CN105894848A - Bus arrival time predicating method based on network - Google Patents
Bus arrival time predicating method based on network Download PDFInfo
- Publication number
- CN105894848A CN105894848A CN201610484654.5A CN201610484654A CN105894848A CN 105894848 A CN105894848 A CN 105894848A CN 201610484654 A CN201610484654 A CN 201610484654A CN 105894848 A CN105894848 A CN 105894848A
- Authority
- CN
- China
- Prior art keywords
- surveillance center
- arrival time
- bus
- time
- stop plate
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/123—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams
- G08G1/127—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams to a central station ; Indicators in a central station
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a bus arrival time predicating method based on the network. The bus arrival time predicating method comprises the following steps: integrating traffic data based on an urban traffic condition, quantifying the traffic data into influence factors for quantifying the traffic condition; forming a database by the quantified traffic condition, wherein the database is a footstone of all programs for predicating bus arrival time. The optimal average time of the bus arrival is obtained by virtue of a BP nerve network, so that the optical arrival time of the bus can be obtained, and therefore, the obtained data is very convenient for trip of people.
Description
Technical field
The invention belongs to networking technology area, particularly to a kind of network bus arrival time Forecasting Methodology.
Background technology
In same public bus network, the different road conditions such as major trunk roads, subsidiary road, loop wire section can affect the speed of service of public transit vehicle；What the Changes in weather such as rain, snow, sand and dust, dense fog also can inevitably delay vehicle reaches the time.Owing to electronic stop plate is only set up at the important station of part, therefore, public transit vehicle arrives journey time total before next sets up the website of electronic stop plate and can be divided into following several part: vehicle is with the travel speed average running time by section；Because of the queuing delay time at stop of Signalized control impact at downstream intersection；Vehicle passes through the time by this crossing；The time that several websites rest because of passenger getting on/off before prediction website；The time that several websites lose because of the deceleration of vehicles while passing station and acceleration before prediction website.Therefore, during public transit vehicle arrival time is predicted, algorithm needs to take into full account the impact of above-mentioned various factors, uses suitable error compensation means, thus improves the precision of prediction of the vehicle time of advent to greatest extent.
To sum up, every factors quantization, by the every combined factors affecting traffic arrival time being considered, is drawn optimal arrival time based on network by the present invention, substantially increases the precision of bus arrival time prediction.
Summary of the invention
Problem to be solved by this invention is to provide a kind of network bus arrival time Forecasting Methodology.
To achieve these goals, the technical scheme that the present invention takes is:
A kind of network bus arrival time Forecasting Methodology, comprises the steps:
(1) historical data base of bus running state is initially set up；
(2) BP neural net method is used to be trained historical data showing that bus is by an optimal average travel time arriving electronic stop plate of dispatching a car；
(3) introduce bus dynamic operation information and revise the optimal average travel time provided by BP neural net method；
Preferably, it is as follows that described step (1) historical data base sets up process: bus is in running, to total activation, Surveillance center uploads running state information, including the journey time between different periods bus stop, crossing quantity, the volume of the flow of passengers, line length, weather condition and passenger satisfaction information, total activation Surveillance center stores after information being carried out taxonomic revision according to peak hour, Ping Feng, night in units of sky, updates historical data base simultaneously.
Preferably, described step (2) BP neural net method uses the BP neutral net of three-decker, wherein input layer is for affect journey time principal element, output layer is optimal average travel time, the neuron number of hidden layer is determined by input neuron number and output neuron number, generally uses below equation to obtain: L=Nm/ (n+m), and wherein m and n is output, input neuron number, L is hidden nodes, and N is sample size.
Preferably, described step (3) is revised optimal average travel time and is comprised the following steps:
1) Surveillance center obtains gps data, determines and arrives information of vehicles recently, and calculates its anticipated in-position；
2) Surveillance center judges whether vehicle physical location is more than 50m with the spacing of anticipated in-position, if it is, perform step 3), if NO perform step 4)；
3) predicted time is revised by Surveillance center, and predicted time information is sent to electronic stop plate, and it is shown by electronic stop plate；
4) Surveillance center judges whether vehicle runs into red light at previous crossing, purpose station, shows it to electronic stop plate, electronic stop plate if it is, Surveillance center sends " section blocks up; bus arrives and will slightly delay " information, and performs step 5), if it has not, then return step 1)；
5) Surveillance center uses smoothing algorithm to retrieve vehicle arrival time predictive value simultaneously, and sends it to electronic stop plate, and it is shown by electronic stop plate；
6) after vehicle arrives at a station, Surveillance center judges whether vehicle sets off, if it is, perform step 1), if it has not, electronic stop plate shows " vehicle arrives at a station " information.
Preferably, the input layer of described step (2) BP neutral net affects journey time principal element include investigating period, the volume of the flow of passengers, crossing quantity, path length, weather condition and passenger satisfaction.
Preferably, during described step (3) revises the step 3) of optimal average travel time Surveillance center by 100m to revise predicted time.
Beneficial effect: the invention provides a kind of network bus arrival time Forecasting Methodology, traffic data is carried out comprehensively by traffic based on city, it is quantified as factor of influence traffic is quantified, then the traffic composition data base that will quantify, become the foundation stone of all programs that the present invention predicts that the public transport time arrives at a station, the optimal average time of bus arrival is drawn by BP neural net method, thus can draw the optimal arrival time of bus, the trip that the data so drawn just can greatly be convenient for people to.
Detailed description of the invention
Embodiment
1
:
A kind of network bus arrival time Forecasting Methodology, its processing technique comprises the steps:
(1) historical data base of bus running state is initially set up, it is as follows that historical data base sets up process: bus is in running, to total activation, Surveillance center uploads running state information, including the journey time between different periods bus stop, crossing quantity, the volume of the flow of passengers, line length, weather condition and passenger satisfaction information, total activation Surveillance center stores after information being carried out taxonomic revision according to peak hour, Ping Feng, night in units of sky, updates historical data base simultaneously；
(2) BP neural net method is used to be trained historical data showing that bus is by an optimal average travel time arriving electronic stop plate of dispatching a car, BP neural net method uses the BP neutral net of three-decker, wherein input layer is for affect journey time principal element, including investigating the period, the volume of the flow of passengers, crossing quantity, path length, weather condition and passenger satisfaction, output layer is optimal average travel time, the neuron number of hidden layer is determined by input neuron number and output neuron number, below equation is generally used to obtain: L=Nm/ (n+m), wherein m and n is output, input neuron number, L is hidden nodes, N is sample size；
(3) introduce bus dynamic operation information and revise the optimal average travel time provided by BP neural net method, revise optimal average travel time and comprise the following steps:
1) Surveillance center obtains gps data, determines and arrives information of vehicles recently, and calculates its anticipated in-position；
2) Surveillance center judges whether vehicle physical location is more than 50m with the spacing of anticipated in-position, if it is, perform step 3), if NO perform step 4)；
3) predicted time is revised by 100m by Surveillance center, and predicted time information is sent to electronic stop plate, and it is shown by electronic stop plate；
4) Surveillance center judges whether vehicle runs into red light at previous crossing, purpose station, shows it to electronic stop plate, electronic stop plate if it is, Surveillance center sends " section blocks up; bus arrives and will slightly delay " information, and performs step 5), if it has not, then return step 1)；
5) Surveillance center uses smoothing algorithm to retrieve vehicle arrival time predictive value simultaneously, and sends it to electronic stop plate, and it is shown by electronic stop plate；
6) after vehicle arrives at a station, Surveillance center judges whether vehicle sets off, if it is, perform step 1), if it has not, electronic stop plate shows " vehicle arrives at a station " information.
After process above, taking out sample respectively, measurement result is as follows:
| Success rate prediction | With actual arrival time error/min | Execution process error rate | Perform precision | |
| Embodiment 1 | 93.2% | 2.5 | 0.5‰ | 0.001 |
| Prior art | 84.7% | 3.2 | 0.8‰ | 0.010 |
Can draw according to above table data, when embodiment 1 implements network bus arrival time Forecasting Methodology, the success rate of prediction is 93.2%, it is 2.5min with error actual time, performing error rate is 0.5 ‰, performing precision is 0.001, and the success rate of prior art standard method prediction is 84.7%, it is 3.2min with error actual time, performing error rate is 0.8 ‰, performing precision is 0.010, this shows the present invention network bus arrival time Forecasting Methodology, success rate prediction is high, little with actual arrival time error, the error rate performed is low, the precision performed is high, therefore the present invention has significant superiority.
The invention provides a kind of network by recognition of face method for distinguishing, traffic data is carried out comprehensively by traffic based on city, it is quantified as factor of influence traffic is quantified, then the traffic composition data base that will quantify, become the foundation stone of all programs that the present invention predicts that the public transport time arrives at a station, the optimal average time of bus arrival is drawn by BP neural net method, thus can draw the optimal arrival time of bus, the trip that the data so drawn just can greatly be convenient for people to.
The foregoing is only embodiments of the invention; not thereby the scope of the claims of the present invention is limited; every equivalent structure utilizing description of the invention content to be made or equivalence flow process conversion; or directly or indirectly it is used in other relevant technical fields, the most in like manner it is included in the scope of patent protection of the present invention.
Claims (6)
1. a network bus arrival time Forecasting Methodology, it is characterised in that its preparation technology includes:
(1) historical data base of bus running state is initially set up；
(2) BP neural net method is used to be trained historical data showing that bus is by an optimal average travel time arriving electronic stop plate of dispatching a car；
(3) introduce bus dynamic operation information and revise the optimal average travel time provided by BP neural net method.
2. the network bus arrival time Forecasting Methodology processed described in claim 1, it is characterized in that: it is as follows that described step (1) historical data base sets up process: bus is in running, to total activation, Surveillance center uploads running state information, including the journey time between different periods bus stop, crossing quantity, the volume of the flow of passengers, line length, weather condition and passenger satisfaction information, total activation Surveillance center stores after information being carried out taxonomic revision according to peak hour, Ping Feng, night in units of sky, updates historical data base simultaneously.
3. the network bus arrival time Forecasting Methodology processed described in claim 1, it is characterized in that: described step (2) BP neural net method uses the BP neutral net of three-decker, wherein input layer is for affect journey time principal element, output layer is optimal average travel time, the neuron number of hidden layer is determined by input neuron number and output neuron number, below equation is generally used to obtain: L=Nm/ (n+m), wherein m and n is output, input neuron number, L is hidden nodes, and N is sample size.
4. the network bus arrival time Forecasting Methodology processed described in claim 1, it is characterised in that: described step (3) is revised optimal average travel time and is comprised the following steps:
1) Surveillance center obtains gps data, determines and arrives information of vehicles recently, and calculates its anticipated in-position；
2) Surveillance center judges whether vehicle physical location is more than 50m with the spacing of anticipated in-position, if it is, perform step 3), if NO perform step 4)；
3) predicted time is revised by Surveillance center, and predicted time information is sent to electronic stop plate, and it is shown by electronic stop plate；
4) Surveillance center judges whether vehicle runs into red light at previous crossing, purpose station, shows it to electronic stop plate, electronic stop plate if it is, Surveillance center sends " section blocks up; bus arrives and will slightly delay " information, and performs step 5), if it has not, then return step 1)；
5) Surveillance center uses smoothing algorithm to retrieve vehicle arrival time predictive value simultaneously, and sends it to electronic stop plate, and it is shown by electronic stop plate；
6) after vehicle arrives at a station, Surveillance center judges whether vehicle sets off, if it is, perform step 1), if it has not, electronic stop plate shows " vehicle arrives at a station " information.
5. according to the network bus arrival time Forecasting Methodology described in processing claim 3, it is characterised in that: the input layer of described step (2) BP neutral net affects journey time principal element and includes investigating period, the volume of the flow of passengers, crossing quantity, path length, weather condition and passenger satisfaction.
6. according to network bus arrival time Forecasting Methodology described in processing claim 4, it is characterised in that: described step (3) revises in the step 3) of optimal average travel time Surveillance center by 100m to revise predicted time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610484654.5A CN105894848A (en) | 2016-06-29 | 2016-06-29 | Bus arrival time predicating method based on network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610484654.5A CN105894848A (en) | 2016-06-29 | 2016-06-29 | Bus arrival time predicating method based on network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105894848A true CN105894848A (en) | 2016-08-24 |
Family
ID=56719204
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610484654.5A Withdrawn CN105894848A (en) | 2016-06-29 | 2016-06-29 | Bus arrival time predicating method based on network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105894848A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106652534A (en) * | 2016-12-14 | 2017-05-10 | 北京工业大学 | Method for predicting arrival time of bus |
| WO2018129850A1 (en) * | 2017-01-10 | 2018-07-19 | Beijing Didi Infinity Technology And Development Co., Ltd. | Method and system for estimating time of arrival |
| CN110361019A (en) * | 2018-04-11 | 2019-10-22 | 北京搜狗科技发展有限公司 | For predicting method, apparatus, electronic equipment and the readable medium of navigation time |
| CN111523560A (en) * | 2020-03-18 | 2020-08-11 | 第四范式（北京）技术有限公司 | Training method, prediction method, device and system for number prediction model of arriving trucks |
| CN114842157A (en) * | 2022-04-21 | 2022-08-02 | 上海智能网联汽车技术中心有限公司 | Intelligent networking public transportation supervision method based on digital twins |
| CN115063978A (en) * | 2022-07-27 | 2022-09-16 | 武汉微晶石科技股份有限公司 | Bus arrival time prediction method based on digital twins |
-
2016
- 2016-06-29 CN CN201610484654.5A patent/CN105894848A/en not_active Withdrawn
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106652534A (en) * | 2016-12-14 | 2017-05-10 | 北京工业大学 | Method for predicting arrival time of bus |
| CN106652534B (en) * | 2016-12-14 | 2019-08-16 | 北京工业大学 | A method of prediction bus arrival time |
| WO2018129850A1 (en) * | 2017-01-10 | 2018-07-19 | Beijing Didi Infinity Technology And Development Co., Ltd. | Method and system for estimating time of arrival |
| GB2564181A (en) * | 2017-01-10 | 2019-01-09 | Beijing Didi Infinity Technology & Dev Co Ltd | Method and system for estimating time of arrival |
| US10816352B2 (en) | 2017-01-10 | 2020-10-27 | Beijing Didi Infinity Technology And Development Co., Ltd. | Method and system for estimating time of arrival |
| CN110361019A (en) * | 2018-04-11 | 2019-10-22 | 北京搜狗科技发展有限公司 | For predicting method, apparatus, electronic equipment and the readable medium of navigation time |
| CN110361019B (en) * | 2018-04-11 | 2022-01-11 | 北京搜狗科技发展有限公司 | Method, device, electronic equipment and readable medium for predicting navigation time |
| CN111523560A (en) * | 2020-03-18 | 2020-08-11 | 第四范式（北京）技术有限公司 | Training method, prediction method, device and system for number prediction model of arriving trucks |
| CN114842157A (en) * | 2022-04-21 | 2022-08-02 | 上海智能网联汽车技术中心有限公司 | Intelligent networking public transportation supervision method based on digital twins |
| CN115063978A (en) * | 2022-07-27 | 2022-09-16 | 武汉微晶石科技股份有限公司 | Bus arrival time prediction method based on digital twins |
| CN115063978B (en) * | 2022-07-27 | 2022-11-18 | 武汉微晶石科技股份有限公司 | Bus arrival time prediction method based on digital twins |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106127344A (en) | A kind of network bus arrival time Forecasting Methodology | |
| CN105894848A (en) | Bus arrival time predicating method based on network | |
| CN102081859B (en) | Control method of bus arrival time prediction model | |
| WO2021212866A1 (en) | Vehicle travel volume prediction model construction method, and prediction method and system | |
| US20190266891A1 (en) | A method to quantitatively analyze the effects of urban built environment on road travel time | |
| CN102737504B (en) | Method for estimating bus arrival time in real time based on drive characteristics | |
| CN104200649B (en) | Based on the rush-hour path resource dispatching distribution System and method for of pre-first to file | |
| CN105946860B (en) | A kind of bend speed prediction method for considering driving style | |
| Li et al. | Public bus arrival time prediction based on traffic information management system | |
| CN105225473B (en) | A kind of fast line design method of public transport based on website efficiency calculation | |
| CN109275121B (en) | Vehicle trajectory tracking method based on adaptive extended Kalman filtering | |
| CN112927503B (en) | Method for coordinating and controlling main line speed limitation and ramp fusion of expressway in rainy days | |
| CN104637334A (en) | Real-time predicting method for arrival time of bus | |
| CN110084397B (en) | Subway through line planning method | |
| CN109190811B (en) | Vehicle speed tracking method based on adaptive extended Kalman filtering | |
| CN104318759B (en) | Bus stop station time real-time estimation method based on self-learning algorithm and system | |
| CN108510730A (en) | Vehicle dispatching method and system between shared automobile site | |
| CN103440422A (en) | Bus behind-schedule recovering method based on arrival time predication with time window | |
| CN108830399A (en) | What a kind of rail traffic website plugged into the facility equilibrium of supply and demand optimizes and revises method | |
| CN106327867B (en) | Bus punctuation prediction method based on GPS data | |
| CN104408948A (en) | Vehicle-mounted-GPS-based public transport priority signal control method of urban road traffic | |
| CN105869402B (en) | Express highway section speed modification method based on polymorphic type floating car data | |
| CN106097717A (en) | The signalized intersections average transit time method of estimation merged based on two class floating car datas | |
| Mittal et al. | Network flow relations and travel time reliability in a connected environment | |
| CN110046824A (en) | A kind of operation Time segments division method of city public traffic circuit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20160824 |
|
| WW01 | Invention patent application withdrawn after publication |