, a further implementation manner is provided. In S2, the flight task is decomposed to obtain an interaction subtask set, including:

[0024] Determine the relatively independent manipulation tasks of the pilot during the task execution process, and form a bottom-layer interaction task set at the execution level.

[0025] For the aspects and any possible implementation manners described above, a further implementation manner is provided. According to the reference time of each interaction task, the operation sequence, operation density, and operation performance of the previous action are evaluated in real time to obtain the current task operation performance, and the operation performance is multiplied by the human-machine function allocation coefficient to obtain the human-machine interaction real-time evaluation value.

[0026] For the aspects and any possible implementation manners described above, a further implementation manner is provided. The human-machine function allocation reference threshold is the ratio of the basic ability value of a person to the fatigue state coefficient.

[0027] The present invention also provides a driving platform, and the driving platform adopts the human-machine function allocation method based on scenario factors of the present invention.

[0028] The present invention also provides an aircraft, and the aircraft includes the driving platform of the present invention.

[0029] Advantageous technical effects of the present invention

[0030] The human-machine function allocation method and cockpit system based on scenario factors provided by the embodiments of the present invention are used to solve the problems of load distribution and safety during the process of a pilot operating an aircraft to perform a flight mission. By identifying scenario factors, sorting out the relationships among the aircraft, the environment, and the pilot, obtaining aircraft parameters in real time to evaluate the aircraft state, and analyzing the pilot's operation performance in real time to evaluate the human-machine function allocation, the degree of participation, workload, and operation performance of the pilot during the task execution are optimized through the human-machine function allocation method, and the matching degree of the human-machine-environment triad is dynamically and real-timely evaluated, so that the human-machine system matches and coordinates with each other to achieve the real-time optimum of the human-machine system and ensure safe and efficient flight. Description of the Drawings

[0031] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings, where:

[0032] Figure 1 is a schematic flowchart of the method in the embodiments of the present invention;

[0033] Figure 2 is a schematic diagram of the specific operation steps in the method of the embodiments of the present invention. Detailed Embodiments

[0034] To make the technical problems, technical solutions, and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the drawings and specific embodiments, but the embodiments of the present invention are not limited thereto.

[0035] As Figure 1 - Figure 2 shown, a human-machine function allocation method based on scenario factors of the present invention includes the steps of:

[0036] S1. Divide the scenario dimensions of the flight process, determine the scenario factors under different scenario dimensions and assign values, and couple the scenario factors to obtain the human-machine function allocation coefficient corresponding to the determined scenario;

[0037] S2. Decompose the flight mission to obtain underlying interaction tasks, determine the interaction task set corresponding to the scenario factors, and measure the reference time required to complete each of the interaction tasks;

[0038] S3. Identify the current scenario factors, calculate the human-machine function allocation coefficient in the scenario of coupling multiple scenario factors in real time, use parameters such as the human-machine function allocation coefficient and the reference time for fuzzy evaluation, obtain the real-time evaluation value of human-machine interaction, compare the real-time evaluation value of human-machine interaction with the human-machine function allocation threshold corresponding to the scenario factors, and construct a real-time dynamic human-machine function allocation mechanism.

[0039] Preferably, the scenario dimensions in S1 in the embodiments of the present invention include: weather conditions, flight phases, pilot status, aircraft status, and / or route / terminal area conditions.

[0040] Preferably, the scenario factors in the embodiments of the present invention in S1 include:

[0041] The weather scenario dimension includes: visibility, precipitation, temperature, relative humidity, sky cover, surface wind / route wind, special meteorology; each factor can be further divided until it can be evaluated by the pilot. For example, precipitation can be further divided into: rain, shower, drizzle, snow, snow shower, graupel, ice pellets, hail, small hail, squall hail; special meteorology can be further divided into: dust devil, squall, funnel cloud, dust storm, sandstorm, thunderstorm, tropical cyclone, turbulence, salt fog, wind shear, and / or volcanic ash; each factor can be further divided until it can be evaluated by the pilot.

[0042] The flight phase scenario dimension includes: flight plan, pre-flight preparation, pushback / tow and start, taxi out, takeoff, climb, en-route climb, cruise, descent, hold, approach, landing, taxi in, post-flight, end of flight, ground service, and / or ground maintenance; each factor can be further divided until it can be evaluated by the pilot.

[0043] The pilot status scenario dimension includes: normal, fatigued, and / or incapacitated; each factor can be further divided until it can be evaluated by the pilot.

[0044] The flight status scenario dimension includes: normal, engine failure, flight control system failure, landing gear system failure, navigation system failure, and / or air conditioning system failure, etc.; each factor can be further divided until it can be evaluated by the pilot. For example, engine failure can be further divided into: single engine failure, dual engine failure, and / or engine degradation; flight control system failure can be further divided into: elevator failure, stabilizer failure, high lift system failure (flap / slat jam), aileron failure, rudder failure, and / or spoiler failure.

[0045] The en-route / terminal area condition scenario dimension includes: runway condition, airport altitude, and / or terminal area traffic density, etc. Each factor can be further divided until it can be evaluated by the pilot; for example, runway condition can be divided into: dry runway, wet runway, contaminated runway.

[0046] Preferably, the human-machine function allocation thresholds corresponding to the scenario factors with different values in the embodiments of the present invention include: based on the coupling of scenario factors in different dimensions, an evaluation or simulation training method is used to comprehensively evaluate the human-machine function allocation thresholds corresponding to the scenario factors with different values.

[0047] The specific process of the present invention is as follows: The human-machine function allocation method based on scenario factor recognition includes the following steps:

[0048] a) Scenario Dimension Division during Pilot Flight

[0049] First, comprehensively analyze the aircraft operation process and divide the scenario dimensions that affect the completion of the flight mission. The divided dimensions should be as relatively independent as possible. The division of the scenario dimension examples given in the present invention includes five scenario dimensions: weather condition, flight phase, pilot status, aircraft status, and route / terminal area conditions.

[0050] b) Identify Scenario Factors and Assign Values

[0051] Identify the scenario factors in all scenario dimensions and assign values to them.

[0052] The assignment of scenario factors can be evaluated through in-the-loop simulation experiments. In the in-the-loop simulation experiment of the present invention, the scenario factors are assigned values from 1 to 10. The higher the score, the greater the impact on the flight mission and the greater the effort made by the pilot when performing the mission. For example, in the weather condition dimension: floating dust = 3, gust = 6, thunderstorm = 9; in the flight phase dimension: flight plan = 1, pre-flight preparation = 1, pushback / tow and start = 1, taxi out, takeoff = 6, climb = 5, en-route climb = 4, cruise = 3, descent = 5, hold = 4, approach = 7, landing = 9, taxi in = 2, post-flight = 1, end of flight = 1; in the pilot status dimension: normal = 1, fatigue = 6, incapacitation = 10; in the aircraft status dimension: normal = 1, single engine failure = 8, dual engine failure = 10, engine degradation = 5, etc.; in the route / terminal area conditions dimension: dry runway = 1, wet runway = 4, contaminated runway = 6, etc.

[0053] c) Determine the Man-Machine Function Allocation Coefficient

[0054] Based on the coupling calculation of scenario factors in different dimensions, determine the man-machine function allocation coefficient under a certain scenario. Methods such as fuzzy mathematics calculation and post-evaluation of pilot in-the-loop simulation can be used. The calculation method of the man-machine function allocation coefficient for the example given in the present invention is as follows.

[0055] (1). Directly superimpose the scenario factors between different dimensions;

[0056] (2). For scenario factors in the same dimension, add the highest factor value and the product of other factor values multiplied by a coefficient.

[0057] Superimpose the results of (1) and (2) again to obtain the man-machine function allocation coefficient.

[0058] For example: gust (3), takeoff (5), pilot normal (1), single engine failure (8), terminal area busy (4), contaminated runway (6), the man-machine function allocation coefficient in this scenario is:

[0059] 3 + 5 + 1 + 8 + (6 + 0.3×4) = 24.2

[0060] d) Determine the pilot interaction task set in a specific scenario

[0061] Determine the various tasks that the pilot needs to perform during the flight, break down the relatively independent control tasks during the task execution, and form the underlying interaction task set at the execution level. In this example, the decomposed interaction tasks include stabilizing the aircraft attitude, adjusting the target altitude, disconnecting the autopilot, etc. According to the target system and target tasks, determine the pilot interaction task set in the specific scenario determined in step c.

[0062] e) Determine the reference time for the underlying interaction tasks

[0063] Conduct experiments based on the determined underlying interaction task set to measure the operation reference time required to complete each interaction task. In this example, the average value is obtained by multiple rounds of actual tests by multiple pilots to obtain the reference time. For example, the reference time for adjusting the target altitude = 2.8s

[0064] f) Complete real-time dynamic human-machine allocation

[0065] Use the relevant parameters obtained in real time to identify the current scenario factors, and automatically match the underlying interaction task set in the current scenario. The parameters given in this example include aircraft altitude, speed, attitude, system status, air traffic control information, etc. Use the above parameters to identify the current scenario factors, and at the same time use the method in step c to calculate the human-machine function allocation coefficient in this scenario. At the same time, collect the pilot operation performance. In this example, the actual operation time, reference time, actual operation sequence, operation interval time, and operation accuracy in the past 5 minutes measured by the driving platform are given. The calculation method of the operation performance of this task is:

[0066] (Actual operation time / reference time) / Operation accuracy in the past 5 minutes + Operation performance of the previous task / Operation interval time = Operation performance of this task

[0067] For example: (1.2 / 1) / 95% + 1.2 / 3 = 1.66

[0068] The calculation method of the real-time evaluation value of human-machine interaction is:

[0069] Operation performance of this task × Human-machine function allocation coefficient in the current scenario = Real-time evaluation value of human-machine interaction

[0070] For example: 1.66 × 24.2 = 40.172

[0071] Determine the reference threshold for human-machine function allocation. The reference threshold represents the ability state of people. In this example, a method for the reference threshold of human-machine function allocation is given, and the calculation method of the reference threshold of human-machine function allocation is as follows:

[0072] Basic ability value of human / fatigue state coefficient = Man-machine function allocation benchmark threshold value

[0073] Assume that the basic ability value of a human is 100, and the fatigue state coefficient can be detected in real time by a physiological detection system. For example, the detection parameters of physiological devices such as electroencephalogram, electrocardiogram, and eye movement. If the fatigue state coefficients are 1.5 and 3, etc., then the man-machine function allocation benchmark threshold values are 100 / 1.5 = 66.666 and 100 / 3 = 33.333 respectively.

[0074] When the real-time evaluation value of man-machine interaction ≤ the man-machine function allocation benchmark threshold value, the system follows the man-machine function allocation benchmark threshold value allocation principle;

[0075] For example: 40.172 < 66.666

[0076] When the real-time evaluation value of man-machine interaction > the man-machine function allocation benchmark threshold value, the next operation task changes the man-machine function allocation scheme according to the real-time evaluation value of man-machine interaction. The aircraft autonomously completes the operation, and the human completes the monitoring role.

[0077] For example: 40.172 > 33.333.

[0078] The present invention also provides a driving platform, in which the cockpit adopts the man-machine function allocation method based on scenario factors described in the present invention.

[0079] The present invention also provides an aircraft, and the aircraft includes the driving platform of the present invention.

[0080] The above description shows and describes several preferred embodiments of the present invention. However, as mentioned above, it should be understood that the present invention is not limited to the form disclosed herein, should not be regarded as excluding other embodiments, but can be used in various other combinations, modifications and environments, and can be changed within the scope of the application concept of the present invention through the above teachings or the technology or knowledge in related fields. And the changes and modifications made by those skilled in the art that do not depart from the spirit and scope of the present invention should all be within the protection scope of the appended claims of the present invention.

Claims

1. A human-machine function allocation method based on scenario factors, characterized in that, it includes the steps of: S1. Divide the scenario dimensions of the flight process, determine the scenario factors under different scenario dimensions and assign values, and determine the corresponding human-machine function allocation coefficients according to the scenario factors; S2. Decompose the flight tasks to obtain an interaction task set, determine the interaction task set corresponding to the scenario factors, and measure the benchmark time required to complete each of the interaction tasks; S3. Identify the current scenario factors, calculate in real time the human-machine function allocation coefficients in the scenario of multi-scenario factor coupling, use the human-machine function allocation coefficients and the benchmark time for evaluation, obtain the real-time evaluation value of human-machine interaction, and compare the real-time evaluation value of human-machine interaction with the human-machine function allocation threshold corresponding to the multi-scenario factors to construct a real-time dynamic human-machine function allocation mechanism.

2. The human-machine function allocation method based on scenario factors according to claim 1, characterized in that, the scenario dimensions in S1 include weather, flight phase, pilot status, flight status and / or route / terminal area conditions.

3. The human-machine function allocation method based on scenario factors according to claim 2, characterized in that, the weather scenario dimension includes: visibility, precipitation, temperature, relative humidity, sky cover, surface wind / route wind and / or special meteorology; the flight phase scenario dimension includes: flight plan, pre-flight preparation, pushback / tow and start, taxi out, takeoff, climb, en-route climb, cruise, descent, hold, approach, landing, taxi in, post-flight, end of flight, ground service and / or ground maintenance; the pilot status scenario dimension includes: normal, fatigued and / or incapacitated; the flight status scenario dimension includes: normal, engine failure, flight control system failure, landing gear system failure, navigation system failure and / or air conditioning system failure; the route / terminal area conditions scenario dimension includes: runway status, airport altitude and / or terminal area busyness status.

4. The human-machine function allocation method based on scenario factors according to claim 3, characterized in that, each of the scenario factors can be further divided until it can be evaluated by the pilot.

5. The human-machine function allocation method based on scenario factors according to claim 1, characterized in that, determining the corresponding human-machine function allocation coefficients according to the scenario factors includes: based on the coupling of scenario factors in different dimensions, using an evaluation or simulation training method to comprehensively evaluate the human-machine function allocation coefficients corresponding to the scenario factors with different values.

6. The human-machine function allocation method based on scenario factors according to claim 1, characterized in that, measuring the benchmark time required to complete each of the interaction tasks in S2 includes: using a measurement method to determine the benchmark time required to complete each of the interaction tasks.

7. The human-machine function allocation method based on scenario factors according to claim 1, characterized in that, in S3, the current scenario factors are comprehensively judged through the aircraft altitude, speed, attitude, system status and / or control information obtained in real time, and the human-machine function allocation coefficients are calculated.

8. The human-machine function allocation method based on scenario factors according to claim 1, wherein, the interaction tasks include stabilizing the aircraft attitude, adjusting the target altitude, and / or disconnecting the autopilot.

9. A driving platform, wherein, the driving platform adopts the human-machine function allocation method based on scenario factors according to any one of claims 1-8.

10. An aircraft, wherein, the aircraft includes the driving platform according to claim 9.

Images