CN105261241B - Air traffic control analog simulation method for detecting abnormality and device based on Hopfield neural network - Google Patents
Air traffic control analog simulation method for detecting abnormality and device based on Hopfield neural network Download PDFInfo
- Publication number
- CN105261241B CN105261241B CN201510645259.6A CN201510645259A CN105261241B CN 105261241 B CN105261241 B CN 105261241B CN 201510645259 A CN201510645259 A CN 201510645259A CN 105261241 B CN105261241 B CN 105261241B
- Authority
- CN
- China
- Prior art keywords
- index
- parameter
- sample
- control
- grade
- 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
Links
Abstract
The present invention provides a kind of air traffic control analog simulation method for detecting abnormality and device, and methods described includes：Step 1：The sample parameter that controller inputs is gathered by radar control analog machine, grade discrete type criteria for classification is determined；Step 2：According to the criteria for classification, grade discrete type classification is carried out to each sample parameter, and classification results are encoded, the corresponding sample composite index of each sample parameter is obtained；Step 3：The sample parameter and sample composite index classified based on grade discrete type, training obtains Hopfield neural network, and calculates the Hopfield neural network factor；Step 4：The real-time Simulation parameter that controller inputs is gathered by radar control analog machine；Step 5：The real-time Simulation parameter is classified according to grade discrete type, according to the Hopfield neural network, corresponding composite index is calculated；Step 6：If the composite index drawn in step 4 belongs to abnormal class, abnormality warnings are carried out.Therefore, it is possible to be detected to the analog parameter inputted in real time in controller in the air traffic control analog simulation abnormality detecting process, the corresponding classification of input parameter and abnormal operation prompting are detected accurately and in time.
Description
Technical field
The present invention relates to a kind of technical field of air traffic control, more particularly to a kind of air traffic control analog simulation
Method for detecting abnormality and device.
Background technology
In order to ensure all kinds of flying activities safety and in order, air traffic control service seems quite important.It is modern empty
Middle traffic control service is to the effect that：Air traffic controller relies on modern communicationses, navigation, surveillance technology, to administrative boat
Pocket is implemented management and controlled, and coordinates and instructs its motion path and pattern, to prevent aerial airborne vehicle and airborne vehicle from bumping against, with
And airborne vehicle bumps against with barrier in airdrome maneuver area, safeguards and accelerate the olderly flowage of air traffic.Air traffic control
Sector is the fundamental space unit of air traffic control, generally, the sky of air traffic control service is provided for airborne vehicle
Domain is delineated as some control sectors, each one controller's work seat of control sector correspondence.In order to ensure that controller can
Efficiently and accurately the airborne vehicle olderly flowage in controlled air space, provides some simulation air traffic control controls in the prior art
Simulation device and method.
For example, Chinese Patent Application No. is a kind of based on virtual tube to be disclosed in CN201410487083.1 patent application
The spatial domain emulation mode and its device of system person, this method includes：Obtain default flight plan and flight path conflict rule and wind bar
Part；If judgement knows that flight plan and flight path conflict rule are legal, aircraft performance data are obtained；According to flight plan, wind
Condition and aircraft performance data obtain the first trace information of airborne vehicle, and detect whether to receive control order；If detection
To control order, then according to aircraft performance data, flight path conflict rule and control order, flight path conflict statistics letter is obtained
Breath；If being not detected by control order, according to aircraft performance data, flight path conflict rule and the first trace information, obtain
Flight path conflict statistical information；So as to improve the real-time of emulation.
But in actual spatial domain control, it may appear that the problem of many unexpected, only by simulation of the prior art
Simulator and method, comprehensive, comprehensive simulating, the demand of detection are carried out to air traffic control process it is difficult to meet；And hair
A person of good sense has found that analog simulation method and device of the prior art can not point out control during the present invention is realized
Exception error information of the member in simulation process.
The content of the invention
In order to solve to lack in the prior art can to air traffic control process carry out comprehensively, comprehensive simulating, detection and
The technical problem of abnormal information prompting, the present invention provides a kind of sky that can well emulate, detect control human users' process
Middle traffic control analog simulation method for detecting abnormality and device.
To achieve these goals, the technical scheme that the present invention is provided includes：
On the one hand there is provided a kind of air traffic control analog simulation method for detecting abnormality, it is characterised in that this method bag
Include：
Step 1：The sample parameter that controller inputs is gathered by radar control analog machine, grade discrete type contingency table is determined
It is accurate；
Step 2：According to the criteria for classification, grade discrete type classification is carried out to each sample parameter, and classification is tied
Fruit is encoded, and obtains the corresponding sample composite index of each sample；
Step 3：The sample parameter and sample composite index classified based on grade discrete type, training obtain Hopfield god
Through network, and calculate the Hopfield neural network factor；
Step 4：The real-time Simulation parameter that controller inputs is gathered by radar control analog machine；
Step 5：The real-time Simulation parameter is classified according to grade discrete type, according to the Hopfield neural net
Network, calculates corresponding composite index；
Step 6：If the composite index drawn in step 5 belongs to abnormal class, abnormality warnings are carried out.
Further, the sample parameter and/or the real-time Simulation parameter include control road ability parameter, control complexity
Property parameter, control security parameters, directed economy parameter, control workload parameter.
Further, the control road ability parameter includes the duration, sector shipping kilometre, sector of controller's emulation testing
Hours underway, sector traffic current density, the control complexity parameter are climbed under number of times, sector airborne vehicle including sector airborne vehicle
Drop number of times, sector airborne vehicle change fast number of times, sector airborne vehicle and changed one's profession number of times, and the control security parameters are rushed in short term including sector
Prominent alert frequency, sector minimum safe altitude alert frequency, the directed economy parameter include the queuing of airborne vehicle in sector
Length, airborne vehicle delay sortie rate, airborne vehicle delay time at stop, airborne vehicle mean delay time, the control workload parameter
Including the empty talk channel occupancy in land, the empty talk times in land.
Further：The step 1 includes：
(1) 5 classification grades are set；The ratio of each classification grade is 1:2:4:2:1；
(2) the control road ability index and ATC controller workload index in sample parameter are proportionally 1:2:4:2:1
Descending is arranged；Control complexity profile, control safety indexes, directed economy index in sample parameter are proportionally 1:
2:4:2:1 ascending order is arranged；
(3) using the sample parameter index average value of each grade as the grade separation index critical value.
Further, the step 2 includes：
(1) when a certain index of sample data is better than the critical value of grade separation index, corresponding neuron state is set to
1, otherwise corresponding neuron state be set to -1；
(2) for control road ability index and ATC controller workload index, be more than when the value of input parameter index or
When person is equal to the critical value of a certain grade separation index, represent that the input parameter index is critical better than this grade separation index
Value；And for control complexity profile, control safety indexes, directed economy index, be less than when the value of input index or
When person is equal to the critical value of a certain grade separation index, represent that the input parameter index is critical better than this grade separation index
Value；
(3) composite index is the grade belonging to after all parameter level discrete types are classified.
Further, the Hopfield neural network in the step 3 is discrete type, is provided with two layers of neuron.
Further, real-time Simulation parameter includes according to the classification of grade discrete type in the step 5：
(1) when a certain index of real-time Simulation parameter is better than the critical value of grade separation index, corresponding neuron state
1 is set to, otherwise corresponding neuron state is set to -1；
(2) for control road ability index and ATC controller workload index, be more than when the value of input parameter index or
When person is equal to the critical value of a certain grade separation index, represent that the input parameter index is critical better than this grade separation index
Value；And for control complexity profile, control safety indexes, directed economy index, be less than when the value of input index or
When person is equal to the critical value of a certain grade separation index, represent that the input parameter index is critical better than this grade separation index
Value.
On the other hand, the present invention also provides a kind of air traffic control analog simulation abnormal detector, it is characterised in that
The device includes：
Radar control analog machine, the real-time analog data inputted for collecting sample data and controller；Wherein, the sample
Notebook data include radar control analog machine gather controller in sample parameter thereon, and by the sample parameter according to etc. it is grading
Row discrete type classification numerical value；
Data discrete processing unit, grade is carried out for the real-time analog data to the sample parameter and controller's input
Discrete type is classified；
Hopfield neural network unit, the sample parameter for being classified based on grade discrete type is referred to corresponding synthesis
Number builds Hopfield neural network；
Computing unit, for by Hopfield neural network, obtaining the real-time analog data correspondence of controller's input
Composite index.
Further, the air traffic control analog simulation abnormal detector is provided with alarm unit, for detecting
Abnormal composite index, carries out abnormality warnings.
Further, the air traffic control analog simulation abnormal detector is provided with limiting operation unit, and
Only after certification of the user by the limiting operation unit, the sample data could be changed.
The above-mentioned technical proposal provided using the present invention, can at least obtain following beneficial effect：
1st, the input/output relation that can be stablized by Hope's that moral neutral net combination sample parameter, can be to pipe
The analog parameter that system person inputs in traffic control analog simulation abnormality detecting process in real time in the air detected, in time, accurate
The corresponding classification of ground detection input parameter.Further, using Hopfield (Hopfield) neural network model, Ke Yishi
One-to-one emulation testing now is carried out to single controller, it is not necessary to multiple controllers are wanted in test process while operating to unite
Meter analysis.
2nd, by the way that classification in sample data is carried out into grade classification, the corresponding classification of real-time Simulation parameter can be calculated, because
This, can alert abnormal real-time Simulation parameter.
3rd, sample data is arranged to rewritable, controller can be allowed in the training process, oneself sets sample data,
More suitable sample data can be obtained；And can by priority assignation, can preferably management and control sample data, improve empty
Middle traffic control analog simulation abnormal detector friendly.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It is clear that or being understood by implementing technical scheme.The purpose of the present invention and other advantages can be by saying
Specifically noted structure and/or flow are realized and obtained in bright book, claims and accompanying drawing.
Brief description of the drawings
Fig. 1 is a kind of flow for air traffic control analog simulation method for detecting abnormality that the embodiment of the present invention one is related to
Figure；
Fig. 2 is a kind of structure chart for Hopfield neural network that the embodiment of the present invention one is related to；
Fig. 3 is a kind of block diagram for air traffic control analog simulation abnormal detector that the embodiment of the present invention one is related to；
Fig. 4 is a kind of flow for air traffic control analog simulation method for detecting abnormality that the embodiment of the present invention two is related to
Figure；
Fig. 5 is a kind of block diagram for air traffic control analog simulation abnormal detector that the embodiment of the present invention two is related to.
Embodiment
Describe embodiments of the present invention in detail below with reference to drawings and Examples, how the present invention is applied whereby
Technological means solves technical problem, and reaches the implementation process of technique effect and can fully understand and implement according to this.Need explanation
, these specific descriptions are to allow those of ordinary skill in the art to be more prone to, clearly understand the present invention, rather than to this hair
Bright limited explanation；As long as and not constituting each embodiment in conflict, the present invention and each spy in each embodiment
Levying to be combined with each other, and the technical scheme formed is within protection scope of the present invention.
In addition, the step of the flow of accompanying drawing is illustrated can a such as group controller executable instruction control system
It is middle perform, and, although logical order is shown in flow charts, but in some cases, can be with different from herein
Order performs shown or described step.
In order to make it easy to understand, in following description：Air traffic controller is referred to as " controller ", air traffic control letter
Referred to as " control ", air traffic control sector is referred to as " sector ".
Below by the drawings and specific embodiments, technical scheme is described in detail.
Embodiment one
As shown in figure 1, the present embodiment provides a kind of air traffic control analog simulation method for detecting abnormality, this method bag
Include：
S101, collecting sample and sample separation classification：
Controller is gathered by radar control analog machine to press in sample parameter thereon and composite index, and by sample parameter
Discrete type classification is carried out according to grade.
Preferably, sample parameter includes control road ability parameter, control complexity parameter, control security parameters, control
Economy parameter, control workload parameter.
Preferably, when control road ability parameter includes duration, sector shipping kilometre, the sector navigation of controller's emulation testing
Between, sector traffic current density, control complexity parameter including sector airborne vehicle climb number of times, sector airborne vehicle decline number of times, fan
Area's airborne vehicle changes fast number of times, sector airborne vehicle and changed one's profession number of times, and control security parameters include sector short term collision alert frequency, fan
Area's minimum safe altitude alert frequency, directed economy parameter includes the queue length of airborne vehicle in sector, airborne vehicle delay frame
Secondary rate, airborne vehicle delay time at stop, airborne vehicle mean delay time, control workload parameter include the empty talk channel in land and taken
Rate, the empty talk times in land.
16 parameters for choosing control analog simulation abnormality detection are analyzed, then each data point has 16 dimensions, can
It is designated as：
xi={ xi,j, j=1,2 ..., 16 }
Wherein, control road ability index is { xi,1,xi,2,xi,3,xi,4, controller's emulation testing duration, fan are represented respectively
Area's shipping kilometre, sector hours underway and sector traffic current density；Control complexity profile is { xi,5,xi,6,xi,7,xi,8, point
Not Biao Shi sector airborne vehicle climb number of times, sector airborne vehicle decline number of times, sector airborne vehicle changes fast number of times and airborne vehicle changes flight number
Number；Control safety indexes are { xi,9,xi,10, sector short term collision alert frequency and sector minimum safe altitude are represented respectively
Alert frequency；Directed economy index is { xi,11,xi,12,xi,13,xi,14, queue length, airborne vehicle delay sortie are represented respectively
Rate, airborne vehicle delay time at stop and airborne vehicle mean delay time；ATC controller workload index is { xi,15,xi,16, represent respectively
The empty talk times of land sky talk channel occupancy and land.
Wherein, controller's emulation testing duration refers to that controller completes the time that emulation testing is spent；In the navigation of sector
Journey refers to the summation for the airborne vehicle shipping kilometre that controller is commanded in emulation testing；Sector hours underway refers to that controller exists
The summation for the airborne vehicle hours underway commanded in emulation testing；Sector traffic current density be to controller in emulation testing institute
The airborne vehicle sortie dense degree of commander is estimated；The airborne vehicle number of times that climbs in sector refers to that controller is commanded in emulation testing
Airborne vehicle climb the summation of number of times；Sector airborne vehicle declines number of times and refers to the airborne vehicle that controller is commanded in emulation testing
Decline the summation of number of times；Sector airborne vehicle changes fast number of times and refers to the airborne vehicle speed change that controller is commanded in emulation testing
The summation of number of times；Sector airborne vehicle changes flight number number and refers to the airborne vehicle course change number of times that controller is commanded in emulation testing
Summation；Sector short term collision alert frequency refers to that controller produces time of airborne vehicle short term collision alert in emulation testing
Number；Sector minimum safe altitude alert frequency refers to that controller produces the alarm of airborne vehicle minimum safe altitude in emulation testing
Number of times；If the queuing situations such as wait that spiral occurs in airborne vehicle when entering sector, queuing airborne vehicle is defined as, definition is queued up
Length is the quantity of queuing airborne vehicle；Airborne vehicle delay sortie rate is the meter that flown in the delay sortie of airborne vehicle divided by emulation testing
The airborne vehicle quantity altogether drawn；The airborne vehicle delay time at stop is the republicanism of each airborne vehicle delay time at stop；During airborne vehicle mean delay
Between for airborne vehicle delay time at stop divided by the flight number of times that is delayed altogether；Land sky talk channel occupancy refers to controller in emulation testing
Duration inland sky duration of call accounting；Land sky talk times refer to the number of times of sky call in land in controller's emulation testing.
Wherein, radar control analog machine has the airborne vehicle motion simulation model of pinpoint accuracy and fidelity；Simulation is true
The man-machine interface of control system shows man-machine interface and optional there is provided the radar control of simulated real system and flight information, real
Show terminal regulation to show and operate and the at utmost emulation of real system；Have the characteristics that：
The whole nation or local spatial domain background atlas, Standard Flight process, flight plan etc. can be set up, training institute can be set
Meteorologic parameter such as radar type and parameter, ground and the weather clutter and wind that are related to, cloud etc..
Radar control training function, system can emulate list/Comprehensive Radar flight path, one/secondary radar point mark and flight path, flight
The various signals such as information, meteorologic information, notice to airmen, and the various training sections for meeting civil aviaton of China relevant regulations can be provided
Mesh；Extensive, a wide range of, comprehensive combined training can also be realized with Tower Simulator System Seamless integration-.
Digital voice communications and integrated automatic speech recognition synthesis system are provided, system realizes full digital emulation words
Sound communication system, and the automatic identification and response speech of control voice commands are realized by integrated speech identification and Compositing Engine
Be automatically synthesized function.
Patterned training overall process monitoring, control and record, radar control analog machine provide from start, start instruction
Practice, change training parameter, terminate training to the graphical monitoring of overall process for closing whole system and control, and can be complete to training
Process is recorded, and online rollback is carried out to training and is played back afterwards.
Radar control analog machine also provides the access and processing of actual signal, and the training mode based on actual signal,
System can receive and handle domestic various air Traffic Control radar datas, and current true air situation is presented in real time, can be by real-time or history
The radar and flight information data of record automatically extract and are converted to simulated training subject.
Preferably, the radar control analog machine 101 in the present embodiment is additionally provided with voice module, and the voice module 101 can
To gather or record time loss of the controller during operational radar control analog machine 101, it can thus gather
To analog simulation parameters such as the empty talk channel occupancy in land in control workload parameter, the empty talk times in land.It should be noted
Be that voice module can also be the specific installation being placed in radar control analog machine 101, and can be with radar control mould
Plan machine 101 is communicated.
Selected different grades of controller participates in radar simulation machine emulation testing, is adopted for the test process of every controller
Sample, obtains above-mentioned 16 input parameters of each sample.Meanwhile, organize senior control teacher to every controller in the emulation testing
Performance in journey carries out normal condition grade separation.Classification grade be Y=1,2,3,4,5, respectively represent state it is outstanding, good,
Normally, it is normal, abnormal.Sample index's data instance is as follows：
Table 1 is directed to certain controller's normal sample parameter of certain Simulation Test Environment
Then, the sample data corresponding to control road ability parameter and ATC controller workload parameter is arranged according to descending
Row, control complexity parameter, control security parameters, the sample data corresponding to directed economy parameter are arranged according to ascending order,
And according to 1:2:4:2:1 sample proportion divided rank, regard sample index's statistical average of each grade as Index grading
Standard, it is as shown in the table：
The controller of table 2 operates grading standard
In the present embodiment, the neural original state of Discrete Hopfield Neural Network only has 1 and -1 two kind, therefore by parameter
, it is necessary to be encoded when being mapped as the state of neuron.Coding rule is appointed as：When a certain supplemental characteristic " being better than " of controller
During the critical value of this index, for neuron state be set to " 1 ", be otherwise " -1 ".
And composite index refers to that controller operates whether last result exception or the index parameter such as does not meet.
Because the good and bad principle of different type index differs, defined herein " being better than " is：For control road ability index and
ATC controller workload index, when the value for detecting data is more than or equal to the critical value of a certain grading index value, table
Show that the detection data " are better than " critical value of this index；And passed through for control complexity profile, control safety indexes, control
Ji property index, when the value for detecting data is less than or equal to the critical value of a certain grading index value, represents the detection number
According to the critical value of " being better than " this index.
Table 3 lists the operational parameter data of a certain controller in certain emulation testing and encoded with grade.
The operation index data of a certain controller in certain emulation testing of table 3 are encoded with grade
S102, set up Hopfield neural network：
Hopfield (Hopfield) nerve net set up between sample parameter and hierarchical discrete type grouped data value
Network, and calculate the Hopfield neural network factor.Preferably, the training sample of controller's sample data and grade coding is obtained
After this collection, Discrete Hopfield Neural Network is created using the Neural Network Toolbox of MATLAB softwares.
As shown in Fig. 2 a kind of structural representation of Hopfield (Hopfield) neutral net provided for the present embodiment
Figure, it is preferable that Hopfield neural network is Scattered neuronal network；And the Hopfield neural network is provided with
Two layers of neuron；Wherein, in Hopfield neutral nets, the 0th layer is not actual neuron, is intended only as the input of network,
Without computing function；First layer performs the product to input information and weight coefficient and cumulative summation as neuron, and via non-
Output information is produced after linear function processing.
The present embodiment preferably, the suggestion process of Hopfield (Hopfield) neutral net：First according to above-mentioned table 1
In corresponding 16 sample parameters, carry out grade it is encoded translated after, it is possible to 16 parameters are converted into " 1 ", " -1 " respectively,
Then according to the corresponding composite index of sample data, i.e., whether last data are abnormal, can equally use " 1 ", and " -1 " is entered
Line flag；Then can be obtained by Hopfield (Hopfield) neutral net network factors (every neutral net plus
Weights)；Then it is also that 16 parameters first are carried out into grade coding respectively to turn during follow-up real-time Simulation parameter detecting
After alternatively, then by the network factors of Hopfield (Hopfield) neural network model calculate last composite index.
S103, the real-time Simulation parameter of collection controller's input：
Real-time Simulation parameter and progress discrete type grade that controller inputs thereon are gathered by radar control analog machine
Classification；Wherein, the data type that real-time Simulation parameter is included is identical with the parameter type of above-mentioned sample data, carries out discrete type etc.
The standard of level classification is also identical with sample data.
S104, the Hopfield neural network according to above-mentioned foundation, are calculated comprehensive after real-time Simulation parameter discretization
Hop index：
Real-time Simulation parameter is calculated after real-time Simulation parameter discretization according to the Hopfield neural network factor
Composite index.
On the other hand, as shown in figure 3, the present embodiment also provides a kind of air traffic control analog simulation abnormal detector
100, the device 100 includes：
Radar control analog machine 101, the real-time analog data inputted for collecting sample data and controller；Wherein, sample
Notebook data includes radar control analog machine 101 and gathers controller in sample parameter thereon and corresponding composite index, and by institute
State input parameter and carry out discrete type classification according to grade；
Data discrete processing unit 103, can be between the sample parameter and the corresponding discrete type numerical value of composite index
Set up Hopfield neural network；And classified and the factor in the Hopfield neural network by grade discrete type
Calculate the corresponding output integrated index of real-time analog data of controller's input.
Specifically, air traffic control analog simulation abnormal detector 100 passes through radar control mould during dispatching from the factory
Plan machine 101 sets predetermined parameter into sample data memory cell 102；And Hopfield neural network is according to sample
Data, which obtain network factors, directly to be calculated by Matlab softwares, be collectively stored in sample data memory cell.
The above-mentioned technical proposal provided using the present embodiment, can at least obtain following beneficial effect：
The input/output relation that can be stablized by Hope's that moral neutral net combination sample parameter, can be to control
The analog parameter that member inputs in traffic control analog simulation abnormality detecting process in real time in the air detected, accurately and in time
Detect the corresponding classification of input parameter.Further, using Hopfield (Hopfield) neural network model, it is possible to achieve
One-to-one emulation testing is carried out to single controller, it is not necessary to multiple controllers are wanted in test process while operating to count
Analysis.
Embodiment two
As shown in figure 4, embodiment two is on the basis of embodiment one, traffic control analog simulation abnormality detection side in the air
Step S407, warning prompt are added in method：
The step of being alerted in data value after real-time Simulation parameter discretization the classification of specific grade.
Preferably, the classification of grade where specific grade refers to after the corresponding discretization of exceptional sample parameter；If managed
If data after the real-time Simulation parameter discretization that system person inputs on radar control analog machine and abnormal sample data from
Value after dispersion decides that operation exception of the controller on radar control analog machine, it is necessary to be alerted in a class
Prompting.
As shown in figure 5, on the basis of embodiment two is relative to embodiment one, traffic control analog simulation is examined extremely in the air
Survey in device and add alarm unit, it is preferable that alarm unit can warn different sound according to discrete type classification species；Its
In, the alarm unit can be the voice playing unit for being provided with loudspeaker, or be the suggestion device of specific sound, such as buzzing
Device.
The above-mentioned technical proposal provided using the present embodiment, can at least obtain following beneficial effect：
By the way that classification in sample data is carried out into grade classification, the corresponding classification of real-time Simulation parameter can be calculated, therefore,
Abnormal real-time Simulation parameter can be alerted.
Embodiment three
Embodiment three is on the basis of embodiment one or embodiment two further to air traffic control analog simulation
Abnormal detector is optimized, specifically：
Sample data is in the air rewritable parameter in traffic control analog simulation abnormal detector；Further,
Air traffic control analog simulation abnormal detector is provided with limiting operation unit, and only when user passes through limiting operation
After the certification of unit, sample data could be changed.
The above-mentioned technical proposal provided using the present embodiment, can at least obtain following beneficial effect：
Sample data is arranged to rewritable, controller can be allowed in the training process, oneself sets sample data, can
To obtain more suitable sample data；And can by priority assignation, can preferably management and control sample data, improve aerial
Traffic control analog simulation abnormal detector friendly.
Finally it should be noted that described above is only highly preferred embodiment of the present invention, not the present invention is appointed
What formal limitation.Any those skilled in the art, it is without departing from the scope of the present invention, all available
The way and technology contents of the disclosure above make many possible variations and simple replacement etc. to technical solution of the present invention, these
Belong to the scope of technical solution of the present invention protection.
Claims (10)
1. a kind of air traffic control analog simulation method for detecting abnormality, it is characterised in that including：
Step 1：The sample parameter that controller inputs is gathered by radar control analog machine, grade discrete type criteria for classification is determined；
Step 2：According to the criteria for classification, grade discrete type classification is carried out to each sample parameter, and classification results are entered
Row coding, obtains the corresponding sample composite index of each sample parameter；
Step 3：The sample parameter and sample composite index classified based on grade discrete type, training obtain Hopfield neural net
Network, and calculate the Hopfield neural network factor；
Step 4：The real-time Simulation parameter that controller inputs is gathered by radar control analog machine；
Step 5：The real-time Simulation parameter is classified according to grade discrete type, according to the Hopfield neural network, meter
Calculate corresponding composite index；
Step 6：If the composite index drawn in step 5 belongs to abnormal class, abnormality warnings are carried out.
2. according to the method described in claim 1, it is characterised in that the sample parameter and/or the real-time Simulation parameter bag
Include control road ability parameter, control complexity parameter, control security parameters, directed economy parameter, control workload ginseng
Number.
3. method according to claim 2, it is characterised in that the control road ability parameter includes controller's emulation testing
Duration, sector shipping kilometre, sector hours underway, sector traffic current density, the control complexity parameter include sector boat
Climb number of times, sector airborne vehicle of pocket declines number of times, sector airborne vehicle and changes fast number of times, sector airborne vehicle and change one's profession number of times, the pipe
Security parameters processed include sector short term collision alert frequency, sector minimum safe altitude alert frequency, the directed economy
Parameter includes the queue length of airborne vehicle in sector, airborne vehicle delay sortie rate, airborne vehicle delay time at stop, airborne vehicle mean delay
Time, the control workload parameter includes the empty talk channel occupancy in land, the empty talk times in land.
4. method as claimed in claim 2, it is characterised in that：The step 1 includes：
(1) 5 classification grades are set；The ratio of each classification grade is 1:2:4:2:1；
(2) the control road ability index and ATC controller workload index in sample parameter are proportionally 1:2:4:2:1 descending
Arrangement；Control complexity profile, control safety indexes, directed economy index in sample parameter are proportionally 1:2:4:
2:1 ascending order is arranged；
(3) using the sample parameter index average value of each grade as the grade separation index critical value.
5. method as claimed in claim 4, it is characterised in that the step 2 includes：
(1) when a certain index of sample data is better than the critical value of grade separation index, corresponding neuron state is set to 1, no
Then corresponding neuron state is set to -1；
(2) for control road ability index and ATC controller workload index, when the value of input parameter index is more than or waits
When the critical value of a certain grade separation index, represent that the input parameter index is better than the critical value of this grade separation index；
And for control complexity profile, control safety indexes, directed economy index, when the value of input index is less than or waits
When the critical value of a certain grade separation index, represent that the input parameter index is better than the critical value of this grade separation index；
(3) composite index is the grade belonging to after parameter level discrete type is classified.
6. according to the method described in claim 1, it is characterised in that the Hopfield neural network in the step 3 be from
Type is dissipated, two layers of neuron is provided with.
7. the method as described in claim 1, it is characterised in that real-time Simulation parameter is according to grade discrete type in the step 5
Classification includes：
(1) when a certain index of real-time Simulation parameter is better than the critical value of grade separation index, corresponding neuron state is set to
1, otherwise corresponding neuron state be set to -1；
(2) for control road ability index and ATC controller workload index, when the value of input parameter index is more than or waits
When the critical value of a certain grade separation index, represent that the input parameter index is better than the critical value of this grade separation index；
And for control complexity profile, control safety indexes, directed economy index, when the value of input index is less than or waits
When the critical value of a certain grade separation index, represent that the input parameter index is better than the critical value of this grade separation index.
8. a kind of air traffic control analog simulation abnormal detector, it is characterised in that the device includes：Radar control is simulated
Machine, the real-time analog data inputted for collecting sample data and controller；Wherein, the sample data includes radar control mould
Plan machine gathers controller in sample parameter thereon, and the sample parameter is carried out into discrete type classification numerical value according to grade；
Data discrete processing unit, carries out grade discrete for the real-time analog data to the sample parameter and controller's input
Type is classified；
Hopfield neural network unit, for sample parameter and the corresponding composite index structure classified based on grade discrete type
Build Hopfield neural network；
Computing unit, for by Hopfield neural network, the real-time analog data for obtaining controller's input to be corresponding comprehensive
Hop index.
9. device according to claim 8, it is characterised in that the air traffic control analog simulation abnormal detector
Alarm unit is provided with, for detecting abnormal composite index, abnormality warnings are carried out.
10. device according to claim 9, it is characterised in that the air traffic control analog simulation abnormality detection dress
Install and be equipped with limiting operation unit, and only could change institute after certification of the user by the limiting operation unit
State sample data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510645259.6A CN105261241B (en) | 2015-09-30 | 2015-09-30 | Air traffic control analog simulation method for detecting abnormality and device based on Hopfield neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510645259.6A CN105261241B (en) | 2015-09-30 | 2015-09-30 | Air traffic control analog simulation method for detecting abnormality and device based on Hopfield neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105261241A CN105261241A (en) | 2016-01-20 |
| CN105261241B true CN105261241B (en) | 2017-11-07 |
Family
ID=55100906
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510645259.6A Active CN105261241B (en) | 2015-09-30 | 2015-09-30 | Air traffic control analog simulation method for detecting abnormality and device based on Hopfield neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105261241B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114664121B (en) * | 2022-03-23 | 2024-01-09 | 合肥置顶信息技术有限公司 | Intelligent error correction civil aviation meteorological observation making and publishing system and method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102456158A (en) * | 2010-10-26 | 2012-05-16 | 中国民航大学 | Security assessment method for air traffic management (ATM) information system based on ANNBP (Artificial Neural Network Blood Pressure) model |
| CN102749573A (en) * | 2012-07-27 | 2012-10-24 | 重庆大学 | Analog circuit fault diagnosis method based on wavelet packet analysis and Hopfield network |
| DE102012104391A1 (en) * | 2012-05-22 | 2013-11-28 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Air traffic control system |
| KR20140092433A (en) * | 2012-12-27 | 2014-07-24 | 인하대학교 산학협력단 | Air traffic control integrated system |
| CN104252797A (en) * | 2014-09-22 | 2014-12-31 | 北京航空航天大学 | Virtual controller-based airspace simulation method and device thereof |
| CN104363134A (en) * | 2014-11-11 | 2015-02-18 | 成都民航空管科技发展有限公司 | Control transferring simulation test method, device and system of air traffic control automation system |
-
2015
- 2015-09-30 CN CN201510645259.6A patent/CN105261241B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102456158A (en) * | 2010-10-26 | 2012-05-16 | 中国民航大学 | Security assessment method for air traffic management (ATM) information system based on ANNBP (Artificial Neural Network Blood Pressure) model |
| DE102012104391A1 (en) * | 2012-05-22 | 2013-11-28 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Air traffic control system |
| CN102749573A (en) * | 2012-07-27 | 2012-10-24 | 重庆大学 | Analog circuit fault diagnosis method based on wavelet packet analysis and Hopfield network |
| KR20140092433A (en) * | 2012-12-27 | 2014-07-24 | 인하대학교 산학협력단 | Air traffic control integrated system |
| CN104252797A (en) * | 2014-09-22 | 2014-12-31 | 北京航空航天大学 | Virtual controller-based airspace simulation method and device thereof |
| CN104363134A (en) * | 2014-11-11 | 2015-02-18 | 成都民航空管科技发展有限公司 | Control transferring simulation test method, device and system of air traffic control automation system |
Non-Patent Citations (2)
| Title |
|---|
| 基于BP网络的空中交通管制运行品质评价;张建平 等;《西南交通大学学报》;20130630;第48卷(第3期);第553-558页 * |
| 基于Hopfield神经网络的中考达线等级预测模型;李静 等;《山西电子技术》;20130228(第1期);第6-8页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105261241A (en) | 2016-01-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Majumdar et al. | Factors affecting air traffic controller workload: Multivariate analysis based on simulation modeling of controller workload | |
| CN103530704B (en) | A kind of air dynamic traffic volume in terminal airspace prognoses system and method thereof | |
| Stroeve et al. | Contrasting safety assessments of a runway incursion scenario: Event sequence analysis versus multi-agent dynamic risk modelling | |
| CN105531748B (en) | Landing judges that accessory system, landing judge that householder method and landing judge auxiliary program | |
| CN107818396A (en) | For changing the decision assistant of flight plan | |
| Herrema et al. | A machine learning model to predict runway exit at Vienna airport | |
| CN105261240B (en) | A kind of sector runnability method for comprehensive detection and system based on cluster analysis | |
| CN110060513A (en) | Workload for air traffic controllers appraisal procedure based on historical trajectory data | |
| Majumdar et al. | Estimation of European airspace capacity from a model of controller workload | |
| CN108475445A (en) | The method and system of the automation fusion and analysis of multi-source aircraft data | |
| CN106023655A (en) | Sector air traffic congestion state monitoring method | |
| CN105956790A (en) | Low-altitude flight situation safety evaluation indexes and evaluation method thereof | |
| CN105118333B (en) | A kind of air traffic control analog simulation method for detecting abnormality and device based on multiple regression model | |
| CN107067823A (en) | The computational methods and device of a kind of low coverage parallel runways capacity | |
| CN107239905A (en) | Onboard networks safety risk estimating method based on advanced AHP GCM | |
| CN105118332A (en) | Air traffic control analog simulation abnormality detection method and device based on clustering analysis method | |
| Gillet et al. | Enhancement in realism of ATC simulations by improving aircraft behaviour models | |
| CN105261241B (en) | Air traffic control analog simulation method for detecting abnormality and device based on Hopfield neural network | |
| CN111175852B (en) | Airport fog forecast early warning method based on long-time memory algorithm | |
| CN105303898B (en) | A kind of air traffic control analog simulation method for detecting abnormality and device based on principal component analysis | |
| CN110349444A (en) | Air traffic flow management method based on big data | |
| CN106529835A (en) | Daily traffic capacity determining method and device of terminal area | |
| CN117035187A (en) | Pilot operation behavior prediction model construction method and system | |
| Sun et al. | A method of analysis integrating HCR and ETA modeling for determining risks associated with inadequate flight separation events | |
| Raballand et al. | DROSERA: A DROne Simulation Environment for Risk Assessment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |