CN106379379B - A kind of Forecasting Methodology of urban track traffic passenger getting on/off time - Google Patents
A kind of Forecasting Methodology of urban track traffic passenger getting on/off time Download PDFInfo
- Publication number
- CN106379379B CN106379379B CN201610881642.6A CN201610881642A CN106379379B CN 106379379 B CN106379379 B CN 106379379B CN 201610881642 A CN201610881642 A CN 201610881642A CN 106379379 B CN106379379 B CN 106379379B
- Authority
- CN
- China
- Prior art keywords
- passenger
- getting
- passengers
- time
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000006399 behavior Effects 0.000 claims description 28
- 230000008859 change Effects 0.000 claims description 22
- 238000010586 diagram Methods 0.000 claims description 12
- 238000009826 distribution Methods 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 5
- 238000007619 statistical method Methods 0.000 claims description 3
- 238000004904 shortening Methods 0.000 abstract description 2
- 238000011160 research Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000033001 locomotion Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012888 cubic function Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/60—Testing or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a kind of Forecasting Methodology of urban track traffic passenger getting on/off time, the method includes:S1:Acquisition trajectory traffic circulation information obtains get on and off number and passenger of passenger and gets on and off the scatter plot of time;S2:It is fitted the scatter plot and obtains passenger and get on and off flow changing curve, establish the multi-stage model of passenger loading time prediction and passenger getting off car time prediction model;S3:Consider that passenger is lined up behavior and the model is optimized;S4:Passenger is obtained using the model of least square method solving-optimizing to get on and off time real-time prediction model, the present invention establishes the multi-stage model of passenger loading time prediction, and consider that passenger is lined up behavior and gets on and off to passenger the influence of time, it can more precisely predict that passenger gets on and off the time, the efficiency of operation of rail traffic is improved, the proposition for the time-optimized scheme that gets on and off to shortening passenger has directive significance.
Description
Technical Field
The invention relates to the field of urban rail transit operation, in particular to a method for predicting the time for passengers to get on or off a train in urban rail transit.
Background
In the 2l century, with the continuous improvement of the urbanization level of China, the population density of cities is rapidly increased, and the traffic jam problem caused by the population density is more and more severe, which becomes one of the important factors restricting the development of economy, society and culture. Urban rail transit is an important component of public transportation and becomes an effective transportation mode for solving urban traffic congestion. Because urban rail transit has the characteristics of energy conservation, land conservation, large transportation capacity, all weather, punctuality, no pollution, safety and the like, the following conclusion can be drawn: the development of urban rail transit completely conforms to the principle of sustainable development. Therefore, it will be the golden period of the vigorous development of urban rail transit for a long time in the future. According to reliable data, the total operating mileage of the rail transit which is possessed by dozens of cities such as Beijing, Shanghai and the like in China reaches 3290 kilometers by 2015. According to long-term planning, the total mileage of urban rail transit in China reaches 6100 kilometers by 2020, wherein the total mileage of urban rail transit in Beijing is over 1000 kilometers, public transport becomes a main travel vehicle for about 80% of citizens, and about 50% of people often use urban rail transit as a travel vehicle.
At present, the total passenger flow of the urban rail transit road network in Beijing city has reached 1100 ten thousand people in the peak day, and along with the continuous perfection of road network, the passenger flow increases thereupon, but meanwhile, the problem of operation management is prominent day by day, the passenger detention problem of some station platforms is waited for to solve urgently, especially in the morning and evening peak period, the management measure to the station platform passenger is not perfect enough, the passenger detention problem has brought huge pressure for the station management, passenger's trip efficiency has been reduced. Currently, researchers have increasingly studied the influencing factors influencing the operation of rail transit as people improve their level of travel, increase their notion of time, and increase their demands for safety. In a subway station, getting on and off a train is one of main traffic activities, and the speed of passengers getting on and off the train not only influences the activities of people in the subway station, but also influences the stop time of subway trains and the service level of the subway. The method has the advantages that factor influence analysis is carried out on the getting-on and getting-off time of subway passengers, and the method has important significance for improving the subway riding environment and improving the subway service level.
