CN103198707B - A kind of vehicle regulate and control method based on traffic flow character dangerous under fine day situation - Google Patents

Abstract

The invention discloses a kind of vehicle regulate and control method based on traffic flow character dangerous under fine day situation: step 10) obtains the transport information of accident section; Step 20) gather accident group traffic data under fine day situation; Step 30) gather normal group traffic data under fine day situation; Step 40) set up the total sample of traffic flow data; Step 50) set up initial traffic hazard probabilistic relation formula; Step 60) determine under calibrated fine day state traffic hazard probabilistic relation formula; Step 70) detect the probability that traffic hazard occurs under fine day state in section, and regulate and control vehicle; Step 80) repeat step 70), gather the traffic flow parameter of next setting-up time T, carry out the judgement that traffic hazard probability occurs in section, until detection of end.This vehicle regulate and control method detects through street in real time, under fine day state, traffic hazard probability occurs, and regulates and controls vehicle, reduces traffic hazard.

Description

A kind of vehicle regulate and control method based on traffic flow character dangerous under fine day situation

Technical field

The invention belongs to urban express way vehicular traffic intelligent management and control field, specifically, relate to a kind of vehicle regulate and control method based on traffic flow character dangerous under fine day situation.

Background technology

In order to carry out traffic accident black-spots discriminating, evaluate the impact of various means of transportation for traffic safety, conventional traffic security study predicts a road or the expectation accident frequency (or accident rate) of some road section within following a period of time by traffic Accident Forecast Model.Conventional traffic accident prediction model adopts the data such as (being generally 1 year) traffic parameter mean value (as annual average daily traffic etc.), means of transportation feature (as number of track-lines, shoulder width etc.) and environmental baseline (as weather condition, pavement behavior etc.) in a certain long period section to set up traffic hazard frequency and the volume of traffic, macro-relation between roadway characteristic and environmental characteristic usually.

Along with the development of intelligent transport technology, the accuracy of detection of Traffic flow detecting equipment is more and more higher, and increasing highway starts to be equipped with various Traffic flow detecting equipment, such as earth coil, traffic flow video recognition system, microwave detector etc.Simultaneously, the telecommunication flow information that before many scholars are occurred by research traffic hazard, Traffic flow detecting equipment captures finds, there is certain statistical relationship in traffic flow character and traffic hazard, namely there is excessive risk traffic flow modes, correspond to higher contingency occurrence probability.How the appearance of real time discriminating excessive risk traffic flow modes becomes one of gordian technique of freeway dynamic traffic safety management system, when excessive risk traffic flow modes being detected, system is eliminated excessive risk traffic flow modes by control algolithm thus is reached the object reducing street accidents risks.

Although there are some researches show, the traffic data that excessive risk traffic flow modes can be obtained by Traffic flow detecting on highway differentiates.But existing research often have ignored the impact of weather condition on street accidents risks, and namely under different weather condition, (such as fine day and rainy day) excessive risk traffic flow modes feature is not identical.

Summary of the invention

Technical matters: technical matters to be solved by this invention is: a kind of vehicle regulate and control method based on traffic flow character dangerous under fine day situation is provided, this vehicle regulate and control method utilizes Traffic flow detecting equipment to obtain real time traffic data, traffic hazard probability is there is in real-time detection through street under fine day state, vehicle is regulated and controled, reduces traffic hazard.

Technical scheme: for solving the problems of the technologies described above, the vehicle regulate and control method based on traffic flow character dangerous under fine day situation that the present invention adopts, this vehicle regulate and control method comprises the following steps:

Step 10) obtains the transport information of accident section: on through street, install q Traffic flow detecting equipment, through street between adjacent two Traffic flow detecting equipment is set to a section, gather the traffic accident information of section to be detected under fine day situation, comprise time of origin and the scene of each traffic hazard, and establish two the Traffic flow detecting equipment being positioned at traffic hazard scene upstream and downstream; Q be greater than 1 integer;

Step 20) gather accident group traffic data under fine day situation: by being arranged on two Traffic flow detecting equipment of traffic hazard scene upstream and downstream, gather the accident group traffic data of this section under fine day state before traffic hazard generation, described accident group traffic data comprises the upstream traffic occupation rate mean value x of this section before traffic hazard occurs, in setting-up time T ₁, downstream car speed standard deviation x ₂, the absolute value x of upstream and downstream car speed difference ₃3 traffic flow parameters;

Step 30) gather normal group traffic data under fine day situation: corresponding to often playing traffic hazard under fine day situation, normal group traffic data under random selecting S fine day situation, described normal group traffic data comprises by being positioned at traffic hazard scene upstream and downstream two Traffic flow detecting equipment, when there is not traffic hazard in this section, in setting-up time T, the upstream traffic occupation rate mean value x of collection ₁, downstream car speed standard deviation x ₂, the absolute value x of upstream and downstream car speed difference ₃; S be greater than 1 integer;

Step 40) set up the total sample of traffic flow data under fine day situation: by step 20) accident group traffic data under the fine day situation that gathers and step 30) normal group traffic data under the fine day situation that gathers, be combined into the total sample of traffic flow data, the total sample of traffic flow data contains n subsample;

Step 50) utilize probit method, set up the initial traffic hazard probabilistic relation formula under fine day state as the formula (1):

$P(y_i=1|x_i)=\frac{1}{\sqrt{2\mathrm{\π}}}{\∫}_{-\∞}^{{\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i}}\exp (-\frac{{({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})}^2}{2})d({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})$ Formula (1)

In formula (1), i=1,2 ..., n; P (y _i=1|x _i) to represent in traffic flow data total sample that the probability of traffic hazard occurs in i-th subsample, y _irepresent the situation of i-th subsample generation traffic hazard in the total sample of traffic flow data, y _ivalue be 1 or 0, y _i=1 represents that in the total sample of traffic flow data, i-th subsample traffic hazard occurs, y _i=0 represents that in the total sample of traffic flow data, i-th subsample traffic hazard does not occur, P (y _i=0|x _i) to represent in traffic flow data total sample that the probability of traffic hazard does not occur in i-th subsample, P (y _i=0|x _i)=1-P (y _i=1|x _i); x _1irepresent the upstream traffic occupation rate mean value of i-th subsample in the total sample of traffic flow data, x _2irepresent the downstream car speed standard deviation of i-th subsample in the total sample of traffic flow data, x _3irepresent the absolute value of the upstream and downstream car speed difference of i-th subsample in the total sample of traffic flow data, β ₀for constant coefficient, β ₁for x _1icoefficient, β ₂for x _2icoefficient, β ₃for x _3icoefficient;

Step 60) determine under calibrated fine day state traffic hazard probabilistic relation formula:

By the maximal value of measuring and calculating formula (2), determine β ₀, β ₁, β ₂, β ₃value;

$\ln L\left(x_i\right)=\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\left(\begin{array}{c}{y}_i\ln \frac{1}{\sqrt{2\mathrm{\π}}}{\∫}_{-\∞}^{{\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i}}\exp (-\frac{{({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})}^2}{2})d({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})\\ +(1-y_i)\ln (1-\frac{1}{\sqrt{2\mathrm{\π}}}{\∫}_{-\∞}^{{\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i}}\exp (-\frac{{({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})}^2}{2}))d({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})\end{array}\right)$ Formula (2)

Wherein, lnL (x _i) represent the natural logarithm value of likelihood function;

Then the β will recorded ₀, β ₁, β ₂, β ₃value is brought in formula (1), as the traffic hazard probabilistic relation formula under calibrated fine day state;

Step 70) detect the probability that traffic hazard occurs under fine day state in section, and regulate and control vehicle: set this through street under fine day state, the threshold value that traffic hazard probability occurs is P ₀the Traffic flow detecting equipment utilizing step 10) to arrange, gather 3 the traffic flow parameters of current section to be detected in setting-up time T, then bring current 3 traffic flow parameters into step 60) in the traffic hazard probabilistic relation formula set up, obtain traffic hazard probable value P (y _i=1|x _i), if P is (y _i=1|x _i) >P ₀then show that this section is current and have the risk that traffic hazard occurs, by variable message board, early warning is carried out to driver in this front, section, and start opertaing device, by controlling the ring road of through street or the Intersections of through street, reduce upstream vehicle flow, by variable speed-limit plate to Current vehicle speed limit, reduce the travel speed of upstream vehicle; As P (y _i=1|x _i)≤P ₀time, then show that this section is current for safe condition, without the need to giving the alarm prompting;

Step 80) repeat step 70), gather the traffic flow parameter of next setting-up time T, carry out the judgement that traffic hazard probability occurs in section, and then vehicle is regulated and controled, until detection of end.

Beneficial effect: compared with prior art, technical scheme of the present invention has following beneficial effect:

1. vehicle regulation and control accuracy rate is high, improves the driving safety of vehicle.Existing traffic hazard Probability Detection method only utilizes traffic flow data to calculate traffic hazard probability, does not consider the impact of weather conditions on traffic hazard.Vehicle regulate and control method of the present invention is specially for the vehicle regulation and control under fine day state.The present invention gathers traffic flow parameter, and adds the influence factor of fine day state to traffic hazard, can improve traffic hazard Probability Detection precision.Traffic hazard probabilistic relation formula under the fine day state that the present invention sets up, considers the impact of weather conditions on traffic hazard.Like this, this traffic hazard probabilistic relation formula just can reflect that the probability of traffic hazard occurs in section more accurately, because it is not only relevant with vehicle itself, also relevant with accident weather conditions at that time that traffic hazard occurs.The traffic data in the section of Real-time Collection is brought in traffic hazard probabilistic relation formula, in real time traffic hazard is occurred to section and detect.According to traffic hazard probability, determine current the need of startup early warning means, reduce street accidents risks, thus improve the accuracy rate of vehicle regulation and control, reduce traffic hazard, effectively ensured the traffic safety of through street.

2. testing process is simple.In step 70 of the present invention) after traffic hazard probabilistic relation formula under the fine day state of establishing, only need to gather the new traffic flow parameter in section, just can in real-time estimate setting-up time, the probability of this section generation traffic hazard, easy to use, practical, there is good application prospect.

Accompanying drawing explanation

Fig. 1 is the laying schematic diagram of through street of the present invention.

Fig. 2 is FB(flow block) of the present invention.

Embodiment

Below in conjunction with drawings and Examples, technical scheme of the present invention is described in further detail.

As depicted in figs. 1 and 2, the vehicle regulate and control method based on traffic flow character dangerous under fine day situation of the present invention, comprises the following steps:

Step 10) obtains the transport information of accident section: on through street, install q Traffic flow detecting equipment, through street between adjacent two Traffic flow detecting equipment is set to a section, gather the traffic accident information of section to be detected under fine day situation, comprise time of origin and the scene of each traffic hazard, and establish two the Traffic flow detecting equipment being positioned at traffic hazard scene upstream and downstream.Q be greater than 1 integer.

In step 10), the spacing of two adjacent Traffic flow detecting equipment is 500 meters to 1500 meters, and Traffic flow detecting equipment is evenly arranged along through street.Traffic flow detecting equipment is electromagnetic induction coil, or video traffic flow assay device.

Step 20) gather accident group traffic data under fine day situation: by being arranged on two Traffic flow detecting equipment of traffic hazard scene upstream and downstream, gather the accident group traffic data of this section under fine day state before traffic hazard generation, described accident group traffic data comprises the upstream traffic occupation rate mean value x of this section before traffic hazard occurs, in setting-up time T ₁, downstream car speed standard deviation x ₂with the absolute value x of upstream and downstream car speed difference ₃3 traffic flow parameters.

