CN114638538B - Fatigue early warning method, device and system for controller and early warning threshold acquisition method - Google Patents

Fatigue early warning method, device and system for controller and early warning threshold acquisition method Download PDF

Info

Publication number
CN114638538B
CN114638538B CN202210351997.XA CN202210351997A CN114638538B CN 114638538 B CN114638538 B CN 114638538B CN 202210351997 A CN202210351997 A CN 202210351997A CN 114638538 B CN114638538 B CN 114638538B
Authority
CN
China
Prior art keywords
air
fatigue
early warning
controller
time
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210351997.XA
Other languages
Chinese (zh)
Other versions
CN114638538A (en
Inventor
张建平
陈振玲
吴卿刚
田小强
王丽伟
胡鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Second Research Institute of CAAC
Original Assignee
Second Research Institute of CAAC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Second Research Institute of CAAC filed Critical Second Research Institute of CAAC
Priority to CN202210351997.XA priority Critical patent/CN114638538B/en
Publication of CN114638538A publication Critical patent/CN114638538A/en
Application granted granted Critical
Publication of CN114638538B publication Critical patent/CN114638538B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06398—Performance of employee with respect to a job function
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Marketing (AREA)
  • Quality & Reliability (AREA)
  • Data Mining & Analysis (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Evolutionary Biology (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Primary Health Care (AREA)
  • Traffic Control Systems (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

The application provides a controller fatigue early warning method, a device, a system and an early warning threshold value acquisition method, which are used for acquiring fatigue early warning parameters in a preset time period of all control units so as to further acquire fatigue coefficients of the whole control industry and all control units, comparing the group fatigue degree acquired by fatigue test before a post with a group early warning threshold value acquired by predicting the post fatigue requirement of a post to be on duty, comparing the individual fatigue degree of a controller acquired by fatigue monitoring in the post with a controller individual fatigue early warning threshold value acquired by predicting the post on duty fatigue requirement in a future time period of the controller, and realizing fatigue monitoring, prediction and early warning on the whole industry, independent control units, groups and controller individuals in a strategy stage of the group layer, thereby being beneficial to managing and controlling fatigue risks from multiple directions so as to ensure aviation safety.

