CN105185103B - A kind of management control method of Link Travel Time - Google Patents
A kind of management control method of Link Travel Time Download PDFInfo
- Publication number
- CN105185103B CN105185103B CN201510654369.9A CN201510654369A CN105185103B CN 105185103 B CN105185103 B CN 105185103B CN 201510654369 A CN201510654369 A CN 201510654369A CN 105185103 B CN105185103 B CN 105185103B
- Authority
- CN
- China
- Prior art keywords
- time
- traffic
- road section
- traffic data
- data sequence
- 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 34
- 230000004927 fusion Effects 0.000 claims abstract description 37
- 238000005070 sampling Methods 0.000 claims abstract description 8
- 238000013528 artificial neural network Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000013507 mapping Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 14
- 238000004891 communication Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 230000000737 periodic effect Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 210000002569 neuron Anatomy 0.000 claims description 4
- 230000001934 delay Effects 0.000 claims description 3
- 238000000611 regression analysis Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 14
- 230000006870 function Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000011144 upstream manufacturing Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000013075 data extraction Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000029305 taxis Effects 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of management control method of Link Travel Time, comprise the following steps, S01:Traffic data is gathered using SCOOT classes traffic control system and is handled;S02:Traffic data is gathered using global position system and is handled;S03:The SCOOT classes traffic control system is merged with the traffic data that the global position system is transferred to using the converged services device, and generates fusion output result;S04:Using the converged services device Traffic information demonstration, Intelligent Dynamic system for traffic guiding are sent to by output result is merged.The present invention greatly reduces the procurement cost of dynamic information without additionally putting into;Overcome the Link Travel Time caused by the reason such as SCOOT class traffic control system data samplings interval is inconsistent and obtain and lack the problems such as good data basis, global position system matching effect near intersection be bad.
Description
Technical Field
The invention relates to the technical field of intelligent traffic, in particular to a road section travel time management control method based on a SCOOT traffic control system and a satellite positioning system.
Background
The road section travel time is the most intuitive and effective traffic parameter for reflecting the road traffic state, and is an important basis for carrying out traffic congestion management and dynamic path guidance. At present, the method for acquiring the travel time of the road section can be divided into two methods, namely direct acquisition and indirect acquisition. The direct acquisition method needs to arrange license plate recognition facilities at the starting and ending points of each road section, so that the required cost is too high, and the method is difficult to realize in actual engineering. Therefore, indirect acquisition methods based on other traffic data have been one of the important research subjects in the international traffic engineering field.
The SCOOT (Cycle, Offset Optimization Technique) system, namely the LvBir, Signal period and LvHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHlHl. In view of the excellent control effect of SCOOT, relevant researchers at home and abroad successively develop some traffic signal control systems similar to SCOOT, the systems all adopt a vehicle detector layout scheme and a timing optimization algorithm similar to SCOOT, and the traffic signal control systems and the SCOOT systems are collectively called as SCOOT type traffic signal control systems. With the wide-range application of Satellite positioning systems such as a Global Positioning System (GPS) and a BeiDou Navigation Satellite System (BDS) in the traffic field, vehicle-mounted devices have been widely applied to the aspects of vehicle scheduling, monitoring, Navigation and the like of taxis, logistics vehicles, buses and the like, and a large amount of data is also accumulated. The two data sources become the most important traffic data acquisition means in urban roads, and the travel time is calculated by using the two data sources, so that the method has important practical significance for improving the coordination of traffic control, traffic guidance and traffic guidance at low cost.
However, the SCOOT traffic control system acquires traffic data by taking the green light time as a time interval, and the green light time is a time-varying parameter, so that the comparability of the traffic data in each time interval is reduced, and the road section travel time acquisition lacks a good data basis. At present, related research results are few, and it is assumed that a vehicle detector of a traffic control system of the SCOOT type can provide traffic data according to a certain fixed sampling interval, and even on the premise of some data which cannot be provided at present, the assumptions do not conform to the actual situation of the traffic control system of the SCOOT type, or are difficult to be realized by engineering means in a short time.
For a satellite positioning system, the sample size of a floating car is a key factor for determining the obtaining effect of the travel time of a road section, but the running cost of the system determines that the model of the floating car is often single, the model composition of a traffic flow is complex, and different types of vehicles have different running characteristics, so that the running condition of the floating car is difficult to completely represent the whole condition of the traffic flow. In addition, due to the shielding of the trees, tall buildings, tunnels and the like on satellite signals, a GPS detection blind area can be caused in some specific places, and the calculation effect of the road section travel time can be reduced. In addition, the existing research shows that due to the influence of signal control, the vehicle stops or walks near the intersection, so that the map matching effect is poor, and the road section travel time obtaining effect is poor.
Disclosure of Invention
The purpose of the invention is: the method aims at solving the problems that good data foundation is lacked for acquiring the road section travel time and the like caused by inconsistent data sampling intervals of the SCOOT traffic control system and the like, and provides an effective road section travel time acquisition method based on the SCOOT traffic control system data; aiming at the problem of poor output effect of the road section travel time caused by the reasons of difficult matching of sample size and partial area maps and the like, an effective road section travel time acquisition method based on satellite positioning system data is provided; based on the road section travel time output results of the two data sources, the method for obtaining the urban road section travel time in a fusion mode is provided, and the output effect of the road section travel time is further improved.
The technical scheme for achieving the purpose is as follows: a management control method for road section travel time comprises the following steps,
s01: collecting and processing traffic data by using a SCOOT traffic control system, and sending the processed traffic data to a fusion server;
s02: collecting and processing traffic data by using a satellite positioning system, and sending the processed traffic data to a fusion server;
s03: fusing the traffic data transmitted by the SCOOT traffic control system and the satellite positioning system by using the fusion server, and generating a fusion output result;
s04: and transmitting the fusion output result to a traffic information issuing and intelligent dynamic traffic guidance system by utilizing the fusion server.
The step S01 includes the steps of,
s011: determining and extracting a first space scale and a first time scale obtained by the road section travel time by using an SCOOT traffic control system;
s012: collecting traffic data of intersections in a periodic time interval, and transmitting the traffic data to an information server of the SCOOT traffic control system of a traffic information center by using a communication system, wherein the traffic data comprises traffic parameter data and traffic signal control data, and the traffic parameter data comprises traffic flow, average speed and occupancy rate; the traffic signal control data comprises a period duration and a green light duration;
s013: constructing a virtual traffic data sequence for actual traffic data by using an information server of the SCOOT traffic control system;
s014: and designing a first acquisition model of the road section travel time by using the BP neural network, generating a first output result of the road section travel time, and transmitting the first output result to the fusion server.
The first spatial dimension in step S011 is a road between two consecutive stop line reverse extension lines.
The step S013 includes the following steps,
s0131: converting the traffic parameter data;
the step S0131 includes the steps of,
s01311: conversion of traffic flow:
the number of vehicles passing through in unit time is shown as the following formula:
in the formula, Ci(s) and qi(s) cycle and traffic flow of the ith time interval of the actual traffic data sequence respectively;the number of passing vehicles in unit time;
the mapping relation of the traffic flow converted from the actual traffic data sequence to the virtual traffic data sequence is as follows:
wherein q isj(x) The total flow of the jth time interval of the virtual traffic data sequence; t is tiThe length of the jth time interval of the virtual traffic data sequence in the ith time interval of the actual traffic data sequence is set; n is the number of the virtual traffic data sequence occupying the actual traffic data sequence at the jth time interval;
s01312: converting the average vehicle speed;
the average speed is the average value of the speed of the vehicle point, and the mapping relation converted from the actual traffic data sequence into the virtual traffic data sequence is as follows:
wherein v isj(x) The average vehicle speed of the jth time interval of the virtual traffic data sequence; v. ofi(s) is the average vehicle speed of the ith time interval of the actual traffic data series,the number of passing vehicles in unit time; t is tiThe time length of the jth time interval position of the virtual traffic parameter data sequence and the ith time interval of the actual traffic parameter data sequence is obtained;
s01313: converting the occupancy rate;
the occupancy rate is the ratio of the time accumulated value occupied by the vehicle to the measured time, and the mapping relation converted from the actual traffic data sequence into the virtual traffic data sequence is as follows:
wherein o isj(x) The occupancy rate of the jth time interval of the virtual traffic data sequence is shown; oi(s) occupancy of the ith time interval of the actual traffic data sequence, tiThe time length of the jth time interval position of the virtual traffic parameter data sequence and the ith time interval of the actual traffic parameter data sequence is obtained;
s0132: the traffic signal controls the conversion of the data,
the step S0132 includes the steps of,
s01321: the cycle duration is converted from the green light duration,
the optimization of the SCOOT traffic control system timing parameters adopts a continuous micro-adjustment mode, the green light time length and the period time length of adjacent signal periods have small changes, and the mapping relation of the period time length and the green light time length converted from an actual traffic data sequence into a virtual traffic data sequence is as follows:
wherein, gj(x)、Cj(x) Respectively the average green light duration and the average cycle duration of the jth time interval of the virtual traffic data sequence; gi(s) Green duration for the ith time interval of the actual traffic data sequence, Ci(s) is the ith periodic time interval of the actual traffic data sequence.
The BP neural network in step S014 is a three-layer BP neural network including a hidden layer, and a training function of the BP neural network is a sigmood function; the training error is the root mean square error RMSE.
The step S02 includes the steps of,
s021: determining and extracting a second space scale and a second time scale obtained by the road section travel time by using a satellite positioning system, wherein the second space scale is consistent with the first space scale, and the first time scale is consistent with the first time scale;
s022: in a certain sampling time interval, various information data of the vehicle-mounted equipment are acquired by using a satellite positioning system, and the various information data of the vehicle-mounted equipment are uploaded to an information server of the satellite positioning system of a traffic information center through communication equipment;
s023: and designing a second acquisition model for the travel time of the basic road section and the intersection delay time by using an information server and a GIS (geographic information system) of the satellite positioning system, generating a second output result of the road section travel time, and transmitting the second output result to the fusion server.
The step S023 includes the steps of,
s0231: designing a model of vehicle travel time of a basic road section;
the step S0231 includes the steps of,
s02311: calculating the driving time of the single-vehicle basic road section,
assuming that the vehicle keeps running at a constant speed between adjacent positioning points, the extraction formula of the road section boundary moment is as follows
Wherein t ″ (t) and t' (t +1) respectively represent the current road section end point boundary time and the downstream road section start point boundary time; t (t), t (t-n (t)) respectively represent the positioning time of the current matching point and the previous matching point; l '(t) and L' (t-n (t)) respectively represent the distance between the current matching point and the previous matching point data and the current road section terminal point boundary;
the calculation formula of the driving time of the basic road section of the bicycle is
T′=t″-t′
Wherein: t' is the travel time of the basic road section of the single sample vehicle; t 'and t' are respectively the time when the sample vehicle passes through the starting and ending boundaries of the road section;
s02312: calculating the running time of the basic road section of the sample vehicle,
the running time of the basic road section of the sample vehicle is the average level of the running time of all basic road sections of the single vehicle passing through the specific road section within the specific time scale, and the average value of the running time of the basic road sections of the single vehicle can be directly taken, namely
Wherein,the running time of the basic road section of the sample vehicle is taken as the running time of the basic road section of the sample vehicle;
s02313: a traffic flow basic link travel time calculation,
the travel time of the basic road section of the traffic flow refers to the average level of the travel time of all basic road sections of vehicles passing through the specific road section within a specific time scale, and the statistical analysis calculation formula is adopted as
Wherein: t (l)1) The travel time of the traffic flow basic road section is; f is a regression function established by regression analysis;
s0232: designing an intersection delay time model;
the step S0232 includes the steps of,
s02321: the calculation of the delay time of the intersection is carried out,
estimating intersection delays using the Webster equation, i.e.
Wherein,the intersection delay time is C, and the cycle duration is C; g is the duration of a green light; q is traffic flow; u is the split between the split and the split, i.e., g/C; x is the saturation, i.e., (qXC)/(sxg); s is the saturation flow rate.
S0233: calculating the travel time of the road section; the link travel time being the sum of the basic link travel time and the intersection delay time, i.e.
The technical scheme has the advantages that: the management control method for the road section travel time does not need additional investment, and greatly reduces the acquisition cost of the dynamic traffic information; the problem that good data foundation is not available for obtaining the road section travel time due to the fact that sampling intervals of SCOOT traffic control system data are not consistent and the like is solved, and the output effect of the road section travel time is improved; the problem of poor acquisition effect of the road section travel time caused by the reasons of difficult matching of the sample size and partial area maps and the like is solved, and the output effect of the road section travel time is improved; the model is obtained based on the fusion of the two data sources, so that the output effect of the travel time of the road section is further improved, the coordination degree of traffic signal control, traffic information guidance and traffic command can be obviously improved, and more powerful decision support is provided for maximally improving the traffic congestion dispersion effect.
Drawings
The invention is further described below with reference to the figures and examples.
Fig. 1 is a general flowchart of a link travel time management control method according to an embodiment of the present invention.
Fig. 2 is a flow chart for acquiring a road section travel time based on the SCOOT-type traffic control system according to the embodiment of the present invention.
Fig. 3 is a flowchart of a road section travel time acquisition based on a satellite positioning system according to an embodiment of the present invention.
Fig. 4 is a schematic diagram of determining a spatial scale of the SCOOT-type traffic control system according to the embodiment of the present invention.
Fig. 5 is a schematic diagram of the cycle and green time duration of the SCOOT-type traffic control system according to the embodiment of the present invention.
Fig. 6 is a diagram of a BP neural network model structure based on the SCOOT-type traffic control system according to the embodiment of the present invention.
Fig. 7 is a schematic diagram of a road section boundary time extraction method based on a satellite positioning system according to an embodiment of the present invention.
Fig. 8 is a flowchart of a road section travel time fusion acquisition process according to an embodiment of the present invention.
Detailed Description
Example (b): as shown in fig. 1, a management control method for road section and travel time, wherein a traffic information collection subsystem in an intelligent transportation system in an urban area used in this embodiment is mainly composed of an external field device, a communication system, a traffic information center related server, and the like, and a specific operation flow includes 3 modules below.
1. Traffic control system based on SCOOT class: determining a space scale and a time scale obtained by the travel time of the road section; uploading traffic parameter data and signal lamp configuration information of the intersection to a traffic information center SCOOT traffic control system information server by using a communication system and taking a period as a time interval; the SCOOT traffic control system information server constructs a virtual traffic data sequence for the actual traffic data sequence; the SCOOT traffic control system information server acquires the model by using the road section travel time, generates a road section travel time output result and transmits the road section travel time output result to the fusion server.
2. Based on the satellite positioning system: determining a space scale and a time scale obtained by the travel time of the road section; the vehicle-mounted equipment uploads fields such as vehicle number, license plate, precision, latitude, instantaneous speed, direction angle, positioning time and the like to a satellite positioning system information server of a communication information center through wireless communication equipment at a certain time interval; the satellite positioning System Information server combines with a GIS (Geographic Information System, GIS) System, and utilizes the basic road section driving time and intersection delay time acquisition model provided by the invention to generate a road section travel time output result and transmit the road section travel time output result to the fusion server.
3. A road section travel time fusion acquisition module: the fusion server receives the road section travel time output results based on the two data sources, utilizes the road section travel time fusion acquisition model to generate a fusion output result, and transmits the fusion output result to subsequent subsystems of the intelligent traffic system such as traffic information issuing and dynamic traffic guidance so as to provide data support for the subsequent subsystems.
The method for managing and controlling the road section travel time of the embodiment comprises the following steps.
S01: and collecting and processing the traffic data by using the SCOOT traffic control system, and sending the processed traffic data to the fusion server.
As shown in fig. 2, the step S01 includes the following steps.
As shown in fig. 4, S011: determining and extracting a first spatial scale and a first time scale of the road section travel by using an SCOOT traffic control system; the first spatial dimension in step S011 is a road between two consecutive stop line reverse extension lines.
Specifically, the method comprises the following steps: the first space scale determining method for obtaining the road section travel time is that the position of a reverse extension line of a stop line on the upstream of a lane is used as a boundary for dividing the road section, and a road between two continuous reverse extension lines of the stop line is called as a road section; the first time scale determining method for acquiring the road section travel time refers to comprehensively considering the minimum total delay of the road network and the psychological habits of travelers caused by the construction of the virtual traffic data sequence, and preferably 150s or 300s is recommended.
S012: collecting traffic data of intersections in a periodic time interval, and transmitting the traffic data to an information server of the SCOOT traffic control system of a traffic information center by using a communication system, wherein the traffic data comprises traffic parameter data and traffic signal control data, and the traffic parameter data comprises traffic flow, average speed and occupancy rate; the traffic signal control data includes a cycle duration, a green light duration.
S013: and constructing a virtual traffic data sequence for the actual traffic data by using the information server of the SCOOT traffic control system. The construction of the virtual traffic data sequence of the SCOOT traffic control system refers to converting a dynamically changed actual traffic data sequence into a virtual traffic data sequence with a fixed time scale through a corresponding conversion relation, specifically including conversion of traffic flow, average speed, occupancy, traffic control parameters and the like.
The method comprises the following steps of 1) obtaining the space scale by the road section travel time: the SCOOT traffic control system takes an intersection as a minimum recording unit, and the acquired traffic data comprises two types of traffic signal control data and traffic parameter data. Wherein, the former mainly comprises a period, a green light time and the like; the latter mainly includes traffic flow, average vehicle speed, occupancy, and the like. The vehicle detector of the SCOOT traffic control system is arranged near the reverse extension line position of the upstream stop line of the lane, and the sampling interval of traffic parameter data is the duration of green light. In order to fully utilize basic data of the SCOOT traffic control system, the position of a stop line reverse extension line on the upstream of a lane is used as a boundary for dividing a road section, and a road between two continuous stop line reverse extension lines is called the road section.
2) The time scale determination method for acquiring the road section travel time comprises the following steps: the inconsistency of the time interval between the virtual traffic data sequence and the actual traffic data sequence may cause the corresponding data extraction points to be different, thereby causing a certain time delay. When determining the time scale of the road section travel time estimation, the minimum total delay of the road network and the psychological habits of travelers should be comprehensively considered, and 150s or 300s is preferably recommended.
The specific steps are as follows.
The step S013 includes the following steps.
S0131: and converting the traffic parameter data. The step S0131 includes the following steps.
S01311: and (4) converting the traffic flow.
The number of vehicles passing in unit time is shown as formula (1) if the vehicles arrive uniformly:
wherein, C in the formulai(s) and Ci(s) respectively representing the ith cycle time interval and the traffic flow of the actual traffic data sequence;is the number of vehicles passing in a unit time.
The mapping relation of the traffic flow converted from the actual traffic data sequence to the virtual traffic data sequence is as follows:
wherein q isj(x) For virtual traffic data sequencesColumn j total flow rate for time interval; t is tiThe time length of the jth time interval position of the virtual traffic parameter data sequence and the ith time interval of the actual traffic parameter data sequence is obtained; n is the number of the virtual traffic data sequence occupying the actual traffic data sequence at the jth time interval.
S01312: and converting the average vehicle speed.
The average speed is the average value of the speed of the vehicle point, and the mapping relation converted from the actual traffic data sequence into the virtual traffic data sequence is as follows:
wherein v isj(x) The average vehicle speed of the jth time interval of the virtual traffic data sequence; v. ofi(s) is the average vehicle speed of the ith time interval of the actual traffic data series,the number of passing vehicles in unit time; t is tiThe time length of the jth time interval bit of the virtual traffic parameter data sequence and the ith time interval of the actual traffic parameter data sequence is obtained.
S01313: and converting the occupancy rate.
The occupancy rate is the ratio of the time accumulated value occupied by the vehicle to the measured time, and the mapping relation converted from the actual traffic data sequence into the virtual traffic data sequence is as follows:
wherein o isj(x) The occupancy rate of the jth time interval of the virtual traffic data sequence is shown; oi(s) occupancy of the ith time interval of the actual traffic data sequence, tiFor the jth time interval bit of the virtual traffic parameter data sequence and the ith time of the actual traffic data sequenceThe duration of the interval;
as shown in fig. 5, S0132: the step S0132 includes the following steps.
S01321: the cycle duration and the green light duration are converted.
The optimization of the SCOOT traffic control system timing parameters adopts a continuous micro-adjustment mode, the green light time length and the period time length of adjacent signal periods have small changes, and the mapping relation of the period time length and the green light time length converted from an actual traffic data sequence into a virtual traffic data sequence is as follows:
wherein, gj(x)、Cj(x) Respectively the average green light duration and the average cycle duration of the jth time interval of the virtual traffic data sequence; gi(s) Green duration for the ith time interval of the actual traffic data sequence, Ci(s) is the ith periodic time interval of the actual traffic data sequence.
The inconsistency of the time interval between the virtual traffic data sequence and the actual traffic data sequence may cause the corresponding data extraction points to be different, thereby causing a certain time delay. When determining the time scale of the road section travel time simulation, the minimum total delay of the road network and the psychological habits of travelers should be comprehensively considered, and 150s or 300s is preferably recommended.
The BP neural network in step S014 is a three-layer BP neural network including a hidden layer, and a training function of the BP neural network is a sigmood function; the training error is the root mean square error RMSE.
As shown in fig. 6, specifically: the road section travel time acquisition model based on the SCOOT traffic control system is that a three-layer BP neural network containing a hidden layer is constructed, a virtual traffic data sequence of the SCOOT traffic signal control system is used as input, and the virtual traffic data sequence comprises 5 parameters including traffic flow, average speed, occupancy rate, green light duration and cycle duration; taking the road section travel time with the same space and time scale as output; the number of hidden layer neurons is set to 9 according to the principle of (2 multiplied by the number of input neurons-1); the training function adopts a Sigmiod function; the training error is the root mean square error RMSE.
S014: and designing a first acquisition model of the road section travel time by using the BP neural network, generating a first output result of the road section travel time, and transmitting the first output result to the fusion server.
The BP neural network is one of the most widely applied neural networks at present, has the characteristic of learning and storing a large number of input-output mode mapping relations, and does not need to disclose a mathematical model describing the mapping relations in advance, and the invention establishes a road section travel time simulation model based on the BP neural network.
Since a three-layer BP neural network containing one hidden layer can approximate any nonlinear continuous function, the number of hidden layers is set to 1. The virtual traffic data sequence of the SCOOT traffic signal control system is used as input, and the virtual traffic data sequence comprises 5 parameters including traffic flow, average speed, occupancy, green light duration and cycle duration; taking the road section travel time with the same space and time scale as output; the number of hidden layer neurons is set to 9 according to the principle of (2 multiplied by the number of input neurons-1); the training function adopts a Sigmiod function; the training error is the root mean square error RMSE.
S02: and acquiring and processing the traffic data by using a satellite positioning system, and sending the processed traffic data to the fusion server.
In order to enable the road section travel time fusion acquisition model to have a good data base, the space scale and the time scale of the satellite positioning system module are consistent with those of the SCOOT traffic control system module.
In order to solve the problem that the application effect of a satellite positioning system near an intersection is poor, the road section travel time is divided into two parts of natural road section travel time and intersection delay time, and the travel time l of the two parts is calculated respectively1Is the natural road section length, l2The length of the intersection section is 70-90 m, 50-70 m and 30-40 m from the distance stop line of the main road, the secondary main road and the branch road to the distance stop line of the road without the canalization section, wherein the canalization starting point is taken as a boundary point for the intersection section and the canal starting point is generally taken as a standard for actual road survey.
As shown in fig. 3, the step S02 includes the following steps.
S021: and the space scale and the time scale acquired based on the road section travel time of the satellite positioning system are consistent with those of the SCOOT traffic control system. And determining and extracting a second space scale and a second time scale acquired by the road section travel time by using a satellite positioning system, wherein the second space scale is consistent with the first space scale, and the first time scale is consistent with the first time scale.
S022: and in a certain sampling time interval, various information data of the vehicle-mounted equipment are acquired by using the satellite positioning system, and the various information data of the vehicle-mounted equipment are uploaded to an information server of the satellite positioning system of the traffic information center through the communication equipment.
S023: and designing a second simulation model for the driving time of the basic road section and the intersection delay time by using an information server and a GIS (geographic information system) of the satellite positioning system, generating a second output result of the road section travel time, and transmitting the second output result to the fusion server. The road section travel time acquisition model based on the satellite positioning system data is that the road section travel time is divided into two parts of natural road section driving time and intersection delay time, and the travel time of the two parts is calculated respectively.
1. The basic road section running time acquisition comprises three parts of acquiring the running time of a single-vehicle basic road section, acquiring the running time of a sample-vehicle basic road section and acquiring the running time of a traffic flow basic road section;
2. intersection delay is calculated by using a Webster formula. The specific steps are as follows.
The step S023 includes the following steps.
S0231: and designing a basic road section driving time acquisition model.
The step S0231 includes the following steps.
S02311: and calculating the driving time of the basic road section of the single vehicle.
As shown in fig. 7, the satellite positioning system data generally provides fields such as vehicle number, license plate, accuracy, latitude, instantaneous speed, heading angle, and positioning time, as shown in table 1.
Table 1 example satellite positioning system data.
Assuming that the vehicle keeps running at a constant speed between adjacent positioning points, the extraction formula of the road section boundary moment is as follows
Wherein t ″ (t) and t' (t +1) respectively represent the current road section end point boundary time and the downstream road section start point boundary time; t (t), t (t-n (t)) respectively represent the positioning time of the current matching point and the previous matching point; l '(t) and L' (t-n (t)) respectively represent the distance between the current matching point and the previous matching point data and the current road section terminal point boundary;
the calculation formula of the driving time of the basic road section of the bicycle is
T′=t″-t′ (8)
Wherein: t' is the travel time of the basic road section of the single sample vehicle; t 'and t' are respectively the time when the sample vehicle passes the starting and ending boundary of the road section.
S02312: and calculating the running time of the basic road section of the sample vehicle.
The running time of the basic road section of the sample vehicle is the average level of the running time of all basic road sections of the single vehicle passing through the specific road section within the specific time scale, and the average value of the running time of the basic road sections of the single vehicle can be directly taken, namely
Wherein,the travel time of the basic road section of the sample vehicle is obtained.
S02313: and calculating the travel time of the traffic flow basic road section.
The travel time of the basic road section of the traffic flow refers to the average level of the travel time of all basic road sections of vehicles passing through the specific road section within a specific time scale, and the statistical analysis calculation formula is adopted as
Wherein: t (l)1) The travel time of the traffic flow basic road section is; f is a regression function established by regression analysis;
s0232: designing an intersection delay time model; the step S0232 includes the following steps.
S02321: and calculating delay time of the intersection.
Estimating intersection delays using the Webster equation, i.e.
Wherein,the intersection delay time is C, and the cycle duration is C; g is the duration of a green light; q is traffic flow; u is the split between the split and the split, i.e., g/C; x is the saturation, i.e., (qXC)/(sxg); is the saturation flow rate.
S0233: calculating the travel time of the road section; the link travel time being the sum of the basic link travel time and the intersection delay time, i.e.
S03: and fusing the traffic data transmitted by the SCOOT traffic control system and the satellite positioning system by using the fusion server, and generating a fusion output result.
As shown in fig. 8, the step S03 includes the following steps.
S031: and constructing a three-layer BP neural network containing an implicit layer.
S032: and taking the first output result of the SCOOT traffic signal control system, the second output result of the satellite positioning system and the number of the sample vehicles as input.
S033: and taking the road section travel time with the same spatial and time scale as output.
Specifically, the method comprises the following steps: the road section travel time fusion acquisition model is that a three-layer BP neural network containing a hidden layer is constructed, and the calculation result of the SCOOT traffic signal control system module, the calculation result of the satellite positioning system module and the number of sample vehicles are used as input; taking the road section travel time with the same space and time scale as output; the number of hidden layer neurons is set to 5 according to the principle of (2 multiplied by the number of input neurons-1); the training function adopts a Sigmiod function; the training error is the root mean square error RMSE.
S04: and transmitting the fusion output result to a traffic information issuing and intelligent dynamic traffic guidance system by utilizing the fusion server.
It should be noted that many variations and modifications of the embodiments of the present invention fully described are possible and are not to be considered as limited to the specific examples of the above embodiments. The above examples are given by way of illustration of the invention and are not intended to limit the invention. In summary, the scope of the invention should include such variations as would be apparent to one of ordinary skill in the art.
Claims (8)
1. A management control method for road section travel time is characterized in that: which comprises the following steps of,
s01: collecting and processing traffic data by using a SCOOT traffic control system, and sending the processed traffic data to a fusion server;
s02: collecting and processing traffic data by using a satellite positioning system, and sending the processed traffic data to a fusion server;
s03: fusing the traffic data transmitted by the SCOOT traffic control system and the satellite positioning system by using the fusion server, and generating a fusion output result;
s04: the fusion server is used for transmitting a fusion output result to a traffic information issuing and intelligent dynamic traffic guidance system;
the step S01 includes the steps of,
s011: determining and extracting a first space scale and a first time scale obtained by the road section travel time by using an SCOOT traffic control system;
s012: collecting traffic data of intersections in a periodic time interval, and transmitting the traffic data to an information server of the SCOOT traffic control system of a traffic information center by using a communication system, wherein the traffic data comprises traffic parameter data and traffic signal control data, and the traffic parameter data comprises traffic flow, average speed and occupancy rate; the traffic signal control data comprises a period duration and a green light duration;
s013: constructing a virtual traffic data sequence for actual traffic data by using an information server of the SCOOT traffic control system;
s014: and designing a first acquisition model of the road section travel time by using the BP neural network, generating a first output result of the road section travel time, and transmitting the first output result to the fusion server.
2. The link travel time management control method according to claim 1, characterized in that: the first spatial dimension in step S011 is a road between two consecutive stop line reverse extension lines.
3. The link travel time management control method according to claim 1, characterized in that: the step S013 includes the following steps,
s0131: converting the traffic parameter data;
the step S0131 includes the steps of,
s01311: conversion of traffic flow:
the number of vehicles passing through in unit time is shown as the following formula:
in the formula, Ci(s) and qi(s) cycle and traffic flow of the ith time interval of the actual traffic data sequence respectively;the number of passing vehicles in unit time;
the mapping relation of the traffic flow converted from the actual traffic data sequence to the virtual traffic data sequence is as follows:
wherein q isj(x) The total flow of the jth time interval of the virtual traffic data sequence; t is tiThe length of the jth time interval of the virtual traffic data sequence in the ith time interval of the actual traffic data sequence is set; n is the number of the virtual traffic data sequence occupying the actual traffic data sequence at the jth time interval;
s01312: converting the average vehicle speed;
the average speed is the average value of the speed of the vehicle point, and the mapping relation converted from the actual traffic data sequence into the virtual traffic data sequence is as follows:
wherein v isj(x) The average vehicle speed of the jth time interval of the virtual traffic data sequence; v. ofi(s) is the average vehicle speed of the ith time interval of the actual traffic data series,the number of passing vehicles in unit time; t is tiFor the jth time interval bit of the virtual traffic parameter data sequence and the ith time interval bit of the actual traffic data sequenceThe duration of the time interval;
s01313: converting the occupancy rate;
the occupancy rate is the ratio of the time accumulated value occupied by the vehicle to the measured time, and the mapping relation converted from the actual traffic data sequence into the virtual traffic data sequence is as follows:
wherein o isj(x) The occupancy rate of the jth time interval of the virtual traffic data sequence is shown; oi(s) occupancy of the ith time interval of the actual traffic data sequence, tiThe time length of the jth time interval position of the virtual traffic parameter data sequence and the ith time interval of the actual traffic parameter data sequence is obtained;
s0132: the traffic signal controls the conversion of the data,
the step S0132 includes the steps of,
s01321: the cycle duration is converted from the green light duration,
the optimization of the SCOOT traffic control system timing parameters adopts a continuous micro-adjustment mode, the green light time length and the period time length of adjacent signal periods have small changes, and the mapping relation of the period time length and the green light time length converted from an actual traffic data sequence into a virtual traffic data sequence is as follows:
wherein, gj(x)、Cj(x) Respectively the average green light duration and the average cycle duration of the jth time interval of the virtual traffic data sequence; gi(s) a green time duration for an ith time interval of the actual traffic data sequence; ci(s) is the period of the ith time interval of the actual traffic data sequence.
4. The link travel time management control method according to claim 1, characterized in that: the BP neural network in step S014 is a three-layer BP neural network including a hidden layer, and a training function of the BP neural network is a sigmood function; the training error is the root mean square error RMSE.
5. The link travel time management control method according to claim 1, characterized in that: the step S02 includes the steps of,
s021: determining and extracting a second space scale and a second time scale obtained by the road section travel time by using a satellite positioning system, wherein the second space scale is consistent with the first space scale, and the first time scale is consistent with the first time scale;
s022: in a certain sampling time interval, various information data of the vehicle-mounted equipment are acquired by using a satellite positioning system, and the various information data of the vehicle-mounted equipment are uploaded to an information server of the satellite positioning system of a traffic information center through communication equipment;
s023: and designing a second acquisition model for the driving time of the basic road section and the intersection delay time by using an information server and a GIS (geographic information system) of the satellite positioning system, generating a second output result of the road section travel time, and transmitting the second output result to the fusion server.
6. The link travel time management control method according to claim 1, characterized in that: the step S023 includes the steps of,
s0231: designing a basic road section driving obtaining model;
the step S0231 includes the steps of,
s02311: calculating the driving time of the single-vehicle basic road section,
assuming that the vehicle keeps running at a constant speed between adjacent positioning points, the extraction formula of the road section boundary moment is as follows
Wherein t ″ (t) and t' (t +1) respectively represent the current road section end point boundary time and the downstream road section start point boundary time; t (t), t (t-n (t)) respectively represent the positioning time of the current matching point and the previous matching point; l '(t) and L' (t-n (t)) respectively represent the distance between the current matching point and the previous matching point data and the current road section terminal point boundary;
the calculation formula of the driving time of the basic road section of the bicycle is
T′=t′-t′
Wherein: t' is the travel time of the basic road section of the single sample vehicle; t 'and t' are respectively the time when the sample vehicle passes through the starting and ending boundaries of the road section;
s02312: calculating the running time of the basic road section of the sample vehicle,
the running time of the basic road section of the sample vehicle is the average level of the running time of all basic road sections of the single vehicle passing through the specific road section within the specific time scale, and the average value of the running time of the basic road sections of the single vehicle can be directly taken, namely
Wherein,the running time of the basic road section of the sample vehicle is taken as the running time of the basic road section of the sample vehicle;
s02313: a traffic flow basic link travel time calculation,
the travel time of the basic road section of the traffic flow refers to the average level of the travel time of all basic road sections of vehicles passing through the specific road section within a specific time scale, and the statistical analysis calculation formula is adopted as
Wherein: t (l)1) The travel time of the traffic flow basic road section is; f is a regression function established by regression analysis;
s0232: designing an intersection delay time calculation model;
the step S0232 includes the steps of,
s02321: the calculation of the delay time of the intersection is carried out,
estimating intersection delays using the Webster equation, i.e.
Wherein,the intersection delay time is C, and the cycle duration is C; g is the duration of a green light; q is traffic flow; u is the split between the split and the split, i.e., g/C; x is the saturation, i.e., (qXC)/(sxg); s is the saturation flow rate;
s0233: calculating the travel time of the road section; the link travel time being the sum of the basic link travel time and the intersection delay time, i.e.
7. The link travel time management control method according to claim 6, characterized in that: the step S03 includes the steps of,
s031: constructing a three-layer BP neural network containing a hidden layer;
s032: taking the first output result of the SCOOT traffic signal control system, the second output result of the satellite positioning system and the number of sample vehicles as input;
s033: and taking the road section travel time with the same spatial and time scale as output.
8. The link travel time management control method according to claim 7, characterized in that:
the number of hidden layer neurons of the BP neural network is set to be 5 according to the principle of (2 multiplied by the number of input neurons-1); the training function adopts a Sigmiod function; the training error is the root mean square error RMSE.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510654369.9A CN105185103B (en) | 2015-10-10 | 2015-10-10 | A kind of management control method of Link Travel Time |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510654369.9A CN105185103B (en) | 2015-10-10 | 2015-10-10 | A kind of management control method of Link Travel Time |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105185103A CN105185103A (en) | 2015-12-23 |
CN105185103B true CN105185103B (en) | 2018-02-16 |
Family
ID=54907146
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510654369.9A Active CN105185103B (en) | 2015-10-10 | 2015-10-10 | A kind of management control method of Link Travel Time |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105185103B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106781468B (en) | 2016-12-09 | 2018-06-15 | 大连理工大学 | Link Travel Time Estimation method based on built environment and low frequency floating car data |
CN109035815A (en) * | 2018-08-16 | 2018-12-18 | 公安部交通管理科学研究所 | Traffic signal optimization system and operation method based on multi-source traffic big data |
CN111696343B (en) * | 2019-03-12 | 2022-04-05 | 北京嘀嘀无限科技发展有限公司 | Track data processing method and device |
CN110220526B (en) * | 2019-05-15 | 2023-07-04 | 浙江工业大学之江学院 | ANPR vehicle guidance scheme generation method based on path time value |
CN110796885B (en) * | 2019-11-06 | 2020-11-13 | 北京交通大学 | Parking guidance method and parking lot guidance system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101739814A (en) * | 2009-11-06 | 2010-06-16 | 吉林大学 | SCATS coil data-based traffic state online quantitative evaluation and prediction method |
CN101739825A (en) * | 2009-11-06 | 2010-06-16 | 吉林大学 | GPS floating vehicle-based traffic data fault identification and recovery method |
CN101739815A (en) * | 2009-11-06 | 2010-06-16 | 吉林大学 | On-line recognition method of road traffic congestion state |
CN102930718A (en) * | 2012-09-20 | 2013-02-13 | 同济大学 | Intermittent flow path section travel time estimation method based on floating car data and coil flow fusion |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101112191B1 (en) * | 2010-04-20 | 2012-03-13 | 한국항공대학교산학협력단 | Agent-based travel time estimation apparatus and method thereof |
-
2015
- 2015-10-10 CN CN201510654369.9A patent/CN105185103B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101739814A (en) * | 2009-11-06 | 2010-06-16 | 吉林大学 | SCATS coil data-based traffic state online quantitative evaluation and prediction method |
CN101739825A (en) * | 2009-11-06 | 2010-06-16 | 吉林大学 | GPS floating vehicle-based traffic data fault identification and recovery method |
CN101739815A (en) * | 2009-11-06 | 2010-06-16 | 吉林大学 | On-line recognition method of road traffic congestion state |
CN102930718A (en) * | 2012-09-20 | 2013-02-13 | 同济大学 | Intermittent flow path section travel time estimation method based on floating car data and coil flow fusion |
Non-Patent Citations (1)
Title |
---|
基于多源数据的交通状态监测与预测方法研究;李琦;《中国优秀博士学位论文全文数据库》;20130815;正文第26-27、48-49、70页 * |
Also Published As
Publication number | Publication date |
---|---|
CN105185103A (en) | 2015-12-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105185103B (en) | A kind of management control method of Link Travel Time | |
CN108805348B (en) | Method and device for controlling and optimizing intersection signal timing | |
WO2018149308A1 (en) | Road traffic optimization method and device and electronic apparatus | |
EP2427726B1 (en) | Methods and systems for creating digital transportation networks | |
CN102737510B (en) | Real-time traffic condition acquisition method based on mobile intelligent terminal | |
WO2018149307A1 (en) | Method and apparatus for analyzing traffic conditions and electronic device | |
US10475336B2 (en) | System for forecasting traffic condition pattern by analysis of traffic data and forecasting method thereof | |
CN106971535B (en) | A kind of urban traffic blocking index computing platform based on Floating Car GPS real time data | |
US8260532B2 (en) | Traffic probe in-vehicle map-based process to reduce data communications and improve accuracy | |
CN109615851B (en) | Sensing node selection method based on key road section in crowd sensing system | |
CN108896064A (en) | The arrival time Prediction System applied to GPS navigation system based on information sharing | |
CN105590452B (en) | Automatically generate the method and its device of electronic road form | |
CN106023620A (en) | Big-data-based traffic light prompting system | |
CN105096590B (en) | Traffic information creating method and traffic information generating device | |
CN109360420B (en) | Public traffic big data processing system and method | |
CN112652172B (en) | Road section traffic volume analysis method based on vehicle GPS track | |
CN104318768A (en) | Hadoop based self-adaption traffic information tiled map generating system and method | |
CN108171968A (en) | The road condition analyzing system and method for position data based on mobile terminal device signaling | |
CN108390928A (en) | A kind of Destination Management platform based on big data | |
WO2018045974A1 (en) | Method, apparatus, and system for determining traffic light timing | |
CN117546218A (en) | Distributed multitasking machine learning for traffic prediction | |
JP2022000801A (en) | Vehicle navigation method, vehicle navigation device, electronic device, storage medium, vehicle navigation system, cloud control platform, and computer program | |
CN109493601B (en) | Bus branch line setting method | |
CN110879862B (en) | Vehicle Information Query System Based on Internet of Things | |
Gong et al. | Estimating link travel time with sparse GPS data on highway corridors |
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 | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210623 Address after: 13 / F, 525 Jianguo East Road, Huangpu District, Shanghai 200025 Patentee after: SHANGHAI URBAN TRANSPORTATION DESIGN INSTITUTE Co.,Ltd. Address before: 200092 No. two, 901 North Road, Yangpu District, Shanghai, Zhongshan Patentee before: SHANGHAI MUNICIPAL ENGINEERING DESIGN INSTITUTE (Group) Co.,Ltd. |