CN109308805A - A kind of road network MFD estimating and measuring method based on self-adaptive weighted average data fusion - Google Patents
A kind of road network MFD estimating and measuring method based on self-adaptive weighted average data fusion Download PDFInfo
- Publication number
- CN109308805A CN109308805A CN201810948765.6A CN201810948765A CN109308805A CN 109308805 A CN109308805 A CN 109308805A CN 201810948765 A CN201810948765 A CN 201810948765A CN 109308805 A CN109308805 A CN 109308805A
- Authority
- CN
- China
- Prior art keywords
- traffic
- road network
- mfd
- data
- network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to nerual network technique method fields, more specifically, it is related to a kind of road network MFD estimating and measuring method based on self-adaptive weighted average data fusion, a kind of road network MFD estimating and measuring method based on self-adaptive weighted average data fusion is provided, LDD is estimated into method and the FCD estimation resulting traffic data of method combines consideration, with 100% networking car data (Network Car Data under car networking, NCD) traffic parameter estimated is inspection data, introduce dynamic error, the self-adaptive weighted average data fusion model of the network power magnitude of traffic flow and network power traffic density is established respectively, to can get the more accurate network power magnitude of traffic flow and network power traffic density, to more accurately estimate road network MFD.In the section for having fixed detector, self-adaptive weighted average data fusion is carried out to fixed detector and Floating Car traffic data collected；In the section of not fixed detector, the section weighting magnitude of traffic flow and weighting traffic density are extracted with the traffic data that Floating Car acquires, estimates road network MFD.
Description
Technical field
The present invention relates to nerual network technique method fields, are based on self-adaptive weighted average number more particularly, to one kind
According to the road network MFD estimating and measuring method of fusion.
Background technique
Urban traffic blocking brings huge challenge to urban transportation.How to alleviate Urban Traffic Jam Based to have become
The focus on research direction of numerous scholars, scholars propose various traffic control strategies, are effectively relieved to a certain extent
Urban traffic blocking, but as the continuous increase of wagon flow, traffic congestion grow in intensity, various traffic control strategies will be not suitable for.
In the recent period, two scholars [iiiiiiivv~vi] of Daganzo and Geroliminis disclose macroscopical parent map (Macroscopic
Fundamental Diagrams, MFD) outness, they think that MFD not only can be to city road network from macroscopic aspect
It is described, and can monitor and predict road grid traffic operating status, to implement traffic to supersaturated road network from macroscopic aspect
Control strategy provides new approaches, however the MFD for how obtaining city road network becomes a big difficulty again.Road network MFD can lead at present
The traffic data of fixed detector (such as toroidal inductor, microwave, video detector) or the acquisition of GPS Floating Car is crossed to estimate
It surveys.Fixed detector data estimation method (Loop Detector Data, LDD estimate method) is the fixation by being mounted on section
Detector acquires traffic data in real time, then utilizes MFD correlation theory, estimates road network MFD.Floating car data estimates method
(Floating Car Data, FCD estimate method) is by being equipped with the vehicle of GPS car-mounted terminal (such as taxi, public transport), in fact
When acquire road network Floating Car traffic data, using Edie (1963) [vii] propose wheelpath estimate method, obtain road network and add
The magnitude of traffic flow and weighting traffic density are weighed, to estimate road network MFD.Some scholars study two kinds of estimating and measuring methods, such as
(Courbon et al., 2011) [viii] is to three kinds of estimation sides road network MFD such as theoretical analysis, LDD estimation method, FCD estimation methods
Method is compared analysis, studies fixed detector position and the harmonious influence to MFD estimation of Floating Car covering.(Nagle etc.
People, 2013) when [ix] proposes Floating Car coverage rate at least 15%, method is estimated using FCD, can get accurate road network MFD,
But premise in this way is to must be known by Floating Car coverage rate, and Floating Car is uniform in the distribution of road network.(Lu etc.
People, 2013) [x] utilizes practical intersection video detection data and taxi floating data, estimation road network MFD, and finds data
What the estimation result (Leclercq et al., 2014) [xi] that processing time interval will affect road network MFD was obtained using practical road network
Traffic data compares LDD estimation two kinds of road network MFD estimating and measuring method differences such as method and FCD estimation method, and has inquired into two methods
The scope of application.(Du et al., 2016) [xii] is directed to Floating Car coverage rate non-uniform actual conditions in road network, it is assumed that certain
Floating Car ratio of a specific starting point into terminal is known, Floating Car ratio of equal value needed for estimating road grid traffic flow,
And using a small number of floating car data estimation road grid traffic flows and traffic density, to estimate road network MFD.But actually fixed inspection
The traffic data of part way can only be collected by surveying device, and the section for not installing fixed detector can not then obtain traffic data, and
The coverage rate of GPS Floating Car is low, and traffic data amount is insufficient, and there are biggish errors by the road network MFD estimated.(Amb ü hl L etc.
People, 2016) [xiii] all estimates road network MFD only with above-mentioned one of method for most of documents, seldom ties the two
Altogether the case where, proposes above two method carrying out data fusion, thus the more accurate road network MFD of estimation, but its
Data anastomosing algorithm is to obtain by a large amount of empirical experimentations, and do not have general applicability.(Jin Sheng et al., 2018) [xiv]
It is proposed the data of microwave detector and Car license recognition are merged, construct MFD estimating and measuring method, but its data fusion model with
The ratio that road section length where detector accounts for road network total length is weight, does not consider traffic flow discreteness and detector performance to friendship
The influence of logical parameters precision.
Summary of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide one kind to be based on self-adaptive weighted average data fusion
Road network MFD estimating and measuring method, by LDD estimate method and FCD estimation the resulting traffic data of method combine consideration, under car networking
The traffic parameter of 100% networking car data (Network Car Data, NCD) estimation is inspection data, introduces dynamic error, point
The self-adaptive weighted average data fusion model of the network power magnitude of traffic flow and network power traffic density is not established, in order to obtain
The more accurate network power magnitude of traffic flow and network power traffic density are obtained, to more accurately estimate road network MFD.Having
The section of fixed detector carries out self-adaptive weighted average data to fixed detector and Floating Car traffic data collected and melts
It closes, obtains the section weighting magnitude of traffic flow and weighting traffic density；In the section of not fixed detector, the friendship acquired with Floating Car
Logical data extract the section weighting magnitude of traffic flow and weighting traffic density.The last network power magnitude of traffic flow according to data fusion and
Traffic density is weighted, road network MFD is estimated.
In order to solve the above technical problems, the technical solution adopted by the present invention is that:
A kind of road network MFD estimating and measuring method based on self-adaptive weighted average data fusion is provided, the specific steps are as follows:
(1) LDD is estimated into method and the resulting traffic data of FCD estimation method combines, to 100% networking car data under car networking
The traffic parameter of estimation is inspection data,
(2) after step (1), dynamic error is introduced, in the section for being equipped with fixed detector, to fixed detector and is floated
Motor-car traffic data collected carries out self-adaptive weighted average data fusion, obtains the section weighting magnitude of traffic flow and weighting traffic
Density；In the section of not fixed detector, the section weighting magnitude of traffic flow and weighting are extracted with the traffic data that Floating Car acquires
Traffic density；
(3) after step (2), the network power magnitude of traffic flow is established respectively and the adaptive of network power traffic density adds
Weight average data fusion model obtains the accurate network power magnitude of traffic flow and network power traffic density；
(4) after step (3), according to the network power magnitude of traffic flow and weighting traffic density of data fusion, estimate road
Net MFD.
Preferably, in step (1), LDD estimates method, and specific step is as follows:
(1) each section is mounted on fixed detector (such as ring coil detector, video acquisition detection first in road network
Device etc.), then the road section traffic volume flow and traffic density that can be directly acquired by fixed detector estimate road network MFD,
(2) after step (1), the MFD correlation reason that is proposed according to (Geroliminis and Daganzo, 2008)
By, it is known that:
In formula: N --- road network move vehicle number (veh)；
qw、kw、ow--- the network power magnitude of traffic flow (veh/h), network power traffic density (veh/km), network power
Time occupancy；
i、li--- the length (km) of section i and the section；
qi、ki、oi--- flow (veh/h), density (vehk/km) and the time occupancy of section i；
The average vehicle commander of s --- vehicle.
Preferably, in step (1), FCD estimates method, and specific step is as follows:
When known to the track of all vehicles of road network, the magnitude of traffic flow and traffic density of road network can be calculated according to wheel paths,
Formula is as follows:
In formula: k --- road grid traffic density, veh/km；
Q --- road grid traffic flow, veh/h；
The vehicle number recorded in m --- collection period T；
N --- section sum in road network；
tj--- the running time of jth vehicle, s in collection period T；
li--- the length in the i-th section, m；
T --- collection period, s；
Dj --- the operating range of jth vehicle, m in collection period T；
Tm--- the sum of the running time of all vehicles of road network, s in collection period T.
Dm--- the sum of the operating range of all vehicles of road network, s in collection period T.
If being actually difficult to obtain the driving status (operating range and running time) of all vehicles, with regard to fetching portion Floating Car
Driving status；Nagle (2014) puts forward a hypothesis known to ratio ρ of the Floating Car in road network, and uniform in each region of road network
Distribution, then can estimate the magnitude of traffic flow and traffic density of road network, formula is as follows according to above-mentioned formula:
In formula:--- the road grid traffic density estimated using floating car data, veh/km；
--- the road grid traffic flow estimated using floating car data, veh/h；
The Floating Car number recorded in m ' --- collection period T；
N --- section sum in road network
tj′--- the running time of jth in collection period T ' Floating Car, s；
li--- the length in the i-th section, m；
T --- collection period, s；
dj′--- the operating range of jth in collection period T ' vehicle, m；.
Preferably, in step (2), in weighted mean method, the step of weighted factor is most critical is determined, it is flat based on weighting
The calculation formula of the multisource data fusion value of equal method are as follows:
Wherein, yi(t) --- in the traffic parameter that i-th kind of detection mode of t moment obtains；
wi(t) --- the weighted factor of detection mode in t moment i-th.
Preferably, in step (2), self-adaptive weighted average data are melted in model,
The determination to adaptive weighted factor is first had to, specific as follows:
In self-adaptive weighted average method, dynamic error e is introducedd,i(t-1), expression formula are as follows:
In formula, ed,i(t-1) --- in the dynamic error of i-th kind of detection method of t-1 period；
K --- the k period before the t period；
ear,i(t-k) --- the absolute relative error of detection mode, expression formula in the t-k period i-th are as follows:
Wherein, y (t-1) --- it is the real data of t-1 period；
yi(t-1) --- it is the estimated data of i-th kind of detection method of t-1 period；
The weighted factor of various detection modes becomes larger with becoming smaller for dynamic error, therefore, is determined with inverse proportion method each
The initial weighting factor of detection mode, expression formula are as follows:
In order to which the sum of weighted factor for guaranteeing all detection modes is 1, be normalized, obtain final weighting because
Son are as follows:
Preferably, in step (2), self-adaptive weighted average data are melted in model, the crucial ginseng of two of road network MFD estimation
Number is the network power magnitude of traffic flow and network power traffic density, it is therefore desirable to network power magnitude of traffic flow Fusion Model and road network
Traffic density Fusion Model is weighted, specific method and step is as follows:
A) fixed detector estimation method and the resulting road network MFD ginseng of floating car data estimation method before the input t-1 moment
Number；
B) the MFD parameter obtained using 100% networking vehicle, using formula (9), calculates absolute relative error as real data；
C) formula (8) are utilized, calculates dynamic error；
D) formula (10) are utilized, determines initial weighting factor；
E) formula (11) are utilized, normalizes weighted factor；
F) input t moment fixed detector estimation method and Floating Car acquire the resulting MFD parameter of estimation method；
G) the MFD parameter of t moment estimation and normalization weighted factor input adaptive are weighted and averaged Fusion Model；
8) the MFD parameter as a result, after obtaining t moment data fusion is exported.
In addition, estimating to verify LDD estimation method, FCD estimation method, self-adaptive weighted average data fusion model and NCD
The resulting road network MFD otherness of method, adoption status ratio (Traffic State Ratio, R) assess the roads of various estimating and measuring methods
MFD otherness is netted, formula is as follows:
In formula, Run--- the road network MFD parameter state ratio under non-congestion status；
Rco--- the road network MFD parameter state ratio under congestion status；
kt,qt--- the network power traffic density and the network power magnitude of traffic flow of t moment；
kc, qc--- the critical weighting traffic density of road network and the critical weighting magnitude of traffic flow of road network；
kj--- road network obstruction density, i.e., the network power traffic density when weighting magnitude of traffic flow is 0.
Therefore, road network MFD otherness can be understood as the difference of state ratio, and definition Δ is the different resulting road networks of estimation method
MFD difference, Δ is bigger to illustrate that road network MFD difference is bigger, otherwise difference is smaller, expression formula are as follows:
In formula, --- the non-congestion of road network MFD and congestion status ratio under car networking environment；
--- the non-congestion of road network MFD and congestion status ratio under self-adaptive weighted average data fusion；
--- the non-congestion of road network MFD and congestion status ratio under floating car data estimation method；
--- the non-congestion of road network MFD and congestion status ratio under fixed detector estimation method.
Compared with prior art, the beneficial effects of the present invention are:
The present invention provides a kind of road network MFD estimating and measuring method based on self-adaptive weighted average data fusion, and LDD is estimated
Method and the FCD estimation resulting traffic data of method combine consideration, with 100% networking car data (Network Car under car networking
Data, NCD) estimation traffic parameter be inspection data, introduce dynamic error, establish the network power magnitude of traffic flow and road network respectively
The self-adaptive weighted average data fusion model of traffic density is weighted, to can get the more accurate network power magnitude of traffic flow
With network power traffic density, thus more accurately estimate road network MFD.In the section for having fixed detector, to fixed test
Device and Floating Car traffic data collected carry out self-adaptive weighted average data fusion, obtain the section weighting magnitude of traffic flow and add
Weigh traffic density；In the section of not fixed detector, section is extracted with the traffic data that Floating Car acquires and weights the magnitude of traffic flow
With weighting traffic density.The last network power magnitude of traffic flow and weighting traffic density according to data fusion, estimates road network MFD.
Detailed description of the invention
Fig. 1 is the self-adaptive weighted average data fusion flow chart of embodiment network power magnitude of traffic flow Fusion Model.
Fig. 2 is Tianhe District core road network layout.
Fig. 3 is the schematic diagram that the network power magnitude of traffic flow of various estimating and measuring methods compares.
Fig. 4 is the schematic diagram that the network power traffic density of various estimating and measuring methods compares.
Fig. 5 is the schematic diagram of the resulting road network MFD of various estimating and measuring methods.
Fig. 6 is the schematic diagram of the resulting road network MFD of various estimating and measuring methods.
Fig. 7 is the schematic diagram of the resulting road network MFD state vs of each estimation method.
Fig. 8 is the schematic diagram of each estimation method and the resulting road network MFD difference value of NCD method.
Specific embodiment
The present invention is further illustrated With reference to embodiment.Wherein, attached drawing only for illustration,
What is indicated is only schematic diagram, rather than pictorial diagram, should not be understood as the limitation to this patent；Reality in order to better illustrate the present invention
Example is applied, the certain components of attached drawing have omission, zoom in or out, and do not represent the size of actual product；To those skilled in the art
For, the omitting of some known structures and their instructions in the attached drawings are understandable.
The same or similar label correspond to the same or similar components in the attached drawing of the embodiment of the present invention；It is retouched in of the invention
In stating, it is to be understood that if the orientation or positional relationship for having the instructions such as term " on ", "lower", "left", "right" is based on attached drawing
Shown in orientation or positional relationship, be merely for convenience of description of the present invention and simplification of the description, rather than indication or suggestion is signified
Device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore positional relationship is described in attached drawing
Term only for illustration, should not be understood as the limitation to this patent, for the ordinary skill in the art, can
To understand the concrete meaning of above-mentioned term as the case may be.
Embodiment
As Fig. 1 to 7 show a kind of road network MFD estimating and measuring method based on self-adaptive weighted average data fusion of the present invention
Embodiment, the specific steps are as follows:
(1) LDD is estimated into method and the resulting traffic data of FCD estimation method combines, to 100% networking car data under car networking
The traffic parameter of estimation is inspection data,
(2) after step (1), dynamic error is introduced, in the section for being equipped with fixed detector, to fixed detector and is floated
Motor-car traffic data collected carries out self-adaptive weighted average data fusion, obtains the section weighting magnitude of traffic flow and weighting traffic
Density；In the section of not fixed detector, the section weighting magnitude of traffic flow and weighting are extracted with the traffic data that Floating Car acquires
Traffic density；
(3) after step (2), the network power magnitude of traffic flow is established respectively and the adaptive of network power traffic density adds
Weight average data fusion model obtains the accurate network power magnitude of traffic flow and network power traffic density；
(4) after step (3), according to the network power magnitude of traffic flow and weighting traffic density of data fusion, estimate road
Net MFD.
Wherein, in step (1), LDD estimates method, and specific step is as follows:
(1) each section is mounted on fixed detector (such as ring coil detector, video acquisition detection first in road network
Device etc.), then the road section traffic volume flow and traffic density that can be directly acquired by fixed detector estimate road network MFD,
(2) after step (1), the MFD correlation reason that is proposed according to (Geroliminis and Daganzo, 2008)
By[1~6], it is known that:
In formula: N --- road network move vehicle number (veh)；
qw、kw、ow--- the network power magnitude of traffic flow (veh/h), network power traffic density (veh/km), network power
Time occupancy；
i、li--- the length (km) of section i and the section；
qi、ki、oi--- flow (veh/h), density (vehk/km) and the time occupancy of section i；
The average vehicle commander of s --- vehicle.
In addition, FCD estimates method, and specific step is as follows in step (1):
When known to the track of all vehicles of road network, the magnitude of traffic flow and traffic density of road network can be calculated according to wheel paths,
Formula is as follows:
In formula: k --- road grid traffic density, veh/km；
Q --- road grid traffic flow, veh/h；
The vehicle number recorded in m --- collection period T；
N --- section sum in road network；
tj--- the running time of jth vehicle, s in collection period T；
li--- the length in the i-th section, m；
T --- collection period, s；
Dj --- the operating range of jth vehicle, m in collection period T；
Tm--- the sum of the running time of all vehicles of road network, s in collection period T.
Dm--- the sum of the operating range of all vehicles of road network, s in collection period T.
If being actually difficult to obtain the driving status (operating range and running time) of all vehicles, with regard to fetching portion Floating Car
Driving status；Nagle (2014) puts forward a hypothesis known to ratio ρ of the Floating Car in road network, and uniform in each region of road network
Distribution, then can estimate the magnitude of traffic flow and traffic density of road network, formula is as follows according to above-mentioned formula:
In formula:--- the road grid traffic density estimated using floating car data, veh/km；
--- the road grid traffic flow estimated using floating car data, veh/h；
The Floating Car number recorded in m' --- collection period T；
N --- section sum in road network
tj'--- the running time of jth in collection period T ' Floating Car, s；
li--- the length in the i-th section, m；
T --- collection period, s；
dj'--- the operating range of jth in collection period T ' vehicle, m；.
Wherein, in step (2), in weighted mean method, the step of weighted factor is most critical is determined, based on weighted average
The calculation formula of the multisource data fusion value of method are as follows:
Wherein, yi(t) --- in the traffic parameter that i-th kind of detection mode of t moment obtains；
wi(t) --- the weighted factor of detection mode in t moment i-th.
In addition, self-adaptive weighted average data are melted in model in step (2),
The determination to adaptive weighted factor is first had to, specific as follows:
In self-adaptive weighted average method, dynamic error e is introducedd,i(t-1), expression formula are as follows:
In formula, ed,i(t-1) --- in the dynamic error of i-th kind of detection method of t-1 period；
K --- the k period before the t period；
ear,i(t-k) --- the absolute relative error of detection mode, expression formula in the t-k period i-th are as follows:
Wherein, y (t-1) --- it is the real data of t-1 period；
yi(t-1) --- it is the estimated data of i-th kind of detection method of t-1 period；
The weighted factor of various detection modes becomes larger with becoming smaller for dynamic error, therefore, is determined with inverse proportion method each
The initial weighting factor of detection mode, expression formula are as follows:
In order to which the sum of weighted factor for guaranteeing all detection modes is 1, be normalized, obtain final weighting because
Son are as follows:
Wherein, in step (2), self-adaptive weighted average data are melted in model, two key parameters of road network MFD estimation
For the network power magnitude of traffic flow and network power traffic density, it is therefore desirable to which network power magnitude of traffic flow Fusion Model and road network add
Traffic density Fusion Model is weighed, specific method and step is as follows:
A) fixed detector estimation method and the resulting road network MFD ginseng of floating car data estimation method before the input t-1 moment
Number；
B) the MFD parameter obtained using 100% networking vehicle, using formula (9), calculates absolute relative error as real data；
C) formula (8) are utilized, calculates dynamic error；
D) formula (10) are utilized, determines initial weighting factor；
E) formula (11) are utilized, normalizes weighted factor；
F) input t moment fixed detector estimation method and Floating Car acquire the resulting MFD parameter of estimation method；
G) the MFD parameter of t moment estimation and normalization weighted factor input adaptive are weighted and averaged Fusion Model；
H) the MFD parameter as a result, after obtaining t moment data fusion is exported.
In addition, estimating to verify LDD estimation method, FCD estimation method, self-adaptive weighted average data fusion model and NCD
The resulting road network MFD otherness of method, adoption status ratio (Traffic State Ratio, R) assess the roads of various estimating and measuring methods
MFD otherness is netted, formula is as follows:
In formula, Run--- the road network MFD parameter state ratio under non-congestion status；
Rco--- the road network MFD parameter state ratio under congestion status；
kt,qt--- the network power traffic density and the network power magnitude of traffic flow of t moment；
kc, qc--- the critical weighting traffic density of road network and the critical weighting magnitude of traffic flow of road network；
kj--- road network obstruction density, i.e., the network power traffic density when weighting magnitude of traffic flow is 0.
Therefore, road network MFD otherness can be understood as the difference of state ratio, and definition Δ is the different resulting road networks of estimation method
MFD difference, Δ is bigger to illustrate that road network MFD difference is bigger, otherwise difference is smaller, expression formula are as follows:
In formula, --- the non-congestion of road network MFD and congestion status ratio under car networking environment；
--- the non-congestion of road network MFD and congestion status ratio under self-adaptive weighted average data fusion；
--- the non-congestion of road network MFD and congestion status ratio under floating car data estimation method；
--- the non-congestion of road network MFD and congestion status ratio under fixed detector estimation method.
The present embodiment chooses reported in Tianhe district of Guangzhou core road network intersection group as research object, the road network by Milky Way road,
The trunk roads such as Milky Way East Road, Milky Way North Road, sport West Road, sport East Road and partial branch composition, including more than 7 level-crossings
Mouthful, more than 20 entrances, as shown in Figure 2.Traffic flow data is with SCATS traffic signal control system in the height on the 6th of August in 2017
Based on peak hour (18:00-19:00) institute detection data.
(1) using reported in Tianhe district of Guangzhou core road network intersection group as test block, according to above-mentioned basic data, Vissim is utilized
Traffic simulation software establishes Traffic Flow Simulation Models, and 5% vehicle is set as Floating Car, is arranged in each section middle position and detects
100% vehicle is set as networking vehicle (special Floating Car) by device, constructs car networking Environmental Communication model, adaptive for obtaining
The verification data of data Fusion Model should be weighted and averaged.In order to simulate road network from ebb-peak-congestion whole process, at this
In road network simulation model, traffic flow is simulated since ebb, and each section in road network boundary is driven into the volume of traffic and increased every 900s
100pcu/h acquires 1 data every 300s, acquires 100 times altogether until emulating 30000s altogether to the hypersaturated state on peak
Data.
(2) assume Floating Car and networking vehicle every the data such as 5 seconds uploads vehicle number, running time, operating ranges, foundation
FCD estimates method, calculates Floating Car network power magnitude of traffic flow qFCD every 300 seconds, Floating Car network power traffic density
KFCD, networking vehicle network power magnitude of traffic flow qNCD, networking vehicle network power traffic density kNCD；Equally acquired every 300 seconds
The road section traffic volume density of each section detector, road section traffic volume flow estimate method according to LDD, calculate the network power every 300 seconds
Magnitude of traffic flow qLDD and network power traffic density kLDD.
(3) according to self-adaptive weighted average data fusion process, using macroprogramming to each interval time in Excel
LDD estimates method, the resulting network power magnitude of traffic flow of FCD estimation method and network power traffic density and carries out self-adaptive weighted average
Data fusion, the day part road network MFD network power magnitude of traffic flow and network power traffic density after finally obtaining data fusion.
(4) the road network MFDF based on FCD estimation is generated respectively, based on the road network MFDL of LDD estimation, based on adaptive weighted
The MFDAWA of average data fusion estimation generates fitting function based on the road network standard MFDN of networking wheel paths, calculates each quasi-
Close the critical weighting traffic density of function, the critical weighting magnitude of traffic flow, jam density, road network MFD resulting to various estimation methods
Carry out difference analysis.
Data comparison is carried out to qAWA, qFCD, qLDD, the qNCD in 100 periods, as shown in figure 3, to 100 periods
KAWA, kFCD, kLDD, kNCD carry out data comparison, as shown in Figure 4.From Fig. 3-4 it is found that FCD estimates the resulting network power of method
The magnitude of traffic flow and network power traffic density amplitude of variation are larger, this is because Floating Car negligible amounts；LDD estimates method and Che Lian
Net estimates the resulting network power magnitude of traffic flow and the variation of network power traffic density is relatively stable, and variation tendency more one
It causes, with the passage of simulation time, the network power magnitude of traffic flow and network power traffic density are gradually increased, then at one section
It is interior to maintain more stable value, next sharply decline again, but the resulting network power magnitude of traffic flow of LDD estimation method and road network add
Power traffic density is respectively less than the network power magnitude of traffic flow and network power traffic density of NCD estimation, this is because when reaching number
When according to acquisition interval, small part vehicle not yet reaches fixed detector.
Analysis emulation data, obtain the absolute relative error of qLDD, qFCD, qAWA and qNCD average value and kLDD,
The average value of the absolute relative error of kFCD, kAWA and kNCD, as shown in table 1,2.
Average value of the table 1 relative to the phase error absolute value of qNCD
Average value of the table 2 relative to the phase error absolute value of kNCD
From table 1, table 2 it is found that the average value of the phase error absolute value of qFCD and kFCD is maximum, respectively 11.52% He
12.26%；The average value of the phase error absolute value of qLDD and kLDD takes second place, and respectively 8.22% and 11.54%；Through adaptive
After data fusion should be weighted and averaged, the average value of the phase error absolute value of qAWA and kAWA is respectively 6.51% and 9.56%,
Closest to standard value qNCD and kNCD.
Using various estimation data, the road network MFDF based on FCD estimation method is generated, the road network MFDL of method is estimated based on LDD,
Based on the MFDAWA of self-adaptive weighted average data fusion estimation, based on the road network standard MFDN of networking wheel paths, such as Fig. 5 institute
Show.
As can be seen from Figure 5, biggish discreteness is presented in the scatterplot of MFDF, and the scatterplot of MFDL, MFDAWA, MFDN are more concentrated,
And as the passage of simulation time, the network power magnitude of traffic flow and network power traffic density are gradually increased, network power
For traffic density since 70veh/km, road network maintains the higher weighting magnitude of traffic flow, as network power traffic density increases,
The network power magnitude of traffic flow sharply declines, and hypersaturated state occurs in road network.Road network MFD has also appeared " hysteresis phenomenon " simultaneously, accords with
The characteristic of combining net MFD.Data fitting is carried out to the scatterplot of each MFD, obtains fitting function, calculate various fitting functions it is critical plus
Traffic density, the critical weighting magnitude of traffic flow and jam density are weighed, as shown in table 3.
The fitting function of each MFD of table 3
Using formula 12, formula 13 calculates the state ratio R and difference value Δ of the resulting road network MFD of various estimating and measuring methods, such as
Shown in Fig. 6, Fig. 7.
From Fig. 6, Fig. 7 it is found that FCD estimation method road network MFD state ratio and difference value variation it is bigger, LCD estimate method and
The state ratio of self-adaptive weighted average number fusion and difference value variation are more stable.Calculate the road network MFD difference value of each estimation method
Mean value, maximum and the minimum of absolute value, as shown in table 4:
Respectively estimation method and NCD estimate the resulting road network MFD difference value of method to table 4
As known from Table 4, FCD estimates the resulting road network MFD difference maximum of method, | Δ | mean value 0.0895, LDD estimate method
The road network MFD difference estimated with AWA data fusion method is smaller, but the closer mark of road network MFD that AWA data fusion method is estimated
Quasi- road network MFD, | Δ | mean value 0.0615.It can be seen that the road network MFD after self-adaptive weighted average data fusion is more quasi-
Really.
Obviously, the above embodiment of the present invention be only to clearly illustrate example of the present invention, and not be pair
The restriction of embodiments of the present invention.For those of ordinary skill in the art, may be used also on the basis of the above description
To make other variations or changes in different ways.There is no necessity and possibility to exhaust all the enbodiments.It is all this
Made any modifications, equivalent replacements, and improvements etc., should be included in the claims in the present invention within the spirit and principle of invention
Protection scope within.
Claims (6)
1. a kind of road network MFD estimating and measuring method based on self-adaptive weighted average data fusion, which is characterized in that specific steps are such as
Under:
(1) LDD is estimated into method and the resulting traffic data of FCD estimation method combines, to 100% networking car data estimation under car networking
Traffic parameter be inspection data,
(2) after step (1), dynamic error is introduced, in the section for being equipped with fixed detector, to fixed detector and Floating Car
Traffic data collected carries out self-adaptive weighted average data fusion, obtains the section weighting magnitude of traffic flow and weighting traffic is close
Degree；In the section of not fixed detector, the section weighting magnitude of traffic flow is extracted with the traffic data that Floating Car acquires and weighting is handed over
Flux density；
(3) after step (2), the network power magnitude of traffic flow is established respectively and the adaptive weighted of network power traffic density is put down
Equal data fusion model obtains the accurate network power magnitude of traffic flow and network power traffic density；
(4) after step (3), according to the network power magnitude of traffic flow and weighting traffic density of data fusion, estimate road network
MFD。
2. the road network MFD estimating and measuring method based on self-adaptive weighted average data fusion according to claim 1, which is characterized in that
In step (1), LDD estimates method, and specific step is as follows:
(1) each section is mounted on fixed detector (such as ring coil detector, video acquisition detector first in road network
Deng), then the road section traffic volume flow and traffic density that can be directly acquired by fixed detector estimate road network MFD,
(2) after step (1), the MFD correlation theory [1 that is proposed according to (Geroliminis and Daganzo, 2008)
~6], it is known that:
In formula: N --- road network move vehicle number (veh)；
qw、kw、ow--- the network power magnitude of traffic flow (veh/h), network power traffic density (veh/km), network power time
Occupation rate；
i、li--- the length (km) of section i and the section；
qi、ki、oi--- flow (veh/h), density (vehk/km) and the time occupancy of section i；
The average vehicle commander of s --- vehicle.
3. the road network MFD estimating and measuring method according to claim 2 based on self-adaptive weighted average data fusion, feature exist
In in step (1), FCD estimates method, and specific step is as follows:
When known to the track of all vehicles of road network, the magnitude of traffic flow and traffic density of road network, formula can be calculated according to wheel paths
It is as follows:
In formula: k --- road grid traffic density, veh/km；
Q --- road grid traffic flow, veh/h；
The vehicle number recorded in m --- collection period T；
N --- section sum in road network；
tj--- the running time of jth vehicle, s in collection period T；
li--- the length in the i-th section, m；
T --- collection period, s；
Dj --- the operating range of jth vehicle, m in collection period T；
Tm--- the sum of the running time of all vehicles of road network, s in collection period T.
Dm--- the sum of the operating range of all vehicles of road network, s in collection period T.
If being actually difficult to obtain the driving status (operating range and running time) of all vehicles, with regard to the row of fetching portion Floating Car
Sail state；Nagle (2014) puts forward a hypothesis known to ratio p of the Floating Car in road network, and is uniformly distributed in each region of road network,
So according to above-mentioned formula, the magnitude of traffic flow and traffic density of road network can be estimated, formula is as follows:
In formula:--- the road grid traffic density estimated using floating car data, veh/km；
--- the road grid traffic flow estimated using floating car data, veh/h；
The Floating Car number recorded in m' --- collection period T；
N --- section sum in road network
tj'--- the running time of jth in collection period T ' Floating Car, s；
li--- the length in the i-th section, m；
T --- collection period, s；
dj'--- the operating range of jth in collection period T ' vehicle, m；.
4. the road network MFD estimating and measuring method according to claim 3 based on self-adaptive weighted average data fusion, feature exist
In in step (2), in weighted mean method, determining the step of weighted factor is most critical, the multi-source number based on weighted mean method
According to the calculation formula of fusion value are as follows:
Wherein, yi(t) --- in the traffic parameter that i-th kind of detection mode of t moment obtains；
wi(t) --- the weighted factor of detection mode in t moment i-th.
5. the road network MFD estimating and measuring method according to claim 3 based on self-adaptive weighted average data fusion, feature exist
In, in step (2), self-adaptive weighted average data are melted in model,
The determination to adaptive weighted factor is first had to, specific as follows:
In self-adaptive weighted average method, dynamic error e is introducedd,i(t-1), expression formula are as follows:
In formula, ed,i(t-1) --- in the dynamic error of i-th kind of detection method of t-1 period；
K --- the k period before the t period；
ear,i(t-k) --- the absolute relative error of detection mode, expression formula in the t-k period i-th are as follows:
Wherein, y (t-1) --- it is the real data of t-1 period；
yi(t-1) --- it is the estimated data of i-th kind of detection method of t-1 period；
The weighted factor of various detection modes becomes larger with becoming smaller for dynamic error, therefore, determines each detection with inverse proportion method
The initial weighting factor of mode, expression formula are as follows:
In order to which the sum of the weighted factor for guaranteeing all detection modes is 1, it is normalized, obtains final weighted factor
Are as follows:
6. the road network MFD estimating and measuring method according to claim 5 based on self-adaptive weighted average data fusion, feature exist
In in step (2), self-adaptive weighted average data are melted in model, and two key parameters of road network MFD estimation are network power
The magnitude of traffic flow and network power traffic density, it is therefore desirable to network power magnitude of traffic flow Fusion Model and network power traffic density
Fusion Model, specific method and step are as follows:
A) fixed detector estimation method and floating car data estimate the resulting road network MFD parameter of method before the input t-1 moment；
B) the MFD parameter obtained using 100% networking vehicle, using formula (9), calculates absolute relative error as real data；
C) formula (8) are utilized, calculates dynamic error；
D) formula (10) are utilized, determines initial weighting factor；
E) formula (11) are utilized, normalizes weighted factor；
F) input t moment fixed detector estimation method and Floating Car acquire the resulting MFD parameter of estimation method；
G) the MFD parameter of t moment estimation and normalization weighted factor input adaptive are weighted and averaged Fusion Model；
H) the MFD parameter as a result, after obtaining t moment data fusion is exported.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810948765.6A CN109308805A (en) | 2018-08-20 | 2018-08-20 | A kind of road network MFD estimating and measuring method based on self-adaptive weighted average data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810948765.6A CN109308805A (en) | 2018-08-20 | 2018-08-20 | A kind of road network MFD estimating and measuring method based on self-adaptive weighted average data fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109308805A true CN109308805A (en) | 2019-02-05 |
Family
ID=65223738
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810948765.6A Pending CN109308805A (en) | 2018-08-20 | 2018-08-20 | A kind of road network MFD estimating and measuring method based on self-adaptive weighted average data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109308805A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110232398A (en) * | 2019-04-24 | 2019-09-13 | 广东交通职业技术学院 | A kind of road network sub-area division and its appraisal procedure based on Canopy+Kmeans cluster |
| CN110675630A (en) * | 2019-10-08 | 2020-01-10 | 广东交通职业技术学院 | Method for determining minimum coverage rate of networked vehicles |
| CN110827540A (en) * | 2019-11-04 | 2020-02-21 | 黄传明 | Motor vehicle movement mode recognition method and system based on multi-mode data fusion |
| CN111127880A (en) * | 2019-12-16 | 2020-05-08 | 西南交通大学 | MFD-based grid network traffic performance analysis method |
| CN111739293A (en) * | 2020-06-10 | 2020-10-02 | 广东世纪高通科技有限公司 | Data fusion method and device |
| CN113506440A (en) * | 2021-09-08 | 2021-10-15 | 四川国蓝中天环境科技集团有限公司 | Traffic state estimation method for multi-source data fusion under Lagrange coordinate system |
| CN113947905A (en) * | 2021-10-19 | 2022-01-18 | 交通运输部公路科学研究所 | Traffic operation situation sensing method, module and system |
| CN114358416A (en) * | 2021-12-31 | 2022-04-15 | 广东工业大学 | Public transport road network partitioning method, system, equipment and medium based on multi-source traffic data |
| CN115641721A (en) * | 2022-12-06 | 2023-01-24 | 南京感动科技有限公司 | Multi-source traffic flow index fusion and road condition calculation method based on fusion index |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102646332A (en) * | 2011-02-21 | 2012-08-22 | 日电（中国）有限公司 | Traffic state estimation device and method based on data fusion |
| CN105355049A (en) * | 2015-11-05 | 2016-02-24 | 北京航空航天大学 | Highway running state evaluation method based on macroscopic fundamental diagram |
| CN105702031A (en) * | 2016-03-08 | 2016-06-22 | 北京航空航天大学 | Macroscopic fundamental diagram-based road network key section identification method |
| CN106960582A (en) * | 2017-03-12 | 2017-07-18 | 浙江大学 | A kind of method of the region bottleneck control based on macroscopical parent map |
| CN106971538A (en) * | 2017-04-26 | 2017-07-21 | 同济大学 | A kind of method for drafting of the macroscopical parent map of Regional Road Network traffic behavior |
-
2018
- 2018-08-20 CN CN201810948765.6A patent/CN109308805A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102646332A (en) * | 2011-02-21 | 2012-08-22 | 日电（中国）有限公司 | Traffic state estimation device and method based on data fusion |
| CN105355049A (en) * | 2015-11-05 | 2016-02-24 | 北京航空航天大学 | Highway running state evaluation method based on macroscopic fundamental diagram |
| CN105702031A (en) * | 2016-03-08 | 2016-06-22 | 北京航空航天大学 | Macroscopic fundamental diagram-based road network key section identification method |
| CN106960582A (en) * | 2017-03-12 | 2017-07-18 | 浙江大学 | A kind of method of the region bottleneck control based on macroscopical parent map |
| CN106971538A (en) * | 2017-04-26 | 2017-07-21 | 同济大学 | A kind of method for drafting of the macroscopical parent map of Regional Road Network traffic behavior |
Non-Patent Citations (2)
| Title |
|---|
| LUKAS AMBÜHL, MONICA MENENDEZ: "《Data fusion algorithm for macroscopic fundamental diagram estimation》", 《TRANSPORTATION RESEARCH PART C》 * |
| 吴笛: "《基于信息融合技术的绕城高速交通流诱导***模型研究》", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110232398A (en) * | 2019-04-24 | 2019-09-13 | 广东交通职业技术学院 | A kind of road network sub-area division and its appraisal procedure based on Canopy+Kmeans cluster |
| CN110675630A (en) * | 2019-10-08 | 2020-01-10 | 广东交通职业技术学院 | Method for determining minimum coverage rate of networked vehicles |
| CN110827540A (en) * | 2019-11-04 | 2020-02-21 | 黄传明 | Motor vehicle movement mode recognition method and system based on multi-mode data fusion |
| CN110827540B (en) * | 2019-11-04 | 2021-03-12 | 黄传明 | Motor vehicle movement mode recognition method and system based on multi-mode data fusion |
| CN111127880A (en) * | 2019-12-16 | 2020-05-08 | 西南交通大学 | MFD-based grid network traffic performance analysis method |
| CN111739293A (en) * | 2020-06-10 | 2020-10-02 | 广东世纪高通科技有限公司 | Data fusion method and device |
| CN113506440A (en) * | 2021-09-08 | 2021-10-15 | 四川国蓝中天环境科技集团有限公司 | Traffic state estimation method for multi-source data fusion under Lagrange coordinate system |
| CN113506440B (en) * | 2021-09-08 | 2021-11-30 | 四川国蓝中天环境科技集团有限公司 | Traffic state estimation method for multi-source data fusion under Lagrange coordinate system |
| CN113947905A (en) * | 2021-10-19 | 2022-01-18 | 交通运输部公路科学研究所 | Traffic operation situation sensing method, module and system |
| CN114358416A (en) * | 2021-12-31 | 2022-04-15 | 广东工业大学 | Public transport road network partitioning method, system, equipment and medium based on multi-source traffic data |
| CN115641721A (en) * | 2022-12-06 | 2023-01-24 | 南京感动科技有限公司 | Multi-source traffic flow index fusion and road condition calculation method based on fusion index |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109308805A (en) | A kind of road network MFD estimating and measuring method based on self-adaptive weighted average data fusion | |
| CN109272746A (en) | A kind of MFD estimating and measuring method based on BP neural network data fusion | |
| CN101789182B (en) | Traffic signal control system and method based on parallel simulation technique | |
| CN105513359B (en) | A kind of urban expressway traffic method for estimating state based on smart mobile phone movement detection | |
| CN104157139B (en) | A kind of traffic congestion Forecasting Methodology and method for visualizing | |
| CN108053645A (en) | A kind of signalized intersections cycle flow estimation method based on track data | |
| CN108960426A (en) | Road grade Synthesize estimation system based on BP neural network | |
| CN104282162A (en) | Adaptive intersection signal control method based on real-time vehicle track | |
| CN104298540B (en) | A kind of underlying model parameter correcting method of traffic simulation software | |
| CN108254069A (en) | Urban road noise Forecasting Methodology | |
| CN105046956A (en) | Traffic flow simulating and predicting method based on turning probability | |
| CN111553527B (en) | Road traffic time prediction method based on PSO and neural network series optimization | |
| CN104900057B (en) | A kind of Floating Car map-matching method in the major-minor road of city expressway | |
| Zhi-Peng et al. | An improved adaptive exponential smoothing model for short-term travel time forecasting of urban arterial street | |
| CN103778299A (en) | Dynamic traffic flow based forecast method of noise in peripheral zone of long straight road | |
| CN110796876A (en) | Road section vehicle total number estimation method based on Kalman filtering | |
| CN112530177B (en) | Kalman filtering-based vehicle queuing length estimation method in Internet of vehicles environment | |
| Jiang et al. | Travel time prediction model for urban road network based on multi-source data | |
| CN109816983A (en) | A kind of short-term traffic flow forecast method based on depth residual error network | |
| CN106846808B (en) | A kind of vehicle parking based on license plate data time number calculating method | |
| CN109255948B (en) | Lane-dividing traffic flow proportion prediction method based on Kalman filtering | |
| CN106571032A (en) | OD calibration method using mobile phone signaling big data and dynamic traffic assignment | |
| CN104616509A (en) | Traffic microscopic simulation based urban grade crossing signalized intersection optimization method and system | |
| CN102074112A (en) | Time sequence multiple linear regression-based virtual speed sensor design method | |
| Dong et al. | Analysis and control of intelligent traffic signal system based on adaptive fuzzy neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190205 |
|
| RJ01 | Rejection of invention patent application after publication |