In step 20) in, by upstream and downstream two Traffic flow detecting equipment, the traffic flow data in section to be detected is gathered according to sampling step length, this traffic flow data comprises upstream traffic occupation rate, upstream car speed and downstream car speed, then calculate mean value or the standard deviation of each parameter every setting-up time T, obtain upstream traffic occupation rate mean value x ₁, downstream car speed standard deviation x ₂with the absolute value x of upstream and downstream car speed difference ₃.Sampling step length is preferably 30 seconds.Setting-up time T is preferably 5-10 minutes.

Step 30) gather normal group traffic data under fine day situation: corresponding to often playing traffic hazard under fine day situation, normal group traffic data under random selecting S fine day situation, described normal group traffic data comprises by being positioned at traffic hazard scene upstream and downstream two Traffic flow detecting equipment, when there is not traffic hazard in this section, in setting-up time T, the upstream traffic occupation rate mean value x of collection ₁, downstream car speed standard deviation x ₂with the absolute value x of upstream and downstream car speed difference ₃.S be greater than 1 integer.As preferably, S equals 10.

Step 40) set up the total sample of traffic flow data under fine day situation: by step 20) accident group traffic data under the fine day situation that gathers and step 30) normal group traffic data under the fine day situation that gathers, be combined into the total sample of traffic flow data, the total sample of traffic flow data contains n subsample.

Step 50) utilize probit method, set up the initial traffic hazard probabilistic relation formula under fine day state as the formula (1):

$P(y_i=1|x_i)=\frac{1}{\sqrt{2\mathrm{\π}}}{\∫}_{-\∞}^{{\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i}}\exp (-\frac{{({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})}^2}{2})d({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})$

Formula (1)

In formula (1), i=1,2 ..., n; P (y _i=1|x _i) to represent in traffic flow data total sample that the probability of traffic hazard occurs in i-th subsample, y _irepresent the situation of i-th subsample generation traffic hazard in the total sample of traffic flow data, y _ivalue be 1 or 0, y _i=1 represents that in the total sample of traffic flow data, i-th subsample traffic hazard occurs, y _i=0 represents that in the total sample of traffic flow data, i-th subsample traffic hazard does not occur, P (y _i=0|x _i) to represent in traffic flow data total sample that the probability of traffic hazard does not occur in i-th subsample, P (y _i=0|x _i)=1-P (y _i=1|x _i); x _1irepresent the upstream traffic occupation rate mean value of i-th subsample in the total sample of traffic flow data, x _2irepresent the downstream car speed standard deviation of i-th subsample in the total sample of traffic flow data, x _3irepresent the absolute value of the upstream and downstream car speed difference of i-th subsample in the total sample of traffic flow data, β ₀for constant coefficient, β ₁for x _1icoefficient, β ₂for x _2icoefficient, β ₃for x _3icoefficient.

Step 60) determine under calibrated fine day state traffic hazard probabilistic relation formula:

By the maximal value of measuring and calculating formula (2), determine β ₀, β ₁, β ₂, β ₃value;

$\ln L\left(x_i\right)=\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\left(\begin{array}{c}{y}_i\ln \frac{1}{\sqrt{2\mathrm{\π}}}{\∫}_{-\∞}^{{\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i}}\exp (-\frac{{({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})}^2}{2})d({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})\\ +(1-y_i)\ln (1-\frac{1}{\sqrt{2\mathrm{\π}}}{\∫}_{-\∞}^{{\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i}}\exp (-\frac{{({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})}^2}{2}))d({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})\end{array}\right)$ Formula (2)

Wherein, lnL (x _i) represent the natural logarithm value of likelihood function;

Then the β will recorded ₀, β ₁, β ₂, β ₃value is brought in formula (1), as the traffic hazard probabilistic relation formula under calibrated fine day state;

Step 70) detect the probability that traffic hazard occurs under fine day state in section, and regulate and control vehicle: set this through street under fine day state, the threshold value that traffic hazard probability occurs is P ₀the Traffic flow detecting equipment utilizing step 10) to arrange, gather 3 the traffic flow parameters of current section to be detected in setting-up time T, then bring current 3 traffic flow parameters into step 60) in the traffic hazard probabilistic relation formula set up, obtain traffic hazard probable value P (y _i=1|x _i), if P is (y _i=1|x _i) >P ₀then show that this section is current and have the risk that traffic hazard occurs, by variable message board, early warning is carried out to driver in this front, section, and start opertaing device, by controlling the ring road of through street or the Intersections of through street, reduce upstream vehicle flow, by variable speed-limit plate to Current vehicle speed limit, reduce the travel speed of upstream vehicle; As P (y _i=1|x _i)≤P ₀time, then show that this section is current for safe condition, without the need to the prompting that gives the alarm.By variable speed-limit plate to Current vehicle speed limit, the car speed amplitude of each adjustment change is within 5km/h.As preferably, P ₀equal 0.1.

Step 80) repeat step 70), gather the traffic flow parameter of next setting-up time T, carry out the judgement that traffic hazard probability occurs in section, and then vehicle is regulated and controled, until detection of end.

Dangerous traffic flow character refers to that traffic flow character correspond to higher traffic hazard probability of happening.The telecommunication flow information captured by Traffic flow detecting equipment is found, traffic flow character and traffic hazard exist certain relation.That is, dangerous traffic flow character, correspond to higher contingency occurrence probability.

In vehicle regulate and control method of the present invention, the pick-up unit of application comprises Traffic flow detecting equipment.Traffic flow detecting equipment is according to setting step-length, the traffic data in Real-time Collection section to be detected.

Bring the arithmetic for real-time traffic flow parameter collected into step 60 of the present invention) in traffic hazard probabilistic relation formula under the fine day state set up, calculate the probability of current generation traffic hazard.If the probable value recorded is greater than the probability threshold value P of setting ₀, then showing that this section is current has the risk that traffic hazard occurs, and should give the alarm, and the control program activated in dynamic traffic control system reduces accident risk, then continues image data; If the probable value recorded is less than or equal to the probability threshold value P of setting ₀, then without the need to sending early warning, vehicle not being regulated and controled, continuing image data, judging next time.

Vehicle regulate and control method of the present invention is according to the real time traffic data gathered, judging that section to be detected is current and whether there is the risk that traffic hazard occurs, is the probability adopting the traffic hazard probabilistic relation formula set up by probit method to judge section to be detected generation traffic hazard.

Practice process of the present invention is divided into the traffic hazard probabilistic relation formula set up under fine day state, and detects traffic hazard probability and regulation and control vehicle two processes.

Set up the traffic hazard probabilistic relation formula under fine day state: collect or gather the traffic data in the setting-up time of section to be detected.In order to ensure that the accident probability relational expression set up can have good precision of prediction, the sample of collection is as far as possible large, and usual accident group data sample is greater than 200, and normal group data sample is greater than 400.According to above-mentioned steps 10) to step 60) set up traffic hazard probabilistic relation formula under fine day state.

Detect traffic hazard probability and regulation and control vehicle: the upstream traffic occupation rate mean value x in Real-time Collection section to be detected ₁, downstream car speed standard deviation x ₂with the absolute value x of upstream and downstream car speed difference ₃, these 3 traffic flow parameters are substituted in the traffic hazard probabilistic relation formula under the fine day state set up, according to the probable value that this relational expression is calculated, real-time estimate are carried out to through street traffic hazard.If the probable value obtained is greater than threshold value P ₀, show that detecting section has the possibility that traffic hazard occurs, then carry out early warning by variable message board to driver in this front, section, and start opertaing device, reduce upstream vehicle flow and travel speed; Otherwise, when probable value is less than or equal to threshold value P ₀, showing that this section is less at the probability of current generation traffic hazard, is safe condition, without the need to regulating and controlling vehicle.

Embodiment

Utilize the true traffic flow on U.S. markon welfare Asia I-880 road and casualty data, the performance of test the present invention under fine day state in traffic hazard real-time estimate.The data gathered comprise upstream traffic occupation rate mean value x ₁, downstream car speed standard deviation x ₂with the absolute value x of upstream and downstream car speed difference ₃.

Existing 729 accident group traffic data samples, and 7290 normal group traffic data samples (namely the traffic data gathered under traffic hazard condition does not occur).From whole sample, random selecting 510 accident group traffic data samples and 5100 normal group traffic data samples are used as training set.219 remaining accident group traffic data samples and 2190 normal group traffic data samples are used as detected set, are used for testing precision of prediction of the present invention.

Combined training collection, according to step 10) of the present invention to step 60) set up traffic hazard probabilistic relation formula under calibrated fine day state, the traffic flow parameter in this relational expression and coefficient as shown in table 1.

Table 1

Traffic flow parameter	Coefficient
		Upstream traffic occupation rate mean value (x 1）	0.036（β 1）
Downstream car speed standard deviation (x 2）	0.059（β 2）
		Absolute value (the x of upstream and downstream car speed difference 3）	0.074（β 3）
Constant	-3.579（β 0）

The traffic hazard probabilistic relation formula under this fine day state is utilized to differentiate the detected set comprising 219 accident group traffic data samples and 2190 normal group traffic data samples, the detection accuracy of this traffic hazard probabilistic relation formula to accident group traffic data sample is 59.0%, be 76.7% to the detection accuracy of normal group traffic data sample, total detection accuracy is 75.1%.Therefore, method of the present invention is by detecting through street traffic hazard probability, and regulation and control vehicle, can effectively reduce the generation of traffic hazard.Method of the present invention has actual engineering application and is worth.

Claims (2)

1. based on a vehicle regulate and control method for traffic flow character dangerous under fine day situation, it is characterized in that, this vehicle regulate and control method comprises the following steps:

Step 10) obtain the transport information of accident section: q Traffic flow detecting equipment is installed on through street, through street between adjacent two Traffic flow detecting equipment is set to a section, gather the traffic accident information of section to be detected under fine day situation, comprise time of origin and the scene of each traffic hazard, and establish two the Traffic flow detecting equipment being positioned at traffic hazard scene upstream and downstream; The spacing of two adjacent Traffic flow detecting equipment is 500 meters to 1500 meters, and Traffic flow detecting equipment is evenly arranged along through street; Q be greater than 1 integer;

Step 20) gather accident group traffic data under fine day situation: by being arranged on two Traffic flow detecting equipment of traffic hazard scene upstream and downstream, gather the accident group traffic data of this section under fine day state before traffic hazard generation, described accident group traffic data comprises the upstream traffic occupation rate mean value x of this section before traffic hazard occurs, in setting-up time T ₁, downstream car speed standard deviation x ₂with the absolute value x of upstream and downstream car speed difference ₃3 traffic flow parameters; By section to be detected upstream and downstream two Traffic flow detecting equipment, gather the traffic flow parameter in section to be detected according to sampling step length, described sampling step length is 30 seconds;

Step 30) gather normal group traffic data under fine day situation: corresponding to often playing traffic hazard under fine day situation, normal group traffic data under random selecting S fine day situation, described normal group traffic data comprises by being positioned at traffic hazard scene upstream and downstream two Traffic flow detecting equipment, when there is not traffic hazard in this section, in setting-up time T, the upstream traffic occupation rate mean value x of collection ₁, downstream car speed standard deviation x ₂with the absolute value x of upstream and downstream car speed difference ₃; S=10;

Step 40) set up the total sample of traffic flow data under fine day situation: by step 20) accident group traffic data under the fine day situation that gathers and step 30) normal group traffic data under the fine day situation that gathers, be combined into the total sample of traffic flow data, the total sample of traffic flow data contains n subsample;

Step 50) utilize probit method, set up such as formula the initial traffic hazard probabilistic relation formula under the fine day state shown in (1):

$P(y_i=1|x_i)=\frac{1}{\sqrt{2\mathrm{\π}}}{\∫}_{-\∞}^{{\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i}}\exp (-\frac{{({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})}^2}{2})d({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})$

Formula (1)

In formula (1), i=1,2 ..., n; P (y _i=1|x _i) to represent in traffic flow data total sample that the probability of traffic hazard occurs in i-th subsample, y _irepresent the situation of i-th subsample generation traffic hazard in the total sample of traffic flow data, y _ivalue be 1 or 0, y _i=1 represents that in the total sample of traffic flow data, i-th subsample traffic hazard occurs, y _i=0 represents that in the total sample of traffic flow data, i-th subsample traffic hazard does not occur, P (y _i=0|x _i) to represent in traffic flow data total sample that the probability of traffic hazard does not occur in i-th subsample, P (y _i=0|x _i)=1-P (y _i=1|x _i); x _1irepresent the upstream traffic occupation rate mean value of i-th subsample in the total sample of traffic flow data, x _2irepresent the downstream car speed standard deviation of i-th subsample in the total sample of traffic flow data, x _3irepresent the absolute value of the upstream and downstream car speed difference of i-th subsample in the total sample of traffic flow data, β ₀for constant coefficient, β ₁for x _1icoefficient, β ₂for x _2icoefficient, β ₃for x _3icoefficient;

Step 60) determine under calibrated fine day state traffic hazard probabilistic relation formula:

By the maximal value of measuring and calculating formula (2), determine β ₀, β ₁, β ₂, β ₃value;

$\ln L\left(x_i\right)=\underset{i=1}{\overset{n}{\mathrm{\Σ}}}\left(\begin{array}{c}{y}_i\ln \frac{1}{\sqrt{2\mathrm{\π}}}{\∫}_{-\∞}^{{\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i}}\exp (-\frac{{({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})}^2}{2})d({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})\\ +(1-y_i)\ln (1-\frac{1}{\sqrt{2\mathrm{\π}}}{\∫}_{-\∞}^{{\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i}}\exp (-\frac{{({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})}^2}{2}))d({\mathrm{\β}}_0+{\mathrm{\β}}_1{x}_{1i}+{\mathrm{\β}}_2{x}_{2i}+{\mathrm{\β}}_3{x}_{3i})\end{array}\right)$

Formula (2)

Wherein, lnL (x _i) represent the natural logarithm value of likelihood function;

Then the β will recorded ₀, β ₁, β ₂, β ₃value is brought in formula (1), as the traffic hazard probabilistic relation formula under calibrated fine day state;

Step 70) detect the probability that traffic hazard occurs under fine day state in section, and regulate and control vehicle: set this through street under fine day state, the threshold value that traffic hazard probability occurs is P ₀utilize step 10) the Traffic flow detecting equipment that arranges, gather 3 the traffic flow parameters of current section to be detected in setting-up time T, then bring current 3 traffic flow parameters into step 60) in the traffic hazard probabilistic relation formula set up, obtain traffic hazard probable value P (y _i=1|x _i), if P is (y _i=1|x _i) >P ₀then show that this section is current and have the risk that traffic hazard occurs, by variable message board, early warning is carried out to driver in this front, section, and start opertaing device, by controlling the ring road of through street or the Intersections of through street, reduce upstream vehicle flow, by variable speed-limit plate to Current vehicle speed limit, the car speed amplitude of each adjustment change, within 5km/h, reduces the travel speed of upstream vehicle; As P (y _i=1|x _i)≤P ₀time, then show that this section is current for safe condition, without the need to giving the alarm prompting; Described setting-up time T is 5-10 minutes; P ₀equal 0.1;

Step 80) repeat step 70), gather the traffic flow parameter of next setting-up time T, carry out the judgement that traffic hazard probability occurs in section, and then vehicle is regulated and controled, until detection of end.

2. according to the vehicle regulate and control method based on traffic flow character dangerous under fine day situation according to claim 1, it is characterized in that, described Traffic flow detecting equipment is electromagnetic induction coil, or video traffic flow assay device.