CN110363361A - A kind of method and system for predicting variable sliding time based on big data - Google Patents
A kind of method and system for predicting variable sliding time based on big data Download PDFInfo
- Publication number
- CN110363361A CN110363361A CN201910674628.2A CN201910674628A CN110363361A CN 110363361 A CN110363361 A CN 110363361A CN 201910674628 A CN201910674628 A CN 201910674628A CN 110363361 A CN110363361 A CN 110363361A
- Authority
- CN
- China
- Prior art keywords
- sliding time
- variable sliding
- time
- airport
- follows
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000009826 distribution Methods 0.000 claims abstract description 38
- 230000000007 visual effect Effects 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000005520 cutting process Methods 0.000 claims description 32
- 230000006870 function Effects 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000012800 visualization Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 230000008676 import Effects 0.000 claims description 5
- 241000208340 Araliaceae Species 0.000 claims description 4
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 4
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 4
- 235000008434 ginseng Nutrition 0.000 claims description 4
- 230000003111 delayed effect Effects 0.000 abstract description 8
- 239000000284 extract Substances 0.000 abstract description 5
- 238000007726 management method Methods 0.000 description 18
- 238000010276 construction Methods 0.000 description 11
- 238000013079 data visualisation Methods 0.000 description 11
- 238000004519 manufacturing process Methods 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 8
- 238000013459 approach Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 230000008707 rearrangement Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000004141 dimensional analysis Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000012163 sequencing technique 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"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of method and system that variable sliding time is predicted based on big data, it is related to civil aviaton's message area, the following steps are included: the historical data in analysis airport coordinated decision system database, therefrom extract flight for putting forth operation data, determine the main affecting parameters of flight for putting forth, setting weighted value and dynamic adjustment weight proportion;Tree-model is promoted using gradient to be modeled, and obtains variable sliding time dynamic estimation model, the real data of main affecting parameters is input in variable sliding time dynamic estimation model, the probability distribution of variable sliding time is estimated, calculates desired value;Variable sliding time is visualized;Utilize the variable sliding time desired value of visual presentation, carry out the clearance sequence of aircraft, the present invention is based on the A-CDM systems built manually to predict that intelligent predicting can be changed sliding time, aid decision is visualized by big data, so that large area is delayed to be prevented and alleviate.
Description
Technical field
The present invention relates to civil aviaton's message areas, and in particular to it is a kind of based on big data predict variable sliding time method and
System.
Background technique
Chinese Civil Aviation is in fast development, but Civil Aviation Industry existing information construction level relatively lags behind: in hardware aspect, especially
The problems such as it is that network construction level lags behind business development, and incomplete, transmission speed that there are coverage areas is limited;In software side
Face, there are a large amount of repeated construction, data silo, shortage data interconnection intercommunication, systems to need to upgrade.In face of challenge, civil aviaton
It proposes in the industry to wish to make full use of modern information technologies, to Civil Aviation Airport passenger and freight transportation guarantee and digital management, visualization
Present, it is intelligent support, gradually assign airport more and more intelligence, improve comprehensively the production on airport, safety, service, logistics,
Guarantee efficiency, service quality and the management level of the links such as management, traffic, business and environmental protection.Meanwhile it also wanting to lead in the industry
It crosses new mechanism and new technology solves the chronic illnesses such as flight large area delay.
Currently, flight dynamic information transmitting, airport aircraft gate resource allocation and weather warning analysis etc. rely primarily on people
Work operation is completed.Manual operation has the following problems: first is that the experience and familiarity difference of different personnel will lead to result and
Efficiency is multifarious;Second is that because inevitably there is certain mistake in subjective and objective factor;Third is that in the processing of a large amount of concurrent datas, people
Work efficiency rate is unable to ensure efficiency.
Summary of the invention
According to the above-mentioned deficiencies of the prior art, a kind of pre- based on big data the technical problem to be solved by the present invention is to propose
The method and system for surveying variable sliding time, when manually predicting that intelligent predicting can be changed sliding based on the A-CDM system built
Between, aid decision is visualized by big data, so that large area is delayed to be prevented and alleviate.
A method of variable sliding time is predicted based on big data, comprising the following steps:
The historical data in airport coordinated decision system database is analyzed, flight for putting forth operation data is therefrom extracted, determines boat
The main affecting parameters of class's departure from port, and the weighted value of the items main affecting parameters is set, dynamic adjusts every main influence
The weight proportion of parameter;
The historical data for importing main affecting parameters carries out parameter learning, and the data for importing the major parameter obtained in the recent period are increased
Amount study promotes tree-model using gradient and is modeled, is fitted a basic function, obtain variable sliding time dynamic
Estimate model, the basic functionThe process of fitting are as follows:
(1)
(2)
(3)
Basic functionTraining step are as follows:
1) one group of cutting dimension j and cutting value S are found, so that the cutting dimension j and cutting value S meet formula (4), the public affairs
Formula (4) are as follows:
(4)
Wherein,,,;
2) input space is divided into two sub-regions by the training dataset (j, s) inputted with the step 1), and uses formula
(5) each corresponding output valve of subregion, the formula (5) are determined are as follows:
(5)
3) recursively each subregion is continued to divide, so that each subregion is further subdivided into two new subregions, and
Each corresponding output valve of new subregion is determined using step 1) and step 2, this step is recycled until meeting and stops item
Part.The stop condition is determined by the minimum sample number that incorporates subregion into or the depth capacity for establishing Taxonomy and distribution;
4) input space is divided into M region, Taxonomy and distribution is generated using formula (6), it is described
Formula (6) are as follows:
(6);
The real data of main affecting parameters is input in the variable sliding time dynamic estimation model, variable cunning is estimated
The probability distribution of dynamic time, calculates desired value, and the desired value is variable sliding time;
The variable sliding time is visualized;
Using the variable sliding time desired value of visual presentation, the clearance sequence of aircraft is carried out.
Optionally, the main affecting parameters include runway, into/departure from port, early late peak, type/seat in the plane, weather, state
Border/the country, large area flight are delayed parameter.
Optionally, the variable sliding time is visualized, is specifically included:
For different application scene, carried out by Google Chart, D3, Tableau, HightCharts or Datawrapper
It visualizes, by variable sliding time by way of figure, table, by geographical space, time series or logical relation different dimensional
Degree, is shown by visual element such as shape, position, color, text, symbol.
Optionally, using the variable sliding time desired value of visual presentation, the clearance sequence of aircraft is carried out, it is specific to wrap
It includes:
The computation rule of wheel time is removed on airport according to target, is calculated after target removes the wheel time and is submitted to ATM Bureau, airport passes through
The airport coordinated decision system, which to ATM Bureau provides target, to be removed the wheel time as calculating and removes the calculation basis for taking turns the time, then by sky
Calculating is removed the wheel time and is distributed to airport by pipe office, and blank pipe recycles variable sliding time to resequence outgoing flight, from
And the existing resource on reasonable arrangement airport, blank pipe and airline.
Optionally, the calculation method of the computation rule are as follows:
Target removes wheel time=E.T.A+and variable sliding time+minimum misses the stop and ensures the time;
The minimum, which is missed the stop, ensures the computation rule of time are as follows:
60 and 60 aircrafts below are 40 minutes, and 61 to 150 aircrafts are 50 minutes, 151 to 250
Aircraft is 60 minutes, and 251 to 500 aircrafts are 75 minutes, and 500 or more aircrafts are 120 minutes.
A kind of system that variable sliding time is predicted based on big data, comprising:
Parameter acquisition module: the historical data in analysis airport coordinated decision system database therefrom extracts flight for putting forth fortune
Row data, determine the main affecting parameters of flight for putting forth, and set the weighted value of every main affecting parameters, and dynamic adjusts
The weight proportion of every main affecting parameters;
Model buildings module: the historical data for importing main affecting parameters carries out parameter learning, imports the main ginseng obtained in the recent period
Several data carry out incremental learning, promote tree-model using gradient and are modeled, are fitted a basic function, obtaining can
Become sliding time dynamic estimation model, the basic functionThe process of fitting are as follows:
(1)
(2)
(3)
Basic functionTraining step are as follows:
1) one group of cutting dimension j and cutting value S are found, so that the cutting dimension j and cutting value S meet formula (4), formula
(4) are as follows:
(4)
Wherein,,,;
2) input space is divided into two sub-regions by the training dataset (j, s) inputted with the step 1), and uses formula
(5) each corresponding output valve of subregion, the formula (5) are determined are as follows:
(5)
3) recursively each subregion is continued to divide, so that each subregion is further subdivided into two new subregions, and
Each corresponding output valve of new subregion is determined using step 1) and step 2, this step is recycled until meeting and stops item
Part.The stop condition is determined by the minimum sample number that incorporates subregion into or the depth capacity for establishing Taxonomy and distribution;
4) input space is divided into M region, Taxonomy and distribution is generated using formula (6), it is described
Formula (6) are as follows:
(6);
Computing module: the real data of main affecting parameters is input in the variable sliding time dynamic estimation model, is estimated
The probability distribution for counting out variable sliding time, calculates desired value, and the desired value is variable sliding time;
Visualization model: the variable sliding time is visualized;
Resource distribution module: using the variable sliding time desired value visualized, the clearance sequence of aircraft is carried out.
Optionally, the main affecting parameters include runway, into/departure from port, early late peak, type/seat in the plane, weather, state
Border/the country, large area flight are delayed parameter.
Optionally, the visualization model specifically includes:
For different application scene, carried out by Google Chart, D3, Tableau, HightCharts or Datawrapper
It visualizes, by variable sliding time by way of figure, table, by geographical space, time series or logical relation different dimensional
Degree, is shown by visual element such as shape, position, color, text, symbol.
Optionally, the resource distribution module specifically includes:
The computation rule of wheel time is removed on airport according to target, is calculated after target removes the wheel time and is submitted to ATM Bureau, airport passes through
The airport coordinated decision system, which to ATM Bureau provides target, to be removed the wheel time as calculating and removes the calculation basis for taking turns the time, then by sky
Calculating is removed the wheel time and is distributed to airport by pipe office, and blank pipe recycles variable sliding time to resequence outgoing flight, from
And the existing resource on reasonable arrangement airport, blank pipe and airline.
Optionally, the calculation method of the computation rule are as follows:
Target removes wheel time=E.T.A+and variable sliding time+minimum misses the stop and ensures the time;
The minimum, which is missed the stop, ensures the computation rule of time are as follows:
60 and 60 aircrafts below are 40 minutes, and 61 to 150 aircrafts are 50 minutes, 151 to 250
Aircraft is 60 minutes, and 251 to 500 aircrafts are 75 minutes, and 500 or more aircrafts are 120 minutes.
The present invention has the advantages that based on the A-CDM system built to flight operation historical data be collected and
Arrange, aircraft is slided from outgoing flight aircraft gate to takeoff runway using big data technology, or from landing runway slide to
Analyzed and excavated to the port flight aircraft gate actually used time, thus precisely predict it is next approach or the VTT of outgoing flight,
After obtaining VTT, by big data visualization technique, intuitively it is presented to Gate Position Scheduling or blank pipe department and relevant person in charge is let pass
Sequence more accurately arranges the boarding of passenger, reduces the waiting time of passenger aboard;Reasonable arrangement oiling, deicing vehicle etc.
Resource, avoid as ground safeguard is not in place and caused by the generation etc. of flight tardy problem by the prediction of VTT be decision
Management is provided and is accurately referred to, and accurately grasps marketing data, reduces blind investment and repeated construction, realizes that the resource of the whole industry is total
It enjoys, reduces cost, take with realizing airport and ensure more intelligent, production process is more efficient, realizes seat in the plane reasonable distribution, sufficiently benefit
With the free time of seat in the plane, the configuration of resource is reduced, reduces operation cost, improves flight punctuality rate, promotes customer service quality,
It promotes flight to leave the port clearance rate, the precise arrangements boarding time.
Detailed description of the invention
Fig. 1 is the flow diagram of specific embodiment of the invention method;
Fig. 2 is the structural block diagram of specific embodiment of the invention system.
Specific embodiment
To be easy to understand the technical means, the creative features, the aims and the efficiencies achieved by the present invention, below with reference to
Specific embodiment, the present invention is further explained.
As one embodiment, the present invention proposes a kind of method for predicting variable sliding time based on big data, including with
Lower step:
The historical data in airport coordinated decision system database is analyzed, flight for putting forth operation data is therefrom extracted, determines boat
The main affecting parameters of class's departure from port, and the weighted value of the items main affecting parameters is set, dynamic adjusts every main influence
The weight proportion of parameter;
The historical data for importing main affecting parameters carries out parameter learning, and the data for importing the major parameter obtained in the recent period are increased
Amount study promotes tree-model using gradient and is modeled, is fitted a basic function, obtain variable sliding time dynamic
Estimate model, the basic functionThe process of fitting are as follows:
(1)
(2)
(3)
Basic functionTraining step are as follows:
1) one group of cutting dimension j and cutting value S are found, so that the cutting dimension j and cutting value S meet formula (4), the public affairs
Formula (4) are as follows:
(4)
Wherein,,,;
2) input space is divided into two sub-regions by the training dataset (j, s) inputted with the step 1), and uses formula
(5) each corresponding output valve of subregion, the formula (5) are determined are as follows:
(5)
3) recursively each subregion is continued to divide, so that each subregion is further subdivided into two new subregions, and
Each corresponding output valve of new subregion is determined using step 1) and step 2, this step is recycled until meeting and stops item
Part.The stop condition is determined by the minimum sample number that incorporates subregion into or the depth capacity for establishing Taxonomy and distribution;
4) input space is divided into M region, Taxonomy and distribution is generated using formula (6), it is described
Formula (6) are as follows:
(6);
The real data of main affecting parameters is input in the variable sliding time dynamic estimation model, variable cunning is estimated
The probability distribution of dynamic time, calculates desired value, and the desired value is variable sliding time;
The variable sliding time is visualized;
Using the variable sliding time desired value of visual presentation, the clearance sequence of aircraft is carried out.
Also propose a kind of system that variable sliding time is predicted based on big data, comprising:
Parameter acquisition module: the historical data in analysis airport coordinated decision system database therefrom extracts flight for putting forth fortune
Row data, determine the main affecting parameters of flight for putting forth, and set the weighted value of every main affecting parameters, and dynamic adjusts
The weight proportion of every main affecting parameters;
Model buildings module: the historical data for importing main affecting parameters carries out parameter learning, imports the main ginseng obtained in the recent period
Several data carry out incremental learning, promote tree-model using gradient and are modeled, are fitted a basic function, obtaining can
Become sliding time dynamic estimation model, the basic functionThe process of fitting are as follows:
(1)
(2)
(3)
Basic functionTraining step are as follows:
1) one group of cutting dimension j and cutting value S are found, so that the cutting dimension j and cutting value S meet formula (4), the public affairs
Formula (4) are as follows::
(4)
Wherein,,,;
2) input space is divided into two sub-regions by the training dataset (j, s) inputted with the step 1), and uses formula
(5) each corresponding output valve of subregion, the formula (5) are determined are as follows:
(5)
3) recursively each subregion is continued to divide, so that each subregion is further subdivided into two new subregions, and
Each corresponding output valve of new subregion is determined using step 1) and step 2, this step is recycled until meeting and stops item
Part.The stop condition is determined by the minimum sample number that incorporates subregion into or the depth capacity for establishing Taxonomy and distribution;
4) input space is divided into M region, Taxonomy and distribution is generated using formula (6), it is described
Formula (6) are as follows:
(6);
Computing module: the real data of main affecting parameters is input in the variable sliding time dynamic estimation model, is estimated
The probability distribution for counting out variable sliding time, calculates desired value, and the desired value is variable sliding time;
Visualization model: the variable sliding time is visualized;
Resource distribution module: using the variable sliding time desired value visualized, the clearance sequence of aircraft is carried out.
By the design of this method and system, flight operation historical data is carried out based on the A-CDM system built
Collect and arrange, aircraft is slided from outgoing flight aircraft gate to takeoff runway using big data technology, or from landing runway
It slides to the port flight aircraft gate actually used time and is analyzed and excavated, to precisely predict next approach or outgoing flight
VTT, after obtaining VTT, by big data visualization technique, be intuitively presented to Gate Position Scheduling or blank pipe department and related be responsible for
People, which lets pass, to sort, and more accurately arranges the boarding of passenger, reduces the waiting time of passenger aboard;Reasonable arrangement is refueled, is removed
The resources such as ice machine, avoid as ground safeguard is not in place and caused by flight tardy problem generation etc., by the prediction of VTT,
It provides for decision-making management and accurately refers to, accurately grasp marketing data, reduce blind investment and repeated construction, realize the whole industry
Resource-sharing, reduces cost, takes with realizing airport and ensures more intelligent, and production process is more efficient, realizes seat in the plane reasonable distribution,
The free time for making full use of seat in the plane reduces the configuration of resource, reduces operation cost, improves flight punctuality rate, promotes passenger's clothes
It is engaged in quality, promotes flight and leave the port clearance rate, the precise arrangements boarding time.
Relatively good implementation of the present invention is described in detail below.
Current civil aviation authority, which has begun, promotes airport coordinated decision system (Airport Cooperation Decision
Making, A-CDM) construction, and be clearly understood that, variable coasting time in A-CDM (Variable Taxi Time,
VTT) parameter, for flight accurately take off in place and normally, blank pipe reasonable arrangement seat in the plane and optimization air route arrange etc., have very
Important meaning.The value of VTT is currently based on artificial experience and estimates at present, generally for different airports, same airport it is each
Terminal, each runway and remote/close estimated coasting time in seat in the plane were at 20 minutes to 60 minutes;But to specific aircraft gate and the aircraft
Takeoff runway between the time span that needs to slide, then can not accurately be estimated by existing method.
Based on the deployment to VTT, complete to engineering, shelter bridge, cleaning, oil plant, fleet, passenger facilities, airline, sky
The multi-sources such as pipe data acquisition on the basis of, integrate airport monitoring system, departure system, safe examination system, Gate Position Scheduling system,
The data such as blank pipe ground monitoring incorporate the data such as weather, Scheduled Flight, the passenger on each airport in the whole nation, inquired by Flight Information,
Weather warning, flight ensure the information such as control, seat in the plane early warning analysis, and on big data Visualization Platform, realization stops aircraft
By commander and related co-ordination, automatic, intelligence commander and distribution, realize flight operation control and each support link Business Stream
Cheng Youhua.
In short, VTT can generate guiding function actively, positive to Airport Operation Management thinking and operation mode, mainly
Including the following aspects:
(1) it pushes airport operations decision to drive from fuzzy micro-judgment to precision data, promotes single department service ability;
(2) service hoisting respectively stays the collaboration efficiency between a unit, promotes whole team implementation capacity;
(3) the delay disposition of large area flight is successfully managed, potential Mass disturbance occurrence probability is reduced;
(4) it helps Aerodrome Operations management to excavate big data value, realizes that self is evolved and upgrade entire operation flow;
(5) further push big data in the universal of Civil Aviation Industry.
Big data technology in civil aviaton's informationization using particularly significant and extensive, either civilian transport aviation is still led to
Pass through multiple view integration, multi-dimensional data analysis and more chart datas around safety, operation and the big theme of income three with aviation
View interaction linkage.
Referring to Fig. 1, proposing a kind of method for predicting variable sliding time based on big data, this method packet in the present embodiment
Include following steps:
S1 the historical data in airport coordinated decision system database) is analyzed, therefrom extracts flight for putting forth operation data, sufficiently
Analyze and excavate the factor for influencing VTT value, determine the main affecting parameters of flight for putting forth, main affecting parameters include runway,
Into/departure from port, early late peak, type/seat in the plane, weather, the world/country, the delay of large area flight etc. parameter, and set items
The weighted value of main affecting parameters, dynamic adjusts the weight proportion of every main affecting parameters in actual operation.
The application study of VTT in actual production.In civil aviation, due to the type of aircraft, stand, take off/
The difference of landing duty runway, the coasting time of aircraft is also different.It can be more accurately predicted and be sailed using VTT
Class takes off or enters the time.Meanwhile significant data resource of the time parameter as blank pipe, blank pipe reasonably optimizing can be helped to navigate
Road arranges, thus reduce to the greatest extent as flow control and caused by flight be delayed.Rearrangement for outgoing flight can close as far as possible
Reason arranges the existing resource of airport, blank pipe and aviation public affairs;For the flight that approaches, aircraft gate can be more reasonably arranged.
S2 the historical data for) importing main affecting parameters carries out parameter learning, imports the number of the major parameter obtained in the recent period
According to incremental learning is carried out, tree-model is promoted using gradient and is modeled, a basic function is fitted, target is to find one
Group basic function, make basic function'sThe effect that function is fitted historical data reaches most preferably, obtains
Variable sliding time dynamic estimation model, basic functionThe process of fitting are as follows:
(1)
(2)
(3)
Gradient boosted tree generallys use Taxonomy and distribution (CART) as basic function.
Wherein, basic functionTraining step are as follows:
S21 one group of cutting dimension j and cutting value S) are found, so that cutting dimension j and cutting value S meet formula (4), formula (4)
Are as follows:
(4)
Wherein,,,;
S22) input space is divided into two sub-regions by the training dataset (j, s) inputted with step 1), and uses formula
(5) the corresponding output valve of each subregion, formula (5) are determined are as follows:
(5)
S23) recursively each subregion is continued to divide, so that each subregion is further subdivided into two new subregions,
And use step S21) and step S22) determine each corresponding output valve of new subregion, it recycles this step and stops until meeting
Condition.The stop condition is determined by the minimum sample number that incorporates subregion into or the depth capacity for establishing Taxonomy and distribution
It is fixed;
S24 the input space) is divided into M region, Taxonomy and distribution, formula are generated using formula (6)
(6) are as follows:
(6).
S3) real data of main affecting parameters is input in variable sliding time dynamic estimation model, estimating can
The probability distribution for becoming sliding time, calculates desired value, desired value is VTT, while practicing, correcting using a large amount of operations, is made
The model desired value and true value error finally used is minimum, using final model desired value as reckoning as a result, can ensure
The VTT of prediction and practical VTT error were less than 5 minutes;
S4 the research that shows) is realized according to big data visualization technique, for different application scene, by Google Chart,
The tools such as D3, Tableau, HightCharts or Datawrapper are visualized, by the complicated uninteresting VTT number of magnanimity
According to figure, by way of table, by different dimensions such as geographical space, time series or logical relations, by visual element such as shape,
Position, color, text, symbol etc. are shown, and understand the rule and value of data behind in the short time in practical applications, real
Existing General Promotion of the civil aviation field from passenger facilities to administrative decision.
The developing direction on " wisdom airport " is proposed in Civil Aviation Industry, it would be desirable to modern information technologies are made full use of, to airliner
Field passenger and freight transportation guarantee and digital management, visualization are presented, intelligence is supported, gradually the imparting more and more wisdom in airport,
Guarantee efficiency, the Service Quality of the links such as production, safety, service, logistics, management, traffic, business and the environmental protection on airport are improved comprehensively
Amount and management level.But it " wisdom airport " concept and has a wide extension, rarely has successful case at present, we pay close attention to the life on airport
Link is produced, from the visual angle of A-CDM system Construction, carries out the informationization and big data visualization in terms of flight is run with operation management
Construction.It connects to form information sharing, information integration or synthetic operation by the system that business platform is closely related airport;
Then on the basis of data interconnection intercommunication, data acquisition, data cleansing, data mining are realized, big data visualization is realized, has
Help Civil Aviation Industry site administrator and promotes business efficiency.
S5) computation rule of wheel time (Target OFF-Block Time, TOBT) is removed on airport according to target, is calculated
ATM Bureau is submitted to after TOBT, airport provides TOBT as calculating to ATM Bureau by A-CDM and removes wheel time (Calculated
OFF-Block Time, COBT) calculation basis, the calculation method of computation rule are as follows: TOBT=E.T.A
(Estimated Time of Arrival, ETA)+VTT+ minimum misses the stop and ensures time (Minimum Turn-round
Time, MTTT), then the wheel time is removed into calculating by ATM Bureau and is distributed to airport, blank pipe recycles variable sliding time to navigate departure from port
Class resequences, thus the existing resource on reasonable arrangement airport, blank pipe and airline.
Referring to Fig. 2, referring to Fig. 1, also proposing a kind of to predict variable sliding time based on big data in the present embodiment
System, method includes the following steps:
Parameter acquisition module: the historical data in analysis airport coordinated decision system database therefrom extracts flight for putting forth fortune
Row data are sufficiently analyzed and are excavated the factor for influencing VTT value, determine the main affecting parameters of flight for putting forth, main to influence ginseng
Number includes runway, is delayed etc. parameter into/departure from port, early late peak, type/seat in the plane, weather, the world/country, large area flight,
And the weighted value of every main affecting parameters is set, dynamic adjusts the weight ratio of every main affecting parameters in actual operation
Example.
The application study of VTT in actual production.In civil aviation, due to the type of aircraft, stand, take off/
The difference of landing duty runway, the coasting time of aircraft is also different.It can be more accurately predicted and be sailed using VTT
Class takes off or enters the time.Meanwhile significant data resource of the time parameter as blank pipe, blank pipe reasonably optimizing can be helped to navigate
Road arranges, thus reduce to the greatest extent as flow control and caused by flight be delayed.Rearrangement for outgoing flight can close as far as possible
Reason arranges the existing resource of airport, blank pipe and aviation public affairs;For the flight that approaches, aircraft gate can be more reasonably arranged.
Model buildings module: the historical data for importing main affecting parameters carries out parameter learning, imports the master obtained in the recent period
It wants the data of parameter to carry out incremental learning, tree-model is promoted using gradient and is modeled, a basic function is fitted, mesh
Mark is to find one group of basic function, make basic function'sThe effect that function is fitted historical data reaches
To best, variable sliding time dynamic estimation model, basic function are obtainedThe process of fitting are as follows:
(1)
(2)
(3)
Gradient boosted tree generallys use Taxonomy and distribution (CART) as basic function.
Wherein, basic functionTraining step are as follows:
S1) input cutting dimension j and cutting value s, is handled cutting dimension j and cutting value s using formula (4), formula (4)
Are as follows:
(4)
Wherein,,,;
S2) input space is divided into two sub-regions by the training dataset (j, s) inputted with step 1), and uses formula (5)
Determine the corresponding output valve of each subregion, formula (5) are as follows:
(5)
S3) recursively each subregion is continued to divide, so that each subregion is further subdivided into two new subregions, and
Using step S1) and step S2) determine each corresponding output valve of new subregion, this step, which is recycled, until meeting stops item
Part.The stop condition is determined by the minimum sample number that incorporates subregion into or the depth capacity for establishing Taxonomy and distribution;
S4 the input space) is divided into M region, Taxonomy and distribution, formula (6) are generated using formula (6)
Are as follows:
(6).
Computing module: the real data of main affecting parameters is input in variable sliding time dynamic estimation model, is estimated
The probability distribution for counting out variable sliding time, calculates desired value, desired value is VTT, while practicing, repairing using a large amount of operations
Just, make the model desired value finally used and true value error minimum, using final model desired value as reckoning as a result, can
The VTT for ensureing prediction and practical VTT error were less than 5 minutes;
Visualization model: realize that the research showed passes through Google for different application scene according to big data visualization technique
The tools such as Chart, D3, Tableau, HightCharts or Datawrapper are visualized, and magnanimity complexity is uninteresting
VTT data figure, by way of table, by different dimensions such as geographical space, time series or logical relations, pass through visual element
Such as shape, position, color, text, symbol are shown, understand in the short time in practical applications data behind rule and
Value realizes General Promotion of the civil aviation field from passenger facilities to administrative decision.
The developing direction on " wisdom airport " is proposed in Civil Aviation Industry, it would be desirable to modern information technologies are made full use of, to airliner
Field passenger and freight transportation guarantee and digital management, visualization are presented, intelligence is supported, gradually the imparting more and more wisdom in airport,
Guarantee efficiency, the Service Quality of the links such as production, safety, service, logistics, management, traffic, business and the environmental protection on airport are improved comprehensively
Amount and management level.But it " wisdom airport " concept and has a wide extension, rarely has successful case at present, we pay close attention to the life on airport
Link is produced, from the visual angle of A-CDM system Construction, carries out the informationization and big data visualization in terms of flight is run with operation management
Construction.It connects to form information sharing, information integration or synthetic operation by the system that business platform is closely related airport;
Then on the basis of data interconnection intercommunication, data acquisition, data cleansing, data mining are realized, big data visualization is realized, has
Help Civil Aviation Industry site administrator and promotes business efficiency.
Resource distribution module: it is advised according to the calculating that target removes wheel time (Target OFF-Block Time, TOBT) on airport
Then, ATM Bureau is submitted to after calculating TOBT, airport provides TOBT as calculating to ATM Bureau by A-CDM and removes the wheel time
The calculation basis of (Calculated OFF-Block Time, COBT), the calculation method of computation rule are as follows: TOBT=expect
It misses the stop up to time (Estimated Time of Arrival, ETA)+VTT+ minimum and ensures time (Minimum Turn-
Round Time, MTTT), then the wheel time is removed into calculating by ATM Bureau and is distributed to airport, blank pipe recycles variable sliding time pair
Outgoing flight is resequenced, thus the existing resource on reasonable arrangement airport, blank pipe and airline.
A-CDM system can accomplish according to the push of VTT:
(1) boarding time for more accurately arranging passenger reduces the waiting time of passenger aboard;
(2) resources such as reasonable arrangement oiling, deicing vehicle, avoid as ground safeguard is not in place and caused by flight delay etc..
The time point including following four publication can be issued before flight landing and when landing automatically: flight planning generation,
Front is taken off, our station takes off first 55 minutes (flight does not land) and flight landing, and airport is calculated according to the computation rule of TOBT
ATM Bureau is submitted after TOBT, calculation method is as follows:
It calculates for the first time: when flight planning generates, TOBT=planned time;
Before landing: TOBT=ETA+VTT+minimum, which is missed the stop, ensures the time;
After landing: TOBT=current time+residue support mission is maximum time-consuming.
For the present embodiment, the computation rule of MTTT refering to table 1, specifically:
Table 1
I.e. 60 and 60 aircrafts below are 40 minutes, and 61 to 150 aircrafts are 50 minutes, 151 to 250
Aircraft be 60 minutes, 251 to 500 aircrafts are 75 minutes, and 500 or more aircrafts are 120 minutes.
The VTT value that this method predicts can be also used for Gate Position Scheduling, aircraft landing to entering the time consumed by position, by
To the influence of the uncontrollable factors such as runway, weather, type, flight, seat in the plane.In order to reduce flight risk of time delay, while improving ground
Face ensures the timeliness of service, to the coasting time of aircraft by the way of based on big data visualization technique and machine learning
Calculated, according to the VTT for the flight that approaches, the holding time of each seat in the plane and the prediction of conflict time are more quasi- when to Gate Position Scheduling
Really, be conducive to making full use of for seat in the plane resource.
Civil Aviation Industry faces a significant challenge so far, i.e. flight delay is possible to because other emergency events, which develop, becomes boat
Class's large area delay.
When the delay of large area flight does not occur, VTT can help blank pipe reasonably optimizing air route to arrange, to reduce flight
Delay.Analysis mining is carried out by the data to airport coordinated decision system, Visual Chart mode shows, effectively auxiliary
Production is helped to improve efficiency.It can help airport reasonable distribution seat in the plane resource.From runway, check-in sales counter, boarding gate, seat in the plane, type
Intelligent Gate Position Scheduling is realized etc. multiple dimensional analysis.Under the premise of guaranteeing ground flying safety, pass through the rational management of resource
With distribute rationally, aircraft gate utilization rate and ground service quality are improved, thus Improve Efficiency.
When large area flight, which is delayed, to be occurred, the clearance sequencing management of blank pipe is particularly important, may be implemented to depart from port by VTT
The rearrangement of flight, can reasonable arrangement airport, airline and blank pipe as far as possible existing resource;Make flight can be with quickly and orderly
The case where ground takes off, and alleviates the delay aggravation of large area flight from microcosmic point.
The VTT predicted by this method can be with expanded application in General Aviation.By right in civil aviation
The practical application of VTT analyzes the concrete condition of General Aviation and is applied, thus realize General Aviation medical aid, agriculture,
The application in the fields such as woods, fishing and scientific research much sooner, efficiently, change information not in time, inaccuracy, uncontrollable status, promoted
Service experience.
Bring achievement in VTT practical application can be embodied by the change of the indexs of correlation such as production efficiency.Including big
In the case of the delay of area flight, the lifting values of regular rate of scheduled flight;The value added of airport passenger and goods postal handling capacity, and it is practical raw
The promotion degree and the increasing degree of running income etc. of working efficiency during production.
In conclusion the present invention has the advantages that based on the A-CDM system built to flight run historical data into
Row is collected and is arranged, and is slided from outgoing flight aircraft gate to takeoff runway using big data technology to aircraft, or is run from landing
Road slides to the port flight aircraft gate actually used time and is analyzed and excavated, to precisely predict next boat that approaches or depart from port
The VTT of class after obtaining VTT, by big data visualization technique, is intuitively presented to Gate Position Scheduling or blank pipe department and correlation is negative
People's clearance sequence is blamed, the boarding of passenger is more accurately arranged, reduces the waiting time of passenger aboard;Reasonable arrangement oiling,
The resources such as deicing vehicle, avoid as ground safeguard is not in place and caused by flight tardy problem generation etc., pass through the pre- of VTT
It surveys, provides for decision-making management and accurately refer to, accurately grasp marketing data, reduce blind investment and repeated construction, realize full row
The resource-sharing of industry, reduces cost, takes with realizing airport and ensures more intelligent, production process is more efficient, realizes that seat in the plane is reasonable
Distribution, makes full use of the free time of seat in the plane, reduces the configuration of resource, reduces operation cost, improves flight punctuality rate, promotes trip
Objective service quality promotes flight and leaves the port clearance rate, the precise arrangements boarding time.
As known by the technical knowledge, the present invention can pass through the embodiment party of other essence without departing from its spirit or essential feature
Case is realized.Therefore, embodiment disclosed above, in all respects are merely illustrative, not the only.Institute
Have within the scope of the present invention or is included in the invention in the change being equal in the scope of the present invention.
Claims (10)
1. a kind of method for predicting variable sliding time based on big data, it is characterised in that: the following steps are included:
The historical data in airport coordinated decision system database is analyzed, flight for putting forth operation data is therefrom extracted, determines boat
The main affecting parameters of class's departure from port, and the weighted value of the items main affecting parameters is set, dynamic adjusts every main influence
The weight proportion of parameter;
The historical data for importing main affecting parameters carries out parameter learning, and the data for importing the major parameter obtained in the recent period are increased
Amount study promotes tree-model using gradient and is modeled, is fitted a basic function, obtain variable sliding time dynamic
Estimate model, the basic functionThe process of fitting are as follows:
(1)
(2)
(3)
Basic functionTraining step are as follows:
1) one group of cutting dimension j and cutting value S are found, so that the cutting dimension j and cutting value S meet formula (4), the public affairs
Formula (4) are as follows:
(4)
Wherein,,,;
2) input space is divided into two sub-regions by the training dataset (j, s) inputted with the step 1), and uses formula
(5) each corresponding output valve of subregion, the formula (5) are determined are as follows:
(5)
3) recursively each subregion is continued to divide, so that each subregion is further subdivided into two new subregions, and
Each corresponding output valve of new subregion is determined using step 1) and step 2, this step is recycled until meeting and stops item
Part, the stop condition are determined by the minimum sample number that incorporates subregion into or the depth capacity for establishing Taxonomy and distribution;
4) input space is divided into M region, Taxonomy and distribution is generated using formula (6), it is described
Formula (6) are as follows:
(6);
The real data of main affecting parameters is input in the variable sliding time dynamic estimation model, variable cunning is estimated
The probability distribution of dynamic time, calculates desired value, and the desired value is variable sliding time;
The variable sliding time is visualized;
Using the variable sliding time desired value of visual presentation, the clearance sequence of aircraft is carried out.
2. a kind of method for predicting variable sliding time based on big data according to claim 1, it is characterised in that: described
Main affecting parameters include runway, prolong into/departure from port, early late peak, type/seat in the plane, weather, the world/country, large area flight
Accidentally parameter.
3. a kind of method for predicting variable sliding time based on big data according to claim 1, it is characterised in that: to institute
It states variable sliding time to be visualized, specifically include:
For different application scene, carried out by Google Chart, D3, Tableau, HightCharts or Datawrapper
It visualizes, by variable sliding time by way of figure, table, by geographical space, time series or logical relation different dimensional
Degree, is shown by visual element such as shape, position, color, text, symbol.
4. a kind of method for predicting variable sliding time based on big data according to claim 1, it is characterised in that: utilize
The variable sliding time desired value visualized carries out the clearance sequence of aircraft, specifically includes:
The computation rule of wheel time is removed on airport according to target, is calculated after target removes the wheel time and is submitted to ATM Bureau, airport passes through
The airport coordinated decision system, which to ATM Bureau provides target, to be removed the wheel time as calculating and removes the calculation basis for taking turns the time, then by sky
Calculating is removed the wheel time and is distributed to airport by pipe office, and blank pipe recycles variable sliding time to resequence outgoing flight, from
And the existing resource on reasonable arrangement airport, blank pipe and airline.
5. a kind of method for predicting variable sliding time based on big data according to claim 4, it is characterised in that: described
The calculation method of computation rule are as follows:
Target removes wheel time=E.T.A+and variable sliding time+minimum misses the stop and ensures the time;
The minimum, which is missed the stop, ensures the computation rule of time are as follows:
60 and 60 aircrafts below are 40 minutes, and 61 to 150 aircrafts are 50 minutes, 151 to 250
Aircraft is 60 minutes, and 251 to 500 aircrafts are 75 minutes, and 500 or more aircrafts are 120 minutes.
6. a kind of system for predicting variable sliding time based on big data, it is characterised in that: include:
Parameter acquisition module: the historical data in analysis airport coordinated decision system database is therefrom extracted and is sailed
Class's departure from port operation data, determines the main affecting parameters of flight for putting forth, and sets the power of every main affecting parameters
Weight values, dynamic adjust the weight proportion of every main affecting parameters;
Model buildings module: the historical data for importing main affecting parameters carries out parameter learning, imports the main ginseng obtained in the recent period
Several data carry out incremental learning, promote tree-model using gradient and are modeled, are fitted a basic function, obtaining can
Become sliding time dynamic estimation model, the basic functionThe process of fitting are as follows:
(1)
(2)
(3)
Basic functionTraining step are as follows:
1) one group of cutting dimension j and cutting value S are found, so that the cutting dimension j and cutting value S meet formula (4), the public affairs
Formula (4) are as follows::
(4)
Wherein,,,;
2) input space is divided into two sub-regions by the training dataset (j, s) inputted with the step 1), and uses formula
(5) each corresponding output valve of subregion, the formula (5) are determined are as follows:
(5)
3) recursively each subregion is continued to divide, so that each subregion is further subdivided into two new subregions, and
Each corresponding output valve of new subregion is determined using step 1) and step 2, this step is recycled until meeting and stops item
Part, the stop condition are determined by the minimum sample number that incorporates subregion into or the depth capacity for establishing Taxonomy and distribution;
4) input space is divided into M region, Taxonomy and distribution is generated using formula (6), it is described
Formula (6) are as follows:
(6);
Computing module: the real data of main affecting parameters is input to the variable sliding time dynamic estimation mould
In type, the probability distribution of variable sliding time is estimated, desired value is calculated, when the desired value is variable sliding
Between;
Visualization model: the variable sliding time is visualized;
Resource distribution module: using the variable sliding time desired value visualized, the clearance sequence of aircraft is carried out.
7. a kind of system for predicting variable sliding time based on big data according to claim 6, it is characterised in that: described
Main affecting parameters include runway, prolong into/departure from port, early late peak, type/seat in the plane, weather, the world/country, large area flight
Accidentally parameter.
8. a kind of system for predicting variable sliding time based on big data according to claim 16, it is characterised in that: institute
Visualization model is stated to specifically include:
For different application scene, carried out by Google Chart, D3, Tableau, HightCharts or Datawrapper
It visualizes, by variable sliding time by way of figure, table, by geographical space, time series or logical relation different dimensional
Degree, is shown by visual element such as shape, position, color, text, symbol.
9. a kind of system for predicting variable sliding time based on big data according to claim 6, it is characterised in that: described
Resource distribution module specifically includes:
The computation rule of wheel time is removed on airport according to target, is calculated after target removes the wheel time and is submitted to ATM Bureau, airport passes through
The airport coordinated decision system, which to ATM Bureau provides target, to be removed the wheel time as calculating and removes the calculation basis for taking turns the time, then by sky
Calculating is removed the wheel time and is distributed to airport by pipe office, and blank pipe recycles variable sliding time to resequence outgoing flight, from
And the existing resource on reasonable arrangement airport, blank pipe and airline.
10. a kind of system for predicting variable sliding time based on big data according to claim 9, it is characterised in that: institute
State the calculation method of computation rule are as follows:
Target removes wheel time=E.T.A+and variable sliding time+minimum misses the stop and ensures the time;
The minimum, which is missed the stop, ensures the computation rule of time are as follows:
60 and 60 aircrafts below are 40 minutes, and 61 to 150 aircrafts are 50 minutes, 151 to 250
Aircraft is 60 minutes, and 251 to 500 aircrafts are 75 minutes, and 500 or more aircrafts are 120 minutes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910674628.2A CN110363361A (en) | 2019-07-25 | 2019-07-25 | A kind of method and system for predicting variable sliding time based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910674628.2A CN110363361A (en) | 2019-07-25 | 2019-07-25 | A kind of method and system for predicting variable sliding time based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110363361A true CN110363361A (en) | 2019-10-22 |
Family
ID=68220778
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910674628.2A Pending CN110363361A (en) | 2019-07-25 | 2019-07-25 | A kind of method and system for predicting variable sliding time based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110363361A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110852497A (en) * | 2019-10-30 | 2020-02-28 | 南京智慧航空研究院有限公司 | Scene variable slide-out time prediction system based on big data deep learning |
CN112489453A (en) * | 2020-11-18 | 2021-03-12 | 安徽四创电子股份有限公司 | Traffic signal intelligent adjusting method based on neural network |
CN113537555A (en) * | 2021-06-03 | 2021-10-22 | 太原理工大学 | Traffic sub-region model prediction sliding mode boundary control method considering disturbance |
CN114360299A (en) * | 2022-01-11 | 2022-04-15 | 青岛民航凯亚系统集成有限公司 | Airport aircraft towing automatic planning method |
CN115392886A (en) * | 2022-10-28 | 2022-11-25 | 中国民用航空总局第二研究所 | Time reporting method, time reporting device, storage medium and processor of arrival airplane |
WO2023197452A1 (en) * | 2022-04-11 | 2023-10-19 | 中国电子科技集团公司第二十八研究所 | Time-to-space conversion method for flight sequencing information |
CN116956757A (en) * | 2023-09-21 | 2023-10-27 | 中国民航工程咨询有限公司 | Departure flight taxi time prediction method, electronic device, and storage medium |
CN118114952A (en) * | 2024-04-25 | 2024-05-31 | 青岛民航凯亚系统集成有限公司 | Rolling time domain dynamic allocation method and system for civil airport organization boarding tasks |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6069539A (en) * | 1999-05-27 | 2000-05-30 | Cisco Technology, Inc. | VTT power distribution system |
CN106339358A (en) * | 2016-08-16 | 2017-01-18 | 南京航空航天大学 | Prediction method of aircraft scene taxiing time based on multiple regression analysis |
-
2019
- 2019-07-25 CN CN201910674628.2A patent/CN110363361A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6069539A (en) * | 1999-05-27 | 2000-05-30 | Cisco Technology, Inc. | VTT power distribution system |
CN106339358A (en) * | 2016-08-16 | 2017-01-18 | 南京航空航天大学 | Prediction method of aircraft scene taxiing time based on multiple regression analysis |
Non-Patent Citations (3)
Title |
---|
冯霞: "《基于KNN和SVR的航班滑出时间预测》", 《西南交通大学学报》 * |
图灵的猫I: "《对梯度提升树(GBDT)的通俗理解》", 《CSDN博客》 * |
无: "《现行机型最少过站时间标准》", 《百度文库》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110852497A (en) * | 2019-10-30 | 2020-02-28 | 南京智慧航空研究院有限公司 | Scene variable slide-out time prediction system based on big data deep learning |
CN112489453A (en) * | 2020-11-18 | 2021-03-12 | 安徽四创电子股份有限公司 | Traffic signal intelligent adjusting method based on neural network |
CN112489453B (en) * | 2020-11-18 | 2022-03-29 | 安徽四创电子股份有限公司 | Traffic signal intelligent adjusting method based on neural network |
CN113537555A (en) * | 2021-06-03 | 2021-10-22 | 太原理工大学 | Traffic sub-region model prediction sliding mode boundary control method considering disturbance |
CN113537555B (en) * | 2021-06-03 | 2023-04-11 | 太原理工大学 | Traffic sub-region model prediction sliding mode boundary control method considering disturbance |
CN114360299A (en) * | 2022-01-11 | 2022-04-15 | 青岛民航凯亚系统集成有限公司 | Airport aircraft towing automatic planning method |
CN114360299B (en) * | 2022-01-11 | 2023-05-12 | 青岛民航凯亚系统集成有限公司 | Automatic planning method for towing of airport aircraft |
WO2023197452A1 (en) * | 2022-04-11 | 2023-10-19 | 中国电子科技集团公司第二十八研究所 | Time-to-space conversion method for flight sequencing information |
CN115392886A (en) * | 2022-10-28 | 2022-11-25 | 中国民用航空总局第二研究所 | Time reporting method, time reporting device, storage medium and processor of arrival airplane |
CN116956757A (en) * | 2023-09-21 | 2023-10-27 | 中国民航工程咨询有限公司 | Departure flight taxi time prediction method, electronic device, and storage medium |
CN118114952A (en) * | 2024-04-25 | 2024-05-31 | 青岛民航凯亚系统集成有限公司 | Rolling time domain dynamic allocation method and system for civil airport organization boarding tasks |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110363361A (en) | A kind of method and system for predicting variable sliding time based on big data | |
CN104751681B (en) | Statistical learning model based gate position allocation method | |
CN109711619B (en) | Multi-machine-field strategic flight time collaborative optimization method considering air-ground operation restriction | |
CN107944625B (en) | Single-airport flight season change time slot optimization method based on historical operation data driving | |
CN103761585B (en) | Continue transport Dynamic Matching, transport power monitoring and early warning and intelligent dispatching method on airport | |
Chen et al. | Toward a more realistic, cost-effective, and greener ground movement through active routing: a multiobjective shortest path approach | |
CN104751683A (en) | Airport plane taxi scheduling and commanding system and method | |
CN105023068A (en) | Rule mining based flight arrival and departure cooperative scheduling method | |
CN109741638B (en) | Integrated collaborative operation method for entering and leaving field management system | |
CN110378537A (en) | A kind of method and system of airport aircraft gate smart allocation | |
CN110335506A (en) | A kind of termination environment airspace utilization rate calculation method in short-term | |
CN109544000A (en) | Airline towards View of Flight On-time Performance arranges an order according to class and grade plan optimization method and system | |
CN107341620B (en) | BADA fuel consumption rate-based method for calculating delay cost of incoming flights in short-term weather | |
CN105528647A (en) | Airport traffic demand possibility prediction method based on big data analysis | |
CN115081699A (en) | Flight unit scheduling method in public air transportation of large aircraft | |
CN112633562A (en) | Intelligent scheduling method for airport parking positions | |
Ahmadi et al. | Airport operations with electric-powered towing alternatives under stochastic conditions | |
CN102663262A (en) | Flight wave property cost accounting method based on immune algorithm | |
CN112862258B (en) | Limited-nature flight recovery method considering passenger preference | |
Ashford et al. | Passenger behavior and design of airport terminals | |
Rodič et al. | Airport ground crew scheduling using heuristics and simulation | |
Lee | Tradeoff evaluation of scheduling algorithms for terminal-area air traffic control | |
Liu et al. | Modeling and heuristic algorithm of ground ferry vehicle scheduling in large airports | |
CN113947296A (en) | Flight delay recovery method based on multi-agent system | |
Su et al. | Integrated Optimization of Aircraft Surface Operation and De-Icing Resources at Multi De-Icing Zones Airport |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191022 |
|
RJ01 | Rejection of invention patent application after publication |