Description

Fatigue early warning method, device and system for controller and early warning threshold acquisition method
Technical Field
The application relates to the field of early warning, in particular to a method, a device and a system for early warning fatigue of a controller and a method for acquiring an early warning threshold.
Background
The guarantee of civil aviation transportation safety is the basic responsibility of the civil aviation control unit, and a civil aviation air traffic controller (also called a controller) plays a key role in the civil aviation transportation safety, so that fatigue risk management and control of the controller on duty becomes an important and complex task. In recent years, some related technologies for monitoring the fatigue state of the controller in real time are presented, however, the technologies are more focused on monitoring the on-duty state of the controller, and if the fatigue of the controller is found, measures are taken again, so that aviation safety is always in a high-risk state; and the international civil aviation organization clearly indicates in the "fatigue management practice supervision manual" (Doc 9966, second edition, 2019 revision) that fatigue is a physiological state in which human mental or physical strength is reduced, and can impair the alertness of people and the ability to fulfill safety-related operation responsibilities, i.e., fatigue judgment is closely related to post safety responsibilities, and the management goal of fatigue risk is to ensure that relevant people (controllers) maintain sufficient alertness (acceptable fatigue level) while fulfilling responsibilities, it is obvious that the existing controller fatigue detection/monitoring technology cannot pre-determine whether the current fatigue level of the controllers can cope with the work needs to be performed in advance, and it is difficult to satisfy the actual demands of civil aviation safety management. In addition, current technology also fails to pre-judge and evaluate the whole regulatory industry, each regulatory unit, and teams in the regulatory unit in advance. Therefore, how to realize fatigue detection, future post fatigue demand prediction and fatigue early warning on the whole industry, independent control units, teams and controllers in an individual mode in the control unit organization level strategic stage, the team level pre-tactic (before post) stage and the individual level tactic (on post) stage respectively, and further to manage and control fatigue risks of different demands from multiple directions, and guarantee aviation safety is a technical problem which needs to be solved urgently in the prior art.
Disclosure of Invention
Aiming at the technical problems, the application adopts the following technical scheme: a method of controller fatigue warning, the method comprising the steps of: s100, judging whether the current requirement meets the first fatigue judgment requirement, the second fatigue judgment requirement or the third fatigue judgment requirement; when the current demand meets the first fatigue determination demand, executing step S210, when the current demand meets the second fatigue determination demand, executing step S310, otherwise executing step S410; S210, acquiring fatigue early warning parameters air_P= (air_P 1,Air_P2,Air_P3,...,Air_PN) of all control units in a first preset time period, wherein N is the number of all control units, and the fatigue early warning parameters air_P i of the ith control unit at least comprise unit types air_type i, Altitude Air height i, control mode Air manage i, control area Air area i, total number of duty controllers Air num i, the total number of controllers air_num_light i on duty at night, the total number of controllers air_num_high i on duty at peak traffic, the duration of the controller duty air_time i, Controller post attendance time air_work_time i, controller night post attendance time air_light_time i, controller peak flow period post attendance time air_high_time i, The non-station duty time length air_ rwork _time i of the controller and the duty time length air_other_time i of the controller of other jobs are equal to or more than 1 and equal to or less than N; s220, acquiring the integral fatigue coefficient IoF of all control units and/or the unit fatigue coefficient air_ IoF = [ air_ IoF 1,Air_IoF2,Air_IoF3,...,Air_IoFN ] of all control units based on the fatigue early warning parameter air_P, wherein, Unit fatigue coefficient of the ith regulatory unit Air_f i1 =1, a weighting factor for the i-th regulatory unit's controller post duty duration air_work_time i, air_f i2 =0 when the i-th regulatory unit is a civil airport, otherwise, Air_f i2＝Air_fmi×Air_other_timei/Air_work_timei,Air_fmi is a weighting coefficient for other operation times of the ith regulatory unit, air_f i3 is a function of altitude air_height i for the ith regulatory unit, when the guaranteed shelf count is greater than or equal to a preset flow threshold air_ft i for the aircraft of the ith regulatory unit, The ith control unit is judged to be in a peak flow period, and when the ith control unit is in an off-peak flow period, air_f i4 =0; otherwise ,Air_Fi4＝Air_num_highi×Air_high_timei/Air_work_timei,Air_Fi5＝Air_num_nighti×Air_night_timei/Air_work_timei, is a function of the i-th regulatory unit night station duty time length air_light_time i; Air_f i6 is a function of the i-th unit of control, air_ manage i, air_f i7 is a function of the i-th unit of control, air_area i, air_F i8 is the weighting coefficient of the non-post duty time length of the ith control unit; S230, performing fatigue early warning on the whole management industry according to the whole fatigue coefficient IoF, and/or performing fatigue early warning on a control unit with a higher fatigue coefficient group in different control unit types based on the unit fatigue coefficient air_ IoF and the fatigue early warning parameter air_P; S310, obtaining a test fatigue value set_ PreIoF = [ set_ PreIoF 1,Set_PreIoF2,...,Set_PreIoFM ] of a team controller of an ith control unit in a second preset time period before the guard, wherein M is the total number of people of the team controller, and the test fatigue value set_ PreIoF k of the kth controller is determined according to video test data of the kth controller, Obtaining at least one of alertness test data and subjective scale data, wherein k is more than or equal to 1 and less than or equal to M; S320, calculating early warning value set_AL= [ set_AL 1,Set_AL2,...,Set_ALM ] of the team controllers, and early warning based on the early warning value set_AL, wherein set_AL k＝Set_PreIoFk-Set_ALPk,Set_ALPk is fatigue early warning threshold value of kth controllers about to-be-on-duty post, team fatigue early warning threshold value set_ALP= [ set_ALP 1,Set_ALP2,...,Set_ALPM ], Acquiring early warning threshold parameters in a designated time interval in a to-be-attendance time period of the group according to the group, wherein the early warning threshold parameters at least comprise the attendance time of the group, the predicted flight quantity, the predicted attendance duration, the predicted weather condition, the predicted special condition and the predicted attribute of a controller; S410, obtaining a controller Person' S controller integrated fatigue level value person_ IoF =person_c 1×F_pose+Person_C2×F_face+Person_C3 ×f_voice, where f_ pose is the current controller fatigue level value based on behavior gestures, f_face is the current controller fatigue level value based on facial features, f_voice is the current controller fatigue level value based on land-air calls, person_c 1 is the weight coefficient of f_ pose, person_c 2 is the weight coefficient of f_face, person_c 3 is the weight coefficient of f_voice; S420, calculating an early warning value person_AL=person_ IoF-person_ALP of the Person on the controller, and carrying out early warning based on the early warning value person_AL, wherein the individual fatigue early warning threshold person_ALP of the controller is obtained according to early warning threshold judging parameters in a future time zone set in a post duty time period of the Person on the controller in post duty, and the early warning threshold judging parameters at least comprise predicted flight quantity, predicted weather conditions, predicted special conditions and predicted Person attributes of the Person on the controller related to the post in duty.
A controller fatigue warning device, the device comprising: a first data obtaining module, configured to obtain, when a current requirement meets a first fatigue determination requirement, a fatigue early-warning parameter air_p= (air_p 1,Air_P2,Air_P3,...,Air_PN) of all control units in a first preset time period, where N is a number of the all control units, where the fatigue early-warning parameter air_p i of the ith control unit at least includes a unit type air_type i, Altitude Air height i, control mode Air manage i, control area Air area i, total number of duty controllers Air num i, the total number of controllers air_num_light i on duty at night, the total number of controllers air_num_high i on duty at peak traffic, the duration of the controller duty air_time i, Controller post attendance time air_work_time i, controller night post attendance time air_light_time i, controller peak flow period post attendance time air_high_time i, The non-station duty time length air_ rwork _time i of the controller and the duty time length air_other_time i of the controller of other jobs are equal to or more than 1 and equal to or less than N; A first data processing module, configured to obtain an overall fatigue coefficient IoF of the all control units and/or a unit fatigue coefficient air_ IoF = [ air_ IoF 1,Air_IoF2,Air_IoF3,...,Air_IoFN ] of the all control units based on the fatigue early warning parameter air_p, Unit fatigue coefficient of the ith regulatory unit Air_f i1 =1, a weighting factor for the i-th regulatory unit's controller post duty duration air_work_time i, air_f i2 =0 when the i-th regulatory unit is a civil airport, otherwise, Air_f i2＝Air_fmi×Air_other_timei/Air_work_timei,Air_fmi is a weighting coefficient for other operation times of the ith regulatory unit, air_f i3 is a function of altitude air_height i for the ith regulatory unit, when the guaranteed shelf count is greater than or equal to a preset flow threshold air_ft i for the aircraft of the ith regulatory unit, The ith control unit is judged to be in a peak flow period, and when the ith control unit is in an off-peak flow period, air_f i4 =0; otherwise ,Air_Fi4＝Air_num_highi×Air_high_timei/Air_work_timei,Air_Fi5＝Air_num_nighti×Air_night_timei/Air_work_timei, is a function of the i-th regulatory unit night station duty time length air_light_time i; Air_f i6 is a function of the i-th unit of control, air_ manage i, air_f i7 is a function of the i-th unit of control, air_area i, air_F i8 is the weighting coefficient of the non-post duty time length of the ith control unit; The first fatigue early warning module is used for carrying out fatigue early warning on the whole management industry according to the whole fatigue coefficient IoF and/or carrying out fatigue early warning on the control units with higher fatigue coefficients in different control unit types based on the unit fatigue coefficient air_ IoF and the fatigue early warning parameter air_P; A second data obtaining module, configured to obtain, when the current demand meets the second fatigue determination demand, a test fatigue value set_ PreIoF = [ set_ PreIoF 1,Set_PreIoF2,...,Set_PreIoFM ] of the team controller of the ith control unit within a second preset time period before the team controller is on duty, where M is the total number of people of the team controller, where the test fatigue value set_ PreIoF k of the kth controller is according to the video test data of the kth controller, Obtaining at least one of alertness test data and subjective scale data, wherein k is more than or equal to 1 and less than or equal to M; A second data processing module, configured to calculate an early warning value set_al= [ set_al 1,Set_AL2,...,Set_ALM ] of the team controller, where set_al k＝Set_PreIoFk-Set_ALPk,Set_ALPk is a fatigue early warning threshold of the kth controller with respect to a duty to be performed, the team fatigue early warning threshold set_alp= [ set_alp 1,Set_ALP2,...,Set_ALPM ], Acquiring early warning threshold parameters in a designated time interval in a to-be-attendance time period of the group according to the group, wherein the early warning threshold parameters at least comprise the attendance time of the group, the predicted flight quantity, the predicted attendance duration, the predicted weather condition, the predicted special condition and the predicted attribute of a controller; and the second fatigue early warning module is used for early warning based on the early warning value set_AL. A third data acquisition module for acquiring a controller integrated fatigue level value person_ IoF =person_c 1×F_pose+Person_C2×F_face+Person_C3 ×f_voice for a controller Person when the current demand meets a third fatigue determination demand, wherein f_ pose is a current behavior-posture-based controller fatigue level value, f_face is a current facial-feature-based controller fatigue level value, f_voice is a current ground-air call-based controller fatigue level value, Person_c 1 is the weight coefficient of f_ pose, person_c 2 is the weight coefficient of f_face, person_c 3 is the weight coefficient of f_voice; The third data processing module is used for calculating an early warning value person_al=person_ IoF-person_alp of the Person of the controller, wherein the individual early warning threshold person_alp of the controller is obtained according to early warning threshold judging parameters in a future time zone set in a post duty time period of the Person of the controller in post duty, and the early warning threshold judging parameters at least comprise predicted flight quantity, predicted weather conditions, predicted special conditions and predicted Person attributes of the controller related to the post in duty; and the third fatigue early warning module is used for early warning based on the early warning value person_AL.
A controller fatigue early warning system comprising a processor and a non-transitory storage medium storing at least one instruction or at least one program loaded and executed by the processor to implement the fatigue early warning method described above.
A method for acquiring an overall fatigue coefficient early warning threshold total_ALP of a control industry comprises the following steps: s231, acquiring the integral fatigue coefficients and the number of unsafe events of all control units in a plurality of different historical time periods; s232, carrying out data driving iteration by utilizing the integral fatigue coefficients and the number of unsafe events in the plurality of different historical time periods to obtain the integral fatigue coefficient early warning threshold total_ALP.
A method of obtaining the overall fatigue coefficient of all regulatory units and the unit fatigue coefficients of each unit, the method comprising the steps of: s210, acquiring fatigue early warning parameters air_P= (air_P 1,Air_P2,Air_P3,...,Air_PN) of all control units in a first preset time period, wherein N is the number of all control units, and the fatigue early warning parameters air_P i of the ith control unit at least comprise unit types air_type i, Altitude Air height i, control mode Air manage i, control area Air area i, total number of duty controllers Air num i, the total number of controllers air_num_light i on duty at night, the total number of controllers air_num_high i on duty at peak traffic, the duration of the controller duty air_time i, Controller post attendance time air_work_time i, controller night post attendance time air_light_time i, controller peak flow period post attendance time air_high_time i, The non-station duty time length air_ rwork _time i of the controller and the duty time length air_other_time i of the controller of other jobs are equal to or more than 1 and equal to or less than N; s220, acquiring the integral fatigue coefficient IoF of all control units and/or the unit fatigue coefficient air_ IoF = [ air_ IoF 1,Air_IoF2,Air_IoF3,...,Air_IoFN ] of all control units based on the fatigue early warning parameter air_P, wherein, Unit fatigue coefficient of the ith regulatory unit Air_f i1 =1, which is a weighting coefficient of the air_work_time i of the duty time of the controller post of the ith control unit, when the ith control unit is a civil airport, air_f i2 =0, otherwise, air_f i2＝Air_fmi×Air_other_timei/Air_work_timei,Air_fmi is a weighting coefficient of other working time of the ith control unit, air_f i3 is a function of altitude air_height i of the ith control unit, when the aircraft guarantee frame number of the ith control unit is greater than or equal to a preset flow threshold air_ft i, the ith control unit is determined to be in a peak flow period, and when the ith control unit is in a non-peak flow period, air_f i4 =0; otherwise ,Air_Fi4＝Air_num_highi×Air_high_timei/Air_work_timei,Air_Fi5＝Air_num_nighti×Air_night_timei/Air_work_timei, is a function of the i-th regulatory unit night duty time air_light_time i, air_f i6 is a function of the i-th regulatory unit regulatory mode air_ manage i, air_f i7 is a function of the i-th regulatory unit regulatory region air_area i, and air_f i8 is a weighting factor for the non-duty time of the i-th regulatory unit.
A method of obtaining a team fatigue early warning threshold Set ALP, comprising: s331, acquiring an early warning threshold parameter in a specified time interval in a to-be-attended time period of the group, wherein the early warning threshold parameter at least comprises the attendance time, the predicted flight quantity, the predicted attendance duration, the predicted special condition, the predicted weather condition and the predicted attribute of a controller of the group, and the duration of the specified time interval is in a value range of [20 minutes, 300 minutes ]; s332, obtaining a group basic fatigue value set_P= [ set_P 1,Set_P2,...,Set_PM ] of the group according to the early warning threshold parameter, wherein set_P k represents a basic fatigue value of a kth controller of the group; s333, a group fatigue early warning threshold set_alp= [ set_alp 1,Set_ALP2,...,Set_ALPM ] of the group is obtained based on set_p, where set_alp k＝Set_C×Set_Pk and set_c is a group post adjustment coefficient.
A method of obtaining an individual fatigue early warning threshold person_alp for a controller, comprising: s431, acquiring early warning threshold judging parameters in a future time region set in a post attendance time period of a controller Person in post attendance, wherein the early warning threshold judging parameters at least comprise predicted flight quantity, predicted weather conditions, predicted special conditions and predicted attribute of the controller Person, and the duration value range of the future time region is set to be [3 minutes, 20 minutes ]; s432, acquiring a person_F b of a basic requirement value of the duty post fatigue degree of the controller according to the early warning threshold judging parameter; s433, acquiring an individual fatigue early warning threshold value person_ALP= (person_A1+person_A2×person_A3) ×person_F b of the controller according to the person_F b of the basic requirement value of the duty post fatigue degree, wherein person_A1 is a human circadian rhythm coefficient of an individual on duty time controller, and person_A2 is a post coefficient for indicating the requirement of the duty post of the controller for the fatigue degree; person_a3 is a post mission requirement factor that indicates the need for the expected flight plan traffic flow pattern to be tiring for the controller.
The application has at least the following technical effects: fatigue early warning parameters of all control units in a preset time period are obtained, fatigue coefficients of the whole control industry and even all control units are obtained, and fatigue monitoring, prediction and early warning are carried out on the whole control industry, high-risk control units, teams and individuals on the basis of the fatigue coefficients. In addition, by comparing the team fatigue degree obtained by the pre-post fatigue test with a team early warning threshold obtained by predicting the post fatigue requirement of the post to be attended by the team, and by comparing the personal fatigue degree of the controller obtained by fatigue monitoring in the post with the individual fatigue warning threshold of the controller obtained by predicting the post on duty fatigue requirement of the controller in a period of time in the future, whether the management personnel can cope with the working requirement of the post to be attended can be detected before the post, and whether fatigue abnormality occurs in the post personnel in the future for 3-20 minutes can be judged even after the management personnel is on duty, namely whether the management personnel can cope with the future aviation safety requirement from multiple angles is predicted. The fatigue detection, future post fatigue demand prediction and fatigue early warning on the whole industry, independent control units, teams and controller individuals are realized in the control unit organization level strategy stage, the team level pre-tactic (pre-post) stage and the individual level tactic (on-post) stage respectively, so that fatigue risk management and control on different demands from multiple directions are facilitated, and aviation safety is guaranteed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for early warning of fatigue of a controller according to an embodiment of the present application;
FIG. 2 is a block diagram of a controller fatigue warning device according to an embodiment of the present application;
FIG. 3 is a method for obtaining a team fatigue early warning threshold set_ALP according to another embodiment of the present application;
FIG. 4 is a method for obtaining an individual fatigue early warning threshold person_ALP for a controller according to another embodiment of the present application;
fig. 5 is a flowchart of a method for early warning of fatigue of a controller according to another embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
Fig. 1 is a schematic diagram of a method for early warning of fatigue of a controller, which includes the following steps:
S100, judging whether the current demand meets the first fatigue judgment demand, the second fatigue judgment demand or the third fatigue judgment demand, executing step S210 when the current demand meets the first fatigue judgment demand, executing step S310 when the current demand meets the second fatigue judgment demand, otherwise executing step S410. The first fatigue determination requirement is, for example, a fatigue determination requirement of a strategic stage of a control unit organization level, the second fatigue determination requirement is, for example, a fatigue determination requirement of a pre-tactical stage of a team level, the third fatigue determination requirement is, for example, a fatigue determination requirement of an individual level tactical stage, different requirements can be met from three different aspects by distinguishing different stages, for example, in the strategic stage of the control unit organization level, the current condition of the whole control industry can be judged on the whole by calculating the fatigue coefficient of the whole control industry, the whole control industry is regulated and controlled according to the current condition, for example, the quantity of control staff is insufficient, and control staff can be increased. The fatigue coefficient can also be calculated for different control units, the relevant condition of the control units can be judged, and staff adjustment and the like can be performed according to the conditions.
S210, acquiring fatigue early warning parameters air_P= (air_P 1,Air_P2,Air_P3,...,Air_PN) of all control units in a first preset time period, wherein N is the number of all control units, and the fatigue early warning parameters air_P i of the ith control unit at least comprise unit types air_type i, Altitude Air height i, control mode Air manage i, control area Air area i, total number of duty controllers Air num i, the total number of controllers air_num_light i on duty at night, the total number of controllers air_num_high i on duty at peak traffic, the duration of the controller duty air_time i, Controller post attendance time air_work_time i, controller night post attendance time air_light_time i, controller peak flow period post attendance time air_high_time i, The non-station duty time length air_ rwork _time i of the controller and the duty time length air_other_time i of the controller of other jobs are equal to or more than 1 and equal to or less than N.
In the present application, the first preset time period may be a historical time period or a future time period, and the duration of the time period may be set according to specific requirements, for example, may be one week, one month, or the like. When the first preset time period is a future time period, related fatigue early warning parameters can be obtained according to the flight plan of the control unit and the working time of the controller, and safety risk problems of the control industry and/or the control unit in the future time period can be judged according to the fatigue parameters so as to facilitate staff change and the like in advance.
In the present application, the type air_type i of the regulatory unit may be a plurality of types set in advance, for example, may be a regional regulatory unit, a near regulatory unit, a civil regulatory unit in which the tower is regulated and the annual volume is 50-200 ten thousand, or the like. The total number of the control unit types can be divided according to actual conditions. The altitude air_height i of the regulatory unit can be obtained by various means, such as inquiring geographic information, etc. The control mode air_ manage i can be divided into program control, radar monitoring control and other four types. The control region air_area i is measured according to the actual situation. the total number of the on-duty controllers air_num i of the ith control unit, the total number of the on-duty controllers air_num_right i of the ith control unit at night and the total number of the on-duty controllers air_num_high i of the ith control unit at peak traffic period can be acquired by collecting the unique identification of the controllers and the actual working time point of the controllers on the one hand, The individual parameters may on the other hand be obtained according to a flight schedule. The same manner can also be used to obtain the controller duty time air_time i of the ith control unit, the controller post duty time air_work_time i of the ith control unit, the controller night duty time air_light_time i of the ith control unit, the i-th control unit's controller peak traffic period station duty time air_high_time i, the controller off-station duty time air_ rwork _time i, and the controller duty time air_other_time i for other jobs of the control unit. In addition, in the application, when the aircraft hour guarantee frame quantity of the ith control unit is more than or equal to a preset flow threshold air_FT i, the ith control unit is judged to be in a peak flow period. The preset flow threshold air_ft i is set according to actual flight data of a control unit or a flight plan.
S220, acquiring the integral fatigue coefficient IoF of all control units and/or the unit fatigue coefficient air_ IoF = [ air_ IoF 1,Air_IoF2,Air_IoF3,...,Air_IoFN ] of all control units based on the fatigue early warning parameter air_P, wherein, Unit fatigue coefficient of the ith regulatory unit Air_f i1 =1, a weighting factor for the i-th regulatory unit's controller post duty duration air_work_time i, air_f i2 =0 when the i-th regulatory unit is a civil airport, otherwise, Air_f i2＝Air_fmi×Air_other_timei/Air_work_timei,Air_fmi is the weighting coefficient of other operation time of the ith control unit, and the value range is [1.00,4.00], preferably 1.80; Air_f i3 is a function of altitude air_height i for the ith regulatory unit, ranging from [0.00,8.00], preferably 4.21; in the application, when the aircraft hour guarantee frame quantity of the ith control unit is more than or equal to a preset flow threshold air_FT i, the ith control unit is judged to be in a peak flow period, and when the ith control unit is in an off-peak flow period, air_F i4 =0; Otherwise ,Air_Fi4＝Air_num_highi×Air_high_timei/Air_work_timei,Air_Fi5＝Air_num_nighti×Air_night_timei/Air_work_timei, is a function of the ith regulatory unit controller night station duty duration air_num_right i; air_F i6 is a function of an ith control unit control mode air_ manage i, and the value range is [0.00,6.00]; air_F i7 is a function of the ith regulatory unit regulatory region air_area i, and the value range is [0.00,7.00]; air_f i8 is the weighting factor for the off-duty length of the ith regulatory unit, which is in the range of [0.20,1.00], preferably 0.64.
As can be seen from the above, the present application firstly obtains the relevant objective parameters affecting the control units and the control industry, including the unit type air_type i, altitude air_height i, control mode air_ manage i, all of each unit, Control area air_area i, on duty controller total air_num i, night on duty controller total air_num_right i, peak traffic on duty controller total air_num_high i, Controller duty time air_time i, controller post duty time air_work_time i, controller night post duty time air_light_time i, controller peak flow period duty time air_high_time i, the non-station duty time length air_ rwork _time i of the controller and the duty time length air_other_time i of the controller of other operations are combined with a specific calculation method on the basis of the parameters to further calculate the integral fatigue coefficient of the control industry and the fatigue coefficient of each control unit, and by integrating a plurality of influencing factors, The real fatigue degree of the whole industry and each control unit can be evaluated more accurately and objectively, so that the applicability and popularization of the fatigue coefficient acquisition method are stronger.
S230, performing fatigue early warning on the whole management industry according to the whole fatigue coefficient IoF, and/or performing fatigue early warning on a control unit with a higher fatigue coefficient group in different control unit types based on the unit fatigue coefficient air_ IoF and the fatigue early warning parameter air_P. Specifically, in one embodiment, based on the unit fatigue coefficient air_ IoF and the fatigue early warning parameter air_p, performing fatigue early warning on the control units with higher fatigue coefficients in different control unit types is as follows: and sequencing the control units of different types according to the size of the fatigue coefficient, and then performing early warning prompt on the control unit with the numerical value sequenced to the front in the control units of different types, wherein the control unit type data can be obtained from the fatigue early warning parameter air_P, and the corresponding fatigue related data can be obtained from the fatigue coefficient air_ IoF. For example, for the first class of control units, there are 4 corresponding fatigue coefficients of 200, 100, 150 and 300, and then the first class of control units are ranked according to the sizes of 300, 200, 150 and 100, and when the first two classes of control units need to be pre-warned, two control units with fatigue coefficients of 300 and 200 respectively need to be pre-warned. The first type of control unit has 4 examples for explaining the early warning mode conveniently, and does not represent the actual control unit number, and the actual first type of control unit data is based on the actual acquired number. In the application, an early warning alarm standard can be set, when the fatigue coefficient of the control unit is larger than or equal to the early warning alarm standard, the control unit is early warned, otherwise, the early warning is not needed. The early warning alarm standard can be obtained according to historical experience and can also be obtained in other modes, and the method for obtaining the early warning alarm standard is not particularly limited. In another embodiment, based on the unit fatigue coefficient air_ IoF and the fatigue early warning parameter air_p, performing fatigue early warning on the control units with higher fatigue coefficients in different control unit types is as follows: firstly, classifying all control units based on the fatigue early warning parameter air_P, secondly, sorting each type of control units according to the size of the fatigue coefficient, then, classifying each type of control units after sorting into groups with lower, middle and higher fatigue coefficients by adopting a clustering method, and finally, carrying out early warning prompt on the control units which enter the group with higher numerical value after clustering in each type of control units, and clustering the fatigue coefficients of each control unit in a clustering mode, so that the inherent distribution rule among data can be better mined. Specifically, the fatigue coefficients may be clustered using a commonly used K-mean clustering method, and the clustering method used in the present application may be any clustering method in the prior art.
Specifically, according to the integral fatigue coefficient IoF, fatigue early warning is performed on the whole of the management industry, in one embodiment, the integral fatigue coefficient IoF may be compared with a historical integral fatigue coefficient of the whole industry, when the integral fatigue coefficient IoF is greater than the historical integral fatigue coefficient, early warning is performed when the integral fatigue coefficient IoF is greater than the historical integral fatigue coefficient to a certain extent, and in another embodiment, the certain extent may be combined with an unsafe event in a first preset time period (when the first preset time period is a historical time period) of the management unit to determine whether early warning is performed. In yet another embodiment, the early warning is performed when the overall fatigue coefficient IoF is greater than or equal to an overall fatigue coefficient early warning threshold total_alp, wherein the overall fatigue coefficient early warning threshold total_alp is obtained by performing data-driven iteration based on the overall fatigue coefficients of all the regulatory units and the number of unsafe events of all the regulatory units obtained in a plurality of different historical time periods. For example, if the overall fatigue coefficient IoF _1 of all regulatory units in the first historical period is a first value, the number of unsafe events is 0, the overall fatigue coefficient IoF _2 in the second historical period is a second value, and the number of unsafe events is 0, then although the second value IoF _2 > the first value IoF _1, the IoF _2 is not used as the overall fatigue coefficient early warning threshold total_alp because the unsafe events in the second historical period are 0, if the overall fatigue coefficient IoF _3 in the third historical period is a third value, the number of unsafe events is 2, the third value IoF _3 > the second value IoF _2, and more unsafe events occur in the third historical period, the IoF _3 can be used as the overall fatigue coefficient threshold total_alp, and so on, by combining the overall fatigue coefficient and the unsafe events in the historical periods, the overall fatigue coefficient early warning threshold total_alp can be finally obtained. And the duration of the first history time period, the second history time period and the third history time period can be one month, one week and the like, and the integral fatigue coefficient early warning threshold total_ALP can be quickly and effectively obtained by properly selecting the statistical duration.
The embodiment of the invention also discloses a method for acquiring the integral fatigue coefficient early warning threshold total_ALP, which comprises the following steps:
s231, acquiring the integral fatigue coefficients and the number of unsafe events of all control units in a plurality of different historical time periods;
s232, carrying out data driving iteration by utilizing the integral fatigue coefficients and the number of unsafe events in a plurality of different historical time periods to obtain the integral fatigue coefficient early warning threshold total_ALP.
The objective indexes of the control units are obtained, so that the overall fatigue coefficient of the control industry and the unit fatigue coefficient of each control unit can be obtained, whether the overall control industry and the control units have safety risks can be effectively and objectively detected through the overall fatigue coefficient and the unit fatigue coefficient, and when the safety risks are large, the relevant conditions of the control industry can be integrally and properly adjusted, and on the other hand, the control units with higher fatigue coefficients can be timely reminded to make proper adjustment so as to reduce the fatigue risks.
S310, obtaining a test fatigue value set_ PreIoF = [ set_ PreIoF 1,Set_PreIoF2,...,Set_PreIoFM ] of a team controller of an ith control unit in a second preset time period before the team controller is on duty, wherein M is the total number of people of the team controller. Preferably, in the present application, the length of the second preset time period is 5 minutes, which can ensure the detection fidelity of the controller during the test, and can avoid the fake fatigue of the controller caused by the overlong test time, thereby affecting the test authenticity. Specifically, in the application, the test fatigue value set_ PreIoF k of the kth controller is obtained according to at least one of video test data, alertness test data and subjective scale data of the kth controller, wherein k is more than or equal to 1 and less than or equal to M. In one embodiment ,Set_PreIoFk＝Ak1×Wk+Ak2×Uk+Ak3×Vk,Ak1、Ak2、Ak3 is the specific gravity factor, A k1 is in the range of [0,3], preferably 2.4, A k2 is in the range of [4,8], preferably 6, A k3 is in the range of [2,5], preferably 3. Wherein the alertness test data V k = (vo+ve)/Vt, where Vo is the number of neglected target letters, ve is the number of selected erroneous letters, and Vt is the total number of target letters; the alertness test data U k＝t/tT, t is the correct reaction time during the alertness test, t T =500 ms, is the reaction time threshold. Video test dataWherein FPs represents a frame rate per second, tv represents a length of the video, W (l) represents a coverage of eyeballs of a person under test at the first frame, sign { } represents an indication function, wherein sign { wire } = 1, sign { false } = 0, 1+.l+.p, and p=fps×tv are frames of the video.
S320, calculating an early warning value set_AL= [ set_AL 1,Set_AL2,...,Set_ALM ] of the team controller, and carrying out early warning based on the early warning value set_AL, wherein set_AL k＝Set_PreIoFk-Set_ALPk,Set_ALPk is a fatigue early warning threshold value of the kth controller about a duty to be performed, and the team fatigue early warning threshold value set_ALP= [ set_ALP 1,Set_ALP2,...,Set_ALPM ] is obtained according to early warning threshold value parameters in a time interval specified in a duty time period of the team, wherein the early warning threshold value parameters at least comprise duty time of the team, predicted flight volume, predicted duty time, predicted weather condition, predicted special condition and predicted self attribute of the controller. Specifically, when set_al k≥Set_ALPk, i.e., set_al k is greater than or equal to 0, the system gives an early warning to the controller, and the team can arrange other controllers meeting the management requirements in time for replacement.
In one embodiment of the present invention, a method for obtaining a team fatigue early warning threshold set_alp is also disclosed, as shown in fig. 3, the method includes:
S331, acquiring early warning threshold parameters in a designated time interval in a to-be-attendance time period of the group, wherein the early warning threshold parameters at least comprise the attendance time, the predicted flight quantity, the predicted attendance duration, the predicted weather condition, the predicted special condition and the predicted attribute of the controller of the group. Wherein the duration of the specified time interval is in the range of 20 minutes, 300 minutes, preferably 120 minutes, for example, the team starts working at 4 pm, then we set the specified time interval to be 4 to 6 points. The duty time may be, for example, morning, evening, etc., and the flight volume is a predicted flight volume, which may be predicted based on a flight plan of a regulatory unit, for example, a flight volume of 3 flights in a specified time zone, but temporary landings are not excluded, etc., and in this case, it is necessary to predict the flight volume of the group in the specified time zone based on the above-described flight plan and temporary factors. Likewise, the duty duration is also a predicted duty duration of the team, e.g., 1 hour, 2 hours, etc., and the controller's own attributes include, for example, fatigue status, circadian rhythm type, recent sleep status, preface duty condition, gender, age, work age, etc.
And S332, acquiring a group basic fatigue value set_P= [ set_P 1,Set_P2,...,Set_PM ] of the group according to the early warning threshold parameter, wherein set_P k represents the basic fatigue value of a kth controller of the group. Specifically, in this embodiment, the kth controller's base fatigue value set_p k is a function of the early warning threshold parameter of the controller, for example, the duty time assigned to the team, the predicted number of flights, the predicted duration of duty, the predicted weather condition, and the predicted kth controller's own attribute are summed after being assigned different weights to obtain the base fatigue value set_p k.
S333, acquiring a group fatigue early warning threshold value set_ALP= [ set_ALP 1,Set_ALP2,...,Set_ALPM ] of the group based on set_P, wherein set_ALP k＝Set_C×Set_Pk and set_C are group position adjustment coefficients with the value range of [1.0,5.0], such as position adjustment of a control seat and a coordination seat and position adjustment of different sectors of the control seat, and the adjustment coefficients express the allowable maximum internal position adjustment quantity of the group for coping with the position to be on duty. Through using group post adjustment coefficient, can make early warning standard more accords with actual conditions, and then makes early warning is more accurate, in addition, can also satisfy the group and have holistic assurance to the post of will on duty, the regulation deployment of the controller of being convenient for. Further, set_p is continuously optimized according to the early warning false report rate and the false report missing rate.
The most real fatigue degree of the team controllers can be obtained by carrying out fatigue test on the team controllers before the team, and because the team base fatigue value is obtained according to the related plan of the team to be on duty and the properties of the controllers, the actual demands of the team in the future appointed time can be reflected more objectively, the team can obtain the fatigue state of the whole team controllers more accurately and effectively by comparing the two, and the working adjustment is carried out according to the fatigue state, so that the safety risk is generated due to the fatigue of the controllers.
S310, obtaining a controller comprehensive fatigue degree value person_ IoF =person_C 1×F_pose+Person_C2×F_face+Person_C3 ×F_voice of a controller Person, wherein F_ pose is a controller fatigue degree value based on a current behavior gesture, F_face is a controller fatigue degree value based on a current facial feature, F_voice is a controller fatigue degree value based on a land-air call, person_C 1 is a weight coefficient of F_ pose, person_C 2 is a weight coefficient of F_face, and person_C 3 is a weight coefficient of F_voice. The range of person_c 1 is [0.00,0.80], preferably 0.65, the range of person_c 2 is [0.00,0.40], preferably 0.20, the range of person_c 3 is [0.00,0.25], preferably 0.15, and three person_c 1、Person_C2 and person_c 3 cannot take 0.00 at the same time.
In the application, the behavior gesture information of the controller in duty, such as sleeping duty, off duty and the like, is collected in real time through being linked with the monitoring cameras of the control hall or the tower, the facial feature information of the controller in duty is collected through the high-definition cameras arranged at the proper positions of the control screen, and the land-air conversation information of the controller is obtained through real-time collection. Specifically, analyzing and processing collected controller behavior gesture information, and analyzing dynamic data of the body and gesture of the controller to obtain a current controller fatigue degree value F_ pose based on the behavior gesture; analyzing and processing collected facial information of a controller, and analyzing the breathing, blinking, eyelid closure degree and the like of the controller to obtain a current fatigue degree value F_face of the controller based on facial features; analyzing and processing the collected controller air-ground conversation information, identifying controller voice, identifying and analyzing controller semantics, reaction time and the like to obtain the current controller fatigue degree value F_voice based on air-ground conversation. And each of f_phase, f_face and f_voice may be implemented by any method in the prior art, which is not described herein.
S320, calculating an early warning value person_AL=person_ IoF-person_ALP of the controller Person, and carrying out early warning based on the early warning value person_AL. Specifically, when person_ IoF is greater than or equal to person_alp, the system performs early warning, wherein the individual fatigue early warning threshold person_alp of the controller is obtained according to early warning threshold judgment parameters in a future time zone set in a post attendance time period of the Person of the controller in post attendance, and the early warning threshold judgment parameters at least comprise predicted flight number, predicted weather conditions, predicted special conditions and predicted properties of the Person of the controller related to the post in attendance.
In one embodiment of the present invention, a method for obtaining the individual fatigue early warning threshold person_alp of the controller is also disclosed, as shown in fig. 4, the method includes:
s431, acquiring early warning threshold judging parameters in a future time region set in a post attendance time period of a controller Person in post attendance, wherein the early warning threshold judging parameters at least comprise predicted flight quantity, predicted weather conditions, predicted special conditions and predicted attribute of the controller Person, and the time length of the future time region is set to be 3 minutes and 20 minutes, preferably 5 minutes. The controller's own attributes may include, for example, factors that have an impact on controller fatigue, such as fatigue status, circadian rhythm type, recent sleep conditions, preface conditions, gender, age, work age, and the like.
S432, acquiring a duty post fatigue degree basic requirement value person_F b of the controller according to the early warning threshold judging parameter. Specifically, in this embodiment, the duty post fatigue level base demand value person_f b is a function of the early warning threshold decision parameter of the controller, for example, the predicted flight number, the predicted weather condition, and the predicted controller Person attribute are added together after being assigned different weight values.
S433, acquiring an individual fatigue early warning threshold value person_ALP= (person_A1+person_A2×person_A3) ×person_F b of the controller according to the person_F b of the duty fatigue degree basic requirement value, wherein person_A1 is a human circadian rhythm coefficient of an individual on duty time controller, namely a function related to time, such as high coefficient during night shift and low coefficient during white shift; person_a2 is a post coefficient indicating the need for fatigue level for the post where the controller is located, e.g., the coefficient is small when at the controller's premises, the coefficient is large when at the coordinator's premises, the busy sector coefficient is small, and the general sector coefficient is large; person_a3 is a job demand coefficient that indicates the need for the expected flight plan traffic flow pattern to be tiring for the controller, for example when the flow is high, the demand for the controller is high, and the coefficient is small, otherwise the coefficient is large. Further, the person_alp is continuously optimized according to the early warning false report rate and the false report rate.
The working state of the controller on the post can be truly and accurately calculated through collecting real-time data of the on-post personnel and acquiring the judgment threshold according to parameters in the appointed time in the future of the duty post, the real-time state of the controller is supervised, whether the current fatigue state of the controller can meet the safety fatigue requirement in the appointed time in the future is judged, and when the controller is judged to be unable to meet the safety fatigue requirement, alarming is timely carried out and personnel replacement is carried out, so that the safety risk caused by the fatigue of the controller under the condition of the post can be effectively avoided.
In summary, by acquiring fatigue early warning parameters within a preset time period of all control units, fatigue coefficients of the whole control industry and even all control units are acquired, and fatigue monitoring and early warning are performed on the whole control industry and control units with higher fatigue coefficients based on the fatigue coefficients. In addition, by comparing the team fatigue degree obtained by the pre-post fatigue test with a team early warning threshold obtained by predicting the post fatigue requirement of the post to be attended by the team, and by comparing the personal fatigue degree of the controller obtained by fatigue monitoring in the post with the personal fatigue warning threshold of the controller obtained by predicting the post on duty fatigue requirement of the controller in a period of time in the future, whether the management personnel can cope with the working requirement of the post to be attended can be detected before the post, and whether the fatigue risk of the personnel in the post appears in the future for 3-20 minutes can be judged even after the management personnel is on the post, namely whether the management personnel can cope with the future aviation safety requirement from multiple angles can be predicted. The fatigue detection, future post fatigue demand prediction and fatigue early warning on the whole industry, independent control units, teams and controller individuals are realized in the control unit organization level strategy stage, the team level pre-tactic (pre-post) stage and the individual level tactic (on-post) stage respectively, so that fatigue risk management and control on different demands from multiple directions are facilitated, and aviation safety is guaranteed.
Fig. 2 is a schematic diagram of a controller fatigue early warning device 1 according to an embodiment of the present application, where the device 1 includes:
A first data obtaining module 11, configured to obtain, when the current requirement meets the first fatigue determination requirement, a fatigue early warning parameter air_p= (air_p 1,Air_P2,Air_P3,...,Air_PN) of all control units in a first preset time period, where N is the number of all control units, where the fatigue early warning parameter air_p i of the ith control unit at least includes a unit type air_type i, Altitude Air height i, control mode Air manage i, control area Air area i, total number of duty controllers Air num i, the total number of controllers air_num_light i on duty at night, the total number of controllers air_num_high i on duty at peak traffic, the duration of the controller duty air_time i, Controller post attendance time air_work_time i, controller night post attendance time air_light_time i, controller peak flow period post attendance time air_high_time i, The non-station duty time length air_ rwork _time i of the controller and the duty time length air_other_time i of the controller of other jobs are equal to or more than 1 and equal to or less than N.
In the present application, the first fatigue determination requirement may be, for example, a fatigue determination requirement at a strategic stage of a regulatory organization level, which is advantageous for grasping whether or not there is a safety risk from the regulatory industry as a whole. The first preset time period may be a historical time period or a future time period, and the duration of the time period may be set according to specific requirements, for example, may be a week, a month, or the like. When the first preset time period is a future time period, related fatigue early warning parameters can be obtained according to the flight plan of the control unit and the working time of the controller, and safety risk problems of the control industry and/or the control unit in the future time period can be judged according to the fatigue parameters so as to facilitate staff change and the like in advance.
In the present application, the type air_type i of the regulatory unit may be a plurality of types set in advance, for example, may be a regional regulatory unit, a near regulatory unit, a civil regulatory unit in which the tower is regulated and the annual volume is 50-200 ten thousand, or the like. The total number of the control unit types can be divided according to actual conditions. The altitude air_height i of the regulatory unit can be obtained through various ways, such as inquiring about geographical information, etc. The control mode air_ manage i can be divided into program control, radar monitoring control and other four types. The control region air_area i is measured according to the actual situation. the total number of the on-duty controllers air_num i of the ith control unit, the total number of the on-duty controllers air_num_right i of the ith control unit at night and the total number of the on-duty controllers air_num_high i of the ith control unit at peak traffic period can be acquired by collecting the unique identification of the controllers and the actual working time point of the controllers on the one hand, The individual parameters may on the other hand be obtained according to a flight schedule. The same manner can also be used to obtain the controller duty time air_time i of the ith control unit, the controller post duty time air_work_time i of the ith control unit, the controller night duty time air_light_time i of the ith control unit, the i-th control unit's controller peak traffic period station duty time air_high_time i, the controller off-station duty time air_ rwork _time i, and the controller duty time air_other_time i for other jobs of the control unit. In addition, in the application, when the aircraft hour guarantee frame quantity of the ith control unit is more than or equal to a preset flow threshold air_FT i, the ith control unit is judged to be in a peak flow period. The preset flow threshold air_ft i is set according to actual flight data of a control unit or a flight plan.
A first data processing module 12, configured to obtain an overall fatigue coefficient IoF of the all control units and/or a unit fatigue coefficient air_ IoF = [ air_ IoF 1,Air_IoF2,Air_IoF3,...,Air_IoFN ] of the all control units based on the fatigue early warning parameter air_p, where, Unit fatigue coefficient of the ith regulatory unit Air_f i1 =1, a weighting factor for the i-th regulatory unit's controller post duty duration air_work_time i, air_f i2 =0 when the i-th regulatory unit is a civil airport, otherwise, Air_f i2＝Air_fmi×Air_other_timei/Air_work_timei,Air_fmi is the weighting coefficient of other operation time of the ith control unit, and the value range is [1.00,4.00], preferably 1.80; Air_f i3 is a function of altitude air_height i for the ith regulatory unit, ranging from [0.00,8.00], preferably 4.21; in the application, when the aircraft hour guarantee frame quantity of the ith control unit is more than or equal to a preset flow threshold air_FT i, the ith control unit is judged to be in a peak flow period, and when the ith control unit is in an off-peak flow period, air_F i4 =0; Otherwise ,Air_Fi4＝Air_num_highi×Air_high_timei/Air_work_timei,Air_Fi5＝Air_num_nighti×Air_night_timei/Air_work_timei, is a function of the i-th regulatory unit night station duty time length air_light_time i; air_F i6 is a function of an ith control unit control mode air_ manage i, and the value range is [0.00,6.00]; air_F i7 is a function of the ith regulatory unit regulatory region air_area i, and the value range is [0.00,7.00]; air_f i8 is the weighting factor for the off-duty length of the ith regulatory unit, which is in the range of [0.20,1.00], preferably 0.64.
The first fatigue early-warning module 13 is configured to perform fatigue early-warning on the whole management industry according to the whole fatigue coefficient IoF, and/or perform fatigue early-warning on a control unit with a higher fatigue coefficient group in different control unit types based on the unit fatigue coefficient air_ IoF and the fatigue early-warning parameter air_p. Specifically, in one embodiment, based on the unit fatigue coefficient air_ IoF and the fatigue early warning parameter air_p, performing fatigue early warning on the control units with higher fatigue coefficients in different control unit types is as follows: and sequencing the control units of different types according to the size of the fatigue coefficient, and then performing early warning prompt on the control unit with the numerical value sequenced to the front in the control units of different types, wherein the control unit type data can be obtained from the fatigue early warning parameter air_P, and the corresponding fatigue related data can be obtained from the fatigue coefficient air_ IoF. For example, for the first class of control units, there are 4 corresponding fatigue coefficients of 200, 100, 150 and 300, and then the first class of control units are ranked according to the sizes of 300, 200, 150 and 100, and when the first two classes of control units need to be pre-warned, two control units with fatigue coefficients of 300 and 200 respectively need to be pre-warned. The first type of control unit has 4 examples for explaining the early warning mode conveniently, and does not represent the actual control unit number, and the actual first type of control unit data is based on the actual acquired number. In the application, an early warning alarm standard can be set, when the fatigue coefficient of the control unit is larger than or equal to the early warning alarm standard, the control unit is early warned, otherwise, the early warning is not needed. The early warning alarm standard can be obtained according to historical experience and can also be obtained in other modes, and the method for obtaining the early warning alarm standard is not particularly limited. In another embodiment, based on the unit fatigue coefficient air_ IoF and the fatigue early warning parameter air_p, performing fatigue early warning on the control units with higher fatigue coefficients in different control unit types is as follows: firstly, classifying all control units based on the fatigue early warning parameter air_P, secondly, sorting each type of control units according to the size of the fatigue coefficient, then, classifying each type of control units after sorting into groups with lower, middle and higher fatigue coefficients by adopting a clustering method, and finally, carrying out early warning prompt on the control units which enter the group with higher numerical value after clustering in each type of control units, and clustering the fatigue coefficients of each control unit in a clustering mode, so that the inherent distribution rule among data can be better mined. Specifically, the fatigue coefficients may be clustered using a commonly used K-mean clustering method, and the clustering method used in the present application may be any clustering method in the prior art.
Specifically, according to the integral fatigue coefficient IoF, fatigue early warning is performed on the whole of the management industry, in one embodiment, the integral fatigue coefficient IoF and the historical integral fatigue coefficient of the whole industry can be compared, when the integral fatigue coefficient IoF is larger than the historical integral fatigue coefficient, early warning is performed, in another embodiment, early warning is performed when the integral fatigue coefficient IoF is increased to a certain degree than the historical integral fatigue coefficient, and in particular, the certain degree can be combined with unsafe events in a first preset time period of the management unit to judge whether early warning is performed or not. In yet another embodiment, the early warning is performed when the overall fatigue coefficient IoF is greater than or equal to an overall fatigue coefficient early warning threshold total_alp, wherein the overall fatigue coefficient early warning threshold total_alp is obtained by performing data-driven iteration based on the overall fatigue coefficients of all the regulatory units and the number of unsafe events of all the regulatory units obtained in a plurality of different historical time periods. For example, if the overall fatigue coefficient IoF _1 of all regulatory units in the first historical period is a first value, the number of unsafe events is 0, the overall fatigue coefficient IoF _2 in the second historical period is a second value, and the number of unsafe events is 0, then although the second value IoF _2 > the first value IoF _1, the IoF _2 is not used as the overall fatigue coefficient early warning threshold total_alp because the unsafe events in the second historical period are 0, if the overall fatigue coefficient IoF _3 in the third historical period is a third value, the number of unsafe events is 2, the third value IoF _3 > the second value IoF _2, and more unsafe events occur in the third historical period, the IoF _3 can be used as the overall fatigue coefficient threshold total_alp, and so on, by combining the overall fatigue coefficient and the unsafe events in the historical periods, the overall fatigue coefficient early warning threshold total_alp can be finally obtained. And the duration of the first history time period, the second history time period and the third history time period can be one month, one week and the like, and the integral fatigue coefficient early warning threshold total_ALP can be quickly and effectively obtained by properly selecting the statistical duration.
And a second data obtaining module 21, configured to obtain a test fatigue value set_ PreIoF = [ set_ PreIoF 1,Set_PreIoF2,...,Set_PreIoFM ] within a second preset time period before the team controller of the ith control unit is on duty when the current demand meets the second fatigue determination demand, where M is the total number of people in the team controller. The length of the second preset time period may be set by itself, for example, 10 minutes, 5 minutes, 3 minutes, and the like, and preferably, in the present application, the length of the second preset time period is 5 minutes, which on one hand can ensure the detection fidelity of the controller in the test process, and on the other hand, can avoid the fake fatigue of the controller caused by the overlong test time, thereby affecting the authenticity of the test. Specifically, in the application, the test fatigue value set_ PreIoF k of the kth controller is obtained according to at least one of video test data, alertness test data and subjective scale data of the kth controller, wherein k is more than or equal to 1 and less than or equal to M. In one embodiment ,Set_PreIoFk＝Ak1×Wk+Ak2×Uk+Ak3×Vk,Ak1、Ak2、Ak3 is the specific gravity factor, A k1 is in the range of [0,3], preferably 2.4, A k2 is in the range of [4,8], preferably 6, A k3 is in the range of [2,5], preferably 3. Wherein the alertness test data V k = (vo+ve)/Vt, where Vo is the number of neglected target letters, ve is the number of selected erroneous letters, and Vt is the total number of target letters; the alertness test data U k＝t/tT, t is the correct reaction time during the alertness test, t T =500 ms, is the reaction time threshold. Video test dataWherein FPs represents a frame rate per second, tv represents a length of the video, W (l) represents a coverage of eyeballs of a person under test at the first frame, sign { } represents an indication function, wherein sign { wire } = 1, sign { false } = 0, 1+.l+.p, and p=fps×tv are frames of the video.
The second data processing module 22 is configured to calculate an early warning value set_al= [ set_al 1,Set_AL2,...,Set_ALM ] of the team controller, where set_al k＝Set_PreIoFk-Set_ALPk,Set_ALPk is a fatigue early warning threshold value of the kth controller about the to-be-attended post, and the team fatigue early warning threshold value set_alp= [ set_alp 1,Set_ALP2,...,Set_ALPM ] is obtained according to an early warning threshold value parameter in a specified time interval of the team to-be-attended time period, where the early warning threshold value parameter at least includes a duty time of the team, a predicted flight number, a predicted duty duration, a predicted weather condition, a predicted special condition, and a predicted attribute of the team controller itself.
And the second fatigue early warning module 23 is used for early warning based on the early warning value set_AL. Specifically, when set_al k≥Set_ALPk, i.e., set_al k is greater than or equal to 0, the system pre-warns the controller, and the team can timely arrange other controllers meeting the management requirements for replacement.
In one embodiment of the present invention, a method for obtaining a team fatigue early warning threshold set_alp is also disclosed, the method comprising:
S331, acquiring early warning threshold parameters in a designated time interval in a to-be-attendance time period of the group, wherein the early warning threshold parameters at least comprise the attendance time, the predicted flight quantity, the predicted attendance duration, the predicted weather condition, the predicted special condition and the predicted attribute of the controller of the group. Wherein the duration of the specified time interval is in the range of 20 minutes, 300 minutes, preferably 120 minutes, for example, the team starts working at 4 pm, then we set the specified time interval to be 4 to 6 points. The duty time may be, for example, morning, evening, etc., and the flight volume is a predicted flight volume, which may be predicted based on a flight plan of a regulatory unit, for example, a flight volume of 3 flights in a specified time zone, but temporary landings are not excluded, etc., and in this case, it is necessary to predict the flight volume of the group in the specified time zone based on the above-described flight plan and temporary factors. Likewise, the duty duration is also a predicted duty duration of the team, e.g., 1 hour, 2 hours, etc., and the controller's own attributes include, for example, fatigue status, circadian rhythm type, recent sleep status, preface duty condition, gender, age, work age, etc.
And S332, acquiring a group basic fatigue value set_P= [ set_P 1,Set_P2,...,Set_PM ] of the group according to the early warning threshold parameter, wherein set_P k represents the basic fatigue value of a kth controller of the group. Specifically, in this embodiment, the kth controller's basic fatigue value set_p k is a function of the early warning threshold parameter of the controller, for example, the duty time allocated to the team, the predicted flight volume, the predicted duty duration, the predicted weather condition, the predicted special case, and the predicted kth controller's own attribute are assigned different weight values and summed to obtain the basic fatigue value set_p k.
S333, acquiring a group fatigue early warning threshold value set_ALP= [ set_ALP 1,Set_ALP2,...,Set_ALPM ] of the group based on set_P, wherein set_ALP k＝Set_C×Set_Pk and set_C are group position adjustment coefficients with the value range of [1.0,5.0], such as position adjustment of a control seat and a coordination seat and position adjustment of different sectors of the control seat, and the adjustment coefficients express the allowable maximum internal position adjustment quantity of the group for coping with the position to be on duty. Through using group post adjustment coefficient, can make early warning standard more accords with actual conditions, and then makes early warning is more accurate, in addition, can also satisfy the group and have holistic assurance to the post of will on duty, the regulation deployment of the controller of being convenient for. Further, set_p is continuously optimized according to the early warning false report rate and the false report missing rate.
The most real fatigue degree of the team controllers can be obtained by carrying out fatigue test on the team controllers before the team, and because the team base fatigue value is obtained according to the related plan of the team to be on duty and the properties of the controllers, the actual demands of the team in the future appointed time can be reflected more objectively, the team can obtain the fatigue state of the whole team controllers more accurately and effectively by comparing the two, and the working adjustment is carried out according to the fatigue state, so that the safety risk is generated due to the fatigue of the controllers.
The third data obtaining module 31 is configured to obtain a controller integrated fatigue level value person_ IoF =person_c 1×F_pose+Person_C2×F_face+Person_C3 ×f_voice of a controller Person when the current requirement meets the third fatigue determination requirement, where f_ pose is the current controller fatigue level value based on the behavior gesture, f_face is the current controller fatigue level value based on the facial feature, f_voice is the current controller fatigue level value based on the land-air call, person_c 1 is the weight coefficient of f_ pose, person_c 2 is the weight coefficient of f_face, and person_c 3 is the weight coefficient of f_voice. The range of person_c 1 is [0.00,0.80], preferably 0.65, the range of person_c 2 is [0.00,0.40], preferably 0.20, the range of person_c 3 is [0.00,0.25], preferably 0.15, and three person_c 1、Person_C2 and person_c 3 cannot take 0.00 at the same time.
In the application, the on-duty behavior gesture information of the controller, such as the controller sleeping on duty, off duty and the like, is acquired in real time through being linked with the monitoring cameras of the control hall or the tower, the facial feature information of the controller on duty is acquired through the high-definition cameras arranged at the proper positions of the control screen, and the on-duty land and air conversation information of the controller is acquired through real-time acquisition. Specifically, analyzing and processing collected controller behavior gesture information, and analyzing dynamic data of the body and gesture of the controller to obtain a current controller fatigue degree value F_ pose based on the behavior gesture; analyzing and processing collected facial information of a controller, and analyzing the breathing, blinking, eyelid closure degree and the like of the controller to obtain a current fatigue degree value F_face of the controller based on facial features; analyzing and processing the collected controller air-ground conversation information, identifying controller voice, identifying and analyzing controller semantics, reaction time and the like to obtain the current controller fatigue degree value F_voice based on air-ground conversation. And each of f_phase, f_face and f_voice may be implemented by any method in the prior art, which is not described herein.
And a third data processing module 32, configured to calculate an early warning value person_al=person_ IoF-person_alp of the Person on the controller, where the individual fatigue early warning threshold person_alp of the Person on the controller is obtained according to an early warning threshold decision parameter in a future time region set in a post attendance time period of the Person on the controller in a post attendance, where the early warning threshold decision parameter at least includes a predicted flight number, a predicted weather condition, a predicted special condition, and a predicted attribute of the Person on the controller related to the post on the duty.
And a third fatigue early warning module 33, configured to perform early warning based on the early warning value person_al. Specifically, when person_ IoF is greater than or equal to person_ALP, the system performs early warning. Wherein person_alp= (person_a1+person_a2×person_a3) ×person_f b, person_a1 is the human circadian factor where the Person on duty time controller is located, i.e. is a function of time, for example, the factor is high during night shifts and low during white shifts; person_a2 is a post coefficient indicating the need for fatigue level for the post where the controller is located, e.g., the coefficient is small when at the controller's premises, the coefficient is large when at the coordinator's premises, the busy sector coefficient is small, and the general sector coefficient is large; person_a3 is a job task demand coefficient to indicate the need for expected flight plan traffic flow patterns to the extent of fatigue of the pipe, for example when the flow is large, the demand for the pipe is high, the coefficient is smaller, otherwise the coefficient is larger; person_f b is a duty post fatigue level base demand value, obtained from flight plans and historical experience.
In one embodiment of the present invention, a method for obtaining an individual fatigue early warning threshold person_alp of a controller is also disclosed, the method comprising:
s431, acquiring early warning threshold judging parameters in a future time region set in a post attendance time period of a controller Person in post attendance, wherein the early warning threshold judging parameters at least comprise predicted flight quantity, predicted weather conditions, predicted special conditions and predicted attribute of the controller Person, and the time length of the future time region is set to be 3 minutes and 20 minutes, preferably 5 minutes. The controller's own attributes may include, for example, factors that have an impact on controller fatigue, such as fatigue status, circadian rhythm type, recent sleep conditions, preface conditions, gender, age, work age, and the like.
S432, acquiring a duty post fatigue degree basic requirement value person_F b of the controller according to the early warning threshold judging parameter. Specifically, in this embodiment, the duty post fatigue level basic requirement value person_f b is a function of the early warning threshold decision parameter of the controller, for example, the predicted flight number, the predicted weather condition, the predicted special condition, and the predicted attribute of the Person son of the controller are respectively given different weight values and summed to obtain the final product.
S433, acquiring an individual fatigue early warning threshold value person_ALP= (person_A1+person_A2×person_A3) ×person_F b of the controller according to the person_F b of the duty fatigue degree basic requirement value, wherein person_A1 is a human circadian rhythm coefficient of an individual on duty time controller, namely a function related to time, such as high coefficient during night shift and low coefficient during white shift; person_a2 is a post coefficient indicating the need for fatigue level for the post where the controller is located, e.g., the coefficient is small when at the controller's premises, the coefficient is large when at the coordinator's premises, the busy sector coefficient is small, and the general sector coefficient is large; person_a3 is a job demand coefficient that indicates the need for the expected flight plan traffic flow pattern to be tiring for the controller, for example when the flow is high, the demand for the controller is high, and the coefficient is small, otherwise the coefficient is large. Further, the person_alp is continuously optimized according to the early warning false report rate and the false report rate.
The working state of the controller on the post can be truly and accurately calculated through collecting real-time data of the on-post personnel and acquiring the judgment threshold according to parameters in the appointed time in the future of the duty post, the real-time state of the controller is supervised, whether the current fatigue state of the controller can meet the safety fatigue requirement in the appointed time in the future is judged, and when the controller is judged to be unable to meet the safety fatigue requirement, alarming is timely carried out and personnel replacement is carried out, so that the safety risk caused by the fatigue of the controller under the condition of the post can be effectively avoided.
In summary, by acquiring fatigue early warning parameters within a preset time period of all control units, fatigue coefficients of the whole control industry and even all control units are acquired, and fatigue monitoring and early warning are performed on the whole control industry and control units with higher fatigue coefficients based on the fatigue coefficients. In addition, by comparing the team fatigue degree obtained by the pre-post fatigue test with a team early warning threshold obtained by predicting the post fatigue requirement of the post to be attended by the team, and by comparing the personal fatigue degree of the controller obtained by fatigue monitoring in the post with the individual fatigue warning threshold of the controller obtained by predicting the post on duty fatigue requirement of the controller in a period of time in the future, whether the management personnel can cope with the working requirement of the post to be attended can be detected before the post, and whether fatigue abnormality occurs in the post personnel in the future for 3-20 minutes can be judged even after the management personnel is on duty, namely whether the management personnel can cope with the future aviation safety requirement from multiple angles is predicted. The fatigue detection, future post fatigue demand prediction and fatigue early warning on the whole industry, independent control units, teams and controller individuals are realized in the control unit organization level strategy stage, the team level pre-tactic (pre-post) stage and the individual level tactic (on-post) stage respectively, so that fatigue risk management and control on different demands from multiple directions are facilitated, and aviation safety is guaranteed.
In another embodiment of the present application, a flowchart of a method for early warning fatigue of a controller is disclosed, as shown in fig. 5, and the related matters as described above are also applicable to this embodiment, which is not repeated here. The method comprises the following steps:
S100, judging whether the current requirement meets the first fatigue judgment requirement, the second fatigue judgment requirement or the third fatigue judgment requirement; when the current demand meets the first fatigue determination demand, step S210 is executed, when the current demand meets the second fatigue determination demand, step S310 is executed, otherwise step S410 is executed.
S210, acquiring fatigue early warning parameters air_P= (air_P 1,Air_P2,Air_P3,...,Air_PN) of all control units in a first preset time period, wherein N is the number of all control units, and the fatigue early warning parameters air_P i of the ith control unit at least comprise unit types air_type i, Altitude Air height i, control mode Air manage i, control area Air area i, total number of duty controllers Air num i, the total number of controllers air_num_light i on duty at night, the total number of controllers air_num_high i on duty at peak traffic, the duration of the controller duty air_time i, Controller post attendance time air_work_time i, controller night post attendance time air_light_time i, controller peak flow period post attendance time air_high_time i, The non-station duty time length air_ rwork _time i of the controller and the duty time length air_other_time i of the controller of other jobs are equal to or more than 1 and equal to or less than N.
S220, acquiring the integral fatigue coefficient IoF of all control units and/or the unit fatigue coefficient air_ IoF = [ air_ IoF 1,Air_IoF2,Air_IoF3,...,Air_IoFN ] of all control units based on the fatigue early warning parameter air_P, wherein, Unit fatigue coefficient of the ith regulatory unitAir_f i1 =1, which is a weighting coefficient of the air_work_time i of the duty time of the controller post of the ith control unit, when the ith control unit is a civil airport, air_f i2 =0, otherwise, air_f i2＝Air_fmi×Air_other_timei/Air_work_timei,Air_fmi is a weighting coefficient of other working time of the ith control unit, air_f i3 is a function of altitude air_height i of the ith control unit, when the aircraft guarantee frame number of the ith control unit is greater than or equal to a preset flow threshold air_ft i, the ith control unit is determined to be in a peak flow period, and when the ith control unit is in a non-peak flow period, air_f i4 =0; otherwise ,Air_Fi4＝Air_num_highi×Air_high_timei/Air_work_timei,Air_Fi5＝Air_num_nighti×Air_night_timei/Air_work_timei, is a function of the i-th regulatory unit night station duty time length air_light_time i; air_f i6 is a function of air_ manage i for the ith regulatory unit regulatory mode, air_f i7 is a function of air_area i for the ith regulatory unit regulatory region, and air_f i8 is a weighting factor for the off-duty duration of the ith regulatory unit.
S230, acquiring an overall fatigue coefficient early warning threshold value total_ALP of all control units, classifying all control units based on the fatigue early warning parameter air_P, sorting the control units of each type according to the fatigue coefficient according to the unit fatigue coefficient air_ IoF, and grading the sorted control units of each type into lower, middle and higher groups of fatigue coefficients by adopting a clustering method, wherein the overall fatigue coefficient early warning threshold value total_ALP is acquired by carrying out data driving iteration based on the overall fatigue coefficients of all control units and the unsafe event quantity of all control units acquired in a plurality of different historical time periods.
And S240, obtaining fatigue early-warning values total_AL=the overall fatigue coefficients IoF-overall fatigue coefficient early-warning threshold total_ALP of all the control units.
S250, performing fatigue early warning on the whole management industry based on the fatigue early warning values total_AL of all the control units, namely performing early warning when the fatigue early warning values total_AL of all the control units are more than or equal to 0, and/or performing early warning on the control units which enter a group with higher values after clustering in each type of control unit.
S310, acquiring a test fatigue parameter of a team controller of an ith control unit in a second preset time period before the guard, wherein the test fatigue parameter is at least acquired through one of a video test, an alertness test and a subjective scale test; and acquiring early warning threshold parameters in a designated time interval in a to-be-attendance time period of the group, wherein the early warning threshold parameters at least comprise the attendance time of the group, the predicted flight quantity, the predicted attendance duration, the predicted weather condition, the predicted special condition and the predicted attribute of the controller.
S320, obtaining a test fatigue value set_ PreIoF = [ set_ PreIoF 1,Set_PreIoF2,...,Set_PreIoFM ] of the team controllers according to the test fatigue parameters, wherein M is the total number of the team controllers; and acquiring a group basic fatigue value set_p= [ set_p 1,Set_P2,...,Set_PM ] of the group according to the early warning threshold parameter, wherein set_p k represents the basic fatigue value of a kth controller of the group.
S330, acquiring a group fatigue early warning threshold set_ALP= [ set_ALP 1,Set_ALP2,...,Set_ALPM ] of the group based on the group base fatigue value set_P. Wherein, the kth controller is the team post adjustment factor with respect to the fatigue warning threshold set_ALP k＝Set_C×Set_Pk for the to-be-attended post.
S340, calculating an early warning value set_AL= [ set_AL 1,Set_AL2,...,Set_ALM ] of the team controller according to the team fatigue early warning threshold set_ALP and the test fatigue value set_ PreIoF, wherein set_AL k＝Set_PreIoFk-Set_ALPk.
S350, early warning is carried out based on the early warning value set_AL, namely early warning is carried out when set_AL k is more than or equal to 0.
S410, obtaining fatigue degree parameters F_post, F_face and F_voice of a controller Person, wherein F_ pose is a current fatigue degree value of the controller based on the behavior gesture, F_face is a current fatigue degree value of the controller based on the facial feature, F_voice is a current fatigue degree value of the controller based on the land-air conversation, and obtaining early warning threshold judging parameters in a future time zone set in a post duty time period of the controller Person in a post duty, wherein the early warning threshold judging parameters at least comprise a predicted flight number, a predicted weather condition, a predicted special condition and a predicted attribute of the controller Person.
S420, obtaining a controller comprehensive fatigue degree value Person_IoF＝Person_C1×F_pose+Person_C2×F_face+Person_C3×F_voice;Person_C1 of a controller Person, wherein the controller comprehensive fatigue degree value Person_IoF＝Person_C1×F_pose+Person_C2×F_face+Person_C3×F_voice;Person_C1 is a weight coefficient of F_ pose, person_C 2 is a weight coefficient of F_face, and person_C 3 is a weight coefficient of F_voice; and acquiring a duty post fatigue degree basic requirement value person_F b of the controller according to the early warning threshold judgment parameter.
S430, acquiring an individual fatigue early warning threshold value person_ALP= (person_A1+person_A2×person_A3) ×person_F b of the controller according to the person_F b of the duty fatigue degree basic requirement value, wherein person_A1 is a human circadian rhythm coefficient of an individual on duty time controller, namely a function related to time, such as high coefficient during night shift and low coefficient during white shift; person_a2 is a post coefficient indicating the need for fatigue level for the post where the controller is located, e.g., the coefficient is small when at the controller's premises, the coefficient is large when at the coordinator's premises, the busy sector coefficient is small, and the general sector coefficient is large; person_a3 is a job demand coefficient that indicates the need for the expected flight plan traffic flow pattern to be tiring for the controller, for example when the flow is high, the demand for the controller is high, and the coefficient is small, otherwise the coefficient is large.
S440, calculating a pre-warning value person_al=person_ IoF-person_alp of the controller Person.
S450, early warning is carried out based on the early warning value person_AL. When person_AL is more than or equal to 0, early warning is carried out.
A controller fatigue early warning system comprising a processor and a non-transitory storage medium storing at least one instruction or at least one program loaded and executed by the processor to implement the fatigue early warning method provided by the above embodiments.
Embodiments of the present application also provide a non-transitory computer readable storage medium that may be disposed in an electronic device to store at least one instruction or at least one program for implementing one of the methods embodiments, the at least one instruction or the at least one program being loaded and executed by the processor to implement the methods provided by the embodiments described above.
Embodiments of the present application also provide an electronic device comprising a processor and the aforementioned non-transitory computer-readable storage medium.
Embodiments of the present application also provide a computer program product comprising program code for causing an electronic device to carry out the steps of the method according to the various exemplary embodiments of the application as described in the specification, when said program product is run on the electronic device.
While certain specific embodiments of the application have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the application. Those skilled in the art will also appreciate that many modifications may be made to the embodiments without departing from the scope and spirit of the application. The scope of the application is defined by the appended claims.

Claims (13)

1. A method for early warning of fatigue of a pipe, the method comprising the steps of:
s100, judging whether the current requirement meets the first fatigue judgment requirement, the second fatigue judgment requirement or the third fatigue judgment requirement; when the current demand meets the first fatigue determination demand, executing step S210, when the current demand meets the second fatigue determination demand, executing step S310, otherwise executing step S410;
S210, acquiring fatigue early warning parameters air_P= (air_P 1,Air_P2,Air_P3,...,Air_PN) of all control units in a first preset time period, wherein N is the number of all control units, and the fatigue early warning parameters air_P i of the ith control unit at least comprise unit types air_type i, Altitude Air height i, control mode Air manage i, control area Air area i, total number of duty controllers Air num i, the total number of controllers air_num_light i on duty at night, the total number of controllers air_num_high i on duty at peak traffic, the duration of the controller duty air_time i, Controller post attendance time air_work_time i, controller night post attendance time air_light_time i, controller peak flow period post attendance time air_high_time i, The non-station duty time length air_ rwork _time i of the controller and the duty time length air_other_time i of the controller of other jobs are equal to or more than 1 and equal to or less than N;
s220, acquiring the integral fatigue coefficient IoF of all control units and/or the unit fatigue coefficient air_ IoF = [ air_ IoF 1,Air_IoF2,Air_IoF3,...,Air_IoFN ] of all control units based on the fatigue early warning parameter air_P, wherein, Unit fatigue coefficient of the ith regulatory unit The method comprises the steps that a weighting coefficient of a duty time air_work_time i of a post of a controller of an ith control unit is that when the ith control unit is a civil airport, air_F i2 =0, otherwise, air_F i2＝Air_fmi×Air_other_timei/Air_work_timei,Air_fmi is a weighting coefficient of other working time of the ith control unit, air_F i3 is a function of altitude air_height i of the ith control unit, when the aircraft guarantee frame quantity of the ith control unit is more than or equal to a preset flow threshold air_FT i, the ith control unit is judged to be in a peak flow period, and when the ith control unit is in an off-peak flow period, air_F i4 =0; otherwise ,Air_Fi4＝Air_num_highi×Air_high_timei/Air_work_timei,Air_Fi5＝Air_num_nighti×Air_night_timei/Air_work_timei, is a function of the i-th regulatory unit night duty time air_light_time i, air_f i6 is a function of the i-th regulatory unit regulatory mode air_ manage i, air_f i7 is a function of the i-th regulatory unit regulatory region air_area i, and air_f i8 is a weighting factor of the i-th regulatory unit non-duty time;
S230, performing fatigue early warning on the whole management industry according to the whole fatigue coefficient IoF, and/or performing fatigue early warning on a control unit with a higher fatigue coefficient group in different control unit types based on the unit fatigue coefficient air_ IoF and the fatigue early warning parameter air_P;
S310, obtaining a test fatigue value set_ PreIoF = [ set_ PreIoF 1,Set_PreIoF2,...,Set_PreIoFM ] of a group controller of an ith control unit in a second preset time period before the guard, wherein M is the total number of people of the group controller, and the test fatigue value set_ PreIoF k of the kth controller is obtained according to at least one of video test data, alertness test data and subjective scale data of the kth controller, wherein k is more than or equal to 1 and less than or equal to M;
S320, calculating an early warning value set_AL= [ set_AL 1,Set_AL2,...,Set_ALM ] of the team controller, and carrying out early warning based on the early warning value set_AL, wherein set_AL k＝Set_PreIoFk-Set_ALPk,Set_ALPk is a fatigue early warning threshold value of the kth controller about a duty to be performed, and the team fatigue early warning threshold value set_ALP= [ set_ALP 1,Set_ALP2,...,Set_ALPM ] is obtained according to early warning threshold value parameters in a time interval specified in a duty time period of the team, wherein the early warning threshold value parameters at least comprise duty time of the team, predicted flight volume, predicted duty duration, predicted weather condition, predicted special conditions and predicted controller own attributes;
S410, obtaining a controller comprehensive fatigue degree value person_ IoF =person_C 1×F_pose+Person_C2×F_face+Person_C3 ×F_voice of a controller Person, wherein F_ pose is a controller fatigue degree value based on a behavior gesture currently, F_face is a controller fatigue degree value based on facial features currently, F_voice is a controller fatigue degree value based on a land-air call currently, person_C 1 is a weight coefficient of F_ pose, person_C 2 is a weight coefficient of F_face, and person_C 3 is a weight coefficient of F_voice;
S420, calculating an early warning value person_AL=person_ IoF-person_ALP of the Person on the controller, and carrying out early warning based on the early warning value person_AL, wherein the individual fatigue early warning threshold person_ALP of the controller is obtained according to early warning threshold judging parameters in a future time zone set in a post duty time period of the Person on the controller in post duty, and the early warning threshold judging parameters at least comprise predicted flight quantity, predicted weather conditions, predicted special conditions and predicted Person attributes of the Person on the controller related to the post in duty;
Based on the unit fatigue coefficient air_ IoF and the fatigue early warning parameter air_p, performing fatigue early warning on the control units with higher fatigue coefficients in different control unit types, wherein the fatigue early warning is performed by the following steps: firstly, classifying all control units based on the fatigue early warning parameter air_P, secondly, sorting each type of control units according to the size of the fatigue coefficient, then, classifying each type of control units after sorting into groups with lower fatigue coefficient, middle and higher fatigue coefficient by adopting a clustering method, and finally, carrying out early warning prompt on the control units entering the group with higher numerical value after clustering in each type of control units;
the fatigue early warning of the whole management industry according to the whole fatigue coefficient IoF comprises the following steps: when the integral fatigue coefficient IoF is more than or equal to an integral fatigue coefficient early warning threshold total_ALP, early warning is carried out, wherein the integral fatigue coefficient early warning threshold total_ALP is obtained by carrying out data driving iteration based on integral fatigue coefficients of all control units and the number of unsafe events of all control units which are obtained in a plurality of different historical time periods;
The group fatigue early warning threshold set_ALP acquisition comprises the following steps:
S331, acquiring early warning threshold parameters in a designated time interval of a to-be-attendance time period of the group, wherein the early warning threshold parameters at least comprise the attendance time of the group, the predicted flight quantity, the predicted attendance duration, the predicted special conditions, the predicted weather conditions and the predicted controller own attributes, and the duration of the designated time interval is in a value range of [20 minutes, 300 minutes ];
s332, obtaining a group basic fatigue value set_P= [ set_P 1,Set_P2,...,Set_PM ] of the group according to the early warning threshold parameter, wherein set_P k represents a basic fatigue value of a kth controller of the group;
S333, acquiring a group fatigue early warning threshold value set_ALP= [ set_ALP 1,Set_ALP2,...,Set_ALPM ] of the group based on set_P, wherein set_ALP k＝Set_C×Set_Pk and set_C are group post adjustment coefficients;
the acquisition of the individual fatigue early warning threshold person_alp of the controller comprises the following steps:
S431, acquiring early warning threshold judging parameters in a future time region set in a post attendance time period of a controller Person in post attendance, wherein the early warning threshold judging parameters at least comprise predicted flight quantity, predicted weather conditions, predicted special conditions and predicted attribute of the controller Person, and the duration value range of the future time region is set to be [3 minutes, 20 minutes ];
s432, acquiring a person_F b of a basic requirement value of the duty post fatigue degree of the controller according to the early warning threshold judging parameter;
S433, acquiring an individual fatigue early warning threshold value person_ALP= (person_A1+person_A2×person_A3) ×person_F b of the controller according to the person_F b of the basic requirement value of the duty post fatigue degree, wherein person_A1 is a human circadian rhythm coefficient of an individual on duty time controller, and person_A2 is a post coefficient for indicating the requirement of the duty post of the controller for the fatigue degree; person_a3 is a post mission requirement factor that indicates the need for the expected flight plan traffic flow pattern to be tiring for the controller.
2. The method of claim 1, wherein air_f i3 has a value in the range of [0.00,8.00]; the value range of air_F i6 is [0.00,6.00]; the value range of air_F i7 is [0.00,7.00], and the value range of air_F i8 is [0.20,1.00].
3. A method for obtaining a team fatigue early warning threshold set_alp based on the method of claim 1, comprising the steps of:
S331, acquiring an early warning threshold parameter in a specified time interval in a to-be-attended time period of the group, wherein the early warning threshold parameter at least comprises the attendance time, the predicted flight quantity, the predicted attendance duration, the predicted weather condition, the predicted special condition and the predicted attribute of a controller of the group, and the duration of the specified time interval is in a value range of [20 minutes, 300 minutes ];
s332, obtaining a group basic fatigue value set_P= [ set_P 1,Set_P2,...,Set_PM ] of the group according to the early warning threshold parameter, wherein set_P k represents a basic fatigue value of a kth controller of the group;
S333, a group fatigue early warning threshold set_alp= [ set_alp 1,Set_ALP2,...,Set_ALPM ] of the group is obtained based on set_p, where set_alp k＝Set_C×Set_Pk and set_c is a group post adjustment coefficient.
4. A method of obtaining an individual fatigue early warning threshold person_alp for a controller based on the method of claim 1, comprising the steps of:
S431, acquiring early warning threshold judging parameters in a future time region set in a post attendance time period of a controller Person in post attendance, wherein the early warning threshold judging parameters at least comprise predicted flight quantity, predicted weather conditions, predicted special conditions and predicted attribute of the controller Person, and the duration value range of the future time region is set to be [3 minutes, 20 minutes ];
s432, acquiring a person_F b of a basic requirement value of the duty post fatigue degree of the controller according to the early warning threshold judging parameter;
S433, acquiring an individual fatigue early warning threshold value person_ALP= (person_A1+person_A2×person_A3) ×person_F b of the controller according to the person_F b of the basic requirement value of the duty post fatigue degree, wherein person_A1 is a human circadian rhythm coefficient of an individual on duty time controller, and person_A2 is a post coefficient for indicating the requirement of the duty post of the controller for the fatigue degree; person_a3 is a post mission requirement factor that indicates the need for the expected flight plan traffic flow pattern to be tiring for the controller.
5. A method for acquiring an overall fatigue coefficient early warning threshold total_alp based on the method of claim 1, comprising the steps of:
s231, acquiring the integral fatigue coefficients and the number of unsafe events of all control units in a plurality of different historical time periods;
S232, carrying out data driving iteration by utilizing the integral fatigue coefficients and the number of unsafe events in the plurality of different historical time periods to obtain the integral fatigue coefficient early warning threshold total_ALP.
6. A method for obtaining the overall fatigue coefficient of all regulatory units and the unit fatigue coefficients of each unit based on the method of claim 1, comprising the steps of:
S210, acquiring fatigue early warning parameters air_P= (air_P 1,Air_P2,Air_P3,...,Air_PN) of all control units in a first preset time period, wherein N is the number of all control units, and the fatigue early warning parameters air_P i of the ith control unit at least comprise unit types air_type i, Altitude Air height i, control mode Air manage i, control area Air area i, total number of duty controllers Air num i, the total number of controllers air_num_light i on duty at night, the total number of controllers air_num_high i on duty at peak traffic, the duration of the controller duty air_time i, Controller post attendance time air_work_time i, controller night post attendance time air_light_time i, controller peak flow period post attendance time air_high_time i, The non-station duty time length air_ rwork _time i of the controller and the duty time length air_other_time i of the controller of other jobs are equal to or more than 1 and equal to or less than N;
s220, acquiring the integral fatigue coefficient IoF of all control units and/or the unit fatigue coefficient air_ IoF = [ air_ IoF 1,Air_IoF2,Air_IoF3,...,Air_IoFN ] of all control units based on the fatigue early warning parameter air_P, wherein, Unit fatigue coefficient of the ith regulatory unit The method comprises the steps that a weighting coefficient of a duty time air_work_time i of a post of a controller of an ith control unit is that when the ith control unit is a civil airport, air_F i2 =0, otherwise, air_F i2＝Air_fmi×Air_other_timei/Air_work_timei,Air_fmi is a weighting coefficient of other working time of the ith control unit, air_F i3 is a function of altitude air_height i of the ith control unit, when the aircraft guarantee frame quantity of the ith control unit is more than or equal to a preset flow threshold air_FT i, the ith control unit is judged to be in a peak flow period, and when the ith control unit is in an off-peak flow period, air_F i4 =0; otherwise ,Air_Fi4＝Air_num_highi×Air_high_timei/Air_work_timei,Air_Fi5＝Air_num_nighti×Air_night_timei/Air_work_timei, is a function of the i-th regulatory unit night duty time air_light_time i, air_f i6 is a function of the i-th regulatory unit regulatory mode air_ manage i, air_f i7 is a function of the i-th regulatory unit regulatory region air_area i, and air_f i8 is a weighting factor for the non-duty time of the i-th regulatory unit.
7. A controller fatigue warning device, the device comprising:
A first data obtaining module, configured to obtain, when a current requirement meets a first fatigue determination requirement, a fatigue early-warning parameter air_p= (air_p 1,Air_P2,Air_P3,...,Air_PN) of all control units in a first preset time period, where N is a number of the all control units, where the fatigue early-warning parameter air_p i of the ith control unit at least includes a unit type air_type i, Altitude Air height i, control mode Air manage i, control area Air area i, total number of duty controllers Air num i, the total number of controllers air_num_light i on duty at night, the total number of controllers air_num_high i on duty at peak traffic, the duration of the controller duty air_time i, Controller post attendance time air_work_time i, controller night post attendance time air_light_time i, controller peak flow period post attendance time air_high_time i, The non-station duty time length air_ rwork _time i of the controller and the duty time length air_other_time i of the controller of other jobs are equal to or more than 1 and equal to or less than N;
A first data processing module, configured to obtain an overall fatigue coefficient IoF of the all control units and/or a unit fatigue coefficient air_ IoF = [ air_ IoF 1,Air_IoF2,Air_IoF3,...,Air_IoFN ] of the all control units based on the fatigue early warning parameter air_p, Unit fatigue coefficient of the ith regulatory unit Air_f i1 =1, which is a weighting coefficient of the air_work_time i of the duty time of the controller post of the ith control unit, when the ith control unit is a civil airport, air_f i2 =0, otherwise, air_f i2＝Air_fmi×Air_other_timei/Air_work_timei,Air_fmi is a weighting coefficient of other working time of the ith control unit, air_f i3 is a function of altitude air_height i of the ith control unit, when the aircraft guarantee frame number of the ith control unit is greater than or equal to a preset flow threshold air_ft i, the ith control unit is determined to be in a peak flow period, and when the ith control unit is in a non-peak flow period, air_f i4 =0; otherwise ,Air_Fi4＝Air_num_highi×Air_high_timei/Air_work_timei,Air_Fi5＝Air_num_nighti×Air_night_timei/Air_work_timei, is a function of the i-th regulatory unit night station duty time length air_light_time i; air_f i6 is a function of an i-th regulatory unit regulatory mode air_ manage i, air_f i7 is a function of an i-th regulatory unit regulatory region air_area i, and air_f i8 is a weighting coefficient of the off-duty duration of the i-th regulatory unit;
The first fatigue early warning module is used for carrying out fatigue early warning on the whole management industry according to the whole fatigue coefficient IoF and/or carrying out fatigue early warning on the control units with higher fatigue coefficients in different control unit types based on the unit fatigue coefficient air_ IoF and the fatigue early warning parameter air_P;
The second data acquisition module is used for acquiring a test fatigue value set_ PreIoF = [ set_ PreIoF 1,Set_PreIoF2,...,Set_PreIoFM ] of a group controller of an ith control unit in a second preset time period before the guard when the current demand meets the second fatigue judgment demand, wherein M is the total number of the group controller, and the test fatigue value set_ PreIoF k of the kth controller is acquired according to at least one of video test data, alertness test data and subjective scale data of the kth controller, and k is more than or equal to 1 and less than or equal to M;
The second data processing module is used for calculating an early warning value set_al= [ set_al 1,Set_AL2,...,Set_ALM ] of the team controllers, wherein set_al k＝Set_PreIoFk-Set_ALPk,Set_ALPk is a fatigue early warning threshold value of the kth controller about a duty to be performed, and the team fatigue early warning threshold value set_alp= [ set_alp 1,Set_ALP2,...,Set_ALPM ] is obtained according to early warning threshold value parameters in a designated time interval in the team duty time period, and the early warning threshold value parameters at least comprise the duty time of the team, the predicted flight volume, the predicted duty time, the predicted weather condition, the predicted special condition and the predicted controller own attribute;
the second fatigue early warning module is used for early warning based on the early warning value set_AL;
The third data obtaining module is configured to obtain a controller integrated fatigue level value person_ IoF =person_c 1×F_pose+Person_C2×F_face+Person_C3 ×f_voice of a controller Person when the current requirement meets the third fatigue determination requirement, where f_ pose is a controller fatigue level value based on a behavior gesture, f_face is a controller fatigue level value based on a facial feature, f_voice is a controller fatigue level value based on a land-air call, person_c 1 is a weight coefficient of f_ pose, person_c 2 is a weight coefficient of f_face, and person_c 3 is a weight coefficient of f_voice;
the third data processing module is used for calculating an early warning value person_al=person_ IoF-person_alp of the Person of the controller, wherein the individual early warning threshold person_alp of the controller is obtained according to early warning threshold judging parameters in a future time zone set in a post duty time period of the Person of the controller in post duty, and the early warning threshold judging parameters at least comprise predicted flight quantity, predicted weather conditions, predicted special conditions and predicted Person attributes of the controller related to the post in duty;
the third fatigue early warning module is used for early warning based on the early warning value person_AL;
Based on the unit fatigue coefficient air_ IoF and the fatigue early warning parameter air_p, performing fatigue early warning on the control units with higher fatigue coefficients in different control unit types, wherein the fatigue early warning is performed by the following steps: firstly, classifying all control units based on the fatigue early warning parameter air_P, secondly, sorting each type of control units according to the size of the fatigue coefficient, then, classifying each type of control units after sorting into groups with lower fatigue coefficient, middle and higher fatigue coefficient by adopting a clustering method, and finally, carrying out early warning prompt on the control units entering the group with higher numerical value after clustering in each type of control units;
the fatigue early warning of the whole management industry according to the whole fatigue coefficient IoF comprises the following steps: when the integral fatigue coefficient IoF is more than or equal to an integral fatigue coefficient early warning threshold total_ALP, early warning is carried out, wherein the integral fatigue coefficient early warning threshold total_ALP is obtained by carrying out data driving iteration based on integral fatigue coefficients of all control units and the number of unsafe events of all control units which are obtained in a plurality of different historical time periods;
The group fatigue early warning threshold set_ALP acquisition comprises the following steps:
S331, acquiring early warning threshold parameters in a designated time interval of a to-be-attendance time period of the group, wherein the early warning threshold parameters at least comprise the attendance time of the group, the predicted flight quantity, the predicted attendance duration, the predicted special conditions, the predicted weather conditions and the predicted controller own attributes, and the duration of the designated time interval is in a value range of [20 minutes, 300 minutes ];
s332, obtaining a group basic fatigue value set_P= [ set_P 1,Set_P2,...,Set_PM ] of the group according to the early warning threshold parameter, wherein set_P k represents a basic fatigue value of a kth controller of the group;
S333, acquiring a group fatigue early warning threshold value set_ALP= [ set_ALP 1,Set_ALP2,...,Set_ALPM ] of the group based on set_P, wherein set_ALP k＝Set_C×Set_Pk and set_C are group post adjustment coefficients;
the acquisition of the individual fatigue early warning threshold person_alp of the controller comprises the following steps:
S431, acquiring early warning threshold judging parameters in a future time region set in a post attendance time period of a controller Person in post attendance, wherein the early warning threshold judging parameters at least comprise predicted flight quantity, predicted weather conditions, predicted special conditions and predicted attribute of the controller Person, and the duration value range of the future time region is set to be [3 minutes, 20 minutes ];
s432, acquiring a person_F b of a basic requirement value of the duty post fatigue degree of the controller according to the early warning threshold judging parameter;
S433, acquiring an individual fatigue early warning threshold value person_ALP= (person_A1+person_A2×person_A3) ×person_F b of the controller according to the person_F b of the basic requirement value of the duty post fatigue degree, wherein person_A1 is a human circadian rhythm coefficient of an individual on duty time controller, and person_A2 is a post coefficient for indicating the requirement of the duty post of the controller for the fatigue degree; person_a3 is a post mission requirement factor that indicates the need for the expected flight plan traffic flow pattern to be tiring for the controller.
8. The apparatus of claim 7 wherein air_f i3 has a value in the range of [0.00,8.00]; the value range of air_F i6 is [0.00,6.00]; the value range of air_F i7 is [0.00,7.00], and the value range of air_F i8 is [0.20,1.00].
9. The apparatus of claim 7 or 8, wherein based on the unit fatigue coefficient air_ IoF and the fatigue warning parameter air_p, performing fatigue warning on a higher group of regulatory units of different regulatory unit types is: firstly, classifying all control units based on the fatigue early warning parameter air_P, secondly, sorting each type of control units according to the size of the fatigue coefficient, then, classifying each type of sorted control units into groups with lower fatigue coefficient, middle and higher fatigue coefficient by adopting a clustering method, and finally, carrying out early warning prompt on the control units which enter the group with higher numerical value after clustering in each type of control units.
10. The apparatus of claim 7, wherein fatigue pre-warning the management industry as a whole based on the overall fatigue coefficient IoF comprises: and when the integral fatigue coefficient IoF is more than or equal to the integral fatigue coefficient early warning threshold total_ALP, early warning is carried out, wherein the integral fatigue coefficient early warning threshold total_ALP is obtained by carrying out data driving iteration based on the integral fatigue coefficients of all control units and the number of unsafe events of all control units which are obtained in a plurality of different historical time periods.
11. The apparatus of claim 7, wherein the acquisition of the team fatigue early warning threshold Set ALP comprises the steps of:
S331, acquiring an early warning threshold parameter in a specified time interval in a to-be-attended time period of the group, wherein the early warning threshold parameter at least comprises the attendance time, the predicted flight quantity, the predicted attendance duration, the predicted weather condition, the predicted special condition and the predicted attribute of a controller of the group, and the duration of the specified time interval is in a value range of [20 minutes, 300 minutes ];
s332, obtaining a group basic fatigue value set_P= [ set_P 1,Set_P2,...,Set_PM ] of the group according to the early warning threshold parameter, wherein set_P k represents a basic fatigue value of a kth controller of the group;
S333, a group fatigue early warning threshold set_alp= [ set_alp 1,Set_ALP2,...,Set_ALPM ] of the group is obtained based on set_p, where set_alp k＝Set_C×Set_Pk and set_c is a group post adjustment coefficient.
12. The apparatus of claim 7, wherein the acquisition of the individual fatigue early warning threshold person_alp for the controller comprises the steps of:
S431, acquiring early warning threshold judging parameters in a future time region set in a post attendance time period of a controller Person in post attendance, wherein the early warning threshold judging parameters at least comprise predicted flight quantity, predicted weather conditions, predicted special conditions and predicted attribute of the controller Person, and the duration value range of the future time region is set to be [3 minutes, 20 minutes ];
s432, acquiring a person_F b of a basic requirement value of the duty post fatigue degree of the controller according to the early warning threshold judging parameter;
S433, acquiring an individual fatigue early warning threshold value person_ALP= (person_A1+person_A2×person_A3) ×person_F b of the controller according to the person_F b of the basic requirement value of the duty post fatigue degree, wherein person_A1 is a human circadian rhythm coefficient of an individual on duty time controller, and person_A2 is a post coefficient for indicating the requirement of the duty post of the controller for the fatigue degree; person_a3 is a post mission requirement factor that indicates the need for the expected flight plan traffic flow pattern to be tiring for the controller.
13. A controller fatigue warning system comprising a processor and a non-transitory storage medium storing at least one instruction or at least one program, wherein the at least one instruction or the at least one program is loaded and executed by the processor to implement the method of any one of claims 1-6.
CN202210351997.XA 2022-04-02 2022-04-02 Fatigue early warning method, device and system for controller and early warning threshold acquisition method Active CN114638538B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210351997.XA CN114638538B (en) 2022-04-02 2022-04-02 Fatigue early warning method, device and system for controller and early warning threshold acquisition method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210351997.XA CN114638538B (en) 2022-04-02 2022-04-02 Fatigue early warning method, device and system for controller and early warning threshold acquisition method

Publications (2)

Publication Number Publication Date
CN114638538A CN114638538A (en) 2022-06-17
CN114638538B true CN114638538B (en) 2024-08-06

Family

ID=81951128

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210351997.XA Active CN114638538B (en) 2022-04-02 2022-04-02 Fatigue early warning method, device and system for controller and early warning threshold acquisition method

Country Status (1)

Country Link
CN (1) CN114638538B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105282502A (en) * 2015-09-30 2016-01-27 中国民用航空总局第二研究所 Air-traffic controller fatigue detection method, device and system based on confidence interval
CN106580349A (en) * 2016-12-07 2017-04-26 中国民用航空总局第二研究所 Controller fatigue detection method and device and controller fatigue responding method and device

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109214693B (en) * 2018-02-13 2021-11-12 中国民用航空总局第二研究所 Method, system, medium and equipment for evaluating fatigue risk of air traffic controller
CN108446673A (en) * 2018-04-27 2018-08-24 南京航空航天大学 A kind of controller's giving fatigue pre-warning method based on face recognition
CN113327404A (en) * 2021-05-13 2021-08-31 安徽中科昊音智能科技有限公司 Post fatigue state monitoring and warning system for air traffic controller
CN113243917B (en) * 2021-05-18 2023-05-12 中国民用航空总局第二研究所 Fatigue detection method and device for civil aviation controller, electronic equipment and medium

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105282502A (en) * 2015-09-30 2016-01-27 中国民用航空总局第二研究所 Air-traffic controller fatigue detection method, device and system based on confidence interval
CN106580349A (en) * 2016-12-07 2017-04-26 中国民用航空总局第二研究所 Controller fatigue detection method and device and controller fatigue responding method and device

Also Published As

Publication number Publication date
CN114638538A (en) 2022-06-17

Similar Documents

Publication Publication Date Title
CN112884325B (en) Application analysis and health condition evaluation method and system for guest station equipment
US8812428B2 (en) Systems and methods for assessment of fatigue-related contextual performance using historical incident data
CN116012208A (en) Risk area early warning information generation method for smart city and Internet of things system
CN103508277B (en) A kind of intelligent scheduling elevator and treat terraced method
CN106447107B (en) Maintenance method based on aircraft structure health monitoring
CN112181629B (en) Security inspection centralized image judging system and automatic working mode switching control method thereof
CN109284896B (en) Human error mode influence analysis method
CN105225539B (en) The method and system of sector runnability composite index based on principal component analysis
CN110221620A (en) MAS-based multi-unmanned system supervision control station
JP2023519869A (en) Systems and methods for generating flight plans for use by rideshare networks
CN111488803A (en) Airport target behavior understanding system integrating target detection and target tracking
CN110827582A (en) System and method for automatically acquiring flight landing point in emergency
CA3132496A1 (en) Mitigating operational risk in aircraft
CN118153907B (en) Airport navigation operation management method and system
CN117350640A (en) Project progress management method and system
CN114638538B (en) Fatigue early warning method, device and system for controller and early warning threshold acquisition method
CN116758490B (en) Construction site safety helmet wearing detection and early warning method and system based on AI algorithm
CN113409514A (en) Self-service selling system commodity intelligent management system based on cloud computing and data analysis
CN108446202A (en) A kind of judgment method of the safe condition of calculator room equipment
CN111343598A (en) Intelligent fire-fighting vehicle-mounted platform operation method and system with edge computing capability
CN116596307A (en) Method for constructing driver security portrait model based on public transport operation security data
CN110517731A (en) Genetic test quality monitoring data processing method and system
CN109946687A (en) A kind of comprehensive radio frequency system working method decision-making technique of unmanned platform
CN112201082B (en) N-point replacement method for flight release time slot
CN114066162A (en) Intelligent management method and system for alarm event

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant