CN107018019B - A kind of flight delay propagation characteristic analysis method based on complicated evolved network - Google Patents
A kind of flight delay propagation characteristic analysis method based on complicated evolved network Download PDFInfo
- Publication number
- CN107018019B CN107018019B CN201710202141.5A CN201710202141A CN107018019B CN 107018019 B CN107018019 B CN 107018019B CN 201710202141 A CN201710202141 A CN 201710202141A CN 107018019 B CN107018019 B CN 107018019B
- Authority
- CN
- China
- Prior art keywords
- node
- network model
- evolved network
- evolved
- delay
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 30
- 230000003111 delayed effect Effects 0.000 claims abstract description 19
- 238000010276 construction Methods 0.000 claims description 21
- 238000004088 simulation Methods 0.000 claims description 10
- 230000006854 communication Effects 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 8
- 238000005315 distribution function Methods 0.000 claims 8
- 238000011217 control strategy Methods 0.000 claims 1
- 238000005290 field theory Methods 0.000 claims 1
- 238000011084 recovery Methods 0.000 claims 1
- 238000000034 method Methods 0.000 abstract description 16
- 230000000644 propagated effect Effects 0.000 abstract description 7
- 230000015572 biosynthetic process Effects 0.000 abstract description 6
- 230000008569 process Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005511 kinetic theory Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of, and the flight based on complicated evolved network is delayed propagation characteristic analysis method, it is related to Flight Information analysis technical field, the present invention is more biased towards according to airport node in the characteristic being connected with the biggish side of course line passenger flow, it establishes based on side right preferentially regular aviation evolved network model, and then on constructed evolved network model, adjust network parameter, it studies flight and is delayed the different propagation characteristics on air net, the propagation characteristic in air net can not be delayed from the network perspective research flight of macroscopic view by solving in existing flight Delay method, network parameter cannot effectively be changed, it can not be embodied in the Dynamic Evolution of air net formation, the technical issues of different-effect that flight delay is propagated.
Description
Technical field
The present invention relates to Flight Information analysis technical fields, and in particular to a kind of flight delay based on complicated evolved network
Propagation characteristic analysis method.
Background technique
In recent years, as the rapid development of aircraft industry, the demand of air transportation continue to increase, the flight generated therewith is delayed
Problem also has been to be concerned by more and more people.Studies have shown that flight delay can be as the resources such as aircraft, unit be in air net
It is propagated.Meanwhile for different types of airport, network etc., the communication effect of delay is not quite similar.Therefore, delay is sought
Mechanism of transmission in Route Network understands its propagating characteristic in a network, and provide reasonable delay control means at
For airport, airline's urgent problem to be solved.
Currently, the research for the delay propagation problem in air transportation provides mostly from microcosmic angle for same aircraft
The delay of source research upstream flight is influenced caused by subsequent flight bunches, and the representative method of such means has: Bayesian model, row
Team theory etc.;Or the method using proof analysis, flight operational effect is assessed by flight planning, and then analyze delay
The characteristics of propagation, main method are statistical analysis methods.
In general, when delay occur in certain airport node, can under the action of more resources such as aircraft, unit, passenger, to
Other airports are propagated, if not being controlled, delay will finally diffuse to whole network.Therefore, only consider to act on single flight
Microscopic Research Methods, such as Bayesian model are propagated in the delay of string, and queueing theory etc. is not particularly suited for the network perspective from macroscopic view, are seen
The propagation characteristic of delay over the entire network is examined, delay is disclosed and propagates the unified rule on network.On the other hand, air transportation
Complex network of the network as a uncalibrated visual servo, the either network parameters such as number of nodes or the course line volume of the flow of passengers, formed with
Development is all the process gradually to develop.Using the statistical analysis technique of real diagnosis, network parameter cannot be changed, can not be embodied
In the Dynamic Evolution of network, when such as the variation of the course line volume of the flow of passengers, delayed communication effect.Therefore, complex web is utilized
The rule of development of the kinetic theory overall view air net of network, the difference spy for disclosing its formation mechenism, analysis delay dissemination
When point, irreplaceable superiority is shown.
To sum up, disadvantage of the existing technology has: can not be delayed from the network perspective research flight of macroscopic view in air net
In propagation characteristic;Existing method cannot effectively change network parameter, can not be embodied in the dynamic evolution of air net formation
In the process, the different-effect that flight delay is propagated.
Summary of the invention
The object of the present invention is to provide a kind of, and the flight based on complicated evolved network is delayed propagation characteristic analysis method, solves
It can not be from the propagation of the network perspective research flight delay of macroscopic view in air net in existing flight Delay method
Characteristic cannot effectively change network parameter, can not be embodied in the Dynamic Evolution of air net formation, and flight delay passes
The technical issues of different-effect broadcast.
To achieve the above object, the invention adopts the following technical scheme:
A kind of flight delay propagation characteristic analysis method based on complicated evolved network, includes the following steps:
Step 1: establishing Hadoop server cluster, client-server, data are established in Hadoop server cluster
Library module, evolved network model construction module and delay simulation analysis module, client-server, database module, evolution net
Pass through internet communication between network model construction module and delay simulation analysis module;
Step 2: setting each airport is a node, and the line between two nodes is a course line, each
Course line is a side;User inputs the quantity on airport and the volume of the flow of passengers information in all course lines by client-server, and raw
Network parameter is produced, client-server sends the network parameter to database module and stores;
Step 3: evolved network model construction module by the network parameter in internet reading database, by with
Lower step establishes evolved network model:
Step A: evolved network model construction module establishes evolved network model: evolved network model construction module root
According to the network parameter, determines that the sum of the node in evolved network model is N, set the start node of evolved network model
Number is n0, the item number of initial edge is e0;Set side eijFor any one side in evolved network model, side eijWeight be
wij, wherein i is side eijThe number of node that is connected of one end, j is side eijThe number of node that is connected of the other end, just
Beginning sets weight as W0;
Step B: it is t that setting time, which walks parameter, sets the initial value of t as t=0;
Step C: evolved network model construction module is added a new node n into evolved network model, new node n with drill
The number for changing the side being connected in network model is m, and m is less than e0Positive integer;
New node n is with probabilitySelect side eij;Wherein
Local indicates current evolved network model;T indicates time step,
mt+e0And MtIndicate total number of edges of network at this time, ∑localwijIndicate total weight of current network;
Step D: new node n is with Probability p and side eijEnd point be connected, new node n is with probability 1-p and side eijIt is another
Endpoint is connected;New node n causes side eijSide right increase δ, i.e. wij=wij+δ;
Step E: calculating and updates n0=n0+1;It calculates and updates t=t+1;
Step F: step C is repeated to step E, until n0Value be greater than N value, execute step 4;
Step 4: setup parameter ε;When the number of nodes in evolved network model is equal to the total N of node, evolved network mould
Type stops increasing, at this point, the angle value of all nodes of evolved network model is it has been determined that the calculating of evolved network model construction module is drilled
Change the degree distribution function p (k1) of network model, spends distribution function P (k2) be fitted to obtain by the airport degree of selected real network,
Wherein k2Indicate the angle value of real nodes;Machine in degree distribution function p (k1) and selected real air net
The degree distribution function P (k of field2) variance analysis is carried out, gained variance is R2, spend distribution functionWherein power rate exponent gamma=(1+p+2 δ)/(p+ δ), k1 indicate to save in evolved network model
The angle value of point;Work as R2When < ε, evolved network model foundation is completed;Work as R2When > ε, evolved network model construction module adjusts W0、N、
The value of p and δ, and execute step B;
Step 5: delay simulation analysis module reads the evolution by internet from evolved network model construction module
Network model, and construct the flight delay based on airport node by following steps and propagate ASIR model:
Step G: S is definedk(t)、Ik(t) and Rk(t) respectively indicate the normal node of angle value in evolved network model equal to k,
Delay node and delay vanished node account for the ratio for the node that all angle value are k, S in t momentk(t)、Ik(t) and Rk(t) between
Relational expression are as follows:
Sk(t)+Ik(t)+Rk(t)=1;
Step H: definition probability of spreading is λk, it is that χ, recovery rate μ set μ=1 without loss of generality that probability is exempted from mistake;
Step J: according to mean field theory, it is delayed simulation analysis module and is existed according to following differential equation group calculating ASIR model
Communication process in evolved network model:
In the differential equation group: probability of spreading Indicate that angle value is the node of k
Point intensity, NkIt is the set for the node being connected with the node that angle value is k, defines smax=kwmaxIt is evolved network model moderate
Value is the maximum point intensity of the node of k;Defining q is external interference parameter;Θ (I (t)) indicates that angle value is that any of node of k gives
Deckle is delayed the probability that node is connected with one, considers the scales-free network of dereferenced, then:
Θ (I (t))=∑kkP(k)Ik(t)/<k>, wherein<k>=∑k∈NKP (k) indicates being averaged for evolved network model
Angle value;
Step K: user is passed through by the given node initially to involve a delay of client-server, delay simulation analysis module
Internet obtains the node initially to involve a delay from client-server, and by adjusting parameter δ and q, observes in different ginsengs
Under several, Sk(t)、Ik(t) and Rk(t) the slope of curve and peak value difference obtain being delayed propagation rate and range feelings accordingly
Condition;
Step L: given difference originates delay node, and observation flight is delayed different communication effects in a network, and to scheme
Image space formula intuitively shows user, facilitates user to carry out regularity summarization, the analysis of causes and formulates corresponding control strategy.
The evolved network model construction module and delay simulation analysis module are server.
The database module is server cluster.
A kind of flight based on complicated evolved network of the present invention is delayed propagation characteristic analysis method, solves existing
Flight Delay method in can not be from propagation characteristic of the network perspective research flight delay in air net of macroscopic view, no
Network parameter can effectively be changed, can not be embodied in the Dynamic Evolution of air net formation, flight delay is propagated not
The technical issues of with effect;The present invention from macroscopic view air net angle, comprehensive analysis air net self structure characteristic (such as
The course line volume of the flow of passengers) and network operation characteristic, consider delay dissemination, discloses the mechanism of transmission of delay in the entire network;This
Invention building and the higher evolved network of real air net degree of fitting emulate flight delay not by adjusting network parameter
With the communication effect under network environment, delayed propagation characteristic is more clearly illustrated;Inventive algorithm operating process is simple,
Overall space complexity and time complexity are lower, are applicable to handle large complicated network.
Detailed description of the invention
Fig. 1 is general flow chart of the invention;
Fig. 2 is the flow chart that step 3 of the invention arrives step 4;
Fig. 3 is the flow chart of step 5 of the invention.
Specific embodiment
A kind of flight based on complicated evolved network as shown in FIG. 1 to FIG. 3 is delayed propagation characteristic analysis method, including such as
Lower step:
Step 1: establishing Hadoop server cluster, client-server, data are established in Hadoop server cluster
Library module, evolved network model construction module and delay simulation analysis module, client-server, database module, evolution net
Pass through internet communication between network model construction module and delay simulation analysis module;
Step 2: setting each airport is a node, and the line between two nodes is a course line, each
Course line is a side;User inputs the quantity on airport and the volume of the flow of passengers information in all course lines by client-server, and raw
Network parameter is produced, client-server sends the network parameter to database module and stores;
Step 3: evolved network model construction module by the network parameter in internet reading database, by with
Lower step establishes evolved network model:
Step A: evolved network model construction module establishes evolved network model: evolved network model construction module root
According to the network parameter, determines that the sum of the node in evolved network model is N, set the start node of evolved network model
Number is n0, the item number of initial edge is e0;Set side eijFor any one side in evolved network model, side eijWeight be
wij, wherein i is side eijThe number of node that is connected of one end, j is side eijThe number of node that is connected of the other end, just
Beginning sets weight as W0;
Step B: it is t that setting time, which walks parameter, sets the initial value of t as t=0;
Step C: evolved network model construction module is added a new node n into evolved network model, new node n with drill
The number for changing the side being connected in network model is m, and m is the positive integer less than e0;
New node n is with probabilitySelect side eij;Wherein
Wherein local indicates current evolved network model;T indicates the time
Step, mt+e0And MtIndicate total number of edges of network at this time, ∑localwijIndicate total weight of current network;
Step D: new node n is with Probability p and side eijEnd point be connected, new node n is with probability 1-p and side eijIt is another
Endpoint is connected;New node n causes side eijSide right increase δ, i.e. wij=wij+δ;
Step E: calculating and updates n0=n0+1;It calculates and updates t=t+1;
Step F: step C is repeated to step E, until n0Value be greater than N value, execute step 4;
Step 4: setup parameter ε;When the number of nodes in evolved network model is equal to the total N of node, evolved network mould
Type stops increasing, at this point, the angle value of all nodes of evolved network model is it has been determined that the calculating of evolved network model construction module is drilled
Change the degree distribution function p (k1) of network model, spends distribution function P (k2) be fitted to obtain by the airport degree of selected real network,
Wherein k2Indicate the angle value of real nodes;Machine in degree distribution function p (k1) and selected real air net
The degree distribution function P (k of field2) variance analysis is carried out, gained variance is R2, spend distribution function
The angle value of wherein power rate exponent gamma=(1+p+2 δ)/(p+ δ), k1 expression evolved network model interior joint;Work as R2When < ε, evolution net
Network model foundation is completed;As R2 > ε, evolved network model construction module adjusts the value of w0, N, p and δ, and executes step B;
Spend distribution function P (k2) it is that real network is fitted, the live network of selection is different, obtained degree distribution letter
Number P (k2) also different.
Step 5: delay simulation analysis module reads the evolution by internet from evolved network model construction module
Network model, and construct the flight delay based on airport node by following steps and propagate ASIR model:
Step G: S is definedk(t)、Ik(t) and Rk(t) respectively indicate the normal node of angle value in evolved network model equal to k,
Delay node and delay vanished node account for the ratio for the node that all angle value are k, S in t momentk(t)、Ik(t) and Rk(t) between
Relational expression are as follows:
Sk(t)+Ik(t)+Rk(t)=1;
Step H: definition probability of spreading is λk, it is that χ, recovery rate μ set μ=1 without loss of generality that probability is exempted from mistake;
Step J: according to mean field theory, it is delayed simulation analysis module and is existed according to following differential equation group calculating ASIR model
Communication process in evolved network model:
In the differential equation group: probability of spreading Indicate that angle value is the node of k
Point intensity, NkIt is the set for the node being connected with the node that angle value is k, defines smax=kwmaxIt is evolved network model moderate
Value is the maximum point intensity of the node of k;Defining q is external interference parameter;Θ (I (t)) indicates that angle value is that any of node of k gives
Deckle is delayed the probability that node is connected with one, considers the scales-free network of dereferenced, then:
Θ (I (t))=∑kkP(k)Ik(t)/<k>, wherein<k>=∑k∈NKP (k) indicates being averaged for evolved network model
Angle value;
Step K: user is passed through by the given node initially to involve a delay of client-server, delay simulation analysis module
Internet obtains the node initially to involve a delay from client-server, and by adjusting parameter δ and q, observes in different ginsengs
Under several, Sk(t)、Ik(t) and Rk(t) the slope of curve and peak value difference obtain being delayed propagation rate and range feelings accordingly
Condition;
Step L: given difference originates delay node, and observation flight is delayed different communication effects in a network, and to scheme
Image space formula intuitively shows user, facilitates user to carry out regularity summarization, the analysis of causes and formulates corresponding control strategy.
The evolved network model construction module and delay simulation analysis module are server.
The database module is server cluster.
A kind of flight based on complicated evolved network of the present invention is delayed propagation characteristic analysis method, solves existing
Flight Delay method in can not be from propagation characteristic of the network perspective research flight delay in air net of macroscopic view, no
Network parameter can effectively be changed, can not be embodied in the Dynamic Evolution of air net formation, flight delay is propagated not
The technical issues of with effect;The present invention from macroscopic view air net angle, comprehensive analysis air net self structure characteristic (such as
The course line volume of the flow of passengers) and network operation characteristic, consider delay dissemination, discloses the mechanism of transmission of delay in the entire network;This
Invention building and the higher evolved network of real air net degree of fitting emulate flight delay not by adjusting network parameter
With the communication effect under network environment, delayed propagation characteristic is more clearly illustrated;Inventive algorithm operating process is simple,
Overall space complexity and time complexity are lower, are applicable to handle large complicated network.
Claims (3)
1. a kind of flight based on complicated evolved network is delayed propagation characteristic analysis method, characterized by the following steps:
Step 1: establishing Hadoop server cluster, client-server, database mould are established in Hadoop server cluster
Block, evolved network model construction module and delay simulation analysis module, client-server, database module, evolved network mould
Pass through internet communication between type building module and delay simulation analysis module;
Step 2: setting each airport is a node, and the line between two nodes is a course line, each course line
It is a side;User inputs the quantity on airport and the volume of the flow of passengers information in all course lines by client-server, and produces net
Network parameter, client-server send the network parameter to database module and store;
Step 3: evolved network model construction module passes through following step by the network parameter in internet reading database
Suddenly evolved network model is established:
Step A: evolved network model construction module establishes an evolved network model: evolved network model construction module is according to institute
Network parameter is stated, determines that the sum of the node in evolved network model is N, sets the number of the start node of evolved network model
For n0, the item number of initial edge is e0;Set side eijFor any one side in evolved network model, side eijWeight be wij,
In, i is side eijThe number of node that is connected of one end, j is side eijThe number of node that is connected of the other end, initially set
Determining weight is w0;
Step B: it is t that setting time, which walks parameter, sets the initial value of t as t=0;
Step C: a new node n, new node n and evolution net are added into evolved network model for evolved network model construction module
The number on the side being connected in network model is m, and m is the positive integer less than e0;
New node n is with probabilitySelect side eij;Wherein
Wherein local indicates current evolved network model;T table
Show time step, mt+e0And MtIndicate total number of edges of network at this time, ∑localwijIndicate total weight of current network;
Step D: new node n is with Probability p and side eijEnd point be connected, new node n is with probability 1-p and side eijAnother endpoint phase
Even;New node n causes side eijSide right increase δ, i.e. wij=wij+δ;
Step E: calculating and updates n0=n0+1;It calculates and updates t=t+1;
Step F: step C is repeated to step E, until n0Value be greater than N value, execute step 4;
Step 4: setup parameter ε;When the number of nodes in evolved network model is equal to the total N of node, evolved network model stops
Only increase, at this point, the angle value of all nodes of evolved network model is it has been determined that setting degree distribution function p (k1) it is evolved network
The degree distribution function of model, setting degree distribution function P (k2) be airport in selected real air net degree distribution function,
The degree distribution function p (k of evolved network model construction module calculating evolved network model1), spend distribution function P (k2) by selected
The airport degree of real network is fitted to obtain, wherein k2Indicate the angle value of real nodes;The degree distribution function p (k1) with
The degree distribution function P (k on airport in selected real air net2) variance analysis is carried out, gained variance is R2, degree distribution letter
NumberWherein power rate exponent gamma=(1+p+2 δ)/(p+ δ), k1It indicates to develop
The angle value of network model interior joint;Work as R2When < ε, evolved network model foundation is completed;Work as R2When > ε, evolved network model construction
Module adjusts w0, N, p and δ value, and execute step B;
Step 5: delay simulation analysis module reads the evolved network by internet from evolved network model construction module
Model, and construct the flight delay based on airport node by following steps and propagate ASIR model:
Step G: S is definedk(t)、Ik(t) and Rk(t) normal node of the angle value equal to k, delay in evolved network model are respectively indicated
Node and delay vanished node account for the ratio for the node that all angle value are k, S in t momentk(t)、Ik(t) and Rk(t) pass between
It is formula are as follows:
Sk(t)+Ik(t)+Rk(t)=1;
Step H: definition probability of spreading is λk, it is χ, recovery rate μ that probability is exempted from mistake, sets μ=1;
Step J: according to mean field theory, it is delayed simulation analysis module and is being developed according to following differential equation group calculating ASIR model
Communication process in network model:
In the differential equation group: probability of spreading Expression angle value is k
Node point intensity, NkIt is the set for the node being connected with the node that angle value is k, defines smax=kwmaxIt is evolved network mould
Angle value is the maximum point intensity of the node of k in type;Defining q is external interference parameter;Θ (I (t)) indicates that angle value is the node of k
It is any to be delayed the probability that node is connected with one to deckle, consider the scales-free network of dereferenced, then:
Θ (I (t))=∑kkP(k)Ik(T)/<k>, wherein<k>=∑k∈NThe average angle value of kP (k) expression evolved network model;
Step K: user passes through interconnection by the given node initially to involve a delay of client-server, delay simulation analysis module
Net obtains the node initially to involve a delay from client-server, and by adjusting parameter δ and q, observes under different parameters,
Sk(t)、Ik(t) and Rk(t) the slope of curve and peak value difference obtain being delayed propagation rate and range situation accordingly;
Step L: given difference originates delay node, and observation flight is delayed different communication effects in a network, and with image side
Formula intuitively shows user, facilitates user to carry out regularity summarization, the analysis of causes and formulates corresponding control strategy.
2. a kind of flight based on complicated evolved network as described in claim 1 is delayed propagation characteristic analysis method, feature
Be: the evolved network model construction module is server with delay simulation analysis module.
3. a kind of flight based on complicated evolved network as described in claim 1 is delayed propagation characteristic analysis method, feature
Be: the database module is server cluster.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710202141.5A CN107018019B (en) | 2017-03-30 | 2017-03-30 | A kind of flight delay propagation characteristic analysis method based on complicated evolved network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710202141.5A CN107018019B (en) | 2017-03-30 | 2017-03-30 | A kind of flight delay propagation characteristic analysis method based on complicated evolved network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107018019A CN107018019A (en) | 2017-08-04 |
CN107018019B true CN107018019B (en) | 2019-09-20 |
Family
ID=59445588
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710202141.5A Active CN107018019B (en) | 2017-03-30 | 2017-03-30 | A kind of flight delay propagation characteristic analysis method based on complicated evolved network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107018019B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109190700B (en) * | 2018-08-27 | 2020-06-12 | 北京航空航天大学 | Quantitative analysis method for aviation delay propagation |
CN109872074B (en) * | 2019-03-04 | 2023-01-06 | 中国民航大学 | Aviation network delay propagation model based on SIS and establishment method |
CN113393136B (en) * | 2021-06-22 | 2023-05-23 | 中国人民解放军空军工程大学 | Delay propagation characteristic discovery method, system and equipment for air traffic control system |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN105844574A (en) * | 2016-03-25 | 2016-08-10 | 中国民航大学 | Multi-airport four-phase planning design method based on life-cycle theory |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2492328A (en) * | 2011-06-24 | 2013-01-02 | Ge Aviat Systems Ltd | Updating troubleshooting procedures for aircraft maintenance |
-
2017
- 2017-03-30 CN CN201710202141.5A patent/CN107018019B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN105844574A (en) * | 2016-03-25 | 2016-08-10 | 中国民航大学 | Multi-airport four-phase planning design method based on life-cycle theory |
Non-Patent Citations (2)
Title |
---|
"基于复杂网络理论的航班延误波及分析";邵荃等;《航空计算技术》;20150731;全文 * |
"基于机场延误预测的航班计划优化研究";吴薇薇等;《交通运输系统工程与信息》;20161231;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN107018019A (en) | 2017-08-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Nie et al. | Network traffic prediction based on deep belief network in wireless mesh backbone networks | |
Radicchi et al. | Abrupt transition in the structural formation of interconnected networks | |
Milner et al. | Nature-inspired self-organization, control, and optimization in heterogeneous wireless networks | |
CN107018019B (en) | A kind of flight delay propagation characteristic analysis method based on complicated evolved network | |
Carareto et al. | Natural synchronization in power-grids with anti-correlated units | |
CN106326367A (en) | Mixed collaborative recommendation algorithm based on WNBI and RSVD | |
Tanaka et al. | Synchronization and propagation of bursts in networks of coupled map neurons | |
CN104598605A (en) | Method for user influence evaluation in social network | |
CN103838803A (en) | Social network community discovery method based on node Jaccard similarity | |
CN102904815B (en) | Scale-free network based router-level topology modeling method | |
CN106685745B (en) | A kind of constructing network topology method and device | |
Shahrivar et al. | Spectral and structural properties of random interdependent networks | |
Tang et al. | Nash equilibrium and multi criterion aerodynamic optimization | |
CN104977505A (en) | Power grid disturbance source positioning method based on integrated oscillators | |
Zhang et al. | Evolving pseudofractal networks | |
CN102394812B (en) | Self-feedback dynamic self-adaption resource distribution method of cognitive network | |
Nguyen et al. | Fast transient simulation of high-speed channels using recurrent neural network | |
Pi et al. | A directed weighted scale-free network model with an adaptive evolution mechanism | |
Kong | Research on network security situation assessment technology based on fuzzy evaluation method | |
Alvarez-Hamelin et al. | An Internet graph model based on trade-off optimization | |
Lou et al. | Local communities obstruct global consensus: Naming game on multi-local-world networks | |
Yuan et al. | A mixing evolution model for bidirectional microblog user networks | |
Bartz et al. | Dynamical AdS/Yang-Mills model | |
Xu et al. | Degree dependence entropy descriptor for complex networks | |
CN106325069A (en) | Method for designing optimal linear control strategy for wireless network control system |
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 |