CN107145985A - A kind of urban track traffic for passenger flow Regional Linking method for early warning - Google Patents
A kind of urban track traffic for passenger flow Regional Linking method for early warning Download PDFInfo
- Publication number
- CN107145985A CN107145985A CN201710322594.1A CN201710322594A CN107145985A CN 107145985 A CN107145985 A CN 107145985A CN 201710322594 A CN201710322594 A CN 201710322594A CN 107145985 A CN107145985 A CN 107145985A
- Authority
- CN
- China
- Prior art keywords
- mrow
- passenger flow
- msub
- early warning
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000003066 decision tree Methods 0.000 claims abstract description 11
- 238000013480 data collection Methods 0.000 claims abstract description 4
- 230000009467 reduction Effects 0.000 claims abstract description 3
- 235000019580 granularity Nutrition 0.000 claims description 39
- 238000012544 monitoring process Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 16
- 238000010606 normalization Methods 0.000 claims description 11
- 238000000205 computational method Methods 0.000 claims description 7
- 238000012806 monitoring device Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 230000008439 repair process Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 238000005192 partition Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 238000002715 modification method Methods 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 238000007619 statistical method Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a kind of urban track traffic for passenger flow Regional Linking method for early warning, comprise the following steps：Real-time data collection is simultaneously pre-processed to data；Passenger flow short-time forecasting model based on history residual analysis, and the prediction difference that the calculating of real-time difference data obtains predetermined period is combined, and the same period monitor value reduction of combination history obtains the predicted value of predetermined period；The threshold value for obtaining average speed and density is calculated using clustering method, comprehensive distinguishing obtains the passenger flow early warning event in each region；Build the station monitored area passenger flow early warning event discrimination model based on decision tree, draw the crowded risk index of station passenger flow and passenger flow regional early warning index, aggregative weighted obtains station comprehensive pre-warning index, sets up the discrimination formula of station early warning event, and calculating obtains station early warning event class.
Description
Technical field
The invention belongs to field of urban rail, and in particular to a kind of urban track traffic for passenger flow Regional Linking
Method for early warning.
Background technology
Urban rail transit in China development is in the fast-developing phase, and urban structure, track traffic form, passenger flow feature are equal
It is unstable, cause the imbalance between supply and demand in the regular period to protrude, especially show that early evening peak gauze transport power is difficult to meet large passenger flow
The demand of trip, causes urban railway station to be detained crowding phenomenon and protrudes, passenger falls down and passenger's collision event happens occasionally, and causes political affairs
Mansion, operation enterprise, the public greatly pay close attention to.To alleviate website passenger traffic combination pressure problem, current Beijing Metro is at 74 stations
Point takes normalization passenger flow control in early evening peak, following as new line opens operation, and the scope and dynamics of passenger flow control will be by
Step is strengthened.At present, mainly relied on for the setting of the selection of flow control website, flow control time range and flow control intensity in operation management
The work on the spot experience of administrative department, lacks rational scientific explarnation and checking, when running into large-scale activity, extreme climate, burst
During the sudden large passenger flow that event triggers, due to lacking effective passenger flow monitoring means, passenger flow trend prediction and Forewarn evaluation skill
Art means, easily miss optimal Deal with Time and trigger potential passenger flow to trample risk generation.
Therefore, relying on the project support of Traffic In Beijing committee, Municipal Commission of Science and Technology etc., actual demand is runed with reference to Beijing Metro,
Information-based passenger flow data acquisition means are tentatively installed in more than 20 representative stations deployment of Beijing Metro, and realize that passenger flow is careful
Change the acquisition of information；In addition, relying on the project support of the Ministry of Science and Technology, information-based monitoring means and the passenger flow state of automation
Identification technique will obtain further genralrlization and application.However, how on the dynamic data analysis foundation based on limited monitoring point,
Science judges the interaction relation of the passenger flow bearing capacity of subway station and the degree of loading of each monitored area in station, proposes to be applied to subway
Each regional early warning discrimination model of actual management, sets up the early warning method of discrimination of reaction website integrated carrying ability, is urgently to solve
Certainly the problem of.
The content of the invention
It is an object of the invention to provide a kind of urban track traffic for passenger flow Regional Linking method for early warning so that station passenger flow
The passenger flow joint control of management and control and multiple websites becomes finer.
For up to above-mentioned purpose, a kind of urban track traffic for passenger flow Regional Linking method for early warning comprises the following steps：
1) primary monitoring data collection and the pretreatment of primary monitoring data, union meter calculate 30 second basic time granularity
Passenger flow data, including intensity of passenger flow, passenger flow speed and passenger flow data on flows；
2) using the intensity of passenger flow of 30 second basic time granularity, passenger flow speed as input, using based on history residual analysis
Passenger flow short-time forecasting model, prediction obtains passenger flow averag density, the passenger flow average speed of following a variety of time dimensions；
3) using the Historical Monitoring density value of each monitored area in station as input, using data clustering method by each monitored area
Density and cluster centre value that traffic partition is four grades, obtained respectively with reference to monitored area type of service horizontal division threshold value
The averag density and average speed threshold value of monitored area；
4) with the passenger flow forecast of the average speed of real-time passenger flow, the averag density of passenger flow and following a variety of time dimensions
Averag density is input, builds the station monitored area passenger flow early warning event discrimination model based on decision tree, contrasts each monitoring section
The averag density in domain and the threshold value of average speed, comprehensive distinguishing obtain each monitored area passenger flow one-level, two grades, three-level, level Four
Early warning event；
5) using the intensity of passenger flow and weight coefficient of 30 second basic time granularity of monitored area as input, station is calculated overall
Passenger flow weighted density, with reference to the maximum Safe Density threshold value at station, normalization obtains the crowded risk index of station passenger flow；
6) using monitored area passenger flow early warning event as input, early warning risk is done into equal interval quantizing sign, each monitoring section is built
The weight coefficient of domain importance, calculating obtains regional early warning intensity, and normalization obtains passenger flow regional early warning index；
7) using the crowded risk index of station passenger flow and region passenger flow early warning index as input, weighted calculation obtains station early warning
Index；Station early warning event discriminant function is built, quantifies warning grade threshold value, obtains station early warning event.
From the above technical solution of the present invention shows that, the present invention closely surrounds the difficulty for passenger flow early warning in current industry
Topic, and combine that station is actual to run demand, the urban track traffic for passenger flow Regional Linking method for early warning of proposition can become more meticulous visitor
Flow tube control and the passenger flow joint control of multiple websites, so that the service level of urban track traffic is improved, significantly more efficient guarantee passenger
Safety, convenient trip gives full play to the carrying capacity of urban track traffic.
Brief description of the drawings
Accompanying drawing is not intended to drawn to scale.In the accompanying drawings, each identical or approximately uniform group shown in each figure
It can be indicated by the same numeral into part.For clarity, in each figure, not each part is labeled.
Now, by example and the embodiments of various aspects of the invention will be described in reference to the drawings, wherein：
Fig. 1 is the flow chart of the urban track traffic for passenger flow Regional Linking method for early warning of the embodiment of the present invention.
Fig. 2 be step 4) in the station monitored area passenger flow early warning event discrimination model based on decision tree Computing Principle stream
Cheng Tu.
Embodiment
In order to know more about the technology contents of the present invention, especially exemplified by specific embodiment and institute's accompanying drawings are coordinated to be described as follows.
The present invention provides a kind of urban track traffic for passenger flow Regional Linking method for early warning, comprises the following steps：
1) primary monitoring data collection and the pretreatment of primary monitoring data, union meter calculate 30 second basic time granularity
Passenger flow data, including intensity of passenger flow, passenger flow speed and passenger flow data on flows；The primary monitoring data include intensity of passenger flow,
Passenger flow speed and passenger flow flow；
2) using the intensity of passenger flow of 30 second basic time granularity, passenger flow speed as input, using based on history residual analysis
Passenger flow short-time forecasting model, prediction obtains passenger flow averag density, the passenger flow average speed of following a variety of time dimensions；
3) using the Historical Monitoring density value of each monitored area in station as input, using data clustering method by each monitored area
Density and cluster centre value that traffic partition is four grades, obtained respectively with reference to monitored area type of service horizontal division threshold value
The averag density and average speed threshold value of monitored area；
4) with the passenger flow forecast of the average speed of real-time passenger flow, the averag density of passenger flow and following a variety of time dimensions
Averag density is input, builds the station monitored area passenger flow early warning event discrimination model based on decision tree, contrasts each monitoring section
The averag density in domain and the threshold value of average speed, comprehensive distinguishing obtain each monitored area passenger flow one-level, two grades, three-level, level Four
Early warning event, wherein by calculating the average by monitored area average speed v of all pedestrians in L, obtaining passenger flow and putting down
Equal speed is Σ (v)/n, wherein v=L/t；
5) using the intensity of passenger flow and weight coefficient of 30 second basic time granularity of monitored area as input, station is calculated overall
Passenger flow weighted density, with reference to the maximum Safe Density threshold value at station, normalization obtains the crowded risk index of station passenger flow；
6) using monitored area passenger flow early warning event as input, early warning risk is done into equal interval quantizing sign, each monitoring section is built
The weight coefficient of domain importance, calculating obtains regional early warning intensity, and normalization obtains passenger flow regional early warning index；
7) using the crowded risk index of station passenger flow and region passenger flow early warning index as input, weighted calculation obtains station early warning
Index；Station early warning event discriminant function is built, quantifies warning grade threshold value, obtains station early warning event.
The step 1) in, the preprocessing process of primary monitoring data includes data time synchronization and data repair two steps
Suddenly, data time synchronously referred to the integral point time of the acquisition time specification of each monitoring device to the acquisition granularity, and data reparation includes
Missing data distribution characteristics is extracted, data interpolating processing, if missing data is in continuously distributed, using history same period associated data
Repaired；If missing data is in a discrete distribution, row interpolation reparation is entered using Lagrange's interpolation.
In some specific examples, the preprocessing process of primary monitoring data includes data time synchronization and data reparation
Be implemented as follows：
1) data time synchronizing process referred to the integral point time of the acquisition time specification of each monitoring device to the acquisition granularity, from
And it is easy to follow-up data statistics and information processing.Such as original data acquisition granularity is to be spaced for 5 seconds, then when by all collections
Between carry out rounding operation, the number of seconds specification of time was ended up to 0 second or 5 seconds, it is assumed that S is certain acquisition time T number of seconds, then S=
[S/5] * 5, wherein [] is downward rounding operation.
2) data repair process refers to carries out integrality scanning for original data sequence, if there is partial data missing,
Data reparation and recovery need to be carried out using interpolation method；If there is shortage of data in the presence of continuous one piece of data, using the history same period
Data are filled a vacancy and repaired.
Passenger flow data sequence { Y }={ y after time synchronized is carried out for passenger flow monitoring device0,y1,y2…ym-1,ymPress
Ascending sort is carried out according to acquisition time；If equipment acquisition interval is Δ t, according to the beginning of original data sequence and end time,
Construction correspondence time series is { T }={ t0,t1,t2…tn-1,tn, wherein Δ t=tn-tn-1If, m<N, then the data sequence is not
Completely, need to by first time scanning obtain missing data time set { T ' }=t ', t ", t " ' ... ts-1,ts}。
Secondly the distribution character of the time set { T ' } of missing data, if because equipment goes offline or equipment fault reason causes
Shortage of data in continuous a period of time, then need to carry out data reparation using history same period associated data；If due to data transfer
Or resolving causes scattered individual data to lack, then repaired using interpolation method.
First difference processing is carried out to time set { T ' }, obtains judging sequence { Z }={ ▽ T ' }={ zi=ti+1-ti|i
=0,1,2, s-1 }, if zi=Δ t, then repaired using history contemporaneous data sequence, if zi＞ Δ t, then using Lagrange
Interpolation method carries out data reparation.Construct the multinomial of Lagrange's interpolation
The basic function expression formula of wherein interpolating function is：
Wherein L (t) is to need the value of insertion, l in tj(t) it is lagrange polynomial, (tj,yj) represent reality
Observation coordinate value, in tjMoment observes to obtain yjValue.
Further, the step 1) in, each monitoring section in station at the 5 seconds intervals monitored according to station passenger flow monitoring device
The intensity of passenger flow in domain, calculates the intensity of passenger flow of basic time granularity, and obtain 30 seconds substantially using 90% quantile collection meter method
The passenger flow data of time granularity, data set meter calculating process is as follows：
Set device the acquisition granularity is 5s, and the granularity of passenger flow estimation and early warning is 30s, by the number of 6 5s periods in 30s
According to merging, data set meter is obtained；For passenger flow averag density and average speed, averaged is obtained, for passenger flow flow, directly
Connect to ask to add up and be worth to；
Every 30 seconds, the intensity of passenger flow of each 5 seconds time granularities in monitored area in station in first 30 seconds is read, is tried to achieve in 30s
Maximal density：
ρ30s=Max { ρ5s,i},i∈[1,6]
In formula, ρ30sFor the 30 seconds granularity density values in station monitored area, ρ5s,iFor the i-th 5 seconds grains in station monitored area
Spend density value.
Further, the step 2) in intensity of passenger flow short-time forecasting model based on history residual analysis the step of it is as follows：
1) historical data of history same period last week and same period week before last bulk sample sheet is read, first difference processing is carried out, obtains
Historical sample sequence of differencesWherein m is the data sample amount of sampling, and T is history same period correspondence
At the time of, λ is the periodicity of prediction：
2) same day local measured data and same period last week local history data are read, first difference processing is carried out, obtains office
Portion's same day actual measurement sequence of differences { ▽ ρt|t∈[T-m,T]}
3) model value fitting is predicted with historical sample sequence of differences, model is carried out using time series predicting model
Parameter Estimation, calculating obtains prediction model parameterses, and forecast model is as follows：
Wherein ρ (t) represents the predicted density in t, αiFor the weight coefficient of t-i moment density, δiIt is close for the t-i moment
The weighted value of residual error is spent, p is autocorrelation order, and q is partial autocorrelation exponent number；ρ (t-i) is the actual density at t-i moment, ε (t-
I) it is the density residual values at t-i moment；
4) by the same day, locally actual measurement sequence of differences substitutes into forecast model, calculates the prediction obtained in sequence of differences predetermined period
Value：
5) according to the sequence of differences predicted value and the measured value of the history same period of estimation, reduction obtains predetermined period period
Prediction data：
6) the forecast model modification method of festivals or holidays and change shift day：
If a) same day is festivals or holidays, last week is regular working day, then takes the same day to do difference with history festivals or holidays same period data
Processing：
If b) same day is working day, last week is festivals or holidays, then takes the same day to do difference processing with week before last contemporaneous data：
If c) same day is two-day weekend but is adjusted to working, same period last week is normal day off, then takes regular working day after having holidays by turns
Working day same period last week do difference processing：
If d) same day is normal two-day weekend, because taking off to go to work, then the same day should be taken to be made the difference with week before last contemporaneous data last week
Value processing
Further, the step 2) in, using the intensity of passenger flow of 30 second basic time granularity as input, using residual based on history
The passenger flow averag density that the passenger flow short-time forecasting model prediction of difference analysis obtains following a variety of time dimensions is that prediction obtains 2 points
Clock, 4 minutes, 15 minutes, the density value of 30 minutes, are concretely comprised the following steps：
First, using 30 second basic time granularity intensity of passenger flow as input, 2 minutes and 15 minutes grains are counted into by collection of averaging
The intensity of passenger flow of degree：
Secondly, using 2 minutes averag density data as input, using the step described in claim 3, prediction is following 2 minutes
And the intensity of passenger flow value of 4 minutes；Using 15 minutes averag density data as input, using the step described in claim 3, prediction is not
Come 15 minutes and following 30 minutes intensity of passenger flow.
Further, the step 2) in, using 30 second basic time granularity passenger flow flow as input, calculating is obtained 2 minutes
And the passenger flow flow of 15 minutes；With the passenger flow flow of 2 minutes, prediction obtained the passenger flow flow of 2 minutes, 4 minutes；With 15 minutes
Passenger flow flow, prediction obtains the passenger flow flow of 15 minutes, 30 minutes.Concretely comprise the following steps：
First, using 30 second basic time granularity passenger flow flow as input, collection count into 2 minutes and 15 minutes granularities passenger flow stream
Amount：
Next, using 2 minutes volume of the flow of passengers data as input, computational methods are counted using collection, 2 minutes and 4 minutes future of prediction
The volume of the flow of passengers；Using 15 minutes volumes of the flow of passengers as input, computational methods, following 15 minutes of prediction and following 30 minutes passenger flow are counted using collection
Amount.
Further, the step 3) in, it is right according to U.S.'s public transport traffic capacity and service quality manual (second edition)
In the level of service division standard of different zones type, passage and building staircase select E grades of upper density limit values to be used as areal concentration threshold
Value, waits in line area and selects D grades of upper density limits as areal concentration threshold value；Using the method update area density threshold of clustering
Value, carries out clustering processing by the density data of sample and is divided into 4 class data, passenger flow is used as using the cluster centre maximum of 4 classes
The congestion threshold of density.
Further, the step 4) in, the regional early warning event decision model based on decision tree is set up, specific steps are such as
Under：
First, the root node of decision tree is created, selection influences the characteristic attribute of passenger flow early warning event, including：Passenger flow is real-time
Density, real-time traffic, average speed, 2 minutes density of prediction, 4 minutes density of prediction, the attribute such as 15 minutes density of prediction；
Secondly, input sample region passenger flow early warning event training data, and according to the node point of property value structure resulting number
Branch is divided；
Finally, according to actual and prediction passenger flow input data, decision tree discriminatory analysis, output area early warning thing are carried out
Part.
Further, the step 5) in, using the passenger flow monitored density and weight coefficient of monitored area as input, calculate station
Overall passenger flow weighted density, with reference to the maximum Safe Density threshold value at station, normalization obtains the crowded risk index of station passenger flow, has
Body computational methods are：
Represent the averag density of the different monitored areas in station, ρiThe density of each monitored area in station is represented,Represent some
The monitoring point j of monitored area weight coefficient, QjFor the two-way volume of the flow of passengers in some monitoring point statistical time range, ρmaxRepresent some
The maximum allowable density value of monitored area, PRI is the crowded risk index of station passenger flow, using statistical method, counts first three
The value of 98%th quantile of individual month as some monitored area maximum allowable density.
Further, the step 6) in, using monitored area passenger flow early warning event as input, early warning risk is done into equal interval quantizing
Characterize, build the weight coefficient of each monitored area importance, calculating obtains regional early warning intensity, and normalization obtains passenger flow region
Early warning index, circular is：
In formula：For the weight coefficient of each monitored area, with the location of monitored area (platform, paid area, non-pair
Take area) and passenger flow scale correlation；RWI is monitored area passenger flow early warning index, κjFor the value-at-risk of monitored area event, event wind
Danger value obeys linear change feature, and j represents the grade of event, κ1=4, κ2=3, κ3=2, κ4=1；ψiSentence for monitored area event
Determine coefficient, if the monitored area prediction occurring event, be worth for 1, be otherwise 0；N is the quantity of the monitored area at station.
Further, the step 7) in, using the crowded risk index of station passenger flow and region passenger flow early warning index as input, plus
Power calculating obtains station early warning index；Station early warning event discriminant function is built, quantifies warning grade threshold value, obtains station early warning
Event, circular is：
PWI=λ × PRI+ γ × RWI
Wherein, PWI is station early warning index, and PRI is the crowded risk index of station passenger flow, and RWI is that monitored area passenger flow is pre-
Alert index, λ is the crowded concern coefficient in station, and γ is that early warning event in monitored area pays close attention to coefficient, λ+γ=1, λ, γ ∈ [0,1], f
(PWI) it is station early warning event discriminant function, FiRepresent the threshold value of warning of the i-th grade.
In summary, the present invention is using the passenger flow Monitoring Data in each region in station as input, the integrality of scanning analysis data,
And the distribution character of binding deficient data sequence selects historical context Data Matching and data interpolating repair process, from data set
Meter processing method obtains the passenger flow data of a variety of time granularities, realizes the pretreatment of passenger flow data；With the same issue of real-time and history
According to input, handle in real time using calculus of differences and history same period sample difference data sequence, and carry out prediction model parameterses
Estimation, obtains argument sequence forecast model, and the real-time difference data of combination calculates the prediction difference for obtaining predetermined period, and combines
History same period monitor value reduces the predicted value for obtaining predetermined period；With real-time intensity of passenger flow, real-time average speed and a variety of
The predicted density data of time granularity are input, and the threshold value for obtaining average speed and density is calculated using clustering method, comprehensive
Close the passenger flow early warning event for differentiating and obtaining each region；Station passenger flow warning algorithm based on Regional Linking includes setting up station passenger flow
Crowded risk index and passenger flow regional early warning exponential model, aggregative weighted obtain station comprehensive pre-warning index, set up station early warning
The discrimination formula of event, calculating obtains station early warning event class.
Although the present invention is disclosed above with preferred embodiment, so it is not limited to the present invention.Skill belonging to of the invention
Has usually intellectual in art field, without departing from the spirit and scope of the present invention, when can be used for a variety of modifications and variations.Cause
This, the scope of protection of the present invention is defined by those of the claims.
Claims (10)
1. a kind of urban track traffic for passenger flow Regional Linking method for early warning, it is characterised in that comprise the following steps：
1) primary monitoring data collection and the pretreatment of primary monitoring data, union meter calculate the visitor of 30 second basic time granularity
Flow data, including intensity of passenger flow, passenger flow speed and passenger flow data on flows；
2) using the intensity of passenger flow of 30 second basic time granularity, passenger flow speed as input, using the passenger flow based on history residual analysis
Short-time forecasting model, prediction obtains passenger flow averag density, the passenger flow average speed of following a variety of time dimensions；
3) using the Historical Monitoring density value of each monitored area in station as input, using data clustering method by the close of each monitored area
Degree and the cluster centre value that traffic partition is four grades, each monitoring is obtained with reference to monitored area type of service horizontal division threshold value
The averag density and average speed threshold value in region；
4) it is average with the passenger flow forecast of the average speed of real-time passenger flow, the averag density of passenger flow and following a variety of time dimensions
Density is input, builds the station monitored area passenger flow early warning event discrimination model based on decision tree, contrasts each monitored area
The threshold value of averag density and average speed, comprehensive distinguishing obtain each monitored area passenger flow one-level, two grades, three-level, level Four early warning
Event；
5) using the intensity of passenger flow and weight coefficient of 30 second basic time granularity of monitored area as input, the overall passenger flow in station is calculated
Weighted density, with reference to the maximum Safe Density threshold value at station, normalization obtains the crowded risk index of station passenger flow；
6) using monitored area passenger flow early warning event as input, early warning risk is done into equal interval quantizing sign, each monitored area weight is built
The weight coefficient to be spent, calculating obtains regional early warning intensity, and normalization obtains passenger flow regional early warning index；
7) using the crowded risk index of station passenger flow and region passenger flow early warning index as input, weighted calculation obtains station early warning and referred to
Number；Station early warning event discriminant function is built, quantifies warning grade threshold value, obtains station early warning event.
Wherein, the step 1) in, the pretreatment of primary monitoring data includes data time synchronization and data repair two steps；
Data time synchronously referred to the integral point time of the acquisition time specification of each monitoring device to the acquisition granularity；Data reparation includes missing
Data distribution characteristics are extracted, data interpolating processing, if missing data is carried out in continuously distributed using history same period associated data
Repair；If missing data is in a discrete distribution, row interpolation reparation is entered using Lagrange's interpolation.
2. urban track traffic for passenger flow Regional Linking method for early warning according to claim 1, it is characterised in that the step
1) in, the intensity of passenger flow of each monitored area in station at the 5 seconds intervals monitored according to station passenger flow monitoring device calculates 30 seconds bases
The intensity of passenger flow of this time granularity, and using the passenger flow data of 90% quantile collection meter method, 30 second basic time granularity of acquisition,
Data set meter calculating process is as follows：
Set device the acquisition granularity is 5 seconds, and the granularity of passenger flow estimation and early warning is 30 seconds, by the number of 65 second periods in 30s
According to merging, data set meter is obtained；For passenger flow averag density and average speed, averaged is obtained, for passenger flow flow, directly
Connect to ask to add up and be worth to；
Every 30 seconds, the intensity of passenger flow of each 5 seconds time granularities in monitored area in station in first 30 seconds is read, the maximum in 30 seconds is tried to achieve
Density：
ρ30s=Max { ρ5s,i},i∈[1,6]
In formula, ρ30sFor the 30 seconds granularity density values in station monitored area, ρ5s,iIt is close for the i-th 5 seconds granularities in station monitored area
Angle value.
3. urban track traffic for passenger flow Regional Linking method for early warning according to claim 1, it is characterised in that the step
2) modeling procedure of the intensity of passenger flow short-time forecasting model based on history residual analysis is as follows in：
1) historical data of history same period last week and same period week before last bulk sample sheet is read, first difference processing is carried out, obtains history
Sample sequence of differencesWherein m for sampling data sample amount, T be the history same period it is corresponding when
Carve, λ is the periodicity of prediction：
<mrow>
<mo>&dtri;</mo>
<msubsup>
<mi>&rho;</mi>
<mi>t</mi>
<mrow>
<mi>L</mi>
<mi>a</mi>
<mi>s</mi>
<mi>t</mi>
<mi>W</mi>
<mi>e</mi>
<mi>e</mi>
<mi>k</mi>
</mrow>
</msubsup>
<mo>=</mo>
<msubsup>
<mi>&rho;</mi>
<mi>t</mi>
<mrow>
<mi>D</mi>
<mi>a</mi>
<mi>y</mi>
<mo>-</mo>
<mn>7</mn>
</mrow>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>&rho;</mi>
<mi>t</mi>
<mrow>
<mi>D</mi>
<mi>a</mi>
<mi>y</mi>
<mo>-</mo>
<mn>14</mn>
</mrow>
</msubsup>
<mo>;</mo>
</mrow>
2) same day local measured data and same period last week local history data are read, first difference processing is carried out, local work as is obtained
Day actual measurement sequence of differences
<mrow>
<mo>&dtri;</mo>
<msub>
<mi>&rho;</mi>
<mi>t</mi>
</msub>
<mo>=</mo>
<msubsup>
<mi>&rho;</mi>
<mi>t</mi>
<mrow>
<mi>D</mi>
<mi>a</mi>
<mi>y</mi>
</mrow>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>&rho;</mi>
<mi>t</mi>
<mrow>
<mi>D</mi>
<mi>a</mi>
<mi>y</mi>
<mo>-</mo>
<mn>7</mn>
</mrow>
</msubsup>
</mrow>
3) model value fitting is predicted with historical sample sequence of differences, model parameter is carried out using time series predicting model
Estimation, calculating obtains prediction model parameterses, and forecast model is as follows：
<mrow>
<mi>&rho;</mi>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>p</mi>
</munderover>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mi>&rho;</mi>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>-</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>q</mi>
</munderover>
<msub>
<mi>&delta;</mi>
<mi>i</mi>
</msub>
<mi>&epsiv;</mi>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>-</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
</mrow>
Wherein ρ (t) represents the predicted density in t, αiFor the weight coefficient of t-i moment density, δiIt is residual for t-i moment density
The weighted value of difference, p is autocorrelation order, and q is partial autocorrelation exponent number；ρ (t-i) is the actual density at t-i moment, and ε (t-i) is
The density residual values at t-i moment；
4) by the same day, locally actual measurement sequence of differences substitutes into forecast model, calculates the predicted value obtained in sequence of differences predetermined period：
<mrow>
<mo>&dtri;</mo>
<msubsup>
<mi>&rho;</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mo>&prime;</mo>
</msubsup>
<mo>=</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>p</mi>
</munderover>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mo>&dtri;</mo>
<mi>&rho;</mi>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
<mo>-</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>q</mi>
</munderover>
<msub>
<mi>&delta;</mi>
<mi>i</mi>
</msub>
<mi>&epsiv;</mi>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
<mo>-</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>;</mo>
</mrow>
5) according to the sequence of differences predicted value and the measured value of the history same period of estimation, reduction obtains the prediction of predetermined period period
Data：
<mrow>
<msubsup>
<mi>&rho;</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mrow>
<mi>D</mi>
<mi>a</mi>
<mi>y</mi>
</mrow>
</msubsup>
<mo>=</mo>
<mo>&dtri;</mo>
<msubsup>
<mi>&rho;</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mo>&prime;</mo>
</msubsup>
<mo>+</mo>
<msubsup>
<mi>&rho;</mi>
<mrow>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mrow>
<mi>D</mi>
<mi>a</mi>
<mi>y</mi>
<mo>-</mo>
<mn>7</mn>
</mrow>
</msubsup>
</mrow>
6) the forecast model modification method of festivals or holidays and change shift day：
If a) same day is festivals or holidays, last week is regular working day, then takes the same day to do difference processing with history festivals or holidays same period data：
<mrow>
<mo>&dtri;</mo>
<msub>
<mi>&rho;</mi>
<mi>t</mi>
</msub>
<mo>=</mo>
<msubsup>
<mi>&rho;</mi>
<mi>t</mi>
<mrow>
<mi>D</mi>
<mi>a</mi>
<mi>y</mi>
</mrow>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>&rho;</mi>
<mi>t</mi>
<mrow>
<mi>H</mi>
<mi>o</mi>
<mi>l</mi>
<mi>i</mi>
<mi>d</mi>
<mi>a</mi>
<mi>y</mi>
</mrow>
</msubsup>
<mo>;</mo>
</mrow>
If b) same day is working day, last week is festivals or holidays, then takes the same day to do difference processing with week before last contemporaneous data：
<mrow>
<mo>&dtri;</mo>
<msub>
<mi>&rho;</mi>
<mi>t</mi>
</msub>
<mo>=</mo>
<msubsup>
<mi>&rho;</mi>
<mi>t</mi>
<mrow>
<mi>D</mi>
<mi>a</mi>
<mi>y</mi>
</mrow>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>&rho;</mi>
<mi>t</mi>
<mrow>
<mi>D</mi>
<mi>a</mi>
<mi>y</mi>
<mo>-</mo>
<mn>14</mn>
</mrow>
</msubsup>
<mo>;</mo>
</mrow>
If c) same day is two-day weekend but is adjusted to working, same period last week is normal day off, then takes the upper of regular working day after having holidays by turns
The all working days same period do difference processing：
<mrow>
<mo>&dtri;</mo>
<msub>
<mi>&rho;</mi>
<mi>t</mi>
</msub>
<mo>=</mo>
<msubsup>
<mi>&rho;</mi>
<mi>t</mi>
<mrow>
<mi>D</mi>
<mi>a</mi>
<mi>y</mi>
</mrow>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>&rho;</mi>
<mi>t</mi>
<mrow>
<mi>W</mi>
<mi>o</mi>
<mi>r</mi>
<mi>k</mi>
<mi>d</mi>
<mi>a</mi>
<mi>y</mi>
<mo>-</mo>
<mn>7</mn>
</mrow>
</msubsup>
<mo>;</mo>
</mrow>
If d) same day is normal two-day weekend, the same day should be then taken to be done with week before last contemporaneous data at difference to go to work because taking off last week
Reason
<mrow>
<mo>&dtri;</mo>
<msub>
<mi>&rho;</mi>
<mi>t</mi>
</msub>
<mo>=</mo>
<msubsup>
<mi>&rho;</mi>
<mi>t</mi>
<mrow>
<mi>D</mi>
<mi>a</mi>
<mi>y</mi>
</mrow>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>&rho;</mi>
<mi>t</mi>
<mrow>
<mi>D</mi>
<mi>a</mi>
<mi>y</mi>
<mo>-</mo>
<mn>14</mn>
</mrow>
</msubsup>
<mo>.</mo>
</mrow>
4. urban track traffic for passenger flow Regional Linking method for early warning according to claim 1, it is characterised in that the step
2) in, using the intensity of passenger flow of 30 second basic time granularity as input, using the passenger flow short-term prediction mould based on history residual analysis
The passenger flow averag density that type prediction obtains following a variety of time dimensions is that prediction is obtained 2 minutes, 4 minutes, 15 minutes, 30 minutes
Density value, is concretely comprised the following steps：
First, using 30 second basic time granularity intensity of passenger flow as input, counted into 2 minutes by collection of averaging and 15 minutes granularities
Intensity of passenger flow：
<mrow>
<msub>
<mi>&rho;</mi>
<mrow>
<mn>2</mn>
<mi>min</mi>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>4</mn>
</munderover>
<msub>
<mi>&rho;</mi>
<mrow>
<mn>30</mn>
<mi>s</mi>
<mo>,</mo>
<mi>i</mi>
</mrow>
</msub>
</mrow>
<mn>4</mn>
</mfrac>
</mrow>
<mrow>
<msub>
<mi>&rho;</mi>
<mrow>
<mn>15</mn>
<mi>m</mi>
<mi>i</mi>
<mi>n</mi>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>30</mn>
</munderover>
<msub>
<mi>&rho;</mi>
<mrow>
<mn>30</mn>
<mi>s</mi>
<mo>,</mo>
<mi>i</mi>
</mrow>
</msub>
</mrow>
<mn>30</mn>
</mfrac>
</mrow>
Secondly, using 2 minutes averag density data for input, using the step 1) collection meter computational methods, prediction future 2 minutes and
The intensity of passenger flow value of 4 minutes；Using 15 minutes averag density data as input, using the step 1) collection meter computational methods, prediction
Following 15 minutes and following 30 minutes intensity of passenger flow.
5. urban track traffic for passenger flow Regional Linking method for early warning according to claim 1, it is characterised in that the step
2) in, using 30 second basic time granularity passenger flow flow as input, calculating obtains the passenger flow flow of 2 minutes and 15 minutes；With 2 points
The passenger flow flow of clock, prediction obtains the passenger flow flow of 2 minutes, 4 minutes；With the passenger flow flow of 15 minutes, prediction obtain 15 minutes,
The passenger flow flow of 30 minutes.Concretely comprise the following steps：
First, using 30 second basic time granularity passenger flow flow as input, collection count into 2 minutes and 15 minutes granularities passenger flow flow：
<mrow>
<msub>
<mi>Q</mi>
<mrow>
<mn>21</mn>
<mi>min</mi>
</mrow>
</msub>
<mo>=</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>4</mn>
</munderover>
<msub>
<mi>Q</mi>
<mrow>
<mn>30</mn>
<mi>s</mi>
<mo>,</mo>
<mi>i</mi>
</mrow>
</msub>
</mrow>
<mrow>
<msub>
<mi>Q</mi>
<mrow>
<mn>15</mn>
<mi>m</mi>
<mi>i</mi>
<mi>n</mi>
</mrow>
</msub>
<mo>=</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>30</mn>
</munderover>
<msub>
<mi>Q</mi>
<mrow>
<mn>30</mn>
<mi>s</mi>
<mo>,</mo>
<mi>i</mi>
</mrow>
</msub>
</mrow>
Secondly, using 2 minutes volume of the flow of passengers data as input, using the step 1) collection meter computational methods, predict following 2 minutes and 4
The volume of the flow of passengers of minute；Using 15 minutes volumes of the flow of passengers as input, using the step 1) collection meter computational methods, following 15 minutes of prediction and
Following 30 minutes volume of the flow of passengers.
6. urban track traffic for passenger flow Regional Linking method for early warning according to claim 1, it is characterised in that the step
3) in, drawn according to the second edition U.S. public transport traffic capacity and service quality manual for the service level of different zones type
Minute mark is accurate, and passage and building staircase select E grades of upper density limit values as areal concentration threshold value, wait in line area and select in D grades of density
Limit is used as areal concentration threshold value；Using the method update area density threshold of clustering, the density data of sample is gathered
Class processing be divided into 4 class data, using 4 classes cluster centre maximum as intensity of passenger flow congestion threshold.
7. urban track traffic for passenger flow Regional Linking method for early warning according to claim 1, it is characterised in that the step
4) in, the regional early warning event decision model based on decision tree is set up, is comprised the following steps that：
First, the root node of decision tree is created, selection influences the characteristic attribute of passenger flow early warning event, including：Passenger flow real-time density,
Real-time traffic, average speed, 2 minutes density of prediction, 4 minutes density of prediction, the attribute such as 15 minutes density of prediction；
Secondly, input sample region passenger flow early warning event training data, and drawn according to the node branch of property value structure resulting number
Point；
Finally, according to actual and prediction passenger flow input data, decision tree discriminatory analysis, output area early warning event are carried out.
8. urban track traffic for passenger flow Regional Linking method for early warning according to claim 1, it is characterised in that the step
5) in, using the passenger flow monitored density and weight coefficient of monitored area as input, the overall passenger flow weighted density in station is calculated, with reference to car
The maximum Safe Density threshold value stood, normalization obtains the crowded risk index of station passenger flow, and circular is：
<mrow>
<mi>P</mi>
<mi>R</mi>
<mi>I</mi>
<mo>=</mo>
<mfrac>
<mover>
<mi>&rho;</mi>
<mo>&OverBar;</mo>
</mover>
<msub>
<mi>&rho;</mi>
<mrow>
<mi>m</mi>
<mi>a</mi>
<mi>x</mi>
</mrow>
</msub>
</mfrac>
<mo>&times;</mo>
<mn>10</mn>
</mrow>
Represent the averag density of the different monitored areas in station, ρiThe density of each monitored area in station is represented,Represent that some is monitored
The monitoring point j in region weight coefficient, QjFor the two-way volume of the flow of passengers in some monitoring point statistical time range, ρmaxRepresent that some is monitored
The maximum allowable density value in region, PRI is the crowded risk index of station passenger flow, using statistical method, counts first trimester
The 98%th quantile value as some monitored area maximum allowable density.
9. urban track traffic for passenger flow Regional Linking method for early warning according to claim 1, it is characterised in that the step
6) in, using monitored area passenger flow early warning event as input, early warning risk is done into equal interval quantizing sign, each monitored area is built important
The weight coefficient of degree, calculating obtains regional early warning intensity, and normalization obtains passenger flow regional early warning index, circular
For：
<mrow>
<mi>R</mi>
<mi>W</mi>
<mi>I</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mi>W</mi>
<mi>I</mi>
</mrow>
<msub>
<mi>&kappa;</mi>
<mi>m</mi>
</msub>
</mfrac>
<mo>&times;</mo>
<mn>10</mn>
</mrow>
In formula：It is related to the location of monitored area and passenger flow scale for the weight coefficient of each monitored area；RWI is prison
Survey region passenger flow early warning index, κjFor the value-at-risk of monitored area event, event risk value obeys linear change feature, and j is represented
The grade of event, κ1=4, κ2=3, κ3=2, κ4=1；ψiFor monitored area event coefficient of determination, if the monitored area occur it is pre-
Alert event, is worth for 1, is otherwise 0；N is the quantity of the monitored area at station.
10. urban track traffic for passenger flow Regional Linking method for early warning according to claim 1, it is characterised in that the step
It is rapid 7) in, using the crowded risk index of station passenger flow and monitored area passenger flow early warning index as input, it is pre- that weighted calculation obtains station
Alert index；Station early warning event discriminant function is built, quantifies warning grade threshold value, obtains station early warning event, specific calculating side
Method is：
PWI=λ × PRI+ γ × RWI
<mrow>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>P</mi>
<mi>W</mi>
<mi>I</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mi>1</mi>
</mtd>
<mtd>
<mrow>
<mi>P</mi>
<mi>W</mi>
<mi>I</mi>
<mo>&GreaterEqual;</mo>
<msub>
<mi>F</mi>
<mn>1</mn>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mi>2</mi>
</mtd>
<mtd>
<mrow>
<mi>P</mi>
<mi>W</mi>
<mi>I</mi>
<mo>&GreaterEqual;</mo>
<msub>
<mi>F</mi>
<mn>2</mn>
</msub>
<mi>a</mi>
<mi>n</mi>
<mi>d</mi>
<mi> </mi>
<mi>P</mi>
<mi>W</mi>
<mi>I</mi>
<mo><</mo>
<msub>
<mi>F</mi>
<mn>1</mn>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mi>3</mi>
</mtd>
<mtd>
<mrow>
<mi>P</mi>
<mi>W</mi>
<mi>I</mi>
<mo>&GreaterEqual;</mo>
<msub>
<mi>F</mi>
<mn>3</mn>
</msub>
<mi>a</mi>
<mi>n</mi>
<mi>d</mi>
<mi> </mi>
<mi>P</mi>
<mi>W</mi>
<mi>I</mi>
<mo><</mo>
<msub>
<mi>F</mi>
<mn>2</mn>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mi>4</mi>
</mtd>
<mtd>
<mrow>
<mi>P</mi>
<mi>W</mi>
<mi>I</mi>
<mo>&GreaterEqual;</mo>
<msub>
<mi>F</mi>
<mn>4</mn>
</msub>
<mi>a</mi>
<mi>n</mi>
<mi>d</mi>
<mi> </mi>
<mi>P</mi>
<mi>W</mi>
<mi>I</mi>
<mo><</mo>
<msub>
<mi>F</mi>
<mn>3</mn>
</msub>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
Wherein, PWI is station early warning index, and PRI is the crowded risk index of station passenger flow, and RWI is that monitored area passenger flow early warning refers to
Number, λ is the crowded concern coefficient in station, and γ is that early warning event in monitored area pays close attention to coefficient, λ+γ=1, λ, γ ∈ [0,1], f
(PWI) it is station early warning event discriminant function, FiRepresent the threshold value of warning of the i-th grade.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710322594.1A CN107145985A (en) | 2017-05-09 | 2017-05-09 | A kind of urban track traffic for passenger flow Regional Linking method for early warning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710322594.1A CN107145985A (en) | 2017-05-09 | 2017-05-09 | A kind of urban track traffic for passenger flow Regional Linking method for early warning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107145985A true CN107145985A (en) | 2017-09-08 |
Family
ID=59778661
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710322594.1A Pending CN107145985A (en) | 2017-05-09 | 2017-05-09 | A kind of urban track traffic for passenger flow Regional Linking method for early warning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107145985A (en) |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107862437A (en) * | 2017-10-16 | 2018-03-30 | 中国人民公安大学 | The public domain crowd massing method for early warning and system assessed based on risk probability |
| CN108876062A (en) * | 2018-08-13 | 2018-11-23 | 湖北经济学院 | A kind of big data method and device of crime dramas intelligent predicting |
| CN109086926A (en) * | 2018-07-25 | 2018-12-25 | 南京理工大学 | A kind of track traffic for passenger flow prediction technique in short-term based on combination neural net structure |
| CN109377754A (en) * | 2018-10-29 | 2019-02-22 | 东南大学 | A kind of short-term traffic flow speed predicting method under car networking environment |
| CN109523776A (en) * | 2017-09-20 | 2019-03-26 | 株式会社日立制作所 | Public transport operation plan generating means, method and system |
| CN109948204A (en) * | 2019-03-05 | 2019-06-28 | 清华大学 | A kind of high iron catenary dynamic risk analysis method based on Bayesian network |
| CN110121188A (en) * | 2018-02-07 | 2019-08-13 | 成都鼎桥通信技术有限公司 | A kind of high load capacity alarm method |
| CN110119884A (en) * | 2019-04-17 | 2019-08-13 | 五邑大学 | A kind of high-speed railway passenger flow Time segments division method based on neighbour's propagation clustering |
| CN110309399A (en) * | 2018-02-06 | 2019-10-08 | 北京嘀嘀无限科技发展有限公司 | Scene information method for pushing and device based on date classification |
| CN110400462A (en) * | 2019-07-26 | 2019-11-01 | 中国安全生产科学研究院 | Track traffic for passenger flow monitoring and pre-alarming method and its system based on fuzzy theory |
| CN110459050A (en) * | 2019-05-27 | 2019-11-15 | 华南理工大学 | A kind of short-term bus passenger flow prediction technique based on hybrid decision tree |
| CN110493816A (en) * | 2019-08-21 | 2019-11-22 | 上海工程技术大学 | A kind of real-time predicting method for handing over the subway station volume of the flow of passengers for rail |
| CN110909607A (en) * | 2019-10-24 | 2020-03-24 | 北京中润惠通科技发展有限公司 | Device system for sensing passenger flow in intelligent subway operation |
| CN110942411A (en) * | 2019-11-20 | 2020-03-31 | 北京城建设计发展集团股份有限公司 | Subway station passenger flow grading alarm method based on regional linkage |
| CN111063190A (en) * | 2019-12-10 | 2020-04-24 | 北京工业大学 | Pre-control method and system for oversaturated passenger flow of urban rail transit station platform |
| CN111178598A (en) * | 2019-12-16 | 2020-05-19 | 中国铁道科学研究院集团有限公司 | Passenger flow prediction method and system for railway passenger station, electronic device and storage medium |
| CN111242378A (en) * | 2020-01-15 | 2020-06-05 | 湖南日升工程咨询有限公司 | Engineering process dynamic cost control method based on BIM technology |
| CN111260140A (en) * | 2020-01-19 | 2020-06-09 | 武汉中科通达高新技术股份有限公司 | Method for predicting instantaneous return large passenger flow in subway station |
| CN112287837A (en) * | 2020-10-29 | 2021-01-29 | 北京交通大学 | Urban rail transit station sudden large passenger flow early warning method based on data driving |
| CN112749754A (en) * | 2021-01-18 | 2021-05-04 | 中国民航信息网络股份有限公司 | Method and device for early warning abnormal calculation gear-removing time |
| CN112749862A (en) * | 2019-10-31 | 2021-05-04 | 株洲中车时代电气股份有限公司 | Subway self-adaptive scheduling method based on passenger flow classification and electronic equipment |
| CN112766605A (en) * | 2021-02-02 | 2021-05-07 | 郑州地铁集团有限公司 | Multi-source passenger flow prediction system and method based on container cloud platform |
| CN112883340A (en) * | 2021-04-30 | 2021-06-01 | 西南交通大学 | Track quality index threshold value rationality analysis method based on quantile regression |
| CN113159374A (en) * | 2021-03-05 | 2021-07-23 | 北京化工大学 | Data-driven urban traffic flow rate mode identification and real-time prediction early warning method |
| CN113723716A (en) * | 2021-11-02 | 2021-11-30 | 深圳市城市交通规划设计研究中心股份有限公司 | Passenger flow classification early warning abnormity warning method, device and storage medium |
| CN113822462A (en) * | 2021-08-06 | 2021-12-21 | 上海申铁信息工程有限公司 | Station emergency command method and device |
| CN114037564A (en) * | 2021-10-18 | 2022-02-11 | 浪潮卓数大数据产业发展有限公司 | Method for identifying scenic spot passenger flow congestion based on big data |
| CN115544198A (en) * | 2022-10-25 | 2022-12-30 | 北京磁浮有限公司 | Method and related device for monitoring running state of urban rail transit |
| CN115564151A (en) * | 2022-12-06 | 2023-01-03 | 成都智元汇信息技术股份有限公司 | Sudden large passenger flow form identification method and system based on form identification |
| CN115951704A (en) * | 2022-12-17 | 2023-04-11 | 北京思维实创科技有限公司 | Unmanned aerial vehicle subway inspection method and equipment based on BIM model |
| CN117688505A (en) * | 2024-02-04 | 2024-03-12 | 河海大学 | Prediction method and system for vegetation large-range regional negative abnormality |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102436603A (en) * | 2011-08-29 | 2012-05-02 | 北京航空航天大学 | Rail transit full-road-network passenger flow prediction method based on probability tree destination (D) prediction |
| CN102700576A (en) * | 2012-05-18 | 2012-10-03 | 中国铁道科学研究院电子计算技术研究所 | Passenger flow monitoring method of urban rail traffic network |
| CN103984993A (en) * | 2014-05-13 | 2014-08-13 | 东南大学 | Rail transit passenger flow OD distribution real-time speculation method |
| CN105427002A (en) * | 2015-12-29 | 2016-03-23 | 上海仪电物联技术股份有限公司 | Logistic model-based passenger flow prediction method |
| CN106156890A (en) * | 2016-07-07 | 2016-11-23 | 北京交通大学 | Detection of passenger flow and Forecasting Methodology and system thereof in a kind of urban track traffic passage |
-
2017
- 2017-05-09 CN CN201710322594.1A patent/CN107145985A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102436603A (en) * | 2011-08-29 | 2012-05-02 | 北京航空航天大学 | Rail transit full-road-network passenger flow prediction method based on probability tree destination (D) prediction |
| CN102700576A (en) * | 2012-05-18 | 2012-10-03 | 中国铁道科学研究院电子计算技术研究所 | Passenger flow monitoring method of urban rail traffic network |
| CN103984993A (en) * | 2014-05-13 | 2014-08-13 | 东南大学 | Rail transit passenger flow OD distribution real-time speculation method |
| CN105427002A (en) * | 2015-12-29 | 2016-03-23 | 上海仪电物联技术股份有限公司 | Logistic model-based passenger flow prediction method |
| CN106156890A (en) * | 2016-07-07 | 2016-11-23 | 北京交通大学 | Detection of passenger flow and Forecasting Methodology and system thereof in a kind of urban track traffic passage |
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109523776A (en) * | 2017-09-20 | 2019-03-26 | 株式会社日立制作所 | Public transport operation plan generating means, method and system |
| CN107862437A (en) * | 2017-10-16 | 2018-03-30 | 中国人民公安大学 | The public domain crowd massing method for early warning and system assessed based on risk probability |
| CN107862437B (en) * | 2017-10-16 | 2022-02-22 | 中国人民公安大学 | Public area crowd gathering early warning method and system based on risk probability assessment |
| CN110309399A (en) * | 2018-02-06 | 2019-10-08 | 北京嘀嘀无限科技发展有限公司 | Scene information method for pushing and device based on date classification |
| CN110121188A (en) * | 2018-02-07 | 2019-08-13 | 成都鼎桥通信技术有限公司 | A kind of high load capacity alarm method |
| CN109086926A (en) * | 2018-07-25 | 2018-12-25 | 南京理工大学 | A kind of track traffic for passenger flow prediction technique in short-term based on combination neural net structure |
| CN109086926B (en) * | 2018-07-25 | 2022-03-18 | 南京理工大学 | Short-time rail transit passenger flow prediction method based on combined neural network structure |
| CN108876062A (en) * | 2018-08-13 | 2018-11-23 | 湖北经济学院 | A kind of big data method and device of crime dramas intelligent predicting |
| CN108876062B (en) * | 2018-08-13 | 2022-04-12 | 湖北经济学院 | Big data method and device for intelligent prediction of criminal events |
| CN109377754A (en) * | 2018-10-29 | 2019-02-22 | 东南大学 | A kind of short-term traffic flow speed predicting method under car networking environment |
| CN109948204A (en) * | 2019-03-05 | 2019-06-28 | 清华大学 | A kind of high iron catenary dynamic risk analysis method based on Bayesian network |
| CN109948204B (en) * | 2019-03-05 | 2020-11-03 | 清华大学 | Bayesian network-based dynamic risk analysis method for high-speed rail overhead line system |
| CN110119884A (en) * | 2019-04-17 | 2019-08-13 | 五邑大学 | A kind of high-speed railway passenger flow Time segments division method based on neighbour's propagation clustering |
| CN110119884B (en) * | 2019-04-17 | 2022-09-13 | 五邑大学 | High-speed railway passenger flow time interval division method based on neighbor propagation clustering |
| CN110459050B (en) * | 2019-05-27 | 2021-07-20 | 华南理工大学 | Short-term bus passenger flow prediction method based on mixed decision tree |
| CN110459050A (en) * | 2019-05-27 | 2019-11-15 | 华南理工大学 | A kind of short-term bus passenger flow prediction technique based on hybrid decision tree |
| CN110400462A (en) * | 2019-07-26 | 2019-11-01 | 中国安全生产科学研究院 | Track traffic for passenger flow monitoring and pre-alarming method and its system based on fuzzy theory |
| CN110493816A (en) * | 2019-08-21 | 2019-11-22 | 上海工程技术大学 | A kind of real-time predicting method for handing over the subway station volume of the flow of passengers for rail |
| CN110909607A (en) * | 2019-10-24 | 2020-03-24 | 北京中润惠通科技发展有限公司 | Device system for sensing passenger flow in intelligent subway operation |
| CN112749862A (en) * | 2019-10-31 | 2021-05-04 | 株洲中车时代电气股份有限公司 | Subway self-adaptive scheduling method based on passenger flow classification and electronic equipment |
| CN110942411B (en) * | 2019-11-20 | 2022-09-09 | 北京城建设计发展集团股份有限公司 | Regional linkage based subway station passenger flow graded alarm method |
| CN110942411A (en) * | 2019-11-20 | 2020-03-31 | 北京城建设计发展集团股份有限公司 | Subway station passenger flow grading alarm method based on regional linkage |
| CN111063190A (en) * | 2019-12-10 | 2020-04-24 | 北京工业大学 | Pre-control method and system for oversaturated passenger flow of urban rail transit station platform |
| CN111178598A (en) * | 2019-12-16 | 2020-05-19 | 中国铁道科学研究院集团有限公司 | Passenger flow prediction method and system for railway passenger station, electronic device and storage medium |
| CN111242378A (en) * | 2020-01-15 | 2020-06-05 | 湖南日升工程咨询有限公司 | Engineering process dynamic cost control method based on BIM technology |
| CN111242378B (en) * | 2020-01-15 | 2023-09-15 | 正茂日升工程咨询有限公司 | Engineering process dynamic cost management and control method based on BIM technology |
| CN111260140A (en) * | 2020-01-19 | 2020-06-09 | 武汉中科通达高新技术股份有限公司 | Method for predicting instantaneous return large passenger flow in subway station |
| CN112287837A (en) * | 2020-10-29 | 2021-01-29 | 北京交通大学 | Urban rail transit station sudden large passenger flow early warning method based on data driving |
| CN112287837B (en) * | 2020-10-29 | 2021-08-17 | 北京交通大学 | Urban rail transit station sudden large passenger flow early warning method based on data driving |
| CN112749754A (en) * | 2021-01-18 | 2021-05-04 | 中国民航信息网络股份有限公司 | Method and device for early warning abnormal calculation gear-removing time |
| CN112749754B (en) * | 2021-01-18 | 2024-05-14 | 中国民航信息网络股份有限公司 | Method and device for early warning of abnormal calculation of gear withdrawal time |
| CN112766605A (en) * | 2021-02-02 | 2021-05-07 | 郑州地铁集团有限公司 | Multi-source passenger flow prediction system and method based on container cloud platform |
| CN113159374A (en) * | 2021-03-05 | 2021-07-23 | 北京化工大学 | Data-driven urban traffic flow rate mode identification and real-time prediction early warning method |
| CN113159374B (en) * | 2021-03-05 | 2022-04-22 | 北京化工大学 | Data-driven urban traffic flow rate mode identification and real-time prediction early warning method |
| CN112883340A (en) * | 2021-04-30 | 2021-06-01 | 西南交通大学 | Track quality index threshold value rationality analysis method based on quantile regression |
| CN113822462A (en) * | 2021-08-06 | 2021-12-21 | 上海申铁信息工程有限公司 | Station emergency command method and device |
| CN113822462B (en) * | 2021-08-06 | 2023-10-13 | 上海申铁信息工程有限公司 | Station emergency command method and device |
| CN114037564A (en) * | 2021-10-18 | 2022-02-11 | 浪潮卓数大数据产业发展有限公司 | Method for identifying scenic spot passenger flow congestion based on big data |
| CN113723716A (en) * | 2021-11-02 | 2021-11-30 | 深圳市城市交通规划设计研究中心股份有限公司 | Passenger flow classification early warning abnormity warning method, device and storage medium |
| CN115544198B (en) * | 2022-10-25 | 2023-06-30 | 北京磁浮有限公司 | Urban rail transit running state monitoring method and related device |
| CN115544198A (en) * | 2022-10-25 | 2022-12-30 | 北京磁浮有限公司 | Method and related device for monitoring running state of urban rail transit |
| CN115564151A (en) * | 2022-12-06 | 2023-01-03 | 成都智元汇信息技术股份有限公司 | Sudden large passenger flow form identification method and system based on form identification |
| CN115951704B (en) * | 2022-12-17 | 2023-08-15 | 北京思维实创科技有限公司 | BIM model-based unmanned aerial vehicle subway inspection method and equipment |
| CN115951704A (en) * | 2022-12-17 | 2023-04-11 | 北京思维实创科技有限公司 | Unmanned aerial vehicle subway inspection method and equipment based on BIM model |
| CN117688505A (en) * | 2024-02-04 | 2024-03-12 | 河海大学 | Prediction method and system for vegetation large-range regional negative abnormality |
| CN117688505B (en) * | 2024-02-04 | 2024-04-19 | 河海大学 | Prediction method and system for vegetation large-range regional negative abnormality |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107145985A (en) | A kind of urban track traffic for passenger flow Regional Linking method for early warning | |
| CN112598182B (en) | Intelligent scheduling method and system for rail transit | |
| CN105404850B (en) | Station flow monitoring system for passenger, station passenger flow monitoring method and station passenger flow managing and control system, station passenger flow management-control method | |
| EP4030365A1 (en) | Multi-mode multi-service rail transit analog simulation method and system | |
| CN105279572B (en) | City track traffic passenger flow density index calculating and releasing system | |
| CN102436603B (en) | Rail transit full-road-network passenger flow prediction method based on probability tree destination (D) prediction | |
| CN103984994B (en) | Method for predicting urban rail transit passenger flow peak duration | |
| Gong et al. | Hybrid dynamic prediction model of bus arrival time based on weighted of historical and real-time GPS data | |
| CN110634292A (en) | Travel time reliability estimation method based on road resistance performance function | |
| CN114005274B (en) | Expressway toll station graded linkage management and control method based on equivalent weight of passenger car | |
| CN104765974A (en) | Urban rail transit passenger flow density index calculating method | |
| Liu et al. | Understanding urban bus travel time: Statistical analysis and a deep learning prediction | |
| Cheremisin et al. | Artificial intelligence methods to control the energy efficiency of electric rolling stock online | |
| CN104575049A (en) | Viaduct ramp intelligent inducing control method and device based on array radars | |
| CN112669595B (en) | Network taxi booking flow prediction method based on deep learning | |
| Hou et al. | Delay recovery model for high-speed trains with compressed train dwell time and running time | |
| Wen et al. | Visualizing train delays using tableau and the framework of a delay impact visualization system | |
| CN110796301A (en) | Passenger flow prediction method and device based on IC card data | |
| CN107403241A (en) | A kind of urban track traffic for passenger flow second order fluctuation computational methods | |
| CN113780682A (en) | Rail transit system service fault prediction method based on fault marker | |
| Wiarco et al. | The impact of stability factor of train operations to railway line capacity (Kroya-Kutoarjo-Yogyakarta) Indonesia | |
| Lesley | Generalised costs and the value of time as a method of patronage forecasting | |
| Xue et al. | Modelling and simulation of the urban rail transit operation system based on system dynamics | |
| Yuan et al. | Punctuality of train traffic in Dutch railway stations | |
| CN107730105A (en) | City rail bus stream recognition method and system based on AFC data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170908 |
|
| RJ01 | Rejection of invention patent application after publication |