In the process of getting on or off the bus, passengers often get on or off the bus in a robbing mode and are disordered in order, so that the efficiency of getting on or off the bus by the passengers is reduced, and serious potential safety hazards are brought. The phenomena seriously restrict the high-efficiency operation of urban rail transit, so the research on the getting-on and getting-off behaviors of passengers has the functions of predicting and guiding subway operation and the correct dispersion of the getting-on and getting-off behaviors of the passengers, and has very important significance for relieving urban public transit pressure and improving the current public transit situation.
To date, the research on pedestrian traffic is far less advanced than that of motor vehicle traffic at home and abroad, and the investigation and analysis methods thereof need to be continuously improved and perfected. The traditional research method only carries out qualitative research on factors influencing passengers to get on or off the train, so that a prediction method capable of accurately predicting the time of getting on or off the train of the passengers in the peak time and the off-peak time of rail transit is needed, the influence of the behavior of getting on or off the train of the passengers on the time of getting on or off the train of the passengers is considered, and the real-time prediction of the time of getting on or off the train of the passengers under the condition of different passenger flows is reflected more accurately.
Disclosure of Invention
In order to solve the problems, the invention provides a method for predicting the time for passengers to get on or off the train in urban rail transit, which adopts a piecewise function model to establish a prediction model of the time for passengers to get on or off the train, takes the influence of the passenger queuing behavior on the time for passengers to get on or off the train into consideration, optimizes the prediction model of the time for passengers to get on or off the train, can more accurately predict the time for passengers to get on or off the train, provides reference for correctly guiding the behavior of passengers to get on or off the train, and improves the operation efficiency of rail transit.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for predicting the getting-on and getting-off time of urban rail transit passengers is characterized by comprising the following steps:
s1: acquiring running information, platform information, passenger flow information and passenger information of a rail transit train, and carrying out statistical analysis on the information to obtain a scatter diagram of the number of passengers getting on and off and the time of the passengers getting on and off;
s2: fitting a passenger getting-on and getting-off flow change curve according to the scatter diagram, and establishing a piecewise function model for predicting the passenger getting-on time and a passenger getting-off time prediction model according to the curve curvature change;
s3: optimizing the piecewise function model and the passenger getting-off time prediction model by considering passenger queuing behaviors to obtain an optimized prediction model of the getting-on and getting-off time of passengers;
s4: and solving the optimized prediction model of the getting-on and getting-off time of the passenger by adopting a least square method to obtain a real-time prediction model of the getting-on and getting-off time of the passenger.
Preferably, the train operation information includes train arrival time, train departure time, and train stopping interval.
Preferably, the platform information includes a passenger waiting position and a size of a waiting area.
Preferably, the passenger flow information includes passenger flow at an entrance and an exit of a platform, passenger flow on the bus, passenger platform distribution, passenger number in the bus, passenger density in the bus and pedestrian density.
Preferably, the passenger information includes passenger walking speed, passenger per-person floor space, whether to carry luggage and passenger age distribution.
Preferably, in step S2, the curve is divided into an off-peak section, a transition section and a peak section according to the curvature change of the passenger boarding flow rate curve, and a piecewise function model of the passenger boarding time prediction is established as
Wherein, a1,a2,a3,a4,b1,b2,c1,c2,c3The model is an unknown parameter, M is the maximum value of the number of passengers getting on the bus in the off-peak period, and N is the minimum value of the number of passengers getting on the bus in the peak period;
according to the curvature change of the passenger getting-off flow change curve, a passenger getting-off time prediction model is established
f(y)=αyβ
wherein, alpha and beta are unknown parameters of the model.
Preferably, the S3 includes the following steps:
s31: establishing a queue width model of passenger getting-on formed by a plurality of queues of passengers
W=Wlayer+(n-1)Dlayer
Wlayer=Wmax+Wsway
Wherein, W is the queue width model of passenger getting on the bus formed by W multi-queue passengerslayerThe distance between the centers of two adjacent passenger teams along the vertical queue direction, n is the number of the queues, DlayerWidth required for queuing passengers near the center of the door, WmaxMaximum shoulder width of passenger, WswayFor the width of the wave when passengers are queuing near the center of the door, [ X ]]Represents an integer closest to X;
s32: according to the queue width, a door passing capacity model of the train under the passenger queuing behavior is established, and the door passing capacity model is established as
Wherein, CdThe passing capacity of the train door is shown, and z is the number of passengers waiting to get on or off the train;
then, according to the collected information, the queue number of the passengers queuing under the actual condition is obtained, and the average passenger passing capacity model of each queue is obtained
Wherein l is the queue number of the passengers in queue;
therefore, according to the queue width model, a train door passing capacity model under the passenger queuing behavior is obtained as
S33: optimizing the piecewise function model by adopting the train door passing capacity model to obtain an optimized prediction model of the getting-on and getting-off time of passengers, wherein the optimized prediction model is
Where θ is the number of passengers who have got on the bus.
The invention has the following beneficial effects:
the invention discloses a method for predicting the time for passengers to get on or off a train in urban rail transit, which is characterized in that a real-time prediction model of the time for passengers to get on or off the train is established on the basis of a large amount of statistical information and the research on the behavior of passengers to get on or off the train, so that the time for passengers to get on or off the train can be more accurately predicted, a reference is provided for correctly guiding the behavior of passengers to get on or off the train, and meanwhile, the method has guiding significance for providing an optimization scheme for shortening the time for passengers to get on or off the train and.
Drawings
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
Fig. 1 shows a flow chart of a method for predicting the time for passengers to get on or off the train in urban rail transit according to the invention.
Fig. 2 shows a scatter plot of passenger population versus passenger boarding time.
Fig. 3 shows a scatter plot of passenger population versus time for a passenger to disembark.
Fig. 4 shows a diagram of behavior simulation of two teams of passengers boarding.
Fig. 5 shows a schematic diagram of the overlapping of the positions of passengers when they are waiting in line.
Fig. 6 shows simulation results of a real-time prediction model for verifying passenger boarding time.
Fig. 7 shows simulation results of a real-time prediction model for verifying the getting-off time of a passenger.
Detailed Description
In order to more clearly illustrate the invention, the invention is further described below with reference to preferred embodiments and the accompanying drawings. Similar parts in the figures are denoted by the same reference numerals. It is to be understood by persons skilled in the art that the following detailed description is illustrative and not restrictive, and is not to be taken as limiting the scope of the invention.
As shown in fig. 1, the invention discloses a method for predicting the time for passengers to get on or off a train in urban rail transit, which comprises the following steps:
s1: the method comprises the steps of collecting operation information, platform information, passenger flow information and passenger information of the rail transit train, and carrying out statistical analysis on the information to obtain a scatter diagram of the number of passengers getting on or off the train and the time of the passengers getting on or off the train, as shown in fig. 2 and 3.
The method comprises the steps of collecting train operation information, platform information, passenger flow information and passenger information of a certain platform of the rail transit train in different time periods, wherein the train operation information can comprise train arrival time, train departure time and train parking intervals. The passenger flow information comprises passenger entrance and exit passenger flow, boarding passenger flow, alighting passenger flow, passenger platform distribution, passenger number in the vehicle, passenger density in the vehicle, pedestrian density and the like, the passenger information comprises passenger walking speed, passenger per-capita area, whether luggage is carried, passenger age distribution and the like, and the passenger information can be acquired through field acquisition data or monitoring equipment. And then drawing a scatter diagram of the number of passengers getting on and off the bus and the time of the passengers getting on and off the bus according to the acquired information, and analyzing, filtering, extracting, converting and storing the acquired information in a classified manner to form data information required by the experiment.
S2: and fitting a passenger getting-on and getting-off flow change curve according to the scatter diagram, and establishing a piecewise function model for predicting the passenger getting-on time and a passenger getting-off time prediction model according to the curve curvature change.
The passenger boarding and disembarking process can generally be divided into two phases. In the first stage, waiting passengers queue outside the vehicle and wait, and getting-off passengers queue and get out of the vehicle door. In the second stage, the passengers leaving the train leave the train and the passengers waiting for the train get on the train. The passenger boarding flow change curve shows that the boarding time of passengers and the number of passengers for getting on and off the train present a complex nonlinear form, so that the curve is subjected to sectional analysis according to the curvature change of the curve, the curve is divided into an off-peak section, a transition section and a peak section, and a sectional function model for predicting the boarding time of passengers is established.
In the off-peak period, the number of passengers getting on the bus is small, namely, when the passenger flow is low, the passengers can normally queue and wait in the waiting area. At this time, as the number of passengers getting on the vehicle increases, the time for passengers to get on the vehicle and the number of passengers getting on the vehicle are in a linear relationship.
At the peak section, the number of passengers getting on the bus is more, namely when the passenger flow is peak, because of the influence of the density of passengers in the bus, the bottleneck that the passengers get on the bus can be formed at the bus door by the obstruction of the passengers in the bus in the process of getting on the bus. The time of getting on the bus of the passengers and the number of the passengers are approximately square, and the efficiency of getting on the bus of the passengers is reduced along with the increase of the number of the passengers.
The transition section is between the non-peak section and the peak section, the relationship between the passenger boarding time and the number of passengers boarding is more complex, and a cubic function model is adopted to represent a passenger boarding time prediction model between the passenger flow low peak and the passenger flow high peak.
Thereby, a piecewise function model for predicting the boarding time of the passenger can be established, and the piecewise function model is
Wherein, a1,a2,a3,a4,b1,b2,c1,c2,c3The model is an unknown parameter, M is the maximum value of the number of passengers getting on the bus in the off-peak period, and N is the minimum value of the number of passengers getting on the bus in the peak period.
The time for passengers to get off is influenced by the density of passengers waiting on the platform and the queuing behavior of passengers getting on the platform. Assuming that the density of waiting passengers on the platform is unique, when the passenger flow is low, the passengers getting off are distributed near the doors to wait for getting off, so that the passengers getting off are not hindered from getting off, the efficiency of getting off the passengers is improved, and the time for getting off the passengers is low. When the passenger flow is in a peak, the jam of the waiting passengers at the doorway greatly affects the time for the passengers to get off, so that the time for the passengers to get off is greatly increased, and the variation curve of the flow for the passengers to get off shows obvious segmentation characteristics.
Therefore, the passenger getting-off time prediction model is established according to the curvature change of the passenger getting-off flow change curve
f(y)=αyβ
wherein, alpha and beta are unknown parameters of the model.
S3: and optimizing the piecewise function model and the passenger getting-off time prediction model by considering the passenger queuing behavior to obtain an optimized prediction model of the passenger getting-on and getting-off time. The method comprises the following steps:
s31: and establishing a queue width model of passenger boarding formed by a plurality of groups of passengers.
Three main queuing types appear when waiting passengers get on the bus: front door aggregation, two-in-line queuing, and multiple-in-line queuing. The first type can be a bottleneck that prevents passengers from free flow through the door; the second type is shown in fig. 4, where passengers are in two lines, each passenger following behind the other passengers, and no body collision occurs; and in the third type, passengers are arranged in multiple rows, the bodies of the passengers are contacted at the moment, the passengers arranged in the multiple rows can be partially overlapped by two rows due to the limitation of the width of the train doors, the positions of the passengers which are arranged in parallel in the row direction can be overlapped, and the width of the passengers getting on the train and queuing at the moment is smaller than the width of the multiple rows of the train under the normal queuing action.
As shown in FIG. 5, the third type of passenger queuing behavior is analyzed in the invention, and leading passengers in two adjacent queues are q and q respectively1Passengers p and p1Respectively, passenger q and q following in the leading team1The remaining passengers so follow in turn. Passengers get on and off the train with queuing activity, which requires that the passengers have sufficient space both longitudinally and transversely of the train. The space required by the queues in the transverse direction comprises the shoulder width of passengers, the distance of obstacles and the distance between the passengers at the corresponding positions of the two adjacent queues. Under the condition of small pedestrian volume, the walking behavior of passengers is stable and approximately constant motion is realized. As passengers line up in several lines, passengers walk in a staggered space and pedestrians are overlapped in position due to crowding.
At this time, the queue width model of passenger getting on the train formed by the plural passenger trains is
W=Wlayer+(n-1)Dlayer
Wherein, WlayerThe distance between the centers of two adjacent passenger teams along the vertical queue direction, n is the number of the queues, DlayerThe width required when queuing a passenger near the center of the door.
The distance between the centers of the two adjacent passengers along the direction vertical to the queue is
Wlayer=Wmax+Wsway
Wherein, WmaxMaximum shoulder width of passenger, WswayThe width of the wave when passengers near the center of the door are queued.
Thus, the number of queues can be expressed as
Wherein [ X ] represents an integer closest to X.
S32: and establishing a train door passing capacity model under the passenger queuing behavior.
According to the queue width, a door passing capacity model of the train under the passenger queuing behavior is established, and the door passing capacity model is established as
Wherein, CdThe passing capacity of the train door is shown, and z is the number of passengers waiting to get on or off the train;
then, according to the collected information, the queue number of the passengers queuing under the actual condition is obtained, and the average passenger passing capacity model of each queue is obtained
Wherein l is the queue number of the passengers in queue;
therefore, according to the queue width model, a train door passing capacity model under the passenger queuing behavior is obtained as
S33: optimizing the piecewise function model by adopting the train door passing capacity model to obtain an optimized prediction model of the getting-on and getting-off time of passengers, wherein the getting-on and getting-off of the passengers have similar queuing behaviors, so that the optimized prediction model of the getting-on and getting-off time of the passengers is
Wherein theta is the number of passengers who get on the bus, and t (z, theta) is a model for predicting the getting on/off time of passengers waiting to get on/off the bus.
S4: and solving the optimized prediction model of the getting-on and getting-off time of the passenger by adopting a least square method to obtain a real-time prediction model of the getting-on and getting-off time of the passenger.
The invention is further explained by a preferred embodiment, and the invention discloses a method for predicting the getting-on and getting-off time of passengers in urban rail transit, which is adopted to establish a real-time prediction model of the getting-on and getting-off time of the passengers, wherein the method comprises the following steps:
s1: the method comprises the steps of collecting the running information, platform information, passenger flow information and passenger information of the rail transit train at three subway platforms, namely a Beijing subway west single station, a Xuanwu station and a Beijing south station, and obtaining a scatter diagram of the number of passengers getting on and off and the getting on and off time of the passengers by statistically analyzing the information, wherein the scatter diagram is shown in fig. 2 and 3.
S2: and fitting a passenger getting-on and getting-off flow change curve according to the scatter diagram, and establishing a piecewise function model for predicting the passenger getting-on time and a passenger getting-off time prediction model according to the curve curvature change. When the passenger flow is low, the maximum value of the average time for passengers to get on and off is 0.8s, which is mainly influenced by the physical characteristics of the passengers, such as reaction time and psychological factors; when the passenger flow is between the low peak and the high peak, the average time for passengers to get on or off the bus is relatively stable and fluctuates within 0.6-0.7 s; at the time of peak of passenger flow, the average time of passengers getting on the bus is gradually increased due to the influence of the density in the bus, and the maximum time can reach 1.3 s. By means of curvature analysis of the passenger boarding flow rate change curve, when the number of passengers boarding is below 15, the passenger boarding time and the number of passengers boarding are approximately in a linear relation, and therefore the corresponding passenger boarding flow rate change curve is in an off-peak period when the number of passengers boarding is below 15; when the number of passengers getting on the bus is more than 40, the time for passengers getting on the bus and the number of passengers getting on the bus are approximately in a square relation, so that the corresponding change curve of the passenger getting on the bus flow is a peak section when the number of passengers getting on the bus is more than 40; the transition section is a passenger boarding flow change curve corresponding to the situation that the number of passengers boarding the train is more than 15 and less than or equal to 40.
S3: and optimizing the piecewise function model and the passenger getting-off time prediction model by considering the passenger queuing behavior to obtain an optimized prediction model of the passenger getting-on and getting-off time. The method comprises the following steps:
s31: and establishing a queue width model of passenger boarding formed by a plurality of groups of passengers. The passenger waiting area is a rectangle with the area of 20 square meters, wherein the length and the width of the rectangle are respectively 5 meters and 4 meters. Through data analysis, the following results are obtained: when the time for passengers to get on the bus in two teams is shortest and the efficiency is highest, the traveling speed of the passengers is about 1m/s, and the passing capacity of the bus door is 1.56 p/s; when passengers are in three lines, physical contact occurs among the passengers, the position conflicts occur, the crowdedness is increased, the movement of the passengers is limited, the walking speed is about 0.87m/s, and the vehicle door passing capacity is about 1.28 p/s; when passengers are all gathered in front of the door, the density of passengers getting on the vehicle is about 4 persons/square meter, the speed is about 0.8m/s, and the passing capacity of the vehicle door at the bottleneck is close to 0.78 p/s. The efficiency of passengers in two queues is the highest as can be seen from the comparison of the three queuing modes. However, if the number of passengers is small, passenger positions do not overlap, and three-in-one may also be the best option.
S32: and establishing a train door passing capacity model under the passenger queuing behavior. Under the condition that the width of a train door is 1.3m and passengers getting on the train are arranged in two teams, the model for obtaining the average passing capacity of each team of passengers is
Therefore, according to the queue width model, a train door passing capacity model under the passenger queuing behavior is obtained as
S33: optimizing the piecewise function model by adopting the train door passing capacity model to obtain an optimized prediction model of the getting-on and getting-off time of passengers, wherein the getting-on and getting-off of the passengers have similar queuing behaviors, so that the optimized prediction model of the getting-on and getting-off time of the passengers is
Wherein theta is the number of passengers who get on the bus, and t (z, theta) is a model for predicting the getting on/off time of passengers waiting to get on/off the bus.
Solving the piecewise function model by adopting a least square method to obtain a real-time passenger boarding time prediction model, wherein the real-time passenger boarding time prediction model is the maximum value of the number of passengers boarding the non-peak section and the minimum value of the number of passengers boarding the peak section
Wherein,
the least square method is adopted to solve the passenger getting-off time prediction model to obtain a passenger getting-off time real-time prediction model
f(y)=0.854y0.923
In order to verify the accuracy of the invention, 40 groups of statistical data are obtained in total by collecting related statistical information from 7 to 12 points of Beijing Western single station every three days from 5 months of 2016 to obtain the simulation result of the real-time prediction model of the getting-on and getting-off time of passengers, as shown in FIGS. 6 and 7, the average deviation of the simulation result of the real-time prediction of the getting-on and getting-off time of passengers and the statistical data is 0.0439 and 0.0581 respectively, so that the real-time prediction model of the getting-on and getting-off time of passengers can predict the getting-on and getting-off time of passengers under different conditions with high accuracy.
The prediction method for the getting-on and getting-off time of the urban rail transit passenger adopts the piecewise function model to solve the prediction model for the getting-on and getting-off time of the passenger in a piecewise mode, improves the accuracy of the prediction model for the real-time getting-on time of the passenger, optimizes the prediction model for the getting-on and getting-off time of the passenger by considering the queuing behavior of the passenger, can predict the getting-on and getting-off time of the passenger under different queuing behaviors, and has important significance for improving the railway operation efficiency and correctly guiding the passenger.
It should be understood that the above-mentioned embodiments of the present invention are only examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention, and it will be obvious to those skilled in the art that other variations or modifications may be made on the basis of the above description, and all embodiments may not be exhaustive, and all obvious variations or modifications may be included within the scope of the present invention.
Claims (6)
1. A prediction method for getting on and off time of urban rail transit passengers is characterized by comprising the following steps:
s1: acquiring running information, platform information, passenger flow information and passenger information of a rail transit train, and carrying out statistical analysis on the information to obtain a scatter diagram of the number of passengers getting on and off and the time of the passengers getting on and off;
s2: fitting a passenger getting-on and getting-off flow change curve according to the scatter diagram, and establishing a piecewise function model for predicting the passenger getting-on time and a passenger getting-off time prediction model according to the curve curvature change;
s3: optimizing the piecewise function model and the passenger getting-off time prediction model by considering passenger queuing behaviors to obtain an optimized prediction model of the getting-on and getting-off time of passengers;
the S3 includes the steps of:
s31: establishing a queue width model of passenger getting-on formed by a plurality of queues of passengers
W=Wlayer+(n-1)Dlayer
Wlayer=Wmax+Wsway
Wherein, W is the queue width model of passenger getting on the bus formed by W multi-queue passengerslayerThe distance between the centers of two adjacent passenger teams along the vertical queue direction, n is the number of the queues, DlayerWidth required for queuing passengers near the center of the door, WmaxMaximum shoulder width of passenger, WswayFor the width of the wave when passengers are queuing near the center of the door, [ X ]]Represents an integer closest to X;
s32: according to the queue width, a door passing capacity model of the train under the passenger queuing behavior is established, and the door passing capacity model is established as
Wherein, CdThe passing capacity of the train door is shown, and z is the number of passengers waiting to get on or off the train;
then, according to the collected information, the queue number of the passengers queuing under the actual condition is obtained, and the average passenger passing capacity model of each queue is obtained
Wherein l is the queue number of the passengers in queue;
therefore, according to the queue width model, a train door passing capacity model under the passenger queuing behavior is obtained as
S33: optimizing the piecewise function model by adopting the train door passing capacity model to obtain an optimized prediction model of the getting-on and getting-off time of passengers, wherein the optimized prediction model is
Where θ is the number of passengers who have got on the bus.
S4: and solving the optimized prediction model of the getting-on and getting-off time of the passenger by adopting a least square method to obtain a real-time prediction model of the getting-on and getting-off time of the passenger.
2. The method of claim 1, wherein the train operation information includes train arrival time, train departure time, and train stopping interval.
3. The method of claim 1, wherein the platform information comprises a waiting position of a passenger and a size of a waiting area.
4. The method of claim 1, wherein the traffic information comprises platform entrance/exit traffic, boarding traffic, disembarking traffic, passenger platform distribution, number of passengers in a vehicle, density of passengers in a vehicle, and density of pedestrians.
5. The method of claim 1, wherein the passenger information comprises passenger walking speed, passenger per-capita footprint, whether to carry luggage, and passenger age distribution.
6. The method as claimed in claim 1, wherein the step S2 is performed by dividing the curve of the passenger boarding traffic into an off-peak section, a transition section and a peak section according to the curvature change of the curve, and modeling the piecewise function of the passenger boarding time prediction as
Wherein, a1,a2,a3,a4,b1,b2,c1,c2,c3The model is unknown parameters, M is the maximum value of the number of passengers getting on the bus in the off-peak period, N is the minimum value of the number of passengers getting on the bus in the peak period, and x is the number of passengers getting on the bus;
according to the curvature change of the passenger getting-off flow change curve, a passenger getting-off time prediction model is established
f(y)=αyβ
wherein, alpha and β are unknown parameters of the model, and y is the number of passengers getting off the bus.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610881642.6A CN106379379B (en) | 2016-10-09 | 2016-10-09 | A kind of Forecasting Methodology of urban track traffic passenger getting on/off time |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610881642.6A CN106379379B (en) | 2016-10-09 | 2016-10-09 | A kind of Forecasting Methodology of urban track traffic passenger getting on/off time |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106379379A CN106379379A (en) | 2017-02-08 |
CN106379379B true CN106379379B (en) | 2018-06-29 |
Family
ID=57937134
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610881642.6A Active CN106379379B (en) | 2016-10-09 | 2016-10-09 | A kind of Forecasting Methodology of urban track traffic passenger getting on/off time |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106379379B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107521525B (en) * | 2017-07-14 | 2019-08-23 | 深圳市盛路物联通讯技术有限公司 | Information control method and equipment |
CN107578521A (en) * | 2017-08-22 | 2018-01-12 | 西南交通大学 | Queuing management method and system, electronic equipment and computer-readable recording medium |
CN110450822B (en) * | 2018-05-07 | 2021-08-10 | 中车株洲电力机车研究所有限公司 | Rail transit service method, device, equipment and system |
CN110751325B (en) * | 2019-10-16 | 2023-04-18 | 中国民用航空总局第二研究所 | Suggestion generation method, traffic hub deployment method, device and storage medium |
CN112397146B (en) * | 2020-12-02 | 2021-08-24 | 广东美格基因科技有限公司 | Microbial omics data interaction analysis system based on cloud platform |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104217129A (en) * | 2014-09-22 | 2014-12-17 | 北京交通大学 | Passenger flow estimation method for urban rail road network |
CN105046350A (en) * | 2015-06-30 | 2015-11-11 | 东南大学 | AFC data-based public transport passenger flow OD real-time estimation method |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006327239A (en) * | 2005-05-23 | 2006-12-07 | Toshiba Corp | Train diagram preparation assistance device |
JP2007102390A (en) * | 2005-10-03 | 2007-04-19 | Hitachi Ltd | Seat reservation system |
-
2016
- 2016-10-09 CN CN201610881642.6A patent/CN106379379B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104217129A (en) * | 2014-09-22 | 2014-12-17 | 北京交通大学 | Passenger flow estimation method for urban rail road network |
CN105046350A (en) * | 2015-06-30 | 2015-11-11 | 东南大学 | AFC data-based public transport passenger flow OD real-time estimation method |
Non-Patent Citations (1)
Title |
---|
宁波城市轨道交通乘客上下车时间特性分析与建模;晏莉颖;《铁道运输与经济》;20160420;第1、2章,图2、3,表1、2 * |
Also Published As
Publication number | Publication date |
---|---|
CN106379379A (en) | 2017-02-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106379379B (en) | A kind of Forecasting Methodology of urban track traffic passenger getting on/off time | |
Tirachini et al. | Bus congestion, optimal infrastructure investment and the choice of a fare collection system in dedicated bus corridors | |
CN111079875A (en) | Public transport passenger flow monitoring method and device based on multi-source data and storage medium | |
CN108846514B (en) | Method for predicting demand of rail transit passenger flow evacuation in emergency | |
CN110084397B (en) | Subway through line planning method | |
CN109887267B (en) | Conventional public transportation adjusting method for common line segment of rail transit | |
Li et al. | Dwell time estimation models for bus rapid transit stations | |
Li et al. | Public bus arrival time prediction based on traffic information management system | |
CN108364464B (en) | Probability model-based public transport vehicle travel time modeling method | |
CN105225473B (en) | A kind of fast line design method of public transport based on website efficiency calculation | |
CN106971546B (en) | Road section bus permeability estimation method based on bus GPS data | |
CN112085641B (en) | High-speed railway passenger flow distribution method based on train operation scheme | |
Currie et al. | Impact of crowding on streetcar dwell time | |
Diab et al. | The farside story: measuring the benefits of bus stop location on transit performance | |
CN112381260A (en) | Urban rail transit passenger flow management and control optimization method based on station entering proportion | |
CN112562377A (en) | Passenger vehicle real-time scheduling method based on random opportunity constraint | |
CN111401643A (en) | Urban rail transit passenger flow loop self-adaptive intelligent train scheduling method | |
CN110598246A (en) | Improved lane side capacity optimization design method | |
Mikulski | Introduction of telematics for transport | |
CN116542404B (en) | Prediction method for continuous transfer time of station-supporting passengers of passenger transportation hub station | |
CN111367900B (en) | Method for calculating normal current limiting intensity of urban rail transit network based on AFC data | |
CN111723963B (en) | Subway vehicle off-station operation energy optimization method | |
CN113723761B (en) | Multi-dimensional urban public transportation operation service reliability evaluation method based on operation data | |
CN115545336A (en) | Track traffic stroke fine adjustment system and method | |
Reilly et al. | Public transport capacity analysis procedures for developing cities |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |