CN108805337A - Aviation operation is controlled risk management-control method and system - Google Patents
Aviation operation is controlled risk management-control method and system Download PDFInfo
- Publication number
- CN108805337A CN108805337A CN201810486745.1A CN201810486745A CN108805337A CN 108805337 A CN108805337 A CN 108805337A CN 201810486745 A CN201810486745 A CN 201810486745A CN 108805337 A CN108805337 A CN 108805337A
- Authority
- CN
- China
- Prior art keywords
- flight
- risk
- predicted
- typical
- expert
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 84
- 241001269238 Data Species 0.000 claims abstract description 9
- 238000013349 risk mitigation Methods 0.000 claims description 23
- 238000010801 machine learning Methods 0.000 claims description 20
- 230000010006 flight Effects 0.000 claims description 12
- 238000012986 modification Methods 0.000 claims description 12
- 230000004048 modification Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 238000010207 Bayesian analysis Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 230000007613 environmental effect Effects 0.000 description 15
- 238000012502 risk assessment Methods 0.000 description 11
- 230000000694 effects Effects 0.000 description 8
- 238000013480 data collection Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000004576 sand Substances 0.000 description 4
- 238000013210 evaluation model Methods 0.000 description 3
- 230000000116 mitigating effect Effects 0.000 description 3
- 230000001052 transient effect Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 231100001261 hazardous Toxicity 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000033001 locomotion Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000013058 risk prediction model Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000001568 sexual effect Effects 0.000 description 1
- 235000015170 shellfish Nutrition 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G06Q50/40—
Abstract
The present invention provides a kind of aviation operation and controls risk management-control method and system, the method includes：Obtain the risk factors information of flight to be predicted；By in the risk factors information input of the flight to be predicted to the flight risk forecast model pre-established, the risk profile value of the flight to be predicted is obtained；Wherein, the flight risk forecast model is determined according to the risk factors information of the flight in multiple historical datas and according to expert's risk score of the flight in each historical data；If the risk profile value of the flight to be predicted is more than preset risk threshold value, risk management and control is carried out to the flight to be predicted.This method and system make full use of history flight data and expertise, can more accurately and timely assess flight risk.
Description
Technical field
The present invention relates to Risk-warning technical fields, and in particular to a kind of aviation operation, which is controlled risk, management-control method and is
System.
Background technology
Flight operation control risk assessment be airline flight dispatch work important content, and while being assessed, is involved
And risk factors huge number, enormous amount, analysis difficulty it is big.Domestic commerce aviation industry is in rapid growth rank at present
Section, but assessment is controlled risk there is still a need for the experience for relying on dispatch personnel individual and to the sensitivity of risk for flight operation
Degree is used as without coherent reference standard and corrects, especially rapid in change of external conditions, when many factors superposition, no
Conducive to making accurate, timely, objective risk assessment.Meanwhile the risk for recognizing, it is still to rely on personal experience at present
Carry out risk mitigation；So when there are the different same risks of personnel's processing, measure and the effect of risk mitigation may not
Together.Therefore it is particularly significant for the development of aviation industry effectively to run managing and control system of controlling risk for construction.
It is sparse for flight risk assessment casualty data true in this way and along with the different accident origin causes of formation and generation environment
The problem of, researcher is usually studied using two methods：The possibility that a certain event occurs is obtained by consultant expert
And confidence level；There is dangerous possibility in the risk case assessment practical flight recorded by onboard flight data logger
Property.For the expertise that can carry out risk assessment, mainly risky tree, risk are related for the risk model that airline uses
Factor matrix, Bayesian network assessment models.Wherein risk tree, Risk factors matrix method are similar to and store in systems
Model predicted, process more mechanization by comparison, complicated reciprocal effect in no calligraphy learning to expertise.Pattra leaves
This network evaluation model carries out merely the setting of conditional probability, it is difficult to when covering flight risk assessment between multivariable factor extensively
And complicated interaction scenario.Mainly having gauss hybrid models and combine knot of tissue in view of historical data and expertise simultaneously
The mixed risk assessment models of structure factor.It is guidance that gauss hybrid models, which give with the actual event data of past flight, right
The method for the abnormal flight of detection that risk variable is clustered, but for abnormal flight, there is still a need for experts further to examine,
The efficiency of model is not high enough, while being easy to omit high risk flight.In conjunction with the mixed risk assessment models master of organization structure factor
The risk contribution calculation that use tree, combines more factors in terms of level.Above-mentioned model form is excessively single,
It is concentrated mainly on level Risk Calculation, establishing in terms of expertise system is not comprehensive enough true, and for the practical hair of history
The application of raw hazard event data ignores the randomness of event generation, does not fully consider risk factors itself, is unfavorable for
Obtain accurate risk evaluation result.
Invention content
In view of the deficiencies of the prior art, the present invention provides a kind of aviation operation and controls risk management-control method and system.
The management-control method in a first aspect, a kind of aviation operation of offer of the embodiment of the present invention is controlled risk, the method includes：
Obtain the risk factors information of flight to be predicted；
By in the risk factors information input of the flight to be predicted to the flight risk forecast model pre-established, obtain
To the risk profile value of the flight to be predicted；Wherein, the flight risk forecast model is according in multiple historical datas
What the risk factors information of flight and expert's risk score of the flight in preset each historical data determined；
If the risk profile value of the flight to be predicted is more than preset risk threshold value, the flight to be predicted is carried out
Risk management and control.
Second aspect, the embodiment of the present invention provide a kind of aviation operation and control risk managing and control system, the system comprises：
Acquisition module, the risk factors information for obtaining flight to be predicted；
Risk profile module, for by the risk factors information input of the flight to be predicted to the flight pre-established
In risk forecast model, the risk profile value of the flight to be predicted is obtained；Wherein, the flight risk forecast model is basis
The risk factors information of flight in multiple historical datas and the flight in preset each historical data it is special
Family's risk score determines；
Risk mitigation module is right if the risk profile value for the flight to be predicted is more than preset risk threshold value
The flight to be predicted carries out risk management and control.
The third aspect, the embodiment of the present invention provide a kind of electronic equipment, and the equipment includes memory and processor, described
Processor and the memory complete mutual communication by bus；The memory, which is stored with, to be executed by the processor
Program instruction, the processor calls described program instruction to be able to carry out above-mentioned aviation operation and controls risk management-control method.
Fourth aspect, the embodiment of the present invention provide a kind of computer readable storage medium, are stored thereon with computer program,
The computer program realizes that above-mentioned aviation operation is controlled risk management-control method when being executed by processor.
Aviation operation provided in an embodiment of the present invention is controlled risk management-control method and system, is passed through and is obtained flight to be predicted
Risk factors information, by the risk factors information input of flight to be predicted to the flight risk forecast model pre-established,
The risk profile value of flight to be predicted is obtained, if the risk profile value of flight to be predicted is more than preset risk threshold value, is treated
Predict that flight carries out risk management and control.This method and system make full use of history flight data and expertise, can it is more accurate,
Flight risk is assessed in time.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is that aviation operation provided in an embodiment of the present invention is controlled risk the flow chart of management-control method；
Fig. 2 is that aviation operation provided in an embodiment of the present invention is controlled risk management-control method schematic diagram；
Fig. 3 is that aviation operation provided in an embodiment of the present invention is controlled risk the structural schematic diagram of managing and control system；
Fig. 4 is the structural schematic diagram of electronic equipment provided in an embodiment of the present invention.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical solution in the embodiment of the present invention carries out clear, complete description, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
The every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Fig. 1 is that aviation operation provided in an embodiment of the present invention is controlled risk the flow chart of management-control method, as shown in Figure 1, institute
The method of stating includes：
Step 10, the risk factors information for obtaining flight to be predicted；
Step 11, by the risk factors information input of the flight to be predicted to the flight risk profile mould pre-established
In type, the risk profile value of the flight to be predicted is obtained；Wherein, the flight risk forecast model is according to multiple history numbers
Expert's risk score of the risk factors information of flight in and the flight in preset each historical data
Determining；
If step 12, the risk profile value of the flight to be predicted are more than preset risk threshold value, to described to be predicted
Flight carries out risk management and control.
Specifically, system can obtain the risk factors information of flight to be predicted first.Wherein, risk factors information can be with
It is the Flight Information of the value-at-risk that can influence flight to be predicted determined according to expertise.
For example, may include following environmental information according to the risk factors information that expertise determines.In flight takeoff rank
Section, risk factors information may include：Against the wind standard, with the wind standard, crosswind standard (dry runway), crosswind standard (wet runway),
Visibility standards, cloud level standard, crosswind, against the wind, with the wind, wet runway, visibility, the cloud level, sand, wind shear, snow, rain, thunder, ice
Hail, high-altitude aerodrome, high high-altitude aerodrome, special airport, complicated airport, airfield runway quantity, dash road, the runway gradient, international machine
Field, socked-in remaining, airport busy extent and blank pipe communication difficult degree, night flight and the new environmental informations such as airport of setting sail.
In flight landing phases, risk factors information may include：Standard, with the wind standard, (the dry race of crosswind standard against the wind
Road), crosswind standard (wet runway), visibility standards, cloud level standard, crosswind, against the wind, with the wind, wet runway, visibility, the cloud level, raise
It is sand, wind shear, snow, rain, thunder, hail, high-altitude aerodrome, high high-altitude aerodrome, special airport, complicated airport, airfield runway quantity, short
Runway, the runway gradient, International airport, socked-in remaining, airport busy extent, with blank pipe communication difficult degree, night flight, newly open
Plane field and into environmental informations such as nearly landing procedure types.
After system gets the risk factors information of flight to be predicted, the flight pre-established can be entered into
In risk forecast model, which can export the value-at-risk of flight to be predicted, can remember the value-at-risk
For risk profile value.Wherein, flight risk forecast model can be according to the risk factors information of the flight in multiple historical datas
And expert's risk score of the flight in preset each historical data determines.Wherein, expert's risk score can be
Can also be according to dependency number according to the risk score that the risk factors information and expertise of the flight in historical data obtain
According to the scoring with professional reference value of COMPREHENSIVE CALCULATING, can also be by other means acquisition there is practical guidance to refer to
The scoring of meaning.
Then, the risk profile value of flight to be predicted can be compared by system with preset risk threshold value, if wind
Dangerous predicted value is more than risk threshold value, then system can carry out risk management and control to the flight to be predicted.
System can also obtain flight to be predicted and take new risk factors information after risk management and control, by new risk
Factor information is input in flight risk forecast model, new flight risk profile value is obtained, with the effect of detection risk management and control.
Aviation operation provided in an embodiment of the present invention is controlled risk management-control method, by obtain the risk of flight to be predicted because
Prime information is waited in the risk factors information input of flight to be predicted to the flight risk forecast model pre-established
The risk profile value of flight is predicted, if the risk profile value of flight to be predicted is more than preset risk threshold value, to boat to be predicted
Class carries out risk management and control.This method makes full use of history flight data and expertise, can be more accurately and timely to flight
Risk is assessed, and reliable reference is provided for the risk assessment work of dispatch person.
Optionally, on the basis of the above embodiments, the method further includes the foundation of the flight risk forecast model
Process, the process of establishing include：
Obtain the first typical flight sample data set；Wherein, the described first typical flight sample data set includes：Multiple allusion quotations
Expert's risk score of the risk factors information of type flight and each typical flight；Wherein, expert risk score obtains
The method is taken to include：Using the method for adaptive sampling, is chosen from multiple flights and default journey is more than to model foundation percentage contribution
Then the flight of degree threshold value is ranked up the flight chosen according to percentage contribution from high to low, obtain each boat in batches
Expert's risk score of class；
The described first typical flight sample data set is learnt using machine learning method, obtains the flight risk
Prediction model.
Specifically, the flight risk forecast model described in above-described embodiment to establish process specific as follows.
System can obtain the first typical flight sample data set first, as the training for establishing flight risk forecast model
Sample.First, according to expertise determination may to the environmental factor that flight risk has an impact, secondly, using clustering algorithm,
To may respectively be handled the continuous variable and discrete variable that flight risk has an impact in environmental risk factor, from flight history
The flight data collection for including main real situation is obtained in data, constitutes the true flight in historical data；It is added simultaneously and includes
The flight of preset extreme environment information and the fresh typical flight of the others occurred less are as virtual flight.Using adaptive sampling
Method, from multiple flights choose to model foundation percentage contribution be more than predeterminable level threshold value flight, the fortune of this kind of flight
Row data are larger to the contribution degree of model foundation, wherein predeterminable level threshold value can specifically be set according to expertise.So
Afterwards, the flight chosen is ranked up according to the sequence of percentage contribution from high to low, obtains the expert of each flight in batches
Risk score obtains the of the risk factors information comprising multiple typical flights and expert's risk score of each typical flight
One typical flight sample data set, can reduce marking cost in this way.
Wherein, expert's risk score acquisition methods include：Marking rule, marking sample set obtain and marking interface.
Marking rule can be ranked up flight to limit the flight number of every batch of marking according to single or multiple risk factors, complete
Marking is submitted after the marking of this batch flight as a result, carrying out the marking of next batch flight or stopping marking；Marking sample set acquisition is adopted
With dynamic sampling method, after every wheel is given a mark, high score is preferentially found in flight sample set or scoring is uncertain big
Flight, for the sample of marking, stops as next round when promoting sufficiently small to model accuracy caused by new assessed value
It only samples, this dynamic approach can give a mark to the representative flight for all taking off or landing；Marking interface
In, include all Flight Informations of this batch of the information of every flight of sub-category displaying and comparison displaying, relatively hazardous flight
Risk factors highlight, all flight risk profile value real-time displays of this batch.
After getting the first typical flight sample data set, suitable flight risk assessment application scene may be used in system
With the machine learning method of data characteristics, learnt using the first typical flight sample data set.The machine learning method energy
Sparse data is enough utilized, explains the non-linear relation between flight value-at-risk and multiple risk factors, and tolerable risk factor
Between there is complicated reciprocation, meanwhile, using expertise rejecting abnormalities data, prevent model over-fitting.By
Habit process, system can provide risk profile function and risk factors contribution degree anticipation function, provide formula to flight to be predicted
Risk profile value calculated, to establish flight risk forecast model.
Aviation operation provided in an embodiment of the present invention is controlled risk management-control method, is passed through and is obtained the first typical flight sample number
According to collection, is learnt using the typical flight sample data set of machine learning method pair first, obtain flight risk forecast model, it should
Method can make full use of history flight data and expertise, provide more accurate, timely flight risk evaluation model.
Optionally, on the basis of the above embodiments, it is described further include the flight risk forecast model renewal process,
The renewal process includes：
The difference for obtaining risk profile value and expert's risk score in preset time period is more than the newly-increased flight of predetermined threshold value
Risk factors information and each newly-increased flight expert's risk score, as the second typical flight sample data set；
Using Bayesian analysis method, according to flight risk profile mould described in the described second typical flight sample data set pair
Type is updated；
Or
Using machine learning method, to the described first typical flight sample data set and the second typical flight sample number
The population sample data set constituted according to collection is learnt, and updated flight risk forecast model is obtained.
Specifically, system can also be updated the flight risk forecast model in above-described embodiment.
The difference that system can obtain risk profile value and expert's risk score in preset time period is more than predetermined threshold value
Expert's risk score of the risk factors information of newly-increased flight and each newly-increased flight, as the second typical flight sample data
Collection.After system gets the second typical flight sample data set, Bayesian analysis method may be used, according to the second typical boat
Class's sample data set pair flight risk forecast model is updated.According to specific method using Bayesian analysis more new model
The form of risk facior data when the hazard event that sensor obtains occurs and distribution, are inhaled by various forms of likelihood equations
Different types of new data is received, constantly updates the model parameter in flight risk forecast model with correction model.
System can also use machine learning method, to the first typical sample flight notebook data collection and the second typical flight sample
The population sample data set that data set is constituted is learnt, and updated flight risk forecast model is obtained.
Aviation operation provided in an embodiment of the present invention is controlled risk management-control method, and the risk obtained in preset time period is passed through
The difference of predicted value and expert's risk score is described newly-increased more than the risk factors information of the newly-increased flight of predetermined threshold value and each
Expert's risk score of flight, as the second typical flight sample data set, using Bayesian analysis method, according to the second typical case
Flight sample data set pair flight risk forecast model is updated, or uses machine learning method, to the first typical flight
The population sample data set that sample data set and the second typical flight sample data set are constituted is learnt, and updated boat is obtained
Class's risk forecast model.This method can utilize history flight data and expertise to accumulate, continuous updating and expansion flight wind
Dangerous prediction model so that the method is more accurate.
Optionally, on the basis of the above embodiments, the flight of the described first typical flight sample data concentration includes：It goes through
True flight in history data and virtual flight, wherein the true flight in historical data is to use clustering algorithm, is transported to flight
What the flight operation data in row database was screened；The virtual flight refers to including preset for improving flight
The flight of the extreme environment information of risk and other fresh typical flights occurred less.
Specifically, the flight of first typical case's flight sample data concentration described in above-described embodiment may include：History
True flight in data and virtual flight.True flight in historical data is to use clustering algorithm, to flight operation data
What the flight operation data in library was screened, virtual flight can be according to expertise be arranged include preset pole
The flight for holding environmental information, can also be other fresh typical flights occurred less, the environmental information of these flights can improve boat
The risk of class.
For example, virtual flight can be flight when there is hail, heavy rain or heavy snow weather, and occur following extreme
The flight of environmental factor information combination：Special airport or high high-altitude aerodrome and moderate rain；Special airport or high high-altitude aerodrome and moderate snow；
High-altitude aerodrome, wet runway with the wind 4 sections it is above drop to high high-altitude aerodrome flight and dry runway with the wind 6 sections it is above drop to height
High-altitude aerodrome flight.
Aviation operation provided in an embodiment of the present invention is controlled risk management-control method, by the first typical flight sample data
The flight of concentration include into historical data true flight and virtual flight, can expand flight risk forecast model be applicable in
Range so that the method more science.
Optionally, on the basis of the above embodiments, it is preset if the risk profile value of the flight to be predicted is more than
Risk threshold value, then risk management and control is carried out to the flight to be predicted, including：
If the risk profile value of the flight to be predicted is more than preset risk threshold value, preset expert's wind is obtained
Dangerous mitigation strategy, and the risk of the flight to be predicted is alleviated according to expert's risk mitigation measure.
Specifically, if the risk profile value of flight to be predicted is more than risk threshold value, system can be obtained and be preset
Good expert's risk mitigation measure, and the risk of flight to be predicted is delayed according to the expert's risk mitigation measure got
Solution.
System can be obtained before flight actual motion to be predicted according to the preset expert's risk mitigation of expertise
The risk of flight to be predicted is alleviated in measure, and flight to be predicted may be implemented to use expert's risk mitigation measure when running
Desired effect afterwards, to achieve the effect that replicate and shared expertise.System can also obtain flight to be predicted and take specially
Family risk mitigation strategy alleviated after new risk factors information, by new risk factors information input to flight risk
In prediction model, new flight risk profile value is obtained, with the effect of detection risk management and control.
Next, with a specific embodiment detailed description of the present invention technical solution.
Fig. 2 is that aviation operation provided in an embodiment of the present invention is controlled risk management-control method schematic diagram.As shown in Fig. 2, this hair
The aviation operation of bright offer management-control method of controlling risk is as described below.
Step 1, according to history flight data and expertise, select the principal element for influencing flight risk, provide simultaneously
Can alleviate these factors mitigation strategy and alleviation after reducible score value.
The selected risk factors of step 2, basis, pass through cluster using history flight data using unsupervised learning method
With analysis, typical flight is obtained, forms a part of sample of flight risk facior data collection, every sample is believed comprising flight basis
Breath and risk factors information.
Step 3, according to selected risk factors and according to expertise offer, about fresh few appearance, still risk is larger
Environmental information, generate virtual flight, form another part sample of flight risk facior data collection, every sample includes virtual
Flight Information and risk factors information.
Step 4, for flight risk facior data collection, using marking software, to the wind for each flight that data are concentrated
Danger value is assessed and is given a mark, and typical flight sample set is obtained, and typical flight sample set includes that flight risk facior data is concentrated
All Flight Informations and every flight risk score.
Step 5, for typical flight sample set, model is established using machine learning method, reproduction expert analysis mode rule is raw
At flight risk profile function and single or blocking factor contribution degree anticipation function.
Step 6, using flight risk profile function, flight value-at-risk and single or blocking factor tribute to flight to be predicted
Degree of offering is predicted.
Step 7, score for risk profile value and expertise the larger flight of difference, is supplemented into typical flight
Sample set passes through machine learning method more new model.
Step 8, for emerging hazard event, investigate its risk factors, and according to the distribution of risk factors, utilize shellfish
Ye Si analyses are modified flight risk forecast model, and supplement mitigation strategy and effect, control risk pipe to aviation operation
Control system carries out perfect.
Step 9, for the higher flight of value-at-risk, input risk mitigation system, imitated according to risk mitigation measure with alleviating
Fruit provides the flight environmental risk factor information after risk mitigation, re-enters flight risk forecast model and is predicted.
Fig. 3 is that aviation operation provided in an embodiment of the present invention is controlled risk the structural schematic diagram of managing and control system, such as Fig. 3 institutes
Show, the system comprises：Acquisition module 30, risk profile module 31 and risk mitigation module 32, wherein：
Acquisition module 30 is used to obtain the risk factors information of flight to be predicted；Risk profile module 31 by described for waiting for
In the risk factors information input to the flight risk forecast model pre-established for predicting flight, the flight to be predicted is obtained
Risk profile value；Wherein, the flight risk forecast model is believed according to the risk factors of the flight in multiple historical datas
What expert's risk score of breath and the flight in preset each historical data determined；Risk mitigation module 32 is used
If the risk profile value in the flight to be predicted is more than preset risk threshold value, risk pipe is carried out to the flight to be predicted
Control.
Specifically, aviation operation provided in an embodiment of the present invention managing and control system of controlling risk may include：Acquisition module 30,
Risk profile module 31 and risk mitigation module 32.
Acquisition module 30 can obtain the risk factors information of flight to be predicted.Wherein, risk factors information can be root
According to the information for the value-at-risk that can influence flight to be predicted that expertise determines.
For example, may include following environmental information according to the risk factors information that expertise determines.In flight takeoff rank
Section, risk factors information may include：Against the wind standard, with the wind standard, crosswind standard (dry runway), crosswind standard (wet runway),
Visibility standards, cloud level standard, crosswind, against the wind, with the wind, wet runway, visibility, the cloud level, sand, wind shear, snow, rain, thunder, ice
Hail, high-altitude aerodrome, high high-altitude aerodrome, special airport, complicated airport, airfield runway quantity, dash road, the runway gradient, international machine
Field, socked-in remaining, airport busy extent and blank pipe communication difficult degree, night flight and the new environmental informations such as airport of setting sail.
In flight landing phases, risk factors information may include：Standard, with the wind standard, (the dry race of crosswind standard against the wind
Road), crosswind standard (wet runway), visibility standards, cloud level standard, crosswind, against the wind, with the wind, wet runway, visibility, the cloud level, raise
It is sand, wind shear, snow, rain, thunder, hail, high-altitude aerodrome, high high-altitude aerodrome, special airport, complicated airport, airfield runway quantity, short
Runway, the runway gradient, International airport, socked-in remaining, airport busy extent, with blank pipe communication difficult degree, night flight, newly open
Plane field and into environmental informations such as nearly landing procedure types.
Risk profile module 31 can arrive the risk factors information input for the flight to be predicted that acquisition module 30 is got
In the flight risk forecast model pre-established, which can export the value-at-risk of flight to be predicted,
The value-at-risk can be denoted as to risk profile value.Flight risk forecast model can be according to the wind of the flight in multiple historical datas
Dangerous factor information and expert's risk score of the flight in preset each historical data determine.Wherein, historical data
In expert's risk score of flight can be that the risk obtained according to the risk factors information and expertise of history flight is commented
Point, it can also be the scoring with professional reference value according to related data COMPREHENSIVE CALCULATING, can also be by other means
What is obtained has the scoring for actually instructing reference significance.
The risk profile value of flight to be predicted can be compared by risk mitigation module 32 with preset risk threshold value, such as
Fruit risk profile value is more than risk threshold value, then risk mitigation module 32 can carry out risk management and control to the flight to be predicted.Wind
Danger, which alleviates module 32 and can also obtain flight to be predicted, takes new risk factors information after risk management and control, by new risk
Factor information is input in flight risk forecast model, new flight risk profile value is obtained, with the effect of detection risk management and control.
Aviation operation provided in an embodiment of the present invention is controlled risk managing and control system, and function is implemented referring in particular to the above method
Example, details are not described herein again.
Aviation operation provided in an embodiment of the present invention is controlled risk managing and control system, by obtain the risk of flight to be predicted because
Prime information is waited in the risk factors information input of flight to be predicted to the flight risk forecast model pre-established
The risk profile value of flight is predicted, if the risk profile value of flight to be predicted is more than preset risk threshold value, to boat to be predicted
Class carries out risk management and control.The system makes full use of history flight data and expertise, can be more accurately and timely to flight
Risk is assessed, and reliable reference is provided for the risk assessment work of dispatch person.
Optionally, on the basis of the above embodiments, the system comprises：Acquisition module, risk profile module, risk are slow
Module and model building module are solved, wherein：
The model building module includes：First acquisition submodule and model foundation submodule, described first obtains submodule
Block is for obtaining the first typical flight sample data set；Wherein, the described first typical flight sample data set includes：Multiple typical cases
Expert's risk score of the risk factors information of flight and each typical flight；Wherein, the acquisition of expert's risk score
Method includes：Using the method for adaptive sampling, is chosen from multiple flights and predeterminable level is more than to model foundation percentage contribution
Then the flight of threshold value is ranked up the flight chosen according to percentage contribution, obtains each flight in batches from high to low
Expert's risk score；The model foundation submodule is used for using machine learning method to the described first typical flight sample number
Learnt according to collection, obtains the flight risk forecast model.
Specifically, aviation operation provided in an embodiment of the present invention managing and control system of controlling risk may include：Acquisition module, wind
Dangerous prediction module, risk mitigation module and model building module.Wherein, the acquisition module, the risk profile module and institute
It states risk mitigation module to be described in detail in the above-described embodiments, details are not described herein again.
Model building module may include the first acquisition submodule and model foundation submodule.First acquisition submodule can be with
The first typical flight sample data set is obtained, as the training sample for establishing flight risk forecast model.First, it is passed through according to expert
Testing determination may be to the environmental factor that flight risk has an impact, secondly, using clustering algorithm, to possible in environmental risk factor
The continuous variable and discrete variable had an impact to flight risk is handled respectively, is obtained from flight historical data comprising main true
The flight data collection of truth scape constitutes the true flight in historical data；It includes preset extreme environment information to be added simultaneously
Flight and the fresh typical flight of the others occurred less are as virtual flight.Using the method for adaptive sampling, from multiple flights
Choose the flight for being more than predeterminable level threshold value to model foundation percentage contribution, the tribute of the operation data of this kind of flight to model foundation
Degree of offering is larger, wherein predeterminable level threshold value can specifically be set according to expertise.Then, the flight chosen is pressed
It is ranked up according to the sequence of percentage contribution from high to low, obtains expert's risk score of each flight in batches, obtained comprising more
First typical flight sample data of the risk factors information of a typical case's flight and expert's risk score of each typical flight
Collection, can reduce marking cost in this way.
Wherein, expert's risk score acquisition methods include：Marking rule, marking sample set obtain and marking interface.
Marking rule can be ranked up flight to limit the flight number of every batch of marking according to single or multiple risk factors, complete
Marking is submitted after the marking of this batch flight as a result, carrying out the marking of next batch flight or stopping marking；Marking sample set acquisition is adopted
With dynamic sampling method, after every wheel is given a mark, high score is preferentially found in flight sample set or scoring is uncertain big
Flight, for the sample of marking, stops as next round when promoting sufficiently small to model accuracy caused by new assessed value
It only samples, this dynamic approach can give a mark to the representative flight for all taking off or landing；Marking interface
In, include all Flight Informations of this batch of the information of every flight of sub-category displaying and comparison displaying, relatively hazardous flight
Risk factors highlight, all flight risk profile value real-time displays of this batch.
After first acquisition submodule gets the first typical flight sample data set, model foundation submodule may be used
Be suitble to the machine learning method of flight risk assessment application scene and data characteristics, using the first typical flight sample data set into
Row study.The machine learning method can utilize sparse data, explain non-thread between flight value-at-risk and multiple risk factors
Sexual intercourse, and there is complicated reciprocation between tolerable risk factor, meanwhile, using expertise rejecting abnormalities data,
Prevent model over-fitting.By the learning process, system can provide risk profile function and risk factors contribution degree prediction letter
Number, provides formula and calculates the risk profile value of flight to be predicted, to establish flight risk forecast model.
Aviation operation provided in an embodiment of the present invention is controlled risk managing and control system, is passed through and is obtained the first typical flight sample number
According to collection, is learnt using the typical flight sample data set of machine learning method pair first, obtain flight risk forecast model, it should
System can make full use of history flight data and expertise, provide more accurate, timely flight risk evaluation model.
Optionally, on the basis of the above embodiments, the system comprises：Acquisition module, risk profile module, risk are slow
Module and model modification module are solved, wherein：
The model modification module includes：Second acquisition submodule and model modification submodule, described second obtains submodule
Block is used to obtain the newly-increased flight of the difference of risk profile value and expert's risk score in preset time period more than predetermined threshold value
Expert's risk score of risk factors information and each newly-increased flight, as the second typical flight sample data set；Institute
State model modification submodule for use Bayesian analysis method, navigate according to described in the second typical case flight sample data set pair
Class's risk forecast model is updated, or uses machine learning method, to the described first typical flight sample data set and institute
It states the population sample data set that the second typical flight sample data set is constituted to be learnt, obtains updated flight risk profile
Model.
Specifically, aviation operation provided in an embodiment of the present invention managing and control system of controlling risk may include：Acquisition module, wind
Dangerous prediction module, risk mitigation module and model modification module.Wherein, the acquisition module, the risk profile module and institute
It states risk mitigation module to be described in detail in the above-described embodiments, details are not described herein again.
Model modification module may include：Second acquisition submodule and model modification submodule.Second acquisition submodule can
Difference to obtain risk profile value and expert's risk score in every preset time period is more than the newly-increased flight of predetermined threshold value
Expert's risk score of risk factors information and each newly-increased flight, as the second typical flight sample data set.
After second acquisition submodule gets the second typical flight sample data set, model modification submodule may be used
Bayesian analysis method is updated according to the second typical flight sample data set pair flight risk forecast model.Utilize pattra leaves
The specific method of this analysis more new model is the form of risk facior data when being occurred according to the hazard event that sensor obtains
And distribution, different types of new data is absorbed by various forms of likelihood equations, is constantly updated in flight risk forecast model
Model parameter with correction model.
Model modification submodule can also use machine learning method, to the first typical flight sample data set and the second allusion quotation
The population sample data set that type flight sample data set is constituted is learnt, and updated flight risk forecast model is obtained.
Aviation operation provided in an embodiment of the present invention is controlled risk managing and control system, and the risk obtained in preset time period is passed through
The difference of predicted value and expert's risk score is described newly-increased more than the risk factors information of the newly-increased flight of predetermined threshold value and each
Expert's risk score of flight, as the second typical flight sample data set, using Bayesian analysis method, according to the second typical case
Flight sample data set pair flight risk forecast model is updated；Or machine learning method is used, to the first typical flight
The population sample data set that sample data set and the second typical flight sample data set are constituted is learnt, and updated boat is obtained
Class's risk forecast model.The system can utilize history flight data and expertise to accumulate, continuous updating and expansion flight wind
Dangerous prediction model so that the system is more accurate.
Fig. 4 is the structural schematic diagram of electronic equipment provided in an embodiment of the present invention, as shown in figure 4, the equipment includes：Place
Device (processor) 41, memory (memory) 42 and bus 43 are managed, wherein：
The processor 41 and the memory 42 complete mutual communication by the bus 43；The processor 41
For calling the program instruction in the memory 42, to execute the method that above-mentioned each method embodiment is provided, such as including：
Obtain the risk factors information of flight to be predicted；By the risk factors information input of the flight to be predicted to pre-establishing
In flight risk forecast model, the risk profile value of the flight to be predicted is obtained；Wherein, the flight risk forecast model is
According to the flight in the risk factors information of the flight in multiple historical datas and preset each historical data
Expert's risk score determine；If the risk profile value of the flight to be predicted is more than preset risk threshold value, to described
Flight to be predicted carries out risk management and control.
The embodiment of the present invention discloses a kind of computer program product, and the computer program product is non-transient including being stored in
Computer program on computer readable storage medium, the computer program include program instruction, when described program instructs quilt
When computer executes, computer is able to carry out the method that above-mentioned each method embodiment is provided, such as including：Obtain boat to be predicted
The risk factors information of class；By the risk factors information input of the flight to be predicted to the flight risk profile pre-established
In model, the risk profile value of the flight to be predicted is obtained；Wherein, the flight risk forecast model is according to multiple history
The risk factors information of flight in data and expert's risk of the flight in preset each historical data are commented
Divide determination；If the risk profile value of the flight to be predicted be more than preset risk threshold value, to the flight to be predicted into
Row risk management and control.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage
Medium storing computer instructs, and the computer instruction makes the computer execute the side that above-mentioned each method embodiment is provided
Method, such as including：Obtain the risk factors information of flight to be predicted；The risk factors information input of the flight to be predicted is arrived
In the flight risk forecast model pre-established, the risk profile value of the flight to be predicted is obtained；Wherein, the flight wind
Dangerous prediction model is the risk factors information and preset each history according to the flight in multiple historical datas
What expert's risk score of the flight in data determined；If the risk profile value of the flight to be predicted is more than preset risk threshold
Value then carries out risk management and control to the flight to be predicted.
The embodiments such as electronic equipment described above are only schematical, illustrate as separating component wherein described
Unit may or may not be physically separated, and the component shown as unit may or may not be object
Manage unit, you can be located at a place, or may be distributed over multiple network units.It can select according to the actual needs
Some or all of module therein is selected to achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying wound
In the case of the labour for the property made, you can to understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It is realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be expressed in the form of software products in other words, should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Above example is only used to illustrate the technical scheme of the present invention, rather than its limitations；Although with reference to the foregoing embodiments
Invention is explained in detail, it will be understood by those of ordinary skill in the art that：It still can be to aforementioned each implementation
Technical solution recorded in example is modified or equivalent replacement of some of the technical features；And these are changed or replace
It changes, the spirit and scope for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution.
Claims (10)
- The management-control method 1. a kind of aviation operation is controlled risk, which is characterized in that including：Obtain the risk factors information of flight to be predicted；By in the risk factors information input of the flight to be predicted to the flight risk forecast model pre-established, institute is obtained State the risk profile value of flight to be predicted；Wherein, the flight risk forecast model is according to the flight in multiple historical datas Risk factors information and expert's risk score of flight in preset each historical data determine；If the risk profile value of the flight to be predicted is more than preset risk threshold value, risk is carried out to the flight to be predicted Management and control.
- 2. according to the method described in claim 1, it is characterized in that, further including the foundation of the flight risk forecast model Journey, the process of establishing include：Obtain the first typical flight sample data set；Wherein, the described first typical flight sample data set includes：Multiple typical boats Expert's risk score of the risk factors information of class and each typical flight；Wherein, the acquisition side of expert's risk score Method includes：Using the method for adaptive sampling, is chosen from multiple flights and predeterminable level threshold is more than to model foundation percentage contribution Then the flight of value is ranked up the flight chosen according to percentage contribution, obtains each flight in batches from high to low Expert's risk score；The described first typical flight sample data set is learnt using machine learning method, obtains the flight risk profile Model.
- 3. according to the method described in claim 2, it is characterized in that, further including the updated of the flight risk forecast model Journey, the renewal process include：The difference of risk profile value and expert's risk score in acquisition preset time period is more than the wind of the newly-increased flight of predetermined threshold value Expert's risk score of dangerous factor information and each newly-increased flight, as the second typical flight sample data set；Using Bayesian analysis method, according to flight risk forecast model described in the described second typical flight sample data set pair into Row update；OrUsing machine learning method, to the described first typical flight sample data set and the second typical flight sample data set The population sample data set of composition is learnt, and updated flight risk forecast model is obtained.
- 4. according to the method described in claim 2, it is characterized in that, the flight packet that the described first typical flight sample data is concentrated It includes：True flight in historical data and virtual flight, wherein the true flight in historical data is to use clustering algorithm, right What the flight operation data in flight operation data library was screened；The virtual flight refer to include preset extreme ring The flight of border information and other fresh typical flights occurred less.
- 5. if according to the method described in claim 1, it is characterized in that, the risk profile value of the flight to be predicted is more than Preset risk threshold value then carries out risk management and control to the flight to be predicted, including：If the risk profile value of the flight to be predicted is more than preset risk threshold value, it is slow to obtain preset expert's risk Solution measure, and the risk of the flight to be predicted is alleviated according to expert's risk mitigation measure.
- The managing and control system 6. a kind of aviation operation is controlled risk, which is characterized in that including：Acquisition module, the risk factors information for obtaining flight to be predicted；Risk profile module, for by the risk factors information input of the flight to be predicted to the flight risk pre-established In prediction model, the risk profile value of the flight to be predicted is obtained；Wherein, the flight risk forecast model is according to multiple Expert's wind of the risk factors information of flight in historical data and the flight in preset each historical data Danger scoring determination；Risk mitigation module, if the risk profile value for the flight to be predicted is more than preset risk threshold value, to described Flight to be predicted carries out risk management and control.
- 7. system according to claim 6, which is characterized in that further include model building module, the model building module Including：First acquisition submodule, for obtaining the first typical flight sample data set；Wherein, the described first typical flight sample number Include according to collection：Expert's risk score of the risk factors information of multiple typical case's flights and each typical flight；Wherein, specially Family risk score acquisition methods include：Using the method for adaptive sampling, is chosen from multiple flights and model foundation is contributed Then the flight that degree is more than predeterminable level threshold value is ranked up the flight chosen according to percentage contribution from high to low, point Batch obtains expert's risk score of each flight；Model foundation submodule, for being learnt to the described first typical flight sample data set using machine learning method, Obtain the flight risk forecast model.
- 8. system according to claim 7, which is characterized in that further include model modification module, the model modification module Including：Second acquisition submodule, the difference for obtaining risk profile value and expert's risk score in preset time period are more than default Expert's risk score of the risk factors information of the newly-increased flight of threshold value and each newly-increased flight, as the second typical boat Class's sample data set；Model modification submodule, for using Bayesian analysis method, according to the described second typical flight sample data set pair institute It states flight risk forecast model to be updated, or uses machine learning method, to the described first typical flight sample data set The population sample data set constituted with the described second typical flight sample data set is learnt, and updated flight risk is obtained Prediction model.
- 9. a kind of electronic equipment, which is characterized in that including memory and processor, the processor and the memory pass through total Line completes mutual communication；The memory is stored with the program instruction that can be executed by the processor, the processor tune It is able to carry out the method as described in claim 1 to 5 is any with described program instruction.
- 10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program quilt The method as described in claim 1 to 5 is any is realized when processor executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810486745.1A CN108805337B (en) | 2018-05-21 | 2018-05-21 | Aviation operation control risk management and control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810486745.1A CN108805337B (en) | 2018-05-21 | 2018-05-21 | Aviation operation control risk management and control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108805337A true CN108805337A (en) | 2018-11-13 |
| CN108805337B CN108805337B (en) | 2021-06-22 |
Family
ID=64092674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810486745.1A Active CN108805337B (en) | 2018-05-21 | 2018-05-21 | Aviation operation control risk management and control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108805337B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109977546A (en) * | 2019-03-27 | 2019-07-05 | 北京航空航天大学 | A kind of online method for detecting abnormality of four-dimensional track based on unsupervised learning |
| CN110033194A (en) * | 2019-04-17 | 2019-07-19 | 中国民航科学技术研究院 | A kind of aircraft is unstable into nearly detection and evaluation method and electronic equipment |
| CN110443521A (en) * | 2019-08-15 | 2019-11-12 | 中国国际航空股份有限公司 | Flight operation risk acquisition methods, system and computer equipment |
| CN110991883A (en) * | 2019-12-03 | 2020-04-10 | 中国民用航空总局第二研究所 | Operation control system and method based on flight risk preposition |
| WO2021003791A1 (en) * | 2019-07-11 | 2021-01-14 | 清华大学 | Black swan event decision method and apparatus based on subjective and objective joint prediction |
| CN115862388A (en) * | 2022-11-29 | 2023-03-28 | 航天新气象科技有限公司 | Flight low-altitude wind shear early warning method, device, equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101770602A (en) * | 2008-12-31 | 2010-07-07 | 国立成功大学 | Flight safety margin risk evaluating method, specialist system and establishing method thereof |
| US20140122132A1 (en) * | 2008-08-25 | 2014-05-01 | Flightsurance Gmbh | Flight Accident Insurance |
| CN204791130U (en) * | 2015-05-08 | 2015-11-18 | 中国民航大学 | Safe risk monitoring devices of flight operation |
| CN105225007A (en) * | 2015-09-30 | 2016-01-06 | 中国民用航空总局第二研究所 | A kind of sector runnability method for comprehensive detection based on GABP neural network and system |
| CN105787856A (en) * | 2016-03-02 | 2016-07-20 | 中国民航大学 | Pilot safety credit evaluating method |
| US20170178037A1 (en) * | 2015-12-16 | 2017-06-22 | Evan John Kaye | Flight Safety Forecasting and Hazard Avoidance |
-
2018
- 2018-05-21 CN CN201810486745.1A patent/CN108805337B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140122132A1 (en) * | 2008-08-25 | 2014-05-01 | Flightsurance Gmbh | Flight Accident Insurance |
| CN101770602A (en) * | 2008-12-31 | 2010-07-07 | 国立成功大学 | Flight safety margin risk evaluating method, specialist system and establishing method thereof |
| CN204791130U (en) * | 2015-05-08 | 2015-11-18 | 中国民航大学 | Safe risk monitoring devices of flight operation |
| CN105225007A (en) * | 2015-09-30 | 2016-01-06 | 中国民用航空总局第二研究所 | A kind of sector runnability method for comprehensive detection based on GABP neural network and system |
| US20170178037A1 (en) * | 2015-12-16 | 2017-06-22 | Evan John Kaye | Flight Safety Forecasting and Hazard Avoidance |
| CN105787856A (en) * | 2016-03-02 | 2016-07-20 | 中国民航大学 | Pilot safety credit evaluating method |
Non-Patent Citations (2)
| Title |
|---|
| 李大伟 等: "多不利因素综合作用下飞行风险评估方法研究", 《飞机设计》 * |
| 杨杰: "航空公司运行监控风险评估研究", 《中国优秀硕士学位论文全文数据库 经济与管理科学辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109977546A (en) * | 2019-03-27 | 2019-07-05 | 北京航空航天大学 | A kind of online method for detecting abnormality of four-dimensional track based on unsupervised learning |
| CN110033194A (en) * | 2019-04-17 | 2019-07-19 | 中国民航科学技术研究院 | A kind of aircraft is unstable into nearly detection and evaluation method and electronic equipment |
| CN110033194B (en) * | 2019-04-17 | 2021-02-26 | 中国民航科学技术研究院 | Method for detecting and evaluating unstable approach of airplane and electronic equipment |
| WO2021003791A1 (en) * | 2019-07-11 | 2021-01-14 | 清华大学 | Black swan event decision method and apparatus based on subjective and objective joint prediction |
| CN110443521A (en) * | 2019-08-15 | 2019-11-12 | 中国国际航空股份有限公司 | Flight operation risk acquisition methods, system and computer equipment |
| CN110991883A (en) * | 2019-12-03 | 2020-04-10 | 中国民用航空总局第二研究所 | Operation control system and method based on flight risk preposition |
| CN110991883B (en) * | 2019-12-03 | 2022-05-20 | 中国民用航空总局第二研究所 | Operation control system and method based on flight risk preposition |
| CN115862388A (en) * | 2022-11-29 | 2023-03-28 | 航天新气象科技有限公司 | Flight low-altitude wind shear early warning method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108805337B (en) | 2021-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108805337A (en) | Aviation operation is controlled risk management-control method and system | |
| CN103530704B (en) | A kind of air dynamic traffic volume in terminal airspace prognoses system and method thereof | |
| US9965961B2 (en) | En-route flight path optimization | |
| Xue et al. | Modeling human-like decision-making for inbound smart ships based on fuzzy decision trees | |
| CN110334839A (en) | Flight is delayed prediction technique, device, equipment and storage medium | |
| CN109948839B (en) | Method and system for predicting and early warning galloping risk of overhead transmission line | |
| CN110570693B (en) | Flight operation time prediction method based on reliability | |
| Diana | Can machines learn how to forecast taxi-out time? A comparison of predictive models applied to the case of Seattle/Tacoma International Airport | |
| Mahanta et al. | Urban air quality prediction using regression analysis | |
| CN109299815A (en) | Ship trajectory predictions method | |
| CN103164617B (en) | A kind of aircraft behavior prediction system and Forecasting Methodology | |
| CN115857059B (en) | Ice accumulation forecast management method, system, readable storage medium and device | |
| Anwar et al. | Rainfall prediction using extreme gradient boosting | |
| CN112861706A (en) | Road state monitoring method, device, equipment and storage medium | |
| WO2022039675A1 (en) | Method and apparatus for forecasting weather, electronic device and storage medium thereof | |
| CN113706931B (en) | Airspace flow control strategy recommendation method and device, electronic equipment and storage medium | |
| CN112132366A (en) | Prediction system for flight clearance rate | |
| Klüver et al. | A self-enforcing neural network as decision support system for air traffic control based on probabilistic weather forecasts | |
| Dalmau et al. | A machine learning approach to predict the evolution of air traffic flow management delay | |
| US20200073014A1 (en) | Generation of weather analytical scenarios translating likely airport capacity impact from probabilistic weather forecast | |
| CN115662196B (en) | Method and device for processing information of forecast of ice accretion of airplane, electronic equipment and storage medium | |
| CN115508917B (en) | Airport weather element forecasting method, device, equipment and storage medium | |
| CN115310732B (en) | Flight delay prediction method and system | |
| US20220270497A1 (en) | System and method for improved determination of the complexity of air sectors | |
| CN114943114A (en) | Method, device and storage medium for predicting running direction of runway |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |