CN107067764A - A kind of variable guided vehicle road self-adaptation control method of urban intersection - Google Patents
A kind of variable guided vehicle road self-adaptation control method of urban intersection Download PDFInfo
- Publication number
- CN107067764A CN107067764A CN201710168676.5A CN201710168676A CN107067764A CN 107067764 A CN107067764 A CN 107067764A CN 201710168676 A CN201710168676 A CN 201710168676A CN 107067764 A CN107067764 A CN 107067764A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- mtd
- mtr
- mtable
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The invention discloses a kind of variable guided vehicle road self-adaptation control method of urban intersection, the attribute recommended value of the variable guided vehicle road of the entrance driveway is provided first；Then techniques of discriminant analysis is utilized, according to historical traffic amount data and the attribute recommended value of variable guided vehicle road, the coefficient correlation to discriminant analysis function is demarcated；Secondly the real-time traffic amount data detected according to historical traffic amount data and detector, are predicted using k neighbours non parametric regression to following short-term traffic flow；The attribute recommended value of the variable guided vehicle road in future is obtained according to discriminant analysis function, the coefficient correlation of discriminant analysis function is also real-time update；Finally, at the time of selecting variable guided vehicle road turning function conversion, and the clean up time of variable guided vehicle road is calculated, realizes that signal controlling machine carries out lane function conversion and the timing of main pre-signal is coordinated.The present invention improves the utilization rate of variable guided vehicle road, shortens the mean delay of intersection, alleviates urban traffic jam.
Description
Technical field
The present invention relates to road traffic control field, especially a kind of variable guided vehicle road Self Adaptive Control of urban intersection
Method.
Background technology
For the management and control of signalized crossing, generally in the case where keeping lane function constant, letter is utilized
The mode of number phase adjustment adapts to actual transport need.The management and control mode has certain limitation, especially when each turn to is handed over
It is through-flow when the fluctuation of different periods is obvious, often result in unnecessary time-space distribution and waste, or cause traffic congestion.In recent years
Come, urban intersection is provided with variable guided vehicle road, however, the conversion of variable guided vehicle road turning function is often by duty
Traffic police is regulated and controled by the way of manually controlling or taking the lane changing scheme of fixed period, subjective, is caused
The problem of variable guided vehicle road utilization rate is low.
Studied has a case that tidal regime mainly in signalized crossing traffic flow, and for it is same enter
Turn left on mouth road and through-traffic stream is less in the significant case study of different time sections fluctuation, pertinent literature is proposed to be determined manually
When control, sensing control, double parking methods such as line traffic control and master, pre-signal control, but the actual execution of the flow that is proposed
Operability is not strong, and the acquisition and collection of parameter are more difficult, it is difficult to realize the conversion of variable guided vehicle road turning function in real time,
And not using the timing coordinate scheme between suitable main pre-signal.
The content of the invention
The technical problems to be solved by the invention are that there is provided a kind of variable guided vehicle road Self Adaptive Control of urban intersection
Method, can realize the turning function conversion of variable guided vehicle road.
In order to solve the above technical problems, the present invention provides a kind of variable guided vehicle road Self Adaptive Control side of urban intersection
Method, comprises the following steps：
(1) observation and collection of history and Real-Time Traffic Volume data；
(2) history and Real-Time Traffic Volume data obtained based on k neighbours non parametric regression to the step (1), is carried out
The integration in traffic data storehouse, the selection of state vector, the selection of similar mechanism, the determination of neighbour's number and regression function
Build, obtain short-term traffic flow prediction data；
(3) the historical traffic amount data that basis is obtained based on step (1), are turned left, directly by calculating and comparing each entrance driveway
The congestion level of row traffic flow, obtains the variable guided vehicle road attribute recommended value of history；
(4) the variable guiding of history that the historical traffic amount data and the step (3) obtained based on the step (1) are obtained
Track attribute recommended value, based on techniques of discriminant analysis, obtains variable guided vehicle road and turns left and the straight trip corresponding discriminant analysis letter of attribute
Number；
(5) the discriminant analysis letter that the Short-Term Traffic Flow data and the step (4) obtained using the step (2) are obtained
Number, obtains real-time variable guided vehicle road attribute recommended value；
(6) real-time variable guided vehicle road attribute recommended value is obtained according to the step (5), being realized by signal controlling machine can
The timing become between the main pre-signal of guided vehicle road is coordinated, including the selection at conversion moment of variable guided vehicle road turning function and clear
Calculating between space-time, and by the display of the corresponding main pre-signal lamp of signal controlling machine control.
It is preferred that, traffic figureofmerit is chosen in step (1) as analysis left-hand rotation, the characteristic parameter of straight traffic flow proportional,
Including history and Real-Time Traffic Volume data, wherein real-time traffic amount data are obtained by induction coil detector Site Detection,
The vehicle number of point vehicle is counted in each signal period, the left-hand rotation, Through Lane to entrance driveway, and data are uploaded in real time
To control centre；Historical traffic amount data be by real-time traffic amount data accumulation form, for the ease of the storage of data, calculate with
And ensureing the real-time of track attribute conversion, the present invention updates a historical traffic amount database every two weeks, and keeps
For the traffic data of nearest one month.
It is preferred that, k neighbour's non parametric regressions in step (2) are realized in control centre, and traffic data is carried out
Processing specifically includes following steps：
(21) it is a composite number by history and Real-Time Traffic Volume database integration to the integration in traffic flow data storehouse
It is that dynamic updates according to the data in storehouse, and composite database；
(22) to the selection of state vector, definition status vector：
X=[vh(t),vh(t-1),vh(t-2),v(t),v(t-1),v(t-2)] (1)
Wherein, v (t) represents the real-time traffic amount of t periods in composite database, unit：pcu/h；
vh(t) the historical traffic amount of t periods in composite database, unit are represented：pcu/h；
(23) selection of similar mechanism, similitude is defined using Euclidean distance：
Wherein, diFor the Euclidean between the real-time traffic amount and historical traffic amount of adjacent three periods in composite database away from
From unit：pcu/h；D is the Euclidean distance of k arest neighbors in composite database, unit：pcu/h；
(24) determination of neighbour's number, general k is set between 1 to 20, specifically met：
Wherein, Lmin(k) when representing the residual sum of squares (RSS) minimum between the volume of traffic that actual traffic amount and regression forecasting are obtained
Corresponding k, i.e., optimal neighbour's number；
(25) structure of regression function, the magnitude of traffic flow K (t+1) of subsequent period calculation formula：
Wherein, vhi(t) be i-th of neighbour of t periods the volume of traffic, i=1,2 ..., k, unit：pcu/h；
βiFor the regression coefficient of k-th of neighbour.
It is preferred that, step (3) is realized in control centre, and method specifically includes following steps：
(31) design capacity in every track is calculated,
Wherein, NlWhen being not provided with exclusive right-turn lane provided with exclusive left-turn lane for entrance driveway, exclusive left-turn lane
Design capacity, unit：pcu/h；
NsFor the design capacity of Through Lane, unit：pcu/h；
NsrFor Through Lane and straight right lane design capacity sum, unit：pcu/h；
βlFor this face left turning vehicle ratio；
ψsFor Through Lane traffic capacity reduction coefficient, 0.9 can be used；
tgFor the green time in the signal period, unit：s；
t1Start and by the time of stop line, unit to be changed into first car after green light：S, can use 2.3s；
tisIt is that straight trip or right lateral vehicle pass through the Mean Time Between Replacement of stop line, unit：s/pcu；
tcFor signal period, unit：s；
(32) left-hand rotation, the saturation degree S of Through Lane are calculatedi, it is respectively：
Si=Qi/Ni (6)
Wherein, i=l, s, represent and keep straight on respectively；
QiFor the volume of traffic in the track individual signals cycle, unit：pcu/h；
NiFor the design capacity in track, unit:pcu/h.
The threshold value that selection saturation degree 0.8 is changed as track attribute, then have：
(33) differentiated：If the saturation degree in two kinds of tracks is respectively less than 0.8, then now two kinds of tracks are not up to congestion
State, keeps the attribute of original variable guided vehicle road；If the saturation degree of left turn lane is more than the saturation degree of 0.8 and Through Lane
Less than 0.8, then correspondence left turn lane reaches congestion status but Through Lane not yet reaches congestion status, by the variable guiding of history
The suggestion attribute in track is set to；If the saturation degree of the saturation degree of Through Lane left turn lane more than 0.8 is less than 0.8, that
Correspondence Through Lane reaches congestion status but left turn lane not yet reaches congestion status, by the suggestion of the variable guided vehicle road of history
Attribute is set to straight trip；If the saturation degree in two kinds of tracks is all higher than 0.8, then now two kinds of tracks reach congestion status, in order to keep away
Exempt from the possible caused additional cross mouthful delay of now track attribute conversion, still keep the attribute of original variable guided vehicle road.
It is preferred that, step (4) is realized in control centre, and method specifically includes following steps：
(41) clearly there are two differentiation types, you can become the attribute of guided vehicle road to turn left or keeping straight on, be set toClass andClass, to that should have two observation index, i.e. left-turn volume and straight-going traffic amount, whereinClass has s group data,There are t groups in class
Data；
(42) these data are write as matrix form, had：
Wherein, aijForThe value of j-th of variable of i-th group of data, i=1,2 ... s, j=1,2, unit in class：pcu/h；
bijForThe value of j-th of variable of i-th group of data, i=1,2 ... t, j=1,2, unit in class：pcu/h；
Calculate the average value of Various types of data：
Wherein,Represent respectivelyClass andThe average value of each variable of jth of class data, unit：pcu/h；Make two
The matrix A of class data matrix and corresponding average value difference, B：
Thus the mean dispersion error matrix S of two class data can be tried to achieve by below equation：
Solve two element equations：I.e.
It can thus be concluded that going out：
Wherein, first formula is the corresponding discriminant function of object to be discriminated, unit：pcu/h；
Second and third formula is used to calculateClass andThe differentiation average value of class data, unit：pcu/h；
4th formula is used for computational discrimination critical value, unit：pcu/h；
(43) to differentiating that object differentiates, it is assumed that there is an object to be discriminated, its data is X (x1,x2), then its discriminant value
For y=c1x1+c2x2, unit：Pcu/h, if meeting yA>yB, then criterion is advised：If y>y0, then can be determined that
It is on the contrary then can be determined thatIf meeting yA<yB, then criterion is advised：If y>y0, then can be determined thatIt is on the contrary then
It can be determined thatFollowing criterion can be reduced to：
Because discriminant analysis function is determined based on historical traffic amount data and the variable guided vehicle road attribute of history, and go through
History traffic data storehouse updates once every two weeks, and remains the traffic data of nearest one month, therefore obtain
Discriminant analysis function is also to update primary parameter every two weeks.
It is preferred that, in step (6), obtained real-time variable guided vehicle road attribute realizes that track attribute turns by signal controlling machine
Change, stored in control centre, and in order to prevent track attribute frequent switching, have and only continuous three cycles suggestion
When attribute is different from present case, variable guided vehicle road attribute can just change, specifically：
When variable guided vehicle road attribute turns from straight to left, in order to empty main signal left-hand rotation green light open it is bright before master
Through vehicles between pre-signal stop line on road, the straight trip red light of pre-signal needs to end in advance, and in order to make up master
Pre-signal left-hand rotation green light is while Qi Liangshi green time loss, the left-hand rotation green light of pre-signal needs to open bright in advance：
Wherein, t1Deadline in advance, unit are needed for the straight trip red light of pre-signal：s；
t2Need to open bright time, unit in advance for the left-hand rotation green light of pre-signal：s；
V is the average speed of vehicle, unit：m/s；
l1For the distance between main signal stop line and pre-signal stop line, unit：m；
A is the average starting loop of vehicle, unit：m/s2；
When variable guided vehicle road attribute turns from left to straight, in order to empty main signal straight trip green light open it is bright before master
Left turning vehicle between pre-signal stop line on road, the left-hand rotation red light of pre-signal needs to end in advance, and in order to make up master
Pre-signal straight trip green light is while Qi Liangshi green time loss, the straight trip green light of pre-signal needs to open bright in advance：
Wherein, t3Deadline in advance, unit are needed for the left-hand rotation red light of pre-signal：s；
t4Need to open bright time, unit in advance for the straight trip green light of pre-signal：s；
gLFor main signal left-hand rotation green time, unit：s；
qLFor the arrival rate of left-hand rotation car, unit：pcu/s；
C is signal period, unit：s；
SLFor the saturation volume rate of left-hand rotation car, unit：pcu/s.
Beneficial effects of the present invention are：(1) conversion of real-time variable guided vehicle road turning function can be realized, is being used
When k neighbours non parametric regression and techniques of discriminant analysis, historical traffic amount data and the variable guided vehicle road attribute recommended value of history are not
It is changeless, but constantly updated by real-time traffic data；In the discriminant analysis function obtained by historical data
Parameter be also dynamic change, tune is constantly rolled according to real-time traffic data and real-time variable guided vehicle road property value
It is whole, it is possible thereby to improve the utilization rate of variable guided vehicle road, reduce delay of the vehicle in intersection；(2) it can realize main pre-
Timing between signal is coordinated, for the vehicle between the main pre-signal stop line that dissipates, it is proposed that turn to work(in variable guided vehicle road
The calculating of clean up time when can change, and to prevent corresponding green time from losing, there is provided pre-signal is early opened the time, clearly
The right of way of vehicle in variable guided vehicle road so that driver adjusts direction of traffic in time, reduce the unnecessary stand-by period.
Brief description of the drawings
Fig. 1 is method flow schematic diagram of the invention.
Fig. 2 is distributed for the track of the entrance driveway of the present invention, the position dependency relation schematic diagram of main pre-signal stop line.
Fig. 3 is the schematic flow sheet of k neighbour's distribution-free regression procedures of the present invention.
When the value that Fig. 4 is k in optimization k neighbour's distribution-free regression procedures of the invention is different, the residual error turned left and kept straight on
The curve synoptic diagram that quadratic sum changes with k.
The variable guided vehicle road attribute that Fig. 5 is the present invention is left-hand rotation and the signal of traffic data accuracy is verified when keeping straight on
Figure.
Fig. 6 (a) is related to signal period figure when being turned from straight to left for the variable guided vehicle road attribute of the present invention to close
It is schematic diagram.
Fig. 6 (b) is the variable guided vehicle road turning function conversion moment of the invention of the present invention and the phase of signal period figure
Close relation schematic diagram.
Fig. 6 (c) is related to signal period figure when being turned from left to straight for the variable guided vehicle road attribute of the present invention to close
It is schematic diagram.
Fig. 6 (d) is that the variable guided vehicle road turning function conversion moment of the present invention and the dependency relation of signal period figure are shown
It is intended to.
Embodiment
A kind of variable guided vehicle road adaptive control algorithm of urban intersection proposed by the present invention, its flow chart is shown in accompanying drawing 1,
Mainly comprise the following steps：
(1) observation and collection of history and real-time traffic amount data.
The training and test of the variable guided vehicle road adaptive control algorithm of urban intersection of the present invention are all using on Hangzhou
Tang Lu and the literary sunshine south of road entrance driveway traffic data.Intersection south entrance driveway totally four tracks, first is from inside to outside
Left turn lane, Article 2 is left-hand rotation/straight trip changeable driveway, and Article 3 is Through Lane, and Article 4 is straight right lane.It is of the invention real
Apply the relation such as accompanying drawings 2 such as track distribution, the position of main pre-signal stop line of example.The crossing is manually controlled variable by traffic police at present
The change in track, 7 points to 9 points of peak period changeable driveway of the morning on working day is left turn lane, and remaining time is straight traffic
Road.Historical traffic amount data to relevant departments by the way of directly obtaining, and the investigation of real-time traffic data is using artificial
Investigate and detect the mode being combined, the physical dimension and signal timing dial of manual research intersection, with every with induction coil detector
Individual signal period duration is that unit time interval exports the traffic flow data that the entrance driveway turns left and kept straight on, and unit is pcu/h.
The embodiment of the present invention is trained using 268 groups, and 12 groups of data are verified, the ratio description of each Turning movement of use is shown in Table 1：
The ratio of each Turning movement used in the embodiment of the present invention of table 1
(2) based on k neighbours non parametric regression to history and real-time traffic amount data, carry out traffic data storehouse integration,
The selection of state vector, the selection of similar mechanism, the structure of the determination of neighbour's number and regression function, obtain short-term traffic flow
Data, the flow of k neighbour's distribution-free regression procedures of the embodiment of the present invention refers to accompanying drawing 3.According to training data, calculate respectively
Corresponding left-hand rotation, the residual sum of squares (RSS) L of straight trip when neighbour's number k is between 1 to 20Min turns left(k)、LMin keeps straight on(k), it is shown in Table 2, and
And depict accompanying drawing 4.With reference to table 2 and accompanying drawing 4, the left-hand rotation for present example is found, the short-term traffic flow of straight trip is predicted
Optimal neighbour's number is 2.
The relation of the residual sum of squares (RSS) of the embodiment of the present invention of table 2 and neighbour's number
(3) according to historical traffic amount data, calculate and relatively more each entrance driveway left-hand rotation, the saturation degree of through-traffic stream, obtain
The variable guided vehicle road attribute recommended value of history.
In present example, Through Lane traffic capacity reduction coefficient ψsUsing 0.9, the green time t in the signal periodg
For 70s, signal lamp is changed into the time t that first car starts and passes through stop line after green light1Using 2.3s, straight trip or right lateral vehicle
Pass through the Mean Time Between Replacement t of stop lineisFor 2.4s/pcu, signal period tcFor 180s, this face left turning vehicle ratio betalFor
0.383, therefore Through Lane, Through Lane and straight right lane, the design capacity of exclusive left-turn lane distinguish as follows：
According to the traffic data of history and the design capacity in each track, to left-hand rotation and the saturation degree of Through Lane
It is respectively calculated, and judges the recommended value of the variable guided vehicle road attribute of history, table 3 is partial data judged result.
Table 3 judges the variable guided vehicle road attribute of history
(4) historical traffic amount data and the variable guided vehicle road attribute recommended value of history are based on, based on techniques of discriminant analysis, is obtained
The discriminant analysis function of the variable guided vehicle road left-hand rotation of entrance driveway and straight trip attribute respectively.
In formula, x1、x2Turn left and straight-going traffic amount, unit on entrance driveway respectively to be discriminated:pcu/h；
L0、L1The attribute of variable guided vehicle road is represented respectively to turn left and keep straight on.
(5) short-term traffic flow data and discriminant analysis function are used, real-time variable guided vehicle road attribute recommended value is obtained.
The variable guided vehicle road property value of history and real-time variable guided vehicle road attribute recommended value are compared, this is obtained
The accuracy of the validation data set of inventive embodiments, such as accompanying drawing 5.
(6) according to variable guided vehicle road attribute recommended value, the attribute of current time variable guided vehicle road is compareed, is led to variable
Coordinate to be configured to the timing between the main pre-signal in track, such as accompanying drawing 6.
In the embodiment of the present invention, the distance between main signal stop line and pre-signal stop line l1=90m, vehicle is averaged
Speed v=12m/s2, the average starting loop v=12m/s of vehicle2, therefore the straight trip red light of pre-signal is when needing to end in advance
BetweenThe left-hand rotation green light of pre-signal needs to open the bright time in advanceMain signal
Left-hand rotation green time gL=74s, the arrival rate q of left-hand rotation carL=0.11pcu/s, the saturation volume rate S of left-hand rotation carL=0.53pcu/s,
Signal period C=180s, therefore the left-hand rotation red light of pre-signal needs deadline in advancePre-signal
Straight trip green light need to open bright time t in advance4=t2=5s.
The present invention proposes a kind of variable guided vehicle road adaptive control algorithm of urban intersection.Returned based on k neighbours nonparametric
Prediction short-term traffic flow is returned to carry out；Using techniques of discriminant analysis, between the property value for obtaining traffic data and variable guided vehicle road
Differentiation relation, and obtain real-time variable guided vehicle road attribute recommended value；There is provided the cut-off in advance between main pre-signal
Time and pre-cooling time.The accuracy of model is higher, and the conversion of variable guided vehicle road turning function in real time can be achieved, and protects
The timing for demonstrate,proving main pre-signal is coordinated, and improves the utilization rate of variable guided vehicle road, shortens the mean delay of intersection.
Although the present invention is illustrated and described with regard to preferred embodiment, it is understood by those skilled in the art that
Without departing from scope defined by the claims of the present invention, variations and modifications can be carried out to the present invention.
Claims (6)
1. a kind of variable guided vehicle road self-adaptation control method of urban intersection, it is characterised in that comprise the following steps：
(1) observation and collection of history and Real-Time Traffic Volume data；
(2) history and Real-Time Traffic Volume data obtained based on k neighbours non parametric regression to the step (1), carries out traffic
Measure the structure of integration, the selection of state vector, the selection of similar mechanism, the determination of neighbour's number and the regression function of database
Build, obtain short-term traffic flow prediction data；
(3) according to the historical traffic amount data obtained based on step (1), by calculating and comparing, each entrance driveway turns left, straight trip is handed over
Through-flow congestion level, obtains the variable guided vehicle road attribute recommended value of history；
(4) the variable guided vehicle road of history that the historical traffic amount data and the step (3) obtained based on the step (1) are obtained
Attribute recommended value, based on techniques of discriminant analysis, obtains variable guided vehicle road and turns left and the straight trip corresponding discriminant analysis function of attribute；
(5) the discriminant analysis function that the Short-Term Traffic Flow data and the step (4) obtained using the step (2) are obtained,
Obtain real-time variable guided vehicle road attribute recommended value；
(6) real-time variable guided vehicle road attribute recommended value is obtained according to the step (5), variable lead is realized by signal controlling machine
Coordinate to the timing between the main pre-signal in track, including variable guided vehicle road turning function the conversion moment selection and when emptying
Between calculating, and control by signal controlling machine the display of corresponding main pre-signal lamp.
2. the variable guided vehicle road self-adaptation control method of urban intersection as claimed in claim 1, it is characterised in that step
(1) traffic figureofmerit is chosen in as analysis left-hand rotation, the characteristic parameter of straight traffic flow proportional, including history and arithmetic for real-time traffic flow
Data are measured, wherein real-time traffic amount data are obtained by induction coil detector Site Detection, in each signal period, to entrance driveway
Left-hand rotation, the vehicle number of point vehicle is counted on Through Lane, and data is uploaded into control centre in real time；Historical traffic amount
Data are formed by the accumulation of real-time traffic amount data, for the ease of the storage of data, calculating and guarantee track attribute conversion
Real-time, the present invention updates a historical traffic amount database every two weeks, and remains the volume of traffic of nearest one month
Data.
3. the variable guided vehicle road self-adaptation control method of urban intersection as claimed in claim 1, it is characterised in that step
(2) k neighbour's non parametric regressions in are realized in control centre, and following step is specifically included to traffic data progress processing
Suddenly：
(21) it is a complex data by history and Real-Time Traffic Volume database integration to the integration in traffic flow data storehouse
Data in storehouse, and composite database are that dynamic updates；
(22) to the selection of state vector, definition status vector：
X=[vh(t),vh(t-1),vh(t-2),v(t),v(t-1),v(t-2)] (1)
Wherein, v (t) represents the real-time traffic amount of t periods in composite database, unit：pcu/h；
vh(t) the historical traffic amount of t periods in composite database, unit are represented：pcu/h；
(23) selection of similar mechanism, similitude is defined using Euclidean distance：
<mrow>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>d</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<msup>
<mrow>
<mo>&lsqb;</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>v</mi>
<mi>h</mi>
</msub>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
<mo>-</mo>
<mi>v</mi>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>v</mi>
<mi>h</mi>
</msub>
<mo>(</mo>
<mrow>
<mi>t</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mo>)</mo>
<mo>-</mo>
<mi>v</mi>
<mo>(</mo>
<mrow>
<mi>t</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>v</mi>
<mi>h</mi>
</msub>
<mo>(</mo>
<mrow>
<mi>t</mi>
<mo>-</mo>
<mn>2</mn>
</mrow>
<mo>)</mo>
<mo>-</mo>
<mi>v</mi>
<mo>(</mo>
<mrow>
<mi>t</mi>
<mo>-</mo>
<mn>2</mn>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>&rsqb;</mo>
</mrow>
<mrow>
<mn>1</mn>
<mo>/</mo>
<mn>2</mn>
</mrow>
</msup>
<mo>/</mo>
<mn>3</mn>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>d</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>k</mi>
</munderover>
<mfrac>
<mn>1</mn>
<msub>
<mi>d</mi>
<mi>i</mi>
</msub>
</mfrac>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, diFor the Euclidean distance between the real-time traffic amount and historical traffic amount of adjacent three periods in composite database, list
Position：pcu/h；D is the Euclidean distance of k arest neighbors in composite database, unit：pcu/h；
(24) determination of neighbour's number, general k is set between 1 to 20, specifically met：
<mrow>
<msub>
<mi>L</mi>
<mi>min</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>k</mi>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<mi>v</mi>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
<mo>-</mo>
<msub>
<mi>v</mi>
<mrow>
<mi>h</mi>
<mi>i</mi>
</mrow>
</msub>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, Lmin(k) correspondence when representing the residual sum of squares (RSS) minimum between the volume of traffic that actual traffic amount and regression forecasting are obtained
K, i.e., optimal neighbour's number；
(25) structure of regression function, the magnitude of traffic flow K (t+1) of subsequent period calculation formula：
<mrow>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>v</mi>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>k</mi>
</munderover>
<msub>
<mi>&beta;</mi>
<mi>i</mi>
</msub>
<msub>
<mi>v</mi>
<mrow>
<mi>h</mi>
<mi>i</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>+</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>&beta;</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<mfrac>
<mi>d</mi>
<msub>
<mi>d</mi>
<mi>i</mi>
</msub>
</mfrac>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, vhi(t) be i-th of neighbour of t periods the volume of traffic, i=1,2 ..., k, unit：pcu/h；
βiFor the regression coefficient of k-th of neighbour.
4. the variable guided vehicle road self-adaptation control method of urban intersection as claimed in claim 1, it is characterised in that step
(3) it is to be realized in control centre, method specifically includes following steps：
(31) design capacity in every track is calculated,
<mrow>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>N</mi>
<mi>l</mi>
</msub>
<mo>=</mo>
<msub>
<mi>&beta;</mi>
<mi>l</mi>
</msub>
<msub>
<mi>&Sigma;N</mi>
<mrow>
<mi>s</mi>
<mi>r</mi>
</mrow>
</msub>
<mo>/</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<msub>
<mi>&beta;</mi>
<mi>l</mi>
</msub>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>N</mi>
<mi>s</mi>
</msub>
<mo>=</mo>
<mn>3600</mn>
<msub>
<mi>&psi;</mi>
<mi>s</mi>
</msub>
<mrow>
<mo>(</mo>
<mfrac>
<mrow>
<msub>
<mi>t</mi>
<mi>g</mi>
</msub>
<mo>-</mo>
<msub>
<mi>t</mi>
<mn>1</mn>
</msub>
</mrow>
<msub>
<mi>t</mi>
<mrow>
<mi>i</mi>
<mi>s</mi>
</mrow>
</msub>
</mfrac>
<mo>+</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>/</mo>
<msub>
<mi>t</mi>
<mi>c</mi>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>N</mi>
<mrow>
<mi>s</mi>
<mi>r</mi>
</mrow>
</msub>
<mo>=</mo>
<msub>
<mi>N</mi>
<mi>s</mi>
</msub>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>5</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, NlWhen being not provided with exclusive right-turn lane provided with exclusive left-turn lane for entrance driveway, the design of exclusive left-turn lane is led to
Row ability, unit：pcu/h；
NsFor the design capacity of Through Lane, unit：pcu/h；
NsrFor Through Lane and straight right lane design capacity sum, unit：pcu/h；
βlFor this face left turning vehicle ratio；
ψsFor Through Lane traffic capacity reduction coefficient, 0.9 can be used；
tgFor the green time in the signal period, unit：s；
t1Start and by the time of stop line, unit to be changed into first car after green light：S, can use 2.3s；
tisIt is that straight trip or right lateral vehicle pass through the Mean Time Between Replacement of stop line, unit：s/pcu；
tcFor signal period, unit：s；
(32) left-hand rotation, the saturation degree S of Through Lane are calculatedi, it is respectively：
Si=Qi/Ni (6)
Wherein, i=l, s, represent and keep straight on respectively；
QiFor the volume of traffic in the track individual signals cycle, unit：pcu/h；
NiFor the design capacity in track, unit:pcu/h.
The threshold value that selection saturation degree 0.8 is changed as track attribute, then have：
(33) differentiated：If the saturation degree in two kinds of tracks is respectively less than 0.8, then now two kinds of tracks are not up to congestion shape
State, keeps the attribute of original variable guided vehicle road；If the saturation degree of the saturation degree of left turn lane Through Lane more than 0.8 is small
In 0.8, then correspondence left turn lane reaches congestion status but Through Lane not yet reaches congestion status, by the variable Guide vehicle of history
The suggestion attribute in road is set to；If the saturation degree of the saturation degree of Through Lane left turn lane more than 0.8 is less than 0.8, then
Correspondence Through Lane reaches congestion status but left turn lane not yet reaches congestion status, and the suggestion of the variable guided vehicle road of history is belonged to
Property be set to straight trip；If the saturation degree in two kinds of tracks is all higher than 0.8, then now two kinds of tracks reach congestion status, in order to avoid
Additional cross mouthful delay, still keeps the attribute of original variable guided vehicle road caused by now track attribute conversion is possible.
5. the variable guided vehicle road self-adaptation control method of urban intersection as claimed in claim 1, it is characterised in that step
(4) it is to be realized in control centre, method specifically includes following steps：
(41) clearly there are two differentiation types, you can become the attribute of guided vehicle road to turn left or keeping straight on, be set toClass and
Class, to that should have two observation index, i.e. left-turn volume and straight-going traffic amount, whereinClass has s group data,There are t group numbers in class
According to；
(42) these data are write as matrix form, had：
<mrow>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mover>
<mi>A</mi>
<mo>~</mo>
</mover>
<mo>=</mo>
<mfenced open = "(" close = ")">
<mtable>
<mtr>
<mtd>
<msub>
<mi>a</mi>
<mn>11</mn>
</msub>
</mtd>
<mtd>
<msub>
<mi>a</mi>
<mn>12</mn>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<mtable>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
</mtable>
</mtd>
<mtd>
<mtable>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
</mtable>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>a</mi>
<mrow>
<mi>s</mi>
<mn>1</mn>
</mrow>
</msub>
</mtd>
<mtd>
<msub>
<mi>a</mi>
<mrow>
<mi>s</mi>
<mn>2</mn>
</mrow>
</msub>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mover>
<mi>B</mi>
<mo>~</mo>
</mover>
<mo>=</mo>
<mfenced open = "(" close = ")">
<mtable>
<mtr>
<mtd>
<msub>
<mi>b</mi>
<mn>11</mn>
</msub>
</mtd>
<mtd>
<msub>
<mi>b</mi>
<mn>12</mn>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<mtable>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
</mtable>
</mtd>
<mtd>
<mtable>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
</mtable>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>b</mi>
<mrow>
<mi>i</mi>
<mn>1</mn>
</mrow>
</msub>
</mtd>
<mtd>
<msub>
<mi>b</mi>
<mrow>
<mi>i</mi>
<mn>2</mn>
</mrow>
</msub>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>8</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, aijForThe value of j-th of variable of i-th group of data, i=1,2 ... s, j=1,2, unit in class：pcu/h；
bijForThe value of j-th of variable of i-th group of data, i=1,2 ... t, j=1,2, unit in class：pcu/h；
Calculate the average value of Various types of data：
Wherein,Represent respectivelyClass andThe average value of each variable of jth of class data, unit：pcu/h；Make two class numbers
According to the matrix A of matrix and corresponding average value difference, B：
<mrow>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>A</mi>
<mrow>
<mi>s</mi>
<mo>&times;</mo>
<mn>2</mn>
</mrow>
</msub>
<mo>=</mo>
<mfenced open = "(" close = ")">
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>a</mi>
<mn>11</mn>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>A</mi>
<mn>1</mn>
</mrow>
</msub>
</mrow>
</mtd>
<mtd>
<mrow>
<msub>
<mi>a</mi>
<mn>12</mn>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>A</mi>
<mn>2</mn>
</mrow>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mtable>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
</mtable>
</mtd>
<mtd>
<mtable>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
</mtable>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>a</mi>
<mrow>
<mi>s</mi>
<mn>1</mn>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>A</mi>
<mn>1</mn>
</mrow>
</msub>
</mrow>
</mtd>
<mtd>
<mrow>
<msub>
<mi>a</mi>
<mrow>
<mi>s</mi>
<mn>2</mn>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>A</mi>
<mn>2</mn>
</mrow>
</msub>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>B</mi>
<mrow>
<mi>t</mi>
<mo>&times;</mo>
<mn>2</mn>
</mrow>
</msub>
<mo>=</mo>
<mfenced open = "(" close = ")">
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>b</mi>
<mn>11</mn>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>B</mi>
<mn>1</mn>
</mrow>
</msub>
</mrow>
</mtd>
<mtd>
<mrow>
<msub>
<mi>b</mi>
<mn>12</mn>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>B</mi>
<mn>2</mn>
</mrow>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mtable>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
</mtable>
</mtd>
<mtd>
<mtable>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
</mtable>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>b</mi>
<mrow>
<mi>t</mi>
<mn>1</mn>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>B</mi>
<mn>1</mn>
</mrow>
</msub>
</mrow>
</mtd>
<mtd>
<mrow>
<msub>
<mi>b</mi>
<mrow>
<mi>t</mi>
<mn>2</mn>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>B</mi>
<mn>2</mn>
</mrow>
</msub>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>10</mn>
<mo>)</mo>
</mrow>
</mrow>
Thus the mean dispersion error matrix S of two class data can be tried to achieve by below equation：
<mrow>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mover>
<mi>S</mi>
<mo>^</mo>
</mover>
<mrow>
<mn>2</mn>
<mo>&times;</mo>
<mn>2</mn>
</mrow>
</msub>
<mo>=</mo>
<msup>
<mi>A</mi>
<mo>&prime;</mo>
</msup>
<mi>A</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mover>
<mi>S</mi>
<mo>~</mo>
</mover>
<mrow>
<mn>2</mn>
<mo>&times;</mo>
<mn>2</mn>
</mrow>
</msub>
<mo>=</mo>
<msup>
<mi>B</mi>
<mo>&prime;</mo>
</msup>
<mi>B</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>S</mi>
<mrow>
<mn>2</mn>
<mo>&times;</mo>
<mn>2</mn>
</mrow>
</msub>
<mo>=</mo>
<msub>
<mover>
<mi>S</mi>
<mo>^</mo>
</mover>
<mrow>
<mn>2</mn>
<mo>&times;</mo>
<mn>2</mn>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mover>
<mi>S</mi>
<mo>~</mo>
</mover>
<mrow>
<mn>2</mn>
<mo>&times;</mo>
<mn>2</mn>
</mrow>
</msub>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>11</mn>
<mo>)</mo>
</mrow>
</mrow>
Solve two element equations：I.e.
It can thus be concluded that going out：
<mrow>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>y</mi>
<mo>=</mo>
<msub>
<mi>c</mi>
<mn>1</mn>
</msub>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
<mo>+</mo>
<msub>
<mi>c</mi>
<mn>2</mn>
</msub>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>y</mi>
<mi>A</mi>
</msub>
<mo>=</mo>
<msub>
<mi>c</mi>
<mn>1</mn>
</msub>
<msub>
<mi>x</mi>
<mrow>
<mi>A</mi>
<mn>1</mn>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>c</mi>
<mn>2</mn>
</msub>
<msub>
<mi>x</mi>
<mrow>
<mi>A</mi>
<mn>2</mn>
</mrow>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>y</mi>
<mi>B</mi>
</msub>
<mo>=</mo>
<msub>
<mi>c</mi>
<mn>1</mn>
</msub>
<msub>
<mi>x</mi>
<mrow>
<mi>B</mi>
<mn>1</mn>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>c</mi>
<mn>2</mn>
</msub>
<msub>
<mi>x</mi>
<mrow>
<mi>B</mi>
<mn>2</mn>
</mrow>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>y</mi>
<mn>0</mn>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<mi>s</mi>
<mo>&CenterDot;</mo>
<msub>
<mi>y</mi>
<mi>A</mi>
</msub>
<mo>+</mo>
<mi>t</mi>
<mo>&CenterDot;</mo>
<msub>
<mi>y</mi>
<mi>B</mi>
</msub>
</mrow>
<mrow>
<mi>s</mi>
<mo>+</mo>
<mi>t</mi>
</mrow>
</mfrac>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>12</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, first formula is the corresponding discriminant function of object to be discriminated, unit：pcu/h；
Second and third formula is used to calculateClass andThe differentiation average value of class data, unit：pcu/h；
4th formula is used for computational discrimination critical value, unit：pcu/h；(43) to differentiating that object differentiates, it is assumed that treat
Differentiate object, its data is X (x1,x2), then its discriminant value is y=c1x1+c2x2, unit：Pcu/h, if meeting yA>yB, then build
Discuss criterion：If y>y0, then can be determined thatIt is on the contrary then can be determined thatIf meeting yA<yB, then advise sentencing
Other criterion：If y>y0, then can be determined thatIt is on the contrary then can be determined thatFollowing criterion can be reduced to：
<mrow>
<mi>X</mi>
<mo>&Element;</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mover>
<mi>A</mi>
<mo>~</mo>
</mover>
<mo>,</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>-</mo>
<msub>
<mi>y</mi>
<mn>0</mn>
</msub>
<mo>)</mo>
<mo>(</mo>
<msub>
<mi>y</mi>
<mi>A</mi>
</msub>
<mo>-</mo>
<msub>
<mi>y</mi>
<mi>B</mi>
</msub>
<mo>)</mo>
<mo>></mo>
<mn>0</mn>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mover>
<mi>B</mi>
<mo>~</mo>
</mover>
<mo>,</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>-</mo>
<msub>
<mi>y</mi>
<mn>0</mn>
</msub>
<mo>)</mo>
<mo>(</mo>
<msub>
<mi>y</mi>
<mi>A</mi>
</msub>
<mo>-</mo>
<msub>
<mi>y</mi>
<mi>B</mi>
</msub>
<mo>)</mo>
<mo>></mo>
<mn>0</mn>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>13</mn>
<mo>)</mo>
</mrow>
</mrow>
Because discriminant analysis function is determined based on historical traffic amount data and the variable guided vehicle road attribute of history, and history is handed over
Flux data storehouse updates once every two weeks, and remains the traffic data of nearest one month, therefore obtained differentiation
Analytic function is also to update primary parameter every two weeks.
6. the variable guided vehicle road self-adaptation control method of urban intersection as claimed in claim 1, it is characterised in that step
(6) in, obtained real-time variable guided vehicle road attribute realizes track attribute conversion by signal controlling machine, is deposited in control centre
Storage, and in order to prevent track attribute frequent switching, have and the suggestion attribute in only continuous three cycles is different from present case
When, variable guided vehicle road attribute can just change, specifically：
When variable guided vehicle road attribute turns from straight to left, in order to empty main signal left-hand rotation green light open it is bright before master believe in advance
Through vehicles between number stop line on road, the straight trip red light of pre-signal needs to end in advance, and in order to make up main pre- letter
Number left-hand rotation green light Qi Liangshi simultaneously green time loss, the left-hand rotation green light of pre-signal needs to open bright in advance：
<mrow>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>t</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mfrac>
<msub>
<mi>l</mi>
<mn>1</mn>
</msub>
<mi>v</mi>
</mfrac>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>t</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<msqrt>
<mrow>
<msup>
<mi>v</mi>
<mn>2</mn>
</msup>
<mo>+</mo>
<mn>2</mn>
<msub>
<mi>al</mi>
<mn>1</mn>
</msub>
</mrow>
</msqrt>
<mo>-</mo>
<mi>v</mi>
</mrow>
<mi>a</mi>
</mfrac>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>14</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, t1Deadline in advance, unit are needed for the straight trip red light of pre-signal：s；
t2Need to open bright time, unit in advance for the left-hand rotation green light of pre-signal：s；
V is the average speed of vehicle, unit：m/s；
l1For the distance between main signal stop line and pre-signal stop line, unit：m；
A is the average starting loop of vehicle, unit：m/s2；
When variable guided vehicle road attribute turns from left to straight, in order to empty main signal straight trip green light open it is bright before master believe in advance
Left turning vehicle between number stop line on road, the left-hand rotation red light of pre-signal needs to end in advance, and in order to make up main pre- letter
Number straight trip green light Qi Liangshi simultaneously green time loss, the straight trip green light of pre-signal needs to open bright in advance：
<mrow>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>t</mi>
<mn>3</mn>
</msub>
<mo>=</mo>
<msub>
<mi>g</mi>
<mi>L</mi>
</msub>
<mo>-</mo>
<mfrac>
<mrow>
<msub>
<mi>q</mi>
<mi>L</mi>
</msub>
<mo>&times;</mo>
<mi>C</mi>
</mrow>
<msub>
<mi>S</mi>
<mi>L</mi>
</msub>
</mfrac>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>t</mi>
<mn>4</mn>
</msub>
<mo>=</mo>
<msub>
<mi>t</mi>
<mn>2</mn>
</msub>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>15</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, t3Deadline in advance, unit are needed for the left-hand rotation red light of pre-signal：s；
t4Need to open bright time, unit in advance for the straight trip green light of pre-signal：s；
gLFor main signal left-hand rotation green time, unit：s；
qLFor the arrival rate of left-hand rotation car, unit：pcu/s；
C is signal period, unit：s；
SLFor the saturation volume rate of left-hand rotation car, unit：pcu/s.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710168676.5A CN107067764B (en) | 2017-03-21 | 2017-03-21 | Self-adaptive control method for variable guide lane of urban intersection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710168676.5A CN107067764B (en) | 2017-03-21 | 2017-03-21 | Self-adaptive control method for variable guide lane of urban intersection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107067764A true CN107067764A (en) | 2017-08-18 |
| CN107067764B CN107067764B (en) | 2020-01-03 |
Family
ID=59617820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710168676.5A Active CN107067764B (en) | 2017-03-21 | 2017-03-21 | Self-adaptive control method for variable guide lane of urban intersection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107067764B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108198441A (en) * | 2018-01-26 | 2018-06-22 | 杨立群 | A kind of quick, intelligent traffic system and method |
| CN108281017A (en) * | 2018-03-16 | 2018-07-13 | 武汉理工大学 | A kind of intersection traffic modulating signal control method based on bus or train route cooperative system |
| CN108281013A (en) * | 2018-03-22 | 2018-07-13 | 安徽八六物联科技有限公司 | A kind of road traffic monitoring system |
| CN108510735A (en) * | 2018-04-09 | 2018-09-07 | 宁波工程学院 | A kind of urban road intersection morning evening peak divides the prediction technique of steering flow |
| CN108983771A (en) * | 2018-07-03 | 2018-12-11 | 天津英创汇智汽车技术有限公司 | Vehicle lane-changing decision-making technique and device |
| CN109448371A (en) * | 2018-11-05 | 2019-03-08 | 王晨 | A kind of real-time variable lane control method and control system |
| CN109559513A (en) * | 2018-12-12 | 2019-04-02 | 武汉理工大学 | A kind of Adaptive Signal Control method based on the prediction of adjacent periods flow difference |
| CN109920244A (en) * | 2017-12-12 | 2019-06-21 | 上海宝康电子控制工程有限公司 | Changeable driveway real-time control system and method |
| CN110097752A (en) * | 2019-03-27 | 2019-08-06 | 杭州远眺科技有限公司 | A kind of intelligent and variable guided vehicle road calculation method |
| CN111145564A (en) * | 2020-01-03 | 2020-05-12 | 山东大学 | Self-adaptive variable lane control method and system for signal control intersection |
| CN111915894A (en) * | 2020-08-06 | 2020-11-10 | 北京航空航天大学 | Variable lane and traffic signal cooperative control method based on deep reinforcement learning |
| CN112017434A (en) * | 2020-08-19 | 2020-12-01 | 公安部交通管理科学研究所 | Variable lane control method and system based on space-time cooperation |
| CN115171402A (en) * | 2022-06-24 | 2022-10-11 | 东南大学 | Method for setting reverse variable guide lanes between adjacent T-shaped intersections |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2668631A1 (en) * | 1990-10-29 | 1992-04-30 | Silec Liaisons Elec | Method for control of the signal lights of a crossroads |
| CN102034350A (en) * | 2009-09-30 | 2011-04-27 | 北京四通智能交通***集成有限公司 | Short-time prediction method and system of traffic flow data |
| JP2011237921A (en) * | 2010-05-07 | 2011-11-24 | Sumitomo Electric Ind Ltd | Signal control device and computer program |
| CN102938204A (en) * | 2012-08-03 | 2013-02-20 | 东南大学 | Variable guiding lane steering function conversion control method of city intersections |
| CN103700273A (en) * | 2014-01-06 | 2014-04-02 | 东南大学 | Signal timing optimization method based on variable guide lane |
| CN104464320A (en) * | 2014-12-15 | 2015-03-25 | 东南大学 | Shortest path induction method based on real road network features and dynamic travel time |
| CN105336163A (en) * | 2015-10-26 | 2016-02-17 | 山东易构软件技术股份有限公司 | Short-term traffic flow forecasting method based on three-layer K nearest neighbor |
| CN106297326A (en) * | 2016-10-27 | 2017-01-04 | 深圳榕亨实业集团有限公司 | Based on holographic road network tide flow stream Lane use control method |
-
2017
- 2017-03-21 CN CN201710168676.5A patent/CN107067764B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2668631A1 (en) * | 1990-10-29 | 1992-04-30 | Silec Liaisons Elec | Method for control of the signal lights of a crossroads |
| CN102034350A (en) * | 2009-09-30 | 2011-04-27 | 北京四通智能交通***集成有限公司 | Short-time prediction method and system of traffic flow data |
| JP2011237921A (en) * | 2010-05-07 | 2011-11-24 | Sumitomo Electric Ind Ltd | Signal control device and computer program |
| CN102938204A (en) * | 2012-08-03 | 2013-02-20 | 东南大学 | Variable guiding lane steering function conversion control method of city intersections |
| CN103700273A (en) * | 2014-01-06 | 2014-04-02 | 东南大学 | Signal timing optimization method based on variable guide lane |
| CN104464320A (en) * | 2014-12-15 | 2015-03-25 | 东南大学 | Shortest path induction method based on real road network features and dynamic travel time |
| CN105336163A (en) * | 2015-10-26 | 2016-02-17 | 山东易构软件技术股份有限公司 | Short-term traffic flow forecasting method based on three-layer K nearest neighbor |
| CN106297326A (en) * | 2016-10-27 | 2017-01-04 | 深圳榕亨实业集团有限公司 | Based on holographic road network tide flow stream Lane use control method |
Non-Patent Citations (2)
| Title |
|---|
| SUN XIN ET.AL: ""A multi-objective model for cordon-based congestion pricing schemes with nonlinear distance tolls"", 《J.CENT.SOUTH UNIV》 * |
| 周鹏 等: ""智能可变车道的导向判决算法的研究与实现"", 《武汉理工大学学报》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109920244A (en) * | 2017-12-12 | 2019-06-21 | 上海宝康电子控制工程有限公司 | Changeable driveway real-time control system and method |
| CN108198441A (en) * | 2018-01-26 | 2018-06-22 | 杨立群 | A kind of quick, intelligent traffic system and method |
| CN108198441B (en) * | 2018-01-26 | 2021-06-29 | 杨立群 | Rapid intelligent traffic system and method |
| CN108281017A (en) * | 2018-03-16 | 2018-07-13 | 武汉理工大学 | A kind of intersection traffic modulating signal control method based on bus or train route cooperative system |
| CN108281013A (en) * | 2018-03-22 | 2018-07-13 | 安徽八六物联科技有限公司 | A kind of road traffic monitoring system |
| CN108510735A (en) * | 2018-04-09 | 2018-09-07 | 宁波工程学院 | A kind of urban road intersection morning evening peak divides the prediction technique of steering flow |
| CN108983771A (en) * | 2018-07-03 | 2018-12-11 | 天津英创汇智汽车技术有限公司 | Vehicle lane-changing decision-making technique and device |
| CN109448371A (en) * | 2018-11-05 | 2019-03-08 | 王晨 | A kind of real-time variable lane control method and control system |
| CN109559513A (en) * | 2018-12-12 | 2019-04-02 | 武汉理工大学 | A kind of Adaptive Signal Control method based on the prediction of adjacent periods flow difference |
| CN109559513B (en) * | 2018-12-12 | 2021-07-20 | 武汉理工大学 | Adaptive signal control method based on adjacent period flow difference prediction |
| CN110097752A (en) * | 2019-03-27 | 2019-08-06 | 杭州远眺科技有限公司 | A kind of intelligent and variable guided vehicle road calculation method |
| CN111145564A (en) * | 2020-01-03 | 2020-05-12 | 山东大学 | Self-adaptive variable lane control method and system for signal control intersection |
| CN111915894A (en) * | 2020-08-06 | 2020-11-10 | 北京航空航天大学 | Variable lane and traffic signal cooperative control method based on deep reinforcement learning |
| CN111915894B (en) * | 2020-08-06 | 2021-07-27 | 北京航空航天大学 | Variable lane and traffic signal cooperative control method based on deep reinforcement learning |
| CN112017434A (en) * | 2020-08-19 | 2020-12-01 | 公安部交通管理科学研究所 | Variable lane control method and system based on space-time cooperation |
| CN115171402A (en) * | 2022-06-24 | 2022-10-11 | 东南大学 | Method for setting reverse variable guide lanes between adjacent T-shaped intersections |
| CN115171402B (en) * | 2022-06-24 | 2023-08-29 | 东南大学 | Method for setting reverse variable guiding lanes between adjacent T-shaped intersections |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107067764B (en) | 2020-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107067764A (en) | A kind of variable guided vehicle road self-adaptation control method of urban intersection | |
| CN103996289B (en) | A kind of flow-speeds match model and Travel Time Estimation Method and system | |
| CN103578273B (en) | A kind of road traffic state estimation method based on microwave radar data | |
| CN105279982B (en) | A kind of Single Intersection dynamic traffic signal control method based on data-driven | |
| CN101639978B (en) | Method capable of dynamically partitioning traffic control subregion | |
| CN104157139B (en) | A kind of traffic congestion Forecasting Methodology and method for visualizing | |
| CN105405293B (en) | A kind of road travel time short term prediction method and system | |
| CN107038864A (en) | A kind of crossing inlet guided vehicle road sets reasonability to sentence method for distinguishing | |
| CN101833862B (en) | False-detection resistant annular coil vehicle detector | |
| CN101894477B (en) | Self-locking control method for controlling road network traffic through urban signal lamps | |
| CN110517485B (en) | Short-term traffic flow prediction method based on time interval division | |
| CN103700274B (en) | A kind of traffic flow detection induction method | |
| CN109215350B (en) | Short-term traffic state prediction method based on RFID electronic license plate data | |
| CN108629973A (en) | Road section traffic volume congestion index computational methods based on fixed test equipment | |
| CN106297326A (en) | Based on holographic road network tide flow stream Lane use control method | |
| CN105355049B (en) | A kind of highway evaluation of running status method based on macroscopical parent map | |
| CN101789176B (en) | Forecasting method for port area short-time traffic flow under model of reservation cargo concentration in port | |
| CN105632198A (en) | City area road traffic coordination control method and city area road traffic coordination system based on fuzzy control | |
| CN102629418A (en) | Fuzzy kalman filtering-based traffic flow parameter prediction method | |
| CN103927887A (en) | Array type FPGA traffic state prediction and control system combined with discrete speed model | |
| CN108335496A (en) | A kind of City-level traffic signal optimization method and system | |
| CN112885088B (en) | Multi-turn road coordination control method based on dynamic traffic flow | |
| CN109087507A (en) | A kind of road traffic signal single-point control Benefit Evaluation Method | |
| CN106845768A (en) | Bus hourage model building method based on survival analysis parameter distribution | |
| CN104900070A (en) | Intersection traffic stream modeling and self-adaption control method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |