CN108717583B - Method for predicting passenger volume staying at station in real time under condition of urban rail transit section interruption - Google Patents

Method for predicting passenger volume staying at station in real time under condition of urban rail transit section interruption Download PDF

Info

Publication number
CN108717583B
CN108717583B CN201810446018.2A CN201810446018A CN108717583B CN 108717583 B CN108717583 B CN 108717583B CN 201810446018 A CN201810446018 A CN 201810446018A CN 108717583 B CN108717583 B CN 108717583B
Authority
CN
China
Prior art keywords
station
rail transit
urban rail
interruption
time
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810446018.2A
Other languages
Chinese (zh)
Other versions
CN108717583A (en
Inventor
任刚
王�义
陈佳洁
陆丽丽
徐磊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southeast University
Original Assignee
Southeast University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Southeast University filed Critical Southeast University
Priority to CN201810446018.2A priority Critical patent/CN108717583B/en
Publication of CN108717583A publication Critical patent/CN108717583A/en
Application granted granted Critical
Publication of CN108717583B publication Critical patent/CN108717583B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a real-time prediction method for passenger volume staying at a station under the condition of urban rail transit section interruption, which comprises the steps of collecting card swiping data of an automatic ticket selling and checking system in an urban rail transit stable operation state, establishing a card swiping database of the automatic ticket selling and checking system, counting according to different date types to obtain a standard passenger flow database of the urban rail transit station in the stable operation state, then determining a space influence coefficient and a time influence coefficient of section interruption on the passenger flow of the station according to OD passenger flow data and section interruption related information obtained from an operation unit, and finally calculating to obtain the real-time prediction result of the passenger volume staying at different stations under the condition of section interruption at different date types. The method overcomes the defect that the station detained passenger volume is mainly based on experience in prediction under the condition of interruption of the urban rail transit interval, can improve the prediction precision of the station detained passenger volume, can provide data support for decision makers, and has important application value in the aspects of urban rail transit safety precaution, emergency evacuation and the like.

Description

Method for predicting passenger volume staying at station in real time under condition of urban rail transit section interruption
Technical Field
The invention relates to the field of urban rail transit operation and emergency evacuation, in particular to a method for predicting the passenger capacity staying at a station in real time under the condition of interruption of an urban rail transit interval.
Background
The urban rail transit has the unique advantages of large transportation volume, high speed, accurate time, less pollution, safety and comfort, and has the unique advantages of relieving traffic jam in large cities, and increasingly becomes the key point of construction of large and medium cities in China. By 31.10.2017, 29 cities including Beijing, Shanghai, Shenzhen, Guangzhou, Nanjing, Chongqing, Wuhan, Tianjin and the like have opened operating rail transit lines, the total mileage reaches 3792.19 kilometers, 2536 stations and 128 lines. In the three seasons before 2017, 17 newly-increased start-up construction rail transit lines are added in the city, the total start-up lines are 24, the total mileage reaches 565.79 kilometers, and the stations 371. Urban rail transit becomes the core strength of urban public transportation, and the proportion of the rail transit is up to 40% and the proportion of the secondary attraction composite traffic service is up to 80%. Due to the characteristics of concentrated passenger flow, large transport capacity, preferential space and the like of the rail transit system, once an emergency occurs, operation is delayed or interrupted, a large amount of passenger flow is delayed, and the influence area is large. Taking Nanjing subway as an example, emergency situations such as line signal faults, subway rainwater backflow and the like occur in 8 months 2014, 5 months 2015 and 6 months 2016, so that the urban rail transit operation interval is interrupted, and a large number of passengers are detained. Urban rail transit is a complex system, and the subsystems involved are numerous and have fault conditions. Under the condition of interruption of the urban rail transit section, how to accurately predict the passenger capacity detained by the station in real time has important significance for making an emergency plan and taking related evacuation measures for the station.
The existing estimation of the amount of passengers staying is mainly based on subjective estimation of station personnel, lacks detailed objective data support, is poor in real-time performance, is insufficient in prediction of the probably impending large passenger flow condition, easily causes excessive passenger staying, and has huge potential safety hazards.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the invention provides a method for predicting the passenger staying volume of a station in real time under the condition of interruption of an urban rail transit section, aiming at the characteristics of large subjectivity, low accuracy and poor real-time property of the estimation of the passenger staying volume of the station under the condition of interruption of the existing urban rail transit section, solving the defect that the passenger staying volume of the station under the condition of interruption of the urban rail transit section is mainly based on experience, and improving the prediction precision of the passenger staying volume of the station.
The invention adopts the following technical scheme for solving the technical problems:
the invention provides a real-time prediction method for passengers detained at a bus stop under an interruption condition in an urban rail transit interval, which comprises the following steps of:
step one, collecting standard passenger flow data of a station in a stable operation state of urban rail transit, and establishing a database, wherein the database comprises standard inbound passenger flow data, standard outbound passenger flow data, passenger departure times data and passenger arrival times data;
step two, collecting temporary operation plan and time node data after the interruption of the urban rail transit operation interval;
step three, determining a time influence coefficient and a space influence coefficient of station passenger flow under the condition of interval interruption;
estimating the passenger capacity in the station when the interval interruption occurs;
and step five, under the condition of interruption of the urban rail transit section, predicting the passenger staying at the station at a certain time in the future in real time.
The method for predicting the detained passengers at the bus stop in real time under the condition of interruption of the urban rail transit interval further comprises the following steps that: (1) the urban rail transit operation line is the same as the current situation; (2) in a time period in which no operation accident occurs.
The method for predicting passenger retention at the station under the condition of urban rail transit interval interruption in real time further comprises the following steps of 1:
1) the automatic fare collection system in the stable operation state of the urban rail transit swipes card data, and the field of each piece of data comprises transaction occurrence time, transaction type, transaction equipment number, station number, transaction station, card inside number of the all-purpose card and ticket card type;
2) types of dates, including weekdays, statutory holidays, and general weekends, the collection of dates for each type being denoted D, respectivelyA、 DB、DC；
3) Passenger OD data of subway operation line.
The method for predicting the detained passengers at the bus stop in real time under the condition of the interruption of the urban rail transit section further comprises the step two, wherein the types of the operation sections comprise an interruption section, a single-line two-way operation section and a small traffic two-way operation section.
The method for predicting the detained passengers at the bus stop in real time under the condition of the interruption of the urban rail transit section further comprises the following step three, wherein the spatial influence coefficient is determined according to the following formula:
Figure GDA0003064444310000021
wherein alpha isnThe space influence coefficient of the station n under the interval interruption condition is shown, and m shows the number of stations between the station n and the interruption interval;
step three, the time influence coefficient is determined by the following formula:
Figure GDA0003064444310000022
wherein, betatRepresenting the time-influence coefficient at time T, T, under interval interruption conditionsinterruptIndicates the interval interruption start time, TresumeIndicating the interval interrupt end time.
The method for predicting passenger retention in the station under the condition of urban rail transit section interruption in real time comprises the following steps of four, predicting the passenger volume in the station when section interruption occurs
Figure GDA0003064444310000031
Is derived from the following formula:
Figure GDA0003064444310000032
wherein X is a date type and takes the value of A, B or C; n is a station number corresponding to a unique urban rail transit station; i is the divided minimum time period; FINn，X，iThe standard station entering passenger flow data of the station n in the time period i when the date type is X; FOUT (four opening unified pod)n，X，iThe standard outbound passenger flow data of the station n in the time period i when the date type is X; o isn，X，iThe number of passengers departing in the time period i at the station n when the date type is X; dn，X，iThe number of passengers arriving at station n in time period i when the date type is X; t isinterruptIs interval interrupt occurrence time;
Figure GDA0003064444310000033
the number of passengers at station n when the interruption occurs in the section with date type X.
The method for predicting passenger retention at the bus stop under the interruption condition of the urban rail transit section in real time comprises the following steps ofn，X，tIs derived from the following formula:
(1) when the time T needing prediction is in the interval and the interruption is not recovered, namely Tinterrupt＜t＜TresumeSometimes:
Figure GDA0003064444310000034
(2) when the time T needing to be predicted is in the interval, the normal operation is interrupted, namely T is more than TresumeSometimes:
Figure GDA0003064444310000035
in the formula: x is a date type, and the value of X is A, B or C; n is a station number corresponding to a unique urban rail transit station; i is the divided minimum time period; FINn，X，iThe standard station entering passenger flow data of the station n in the time period i when the date type is X; FOUT (four opening unified pod)n，X，iThe standard outbound passenger flow data of the station n in the time period i when the date type is X; o isn，X，iThe number of passengers departing in the time period i at the station n when the date type is X; dn，X，iThe number of passengers arriving at station n in time period i when the date type is X; t isinterruptIs interval interrupt occurrence time;
Figure GDA0003064444310000041
the number of passengers at a station n when the interruption occurs in the interval with the date type of X; pn，X，tThe number of passengers staying at the station n at the time t when the date type is X.
Compared with the prior art, the invention adopting the technical scheme has the following technical effects:
1) the method takes the station under the condition of urban rail transit section interruption as a research object, forecasts the station passenger staying volume under the condition of urban rail transit interruption by analyzing and calculating historical data and combining actual operation conditions, and provides a more convenient and accurate method for estimating the staying passengers in real time.
2) The invention establishes the traffic flow data statistical table of the station passing in and out and the standard traffic flow database of the stable operation state of the urban rail transit station at different stations, different dates and different time periods by collecting the card swiping data of the automatic ticket selling and checking system, can provide data support for the real-time prediction of the station staying passenger volume under the interruption condition of the urban rail transit section, and also provides reference for the data collection, statistics and processing of the urban rail transit.
3) In consideration of the fact that passenger flow volume and passenger flow distribution of stations are greatly different when different date types are considered, the date is divided into three date types including working days, legal holidays and ordinary weekends, the passenger volume staying on different date types can be predicted more accurately, and applicability and accuracy of the invention are improved.
4) When the urban rail transit operation interval is interrupted, the temporary operation plan made by an operator is taken as a basis, the station retention passenger capacity is predicted in intervals, the operation characteristics of different operation intervals are fully considered, and the prediction reasonability and scientificity can be obviously improved.
5) The time influence coefficient and the space influence coefficient can be determined and corrected according to actual needs, so that the method has higher flexibility and operability, and can meet the use requirements under different conditions.
Drawings
FIG. 1 is a flow chart of a method for predicting passenger capacity staying in a station in real time under the condition of interruption of an urban rail transit section;
FIG. 2 is a schematic diagram of interval division of a temporary operation plan under an interruption condition of an urban rail transit interval;
fig. 3 is a schematic view of operation conditions of different sections after interruption occurs between Nanjing subway line No. 3 sections in the embodiment.
Detailed Description
The technical scheme of the invention is further explained in detail by combining the attached drawings:
it will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The invention provides a real-time prediction method for the passenger volume detained at a station under the interruption condition of an urban rail transit interval, aiming at the characteristics of large subjectivity, low accuracy and poor real-time property of the estimation of the passenger volume detained at the station under the interruption condition of the existing urban rail transit interval. The core method of the invention is to set up passenger flow databases of urban rail transit stations in stable operation states of different stations and different time types by sorting and counting the historical stable operation data of urban rail transit, and predict the passenger staying amount of the stations under the condition of interruption of the urban rail transit section in real time on the basis of setting different influence coefficients according to the temporary operation plan of urban rail transit under the condition of an emergency.
As shown in fig. 1, the method for predicting the passenger capacity staying at a station in real time under the condition of interruption of the urban rail transit section comprises the following steps:
step 1: establishing standard passenger flow database of stable operation state of urban rail transit station
The stable operation state of urban rail transit comprises two necessary conditions: (1) the urban rail transit operation line is the same as the current situation; and (2) a time period in which no operation accident occurs.
Step 1.1: card swiping database for establishing automatic ticket selling and checking system in stable operation state of urban rail transit
And collecting the original card swiping data of the automatic ticket selling and checking system under the condition of meeting the stable operation state of the urban rail transit. The automatic fare collection system card swiping original data generally comprises multiple attributes such as station entering time, transaction occurrence time, transaction types, transaction equipment numbers, station numbers, transaction stations, all-purpose card face numbers, all-purpose card inside numbers, ticket card types and the like, and the attributes such as the transaction occurrence time, the transaction types, the transaction equipment numbers, the station numbers, the transaction stations, the all-purpose card inside numbers, the ticket card types and the like are selected to form an automatic fare collection system card swiping database in the stable operation state of urban rail transit. Table 1 shows an example of a card swiping database of an automatic fare collection system in a stable operation state of urban rail transit.
TABLE 1 card swiping database example of automatic fare collection system for stable operation state of urban rail transit
Figure GDA0003064444310000051
Step 1.2: sorting dates according to different types
The date is divided into three types of working days, weekends and legal holidays, and each type is defined as follows:
a type: working days (normal working days, including post-rest working days);
b type: legal holidays (national legal holidays including holidays such as New year, Qingming festival, labor festival, Dragon festival, mid-autumn festival, national celebration festival, etc.);
class C: ordinary weekends (excluding saturdays and sundays other than weekdays and legal holidays).
The collection of three types of dates, A, B and C, are respectively represented as DA、DB、DC。
Step 1.3: statistical standard passenger flow database for stable operation state of each station of urban rail transit
The method is characterized in that the scale time of the nearest 5 minutes before the earliest running time of the whole network train is taken as the starting time, every 5 minutes is taken as a time period, and the sequence is marked as i (i is 1, 2 and 3.).
Counting the card swiping data of the automatic fare collection system at different stations, different dates and different time periods to obtain the number SIN of passengers entering the station at the ith time period on d days with the date type X (X is A, B and C)d，n，X，iAnd number of passengers SOUTd，n，X，i. The obtained inbound and outbound data were made into a statistical table as shown in table 2.
Table 2 example of traffic data statistics table for different stations, different dates and different time periods
Figure GDA0003064444310000061
And calculating standard inbound passenger flow data with the date type of each station according to the formula (1).
Figure GDA0003064444310000062
In the formula: x is a date type, the value of which is A, B or C;
n is the station number corresponding to the unique urban rail transit station;
i-the minimum time period divided;
DX-a set of dates of date type X;
count(DX) Set DXThe number of elements (c);
FINn，X，i-standard inbound traffic data for station n at time period i when the date type is X;
SINd，n，X，id days with date type X, the number of passengers entering station n in time period i.
Calculating standard station-entering passenger flow data with the date type of each station according to the formula (2)
Figure GDA0003064444310000063
In the formula:
FOUTn，X，i-standard outbound traffic data for station n at time period i when the date type is X;
SOUTd，n，X，id days with date type X, station n isNumber of outbound passengers for i time period.
And calculating standard traffic data of different types of dates and time periods for each station according to formulas (1) and (2), and making the calculated result into a table shown in a table 3 to form a standard passenger flow database of the stable operation state of the urban rail transit station.
TABLE 3 Standard passenger flow database for stable operation state of urban rail transit station
Figure GDA0003064444310000071
Step 1.4: passenger OD data of subway operation line
The passenger flow OD data of a certain antenna network in a stable operation state of urban rail transit is obtained from an urban rail transit operation department, and the format is shown in Table 4. If the station can not provide the data, the predicted OD data in the planning and design of the rail transit line is used as the standard.
Table 4 wire network passenger flow OD data of different date types of urban rail transit
Figure GDA0003064444310000072
And calculating according to the formula (3) to obtain passenger departure times data of different date types, different stations and different time periods.
Figure GDA0003064444310000073
In the formula:
On，X，i-number of passengers departure in time period i for station n with date type X.
And (4) calculating to obtain passenger arrival times data of different date types, different stations and different time periods according to the formula (4).
Figure GDA0003064444310000081
In the formula:
Dn，X，i-number of passengers arriving at station n in time period i with date type X.
Step 2: obtaining related information of interruption of urban rail transit operation interval
Step 2.1: obtaining a temporary operation plan after interruption of an urban rail transit operation interval
When the urban rail transit operation interval is interrupted, an operator can make a temporary operation plan according to actual conditions. When operating according to the temporary operation plan, the line is generally divided into three types of intervals, namely an interruption interval, a single-line bidirectional operation interval and a small-traffic bidirectional operation interval. An example of the division of the interval into the provisional operation plan is shown in fig. 2.
(1) An interruption interval: no vehicle runs in the interval.
(2) Single-line two-way operation interval: only one train operates on one line, and no train operates on the other line.
(3) The small traffic route operation interval: and bidirectional operation is carried out between lines with partial foldback capability.
Step 2.2: acquiring time node data corresponding to interruption of urban rail transit operation interval
Acquiring interval interruption starting time from urban rail transit operation units, and recording the closest 5-minute scale as Tinterrupt(ii) a Acquiring interval interruption end time, and recording the nearest 5-minute scale as Tresume。
And step 3: determining passenger flow impact coefficient under interval interrupt condition
Under the condition of interruption of the urban rail transit section, the passenger flow volume is influenced, the influence is larger when the station number is closer to the interruption section, and the influence is larger when the station number is closer to the interruption occurrence time of the section. Thus, quantization is performed by the spatial and temporal influence coefficients.
Step 3.1: determining spatial influence coefficient under urban rail transit section interruption condition
And (3) determining the space influence coefficients of different operation intervals under the condition of the interruption of the urban rail transit interval according to a formula (5) by combining the operation conditions of the different intervals after the interruption of the urban rail transit interval determined in the step 2.1 occurs.
Figure GDA0003064444310000082
In the formula: alpha is alphan-spatial impact coefficient of station n under interval interruption condition;
m is the number of stations in the n-station distance interruption interval (m is less than or equal to 10).
Step 3.2: determining time influence coefficient under urban rail transit section interruption condition
Determining a time influence coefficient beta under the condition of urban rail transit section interruption according to a formula (6)t。
Figure GDA0003064444310000091
In the formula: beta is at-time influence factor at time t under interval interruption condition;
Tinterrupt-interval interrupt start time;
Tresume-interval interrupt end time.
And 4, step 4: estimation of existing passenger volume in a station when a block break occurs
The number of passengers in the station when the interruption of the urban rail transit section occurs is the basis for predicting the amount of the passengers staying, and is obtained in an accumulated mode by starting the train in the initial shift in the date.
Obtaining the number of passengers in the station when the urban rail transit section is interrupted according to the formula (7)
Figure GDA0003064444310000092
Figure GDA0003064444310000093
In the formula:
Figure GDA0003064444310000094
-number of passengers at station n at the time of interruption of the date type X section.
And 5: real-time prediction of passenger retention amount under urban rail transit interval interruption condition
According to the formula (8) and the formula (9), the passenger retention P under the condition of urban rail transit section interruption is calculatedn，X，tAnd (6) performing prediction.
(1) When the time T needing prediction is in the interval and the interruption is not recovered, namely Tinterrupt＜t＜TresumeAnd (4) calculating the passenger staying according to a formula (8).
Figure GDA0003064444310000095
In the formula:
Pn，X，t-number of passengers detained at time t at station n with date type X.
(2) When the time T needing to be predicted is in the interval, the normal operation is interrupted, namely T is more than TresumeThen, the amount of the staying passengers is calculated according to the formula (9).
Figure GDA0003064444310000101
In the formula:
Figure GDA0003064444310000102
-the number of passengers at station n when the interruption occurred for the date type X interval;
Pn，X，t-number of passengers detained at time t at station n with date type X.
Example 1:
the method takes the example that the operation is interrupted between the line large open road of No. 3 track traffic of Nanjing urban and Nanjing south station after the Nanjing urban Nanjing of Nanjing 7 th 2016 is suddenly attacked by extra heavy rainstorm. The implementation of the method of the invention is further explained by combining the real-time prediction of the passenger staying at the large transit station under the condition of interval interruption:
step 1: establishing standard passenger flow database of stable operation state of urban rail transit station
Step 1.1: card swiping database for establishing automatic ticket selling and checking system in stable operation state of urban rail transit
The operation state of Nanjing urban rail transit started in 4 months in 2017 is stable, and the original card swiping data of the automatic ticket selling and checking system from 1 day in 4 months to 30 days in 6 months in 2017 are collected. The automatic fare collection system card swiping original data generally comprises multiple attributes such as station entering time, transaction occurrence time, transaction types, transaction equipment numbers, station numbers, transaction stations, all-purpose card face numbers, all-purpose card inside numbers, ticket card types and the like, and the attributes such as the transaction occurrence time, the transaction types, the transaction equipment numbers, the station numbers, the transaction stations, the all-purpose card inside numbers, the ticket card types and the like are selected to form an automatic fare collection system card swiping database in the stable operation state of urban rail transit. Table 1 shows a card swiping database of an automatic fare collection system in a stable operation state of urban rail transit.
TABLE 1 card swiping database of automatic fare collection system for stable operation state of urban rail transit
Figure GDA0003064444310000103
Step 1.2: sorting dates according to different types
The date is divided into three types of working days, weekends and legal holidays, and each type is defined as follows:
a type: working days (normal working days, including post-rest working days);
b type: legal holidays (national legal holidays including holidays such as New year, Qingming festival, labor festival, Dragon festival, mid-autumn festival, national celebration festival, etc.);
class C: ordinary weekends (excluding saturdays and sundays other than weekdays and legal holidays).
The collection of three types of dates, A, B and C, are respectively represented as DA、DB、DC。
According to the above definition:
comprises 2017, 4 months, 2 days to 4 days, 4 months, 29 days to 5 months, 1 day and 5 months, 28 days to 30 days;
comprises 8 to 9 days in 4 months, 15 to 16 days in 4 months, 22 to 23 days in 4 months, 6 to 7 days in 5 months, 13 to 14 days in 5 months, 20 to 21 days in 5 months, 3 to 4 days in 6 months, 10 to 11 days in 6 months, 17 to 18 days in 6 months and 24 to 25 days in 6 months in 2017 years;
comprises removing D from 2017 year 4 month 1 day to 6 month 30 dayBAnd DCThe date of the next day.
Step 1.3: statistical standard passenger flow database for stable operation state of each station of urban rail transit
The earliest starting time of the whole network train is 5: 42, the closest preceding 5 minute scale time is selected as the start time, i.e. the start time is 5:40, every 5 minutes is a time period, and is numbered i (i 1, 2, 3.) in that order.
Counting the card swiping data of the automatic fare collection system at different stations, different dates and different time periods to obtain the number SIN of passengers entering the station at the ith time period on d days with the date type X (X is A, B and C)d，n，X，iAnd number of passengers SOUTd，n，X，i. The obtained inbound and outbound data were made into a statistical table as shown in table 2.
Table 22017 statistics table for visitor flow data of station in 4, month, 10, macro-traffic major road and one day
Figure GDA0003064444310000111
Figure GDA0003064444310000121
And calculating standard inbound passenger flow data with the date type of each station according to the formula (1).
Figure GDA0003064444310000122
In the formula: x is a date type, the value of which is A, B or C;
n is the station number, taking the macro transportation road station as an example, n is 107;
i-the minimum time period divided;
DX-a set of dates of date type X;
count(DX) Set DXThe number of elements (c);
FINn，X，i-standard inbound traffic data for station n at time period i when the date type is X;
SINd，n，X，id days with date type X, the number of passengers entering station n in time period i.
And (4) calculating standard inbound passenger flow data with the date type of each station according to the formula (2).
Figure GDA0003064444310000123
In the formula:
FOUTn，X，i-standard outbound traffic data for station n at time period i when the date type is X;
SOUTd，n，X，id days with date type X, number of passengers outbound from station n in time period i.
And calculating standard traffic data of different types of dates and time periods for each station according to formulas (1) and (2), and making the calculated result into a table shown in a table 3 to form a standard passenger flow database of the stable operation state of the urban rail transit station.
TABLE 3 Standard passenger flow database for steady operation state of large transit station
Figure GDA0003064444310000124
Figure GDA0003064444310000131
Step 1.4: passenger OD data of subway operation line
The OD data of the passenger flow of one day in the stable operation state of the urban rail transit is obtained from the urban rail transit operation department, as shown in table 4.
Table 4 wire network passenger flow OD data of different date types of urban rail transit
Figure GDA0003064444310000132
And calculating according to the formula (3) to obtain passenger departure times data of different date types, different stations and different time periods.
Figure GDA0003064444310000133
In the formula:
On，X，i-number of passengers departure in time period i for station n with date type X.
Calculating and obtaining passenger arrival times data D of different date types, different stations and different time periods according to the formula (4)n，X，i。
Figure GDA0003064444310000141
In the formula: dn，X，i-number of passengers arriving at station n in time period i with date type X.
Obtaining passenger departure times data O calculated to obtain different date types, different stations and different time periodsn，X，iAnd passenger arrival
Step 2: obtaining related information of interruption of urban rail transit operation interval
Step 2.1: obtaining a temporary operation plan after interruption of an urban rail transit operation interval
When the urban rail transit operation interval is interrupted, an operator can make a temporary operation plan according to actual conditions. When operating according to the temporary operation plan, the line is generally divided into three types of intervals, namely an interruption interval, a single-line bidirectional operation interval and a small-traffic bidirectional operation interval. An example of the division of the interval into the provisional operation plan is shown in fig. 3.
(1) An interruption interval: no vehicle runs in the interval.
(2) Single-line two-way operation interval: only one train operates on one line, and no train operates on the other line.
(3) The small traffic route operation interval: and bidirectional operation is carried out between lines with partial foldback capability.
Step 2.2: acquiring time node data corresponding to interruption of urban rail transit operation interval
Acquiring interval interruption starting time from urban rail transit operation units, and recording the closest 5-minute scale as Tinterrupt(ii) a Acquiring interval interruption end time, and recording the nearest 5-minute scale as Tresume。
And step 3: determining passenger flow impact coefficient under interval interrupt condition
Under the condition of interruption of the urban rail transit section, the passenger flow volume is influenced, the influence is larger when the station number is closer to the interruption section, and the influence is larger when the station number is closer to the interruption occurrence time of the section. Thus, quantization is performed by the spatial and temporal influence coefficients.
Step 3.1: determining spatial influence coefficient under urban rail transit section interruption condition
FIG. 3 is a schematic view of the operation conditions of different sections after interruption occurs between Nanjing subway No. 3 lines in the embodiment, a macro transportation road station is located in a bidirectional operation section, m is 1 from the interruption section, and the space influence coefficients of different operation sections under the interruption condition of the urban rail transit section are determined
Figure GDA0003064444310000142
Step 3.2: determining time influence coefficient under urban rail transit section interruption condition
2016, 7 months and 7 days take the example of predicting the amount of passenger staying 10 minutes after an accident, at which time the interval interruption has not yet been resumed.
And determining the time influence coefficient under the condition of interruption of the urban rail transit section.
Figure GDA0003064444310000151
And 4, step 4: estimation of existing passenger volume in a station when a block break occurs
The number of passengers in the station when the interruption of the urban rail transit section occurs is the basis for predicting the amount of the passengers staying, and is obtained in an accumulated mode by starting the train in the initial shift in the date.
According to the data in the embodiment, the date type X is a, the station number n is 107, and the section interrupt occurrence time TinterruptThe number of passengers in the station when the urban rail transit section is interrupted is 8:30, and is obtained according to the following formula according to the data of the parameters and the like in the table 3, the table 4 and the steps
Figure GDA0003064444310000152
I.e. 86 people are present at the station when the section break occurs.
Figure GDA0003064444310000153
And 5: real-time prediction of passenger retention amount under urban rail transit interval interruption condition
According to the formula (8) and the formula (9), the passenger retention P under the condition of urban rail transit section interruption is calculatedn，X，tAnd (6) performing prediction.
Using the example of predicting passenger retention at 10 minutes (8:40) after an accident, since the time required for prediction is when the interval break has not yet been restored, i.e., Tinterrupt＜t＜TresumeAnd (4) calculating the passenger staying according to a formula (8). According to the foregoingThe number of passengers in the station when the urban rail transit section is interrupted is obtained in the step
Figure GDA0003064444310000154
Coefficient of temporal influence betat0.35, spatial coefficient of influence α107When the data in table 3 and table 4 were read together with 0.5, 2016 (10 minutes after the occurrence of the section break), 7/8/40, the number of passengers staying at the subway station in the macro transit lane was estimated to be 138.
The foregoing is only a partial embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims (6)

1. A real-time prediction method for passengers staying at a bus station under an interruption condition in an urban rail transit interval is characterized by comprising the following steps:
step one, collecting standard passenger flow data of a station in a stable operation state of urban rail transit, and establishing a database, wherein the database comprises standard inbound passenger flow data, standard outbound passenger flow data, passenger departure times data and passenger arrival times data;
wherein the stable operation state of the urban rail transit needs to simultaneously meet the conditions: (1) the urban rail transit operation line is the same as the current situation; (2) in the time period when no operation accident occurs;
step two, collecting temporary operation plan and time node data after the interruption of the urban rail transit operation interval;
step three, determining a time influence coefficient and a space influence coefficient of station passenger flow under the condition of interval interruption;
estimating the passenger capacity in the station when the interval interruption occurs;
and step five, under the condition of interruption of the urban rail transit section, predicting the passenger staying at the station at a certain time in the future in real time.
2. The method for predicting the detained passengers at the station under the condition of interruption of the urban rail transit section in real time as claimed in claim 1, wherein the step one includes the standard passenger flow data of the station under the stable operation state of the urban rail transit section:
1) the automatic fare collection system in the stable operation state of the urban rail transit swipes card data, and the field of each piece of data comprises transaction occurrence time, transaction type, transaction equipment number, station number, transaction station, card inside number of the all-purpose card and ticket card type;
2) types of dates, including weekdays, statutory holidays, and general weekends, the collection of dates for each type being denoted D, respectivelyA、DB、DC；
3) Passenger OD data of subway operation line.
3. The method as claimed in claim 1, wherein the types of the operation sections in the second step include an interruption section, a single-line bidirectional operation section, and a small-traffic bidirectional operation section.
4. The method according to claim 1, wherein the spatial influence coefficient in step three is determined by the following formula:
Figure FDA0003064444300000011
wherein alpha isnThe space influence coefficient of the station n under the interval interruption condition is shown, and m shows the number of stations between the station n and the interruption interval;
step three, the time influence coefficient is determined by the following formula:
Figure FDA0003064444300000021
wherein, betatIndicating time t under interval interrupt conditionsTime-influence coefficient of (1), TinterruptIndicates the interval interruption start time, TresumeIndicating the interval interrupt end time.
5. The method according to claim 1, wherein the real-time prediction of passengers staying in the station under the condition of the interruption of the urban rail transit section is performed in step four, and the amount of passengers in the station when the section interruption occurs is determined
Figure FDA0003064444300000022
Is derived from the following formula:
Figure FDA0003064444300000023
wherein X is a date type and takes the value of A, B or C; n is a station number corresponding to a unique urban rail transit station; i is the divided minimum time period; FINn，X，iThe standard station entering passenger flow data of the station n in the time period i when the date type is X; FOUT (four opening unified pod)n，X，iThe standard outbound passenger flow data of the station n in the time period i when the date type is X; o isn，X，iThe number of passengers departing in the time period i at the station n when the date type is x; dn，X，iThe number of passengers arriving at station n in time period i when the date type is X; t isinterruptIs interval interrupt occurrence time;
Figure FDA0003064444300000024
the number of passengers at station n when the interruption occurs in the section with date type X.
6. The method according to claim 1, wherein the real-time prediction of passenger staying at the bus stop under the urban rail transit section interrupt condition is performed in step five, wherein the passenger staying amount P under the urban rail transit section interrupt condition is performed in step fiven，X，tIs derived from the following formula:
(1) when the time T needing prediction is in the interval and the interruption is not recovered, namely Tinterrupt＜t＜TresumeAt a time there is：
Figure FDA0003064444300000025
(2) When the time T needing to be predicted is in the interval, the normal operation is interrupted, namely T is more than TresumeSometimes:
Figure FDA0003064444300000026
in the formula: x is a date type, and the value of X is A, B or C; n is a station number corresponding to a unique urban rail transit station; i is the divided minimum time period; FINn，X，iThe standard station entering passenger flow data of the station n in the time period i when the date type is X; FOUT (four opening unified pod)n，X，iThe standard outbound passenger flow data of the station n in the time period i when the date type is X; o isn，X，iThe number of passengers departing in the time period i at the station n when the date type is X; dn，X，iThe number of passengers arriving at station n in time period i when the date type is X; t isinterruptIs interval interrupt occurrence time;
Figure FDA0003064444300000031
the number of passengers at a station n when the interruption occurs in the interval with the date type of X; pn，X，tThe number of passengers staying at the station n at the time t when the date type is X.
CN201810446018.2A 2018-05-11 2018-05-11 Method for predicting passenger volume staying at station in real time under condition of urban rail transit section interruption Active CN108717583B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810446018.2A CN108717583B (en) 2018-05-11 2018-05-11 Method for predicting passenger volume staying at station in real time under condition of urban rail transit section interruption

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810446018.2A CN108717583B (en) 2018-05-11 2018-05-11 Method for predicting passenger volume staying at station in real time under condition of urban rail transit section interruption

Publications (2)

Publication Number Publication Date
CN108717583A CN108717583A (en) 2018-10-30
CN108717583B true CN108717583B (en) 2021-08-03

Family

ID=63899709

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810446018.2A Active CN108717583B (en) 2018-05-11 2018-05-11 Method for predicting passenger volume staying at station in real time under condition of urban rail transit section interruption

Country Status (1)

Country Link
CN (1) CN108717583B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108189870A (en) * 2017-12-29 2018-06-22 中车株洲电力机车研究所有限公司 A kind of dispatching method and equipment based on intelligence rail train
CN110427402B (en) * 2019-07-24 2021-10-08 上海工程技术大学 Rail transit fault delay propagation and spread range estimation system
CN112508247B (en) * 2020-11-26 2024-05-21 交控科技股份有限公司 Traffic abnormality information processing method and device and electronic equipment
CN115689154B (en) * 2022-09-15 2023-07-25 合肥市轨道交通集团有限公司 Urban rail transit scheduling auxiliary decision-making system based on dynamic passenger flow

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106484966A (en) * 2016-09-22 2017-03-08 北京交通大学 A kind of urban track traffic accident dynamic effect scope and strength determining method
CN106503315A (en) * 2016-10-10 2017-03-15 北京市交通信息中心 The determination method of the passenger's trip characteristicses ratio that enters the station under track traffic accident
CN107194497A (en) * 2017-04-27 2017-09-22 北京交通大学 Urban track traffic passenger trip route planing method under a kind of accident
CN107273999A (en) * 2017-04-27 2017-10-20 北京交通大学 A kind of Flow Prediction in Urban Mass Transit method under accident

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106484966A (en) * 2016-09-22 2017-03-08 北京交通大学 A kind of urban track traffic accident dynamic effect scope and strength determining method
CN106503315A (en) * 2016-10-10 2017-03-15 北京市交通信息中心 The determination method of the passenger's trip characteristicses ratio that enters the station under track traffic accident
CN107194497A (en) * 2017-04-27 2017-09-22 北京交通大学 Urban track traffic passenger trip route planing method under a kind of accident
CN107273999A (en) * 2017-04-27 2017-10-20 北京交通大学 A kind of Flow Prediction in Urban Mass Transit method under accident

Also Published As

Publication number Publication date
CN108717583A (en) 2018-10-30

Similar Documents

Publication Publication Date Title
CN108717583B (en) Method for predicting passenger volume staying at station in real time under condition of urban rail transit section interruption
CN108564226B (en) Bus route optimization method based on taxi GPS and mobile phone signaling data
CN108346292B (en) Urban expressway real-time traffic index calculation method based on checkpoint data
CN101236642A (en) Classified passenger flow monitoring system and its method based on ticketing data
CN109637134A (en) A kind of public transport device matching process
Carrasco Quantifying reliability of transit service in Zurich, Switzerland: case study of bus line 31
CN112686417B (en) Subway large passenger flow prediction method, system and electronic equipment
Du et al. Bus bunching identification using smart card data
CN114501336B (en) Road traffic volume measuring and calculating method and device, electronic equipment and storage medium
CN109572763B (en) Train number safety assessment method based on severe weather and late conditions
CN107146413A (en) A kind of smart city service platform
CN114078322B (en) Bus running state evaluation method, device, equipment and storage medium
CN111367900B (en) Method for calculating normal current limiting intensity of urban rail transit network based on AFC data
CN111016976B (en) Train operation deviation propagation condition identification method based on multilayer coupling relation
Chu et al. Reproducing longitudinal in-vehicle traveler experience and the impact of a service reduction with public transit smart card data
Li-Jun et al. Evaluation of the reliability of bus service based on gps and smart card data
CN110245788B (en) Subway passenger flow short-term prediction method based on card swiping data
Screen et al. Data analysis to study sub-threshold delays incurred by Tyne and Wear metro trains
Zhang et al. Short-term forecasting of passenger flow on the metro platform using an improved Kalman filtering method
Büchel et al. The disruption at Rastatt and its effects on the Swiss railway system
CN108230670A (en) Predict the method and apparatus for giving the moving body number of place appearance in given time period
CN113723761B (en) Multi-dimensional urban public transportation operation service reliability evaluation method based on operation data
CN112990658B (en) Bus network timetable reliability calculation method for line simplification optimization
Yu et al. Passenger flow estimation based on smart card data in public transit
Nekraplonna et al. The Analysis of Trajectories in Moscow Subway.

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