CN110119884A - A kind of high-speed railway passenger flow Time segments division method based on neighbour's propagation clustering - Google Patents
A kind of high-speed railway passenger flow Time segments division method based on neighbour's propagation clustering Download PDFInfo
- Publication number
- CN110119884A CN110119884A CN201910307332.7A CN201910307332A CN110119884A CN 110119884 A CN110119884 A CN 110119884A CN 201910307332 A CN201910307332 A CN 201910307332A CN 110119884 A CN110119884 A CN 110119884A
- Authority
- CN
- China
- Prior art keywords
- passenger flow
- sample
- passenger
- time point
- traffic volume
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims description 51
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 239000006185 dispersion Substances 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 6
- 238000013016 damping Methods 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 5
- 230000009514 concussion Effects 0.000 claims description 3
- 238000010835 comparative analysis Methods 0.000 claims description 2
- 238000011158 quantitative evaluation Methods 0.000 claims description 2
- 238000013139 quantization Methods 0.000 claims description 2
- 238000004088 simulation Methods 0.000 claims description 2
- 238000011144 upstream manufacturing Methods 0.000 claims description 2
- 238000011160 research Methods 0.000 description 7
- 238000013456 study Methods 0.000 description 5
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 229910052742 iron Inorganic materials 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000003068 static effect Effects 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The present invention provides a kind of high-speed railway passenger flow Time segments division method based on neighbour's propagation clustering, statistical time is divided into several time points by the present invention, then the passenger flow data for counting each time point, will carry out pretreated sample variable build time point sample sequence；Then, sample sequence is divided using neighbour's propagation clustering algorithm；Finally, optimum cluster result is determined using Cluster Validity Indexes such as CH, Hartigan and IGP, and it is further formed year operation Time segments division result, the present invention carries out cluster merger to the similar time point of the volume of the flow of passengers in year using neighbour's propagation algorithm, and preferable clustering number is determined according to CH, Hart and IGP index, improve the accuracy of classification；It more can objectively and accurately reflect different periods passenger flow demand in year simultaneously, overcome manual division methods subjectivity, low efficiency and the not high disadvantage of precision, lay the foundation to be adaptively adjusted for train running scheme.
Description
Technical field
The present invention relates to high-speed rail technology field, when especially a kind of high-speed railway passenger flow based on neighbour's propagation clustering
Section division methods.
Background technique
Eight cross eight are vertical " gradual perfection of High-speed Railway Network and inter-city railway network, so that more and more middle-long distance passengers
Using high-speed railway as preferred trip mode, as the important factor in order of quality of passenger service, train running scheme is defined
Passenger train starts quantity, section, stop website etc..To improve the service quality of each whereabouts passenger flow on road network, while to the greatest extent may be used
Energy ground reduces train operation cost, and high-speed railway passenger transportation management department needs according to annual passenger flow fluctuating change to the train side of starting
Case is adaptively adjusted, and the passenger flow demand of different periods in year is complied with.
Trip distribution situation in railway network on train, be evaluate traffic programme in passenger train efficiency of the practice it is important according to
According to.Practical Trip distribution of riding is generallyd use to evaluate the traffic programme in passenger train implemented, but is set for that will optimize
The traffic programme in passenger train of meter can only generate the Trip distribution on train by means of bus traveler assignment means to evaluate.Due to visitor
The reasonability of the efficiency and result that flow distribution directly influences the optimum level of traffic programme in passenger train, so train passenger flow point
Method of completing the square is always to study one of the important foundation research topic of railway passenger train operating scheme optimization.
However it is numerous to be related to factor to the adjustment of train running scheme, is complexity, a great system engineering, it is annual right
Its number being adjusted also is limited.High-speed railway is runed according to passenger flow wave characteristic and carries out Time segments division in year, so
It is afterwards a more key tactics to train running scheme adjustment according to the volume of the flow of passengers of day part.Therefore, operation period science
Classifying rationally is the basic premise and important evidence of train running scheme adjustment, is to adjust train running scheme and have dynamic special
Property the adaptable important guarantee of passenger flow demand.Existing high-speed railway operation Time segments division method is, according to target of the whole year line
Road counts the situation of change of passenger flow total amount, is spring transportation phase, summer transportation phase, section vacation and flat peak phase by year operation Time segments division.
Although this way embodies the difference of the volume of the flow of passengers between different periods, but the result quality of Time segments division largely takes
The certainly experience of engineers and technicians on site, defect strong with subjectivity, being easy to cause unreasonable Time segments division result, it is difficult to
Accurately reflect the passenger flow demand in year with seasonal variety characteristic.
Time segments division problem is runed for high-speed railway, there is no correlative study both at home and abroad.The problem in itself be based on
Traffic slot in multi-period control (TOD) intersection Design of Signal divides similar.For the multi-period control of intersection
(TOD) problem of system, domestic and foreign scholars have some correlative studys, main by drawing the tired of some representative intersection one day
Product volume of traffic curve, and determine that the more significant timing node of volume of traffic curvilinear motion is period cut-point by artificial experience,
To realize the classifying rationally of traffic slot, train bus traveler assignment method is usually used earlier almost without independent research
In train running scheme optimizing research, these researchs construct passenger transference network, design based on given train running scheme
Trip generalized cost of passenger, including admission fee expenditure, hourage and crowding effect etc., establish static subscriber's equilibrium assignment model
Or stochastic user equilibrium distribution model, it by flow equalization is assigned on train operation section (referring to history peak, Deng Lianbo, Li Xin
China, Fang Qigen Line for Passenger Transportation correlation Research on Train Plan of Passenger Train [J] railway society, 2004,26 (2): 16-20.).City
Public traffic passenger flow distribution in city's is very similar with high-speed rail bus traveler assignment, which has a large amount of research work.Hamdouch etc.
Trip alternative collection when constructing passenger on time-space network and marching to any station, and then propose and comprehensively consider the departure time
It is required that, the public transport strategy equilibrium distribution model based on timetable under stringent capacity consistency and space-time priority principle, it is above-mentioned main
The capacity consistency and the preferential characteristic of space-time during bus traveler assignment are considered, research is not provided for the characteristic of passenger ticket buying
Analysis, however the characteristic has important influence in the choice for traveling of high-speed railway passenger, it is therefore desirable to design a kind of be applicable in
In the bus traveler assignment method of high-speed railway transportation network.
Summary of the invention
In view of the deficiencies of the prior art, the present invention provides a kind of high-speed railway passenger flow period based on neighbour's propagation clustering stroke
Divide method, when this method carries out reasonable to entire year according to the Variation Features of the volume of the flow of passengers of each whereabouts in High Speed Railway road
Section divides, and improves the adaptability of train running scheme and passenger flow demand.
The technical solution of the present invention is as follows: a kind of high-speed railway passenger flow Time segments division method based on neighbour's propagation clustering, packet
Include following steps:
S1), a year is divided into T time point, and setting high-speed rail route X includes n important websites, statistics of high speed iron
Each time interval t on the X upstream or downstream direction of route roadkInterior each website passenger flow traffic volume, i.e.,
Wherein, XkIndicate time interval tkThe passenger flow traffic volume of interior high-speed rail route X,Indicate time interval tkInterior high iron wire
The passenger flow traffic volume of n-th of website of road X；
S2), judge whether the passenger flow traffic volume of each time point is abnormal using threshold value δ, specially statistical time point
tlThe passenger flow at m adjacent time point sends vector, and calculates its mean valueIf
Then think time point tlPassenger flow traffic volume data be non-abnormal data, be otherwise abnormal data；
Wherein, XlFor time point tlPassenger flow traffic volume；
If data exception, suppressing exception data, and using the passenger flow data at adjacent m time point at the time point to it
Passenger flow traffic volume is fitted reparation, and calculating formula is as follows:
In formula, lkIt (t) is k-1 polynomial fitting, Ln(t) be Lagrange interpolation polynomial, t be the time to be fitted
Point, tjFor j-th of time point, tiFor i-th of time point, XiFor passenger flow matrix, the l at i-th of time pointiIt (t) is i-1 fitting
Multinomial；
Data after fitting is repaired are merged with former normal data, are then standardized using standard deviation between eliminating variable
The difference of scale, calculating formula are as follows:
In formula, Z-score is the value carried out after standard deviation standardization, and x is website passenger's traffic volume at some time point,
For the mean value of website passenger's traffic volumes all in year, σ is the standard deviation of all website passenger traffic volumes in year；
S3), Time segments division is carried out based on neighbour's propagation clustering algorithm, by T time point in passenger flow traffic volume data set
Passenger flow traffic volume data set is represented as candidate class, judge the passenger flow traffic volume in any 2 time intervals similarity s (i,
K), i.e. s (i, k) indicates the passenger flow traffic volume sample X of time interval kkWith a passenger flow traffic volume sample X of interval iiSimilarity,
That is sample XkIt is suitable as sample XiThe quantization degree that represents of class, when algorithm initialization, it is assumed that all samples were represented for class
Possibility is identical, that is, assumes that all s (k, k) are identical Attraction Degree intermediate value p, wherein the calculating formula of similarity of any two sample
Are as follows:
S (i, k)=- | | xi-xk||2；
Wherein, xiIndicate the passenger flow traffic volume sample of i, xkIndicate the passenger flow traffic volume at k moment；
Define reliability matrix r and availability matrix a, wherein reliability matrix r (i, k) is from sample xiIt is directed toward sample
xk, indicate sample xkIt is suitable as xiClass represent representative degree；A (i, k) is from sample xkIt is directed toward sample xi, indicate xiSelection
xkThe appropriate level represented as class；For arbitrary sample xiCalculate the confidence level r (i, k) of other times interval passenger flow traffic volume
The sum of with availability a (i, k), if the maximum sample x of sum of the twokFor class representative, all time point category division results are exported；
Specifically comprise the following steps:
S301), the initial value that reliability matrix r (i, k) and availability matrix a (i, k) is arranged is 0；
S302), the similarity matrix s (i, k) of the passenger flow traffic volume sample of arbitrary time span is calculated, matrix value uses Europe
Formula distance is to estimate, i.e. s (i, k)=- | | xi-xk||2；
It is identical Attraction Degree intermediate value that diagonal entry s (k, k), which is arranged, i.e.,
It is N sample size in formula；
S303), reliability matrix r (i, k) and availability matrix a (i, k) are updated, wherein reliability matrix r (i, k) is more
New calculation formula are as follows:
Availability matrix a (i, k) updates calculation formula are as follows:
S304), setting damping factor λ eliminates the number concussion in iteration, that is,
In formula, rnew(i, k) and rold(i, k) is respectively the reliability matrix that this is obtained with last update；anew(i,
And a k)old(i, k) is respectively the availability matrix that this is obtained with last update；λ ∈ (0,1) is damping factor；
S305), to any passenger flow traffic volume data sample seek its confidence level with all passenger flow traffic volume samples with can
The sum of expenditure, according toFind the class central sample of each sample；
S306), current iteration number updates n ← n+1, judges whether information iteration process reaches the greatest iteration time of setting
Number, i.e. n≤Nmax, it is then algorithm termination, exports all time point category divisions as a result, otherwise return step S302)；
S4), Calinski-Harabasz, Hartigan and In- of different time points category division result are calculated separately
Group Proportion index selects optimal time point classification number and its corresponding category division result；
S5), Time segments division product test and correction are runed, all division classifications of traversal loop carry out each sample
Comparative analysis two-by-two, if time point corresponding to two samples be it is adjacent, merge into an operation period, otherwise, depending on
The period is runed for another；
S6), passenger flow demand adaptability teaching after runing Time segments division, works out train according to day part passenger flow average demand
Starting scheme simultaneously carries out bus traveler assignment simulation, introduces passenger flow satisfactory rate of information demand, train and be averaged attendance and the through rate three of passenger flow
A index carries out quantitative evaluation to the adaptedness of day part passenger flow demand and train running scheme and summarizes.
Further, the Calinski-Harabasz index is mean dispersion error matrix and class in the class based on whole samples
Between mean dispersion error matrix estimate, the corresponding class number of maximum value is as preferable clustering number, i.e.,
In formula, k is cluster numbers, trB (k) be between mean dispersion error matrix mark, trW (k) is the mark of mean dispersion error matrix in class, when n is
Between put sample size.
Further, the Hartigan index is used for the case where cluster numbers are 1, meets the infima species number of Ha≤10
As preferable clustering number, i.e.,
In formula, k is to divide classification sum at the time point of sample clustering result, and trW (k) is the mark of mean dispersion error matrix in class, and n is
Time point sample size.
Further, the In-Group Proportion index is used to measure each sample of distance in certain one kind
Whether nearest sample is in same class, and the average IGP index of all clusters is bigger, and the quality for indicating cluster is better, maximum value
Corresponding class number is preferable clustering number, i.e.,
In formula, u is the category of certain cluster, and Class (j) is the category of sample j, jNFor the nearest sample of distance sample j, #
For the number for meeting condition.
Further, the passenger flow satisfactory rate of information demand is used to embody each passenger flow whereabouts of high-speed railway and related road network
Between, the passenger's conveying capacity and passenger flow need satisfaction degree that train running scheme provides especially are arranged in transport capacity resource condition
Under the constraint of vehicle staffing condition, by the Passenger Traffic that can obtain effective transportation service under the conditions of set train running scheme
It is indicated with the ratio of passenger flow total demand, calculation formula is as follows:
In formula, q'wFor the passenger flow total amount that passenger flow OD conveys high-speed railway w, w is road network passenger flow whereabouts number.
Further, the train attendance that is averaged refers to the average value of all train attendances in range of value, column
Vehicle is averaged the volume of the flow of passengers that attendance refers to that train is carried in its running section and the train provides the weighting ratio of seat seat sum, this
Index is used to reflect passenger between OD pairs of different passenger flows to various types bullet train selection result, and train is averaged attendance
Calculation formula is as follows:
In formula,For the volume of the flow of passengers that train h is carried at section (i, j), AhFor the staffing number of train h, EhFor train h operation
Sector number.
Further, passenger flow demand structure is made of different demand directions, and each demand direction can have arrival mesh
Ground through or transfer riding scheme, passenger flow rate of going directly refers in set train running scheme and passenger flow demand structure
Under, the volume of the flow of passengers to go directly to destination between each passenger flow demand point pair without transfer removes upwards the always ratio of the volume of the flow of passengers with this,
Its calculation formula is:
In formula, w is road network passenger flow whereabouts number, | e | it is the number of transfer of some whereabouts passenger flow,For passenger flow OD between w not
The passenger number to go directly to destination is changed to,Pass through for passenger flow OD between w | e | it is secondary to change to the psgrs. No. of arrived at the destination
Amount.
The invention has the benefit that
1, the present invention combines the volume of the flow of passengers data along station each time point, using neighbour's propagation algorithm to the volume of the flow of passengers in year
Similar time point carries out cluster merger, and determines preferable clustering number according to CH, Hart and IGP index, improves the standard of classification
True property；
2, the high-speed railway provided by the invention in clustering runs Time segments division method combination Cluster Validity Index
Product test, more can objectively and accurately reflect different periods passenger flow demand in year, overcome manual division methods master
The property seen, low efficiency and the not high disadvantage of precision, lay the foundation to be adaptively adjusted for train running scheme；
3, present invention determine that after best cluster result, manual analysis is carried out to cluster result, by operation Time segments division
Product test and correction guarantee the accuracy of planning, while being averaged attendance and passenger flow by passenger flow satisfactory rate of information demand, train
Through rate assesses passenger flow demand adaptability, further increases the adaptation journey of day part passenger flow demand and train running scheme
Degree.
4, the present invention also pre-processes the data of acquisition, suppressing exception data, and using based on Lagrange's interpolation
Method is fitted reparation to abnormal data, to guarantee the availability of data, and then guarantees the reliability of program results.
Detailed description of the invention
Fig. 1 is the process that the high-speed railway based on neighbour's propagation clustering runs Time segments division；
Fig. 2 is operation Time segments division difference cluster numbers Validity Index value schematic diagram in 2014；
Fig. 3 is operation Time segments division difference cluster numbers Validity Index value schematic diagram in 2015；
Fig. 4 is operation period cluster result schematic diagram in 2014；
Fig. 5 is operation period cluster result schematic diagram in 2015.
Specific embodiment
Specific embodiments of the present invention will be further explained with reference to the accompanying drawing:
As shown in Figure 1, the present embodiment provides a kind of high-speed railway passenger flow Time segments division method based on neighbour's propagation clustering,
In order to make it easy to understand, the present embodiment uses on December 31,1 day~2014 January in 2014 and -2015 years on the 1st January in 2015
The passenger flow traffic volume for the high-speed railway that December 31 certain has operated normally is that the present invention will be described for data, which has
9 websites, specifically includes the following steps:
S1), 31 days 1 day~December of January in 2014 and December -2015 years on the 1st January in 2015 are respectively divided on the 31st
For 365 time points, i.e., daily it is a time point, counts the volume of the flow of passengers of this of each time point railway downlink, i.e.,Passenger flow OD matrix on the line downstream direction is described respectively, wherein XkFor when
Between point k the volume of the flow of passengers,For the volume of the flow of passengers of time point k website i；
S2), judge whether the passenger flow traffic volume of each time point is abnormal using threshold value δ, specially statistical time point
tlThe passenger flow at m adjacent time point sends vector, and calculates its mean valueIf
Then think time point tlPassenger flow traffic volume data be non-abnormal data, be otherwise abnormal data；
Wherein, XlFor time point tlPassenger flow traffic volume；
If data exception, suppressing exception data, and using the passenger flow data at adjacent m time point at the time point to it
Passenger flow traffic volume is fitted reparation, and calculating formula is as follows:
In formula, lkIt (t) is k-1 polynomial fitting, Ln(t) be Lagrange interpolation polynomial, t be the time to be fitted
Point, tjFor j-th of time point, tiFor i-th of time point, XiFor passenger flow matrix, the l at i-th of time pointiIt (t) is i-1 fitting
Multinomial；
Data after fitting is repaired are merged with former normal data, are then standardized using standard deviation between eliminating variable
The difference of scale, calculating formula are as follows:
In formula, Z-score is the value carried out after standard deviation standardization, and x is website passenger's traffic volume at some time point,
For the mean value of website passenger's traffic volumes all in year, σ is the standard deviation of all website passenger traffic volumes in year；
S3), Time segments division, neighbour's propagation clustering algorithm (Affinity are carried out based on neighbour's propagation clustering algorithm
Propagation, AP) it is to be clustered on the similarity matrix S constituted by sample number strong point, with other clustering algorithm phases
Together, target is to minimize the distance between each data point and the representative point in each division classification, to realize classification
It divides, specifically includes the following steps:
S301), the value for initializing reliability matrix r (i, k) and availability matrix a (i, k) is 0；
S302), Sample Similarity matrix s (i, k) being calculated, matrix value uses Euclidean distance to estimate, i.e. s (i, k)=- | |
xi-xk||2, setting diagonal entry s (k, k) is identical Attraction Degree intermediate value, i.e.,
It is N sample size in formula, value is 265 in the present embodiment；
S303), update reliability matrix r (i, k) and availability matrix a (i, k), calculating formula are respectively as follows:
Reliability matrix r (i, k) updates calculation formula are as follows:
Availability matrix a (i, k) updates calculation formula are as follows:
S304), setting damping factor eliminates the number concussion in iteration
In formula, rnew(i, k) and rold(i, k) is respectively the reliability matrix that this is obtained with last update；anew(i,
And a k)old(i, k) is respectively the availability matrix that this is obtained with last update；In the present embodiment be arranged damping factor λ=
0.9；
S305), to the volume of the flow of passengers data sample of any point-in-time calculate its to all samples ask confidence level and availability it
With, according toThen the class central sample for finding each sample exports all time point category division knots
Fruit；
S4), since a series of cluster result can be exported when the AP algorithm of step S3) is clustered to sample, therefore use
The various cluster results that Calinski-Harabasz, Hartigan and In-Group Proportion index obtain algorithm
Validity check is carried out, as a result as shown in Figures 2 and 3, as seen from the figure, based on 2014~2015 years high-speed railway passenger flow datas
Optimal sample cluster numbers are 5, as final cluster result, are described as shown in figs. 4 and 5；
S5), all division classifications of traversal loop carry out two-by-two to score the passenger flow data sample of wherein any point-in-time
Analysis splits time point discontinuous in same category, form 2014~2015 years high-speed railways operation Time segments divisions as a result, its
Structure is as shown in table 1；
Table 1 runs Time segments division result
As shown in Table 1, the high-speed railway railway Time segments division result based on passenger flow changing rule is equal within 2014~2015
For 5 classes, 13 operation periods can be divided within 365 days 1 year.Wherein, 2014~2015 operation periods 3, operation period 6, fortune
Battalion's period 7, operation period 8, the time span of operation period 12 are identical, and remaining operation period of time span is different.Study carefully
Its reason is as caused by the difference in spring transportation period over the years.The Spring Festival in 2014 be January 31, i.e., the 31st day；2015
The Spring Festival be 2 months No. 19, i.e., the 50th day.It can be found that per being to enter the operation period 2 in 7 days before the Spring Festival every year.Other operation periods
The corresponding annual time is more obvious, can totally conclude are as follows:
Run 1 time span of period be New Year after with the passenger flow gentle phase before the Spring Festival；When runing period 2~operation period 4
Between span be phase spring transportation commuter rush hour；Run 5 time span of period be the spring transportation phase and the Ching Ming Festival between the passenger flow gentle phase；Operation
Phase commuter rush hour the Ching Ming Festival 6 time span of period is；The visitor Ching Ming Festival operation 7 time span of period is between Labor Day
Levelling is postponed a deadline；Operation 8 time span of period is phase Labor Day commuter rush hour；9 time span of period is runed as May Day labour
The passenger flow gentle phase between section and summer transportation phase；Operation 10 time span of period is phase summer transportation commuter rush hour；Run 11 time of period
Passenger flow of the span between the summer transportation phase and 11 National Day gentle phase；Runing 12 time span of period is that " 11 National Day " passenger flow is high
The peak phase；The passenger flow gentle phase before runing 11 National Day of 13 time span of period and New Year.
S6), operation Time segments division result correction, it is right since operation 3,6,8 time span of period is only one day or several days
For high-speed railway passenger transportation management department, implement the train running scheme meeting of adjustment on a large scale to adapt to these period passenger flow demands
Excessive interference is caused to existing transport project, and needs to consume excessive manpower and material resources.Therefore, it is passed through according to work on the spot
It tests, three operation periods and adjacent operation period of the present embodiment by number of days less than 7 days carry out merger processing, after obtaining correction
High-speed railway operation Time segments division the results are shown in Table 2,
Table 2 runs Time segments division correction result
High-speed railway operation Time segments division result through overcorrection can be concluded are as follows: the operation period 1 is after New Year and before the Spring Festival
The passenger flow gentle phase；The operation period 2 is phase spring transportation commuter rush hour；3 time span of period is runed between spring transportation phase and summer transportation phase
The passenger flow gentle phase；Operation 4 time span of period is phase summer transportation commuter rush hour；Operation 5 time span of period is the summer transportation phase and ten
The passenger flow gentle phase between one National Day；Operation 6 time span of period is " 11 National Day " phase commuter rush hour；When runing period 7
Between passenger flow gentle phase before 11 National Day of span and New Year.Above-mentioned Time segments division conclusion can be used as train running scheme evaluation
With the premise of adjustment, the adaptability of the passenger flow demand and train running scheme that are obtained in each operation period according to prediction is carried out
Evaluation, if evaluation result is undesirable, needs to be adjusted current train starting scheme；
S7), passenger flow demand adaptability teaching, to illustrate based on the operation prepared train running scheme of Time segments division result
There is better adaptability with passenger flow demand, on the basis of runing Time segments division to high-speed railway, according to the passenger flow of day part
It measures mean value and works out train running scheme, and simulate calculating day part train running scheme and refer to passenger flow demand items adaptability teaching
Mark.Meanwhile according to the Time segments division situation in high-speed railway actual operation in 2014,2015, to train running scheme and passenger flow
Demand adaptability compares, and the results are shown in Table 3,
Table 3 and actual operation situation comparing result
As shown in Table 3, under the premise of the number that train running scheme adjusts on a large scale is constant, according to neighbour's propagation clustering
The train running scheme and passenger flow demand of the operation Time segments division result establishment of algorithm have better adaptability.Wherein, 2014
Year passenger flow satisfactory rate of information demand, train be averaged attendance and the through rate of passenger flow has increased separately 7.6%, 16.7%, 14.1%,
Above three index has increased separately 5.7%, 18.4%, 14.4% within 2015.
The daily passenger's traffic volume survey data in station along the present embodiment combination, using neighbour's propagation algorithm in year
The volume of the flow of passengers similar time point carries out cluster merger, and determines preferable clustering number according to CH, Hart and IGP index, in this base
It is designed on plinth and runs Time segments division method in high-speed railway year, Main Conclusions is as follows
(1) high-speed railway based on clustering runs Time segments division method, and combines the result of Cluster Validity Index
It examines, more can objectively and accurately reflect different periods passenger flow demand in year, overcome manual division methods subjectivity, effect
The disadvantage that rate is low and precision is not high lays the foundation to be adaptively adjusted for train running scheme.
(2) show to pass through using certain line of high-speed railway station passenger traffic volume statistical data as the case study of sample
It determines the best cluster result of operation period in year, and manual analysis is carried out to cluster result, it on this basis can will be annual
It is divided into the reasonable operation period.
The above embodiments and description only illustrate the principle of the present invention and most preferred embodiment, is not departing from this
Under the premise of spirit and range, various changes and improvements may be made to the invention, these changes and improvements both fall within requirement and protect
In the scope of the invention of shield.
Claims (7)
1. a kind of high-speed railway passenger flow Time segments division method based on neighbour's propagation clustering, comprising the following steps:
S1), a year is divided into T time point, and setting any one high-speed rail route X includes n important websites, statistics should
Each time interval t on high-speed railway route X upstream or downstream directionkInterior each website passenger flow traffic volume constructs passenger flow square
Battle array, i.e.,
Wherein, XkIndicate time interval tkThe passenger flow traffic volume of interior high-speed rail route X,Indicate time interval tkInterior high-speed rail route X's
The passenger flow traffic volume of n-th of website；
S2), judge whether the passenger flow traffic volume of each time point is abnormal using threshold value δ, specially statistical time point tlIt is adjacent
The passenger flow at m time point send vector, and calculate its mean valueIf
Then think time point tlPassenger flow traffic volume data be non-abnormal data, be otherwise abnormal data；
Wherein, XlFor time point tlPassenger flow traffic volume；
If data exception, suppressing exception data, and Lagrange's interpolation is utilized, according to the adjacent m time at the time point
The passenger flow data of point is fitted reparation to its passenger flow traffic volume, and calculating formula is as follows:
In formula, lkIt (t) is k-1 polynomial fitting, Ln(t) be Lagrange interpolation polynomial, t be time point to be fitted, tj
For j-th of time point, tiFor i-th of time point, XiFor passenger flow matrix, the l at i-th of time pointi(t) multinomial for i-1 fitting
Formula；
Data after fitting is repaired are merged with former normal data, and scale between eliminating variable is then standardized using standard deviation
Difference, calculating formula is as follows:
In formula, Z-score is the value carried out after standard deviation standardization, and x is website passenger's traffic volume at some time point,For year
The mean value of all website passenger traffic volumes in spending, σ are the standard deviation of all website passenger traffic volumes in year；
S3), Time segments division is carried out based on neighbour's propagation clustering algorithm, by the passenger flow at T time point in passenger flow traffic volume data set
Traffic volume data set is represented as candidate class, judges the similarity s (i, k) of the passenger flow traffic volume in any 2 time intervals, phase
The passenger flow traffic volume sample X of time interval k is indicated like degree s (i, k)kWith a passenger flow traffic volume sample X of interval iiSimilarity,
That is sample XkIt is suitable as sample XiThe quantization degree that represents of class, when algorithm initialization, it is assumed that all samples were represented for class
Possibility is identical, that is, assumes that all s (k, k) are identical Attraction Degree intermediate value p, wherein the calculating formula of similarity of any two sample
Are as follows:
S (i, k)=- | | xi-xk||2；
Wherein, xiIndicate the passenger flow traffic volume sample of i, xkIndicate the passenger flow traffic volume at k moment；
Define reliability matrix r and availability matrix a, wherein reliability matrix r (i, k) is from sample xiIt is directed toward sample xk, table
This x of samplekIt is suitable as xiClass represent representative degree；A (i, k) is from sample xkIt is directed toward sample xi, indicate xiSelect xkMake
The appropriate level represented for class；For arbitrary sample xiCalculate other times interval passenger flow traffic volume confidence level r (i, k) and can
The sum of expenditure a (i, k), if the maximum sample x of sum of the twokFor class representative, all time point category division results are exported；
Specifically comprise the following steps:
S301), the initial value that reliability matrix r (i, k) and availability matrix a (i, k) is arranged is 0；
S302), calculate arbitrary time span passenger flow traffic volume sample similarity matrix s (i, k), matrix value using it is European away from
From to estimate, i.e. s (i, k)=- | | xi-xk||2；
It is identical Attraction Degree intermediate value that diagonal entry s (k, k), which is arranged, i.e.,
It is N sample size in formula；
S303), reliability matrix r (i, k) and availability matrix a (i, k) are updated, wherein reliability matrix r (i, k) updates meter
Calculate formula are as follows:
Availability matrix a (i, k) updates calculation formula are as follows:
S304), setting damping factor λ eliminates the number concussion in iteration, that is,
In formula, rnew(i, k) and rold(i, k) is respectively the reliability matrix that this is obtained with last update；anew(i, k) and
aold(i, k) is respectively the availability matrix that this is obtained with last update；λ ∈ (0,1) is damping factor；
S305), the confidence level and availability of itself and all passenger flow traffic volume samples are sought to any passenger flow traffic volume data sample
The sum of, according toFind the class central sample of each sample；
S306), current iteration number updates n ← n+1, judges whether information iteration process reaches the maximum number of iterations of setting,
That is n≤Nmax, it is then algorithm termination, exports all time point category divisions as a result, otherwise return step S302)；
S4), Calinski-Harabasz, Hartigan and In- of different time points category division result are calculated separately
Group Proportion index selects optimal time point classification number and its corresponding category division result；
S5), Time segments division product test and correction are runed, all division classifications of traversal loop carry out two-by-two each sample
Comparative analysis, if time point corresponding to two samples be it is adjacent, merge into an operation period, otherwise, be considered as another
One operation period；
S6), passenger flow demand adaptability teaching after runing Time segments division, is worked out train according to day part passenger flow average demand and is started
Scheme simultaneously carries out bus traveler assignment simulation, introduces that passenger flow satisfactory rate of information demand, train be averaged attendance and passenger flow is gone directly rate three and referred to
Mark carries out quantitative evaluation to the adaptedness of day part passenger flow demand and train running scheme and summarizes.
2. a kind of high-speed railway passenger flow Time segments division method based on neighbour's propagation clustering according to claim 1, special
Sign is: in step S4), the Calinski-Harabasz index is mean dispersion error matrix and class in the class based on whole samples
Between mean dispersion error matrix estimate, the corresponding class number of maximum value is as preferable clustering number, i.e.,
In formula, k is cluster numbers, trB (k) be between mean dispersion error matrix mark, trW (k) is the mark of mean dispersion error matrix in class, and n is time point
Sample size.
3. a kind of high-speed railway passenger flow Time segments division method based on neighbour's propagation clustering according to claim 1, special
Sign is: in step S4), the Hartigan index is used for the case where cluster numbers are 1, meets the infima species number of Ha≤10
As preferable clustering number, i.e.,
In formula, k is cluster numbers, and trW (k) is the mark of mean dispersion error matrix in class, and n is time point sample size.
4. a kind of high-speed railway passenger flow Time segments division method based on neighbour's propagation clustering according to claim 1, special
Sign is: in step S4), the In-Group Proportion index is used to measure each sample of distance in certain one kind
Whether nearest sample is in same class, and the average IGP index of all clusters is bigger, and the quality for indicating cluster is better, maximum value
Corresponding class number is preferable clustering number, i.e.,
In formula, u is the category of certain cluster, and Class (j) is the category of sample j, jNFor the nearest sample of distance sample j, # is to meet
The number of condition.
5. a kind of high-speed railway passenger flow Time segments division method based on neighbour's propagation clustering according to claim 1, special
Sign is: in step S6), the passenger flow satisfactory rate of information demand is used to embody each passenger flow whereabouts of high-speed railway and related road network
Between, the passenger's conveying capacity and passenger flow need satisfaction degree that train running scheme provides especially are arranged in transport capacity resource condition
Under the constraint of vehicle staffing condition, by the Passenger Traffic that can obtain effective transportation service under the conditions of set train running scheme
It is indicated with the ratio of passenger flow total demand, calculation formula is as follows:
In formula, q'wFor the passenger flow total amount that passenger flow OD conveys high-speed railway w, w is road network passenger flow whereabouts number.
6. a kind of high-speed railway passenger flow Time segments division method based on neighbour's propagation clustering according to claim 1, special
Sign is: in step S6), the train attendance that is averaged refers to the average value of all train attendances in range of value, column
Vehicle is averaged the volume of the flow of passengers that attendance refers to that train is carried in its running section and the train provides the weighting ratio of seat seat sum, this
Index is used to reflect passenger between OD pairs of different passenger flows to various types bullet train selection result, and train is averaged attendance
Calculation formula is as follows:
In formula,For the volume of the flow of passengers that train h is carried at section (i, j), AhFor the staffing number of train h, EhFor the area of train h operation
Number of segment.
7. a kind of high-speed railway passenger flow Time segments division method based on neighbour's propagation clustering according to claim 1, special
Sign is: in step S6), passenger flow demand structure is made of different demand directions, and each demand direction can have arrival mesh
Ground through or transfer riding scheme, passenger flow rate of going directly refers in set train running scheme and passenger flow demand structure
Under, the volume of the flow of passengers to go directly to destination between each passenger flow demand point pair without transfer removes upwards the always ratio of the volume of the flow of passengers with this,
Its calculation formula is:
In formula, w is road network passenger flow whereabouts number, | e | it is the number of transfer of some whereabouts passenger flow,It is straight between not changed to w for passenger flow OD
The passenger number arrived at the destination is connect,Pass through for passenger flow OD between w | e | it is secondary to change to the passenger number arrived at the destination.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910307332.7A CN110119884B (en) | 2019-04-17 | 2019-04-17 | High-speed railway passenger flow time interval division method based on neighbor propagation clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910307332.7A CN110119884B (en) | 2019-04-17 | 2019-04-17 | High-speed railway passenger flow time interval division method based on neighbor propagation clustering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110119884A true CN110119884A (en) | 2019-08-13 |
| CN110119884B CN110119884B (en) | 2022-09-13 |
Family
ID=67521058
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910307332.7A Active CN110119884B (en) | 2019-04-17 | 2019-04-17 | High-speed railway passenger flow time interval division method based on neighbor propagation clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110119884B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112181955A (en) * | 2020-09-01 | 2021-01-05 | 西南交通大学 | Data standard management method for information sharing of heavy haul railway comprehensive big data platform |
| CN112749836A (en) * | 2020-12-22 | 2021-05-04 | 蓝海（福建）信息科技有限公司 | Customized passenger intelligent transportation capacity allocation method based on passenger flow time sequence |
| CN113902011A (en) * | 2021-10-08 | 2022-01-07 | 南威软件股份有限公司 | Urban rail transit short-time passenger flow prediction method based on cyclic neural network |
| CN116757390A (en) * | 2023-05-05 | 2023-09-15 | 北京蔚行科技有限公司 | Bus operation period division method based on time sequence clustering |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105857350A (en) * | 2016-03-17 | 2016-08-17 | 中南大学 | High-speed rail train driving method based on section profile passenger flow |
| WO2017063356A1 (en) * | 2015-10-14 | 2017-04-20 | 深圳市天行家科技有限公司 | Designated-driving order predicting method and designated-driving transport capacity scheduling method |
| CN107145985A (en) * | 2017-05-09 | 2017-09-08 | 北京城建设计发展集团股份有限公司 | A kind of urban track traffic for passenger flow Regional Linking method for early warning |
| JP2018503920A (en) * | 2015-01-27 | 2018-02-08 | ベイジン ディディ インフィニティ テクノロジー アンド ディベロップメント カンパニー リミティッド | Method and system for providing on-demand service information |
| CN108665083A (en) * | 2017-03-31 | 2018-10-16 | 江苏瑞丰信息技术股份有限公司 | A kind of method and system for advertisement recommendation for dynamic trajectory model of being drawn a portrait based on user |
| CN108805344A (en) * | 2018-05-29 | 2018-11-13 | 五邑大学 | A kind of high-speed railway network train running scheme optimization method considering time-dependent demand |
-
2019
- 2019-04-17 CN CN201910307332.7A patent/CN110119884B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2018503920A (en) * | 2015-01-27 | 2018-02-08 | ベイジン ディディ インフィニティ テクノロジー アンド ディベロップメント カンパニー リミティッド | Method and system for providing on-demand service information |
| WO2017063356A1 (en) * | 2015-10-14 | 2017-04-20 | 深圳市天行家科技有限公司 | Designated-driving order predicting method and designated-driving transport capacity scheduling method |
| CN105857350A (en) * | 2016-03-17 | 2016-08-17 | 中南大学 | High-speed rail train driving method based on section profile passenger flow |
| CN108665083A (en) * | 2017-03-31 | 2018-10-16 | 江苏瑞丰信息技术股份有限公司 | A kind of method and system for advertisement recommendation for dynamic trajectory model of being drawn a portrait based on user |
| CN107145985A (en) * | 2017-05-09 | 2017-09-08 | 北京城建设计发展集团股份有限公司 | A kind of urban track traffic for passenger flow Regional Linking method for early warning |
| CN108805344A (en) * | 2018-05-29 | 2018-11-13 | 五邑大学 | A kind of high-speed railway network train running scheme optimization method considering time-dependent demand |
Non-Patent Citations (1)
| Title |
|---|
| 刘吉华等: "不同轴重下轮轨损伤行为研究", 《五邑大学学报(自然科学版)》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112181955A (en) * | 2020-09-01 | 2021-01-05 | 西南交通大学 | Data standard management method for information sharing of heavy haul railway comprehensive big data platform |
| CN112181955B (en) * | 2020-09-01 | 2022-12-09 | 西南交通大学 | Data standard management method for information sharing of heavy haul railway comprehensive big data platform |
| CN112749836A (en) * | 2020-12-22 | 2021-05-04 | 蓝海（福建）信息科技有限公司 | Customized passenger intelligent transportation capacity allocation method based on passenger flow time sequence |
| CN113902011A (en) * | 2021-10-08 | 2022-01-07 | 南威软件股份有限公司 | Urban rail transit short-time passenger flow prediction method based on cyclic neural network |
| CN116757390A (en) * | 2023-05-05 | 2023-09-15 | 北京蔚行科技有限公司 | Bus operation period division method based on time sequence clustering |
| CN116757390B (en) * | 2023-05-05 | 2024-08-27 | 北京蔚行科技有限公司 | Bus operation period division method based on time sequence clustering |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110119884B (en) | 2022-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105857350B (en) | A kind of high ferro train based on interval section passenger flow starts method | |
| CN110119884A (en) | A kind of high-speed railway passenger flow Time segments division method based on neighbour's propagation clustering | |
| CN109886491B (en) | Ground bus two-stage optimization scheduling method driven by massive operation data | |
| CN104064028B (en) | Based on public transport arrival time Forecasting Methodology and the system of multiple information data | |
| CN106485359A (en) | A kind of urban track traffic section passenger flow estimation method based on train schedule | |
| CN104766476B (en) | Calculation method for road segment and road network regional traffic state indexes | |
| CN110843870B (en) | Method for maintaining fixed capacity of high-speed railway network graph under abnormal event | |
| CN108564226A (en) | A kind of public bus network optimization method based on taxi GPS and mobile phone signaling data | |
| CN102169524A (en) | Staged multi-path model algorithm of urban rail transit network passenger flow distribution | |
| CN110634292B (en) | Travel time reliability estimation method based on road resistance performance function | |
| CN111191816B (en) | System for identifying travel time chain of urban rail transit passengers | |
| CN109686091B (en) | Traffic flow filling algorithm based on multi-source data fusion | |
| CN104809112A (en) | Method for comprehensively evaluating urban public transportation development level based on multiple data | |
| CN114117700A (en) | Urban public transport network optimization research method based on complex network theory | |
| CN103761589A (en) | Distribution method for urban rail transit | |
| CN105389640A (en) | Method for predicting suburban railway passenger flow | |
| CN110807651A (en) | Intercity railway passenger ticket time-sharing pricing method based on generalized cost function | |
| CN105809280A (en) | Prediction method for airport capacity demands | |
| CN106327867B (en) | Bus punctuation prediction method based on GPS data | |
| CN113935181A (en) | Train simulation operation optimization system construction method based on matched passenger flow | |
| CN112784000A (en) | Passenger searching method based on taxi track data | |
| CN109389305A (en) | Method for judging passenger traffic flow state in urban rail transit section | |
| CN109522584A (en) | A kind of tramcar departure time-table design method | |
| CN112116124A (en) | Auditing method of bus network optimization scheme based on traveler visual angle | |
| CN116451867A (en) | Subway short-time passenger flow prediction method based on space-time travel path calibration |
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 |