CN103198711B - Vehicle regulating and controlling method of lowering probability of traffic accidents of different severity - Google Patents
Vehicle regulating and controlling method of lowering probability of traffic accidents of different severity Download PDFInfo
- Publication number
- CN103198711B CN103198711B CN201310093427.6A CN201310093427A CN103198711B CN 103198711 B CN103198711 B CN 103198711B CN 201310093427 A CN201310093427 A CN 201310093427A CN 103198711 B CN103198711 B CN 103198711B
- Authority
- CN
- China
- Prior art keywords
- traffic
- traffic flow
- value
- represent
- accident
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention discloses a vehicle regulating and controlling method of lowering a probability of traffic accidents of different severity. The method includes the steps: (10) obtaining traffic information of an accident road section; (20) collecting traffic data of the accident road section before accidents happen; (30) collecting the traffic data of the accident road section in a normal state; (40) setting up a traffic flow data sample; (50) setting up a probability function of the traffic accidents of three stages after standardization; (60) measuring and calculating the probability of occurrence of the traffic accidents of the different severity; (70) measuring and calculating a probability threshold value of the traffic accidents of the different severity; (80) detecting the probability of the traffic accidents of the different severity of the road section in real time, and regulating and controlling vehicles; and (90) repeating the step (80), carrying out detection on the probability of the traffic accidents on the road section in following set time T, and regulating and controlling the vehicles until the detection is finished. The vehicle regulating and controlling method detects the probability of the traffic accidents of the different severity in real time, regulates and controls the vehicles, and improves driving safety.
Description
Technical field
The invention belongs to through street technical field of intelligent traffic, specifically, relate to a kind of vehicle regulate and control method reducing different order of severity traffic hazard probability.
Background technology
According to the injures and deaths degree of personnel in traffic hazard, traffic hazard can be divided into different brackets.The lightest incident classification is for only to have property loss (without injures and deaths) accident, and the heaviest incident classification is for there being personnel death's accident.Different order of severity traffic hazards cause the impact of distinct program on economic loss and road.The higher traffic hazard of menace level, not only to causing socioeconomic massive losses, being caused also to the operational efficiency of highway and urban express way simultaneously and having a strong impact on.Thus, how to prevent the generation of the traffic hazard that menace level is higher, such as severely injured or fatal accident, has important practical value and economic implications.
Along with the development of intelligent transport technology, the field of traffic safety traffic flow data utilizing Traffic flow detecting equipment to obtain that begins one's study sets up traffic hazard real-time prediction model.The place different from conventional traffic accident forecast is, traffic hazard real-time prediction model can predict the change at short notice of traffic hazard probability, such as, in 5 minutes, and conventional traffic accident prediction model can only predict the traffic hazard quantity of (in such as following 1 year) in the very longer time in future.Thus, compared with conventional traffic accident prediction model, traffic hazard real-time prediction model is applicable to applying in highway and urban express way intelligent transportation system more, detects the dangerous traffic flow modes of high accident risk in real time.
But most of existing real-time traffic accident prediction model only can predict to traffic hazard probability that unpredictable current traffic accidents menace level cannot provide the probability of each menace level traffic hazard current.The traffic hazard of high menace level causes great impact to social economy and driver's health, thus the traffic hazard for different menace level in highway and urban express way intelligent transportation system should adopt different preventive measure, should adopt the strongest intervention Prevention and control strategy to the traffic hazard of high menace level.
Summary of the invention
Technical matters: technical matters to be solved by this invention is: a kind of vehicle regulate and control method reducing different order of severity traffic hazard probability is provided, this vehicle regulate and control method utilizes Traffic flow detecting equipment to obtain real time traffic data, there is the probability of only property loss accident PDO, slight personal injury accident BC, severe injury or fatal accident KA in real-time detection through street, and then vehicle is regulated and controled accordingly, reduce traffic hazard to occur, improve vehicle driving safety.
Technical scheme: for solving the problems of the technologies described above, the vehicle regulate and control method of the reduction that the present invention adopts different order of severity traffic hazard probability, 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, utilize Traffic flow detecting equipment to gather the traffic hazard data of this through street, and establishment often play traffic hazard scene upstream and downstream two Traffic flow detecting equipment; According to traffic hazard menace level, traffic hazard is fallen into three classes: only property loss accident PDO, slight personal injury accident BC, severe injury or fatal accident KA; Q be greater than 1 integer;
Step 20) gather the traffic data of accident section before accident occurs: often play traffic hazard scene upstream and downstream two Traffic flow detecting equipment by being arranged on, gather the traffic data of all kinds of traffic hazard, described traffic data comprises: before often playing traffic hazard generation, the upstream magnitude of traffic flow mean value x in setting-up time T
1, upstream traffic occupation rate mean value x
2, upstream car speed mean value x
3, upstream magnitude of traffic flow standard deviation x
4, upstream traffic occupation rate standard deviation x
5, upstream car speed standard deviation x
6, downstream magnitude of traffic flow mean value x
7, downstream traffic occupation rate mean value x
8, downstream car speed mean value x
9, downstream magnitude of traffic flow standard deviation x
10, downstream traffic occupation rate standard deviation x
11, downstream car speed standard deviation x
12, the mean value x of difference in flow absolute value between the adjacent lane of upstream
13, occupy the mean value x of rate variance absolute value between the adjacent lane of upstream
14, the mean value x of car speed difference absolute value between the adjacent lane of upstream
15, the mean value x of difference in flow absolute value between the adjacent lane of downstream
16, occupy the mean value x of rate variance absolute value between the adjacent lane of downstream
17, the mean value x of car speed difference absolute value between the adjacent lane of downstream
18, upstream and downstream magnitude of traffic flow difference absolute value x
19, upstream and downstream traffic occupies the absolute value x of rate variance
20with the absolute value x of upstream and downstream car speed difference
2121 traffic flow parameters;
Step 30) gather accident section traffic data in normal state: to often playing traffic hazard, adopt case-control study method, ratio in 1: a is chosen traffic hazard and section traffic data is in normal state occurred, state when described normal condition refers to that traffic hazard do not occur in section, described 1: a refers to the traffic data corresponding to and often play traffic hazard, chooses this traffic hazard and section a group traffic data in normal state occurs; Described traffic data of often organizing comprises the upstream magnitude of traffic flow mean value x of this section in setting-up time T
1, upstream traffic occupation rate mean value x
2, upstream car speed mean value x
3, upstream magnitude of traffic flow standard deviation x
4, upstream traffic occupation rate standard deviation x
5, upstream car speed standard deviation x
6, downstream magnitude of traffic flow mean value x
7, downstream traffic occupation rate mean value x
8, downstream car speed mean value x
9, downstream magnitude of traffic flow standard deviation x
10, downstream traffic occupation rate standard deviation x
11, downstream car speed standard deviation x
12, the mean value x of difference in flow absolute value between the adjacent lane of upstream
13, occupy the mean value x of rate variance absolute value between the adjacent lane of upstream
14, the mean value x of car speed difference absolute value between the adjacent lane of upstream
15, the mean value x of difference in flow absolute value between the adjacent lane of downstream
16, occupy the mean value x of rate variance absolute value between the adjacent lane of downstream
17, the mean value x of car speed difference absolute value between the adjacent lane of downstream
18, upstream and downstream magnitude of traffic flow difference absolute value x
19, upstream and downstream traffic occupies the absolute value x of rate variance
20with the absolute value x of upstream and downstream car speed difference
2121 traffic flow parameters; A be more than or equal to 2 integer;
Step 40) set up traffic flow data sample: by step 20) traffic data before accident occurs of the Three Estate traffic hazard that gathers and step 30) traffic data under the normal condition that gathers, be combined into traffic flow data sample, this traffic flow data sample comprises n subsample;
Step 50) set up calibrated three stages traffic hazard probability function: comprise and set up calibrated first stage traffic hazard probability function, calibrated subordinate phase traffic hazard probability function and calibrated phase III traffic hazard probability function successively, specifically comprise step 501) to step 503)
Step 501) set up calibrated first stage traffic hazard probability function, comprise step 5011) to step 5013):
Step 5011) utilize binary logistic regression structure first stage initial traffic hazard probability function as the formula (1),
Wherein, i=1,2 ..., n; P
(1)(y
1i=1|x
i) to represent in traffic flow data sample that the probability of traffic hazard occurs in first stage traffic hazard probability function in i-th subsample, y
1irepresent the situation of i-th subsample generation traffic hazard in traffic flow data sample, y
1ivalue be 1 or 0, y
1i=1 represents that traffic hazard occurs in i-th subsample, y
1i=0 represents that i-th subsample traffic hazard does not occur, P
(1)(y
1i=0x
i) to represent in traffic flow data sample that the probability of traffic hazard does not occur in i-th subsample, P
(1)(y
1i=0x
i)=1-P
(1)(y
1i=1x
i); x
1irepresent the 1st traffic flow parameter of i-th subsample, x
2irepresent the 2nd traffic flow parameter of i-th subsample, x
21irepresent the 21st traffic flow parameter in i-th subsample, β
1_0represent the constant coefficient in first stage traffic hazard probability function, β
1_1represent in first stage traffic hazard probability function, the coefficient of the 1st traffic flow parameter; β
1_2represent in first stage traffic hazard probability function, the coefficient of the 2nd traffic flow parameter; β
1_21represent in first stage traffic hazard probability function, the coefficient of the 21st traffic flow parameter;
Step 5012) by the maximal value of measuring and calculating formula (2), obtain β
1_0, β
1_1, β
1_2..., β
1_21the value of 22 coefficients:
Wherein, wherein, lnL (β
1, x
i) represent the natural logarithm value of likelihood function;
Step 5013) by step 5012) saliency value of 22 coefficients that obtains compares with setting value B respectively, if the saliency value of coefficient is less than setting value B, then in formula (1), retain traffic flow parameter corresponding to this coefficient, otherwise in formula (1), delete traffic flow parameter corresponding to this coefficient, and be back to step 5011), until the saliency value of the coefficient of traffic flow parameter remaining in formula (1) is all less than setting value B, as calibrated first stage traffic hazard probability function;
Step 502) set up calibrated subordinate phase traffic hazard probability function, comprise step 5021) to step 5023):
Step 5021) in step 40) in the traffic flow data sample set up, delete the traffic data under normal condition, form subordinate phase traffic flow data sample, then utilize the binary logistic regression structure initial traffic hazard probability function of subordinate phase as the formula (3):
Wherein, i=1,2 ..., n
2; n
2represent the subsample quantity that subordinate phase traffic flow data sample packages contains; P
(2)(y
2i=1|x
i) to represent in subordinate phase traffic flow data sample that the probability of slight personal injury accident BC, severe injury or fatal accident KA occurs in subordinate phase traffic hazard probability function in i-th subsample, y
2irepresent the situation of i-th subsample generation traffic hazard in subordinate phase traffic flow data sample, y
2ivalue be 1 or 0, y
2i=1 represents that in subordinate phase traffic flow data sample, slight personal injury accident BC or severely injured or fatal accident KA, y occur in i-th subsample
2i=0 represents that in subordinate phase traffic flow data sample, only property loss accident PDO, P occur in i-th subsample
(2)(y
2i=0x
i) to represent in subordinate phase traffic flow data sample that the probability of only property loss accident PDO occurs in i-th subsample, P
(2)(y
2i=0x
i)=1-P
(2)(y
2i=1x
i); x
1irepresent the 1st traffic flow parameter of i-th subsample in subordinate phase traffic flow data sample, x
2irepresent the 2nd traffic flow parameter of i-th subsample in subordinate phase traffic flow data sample, x
21irepresent the 21st traffic flow parameter in i-th subsample in subordinate phase traffic flow data sample, β
2_0represent the constant coefficient in subordinate phase traffic hazard probability function, β
2_1represent in subordinate phase traffic hazard probability function, the coefficient of the 1st traffic flow parameter; β
2_2represent in subordinate phase traffic hazard probability function, the coefficient of the 2nd traffic flow parameter; β
2_21represent in subordinate phase traffic hazard probability function, the coefficient of the 21st traffic flow parameter;
Step 5022) by the maximal value of measuring and calculating formula (4), obtain β
2_0, β
2_1, β
2_2..., β
2_21the value of 22 coefficients:
Wherein, wherein, lnL (β
2, x
i) represent the natural logarithm value of likelihood function;
Step 5023) by step 5022) saliency value of 22 coefficients that obtains compares with setting value B respectively, if the saliency value of coefficient is less than setting value B, then in formula (3), retain traffic flow parameter corresponding to this coefficient, otherwise in formula (3), delete traffic flow parameter corresponding to this coefficient, and be back to step 5021), until the saliency value of the coefficient of traffic flow parameter remaining in formula (3) is all less than setting value B, as calibrated subordinate phase traffic hazard probability function;
Step 503) set up calibrated phase III traffic hazard probability function, comprise step 5031) to step 5033):
Step 5031) in step 5021) in the subordinate phase traffic flow data sample set up, delete only property loss accident PDO data, retain slight personal injury accident BC and severely injured or fatal accident KA data, as phase III traffic flow data sample, then utilize binary logistic regression structure phase III initial traffic hazard probability function as the formula (5):
Wherein, i=1,2 ..., n
3; n
3represent the subsample quantity that phase III traffic flow data sample packages contains; p
(3)(y
3i=1|x
i) represent that in phase III traffic flow data sample, i-th subsample probability that is severely injured or fatal accident KA occurs in phase III traffic hazard probability function, y
3irepresent the situation of i-th subsample generation traffic hazard in phase III traffic flow data sample, y
3ivalue be 1 or 0, y
3i=1 represents that in phase III traffic flow data sample, severely injured or fatal accident KA, y occur in i-th subsample
3i=0 represents that in phase III traffic flow data sample, slight personal injury accident BC, P occur in i-th subsample
(3)(y
3i=0x
i) to represent in phase III traffic flow data sample that the probability of slight personal injury accident BC occurs in i-th subsample, P
(3)(y
3i=0x
i)=1-P
(3)(y
3i=1x
i); x
1irepresent the 1st traffic flow parameter of i-th subsample in phase III traffic flow data sample, x
2irepresent the 2nd traffic flow parameter of i-th subsample in phase III traffic flow data sample, x
21irepresent the 21st traffic flow parameter in i-th subsample in phase III traffic flow data sample, β
3_0represent the constant coefficient in phase III traffic hazard probability function, β
3_1represent in phase III traffic hazard probability function, the coefficient of the 1st traffic flow parameter; β
3_2represent in phase III traffic hazard probability function, the coefficient of the 2nd traffic flow parameter; β
3_21represent in phase III traffic hazard probability function, the coefficient of the 21st traffic flow parameter;
Step 5032) by the maximal value of measuring and calculating formula (6), obtain β
3_0, β
3_1, β
3_2..., β
3_21the value of 22 coefficients:
Wherein, wherein, lnL (β
3, x
i) represent the natural logarithm value of likelihood function;
Step 5033) by step 5032) saliency value of 22 coefficients that obtains compares with setting value B respectively, if the saliency value of coefficient is less than setting value B, then in formula (5), retain traffic flow parameter corresponding to this coefficient, otherwise in formula (5), delete traffic flow parameter corresponding to this coefficient, and be back to step 5031), until the saliency value of the coefficient of traffic flow parameter remaining in formula (5) is all less than setting value B, as calibrated phase III traffic hazard probability function;
Step 60) calculate different order of severity traffic hazard probability of happening: according to step 50) the calibrated first stage traffic hazard probability function determined, calibrated subordinate phase traffic hazard probability function and calibrated phase III traffic hazard probability function, according to formula (7) to formula (9), calculate respectively only property loss accident PDO slight (x people) body of probability of happening P (PDO), P (the probability of happening P (BC) of injury accident BC and the probability of happening P (KA) of severe injury or fatal accident KA:
P (PDO)=P
(1) (x
i) × (1-P
(2)(x
i)) formula (7)
P (BC)=P
(1)(x
i) × P
(2)(x
i) × (1-P
(3)(x
i)) formula (8)
P (KA)=P
(1)(x
i) × P
(2)(x
i) × P
(3)(x
i) formula (9)
Wherein, P
(1)(x
i) represent the probable value recorded by calibrated first stage traffic hazard probability function, P
(2)(x
i) represent the probable value recorded by calibrated subordinate phase traffic hazard probability function, P
(3)(x
i) represent the probable value recorded by calibrated phase III traffic hazard probability function;
Step 70) calculate the probability threshold value of different order of severity traffic hazard: the probability threshold value P determining only property loss accident PDO according to formula (10) to formula (12) respectively
0_PDO, slight personal injury accident BC probability threshold value P
0_BC, severely injured or fatal accident KA probability threshold value P
0_KA:
P
0_PDO=α
(1)× (1-α
(2)) formula (10)
P
0_BC=α
(1)× α
(2)× (1-α
(3)) formula (11)
P
0_KA=α
(1)× α
(2)× α
(3)formula (12)
Wherein, α
(1)represent in step 40) traffic flow data sample in, only property loss accident PDO, slight personal injury accident BC and quantity summation that is severely injured or fatal accident KA account for the ratio of whole sample; α
(2)representing in step 5021) in the subordinate phase traffic flow data sample set up, slight personal injury accident BC and quantity summation that is severely injured or fatal accident KA account for the ratio of whole sample; α
(3)representing step 5031) in the phase III traffic flow data sample set up, quantity that is severely injured or fatal accident KA accounts for the ratio of whole sample;
Step 80) detect the probability that traffic hazard occurs in section in real time, and regulate and control vehicle: by being arranged on the Traffic flow detecting equipment on through street, real-time detection Current traffic data, by step 20) in corresponding traffic flow parameter bring in formula (7), formula (8) and formula (9), calculate the probability of happening of only property loss accident PDO, slight personal injury accident BC, severe injury or fatal accident KA, as P (PDO) >P
0_PDOtime, then showing that this section is current has the risk that only property loss accident PDO occurs, and carries out early warning in this front, section by variable message board to driver; As P (BC) >P
0_BCtime, then show that this section is current and have the risk that slight personal injury accident BC 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; As P (KA) >P
0_KAtime, then show that this section is current and have the risk that severely injured or fatal accident KA occur, by variable message board, early warning is carried out to driver in this front, section, start opertaing device, by controlling the ring road of through street or the Intersections of through street, reduce upstream vehicle flow, and by variable speed-limit plate to Current vehicle speed limit, reduce the travel speed of upstream vehicle; As P (PDO)≤P
p_PDOtime, then P shows the current risk that only property loss accident PDO does not occur in this section, without the need to sending early warning; As P (BC)≤P
0_BCtime, then show the current risk that slight personal injury accident BC does not occur in this section, without the need to sending early warning; As P (KA)≤P
0_KAtime, then show the current risk that severe injury or fatal accident KA do not occur in this section, without the need to sending early warning;
Step 90) repeat step 80), carry out the detection that different order of severity traffic hazard probability occurs in next setting-up time T section, and regulate and control vehicle, 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 vehicle driving safety.Existing vehicle regulate and control method based on traffic hazard menace level, can not regulate and control vehicle.And vehicle regulate and control method of the present invention regulates and controls vehicle based on traffic hazard menace level.This vehicle regulate and control method to the generation of traffic hazard, can apply preventive measure more effectively.The present invention's intelligent transportation system be used on through street detects the probability of happening of only property loss accident PDO, slight personal injury accident BC, severe injury or the traffic hazard of fatal accident KA Three Estate in real time, when a certain grade street accidents risks of generation having been detected, in this section, vehicle is adjusted accordingly, if there is the risk that only property loss accident PDO occurs, then by variable message board, early warning is carried out to driver in this front, section; If there is the risk that slight personal injury accident BC occurs, then 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; If there is the risk that severely injured or fatal accident KA occur, then by variable message board, early warning is carried out to driver in this front, section, start opertaing device, reduce the travel speed of upstream vehicle flow and upstream vehicle.Vehicle regulate and control method of the present invention, by the measuring and calculating of the traffic hazard probability of happening to different menace level, judges the risk that various traffic hazard occurs, thus regulates and controls vehicle.The accuracy rate that method of the present invention regulates and controls vehicle is high, the effective guarantee driving safety of vehicle.
2. process is simple, practical.In the present invention, by step 50), after obtaining calibrated three stages traffic hazard probability function, only need to gather the new traffic data in section, just can detect in real time in following setting-up time, there is the probability of three kinds of menace level traffic hazards in this section, and then regulation and control vehicle.Method of the present invention is easy to use, practical, has 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 of reduction of the present invention different order of severity traffic hazard probability, 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, utilize Traffic flow detecting equipment to gather the traffic hazard data of this through street, and establishment often play traffic hazard scene upstream and downstream two Traffic flow detecting equipment; According to traffic hazard menace level, traffic hazard is fallen into three classes: only property loss accident PDO, slight personal injury accident BC, severe injury or fatal accident KA; 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 the traffic data of accident section before accident occurs: often play traffic hazard scene upstream and downstream two Traffic flow detecting equipment by being arranged on, gather the traffic data of all kinds of traffic hazard, described traffic data comprises: before often playing traffic hazard generation, the upstream magnitude of traffic flow mean value x in setting-up time T
1, upstream traffic occupation rate mean value x
2, upstream car speed mean value x
3, upstream magnitude of traffic flow standard deviation x
4, upstream traffic occupation rate standard deviation x
5, upstream car speed standard deviation x
6, downstream magnitude of traffic flow mean value x
7, downstream traffic occupation rate mean value x
8, downstream car speed mean value x
9, downstream magnitude of traffic flow standard deviation x
10, downstream traffic occupation rate standard deviation x
11, downstream car speed standard deviation x
12, the mean value x of difference in flow absolute value between the adjacent lane of upstream
13, occupy the mean value x of rate variance absolute value between the adjacent lane of upstream
14, the mean value x of car speed difference absolute value between the adjacent lane of upstream
15, the mean value x of difference in flow absolute value between the adjacent lane of downstream
16, occupy the mean value x of rate variance absolute value between the adjacent lane of downstream
17, the mean value x of car speed difference absolute value between the adjacent lane of downstream
18, upstream and downstream magnitude of traffic flow difference absolute value x
19, upstream and downstream traffic occupies the absolute value x of rate variance
20with the absolute value x of upstream and downstream car speed difference
2121 traffic flow parameters.In 21 traffic flow parameters, the 1st traffic flow parameter is upstream magnitude of traffic flow mean value x
1, the 2nd traffic flow parameter is upstream traffic occupation rate mean value x
2, the 3rd traffic flow parameter is upstream car speed mean value x
3, the 4th traffic flow parameter is upstream magnitude of traffic flow standard deviation x
4, the 5th traffic flow parameter is upstream traffic occupation rate standard deviation x
5, the 6th traffic flow parameter is upstream car speed standard deviation x
6, the 7th traffic flow parameter is downstream magnitude of traffic flow mean value x
7, the 8th traffic flow parameter is downstream traffic occupation rate mean value x
8, the 9th traffic flow parameter is downstream car speed mean value x
9, the 10th traffic flow parameter is downstream magnitude of traffic flow standard deviation x
10, the 11st traffic flow parameter is downstream traffic occupation rate standard deviation x
11, the 12nd traffic flow parameter is downstream car speed standard deviation x
12, the 13rd traffic flow parameter is the mean value x of difference in flow absolute value between the adjacent lane of upstream
13, the 14th traffic flow parameter is the mean value x occupying rate variance absolute value between the adjacent lane of upstream
14, the 15th traffic flow parameter is the mean value x of car speed difference absolute value between the adjacent lane of upstream
15, the 16th traffic flow parameter is the mean value x of difference in flow absolute value between the adjacent lane of downstream
16, the 17th traffic flow parameter is the mean value x occupying rate variance absolute value between the adjacent lane of downstream
17, the 18th traffic flow parameter is the mean value x of car speed difference absolute value between the adjacent lane of downstream
18, the 19th traffic flow parameter is the absolute value x of upstream and downstream magnitude of traffic flow difference
19, the 20th traffic flow parameter is the absolute value x that upstream and downstream traffic occupies rate variance
20, the 21st traffic flow parameter is the absolute value x of upstream and downstream car speed difference
21.
In step 20) in, the front traffic data of accident generation gathering accident section is by section to be detected upstream and downstream two Traffic flow detecting equipment, gather the traffic data in section to be detected according to sampling step length, then calculate the mean value of each parameter every setting-up time T.Described traffic data comprises: before often playing traffic hazard generation, the upstream magnitude of traffic flow mean value x in setting-up time T
1, upstream traffic occupation rate mean value x
2, upstream car speed mean value x
3, upstream magnitude of traffic flow standard deviation x
4, upstream traffic occupation rate standard deviation x
5, upstream car speed standard deviation x
6, downstream magnitude of traffic flow mean value x
7, downstream traffic occupation rate mean value x
8, downstream car speed mean value x
9, downstream magnitude of traffic flow standard deviation x
10, downstream traffic occupation rate standard deviation x
11, downstream car speed standard deviation x
12, the mean value x of difference in flow absolute value between the adjacent lane of upstream
13, occupy the mean value x of rate variance absolute value between the adjacent lane of upstream
14, the mean value x of car speed difference absolute value between the adjacent lane of upstream
15, the mean value x of difference in flow absolute value between the adjacent lane of downstream
16, occupy the mean value x of rate variance absolute value between the adjacent lane of downstream
17, the mean value x of car speed difference absolute value between the adjacent lane of downstream
18, upstream and downstream magnitude of traffic flow difference absolute value x
19, upstream and downstream traffic occupies the absolute value x of rate variance
20with the absolute value x of upstream and downstream car speed difference
21.Sampling step length is preferably 30 seconds.Setting-up time T is preferably 5-10 minutes.
Step 30) gather accident section traffic data in normal state: to often playing traffic hazard, adopt case-control study method, ratio in 1: a is chosen traffic hazard and section traffic data is in normal state occurred, state when described normal condition refers to that traffic hazard do not occur in section, described 1: a refers to the traffic data corresponding to and often play traffic hazard, chooses this traffic hazard and section a group traffic data in normal state occurs; Described traffic data of often organizing comprises the upstream magnitude of traffic flow mean value x of this section in setting-up time T
1, upstream traffic occupation rate mean value x
2, upstream car speed mean value x
3, upstream magnitude of traffic flow standard deviation x
4, upstream traffic occupation rate standard deviation x
5, upstream car speed standard deviation x
6, downstream magnitude of traffic flow mean value x
7, downstream traffic occupation rate mean value x
8, downstream car speed mean value x
9, downstream magnitude of traffic flow standard deviation x
10, downstream traffic occupation rate standard deviation x
11, downstream car speed standard deviation x
12, the mean value x of difference in flow absolute value between the adjacent lane of upstream
13, occupy the mean value x of rate variance absolute value between the adjacent lane of upstream
14, the mean value x of car speed difference absolute value between the adjacent lane of upstream
15, the mean value x of difference in flow absolute value between the adjacent lane of downstream
16, occupy the mean value x of rate variance absolute value between the adjacent lane of downstream
17, the mean value x of car speed difference absolute value between the adjacent lane of downstream
18, upstream and downstream magnitude of traffic flow difference absolute value x
19, upstream and downstream traffic occupies the absolute value x of rate variance
20with the absolute value x of upstream and downstream car speed difference
2121 traffic flow parameters.A be more than or equal to 2 integer.A is preferably 10.
In step 30) in, case-control study method is prior art, see document: " QuantitativeMethodsforHealth Research:APracticalInteractiveGuidetoEpidemiologyandStat istics ", Bruce, N., Pope, D., Stanistreet, D., 2008.JohnWiley & SonsLtd.
Step 40) set up traffic flow data sample: by step 20) traffic data before accident occurs of the Three Estate traffic hazard that gathers and step 30) traffic data under the normal condition that gathers, be combined into traffic flow data sample, this traffic flow data sample comprises n subsample.
Step 50) set up calibrated three stages traffic hazard probability function: comprise and set up calibrated first stage traffic hazard probability function, calibrated subordinate phase traffic hazard probability function and calibrated phase III traffic hazard probability function successively, specifically comprise step 501) to step 503)
Step 501) set up calibrated first stage traffic hazard probability function, comprise step 5011) to step 5013):
Step 5011) utilize binary logistic regression structure first stage initial traffic hazard probability function as the formula (1),
Wherein, i=1,2 ..., n; P
(1)(y
1i=1|x
i) to represent in traffic flow data sample that the probability of traffic hazard occurs in first stage traffic hazard probability function in i-th subsample, y
1irepresent the situation of i-th subsample generation traffic hazard in traffic flow data sample, y
1ivalue be 1 or 0, y
1i=1 represents that traffic hazard occurs in i-th subsample, y
1i=0 represents that i-th subsample traffic hazard does not occur, P
(1)(y
1i=0x
i) to represent in traffic flow data sample that the probability of traffic hazard does not occur in i-th subsample, P
(1)(y
1i=0x
i)=1-P
(1)(y
1i=1x
i); x
1irepresent the 1st traffic flow parameter of i-th subsample, x
2irepresent the 2nd traffic flow parameter of i-th subsample, x
21irepresent the 21st traffic flow parameter in i-th subsample, β
1_0represent the constant coefficient in first stage traffic hazard probability function, β
1_1represent in first stage traffic hazard probability function, the coefficient of the 1st traffic flow parameter; β
1_2represent in first stage traffic hazard probability function, the coefficient of the 2nd traffic flow parameter; β
1_21represent in first stage traffic hazard probability function, the coefficient of the 21st traffic flow parameter.Expression formula β
1_0+ β
1_1x
1i+ β
1_2x
2i+ ...+β
1_21x
21imiddle abridged part is in first stage traffic hazard probability function, and the 3rd traffic flow parameter is to the sum of products of the 20th coefficient that traffic flow parameter is corresponding with it respectively.
Step 5012) by the maximal value of measuring and calculating formula (2), obtain β
1_0, β
1_1, β
1_2..., β
1_21the value of 22 coefficients:
Wherein, wherein, lnL (β
1, x
i) represent the natural logarithm value of likelihood function.
Step 5013) by step 5012) saliency value of 22 coefficients that obtains compares with setting value B respectively, if the saliency value of coefficient is less than setting value B, then in formula (1), retain traffic flow parameter corresponding to this coefficient, otherwise in formula (1), delete traffic flow parameter corresponding to this coefficient, and be back to step 5011), until the saliency value of the coefficient of traffic flow parameter remaining in formula (1) is all less than setting value B, as calibrated first stage traffic hazard probability function;
Step 502) set up calibrated subordinate phase traffic hazard probability function, comprise step 5021) to step 5023):
Step 5021) in step 40) in the traffic flow data sample set up, delete the traffic data under normal condition, form subordinate phase traffic flow data sample, then utilize the binary logistic regression structure initial traffic hazard probability function of subordinate phase as the formula (3):
Wherein, i=1,2 ..., n
2; n
2represent the subsample quantity that subordinate phase traffic flow data sample packages contains; P
(2)(y
2i=1|x
i) to represent in subordinate phase traffic flow data sample that the probability of slight personal injury accident BC, severe injury or fatal accident KA occurs in subordinate phase traffic hazard probability function in i-th subsample, y
2irepresent the situation of i-th subsample generation traffic hazard in subordinate phase traffic flow data sample, y
2ivalue be 1 or 0, y
2i=1 represents that in subordinate phase traffic flow data sample, slight personal injury accident BC or severely injured or fatal accident KA, y occur in i-th subsample
2i=0 represents that in subordinate phase traffic flow data sample, only property loss accident PDO, P occur in i-th subsample
(2)(y
2i=0x
i) to represent in subordinate phase traffic flow data sample that the probability of only property loss accident PDO occurs in i-th subsample, P
(2)(y
2i=0x
i)=1-P
(2)(y
2i=1x
i); x
1irepresent the 1st traffic flow parameter of i-th subsample in subordinate phase traffic flow data sample, x
2irepresent the 2nd traffic flow parameter of i-th subsample in subordinate phase traffic flow data sample, x
21irepresent the 21st traffic flow parameter in i-th subsample in subordinate phase traffic flow data sample, β
2_0represent the constant coefficient in subordinate phase traffic hazard probability function, β
2_1represent in subordinate phase traffic hazard probability function, the coefficient of the 1st traffic flow parameter; β
2_2represent in subordinate phase traffic hazard probability function, the coefficient of the 2nd traffic flow parameter; β
2_21represent in subordinate phase traffic hazard probability function, the coefficient of the 21st traffic flow parameter.Expression formula β
2_0+ β
2_1x
1i+ β
2_2x
2i+ ...+β
2_21x
21imiddle abridged part is in subordinate phase traffic hazard probability function, and the 3rd traffic flow parameter is to the sum of products of the 20th coefficient that traffic flow parameter is corresponding with it respectively.
Step 5022) by the maximal value of measuring and calculating formula (4), obtain β
2_0, β
2_1, β
2_2..., β
2_21the value of 22 coefficients:
Wherein, wherein, lnL (β
2, x
i) represent the natural logarithm value of likelihood function.
Step 5023) by step 5022) saliency value of 22 coefficients that obtains compares with setting value B respectively, if the saliency value of coefficient is less than setting value B, then in formula (3), retain traffic flow parameter corresponding to this coefficient, otherwise in formula (3), delete traffic flow parameter corresponding to this coefficient, and be back to step 5021), until the saliency value of the coefficient of traffic flow parameter remaining in formula (3) is all less than setting value B, as calibrated subordinate phase traffic hazard probability function.
Step 503) set up calibrated phase III traffic hazard probability function, comprise step 5031) to step 5033):
Step 5031) in step 5021) in the subordinate phase traffic flow data sample set up, delete only property loss accident PDO data, retain slight personal injury accident BC and severely injured or fatal accident KA data, as phase III traffic flow data sample, then utilize binary logistic regression structure phase III initial traffic hazard probability function as the formula (5):
Wherein, i=1,2 ..., n
3; n
3represent the subsample quantity that phase III traffic flow data sample packages contains; p
(3)(y
3i=1|x
i) represent that in phase III traffic flow data sample, i-th subsample probability that is severely injured or fatal accident KA occurs in phase III traffic hazard probability function, y
3irepresent the situation of i-th subsample generation traffic hazard in phase III traffic flow data sample, y
3ivalue be 1 or 0, y
3i=1 represents that in phase III traffic flow data sample, severely injured or fatal accident KA, y occur in i-th subsample
3i=0 represents that in phase III traffic flow data sample, slight personal injury accident BC, P occur in i-th subsample
(3)(y
3i=0x
i) to represent in phase III traffic flow data sample that the probability of slight personal injury accident BC occurs in i-th subsample, P
(3)(y
3i=0x
i)=1-P
(3)(y
3i=1x
i); x
1irepresent the 1st traffic flow parameter of i-th subsample in phase III traffic flow data sample, x
2irepresent the 2nd traffic flow parameter of i-th subsample in phase III traffic flow data sample, x
21irepresent the 21st traffic flow parameter in i-th subsample in phase III traffic flow data sample, β
3_0represent the constant coefficient in phase III traffic hazard probability function, β
3_1represent in phase III traffic hazard probability function, the coefficient of the 1st traffic flow parameter; β
3_2represent in phase III traffic hazard probability function, the coefficient of the 2nd traffic flow parameter; β
3_21represent in phase III traffic hazard probability function, the coefficient of the 21st traffic flow parameter.Expression formula β
3_0+ β
3_1x
1i+ β
3_2x
2i+ ...+β
3_21x
21imiddle abridged part is in phase III traffic hazard probability function, and the 3rd traffic flow parameter is to the sum of products of the 20th coefficient that traffic flow parameter is corresponding with it respectively.
Step 5032) by the maximal value of measuring and calculating formula (6), obtain β
3_0, β
3_1, β
3_2..., β
3_21the value of 22 coefficients:
Wherein, wherein, lnL (β
3, x
i) represent the natural logarithm value of likelihood function.
Step 5033) by step 5032) saliency value of 22 coefficients that obtains compares with setting value B respectively, if the saliency value of coefficient is less than setting value B, then in formula (5), retain traffic flow parameter corresponding to this coefficient, otherwise in formula (5), delete traffic flow parameter corresponding to this coefficient, and be back to step 5031), until the saliency value of the coefficient of traffic flow parameter remaining in formula (5) is all less than setting value B, as calibrated phase III traffic hazard probability function.As preferably, setting value B is 0.05.
Step 60) calculate different order of severity traffic hazard probability of happening: according to step 50) the calibrated first stage traffic hazard probability function determined, calibrated subordinate phase traffic hazard probability function and calibrated phase III traffic hazard probability function, according to formula (7) to formula (9), calculate respectively only property loss accident PDO slight (x people) body of probability of happening P (PDO), P (the probability of happening P (BC) of injury accident BC and the probability of happening P (KA) of severe injury or fatal accident KA:
P (PDO)=P
(1)(x
i) × (1-P
(2)(x
i)) formula (7)
P (BC)=P
(1)(x
i) × P
(2)(x
i) × (1-P
(3)(x
i)) formula (8)
P (KA)=P
(1)(x
i) × P
(2)(x
i) × P
(3)(x
i) formula (9)
Wherein, P
(1)(x
i) represent the probable value recorded by calibrated first stage traffic hazard probability function, P
(2)(x
i) represent the probable value recorded by calibrated subordinate phase traffic hazard probability function, P
(3)(x
i) represent the probable value recorded by calibrated phase III traffic hazard probability function.
Step 70) calculate the probability threshold value of different order of severity traffic hazard: the probability threshold value P determining only property loss accident PDO according to formula (10) to formula (12) respectively
0_PDO, slight personal injury accident BC probability threshold value P
0_BC, severely injured or fatal accident KA probability threshold value P
0_KA:
P
0_PDO=α
(1)× (1-α
(2)) formula (10)
P
0_BC=α
(1)× α
(2)× (1-α
(3)) formula (11)
P
0_KA=α
(1)× α
(2)× α
(3)formula (12)
Wherein, α
(1)represent in step 40) traffic flow data sample in, only property loss accident PDO, slight personal injury accident BC and quantity summation that is severely injured or fatal accident KA account for the ratio of whole sample; α
(2)representing in step 5021) in the subordinate phase traffic flow data sample set up, slight personal injury accident BC and quantity summation that is severely injured or fatal accident KA account for the ratio of whole sample; α
(3)representing step 5031) in the phase III traffic flow data sample set up, quantity that is severely injured or fatal accident KA accounts for the ratio of whole sample.
Step 80) detect the probability that traffic hazard occurs in section in real time, and regulate and control vehicle: by being arranged on the Traffic flow detecting equipment on through street, real-time detection Current traffic data, by step 20) in corresponding traffic flow parameter bring in formula (7), formula (8) and formula (9), calculate the probability of happening of only property loss accident PDO, slight personal injury accident BC, severe injury or fatal accident KA, as P (PDO) >P
0_PDOtime, then showing that this section is current has the risk that only property loss accident PDO occurs, and carries out early warning in this front, section by variable message board to driver; As P (BC) >P
0_BCtime, then show that this section is current and have the risk that slight personal injury accident BC 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; As P (KA) >P
0_KAtime, then show that this section is current and have the risk that severely injured or fatal accident KA occur, by variable message board, early warning is carried out to driver in this front, section, start opertaing device, by controlling the ring road of through street or the Intersections of through street, reduce upstream vehicle flow, and by variable speed-limit plate to Current vehicle speed limit, reduce the travel speed of upstream vehicle; As P (PDO)≤P
0_PDOtime, then show the current risk that only property loss accident PDO does not occur in this section, without the need to sending early warning; As P (BC)≤P
0_BCtime, then show the current risk that slight personal injury accident BC does not occur in this section, without the need to sending early warning; As P (KA)≤P
0_KAtime, then show the current risk that severe injury or fatal accident KA do not occur in this section, without the need to sending early warning.By variable speed-limit plate to Current vehicle speed limit, the car speed amplitude of each adjustment change is within 5km/h.
Step 90) repeat step 80), carry out the detection that different order of severity traffic hazard probability occurs in next setting-up time T section, and regulate and control vehicle, until detection of end.
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, and Real-time Collection detects the traffic flow parameter in section.
The arithmetic for real-time traffic flow parameter collected is brought in the calibrated three stages traffic hazard probability function that the present invention sets up, calculate the probability of current generation three kinds of menace level traffic hazards.As P (PDO) >P
0_PDOtime, then showing that this section is current has the risk that only property loss accident PDO occurs, and carries out early warning in this front, section by variable message board to driver; As P (BC) >P
0_BCtime, then show that this section is current and have the risk that slight personal injury accident BC 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; As P (KA) >P
0_KAtime, then show that this section is current and have the risk that severely injured or fatal accident KA occur, by variable message board, early warning is carried out to driver in this front, section, start opertaing device, by controlling the ring road of through street or the Intersections of through street, reduce upstream vehicle flow, and by variable speed-limit plate to Current vehicle speed limit, reduce the travel speed of upstream vehicle.As P (PDO)≤P
0_PDOtime, then show the current risk that only property loss accident PDO does not occur in this section, without the need to sending early warning; As P (BC)≤P
0_BCtime, then show the current risk that slight personal injury accident BC does not occur in this section, without the need to sending early warning; As P (KA)≤P
0_KAtime, then show the current risk that severe injury or fatal accident KA do not occur in this section, without the need to sending early warning.
Vehicle regulate and control method of the present invention is according to the arithmetic for real-time traffic flow parameter gathered, judging the current risk that whether there are generation three kinds of menace level traffic hazards in section to be detected, is adopt the traffic hazard probability function set up by sequence analysis method to judge that the probability of three kinds of menace level traffic hazards occurs in section to be detected.
Practice process of the present invention is divided into sets up calibrated three stages traffic hazard probability function, and detects traffic hazard probability and regulate and control vehicle two processes.
Set up calibrated three stages traffic hazard probability function: in order to ensure that the traffic hazard probability function set up can have good precision of prediction, the sample gathered is as far as possible large, usual accident group data sample (i.e. the traffic data sample of accident group) is greater than 500, and normal group sample (the traffic data sample namely under normal condition) is greater than 1000.According to above-mentioned steps 10) to step 50) set up calibrated three stages traffic hazard probability function.
Detect traffic hazard probability and regulate and control vehicle: the upstream magnitude of traffic flow mean value x in Real-time Collection section to be detected
1, upstream traffic occupation rate mean value x
2, upstream car speed mean value x
3, upstream magnitude of traffic flow standard deviation x
4, upstream traffic occupation rate standard deviation x
5, upstream car speed standard deviation x
6, downstream magnitude of traffic flow mean value x
7, downstream traffic occupation rate mean value x
8, downstream car speed mean value x
9, downstream magnitude of traffic flow standard deviation x
10, downstream traffic occupation rate standard deviation x
11, downstream car speed standard deviation x
12, the mean value x of difference in flow absolute value between the adjacent lane of upstream
13, occupy the mean value x of rate variance absolute value between the adjacent lane of upstream
14, the mean value x of car speed difference absolute value between the adjacent lane of upstream
15, the mean value x of difference in flow absolute value between the adjacent lane of downstream
16, occupy the mean value x of rate variance absolute value between the adjacent lane of downstream
17, the mean value x of car speed difference absolute value between the adjacent lane of downstream
18, upstream and downstream magnitude of traffic flow difference absolute value x
19, upstream and downstream traffic occupies the absolute value x of rate variance
20with the absolute value x of upstream and downstream car speed difference
21, substituting in the calibrated three stages traffic hazard probability function set up by these 21 traffic flow parameters, there are three kinds of traffic hazard probability to vehicle and calculates in real time in measuring and calculating probable value.As P (PDO) >P
0_PDOtime, then showing that this section is current has the risk that only property loss accident PDO occurs, and carries out early warning in this front, section by variable message board to driver; As P (BC) >P
0_BCtime, then show that this section is current and have the risk that slight personal injury accident BC 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; As P (KA) >P
0_KAtime, then show that this section is current and have the risk that severely injured or fatal accident KA occur, by variable message board, early warning is carried out to driver in this front, section, start opertaing device, by controlling the ring road of through street or the Intersections of through street, reduce upstream vehicle flow, and by variable speed-limit plate to Current vehicle speed limit, reduce the travel speed of upstream vehicle; As P (PDO)≤P
0_PDOtime, then show the current risk that only property loss accident PDO does not occur in this section, without the need to sending early warning; As P (BC)≤P
0_BCtime, then show the current risk that slight personal injury accident BC does not occur in this section, without the need to sending early warning; As P (KA)≤P
0_KAtime, then show the current risk that severe injury or fatal accident KA do not occur in this section, without the need to sending early warning.
Embodiment
The U.S. is utilized to add the traffic flow of 2008 of livre Leah state I-880 road and traffic hazard data to test the accuracy of detection of the present invention to different menace level traffic hazard.According to step 10) of the present invention to step 30) collect only property loss accident PDO, the slight casualty data of personal injury accident BC, severe injury or fatal accident KA and the non-casualty data in this section.532 only property loss accident PDO sample, 203 slight personal injury accident BC samples, 59 severe injuries or fatal accident KA samples and 7940 non-accident samples (when namely there is not traffic hazard are comprised in the traffic data sample set up, utilize Traffic flow detecting equipment to gather the traffic flow parameter in this section, form non-accident sample).
Utilize above-mentioned traffic flow data sample, process in accordance with the present invention 50), obtain the traffic flow parameter in calibrated first stage traffic hazard probability function as shown in table 1 and coefficient thereof, traffic flow parameter in calibrated subordinate phase traffic hazard probability function as shown in table 2 and coefficient thereof, the traffic flow parameter in calibrated phase III traffic hazard probability function as shown in table 3 and coefficient thereof.The traffic flow parameter do not listed in every table 1 to table 3, deletes all in traffic hazard probability function.
Table 1
Traffic flow parameter (x) | Coefficient (β) |
Upstream traffic occupation rate mean value (x 2) | 0.069 |
Upstream car speed standard deviation (x 6) | 0.046 |
Downstream car speed standard deviation (x 12) | 0.047 |
Mean value (the x of rate variance absolute value is occupied between the adjacent lane of downstream 17) | 0.093 |
Constant | -1.979 |
Table 2
Traffic flow parameter (x) | Coefficient (β) |
Upstream traffic occupation rate mean value (x 2) | -0.037 |
Downstream magnitude of traffic flow mean value (x 7) | -0.057 |
Constant | 1.893 |
Table 3
Traffic flow parameter (x) | Coefficient (β) |
Upstream car speed mean value (x 3) | 0.033 |
Mean value (the x of car speed difference absolute value between the adjacent lane of upstream 15) | 0.067 |
Downstream magnitude of traffic flow mean value (x 7) | -0.117 |
Constant | -3.51 |
According to step 70 of the present invention), measuring and calculating obtains the probability threshold value P of only property loss accident PDO
0_PDObe 0.061, the probability threshold value P of slight personal injury accident BC
0_BCbe 0.023, the probability threshold value P of severe injury or fatal accident KA
0_KAbe 0.007.According to step 60) set up three kinds of menace level traffic hazard probability of happening measure formulas, former traffic flow sample is calculated, result shows: method of the present invention is 61.8% to only property loss accident PDO predictablity rate, be 63.5% to slight personal injury accident BC predictablity rate, being 62.7% to severely injured or fatal accident KA predictablity rate, is 69.1% to non-accident sample predictions accuracy rate.Therefore, the method using the present invention to propose all has higher accuracy of detection to different menace level traffic hazard, and the detection method that the present invention simultaneously proposes can simplify testing process, easy to use, practical, thus has actual engineering application and is worth.
Claims (8)
1. reduce a vehicle regulate and control method for different order of severity traffic hazard probability, 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, utilize Traffic flow detecting equipment to gather the traffic hazard data of this through street, and establishment often play traffic hazard scene upstream and downstream two Traffic flow detecting equipment; According to traffic hazard menace level, traffic hazard is fallen into three classes: only property loss accident PDO, slight personal injury accident BC, severe injury or fatal accident KA; Q be greater than 1 integer;
Step 20) gather the traffic data of accident section before accident occurs: often play traffic hazard scene upstream and downstream two Traffic flow detecting equipment by being arranged on, gather the traffic data of all kinds of traffic hazard, described traffic data comprises: before often playing traffic hazard generation, the upstream magnitude of traffic flow mean value x in setting-up time T
1, upstream traffic occupation rate mean value x
2, upstream car speed mean value x
3, upstream magnitude of traffic flow standard deviation x
4, upstream traffic occupation rate standard deviation x
5, upstream car speed standard deviation x
6, downstream magnitude of traffic flow mean value x
7, downstream traffic occupation rate mean value x
8, downstream car speed mean value x
9, downstream magnitude of traffic flow standard deviation x
10, downstream traffic occupation rate standard deviation x
11, downstream car speed standard deviation x
12, the mean value x of difference in flow absolute value between the adjacent lane of upstream
13, occupy the mean value x of rate variance absolute value between the adjacent lane of upstream
14, the mean value x of car speed difference absolute value between the adjacent lane of upstream
15, the mean value x of difference in flow absolute value between the adjacent lane of downstream
16, occupy the mean value x of rate variance absolute value between the adjacent lane of downstream
17, the mean value x of car speed difference absolute value between the adjacent lane of downstream
18, upstream and downstream magnitude of traffic flow difference absolute value x
19, upstream and downstream traffic occupies the absolute value x of rate variance
20with the absolute value x of upstream and downstream car speed difference
2121 traffic flow parameters;
Step 30) gather accident section traffic data in normal state: to often playing traffic hazard, adopt case-control study method, ratio in 1: a is chosen traffic hazard and section traffic data is in normal state occurred, state when described normal condition refers to that traffic hazard do not occur in section, described 1: a refers to the traffic data corresponding to and often play traffic hazard, chooses this traffic hazard and section a group traffic data in normal state occurs; Described traffic data of often organizing comprises the upstream magnitude of traffic flow mean value x of this section in setting-up time T
1, upstream traffic occupation rate mean value x
2, upstream car speed mean value x
3, upstream magnitude of traffic flow standard deviation x
4, upstream traffic occupation rate standard deviation x
5, upstream car speed standard deviation x
6, downstream magnitude of traffic flow mean value x
7, downstream traffic occupation rate mean value x
8, downstream car speed mean value x
9, downstream magnitude of traffic flow standard deviation x
10, downstream traffic occupation rate standard deviation x
11, downstream car speed standard deviation x
12, the mean value x of difference in flow absolute value between the adjacent lane of upstream
13, occupy the mean value x of rate variance absolute value between the adjacent lane of upstream
14, the mean value x of car speed difference absolute value between the adjacent lane of upstream
15, the mean value x of difference in flow absolute value between the adjacent lane of downstream
16, occupy the mean value x of rate variance absolute value between the adjacent lane of downstream
17, the mean value x of car speed difference absolute value between the adjacent lane of downstream
18, upstream and downstream magnitude of traffic flow difference absolute value x
19, upstream and downstream traffic occupies the absolute value x of rate variance
20with the absolute value x of upstream and downstream car speed difference
2121 traffic flow parameters; A be more than or equal to 2 integer;
Step 40) set up traffic flow data sample: by step 20) traffic data before accident occurs of the Three Estate traffic hazard that gathers and step 30) traffic data under the normal condition that gathers, be combined into traffic flow data sample, this traffic flow data sample comprises n subsample;
Step 50) set up calibrated three stages traffic hazard probability function: comprise and set up calibrated first stage traffic hazard probability function, calibrated subordinate phase traffic hazard probability function and calibrated phase III traffic hazard probability function successively, specifically comprise step 501) to step 503)
Step 501) set up calibrated first stage traffic hazard probability function, comprise step 5011) to step 5013):
Step 5011) utilize binary logistic regression to build such as formula the initial traffic hazard probability function of the first stage shown in (1),
formula (1)
Wherein, i=1,2 ..., n; P
(1)(y
1i=1|x
i) to represent in traffic flow data sample that the probability of traffic hazard occurs in first stage traffic hazard probability function in i-th subsample, y
1irepresent the situation of i-th subsample generation traffic hazard in traffic flow data sample, y
1ivalue be 1 or 0, y
1i=1 represents that traffic hazard occurs in i-th subsample, y
1i=0 represents that i-th subsample traffic hazard does not occur, P
(1)(y
1i=0|x
i) to represent in traffic flow data sample that the probability of traffic hazard does not occur in i-th subsample, P
(1)(y
1i=0|x
i)=1-P
(1)(y
1i=1|x
i); x
1irepresent the 1st traffic flow parameter of i-th subsample, x
2irepresent the 2nd traffic flow parameter of i-th subsample, x
21irepresent the 21st traffic flow parameter in i-th subsample, β
1_0represent the constant coefficient in first stage traffic hazard probability function, β
1_1represent in first stage traffic hazard probability function, the coefficient of the 1st traffic flow parameter; β
1_2represent in first stage traffic hazard probability function, the coefficient of the 2nd traffic flow parameter; β
1_21represent in first stage traffic hazard probability function, the coefficient of the 21st traffic flow parameter;
Step 5012) by the maximal value of measuring and calculating formula (2), obtain β
1_0, β
1_1, β
1_2..., β
1_21the value of 22 coefficients:
formula (2)
Wherein, lnL (β
1, x
i) represent the natural logarithm value of likelihood function;
Step 5013) by step 5012) saliency value of 22 coefficients that obtains compares with setting value B respectively, if the saliency value of coefficient is less than setting value B, then in formula (1), retain traffic flow parameter corresponding to this coefficient, otherwise in formula (1), delete traffic flow parameter corresponding to this coefficient, and be back to step 5011), until the saliency value of the coefficient of traffic flow parameter remaining in formula (1) is all less than setting value B, as calibrated first stage traffic hazard probability function;
Step 502) set up calibrated subordinate phase traffic hazard probability function, comprise step 5021) to step 5023):
Step 5021) in step 40) in the traffic flow data sample set up, delete the traffic data under normal condition, form subordinate phase traffic flow data sample, then utilize binary logistic regression to build such as formula the initial traffic hazard probability function of the subordinate phase shown in (3):
formula (3)
Wherein, i=1,2 ..., n
2; n
2represent the subsample quantity that subordinate phase traffic flow data sample packages contains; P
(2)(y
2i=1|x
i) to represent in subordinate phase traffic flow data sample that the probability of slight personal injury accident BC, severe injury or fatal accident KA occurs in subordinate phase traffic hazard probability function in i-th subsample, y
2irepresent the situation of i-th subsample generation traffic hazard in subordinate phase traffic flow data sample, y
2ivalue be 1 or 0, y
2i=1 represents that in subordinate phase traffic flow data sample, slight personal injury accident BC or severely injured or fatal accident KA, y occur in i-th subsample
2i=0 represents that in subordinate phase traffic flow data sample, only property loss accident PDO, P occur in i-th subsample
(2)(y
2i=0|x
i) to represent in subordinate phase traffic flow data sample that the probability of only property loss accident PDO occurs in i-th subsample, P
(2)(y
2i=0|x
i)=1-P
(2)(y
2i=1|x
i); x
1irepresent the 1st traffic flow parameter of i-th subsample in subordinate phase traffic flow data sample, x
2irepresent the 2nd traffic flow parameter of i-th subsample in subordinate phase traffic flow data sample, x
21irepresent the 21st traffic flow parameter in i-th subsample in subordinate phase traffic flow data sample, β
2_0represent the constant coefficient in subordinate phase traffic hazard probability function, β
2_1represent in subordinate phase traffic hazard probability function, the coefficient of the 1st traffic flow parameter; β
2_2represent in subordinate phase traffic hazard probability function, the coefficient of the 2nd traffic flow parameter; β
2_21represent in subordinate phase traffic hazard probability function, the coefficient of the 21st traffic flow parameter;
Step 5022) by the maximal value of measuring and calculating formula (4), obtain β
2_0, β
2_1, β
2_2..., β
2_21the value of 22 coefficients:
formula (4)
Wherein, lnL (β
2, x
i) represent the natural logarithm value of likelihood function;
Step 5023) by step 5022) saliency value of 22 coefficients that obtains compares with setting value B respectively, if the saliency value of coefficient is less than setting value B, then in formula (3), retain traffic flow parameter corresponding to this coefficient, otherwise in formula (3), delete traffic flow parameter corresponding to this coefficient, and be back to step 5021), until the saliency value of the coefficient of traffic flow parameter remaining in formula (3) is all less than setting value B, as calibrated subordinate phase traffic hazard probability function;
Step 503) set up calibrated phase III traffic hazard probability function, comprise step 5031) to step 5033):
Step 5031) in step 5021) in the subordinate phase traffic flow data sample set up, delete only property loss accident PDO data, retain slight personal injury accident BC and severely injured or fatal accident KA data, as phase III traffic flow data sample, binary logistic regression is then utilized to build such as formula the initial traffic hazard probability function of the phase III shown in (5):
formula (5)
Wherein, i=1,2 ..., n
3; n
3represent the subsample quantity that phase III traffic flow data sample packages contains; p
(3)(y
3i=1|x
i) represent that in phase III traffic flow data sample, i-th subsample probability that is severely injured or fatal accident KA occurs in phase III traffic hazard probability function, y
3irepresent the situation of i-th subsample generation traffic hazard in phase III traffic flow data sample, y
3ivalue be 1 or 0, y
3i=1 represents that in phase III traffic flow data sample, severely injured or fatal accident KA, y occur in i-th subsample
3i=0 represents that in phase III traffic flow data sample, slight personal injury accident BC, P occur in i-th subsample
(3)(y
3i=0|x
i) to represent in phase III traffic flow data sample that the probability of slight personal injury accident BC occurs in i-th subsample, P
(3)(y
3i=0|x
i)=1-P
(3)(y
3i=1|x
i); x
1irepresent the 1st traffic flow parameter of i-th subsample in phase III traffic flow data sample, x
2irepresent the 2nd traffic flow parameter of i-th subsample in phase III traffic flow data sample, x
21irepresent the 21st traffic flow parameter in i-th subsample in phase III traffic flow data sample, β
3_0represent the constant coefficient in phase III traffic hazard probability function, β
3_1represent in phase III traffic hazard probability function, the coefficient of the 1st traffic flow parameter; β
3_2represent in phase III traffic hazard probability function, the coefficient of the 2nd traffic flow parameter; β
3_21represent in phase III traffic hazard probability function, the coefficient of the 21st traffic flow parameter;
Step 5032) by the maximal value of measuring and calculating formula (6), obtain β
3_0, β
3_1, β
3_2..., β
3_21the value of 22 coefficients:
formula (6)
Wherein, lnL (β
3, x
i) represent the natural logarithm value of likelihood function;
Step 5033) by step 5032) saliency value of 22 coefficients that obtains compares with setting value B respectively, if the saliency value of coefficient is less than setting value B, then in formula (5), retain traffic flow parameter corresponding to this coefficient, otherwise in formula (5), delete traffic flow parameter corresponding to this coefficient, and be back to step 5031), until the saliency value of the coefficient of traffic flow parameter remaining in formula (5) is all less than setting value B, as calibrated phase III traffic hazard probability function;
Step 60) calculate different order of severity traffic hazard probability of happening: according to step 50) the calibrated first stage traffic hazard probability function determined, calibrated subordinate phase traffic hazard probability function and calibrated phase III traffic hazard probability function, according to formula (7) to formula (9), calculate the probability of happening P (PDO) of only property loss accident PDO, the probability of happening P (BC) of slight personal injury accident BC and the probability of happening P (KA) of severe injury or fatal accident KA respectively:
P (PDO)=P
(1)(x
i) × (1-P
(2)(x
i)) formula (7)
P (BC)=P
(1)(x
i) × P
(2)(x
i) × (1-P
(3)(x
i)) formula (8)
P (KA)=P
(1)(x
i) × P
(2)(x
i) × P
(3)(x
i) formula (9)
Wherein, P
(1)(x
i) represent the probable value recorded by calibrated first stage traffic hazard probability function, P
(2)(x
i) represent the probable value recorded by calibrated subordinate phase traffic hazard probability function, P
(3)(x
i) represent the probable value recorded by calibrated phase III traffic hazard probability function;
Step 70) calculate the probability threshold value of different order of severity traffic hazard: the probability threshold value P determining only property loss accident PDO according to formula (10) to formula (12) respectively
0_PDO, slight personal injury accident BC probability threshold value P
0_BC, severely injured or fatal accident KA probability threshold value P
0_KA:
P
0_PDO=α
(1)× (1-α
(2)) formula (10)
P
0_BC=α
(1)× α
(2)× (1-α
(3)) formula (11)
P
0_KA=α
(1)× α
(2)× α
(3)formula (12)
Wherein, α
(1)represent in step 40) traffic flow data sample in, only property loss accident PDO, slight personal injury accident BC and quantity summation that is severely injured or fatal accident KA account for the ratio of whole sample; α
(2)representing in step 5021) in the subordinate phase traffic flow data sample set up, slight personal injury accident BC and quantity summation that is severely injured or fatal accident KA account for the ratio of whole sample; α
(3)representing step 5031) in the phase III traffic flow data sample set up, quantity that is severely injured or fatal accident KA accounts for the ratio of whole sample;
Step 80) detect the probability that traffic hazard occurs in section in real time, and regulate and control vehicle: by being arranged on the Traffic flow detecting equipment on through street, real-time detection Current traffic data, by step 20) in corresponding traffic flow parameter substitute in formula (7), formula (8) and formula (9), calculate the probability of happening of only property loss accident PDO, slight personal injury accident BC, severe injury or fatal accident KA, as P (PDO) >P
0_PDOtime, then showing that this section is current has the risk that only property loss accident PDO occurs, and carries out early warning in this front, section by variable message board to driver; As P (BC) >P
0_BCtime, then show that this section is current and have the risk that slight personal injury accident BC 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; As P (KA) >P
0_KAtime, then show that this section is current and have the risk that severely injured or fatal accident KA occur, by variable message board, early warning is carried out to driver in this front, section, start opertaing device, by controlling the ring road of through street or the Intersections of through street, reduce upstream vehicle flow, and by variable speed-limit plate to Current vehicle speed limit, reduce the travel speed of upstream vehicle; As P (PDO)≤P
0_PDOtime, then show the current risk that only property loss accident PDO does not occur in this section, without the need to sending early warning; As P (BC)≤P
0_BCtime, then show the current risk that slight personal injury accident BC does not occur in this section, without the need to sending early warning; As P (KA)≤P
0_KAtime, then show the current risk that severe injury or fatal accident KA do not occur in this section, without the need to sending early warning;
Step 90) repeat step 80), carry out the detection that different order of severity traffic hazard probability occurs in next setting-up time T section, and regulate and control vehicle, until detection of end.
2. according to the vehicle regulate and control method of reduction according to claim 1 different order of severity traffic hazard probability, it is characterized in that, described step 10) in, 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.
3. according to the vehicle regulate and control method of reduction according to claim 1 different order of severity traffic hazard probability, it is characterized in that, described Traffic flow detecting equipment is electromagnetic induction coil, or video traffic flow assay device.
4. according to the vehicle regulate and control method of reduction according to claim 1 different order of severity traffic hazard probability, it is characterized in that, described step 20) in, by upstream and downstream two Traffic flow detecting equipment, according to the traffic flow data in sampling step length acquisition testing section, described sampling step length is 30 seconds.
5., according to the vehicle regulate and control method of reduction according to claim 1 different order of severity traffic hazard probability, it is characterized in that, described step 30) in, a=10.
6. according to the vehicle regulate and control method of reduction according to claim 1 different order of severity traffic hazard probability, it is characterized in that, described setting-up time T is 5-10 minutes.
7. according to the vehicle regulate and control method of reduction according to claim 1 different order of severity traffic hazard probability, it is characterized in that, described step 80) in, by variable speed-limit plate to Current vehicle speed limit, the car speed amplitude of each adjustment change is within 5km/h.
8. according to the vehicle regulate and control method of reduction according to claim 1 different order of severity traffic hazard probability, it is characterized in that, described setting value B is 0.05.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310093427.6A CN103198711B (en) | 2013-03-21 | 2013-03-21 | Vehicle regulating and controlling method of lowering probability of traffic accidents of different severity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310093427.6A CN103198711B (en) | 2013-03-21 | 2013-03-21 | Vehicle regulating and controlling method of lowering probability of traffic accidents of different severity |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103198711A CN103198711A (en) | 2013-07-10 |
CN103198711B true CN103198711B (en) | 2014-12-17 |
Family
ID=48721197
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310093427.6A Active CN103198711B (en) | 2013-03-21 | 2013-03-21 | Vehicle regulating and controlling method of lowering probability of traffic accidents of different severity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103198711B (en) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106982196B (en) * | 2016-01-19 | 2020-07-31 | 阿里巴巴集团控股有限公司 | Abnormal access detection method and equipment |
CN106355883B (en) * | 2016-10-20 | 2019-11-29 | 同济大学 | A kind of method, apparatus and system obtaining traffic accident probability of happening |
CN108154681B (en) * | 2016-12-06 | 2020-11-20 | 杭州海康威视数字技术股份有限公司 | Method, device and system for predicting risk of traffic accident |
CN106485922B (en) * | 2016-12-20 | 2019-03-12 | 东南大学 | Secondary traffic accident method for early warning based on high-precision traffic flow data |
CN110648537B (en) * | 2019-09-28 | 2021-03-05 | 安徽百诚慧通科技有限公司 | Traffic accident correlation analysis method based on Haen's law |
US11328505B2 (en) * | 2020-02-18 | 2022-05-10 | Verizon Connect Development Limited | Systems and methods for utilizing models to identify a vehicle accident based on vehicle sensor data and video data captured by a vehicle device |
CN112150807B (en) * | 2020-09-18 | 2024-01-09 | 腾讯科技(深圳)有限公司 | Vehicle early warning method and device, storage medium and electronic equipment |
CN113849971B (en) * | 2021-09-16 | 2023-03-28 | 广州文远知行科技有限公司 | Driving system evaluation method and device, computer equipment and storage medium |
CN114970943B (en) * | 2022-03-29 | 2023-04-07 | 浙江省交通投资集团有限公司智慧交通研究分公司 | Expressway accident type and severity prediction method |
CN115293255B (en) * | 2022-08-02 | 2023-05-05 | 河北雄安荣乌高速公路有限公司 | Expressway traffic accident risk model construction and risk discrimination method |
CN115909725B (en) * | 2022-11-01 | 2023-09-15 | 西部科学城智能网联汽车创新中心(重庆)有限公司 | Accident handling method and device based on vehicle-road cooperation |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1758065A2 (en) * | 2005-08-25 | 2007-02-28 | Siemens Aktiengesellschaft | Method for forecasting a traffic condition in a road network and traffic management centre |
CN101540101A (en) * | 2008-03-17 | 2009-09-23 | 上海宝康电子控制工程有限公司 | Method and system for detecting road traffic incidents |
CN102034349A (en) * | 2010-12-23 | 2011-04-27 | 东北林业大学 | Traffic event section segmented speed limiting value determining method |
CN102289933A (en) * | 2011-08-08 | 2011-12-21 | 上海电科智能系统股份有限公司 | Method for predicting grades of spatial effect ranges of traffic event effects on city expressways |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2893544B2 (en) * | 1990-01-11 | 1999-05-24 | 日本信号株式会社 | Abnormal traffic flow detection device |
-
2013
- 2013-03-21 CN CN201310093427.6A patent/CN103198711B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1758065A2 (en) * | 2005-08-25 | 2007-02-28 | Siemens Aktiengesellschaft | Method for forecasting a traffic condition in a road network and traffic management centre |
CN101540101A (en) * | 2008-03-17 | 2009-09-23 | 上海宝康电子控制工程有限公司 | Method and system for detecting road traffic incidents |
CN102034349A (en) * | 2010-12-23 | 2011-04-27 | 东北林业大学 | Traffic event section segmented speed limiting value determining method |
CN102289933A (en) * | 2011-08-08 | 2011-12-21 | 上海电科智能系统股份有限公司 | Method for predicting grades of spatial effect ranges of traffic event effects on city expressways |
Non-Patent Citations (2)
Title |
---|
徐铖铖,等.基于判别分析的高速公路交通安全实时评价指标.《东南大学学报(自然科学版)》.2012,第42卷(第3期),第555-559页. * |
赵雁,等.基于贝叶斯网络理论的交通事件预测模型.《电脑与信息技术》.2011,第19卷(第3期),第21-23,31页. * |
Also Published As
Publication number | Publication date |
---|---|
CN103198711A (en) | 2013-07-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103198711B (en) | Vehicle regulating and controlling method of lowering probability of traffic accidents of different severity | |
CN103198713B (en) | Based on the vehicle regulate and control method of the minimizing traffic hazard of traffic data and weather data | |
CN103150930B (en) | For the rear-end collision real-time predicting method of the normal property the sent out congested link of through street | |
CN102360525B (en) | Discriminant analysis-based high road real-time traffic accident risk forecasting method | |
CN104575051B (en) | Viaduct ramp intelligent signal control method and device based on array radars | |
CN103646534B (en) | A kind of road real-time traffic accident risk control method | |
CN102419905B (en) | Traffic-wave theory-based traffic influence area determining method of expressway accidents | |
CN103895649B (en) | A kind of driver safety driving warning method | |
CN102360526B (en) | Real-time monitoring method for road section state of high road | |
CN103065469B (en) | Travel time determination method and travel time determination device | |
CN104575050B (en) | A kind of fast road ramp intellectual inducing method and device based on Floating Car | |
CN111815967A (en) | Highway dynamic speed limit control method based on secondary traffic accident prevention | |
CN102567811A (en) | Real-time road traffic characteristic based motor vehicle emission measuring and calculating method | |
CN103606269A (en) | Control method for improving traffic efficiency of freeway construction area | |
CN104157156A (en) | Vehicle speed dynamic management and early warning method for dangerous section of expressway | |
CN103198707B (en) | A kind of vehicle regulate and control method based on traffic flow character dangerous under fine day situation | |
CN102568226A (en) | High speed variable speed limit control method based on adverse weather conditions | |
CN102735320A (en) | Method for identifying weights of cars based on dynamic strain of bridges | |
CN105702041A (en) | Highway multisource data fusion state estimation system based on neural network and method thereof | |
CN100481153C (en) | Method for automatically inspecting highway traffic event based on offset minimum binary theory | |
CN104851287A (en) | Method for urban road link travel time detection based on video detector | |
CN103955596A (en) | Accident hotspot comprehensive judging method based on traffic accident collection technology | |
CN104464294A (en) | Method and device for evaluating road segment traffic state based on array radar | |
CN106710242A (en) | Method for recognizing vehicle quantity of motorcade based on dynamic strain of bridge | |
CN103198709B (en) | Vehicle regulating and controlling method for reducing traffic accidents under raining conditions |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |