CN105205565A - Controller workload prediction method and system based on multiple regression model - Google Patents
Controller workload prediction method and system based on multiple regression model Download PDFInfo
- Publication number
- CN105205565A CN105205565A CN201510645215.3A CN201510645215A CN105205565A CN 105205565 A CN105205565 A CN 105205565A CN 201510645215 A CN201510645215 A CN 201510645215A CN 105205565 A CN105205565 A CN 105205565A
- Authority
- CN
- China
- Prior art keywords
- sector
- index
- controller workload
- aircraft
- regression model
- 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.)
- Pending
Links
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a controller workload prediction method and system. The controller workload prediction method comprises the steps of building a multiple regression model according to controller workload prediction related indexes and controller workload prediction sample data; importing air traffic flow situation index prediction data in a controlled sector into the multiple regression model, and obtaining a controller workload prediction result. According to the controller workload prediction method and system, the air traffic flow situation multidimensional indexes which influence controller workload are considered completely and comprehensively, and thereby effective prediction for controller workload is achieved. The designed controller workload prediction system can be applied to an engineering unit and has great operability.
Description
Technical field
The present invention relates to monitoring field, espespecially a kind of ATC controller workload Forecasting Methodology and system.
Background technology
Along with the development of air-transport industry, in order to ensure that the safety of all kinds of flying activity is with orderly, air traffic control service arises at the historic moment and is constantly developed perfect, is tending towards ripe to the eighties in 20th century.Modern wireless air traffic control service is to the effect that: air traffic controller is (referred to as " controller ", lower same) rely on modern communications, navigation, surveillance technology, management is implemented to administrative aircraft and controls, coordinate and instruct its motion path and pattern, hit aircraft and barrier in airdrome maneuver district mutually to prevent aerial aircraft and aircraft to bump against, safeguard and accelerate the olderly flowage of air traffic.The executor of this task is air traffic controller (referred to as " controller ", lower same).Controller's groundwork is the real-time information by radar asorbing paint, and close supervision flight dynamically, and issues various instruction by radio communication equipment to unit, is the work that many sense organs such as collection eye, hand, a mouth are coordinated jointly.Most peak hours/period, individual controller needs the frame of control tens simultaneously aircraft, therefore, controller's brainwork intensity is large, working load is high, often need break tour, easily there is the fatigue state of varying level, ATC controller workload is predicted and the period that may produce overload is intervened, effectively can avoid the generation of fatigue state.
Patent documentation CN104636890A disclosed a kind of method for measuring workload for air traffic controllers on 05 20th, 2015.The method comprising the steps of A: determine control load measurement index, this control load measurement index comprises eye and moves index and voice metrics; Step B: the eye that each eye of real time record moves index corresponding moves achievement data, and the voice metrics data that each voice metrics is corresponding; Step C: the eye of record is moved to achievement data and carries out factorial analysis, calculates the eye that eye moves achievement data and moves multi-stress; Step D: move multi-stress and voice metrics for input factor with eye, control workload value is output factor, sets up control load regression model.
Patent documentation CN102306297A disclosed a kind of method for measuring workload for air traffic controllers in 2012 01 month 04.First the method classifies to basic air traffic event, secondly the classification of basic control behavior is established based on ergonomics, and by radar voice recorder statistical study control call, set up the ATC controller workload statistical model of easily observation, then machine learning is passed through, obtain the basic control cell operation load determined by air traffic event, and determine the correction factor of this working load, the ATC controller workload statistical model finally utilizing this coefficient correction easily to observe, determines ATC controller workload measurement model.The present invention can realize for ATC controller workload accurate quantification tolerance, for civil aviation control skills training, space domain sector Capacity Assessment and AIRSPACE PLANNING design provide foundation.
About the research of ATC controller workload prediction, be mainly reflected at present on the evaluation technology of ATC controller workload, developed successively since 20 century 70s and three class ATC controller workload assessment methods, that is:
(1) according to controller's physiology, behavioural characteristic analysis, control workload intensity is drawn.The physical signs measured comprises the reaction, heart rate, cardiogram, blood pressure, body fluid etc. of electric shock skin, and behavioral indicator comprises equipment operating number of times, the empty air time record in land etc.
(2) the subjective assessment method of observation and questionnaire form is taked, as ATWIT technology (airtrafficworkloadinputtechnique, the air traffic load input technology of US Federal Aviation Administration), NASA-TLX scale (taskloadindex, the task load scale of US National Aeronautics and Space Administration), SWAT scale (subjectiveworkloadanalysistechnique, subjective workload analytical technology) and MCH method (modifiedcooper-harperratings, Cusparia-Ha Bai revised law) etc.
(3) controller's work is segmented, observable work is surveyed to the time of counting and consuming, temporal consumption is converted into for invisible work, realizes the qualitative assessment to ATC controller workload in time measure mode.These class methods comprise DORATASK method (the DirectorateofOperationResearchandAnalysisoftheUnitedKing dom that ICAO recommends, the research and analysis council that plans strategies for of Britain proposes) and MBB method (Messerschmidt, BglkowandBlohmofGermany, Germany plum plug Schmidt, Te Erke and Blume propose), and RAMS method (Re-organizedATCMathematicalSimulator, European blank pipe experimental center proposes).
The correlative study content of current ATC controller workload prediction, mainly have the following disadvantages: (1) research method aspect, qualitative examination is more, and quantitative examination is less, causes objectivity not enough.(2) study index aspect, how from directly reflecting that the index of ATC controller workload is started with, the factor of influence index of less consideration ATC controller workload, index dimension is comparatively single, and not comprehensively, comprehensively, predicting reliability is not high.(3) application aspect, existing research still rests on the laboratory study stage, serves primarily in strategic decision, and few towards the practical engineering application of air traffic control unit.Due to above-mentioned deficiency, the domestic and international research for ATC controller workload prediction is at present caused to be short of all to some extent in objectivity, comprehensive, comprehensive, accuracy and operability etc.
Summary of the invention
The invention provides a kind of more efficiently, objectivity, the ATC controller workload Forecasting Methodology of forecasting accuracy and system can be improved.
The object of the invention is to be achieved through the following technical solutions:
A kind of ATC controller workload Forecasting Methodology, comprises step:
Step 1: the control sector transport air flow situation index choosing certain hour interval, and ATC controller workload index corresponding to situation index is as sample data;
Step 2: according to above-mentioned sample data, sets up linear regression model (LRM) and nonlinear regression model (NLRM);
Step 3: by degree of fitting, conspicuousness and error analysis, compares to linear regression model (LRM) and nonlinear regression model (NLRM), determines ATC controller workload prediction multiple regression model;
Step 4: real-time control sector transport air flow situation index is imported control employee and makes load prediction multiple regression model, obtain ATC controller workload index.
Further, the control sector transport air flow situation index in described step 1 comprises sector and runs road ability index, sector operation complexity profile, sector safety in operation index and sector performance driving economy index.
Further, described control sector transport air flow situation index comprises sector operation road ability index, sector operation complexity profile, sector safety in operation index and sector performance driving economy index;
Sector road ability Testing index comprises sector flow, sector shipping kilometre, sector hours underway and sector traffic flow density respectively;
Sector complicacy Testing index comprise sector aircraft climb number of times, sector aircraft decline number of times, sector aircraft changes fast number of times, sector aircraft changes flight number number;
Sector security Testing index comprises sector short term collision alert frequency and sector minimum safe altitude alert frequency;
Sector economy Testing index comprises sector saturation degree, sector queue length, sector aircraft delay sortie rate, sector aircraft delay time at stop, sector aircraft mean delay time.
Further, in described step 2, standardization conversion is carried out to sample data; Standardization transfer process is as follows:
Make x
ij, x '
ijrepresent the raw data of i-th sample and the data after standardization conversion respectively,
s
jrepresent average and the variance of a jth achievement data respectively, then:
Further, described step 2 specifically comprises:
According to above-mentioned standardization sample data x'
ij(i=1,2 ... m, j=1,2 ... n), set up Multivariate regression model and multiple nonlinear regression model (NLRM) respectively, and solve coefficient b
i,
Wherein Multivariate regression model is:
Y=XB+U (formula 1)
Wherein,
Multiple nonlinear regression model (NLRM) is:
Y=f [(b
1, b
2..., b
k); X
1, X
2..., X
n] (formula 2)
Wherein dependent variable Y is controller's load factor, independent variable X is n item control sector transport air flow situation index, m represents the control sector running performance index sample under the m group time interval, U is except m independent variable is on the stochastic error except the impact of dependent variable Y, Normal Distribution, f represents nonlinear solshing.
Further, described step 3 specifically comprises:
According to the coefficient of determination R that each model returns
2value, F inspection, t inspection, verify respectively and compare degree of fitting, the conspicuousness of two kinds of regression models, on the obvious basis of, conspicuousness higher in model-fitting degree, calculate the metrical error of two kinds of regression models, and choose the minimum a kind of model of error, as the multiple regression model of ATC controller workload prediction.
Further, the real-time control sector transport air flow situation index in step 4 will carry out standardization conversion before input multiple regression model; Standardization transfer process is as follows:
According to the average of the n item index of the sample data in the m group time interval
variance s
j, to control sector transport air flow situation index t
j(j=1,2 ..., n) carry out standardization conversion:
by the data t after conversion
j' import in ATC controller workload prediction multiple regression model.
Further, described method also comprises step 5, when ATC controller workload index exceeds threshold value, and ATC controller workload response alarm.
A kind of prognoses system of ATC controller workload, comprise: construction part module: choose control sector transport air flow situation index, ATC controller workload forecast sample data corresponding for index of correlation are substituted in Multivariate regression model and multiple nonlinear regression model (NLRM) and carries out matching; Obtain the estimates of parameters of Multivariate regression model and multiple nonlinear regression model (NLRM); By statistical test, calculate metrical error, determine ATC controller workload prediction multiple regression model; Prediction module: by control sector transport air flow situation index prediction data importing ATC controller workload prediction multiple regression model, obtain predicting the outcome of ATC controller workload.
Further, system also comprises, standardization modular converter: for carrying out standardization conversion to sample data and control sector transport air flow situation index real time data; Alarm module: exceed threshold value when predicting the outcome, ATC controller workload response alarm.
Further, described prognoses system also comprises control sector traffic flow situation Test database, and the data be coupled with described control sector traffic flow situation Test database draw connection device and index collection device;
Described data are drawn connection device and are comprised the telegram data-interface, integrated track data-interface and the control speech data interface that are coupled with described control sector traffic flow situation Test database respectively;
Described index collection device is for gathering traffic flow situation index in control sector null, and described control sector transport air flow situation index comprises sector and runs road ability index, sector operation complexity profile, sector safety in operation index and sector performance driving economy index; Sector road ability Testing index comprises sector flow, sector shipping kilometre, sector hours underway and sector traffic flow density respectively; Sector complicacy Testing index comprise sector aircraft climb number of times, sector aircraft decline number of times, sector aircraft changes fast number of times, sector aircraft changes flight number number; Sector security Testing index comprises sector short term collision alert frequency and sector minimum safe altitude alert frequency; Sector economy Testing index comprises sector saturation degree, sector queue length, sector aircraft delay sortie rate, sector aircraft delay time at stop, sector aircraft mean delay time;
Described construction part module reads described ATC controller workload prediction index of correlation and ATC controller workload forecast sample data from described control sector traffic flow situation Test database; Described prediction module reads described control sector transport air flow situation index prediction data from described control sector traffic flow situation Indexs measure database.
Beneficial effect of the present invention:
The present invention adopts quantitative analysis method, by to the uninterrupted detection of magnanimity service data and computational analysis, extrapolate accurate future time period transport air flow situation achievement data, and rely on the excavation to historical data, obtain the relation between transport air flow situation and ATC controller workload, on this basis ATC controller workload is predicted, have objective, efficiently, advantage accurately, evaded the defect problem of the empirical management such as artificial prediction fatiguability, easily internalise.What is more important, put forward system and can meet air traffic control unit carries out real-time estimate and alarm actual demand to ATC controller workload, for lifting control operation and management level, optimize control zone structure there is Data support effect.The transport air flow situation various dimensions index affecting ATC controller workload is carried out comprehensively, is considered by the present invention, thus realizes the effective prediction to ATC controller workload.Designed ATC controller workload prognoses system, can be applied to engineering unit, have very strong operability.
Accompanying drawing explanation
Fig. 1 is the schematic diagram of the embodiment of the present invention one ATC controller workload Forecasting Methodology;
Fig. 2 is the schematic diagram of the embodiment of the present invention one ATC controller workload prognoses system;
Fig. 3 is the system logic structure schematic diagram of the embodiment of the present invention two ATC controller workload prediction;
Fig. 4 is the system network architecture schematic diagram of the embodiment of the present invention two ATC controller workload prediction;
Fig. 5 is the systematic functional structrue schematic diagram of the embodiment of the present invention two ATC controller workload prediction;
Fig. 6 is the embodiment of the present invention three integrated track data acquisition function structural representation;
Fig. 7 is the embodiment of the present invention three data under voice schematic flow sheet;
Fig. 8 is the embodiment of the present invention three telegram data acquisition function structural representation;
Fig. 9 is the method schematic diagram of embodiment of the present invention four-pipe system person Workload prediction;
Figure 10 is the multiple nonlinear regression and fitting result schematic diagram of the embodiment of the present invention four;
Figure 11 is the embodiment of the present invention four multiple nonlinear regression and fitting error schematic diagram;
Figure 12 is the structural representation of the embodiment of the present invention five ATC controller workload prognoses system;
Wherein: 1, construction part module; 2, prediction module; 3, standardization modular converter; 4, alarm module: 5, operating index Test database; 6, data draw connection device; 7, index collection device.
Embodiment
Below in conjunction with accompanying drawing and preferred embodiment, the invention will be further described.
Embodiment one
As shown in Figure 1, ATC controller workload Forecasting Methodology disclosed in present embodiment, it comprises step:
S1, choose control sector transport air flow situation index, ATC controller workload index corresponding for index of correlation is substituted in Multivariate regression model and multiple nonlinear regression model (NLRM) as sample data and carries out matching; Obtain Multivariate regression model and multiple nonlinear regression model (NLRM) estimates of parameters, set up heavy linear regression model (LRM) and multiple nonlinear regression model (NLRM);
S2, by degree of fitting, conspicuousness and error analysis, linear regression model (LRM) and nonlinear regression model (NLRM) to be compared, determine ATC controller workload prediction multiple regression model;
S3, control sector transport air flow situation index real time data is imported control employee make load prediction multiple regression model, obtain predicting the outcome of ATC controller workload index.
As shown in Figure 2, present embodiment also discloses a kind of prognoses system of ATC controller workload, comprises,
Construction part module: choose ATC controller workload prediction index of correlation, ATC controller workload forecast sample data corresponding for index of correlation are substituted in multiple regression model and carries out matching; Obtain estimates of parameters and the sample output valve of multiple regression model; Estimates of parameters, sample output valve are imported multiple regression model, obtains sample regression function;
Prediction module: by control sector transport air flow situation index prediction data importing sample regression function, obtain predicting the outcome of ATC controller workload.
Regretional analysis is an important branch in multivariate statistical analysis, and it is the statistical method being detected one or more response variable (i.e. dependent variable) by one group of detection variable (i.e. independent variable).Only have the situation of a dependent variable to be called simple regression, multiple dependent variable is called multiple regression.Consider that ATC controller workload is subject to various factors, setting ATC controller workload, as single response variable, therefore, adopts unitary multiple regression method (abbreviation multiple regression) herein, predicts ATC controller workload.
According to the linear relationship of regression function, multiple linear regression and the basic function model of multiple non-linear regression two kinds can be divided into.The present invention can adopt two kinds of models use, and then little a kind of as final forecast model of Select Error, also can single choice one predict, with simplified operation process.
The present invention adopts quantitative analysis method, by to the uninterrupted detection of magnanimity service data and computational analysis, extrapolate accurate future time period transport air flow situation achievement data, and rely on the excavation to historical data, obtain the relation between transport air flow situation and ATC controller workload, on this basis ATC controller workload is predicted, have objective, efficiently, advantage accurately, evaded the defect problem of the empirical management such as artificial prediction fatiguability, easily internalise.What is more important, put forward system and can meet air traffic control unit carries out real-time estimate and alarm actual demand to ATC controller workload, for lifting control operation and management level, optimize control zone structure there is Data support effect.The transport air flow situation various dimensions index affecting ATC controller workload is carried out comprehensively, is considered by the present invention, thus realizes the effective prediction to ATC controller workload.Designed ATC controller workload prognoses system, can be applied to engineering unit, have very strong operability.
Embodiment two
Present embodiment discloses a kind of system architecture, as the implementing platform of ATC controller workload prediction method, system of the present invention, can be used for implementing Forecasting Methodology of the present invention.
The ATC controller workload prognoses system structure of present embodiment as shown in Figure 3.Workload for air traffic controllers prognoses system mainly comprise a set of control sector traffic flow situation Test database and data draw connect, index collection three zones module.The transport air flow situation data (comprising radar integrated track data, telegram data, VHF recording data etc.) that each information gathering point gathers by control sector traffic flow situation Test database are sorted out, preservation, for ATC controller workload prediction provides data foundation.
Fig. 4,5 disclose a kind of realize prognoses system of the present invention network structure and corresponding functional module structure.System collects real time data by data acquisition server, predicted and alarm server real time monitoring service data by control sector traffic flow situation detection server and ATC controller workload, and the ATC controller workload of future time period is predicted, and alarm is carried out to the period that working load exceeds threshold value.The network platform of whole system will rely on existing management information net, and acquisition platform and blank pipe are produced network and carried out physical isolation, ensure the unidirectional delivery of data, stop network attack, to ensure related data security and production run system reliability.
Embodiment three
Present embodiment discloses a kind of control service data acquisition scheme, including, but not limited to the collection of ATC controller workload prediction index of correlation, ATC controller workload forecast sample data and control sector transport air flow situation index prediction data.
This research for dependent variable, is designated as Y with ATC controller workload index.Control sector transport air flow situation index amounts to 15, and note independent variable X is:
X={X
i, i=1,2 ..., 15} (formula 3.1)
Wherein, road ability Testing index in sector is { X
1, X
2, X
3, X
4, represent sector flow, sector shipping kilometre, sector hours underway and sector traffic flow density respectively; Sector complicacy Testing index is { X
5, X
6, X
7, X
8, represent respectively sector aircraft climb number of times, sector aircraft decline number of times, sector aircraft changes fast number of times, sector aircraft changes flight number number; Sector security Testing index is { X
9, X
10, represent sector short term collision alert frequency and sector minimum safe altitude alert frequency respectively; Sector economy Testing index is { X
11, X
12, X
13, X
14, X
15, represent that sector saturation degree, sector queue length, sector aircraft incur loss through delay sortie rate, sector aircraft delay time at stop, sector aircraft mean delay time respectively.The main of these parameter indexs obtains from the following aspects collection.
Integrated track gathers
Air traffic control automation system carries out data to supervisory signals such as aviation management first and second radars and merges and data processing, and output integrated flight path information, its main processing module comprises radar front end processing module, radar data processing module and flight planning processing module.
The technical program gathers integrated track data from air traffic control automation system, is transmitted by the mode of network.Data acquisition server is resolved the integrated track data gathered, and the information such as height, speed, position obtaining aircraft is used in reference to target and calculates.
Integrated track data acquisition module comprises track data format converting module, track data parsing module, track data memory module, as shown in Figure 6.
Data under voice
Controller and pilot realize the empty voice call in land by VHF communication system.This system receives and dispatches radio station and Signal transmissions by very high frequency(VHF) (VeryHighFrequency, VHF), treating apparatus forms.
Data under voice is from distributing frame and connect collection voice signal, is carried out decoding and storing by empty for land call-information, for the analysis of controller's control commander call load.
As shown in Figure 7, seat speech data is by interior telephone system distributing frame by being with shielding netting wire and connecing drawing-in system data acquisition server, and voice channel is corresponding with seat (sector).
Voice signal gathers (the air-ground call of controller) seat voice from high impedance distributing frame (recording module is 200K ohm), do not affect air-ground call and voice record, adopt multiple-twin cable line to be drawn from distributing frame by voice signal and be connected to speech processor, realize the collection to multiple seats voice and analysis.
Telegram data acquisition
Telegraph switching relay system is the project planning that transmitting-receiving Civil Aviation Flight dynamically fixes telegram, and the data marshalling that the message that Civil Aviation Flight dynamically fixes telegram is specified by several forms by permanent order arrangement.
Telegram data acquisition module draws the telegram data of switching through reporting system and exporting, and carries out format conversion, parsing and storage to data, obtains flight plan data, as shown in Figure 8.This module is preserved being stored in database after the telegram Data Analysis received, and calculates for sector running performance index.
Control sector transport air flow situation index collection
System collects the real-time running datas such as integrated track, flight planning, voice communication from air traffic control automation system, telegraph switching relay system, interior telephone system, with International Civil Aviation Organization (referred to as " ICAO ", down together), US Federal Aviation Administration (FAA) associated documents are reference, set up control sector transport air flow situation index system, comprise: road ability index is run in sector, comprises sector flow, sector shipping kilometre, sector hours underway and sector traffic flow density; Sector run complexity profile, comprise sector aircraft climb number of times, sector aircraft decline number of times, sector aircraft changes fast number of times, sector aircraft changes flight number number; Sector economic index, comprises sector saturation degree, sector queue length, sector aircraft delay sortie rate, sector aircraft delay time at stop, sector aircraft mean delay time.And based on index system export control sector transport air flow situation Indexs measure result.System provides good man-machine interface, checks various real-time statistics figure for user.
Road ability index is run in sector
(1) sector flow
Sector flow refers to the aircraft sortie of administering in the control sector unit interval.System connects the positional information of the aerial aircraft of air traffic control automation system integrated track data acquisition by drawing, in conjunction with the sector borders information configured, calculate sector flow.
(2) sector shipping kilometre
Sector shipping kilometre refers to the summation of the aircraft shipping kilometre of administering in the control sector unit interval.If aircraft sortie number is n in the control sector unit interval, the shipping kilometre of jth frame aircraft is M
i, sector shipping kilometre is M
total, then
system connects the positional information of the aerial aircraft of air traffic control automation system integrated track data acquisition by drawing, in conjunction with the sector borders information configured, calculate sector shipping kilometre.
(3) sector hours underway
Sector hours underway refers to the summation of the aircraft hours underway of administering in the control sector unit interval.If aircraft sortie number is n in the control sector unit interval, the hours underway of the i-th frame aircraft is T
i, sector hours underway is T
total, then
system connects the positional information of the aerial aircraft of air traffic control automation system integrated track data acquisition by drawing, in conjunction with the sector borders information configured, calculate sector hours underway.
(4) sector traffic flow density
Sector traffic flow density is estimating the aircraft sortie dense degree of administering in the control sector unit interval.If sector area is S
sec, in the unit interval, sector flow is n, and in the unit interval, traffic flow density in sector is D
sec, then D
sec=n/S
sec.The sector borders information that system reads configuration obtains sector area, obtains sector traffic flow density in conjunction with sector flow rate calculation.
Complexity profile is run in sector
(1) sector aircraft climbs number of times
The aircraft number of times that climbs in sector refers in the control sector unit interval that the aircraft of administering climbs the summation of number of times.If aircraft sortie number is n in the control sector unit interval, the number of times that climbs of the i-th frame aircraft is c
i, the aircraft number of times that climbs in sector is c
total, then
system is drawn and is connect real time comprehensive track data, and carry out monitoring to the situation of climbing of aircraft in sector and add up, an aircraft climbs a height layer for climbing once, calculates sector aircraft and to climb number of times.
(2) sector aircraft decline number of times
Sector aircraft decline number of times refers to the summation of aircraft decline number of times in the control sector unit interval.If aircraft sortie number is n in the control sector unit interval, the decline number of times of the i-th frame aircraft is D
i, sector aircraft decline number of times is D
total, then
system is drawn and is connect real time comprehensive track data, carries out monitoring and add up the decline situation of aircraft in sector, aircraft decline a height layer for decline once, calculate sector aircraft and to climb number of times.
(3) sector aircraft changes fast number of times
Sector aircraft changes fast number of times and refers to that in the control sector unit interval, aircraft speed changes the summation of number of times.If aircraft sortie number is n in the control sector unit interval, the fast number of times that changes of the i-th frame aircraft is S
i, it is S that sector aircraft changes fast number of times
total, then
system is drawn and is connect real time comprehensive track data, changes situation carry out monitoring and add up the speed of aircraft in sector, and aircraft speed continuously changes that to reach setup parameter be a speed change, calculates sector aircraft and changes fast number of times.
(4) sector aircraft changes flight number number
Sector aircraft changes the summation that flight number number refers to aircraft course change number of times in the control sector unit interval.If aircraft sortie number is n in the control sector unit interval, the flight number number that changes of the i-th frame aircraft is H
i, it is H that sector aircraft changes flight number number
total, then
system is drawn and is connect real time comprehensive track data, carries out monitoring and add up the course change situation of aircraft in sector, and aircraft course continuously changes that to reach setup parameter be a course change, calculates sector aircraft and changes flight number number.
1.1.1.1.1 sector safety in operation index
(1) sector short term collision alert frequency
Sector short term collision alert frequency refers to the aircraft short term collision alert number of times of administering in the control sector unit interval, draws the STCA alarm data statistics connecing air traffic control automation system obtain by system.
(2) sector minimum safe altitude alert frequency
Sector minimum safe altitude alert frequency refers to the aircraft minimum safe altitude alarm number of times of administering in the control sector unit interval, draws the MSAW alarm data statistics connecing air traffic control automation system obtain by system.
1.1.1.1.2 sector performance driving economy index
(1) sector saturation degree
Sector saturation degree refers to the ratio of flow and capacity in the control sector unit interval, and the aircraft maximum quantity can administered in the control sector unit interval is demarcated as control sector capacity.If aircraft sortie number is n in the control sector unit interval, control sector capacity is C, and sector saturation degree is Satu
sec, then Satu
sec=n/C.System reads the sector capacity parameter of configuration, obtains sector saturation degree in conjunction with sector flow rate calculation.
(2) sector queue length
In the aircraft of administering within the control sector unit interval, as there is the queuing situation such as wait that spiral when entering sector, be then defined as queuing aircraft, definition sector queue length is the quantity of queuing aircraft.System is drawn and is connect integrated track data, judges whether target aircraft carries out in sector borders wait of spiraling, and calculates sector queue length.
(3) sortie rate incured loss through delay by sector aircraft
In the aircraft of administering within the control sector unit interval, hours underway is defined as delay aircraft beyond the aircraft of normal range, and the part that hours underway exceeds normal range is defined as the delay time at stop.If aircraft sortie number is n in the control sector unit interval, the delay sortie number of sector aircraft is d, and the delay sortie rate of sector aircraft is Drat
sec, then Drat
sec=d/n.System is drawn and is connect integrated track data, the actual flying time of every frame aircraft in control sector and experience flight time are contrasted, if actual flying time is greater than the experience flight time, be then considered as incuring loss through delay aircraft, and calculate sector aircraft delay sortie rate.
(4) the sector aircraft delay time at stop
In the aircraft of administering within the control sector unit interval, hours underway is defined as delay aircraft beyond the aircraft of normal range, the part that hours underway exceeds normal range is defined as the delay time at stop, and delay time at stop summation is defined as the sector aircraft delay time at stop.If aircraft sortie number is n in the control sector unit interval, the delay time at stop of the i-th frame aircraft is Delay
i, the sector aircraft delay time at stop is Delay
sec, then
system is drawn and is connect integrated track data, the actual flying time of every frame aircraft in control sector and experience flight time are contrasted, if actual flying time is greater than the experience flight time, is then considered as incuring loss through delay aircraft, and calculates the sector aircraft delay time at stop.
(5) the sector aircraft mean delay time
In the aircraft of administering within the control sector unit interval, hours underway is defined as delay aircraft beyond the aircraft of normal range, and the part that hours underway exceeds normal range is defined as the delay time at stop.If the sector aircraft delay time at stop is Delay
sec, in the control sector unit interval, aircraft sortie number is n, and the mean delay time of sector aircraft is Davg
sec, then Davg
sec=Delay
sec/ n.System is drawn and is connect integrated track data, the actual flying time of every frame aircraft in control sector and experience flight time are contrasted, if actual flying time is greater than the experience flight time, is then considered as incuring loss through delay aircraft, and calculates the sector aircraft mean delay time.
ATC controller workload indicator index gathers
Controller need bear on health and spiritual pressure for completing Tasks of Regulation, these pressure can be converted into temporal consumption, alleviate the pressure afforded and the requirement completing objective task by time loss, the length of this time loss is exactly the size of ATC controller workload.In the controller's working time can surveying meter consumes, the empty talk channel occupancy in land is the indicator index of reflection ATC controller workload.
The empty talk channel occupancy in land refers to the empty duration of call accounting in control sector unit interval inland.If control sector is total to land sky call m time in unit interval T, the time span of i-th land sky call is T
i, the empty talk channel occupancy in land is T
rate, then
system draws adapter speech data processed, the controller and the pilot that analyze control seat, corresponding sector converse start time and end time, then the duration that every section is conversed is added up, thus obtain the empty duration of call in land, sector, and then calculate the empty talk channel occupancy in land.
Control sector transport air flow situation index prediction
System connects air traffic control automation system integrated track data and the dynamic fixed form telegram data of telegraph switching relay system Civil Aviation Flight by drawing in real time; obtain the flight plan data of aircraft; comprise flight number, the departure time, original base, land time, the information such as airport of landing; obtain by integrated track the flight information such as height, speed and position aloft of taking off, and calculated by the positional information of 4D Trajectory Prediction technology to future time period aircraft.By calculating the data of the aircraft position information acquisition future transportation fluidised form gesture index of future time period.Wherein, for realizing based on 4D Trajectory Prediction technology for realizing precisely prediction, system establishes aircraft Back ground Information and runnability database, air route route information database.
Embodiment four
Present embodiment discloses a kind of ATC controller workload Forecasting Methodology, the method can be selected the hardware platform of embodiment two to realize, choosing of the Workload prediction index of correlation that it relates to, the collection of ATC controller workload forecast sample data and control sector transport air flow situation index prediction data can reference example three.
Present embodiment adopts multiple linear regression and multiple nonlinear regression model (NLRM) simultaneously, and the model selecting metrical error minimum from both is as final forecast model.
(1) multiple linear regression utilizes linear function to carry out the multiple independent variable X of matching
i(i=1,2 ..., n) and the relation of single dependent variable Y, thus determine the parameter b of Multivariate regression model
i(i=0,1,2 ..., n), be returned in null hypothesis equation, detected the trend of dependent variable by regression equation.The general type of Multivariate regression model is:
Y=b
0+ b
1x
1+ b
2x
2+ ... + b
ix
i+ ... + b
nx
n+ μ (formula 4.1)
Wherein, μ is except n independent variable is on the stochastic error except the impact of dependent variable Y, Normal Distribution.
As if statistics sample has m group statistical data, then the matrix form of Multivariate regression model can be expressed as:
Y=XB+U (formula 4.2)
Wherein,
(formula 4.3)
(2) multiple non-linear regression, be then present nonlinear relationship between supposition independent variable (prediction index) and dependent variable (ATC controller workload), multiple nonlinear model generally can be expressed as:
Y=f [(b
1, b
2..., b
k); X
1, X
2..., X
n] (formula 4.4)
Wherein nonlinear solshing according to sample data feature, can adopt the forms such as quadratic function, power function, exponential function, hyperbolic function.Present embodiment is illustrated with quadratic function:
The parameter b of multiple regression model
iafter estimating, namely after obtaining sample regression function, also need to carry out statistical test to this sample regression function further, comprise degree of fitting inspection, significance test, and the Estimating Confidence Interval etc. of parameter, then calculate metrical error, the little model of final Select Error is as final forecast model.
According to the coefficient of determination R that each model returns
2value, F inspection, t inspection, verify respectively and compare degree of fitting, the conspicuousness of two kinds of regression models, on the obvious basis of, conspicuousness higher in model-fitting degree, calculate the metrical error of two kinds of regression models, and choose the minimum a kind of model of error, as the multiple regression model of sector runnability comprehensive detection.
ATC controller workload prediction algorithm based on multiple regression mainly comprises four parts, i.e. the ratio choosing of the structure of regression model, regression model, ATC controller workload prediction and ATC controller workload response alarm.See Fig. 9, specific algorithm step is:
Step 1: choose variable
Reference example three, according to M group with hour for duration sample input data, obtain the input value of described 15 indexs above.Meanwhile, using controller land sky talk channel occupancy as ATC controller workload index Y.The sample index's data instance obtained is as follows:
Table 1 ATC controller workload prediction index sample data example
Wherein, independent variable X={X
i, i=1,2 ..., 15} is control sector transport air flow situation index, amounts to 15.By the X of table 1
1~ X
151 ~ M group data and the M group data of Y substitute into formula 4.3,4.4 respectively.
Wherein, road ability Testing index in sector is { X
1, X
2, X
3, X
4, represent sector flow, sector shipping kilometre, sector hours underway and sector traffic flow density respectively; Sector complicacy Testing index is { X
5, X
6, X
7, X
8, represent respectively sector aircraft climb number of times, sector aircraft decline number of times, sector aircraft changes fast number of times, sector aircraft changes flight number number; Sector security Testing index is { X
9, X
10, represent sector short term collision alert frequency and sector minimum safe altitude alert frequency respectively; Sector economy Testing index is { X
11, X
12, X
13, X
14, X
15, represent that sector saturation degree, sector queue length, sector aircraft incur loss through delay sortie rate, sector aircraft delay time at stop, sector aircraft mean delay time respectively.
Step 2: data processing
Consider to there is dimension difference and magnitude differences between different index, for convenience of the regretional analysis of model, need to carry out standardization conversion to achievement data.
Make x
ij, x '
ijrepresent the raw data of i-th sample and the data after standardization conversion respectively,
s
jrepresent respectively jth (j=1,2 ..., 15) and the average of individual achievement data and variance, then:
(formula 4.6)
Data x ' after standardization is changed
ij, as the input data of regretional analysis.
Step 3: build regression model
Reference example two, three, build Multivariate regression model and multiple nonlinear regression model (NLRM) respectively, wherein, the form of quadratic function selected by nonlinear regression model (NLRM).By carrying out matching to sample data, obtain the estimates of parameters of two class functions
with sample output valve
wherein
the b of representative formula 4.4
0~ b
nor the b of formula 4.5
0~ b
2nestimated value.
Step 4: inspection regression model
According to the coefficient of determination R that each model returns
2value, F inspection, t inspection, verify respectively and compare degree of fitting, the conspicuousness of two kinds of regression models, on the obvious basis of, conspicuousness higher in model-fitting degree, calculate the metrical error of two kinds of regression models, and choose the minimum a kind of model of error, as the multiple regression model of ATC controller workload prediction.
Step 5: regression model result exports
According to the average of 15 indexs that N group sample data obtains
variance s
j, by control sector transport air flow situation index prediction data
as input data, column criterionization of going forward side by side is changed,
for the input data after process.After carrying out standardization, will
import in ATC controller workload prediction regression model, obtain predicting the outcome of ATC controller workload index.
Step 6: ATC controller workload response alarm
Predicting the outcome according to ATC controller workload, with reference to the ATC controller workload response alarm standard of setting, to reaching alarm standard, produces alarm by system.
According to above-mentioned algorithm flow, gather ACC01 sector, Chengdu index of correlation data and amount to 400 groups, adopt linear function and nonlinear function (quadratic function) to carry out matching to sample data respectively, the Fitting Calculation obtains the R of two class functions
2, p value, and the matching performance data such as average error, maximum error, least error.Respectively fitting effect is compared to the ATC controller workload forecast model based on Multivariate regression model and nonlinear regression model (NLRM).Conclusion is as follows:
Table 2 multiple regression fitting effect contrasts
According to upper table, degree of fitting, the index such as conspicuousness and error of the nonlinear function of present embodiment are all slightly better than linear function.Therefore, choose nonlinear function herein, as the forecast model of ATC controller workload.The fitting result chart of this model and prediction-error image are as shown in Figure 10,11:
To sum up, the ATC controller workload forecast model based on multiple non-linear regression is:
(formula 4.7)
According to formula 4.7, ATC controller workload is predicted.According to control sector transport air flow Tendency Prediction result, obtain the traffic flow situation achievement data of following 5 periods.After standardization, bring in formula 4.7, the ATC controller workload calculating following 5 periods predicts the outcome, as shown in the table.
Table 3 ATC controller workload prediction instance analysis
According to ATC controller workload alarm standard, alarm standard is reached to the working load of future time period controller, carries out corresponding alarm.
This Forecasting Methodology and corresponding system, after putting into operation, need to manage accordingly.The system management recommended has following several:
1. management uses user right, is every user's distributing user name and authority, ensures the security of data, prevents data from leaking.
2. every user corresponding 0 is to multiple role, the authority that each role can be accessed by managerial personnel's flexible allocation and operate.
3. the parameter that system cloud gray model is necessary is set, comprises map parameter, telegram process and radar data process parameter, the long-term parameter that the timetable is shown, system display parameter are arranged, other needs are arranged.
4. provide log management function, be responsible for the operation of recording system, retain the operation information of significant data.Comprise: daily record recording module, log query module, Log backup and removing module.
5. parameter configuration function is provided, for system maintenance personnel provide the instrument of parameter configuration.
6. data exporting function is provided.
The proposed arrangement realizing Forecasting Methodology of the present invention and system is as follows:
Embodiment five
The ATC controller workload Forecasting Methodology of present embodiment, comprises step:
According to ATC controller workload prediction index of correlation and ATC controller workload forecast sample data construct multiple regression model.According to M group with hour for duration sample input data, obtain ATC controller workload prediction index of correlation input value; Using controller land, empty talk channel occupancy is as ATC controller workload index, obtains ATC controller workload forecast sample data.
By control sector transport air flow situation index prediction data importing multiple regression model.
Consider to there is dimension difference and magnitude differences between different index, before structure multiple regression model, first the ATC controller workload of input is predicted that index of correlation and ATC controller workload forecast sample data carry out standardization conversion; Accordingly, to the advanced column criterionization conversion of the control sector transport air flow situation index prediction data importing multiple regression model; The regretional analysis of model can be facilitated like this.
Multiple regression model comprises Multivariate regression model and multiple nonlinear regression model (NLRM), and wherein, quadratic function selected by nonlinear regression model (NLRM).Pattern function is with reference to above-described embodiment.
Respectively by Multivariate regression model and multiple nonlinear regression model (NLRM), matching is carried out to ATC controller workload forecast sample data, obtain two groups of sample regression functions, statistical test is carried out to two groups of sample regression functions, described statistical test step comprises degree of fitting and significance test, when degree of fitting and conspicuousness exceed preset value, then calculate metrical error.
By a kind of multiple regression model minimum for control sector transport air flow situation index prediction data importing metrical error, predicted the outcome.
Threshold value is exceeded, ATC controller workload response alarm when predicting the outcome.
Described control sector transport air flow situation index comprises sector and runs road ability index, sector operation complexity profile, sector safety in operation index and sector performance driving economy index; Sector road ability Testing index comprises sector flow, sector shipping kilometre, sector hours underway and sector traffic flow density respectively; Sector complicacy Testing index comprise sector aircraft climb number of times, sector aircraft decline number of times, sector aircraft changes fast number of times, sector aircraft changes flight number number; Sector security Testing index comprises sector short term collision alert frequency and sector minimum safe altitude alert frequency; Sector economy Testing index comprises sector saturation degree, sector queue length, sector aircraft delay sortie rate, sector aircraft delay time at stop, sector aircraft mean delay time.
As shown in figure 12, present embodiment also discloses a kind of prognoses system of ATC controller workload.It comprises operating index Test database, and the data be coupled with control sector operating index Test database draw connection device and index collection device.
Data are drawn connection device and are comprised the telegram data-interface, integrated track data-interface and the control speech data interface that are coupled with control sector operating index Test database respectively; Index collection device is for gathering traffic flow situation index in control sector null, and control sector transport air flow situation index comprises sector and runs road ability index, sector operation complexity profile, sector safety in operation index and sector performance driving economy index.
ATC controller workload forecast sample data corresponding for index of correlation are substituted in Multivariate regression model and multiple nonlinear regression model (NLRM) and carry out matching by construction part module: choose control sector transport air flow situation index; Obtain the estimates of parameters of Multivariate regression model and multiple nonlinear regression model (NLRM); By statistical test, calculate metrical error, determine ATC controller workload prediction multiple regression model;
Prediction module: by control sector transport air flow situation index prediction data importing ATC controller workload prediction multiple regression model, obtain predicting the outcome of ATC controller workload.
Standardization modular converter: for carrying out standardization conversion to sample data and control sector transport air flow situation index real time data;
Alarm module: exceed threshold value when predicting the outcome, ATC controller workload response alarm.
Construction part module reads ATC controller workload prediction index of correlation and ATC controller workload forecast sample data from control sector operating index Test database; Prediction module reads control sector transport air flow situation index prediction data from control sector operating index Test database.
Described index collection device is for gathering traffic flow situation index in control sector null, and described control sector transport air flow situation index comprises sector and runs road ability index, sector operation complexity profile, sector safety in operation index and sector performance driving economy index; Sector road ability Testing index comprises sector flow, sector shipping kilometre, sector hours underway and sector traffic flow density respectively; Sector complicacy Testing index comprise sector aircraft climb number of times, sector aircraft decline number of times, sector aircraft changes fast number of times, sector aircraft changes flight number number; Sector security Testing index comprises sector short term collision alert frequency and sector minimum safe altitude alert frequency; Sector economy Testing index comprises sector saturation degree, sector queue length, sector aircraft delay sortie rate, sector aircraft delay time at stop, sector aircraft mean delay time.
Above content is in conjunction with concrete preferred implementation further description made for the present invention, can not assert that specific embodiment of the invention is confined to these explanations.For general technical staff of the technical field of the invention, without departing from the inventive concept of the premise, some simple deduction or replace can also be made, all should be considered as belonging to protection scope of the present invention.
Claims (11)
1. an ATC controller workload Forecasting Methodology, is characterized in that, comprises step:
Step 1: the control sector transport air flow situation index choosing certain hour interval, and ATC controller workload index corresponding to situation index is as sample data;
Step 2: according to above-mentioned sample data, sets up linear regression model (LRM) and nonlinear regression model (NLRM);
Step 3: by degree of fitting, conspicuousness and error analysis, compares to linear regression model (LRM) and nonlinear regression model (NLRM), determines ATC controller workload prediction multiple regression model;
Step 4: real-time control sector transport air flow situation index is imported control employee and makes load prediction multiple regression model, obtain ATC controller workload index.
2. ATC controller workload Forecasting Methodology as claimed in claim 1, it is characterized in that, the control sector transport air flow situation index in described step 1 comprises sector and runs road ability index, sector operation complexity profile, sector safety in operation index and sector performance driving economy index.
3. ATC controller workload Forecasting Methodology as claimed in claim 2, it is characterized in that, described control sector transport air flow situation index comprises sector and runs road ability index, sector operation complexity profile, sector safety in operation index and sector performance driving economy index;
Sector road ability Testing index comprises sector flow, sector shipping kilometre, sector hours underway and sector traffic flow density respectively;
Sector complicacy Testing index comprise sector aircraft climb number of times, sector aircraft decline number of times, sector aircraft changes fast number of times, sector aircraft changes flight number number;
Sector security Testing index comprises sector short term collision alert frequency and sector minimum safe altitude alert frequency;
Sector economy Testing index comprises sector saturation degree, sector queue length, sector aircraft delay sortie rate, sector aircraft delay time at stop, sector aircraft mean delay time.
4. the ATC controller workload Forecasting Methodology as described in claim 1 or 3, is characterized in that, carries out standardization conversion in described step 2 to sample data; Standardization transfer process is as follows:
Make x
ij, x '
ijrepresent the raw data of i-th sample and the data after standardization conversion respectively,
s
jrepresent average and the variance of a jth achievement data respectively, then:
5. ATC controller workload Forecasting Methodology as claimed in claim 1, it is characterized in that, described step 2 specifically comprises:
According to above-mentioned standardization sample data x'
ij(i=1,2 ... m, j=1,2 ... n), set up Multivariate regression model and multiple nonlinear regression model (NLRM) respectively, and solve coefficient b
i,
Wherein Multivariate regression model is:
Y=XB+U (formula 1)
Wherein,
Multiple nonlinear regression model (NLRM) is:
Y=f [(b
1, b
2..., b
k); X
1, X
2..., X
n] (formula 2)
Wherein dependent variable Y is control sector runnability aggregative index, independent variable X is n item control sector runnability comprehensive detection index, m represents the control sector running performance index sample under the m group time interval, U is except m independent variable is on the stochastic error except the impact of dependent variable Y, Normal Distribution, f represents nonlinear solshing.
6. ATC controller workload Forecasting Methodology as claimed in claim 1, it is characterized in that, described step 3 specifically comprises:
According to the coefficient of determination R that each model returns
2value, F inspection, t inspection, verify respectively and compare degree of fitting, the conspicuousness of two kinds of regression models, on the obvious basis of, conspicuousness higher in model-fitting degree, calculate the metrical error of two kinds of regression models, and choose the minimum a kind of model of error, as the multiple regression model of ATC controller workload prediction.
7. ATC controller workload Forecasting Methodology as claimed in claim 1, is characterized in that, the real-time control sector transport air flow situation index in step 4 will carry out standardization conversion before input multiple regression model; Standardization transfer process is as follows:
According to the average of the n item index of the sample data in the m group time interval
variance s
j, to control sector transport air flow situation index t
j(j=1,2 ..., n) carry out standardization conversion:
by the data t after conversion
j' import in ATC controller workload prediction multiple regression model.
8. ATC controller workload Forecasting Methodology as claimed in claim 1, it is characterized in that, described method also comprises step 5, when ATC controller workload index exceeds threshold value, ATC controller workload response alarm.
9. a prognoses system for ATC controller workload, is characterized in that, comprises,
ATC controller workload forecast sample data corresponding for index of correlation are substituted in Multivariate regression model and multiple nonlinear regression model (NLRM) and carry out matching by construction part module: choose control sector transport air flow situation index; Obtain the estimates of parameters of Multivariate regression model and multiple nonlinear regression model (NLRM); By statistical test, calculate metrical error, determine ATC controller workload prediction multiple regression model;
Prediction module: by control sector transport air flow situation index prediction data importing ATC controller workload prediction multiple regression model, obtain predicting the outcome of ATC controller workload.
10. the prognoses system of ATC controller workload as claimed in claim 9, is characterized in that, also comprise, standardization modular converter: for carrying out standardization conversion to sample data and control sector transport air flow situation index real time data;
Alarm module: exceed threshold value when predicting the outcome, ATC controller workload response alarm.
The prognoses system of 11. ATC controller workloads as claimed in claim 10, it is characterized in that, also comprise control sector traffic flow situation Test database, the data be coupled with described control sector traffic flow situation Test database draw connection device and index collection device;
Described data are drawn connection device and are comprised the telegram data-interface, integrated track data-interface and the control speech data interface that are coupled with described control sector traffic flow situation Test database respectively;
Described index collection device is for gathering traffic flow situation index in control sector null, and described control sector transport air flow situation index comprises sector and runs road ability index, sector operation complexity profile, sector safety in operation index and sector performance driving economy index; Sector road ability Testing index comprises sector flow, sector shipping kilometre, sector hours underway and sector traffic flow density respectively; Sector complicacy Testing index comprise sector aircraft climb number of times, sector aircraft decline number of times, sector aircraft changes fast number of times, sector aircraft changes flight number number; Sector security Testing index comprises sector short term collision alert frequency and sector minimum safe altitude alert frequency; Sector economy Testing index comprises sector saturation degree, sector queue length, sector aircraft delay sortie rate, sector aircraft delay time at stop, sector aircraft mean delay time;
Described construction part module reads described ATC controller workload prediction index of correlation and ATC controller workload forecast sample data from described control sector traffic flow situation Test database; Described prediction module reads described control sector transport air flow situation index prediction data from described control sector traffic flow situation Test database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510645215.3A CN105205565A (en) | 2015-09-30 | 2015-09-30 | Controller workload prediction method and system based on multiple regression model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510645215.3A CN105205565A (en) | 2015-09-30 | 2015-09-30 | Controller workload prediction method and system based on multiple regression model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105205565A true CN105205565A (en) | 2015-12-30 |
Family
ID=54953234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510645215.3A Pending CN105205565A (en) | 2015-09-30 | 2015-09-30 | Controller workload prediction method and system based on multiple regression model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105205565A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944472A (en) * | 2017-11-03 | 2018-04-20 | 北京航空航天大学 | A kind of airspace operation situation computational methods based on transfer learning |
| CN108171379A (en) * | 2017-12-28 | 2018-06-15 | 无锡英臻科技有限公司 | A kind of electro-load forecast method |
| CN111091244A (en) * | 2019-12-16 | 2020-05-01 | 武汉材料保护研究所有限公司 | Engine lubricating oil change period prediction method |
| CN111126685A (en) * | 2019-12-16 | 2020-05-08 | 武汉材料保护研究所有限公司 | Method for establishing engine lubricating oil quality prediction model |
| CN111968414A (en) * | 2020-08-26 | 2020-11-20 | 成都民航空管科技发展有限公司 | 4D trajectory prediction method and device based on big data and AI and electronic equipment |
| CN114530059A (en) * | 2022-01-14 | 2022-05-24 | 南京航空航天大学 | Dynamic configuration method and system for multi-sector monitoring seat |
| CN117978916B (en) * | 2024-04-01 | 2024-05-28 | 中国民用航空飞行学院 | Method and equipment for predicting call load of controller |
-
2015
- 2015-09-30 CN CN201510645215.3A patent/CN105205565A/en active Pending
Non-Patent Citations (6)
| Title |
|---|
| 何元清 等: "《大学计算机基础》", 31 August 2013 * |
| 周品: "《MATLAB概率与数理统计》", 30 November 2012 * |
| 李鸿吉: "《Visual Basic 6.0数理统计实用算法》", 30 September 2003, 科学出版社 * |
| 袁霄 等: ""基于扇区动态复杂性因素的航空管制员工作负荷计算"", 《安全与环境学报》 * |
| 郭少英 等: "《市场调研与分析技术》", 31 October 2008 * |
| 麦好: "《机器学习实践指南 案例应用解析》", 30 April 2014 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944472B (en) * | 2017-11-03 | 2019-05-28 | 北京航空航天大学 | A kind of airspace operation situation calculation method based on transfer learning |
| CN107944472A (en) * | 2017-11-03 | 2018-04-20 | 北京航空航天大学 | A kind of airspace operation situation computational methods based on transfer learning |
| CN108171379B (en) * | 2017-12-28 | 2021-12-17 | 无锡英臻科技有限公司 | Power load prediction method |
| CN108171379A (en) * | 2017-12-28 | 2018-06-15 | 无锡英臻科技有限公司 | A kind of electro-load forecast method |
| CN111091244A (en) * | 2019-12-16 | 2020-05-01 | 武汉材料保护研究所有限公司 | Engine lubricating oil change period prediction method |
| CN111126685A (en) * | 2019-12-16 | 2020-05-08 | 武汉材料保护研究所有限公司 | Method for establishing engine lubricating oil quality prediction model |
| CN111126685B (en) * | 2019-12-16 | 2023-02-03 | 武汉材料保护研究所有限公司 | Method for establishing engine lubricating oil quality prediction model |
| CN111091244B (en) * | 2019-12-16 | 2023-02-03 | 武汉材料保护研究所有限公司 | Engine lubricating oil change period prediction method |
| CN111968414A (en) * | 2020-08-26 | 2020-11-20 | 成都民航空管科技发展有限公司 | 4D trajectory prediction method and device based on big data and AI and electronic equipment |
| CN111968414B (en) * | 2020-08-26 | 2022-08-05 | 成都民航空管科技发展有限公司 | 4D trajectory prediction method and device based on big data and AI and electronic equipment |
| CN114530059A (en) * | 2022-01-14 | 2022-05-24 | 南京航空航天大学 | Dynamic configuration method and system for multi-sector monitoring seat |
| CN114530059B (en) * | 2022-01-14 | 2023-03-10 | 南京航空航天大学 | Dynamic configuration method and system for multi-sector monitoring seat |
| CN117978916B (en) * | 2024-04-01 | 2024-05-28 | 中国民用航空飞行学院 | Method and equipment for predicting call load of controller |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105205565A (en) | Controller workload prediction method and system based on multiple regression model | |
| CN103530704B (en) | A kind of air dynamic traffic volume in terminal airspace prognoses system and method thereof | |
| CN104835354B (en) | A kind of control load management system and its appraisal procedure of ATC controller workload | |
| CN105160201A (en) | Genetic algorithm back propagation (GABP) neural network based controller workload prediction method and system | |
| CN105225539B (en) | The method and system of sector runnability composite index based on principal component analysis | |
| CN107146065A (en) | Railway engineering management platform system | |
| CN105261240B (en) | A kind of sector runnability method for comprehensive detection and system based on cluster analysis | |
| CN105225007A (en) | A kind of sector runnability method for comprehensive detection based on GABP neural network and system | |
| CN103489053A (en) | Intelligent water resource control platform based on cloud computing and expert system | |
| CN105225193A (en) | A kind of method and system of the sector runnability aggregative index based on multiple regression model | |
| CN113592128A (en) | Big data electric wire netting operation monitoring system | |
| CN105023228B (en) | A kind of passenger based on the flight for putting forth moment assembles monitoring system and monitoring method | |
| CN102306297A (en) | Method for measuring workload for air traffic controllers | |
| TWI604324B (en) | Performance evaluation system and method | |
| CN109190948B (en) | Correlation analysis method for operation of large-scale aviation hub and urban traffic jam | |
| Mott et al. | Estimation of aircraft operations at airports using nontraditional statistical approaches | |
| CN114237110A (en) | Multi-mode data driving-based general aviation fleet reliability monitoring and early warning system | |
| CN113793047A (en) | Pilot cooperative communication capacity evaluation method and device | |
| CN204856924U (en) | Control load management system | |
| CN105096661A (en) | Air traffic flow management system based on vertical profile view and method | |
| Diallo | A predictive aircraft landing speed model using neural network | |
| CN116128197A (en) | Intelligent airport management system and method | |
| CN116258381A (en) | Quantitative evaluation method and device for operation command work | |
| Zhang et al. | A genetic algorithm-based BP neural network method for operational performance assessment of ATC sector | |
| CN112947240A (en) | Intelligent numerical control platform of traction system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151230 |
|
| RJ01 | Rejection of invention patent application after publication |