CN114822024A - Active safety guidance system for expressway agglomerate fog road section - Google Patents
Active safety guidance system for expressway agglomerate fog road section Download PDFInfo
- Publication number
- CN114822024A CN114822024A CN202210409934.5A CN202210409934A CN114822024A CN 114822024 A CN114822024 A CN 114822024A CN 202210409934 A CN202210409934 A CN 202210409934A CN 114822024 A CN114822024 A CN 114822024A
- Authority
- CN
- China
- Prior art keywords
- road section
- fog
- foggy
- section
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/048—Detecting movement of traffic to be counted or controlled with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
- G08G1/0141—Measuring and analyzing of parameters relative to traffic conditions for specific applications for traffic information dissemination
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/095—Traffic lights
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
Abstract
An active safety guidance system for a fog section of an expressway relates to the technical field of traffic, and aims at solving the problem that traffic accidents easily occur on the expressway in fog weather, and comprises an information acquisition subsystem, a central decision subsystem and a guidance control subsystem; the information acquisition subsystem comprises a traffic flow detection unit and a meteorological environment detection unit; the method has the advantages that traffic flow and environment information of the mass fog road section of the expressway are collected, psychological conditions of drivers are fully considered, information prompts are given to the front road to the drivers about to enter the mass fog road section, sight line information induction and variable speed limit are provided for the drivers in the mass fog road section, driving safety level of the mass fog road section can be effectively improved, and high-speed road accidents in mass fog days are reduced.
Description
Technical Field
The invention relates to the technical field of traffic, in particular to an active safety guidance system for a fog road section of a highway.
Background
According to statistics, traffic accidents caused by bad weather account for nearly 1/4 of the total number of accidents on the expressway, wherein the foggy weather can cause drivers to lose sight suddenly and deal with untimely driving, and further the traffic accidents are induced. Therefore, the active safety guidance system for the highway foggy road section is established, and has important significance for improving the traffic safety level of the highway foggy road section.
Disclosure of Invention
The purpose of the invention is: aiming at the problem that traffic accidents easily occur on the expressway in the foggy weather, the active safety guidance system for the foggy highway section is provided.
The technical scheme adopted by the invention to solve the technical problems is as follows:
an active safety guidance system for a fog section of a highway comprises an information acquisition subsystem, a central decision subsystem and a guidance control subsystem;
the information acquisition subsystem comprises a traffic flow detection unit and a meteorological environment detection unit;
the traffic flow detection unit is used for acquiring the traffic flow rate of the group fog road section and the average speed of the group fog road section;
the meteorological environment detection unit is used for acquiring the visibility of the group fog road section;
the central decision-making subsystem makes an induction strategy according to the road surface friction coefficient of the clustered fog road section, the longitudinal slope gradient of the clustered fog road section, the traffic flow rate of the clustered fog road section, the average speed of the clustered fog road section and the visibility of the clustered fog road section, which are acquired by the information acquisition subsystem, wherein the induction strategy comprises a road side warning lamp flashing strategy, a vehicle safe driving speed and a clustered fog road section driving risk severity degree;
and the induction control subsystem adjusts the flickering brightness and frequency of the yellow warning lamp according to the roadside warning lamp flickering strategy and reminds the safe driving speed of the vehicle and the driving risk severity of the foggy road section.
Further, the average vehicle speed of the foggy road section is represented as:
wherein n is the number of passing vehicles, v i Is the speed of each vehicle.
Further, the step of obtaining the road side warning light flashing strategy in the guidance strategy is as follows:
firstly, grading the visibility of a foggy road section, and then formulating a yellow warning lamp flashing strategy according to the visibility grade, wherein the yellow warning lamp flashing strategy is as follows:
| visibility level | Visibility range/m | Luminance/cd | Frequency/times/min |
| First stage | 300～ | -- | -- |
| Second stage | 200～300 | 450 | 45 |
| Three-stage | 150～200 | 550 | 75 |
| Four stages | 100～150 | 650 | 105 |
| Five stages | 50～100 | 750 | 135 |
| Six stages | 25～50 | 1000 | 165 |
。
Further, the step of obtaining the safe driving speed of the vehicle in the guidance strategy is as follows:
firstly, calculating the maximum safe speed according to the road surface friction coefficient of the mass fog road section, the longitudinal slope gradient of the mass fog road section and the visibility, and rounding the maximum safe speed downwards by a multiple of 5 to be used as a suggested speed limit value;
the maximum safe vehicle speed is expressed as:
wherein a is braking deceleration and the unit is m/s 2 ，
f is the friction coefficient of the pavement, f is 0.4, i is the gradient of a longitudinal slope, the unit is percent, an ascending slope is positive, a descending slope is negative, L is the visibility, and the unit is m.
Further, the step of obtaining the driving risk severity of the cluster fog road section in the induction strategy comprises:
the method comprises the following steps: establishing a BP neural network risk assessment model;
the method comprises the following steps: the traffic flow rate of the foggy road section, the average speed of the foggy road section, the visibility of the foggy road section and the longitudinal slope gradient of the foggy road section are taken as input indexes and are quantified, and the method specifically comprises the following steps:
traffic flow rates for the foggy road segment are quantified as the following four criteria:
500 below: 1;
500～750：2；
750～1000：3；
more than 1000: 4;
the unit of the traffic flow rate of the foggy road section is pcu/lane;
the average vehicle speed of the foggy road section is quantized into the following five standards:
70 of the following: 1;
70～80：2；
80～90：3；
90～100：4；
100～110：5；
the average speed unit of the foggy road section is km/h;
the visibility of the foggy road section is quantified as the following six standards:
300 above: 1;
200～300：2；
150～200：3；
100～150：4；
50～100：5；
50 below: 6;
the visibility unit of the foggy road section is m;
the longitudinal slope gradient of the road on the foggy road section is quantized into the following four standards:
1 the following: 1
1～2：2；
2～3：3；
3～4：4；
The gradient of the longitudinal slope of the road in the foggy road section is percent;
the first step is: normalizing the input index;
step one is three: carrying out weight assignment on each input index to obtain the weight of each input index;
step one is: obtaining a driving risk value according to the weight of each input index and the normalized numerical value, and taking the driving risk value as the output of the BP neural network;
step two: and dividing the driving risk value by using a support vector machine algorithm to obtain a dividing threshold of the driving risk value, and generating a driving risk grade judgment result of the foggy road section according to the dividing threshold.
Further, the normalization is expressed as:
wherein x is j The input index after normalization processing is x, min (x) is the minimum value in the original input index, and max (x) is the maximum value in the original input index.
Further, the weight assignment is expressed as:
wherein, K j Is the coefficient of variation of the j-th index, D j Is the mean square error of the j-th index,
is the mean of the j index, A i Is the weight of the jth index.
Further, the driving risk value is expressed as:
further, the second step comprises the following specific steps:
constructing a quadratic programming problem by using a kernel function, classifying by using the constructed quadratic programming problem, obtaining a partition threshold of a driving risk value according to a classification result, and finally generating a driving risk grade judgment result of the foggy road section according to the partition threshold;
the quadratic programming problem is represented as:
0≤α i ≤C，i＝1，2，...，N
wherein N is the number of samples, alpha i ，α j Is Lagrange multiplier, y i ，y j Is a sample x i ，x j Class label of, K (x) i ，x j ) Is a kernel function, taken as
C is a penalty factor, sigma represents the nuclear radius, and sigma is larger than 0;
the judgment result of the driving risk level of the foggy road section is represented as:
| traffic risk classification | Value of risk |
| Low risk | 0～0.5 |
| General risks | 0.5～1 |
| |
1～1.5 |
| High risk | 1.5 or more |
Further, the BP neural network specifically includes:
the number of nodes of the input layer is 4, and the input layer corresponds to 4 influence factors of the traffic flow rate of the foggy road section, the average speed, the visibility of the foggy road section and the longitudinal slope gradient of the foggy road section;
the transfer function of the hidden layer adopts tansig, and the number of nodes is 4;
the output layer transfer function adopts purelin, the number of nodes is 1, and the output result is the driving risk value of the foggy road section;
the training function adopts the rainlm; setting the initial weight and the threshold value between (-1, 1);
the hidden layer output value is as follows:
where f is the hidden layer transfer function, i.e., tansig function, w ij Is a weight, x, between an input layer node i and a hidden layer node j i Is the output value of the input layer node i, b j A threshold value for hidden layer node j;
the tansig function is expressed as:
the output layer output value is expressed as:
where g is the output layer transfer function, i.e. purelin function, v j The weight value between the hidden layer node j and the output layer node is shown, and c is the threshold value of the output layer node;
the purelin function is expressed as:
g(x)＝x
the neural network prediction error is expressed as:
e＝A-Y
wherein A is the desired output;
updating weights w between input layer and hidden layer by prediction error ij Weight v between hidden layer and output layer j And each node threshold b of the hidden layer j And an output layer node threshold, c, expressed as:
w ij ＝w ij +ηS j (1-S j )x i v j e,i＝1,2,3,4；j＝1,2,3,4
v j ＝v j +ηS j e,j＝1,2,3,4
b j ＝b j +ηS j (1-S j )v j e,j＝1,2,3,4
c＝c+e
wherein η is the learning rate.
The invention has the beneficial effects that:
the method has the advantages that traffic flow and environment information of the mass fog road section of the expressway are collected, psychological conditions of drivers are fully considered, information prompts are given to the front road to the drivers about to enter the mass fog road section, sight line information induction and variable speed limit are provided for the drivers in the mass fog road section, driving safety level of the mass fog road section can be effectively improved, and high-speed road accidents in mass fog days are reduced.
Drawings
FIG. 1 is a block diagram of the present application;
FIG. 2 is a diagram of an induction apparatus layout;
FIG. 3 is a schematic diagram illustrating a corresponding relationship between driving risk levels and risk values in a foggy road section;
fig. 4 is a BP neural network flow.
Detailed Description
It should be noted that, in the present invention, the embodiments disclosed in the present application may be combined with each other without conflict.
The first embodiment is as follows: specifically explaining the embodiment with reference to fig. 1, the embodiment describes an active safety guidance system for a fog section of an expressway;
the existing active safety guidance system aiming at the foggy road section generally provides two auxiliary guidance of road profile reinforcement and variable speed limit for a driver, and less adopts vehicle-road cooperation and 5G-V2X technology, so that the information prompt is given to the road ahead of the driver before the driver drives into the foggy road section by combining a variable information board, an in-vehicle voice system and ZigBee and 5G-V2X communication technologies, and the driving safety level of the foggy road section can be effectively improved.
The system comprises an information acquisition subsystem, a central decision subsystem and an induction control subsystem;
the information acquisition subsystem comprises a traffic flow detection unit and a meteorological environment detection unit and acquires related information for subsequent analysis and induction.
The traffic flow detection unit acquires the traffic flow rate of the group fog road section and the average vehicle speed information.
The meteorological environment detection unit acquires visibility information of the group fog road section.
And arranging a radar and an visibility meter on the foggy road section, detecting traffic flow rate and average vehicle speed information of the foggy road section by using the radar, detecting visibility information of the foggy road section by using the visibility meter, and uploading the acquired information to the central decision-making subsystem through a communication network.
The average speed of the foggy road section is as follows:
wherein n is the number of vehicles passing through in a certain time; v. of i Is the speed of each vehicle.
The central decision-making subsystem makes a self-adaptive induction strategy according to the related information uploaded by the information acquisition subsystem, and the self-adaptive induction strategy comprises a roadside warning lamp flashing strategy, a vehicle safe driving speed calculation and a running risk severity degree of a foggy road section.
The central decision subsystem comprises a highway fog cluster section database, the traffic volume, the average speed, the visibility and the road longitudinal slope gradient information of the highway fog cluster section are stored and extracted, and the database is continuously updated by the information uploaded by the information acquisition subsystem.
Grading the visibility level of the foggy road section, and formulating a flashing strategy of a yellow warning lamp according to the visibility level.
According to the visibility grade detected by the visibility meter, the yellow warning light is set according to the traffic warning light (GB/T24965.3), and the setting is shown in the table 1, wherein, the condition of 'minus' indicates that the yellow warning light is not turned on.
Flashing standard table of yellow warning lamp 1
Calculating the maximum safe vehicle speed according to the information such as the road surface friction coefficient, the longitudinal slope gradient, the visibility and the like of the foggy road section, taking a multiple which is less than the maximum safe vehicle speed and is 5 as a suggested speed limit value, and calculating the maximum safe vehicle speed according to the following formula:
wherein a is the braking deceleration (m/s) 2 )，
f is the friction coefficient of the pavement, and is taken as 0.4; i is the slope of the longitudinal slope,%, the ascending slope is positive, and the descending slope is negative; l is the visibility, m.
And the information of the longitudinal slope gradient of the road is input into the central decision subsystem in advance.
The maximum safe vehicle speed on the highway foggy section is shown in table 2.
Maximum safe vehicle speed (km/h) table 2 of highway foggy section
And establishing a BP neural network risk assessment model according to the information such as the traffic flow rate, the average speed, the visibility and the longitudinal slope of the group fog road section, calculating the driving risk level of the group fog road section, and formulating corresponding prompt information.
And according to the database information, quantizing the input indexes:
the hourly traffic flow rate Q (pcu/lane) for the foggy road segment was quantified as the following four criteria:
500 the following: 1;
②500～750：2；
③750～1000：3；
fourthly, more than 1000: 4.
the average vehicle speed (km/h) of the foggy road section is quantized into the following five standards:
70 the following: 1;
②70～80：2；
③80～90：3；
④90～100：4；
⑤100～110：5。
the visibility (m) of foggy road sections is quantified as the following six criteria:
300 and above: 1;
②200～300：2；
③150～200：3；
④100～150：4；
⑤50～100：5；
sixthly, 50 of: 6.
the longitudinal slope gradient (%) of the fogged road section is quantized into the following four standards:
1 the following: 1
②1～2：2；
③2～3：3；
④3～4：4。
The input index of each sample in the database is normalized according to the following formula:
wherein x is j The input index after normalization processing is obtained; x is an original input index; min (x) is the minimum value in the original input indexes; max (x) is the maximum value in the original input index.
And assigning weights to the input indexes, wherein the assignment calculation formula is as follows:
wherein: k j The coefficient of variation of the jth index; d j Is the mean square error of the jth index;
is the mean value of the jth index; a. the j Is the weight of the jth index.
And finally, calculating to obtain a driving risk value according to the weight of each index and the normalized numerical value, wherein the driving risk value is used as the output of the BP neural network, and the driving risk value is calculated according to the following formula:
dividing the risk values by using a support vector machine algorithm to obtain a division threshold value of the risk values, and generating a driving risk grade judgment result of the foggy road section, wherein the process is as follows:
the sample is a multidimensional array formed by four indexes of hour traffic flow rate, average vehicle speed, visibility and longitudinal slope, and cannot be linearly divided, so that the linear division is realized by utilizing a kernel function, and the problem of convex-down quadratic programming is constructed:
0≤α i ≤C,i＝1,2,...,N
wherein: n is the number of samples; alpha (alpha) ("alpha") i ,α j Is a lagrange multiplier; y is i ,y j Is a sample x i ,x j Class labels of (1); k (x) i ,x j ) Is a kernel function, taken as
And C is a penalty factor.
The threshold value of low risk and general risk obtained by the algorithm of the support vector machine is 0.495 and is taken as 0.5; the threshold for general risk and higher risk is 1.034, which is taken as 1; the threshold for higher risk and high risk is 1.478, taken as 1.5. The corresponding relationship between the driving risk level and the risk value of the foggy road section is shown in table 3.
Corresponding relation table 3 between driving risk level and risk value in foggy road section
Constructing a BP neural network, optimizing each input index weight, and enabling the structure to be as shown in FIG. 3:
4 input layer nodes in the BP neural network correspond to 4 influence factors of average hourly flow rate, average vehicle speed, visibility and longitudinal slope gradient; tan sig is adopted as the hidden layer transfer function, and the number of nodes is 4; the output layer transfer function adopts purelin, the number of nodes is 1, and the output result is the driving risk value of the foggy road section; the training function adopts the rainlm; the initial weight and threshold are set between (-1, 1).
The hidden layer output value is as follows:
wherein f is a hidden layer transfer function, namely a tansig function; w is a ij The weight value between the input layer node i and the hidden layer node j is obtained; x is the number of i Is the output value of the input layer node i; b j A threshold value that implies a layer node j.
the tansig function is given by:
the output layer output value is as follows:
wherein g is an output layer transfer function, namely a purelin function; v. of j The weight value between the hidden layer node j and the output layer node; c is the threshold of the output layer node.
The purelin function is given by:
g(x)＝x (10)
the neural network prediction error is calculated as follows:
e＝A-Y (11)
where A is the desired output.
Updating weights w between input layer and hidden layer by prediction error ij Weight v between hidden layer and output layer j And each node threshold b of the hidden layer j And an output layer node threshold c, calculated as:
w ij ＝w ij +ηS j (1-S j )x i v j e,i＝1,2,3,4；j＝1,2,3,4 (12)
v j ＝v j +ηS j e,j＝1,2,3,4 (13)
b j ＝b j +ηS j (1-S j )v j e,j＝1,2,3,4 (14)
c＝c+e (15)
wherein η is the learning rate.
The BP neural network flow is shown in fig. 4:
the guidance control subsystem transmits the guidance strategy to the driver in a visual mode, and comprises a variable information board, a warning lamp and a vehicle-mounted voice system, as shown in fig. 2.
A plurality of warning lights are arranged at equal intervals at the guardrails on two sides of the group fog road section, and the flashing brightness and frequency of the yellow warning lights are adjusted according to the formulated flashing strategy of the yellow warning lights.
And the central control subsystem distributes the vehicle suggested speed limit value to the guidance control subsystem through a communication network.
Lay the variable information board of roadside (I, II, III …) at group's fog highway section, show suggestion speed limit value, this information is reported by voice system in the car simultaneously:
the 'road section speed limit xx' is broadcasted through voice, and if a driver exceeds the speed limit, the 'you overspeed and please drive the speed limit xx' is broadcasted through voice.
And a road side variable information board (O) is arranged in front of the group fog road section to prompt road information of the group fog road section, and the information is simultaneously broadcasted by an in-vehicle voice system. The variable information panel display information is shown in table 4.
Variable information board display information table 4
Example (b):
hardware aspects in this embodiment: the method comprises the steps that an OGREAT X2 radar is selected as a traffic flow rate and vehicle speed detection device, a CS120A visibility meter is selected as a visibility detection device, an STC89C52 single chip microcomputer is selected as a calculation unit, and the arrangement distance of warning lamps is 30 m; software design aspect: adopting C language as programming language; the communication mode is as follows: the ZigBee wireless communication technology is selected to realize the communication between the control host and the radar, the visibility meter, the warning lamp and the variable information board, and the 5G-V2X wireless communication technology is selected to realize the communication between the control host and the vehicle.
The invention is adopted to actively induce a fog section of a certain highway:
(1) the section between the variable information boards of the foggy section is marked as S i The information acquisition subsystem acquires a road section S i Hourly traffic flow rate, average vehicle speed, and visibility.
(2) And uploading the information to a cloud road section database of the central decision subsystem through a communication network by utilizing a ZigBee technology.
(3) For road section S 1 The hourly traffic flow rate was 8000pcu/h, the average vehicle speed was 90km/h, the visibility was 75m, and the longitudinal slope gradient was 2.5%. Calculated by the cloud:
firstly, the roadside warning lamp flickers at a luminance of 75cd, and the frequency is 135 times/min;
the vehicle suggested speed limit value is 45 km/h;
and the risk value is 1.12, corresponding to higher risk.
(4) The ZigBee technology and the 5G-V2X technology are utilized to issue a warning light flashing strategy, a speed limit strategy and road information of a group fog road section to an induction control subsystem:
firstly, the roadside warning lamp flickers at a luminance of 75cd, and the frequency is 135 times/min;
secondly, a variable information board (O) is used as a pre-prompt board to display 'the front fog dangerous road section and the attention speed limit is 45', and the information is simultaneously broadcasted by an in-vehicle voice system;
and thirdly, the variable information board (I) displays the suggested speed limit value 45, and simultaneously, the voice system in the vehicle broadcasts the road speed limit 45, and if the driver exceeds the speed limit, the voice broadcasts that you have overspeed and please drive at the speed limit 45.
(5) The display information of the subsequent variable information boards (II, III and IV …) is calculated from the corresponding road section information.
The vehicle suggested speed limit values for the highway foggy section are shown in table 5.
Vehicle suggested speed limit value (km/h) table 5 of highway foggy section
It should be noted that the detailed description is only for explaining and explaining the technical solution of the present invention, and the scope of protection of the claims is not limited thereby. It is intended that all such modifications and variations be included within the scope of the invention as defined in the following claims and the description.
Claims (10)
1. An active safety guidance system for a fog section of a highway is characterized by comprising an information acquisition subsystem, a central decision subsystem and a guidance control subsystem;
the information acquisition subsystem comprises a traffic flow detection unit and a meteorological environment detection unit;
the traffic flow detection unit is used for acquiring the traffic flow rate of the group fog road section and the average speed of the group fog road section;
the meteorological environment detection unit is used for acquiring the visibility of the group fog road section;
the central decision-making subsystem makes an induction strategy according to the road surface friction coefficient of the clustered fog road section, the longitudinal slope gradient of the clustered fog road section, the traffic flow rate of the clustered fog road section, the average speed of the clustered fog road section and the visibility of the clustered fog road section, which are acquired by the information acquisition subsystem, wherein the induction strategy comprises a road side warning lamp flashing strategy, a vehicle safe driving speed and a clustered fog road section driving risk severity degree;
and the induction control subsystem adjusts the flickering brightness and frequency of the yellow warning lamp according to the roadside warning lamp flickering strategy and reminds the safe driving speed of the vehicle and the driving risk severity of the foggy road section.
2. The active safety guidance system for the fog section of the expressway of claim 1, wherein the average vehicle speed of the fog section is expressed as:
wherein n is the number of passing vehicles, v i Is the speed of each vehicle.
3. The active safety guidance system for the fog section of the highway according to claim 2, wherein the guidance strategy comprises the following steps of:
firstly, grading the visibility of a foggy road section, and then formulating a yellow warning lamp flashing strategy according to the visibility grade, wherein the yellow warning lamp flashing strategy is as follows:
。
4. The active safety guidance system for the fog section of the highway according to claim 3, wherein the step of obtaining the safe driving speed of the vehicle in the guidance strategy is as follows:
firstly, calculating the maximum safe speed according to the road surface friction coefficient of the mass fog road section, the longitudinal slope gradient of the mass fog road section and the visibility, and rounding the maximum safe speed downwards by a multiple of 5 to be used as a suggested speed limit value;
the maximum safe vehicle speed is expressed as:
wherein a is braking deceleration and the unit is m/s 2 ，
f is the friction coefficient of the pavement, f is 0.4, i is the gradient of a longitudinal slope, the unit is percent, an ascending slope is positive, a descending slope is negative, L is the visibility, and the unit is m.
5. The active safety guidance system for the fog-clustered highway section according to claim 4, wherein the step of obtaining the driving risk severity of the fog-clustered highway section in the guidance strategy comprises:
the method comprises the following steps: establishing a BP neural network risk assessment model;
the method comprises the following steps: the traffic flow rate of the foggy road section, the average speed of the foggy road section, the visibility of the foggy road section and the longitudinal slope gradient of the foggy road section are taken as input indexes and are quantified, and the method specifically comprises the following steps:
traffic flow rates for the foggy road segment are quantified as the following four criteria:
500 below: 1;
500～750：2；
750～1000：3；
more than 1000: 4;
the unit of the traffic flow rate of the cluster fog road section is pcu/lane;
the average vehicle speed of the foggy road section is quantized into the following five standards:
70 of the following: 1;
70～80：2；
80～90：3；
90～100：4；
100～110：5；
the average speed unit of the foggy road section is km/h;
the visibility of the foggy road section is quantified as the following six standards:
300 above: 1;
200～300：2；
150～200：3；
100～150：4；
50～100：5；
50 below: 6;
the visibility unit of the foggy road section is m;
the longitudinal slope gradient of the road on the foggy road section is quantized into the following four standards:
1 the following: 1
1～2：2；
2～3：3；
3～4：4；
The gradient of a longitudinal slope of the road in the fog road section is percent;
the first step is: normalizing the input index;
step one is three: carrying out weight assignment on each input index to obtain the weight of each input index;
step one is: obtaining a driving risk value according to the weight of each input index and the normalized numerical value, and taking the driving risk value as the output of the BP neural network;
step two: and dividing the driving risk value by using a support vector machine algorithm to obtain a dividing threshold of the driving risk value, and generating a driving risk grade judgment result of the cluster fog road section according to the dividing threshold.
6. The active safety inducement system according to claim 5, characterized in that the normalization is expressed as:
wherein x is j The input index after normalization processing is x, min (x) is the minimum value in the original input index, and max (x) is the maximum value in the original input index.
7. The active safety guidance system for fog sections on expressways according to claim 6, characterized in that the weight assignment is expressed as:
wherein, K j Is the coefficient of variation of the j-th index, D j Is the mean square error of the j-th index,
is the mean of the j index, A j Is the weight of the jth index.
8. The active safety guidance system for fog sections on expressways according to claim 7, characterized in that the driving risk values are expressed as:
9. the active safety guidance system for the fog-gathered highway section according to claim 8, wherein the second step comprises the following specific steps:
constructing a quadratic programming problem by using a kernel function, classifying by using the constructed quadratic programming problem, obtaining a partition threshold of a driving risk value according to a classification result, and finally generating a driving risk grade judgment result of the foggy road section according to the partition threshold;
the quadratic programming problem is represented as:
wherein N is the number of samples, alpha i ，α j Is Lagrange multiplier, y i ，y j Is a sample x i ，x j Class label of, K (x) i ，x j ) Is a kernel function, taken as
C is a penalty factor, sigma represents the nuclear radius, and sigma is larger than 0;
the judgment result of the driving risk level of the foggy road section is represented as:
。
10. The active safety guidance system for the fog section of the highway according to claim 9, wherein the BP neural network is specifically:
the number of nodes of the input layer is 4, and the input layer corresponds to 4 influence factors of the traffic flow rate of the foggy road section, the average speed, the visibility of the foggy road section and the longitudinal slope gradient of the foggy road section;
the transfer function of the hidden layer adopts tansig, and the number of nodes is 4;
the output layer transfer function adopts purelin, the number of nodes is 1, and the output result is the driving risk value of the foggy road section;
the training function adopts the rainlm; setting the initial weight and the threshold value between (-1, 1);
the hidden layer output value is as follows:
where f is the hidden layer transfer function, i.e., tansig function, w ij Is a weight, x, between an input layer node i and a hidden layer node j i Is the output value of the input layer node i, b j A threshold value for hidden layer node j;
the tansig function is expressed as:
the output layer output value is expressed as:
where g is the output layer transfer function, i.e. purelin function, v j The weight value between the hidden layer node j and the output layer node is shown, and c is the threshold value of the output layer node;
the purelin function is expressed as:
g(x)＝x
the neural network prediction error is expressed as:
e＝A-Y
wherein A is the desired output;
updating weights w between input layer and hidden layer by prediction error ij Weight v between hidden layer and output layer j And each node threshold b of the hidden layer j And an output layer node threshold, c, expressed as:
w ij ＝w ij +ηS j (1-S j )x i v j e,i＝1,2,3,4；j＝1,2,3,4
v j ＝v j +ηS j e,j＝1,2,3,4
b j ＝b j +ηS j (1-S j )v j e,j＝1,2,3,4
c＝c+e
wherein η is the learning rate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210409934.5A CN114822024A (en) | 2022-04-19 | 2022-04-19 | Active safety guidance system for expressway agglomerate fog road section |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210409934.5A CN114822024A (en) | 2022-04-19 | 2022-04-19 | Active safety guidance system for expressway agglomerate fog road section |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114822024A true CN114822024A (en) | 2022-07-29 |
Family
ID=82506154
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210409934.5A Pending CN114822024A (en) | 2022-04-19 | 2022-04-19 | Active safety guidance system for expressway agglomerate fog road section |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114822024A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117275250A (en) * | 2023-09-20 | 2023-12-22 | 南京鑫荣汇信息科技有限公司 | Early warning device and method for induction of expressway fog area |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160082978A1 (en) * | 2013-04-18 | 2016-03-24 | Takashi Ozaki | Driving assistance apparatus and driving assistance method |
| CN108932859A (en) * | 2018-07-18 | 2018-12-04 | 上海市政工程设计研究总院（集团）有限公司 | A kind of the expressway fog early warning and inducible system of gamut real-time monitoring |
| CN112837535A (en) * | 2021-03-22 | 2021-05-25 | 北京百度网讯科技有限公司 | Traffic information processing method, device, system, equipment and storage medium |
| CN112863201A (en) * | 2021-01-07 | 2021-05-28 | 武汉理工大学 | Guiding method based on expressway agglomerate fog area multi-stage early warning system |
| CN113160593A (en) * | 2021-01-18 | 2021-07-23 | 重庆交通大学 | Mountain road driving safety early warning method based on edge cloud cooperation |
| CN113436434A (en) * | 2021-06-25 | 2021-09-24 | 中科路恒工程设计有限公司 | Mountain trunk highway high-risk road section early warning system and method |
-
2022
- 2022-04-19 CN CN202210409934.5A patent/CN114822024A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160082978A1 (en) * | 2013-04-18 | 2016-03-24 | Takashi Ozaki | Driving assistance apparatus and driving assistance method |
| CN108932859A (en) * | 2018-07-18 | 2018-12-04 | 上海市政工程设计研究总院（集团）有限公司 | A kind of the expressway fog early warning and inducible system of gamut real-time monitoring |
| CN112863201A (en) * | 2021-01-07 | 2021-05-28 | 武汉理工大学 | Guiding method based on expressway agglomerate fog area multi-stage early warning system |
| CN113160593A (en) * | 2021-01-18 | 2021-07-23 | 重庆交通大学 | Mountain road driving safety early warning method based on edge cloud cooperation |
| CN112837535A (en) * | 2021-03-22 | 2021-05-25 | 北京百度网讯科技有限公司 | Traffic information processing method, device, system, equipment and storage medium |
| CN113436434A (en) * | 2021-06-25 | 2021-09-24 | 中科路恒工程设计有限公司 | Mountain trunk highway high-risk road section early warning system and method |
Non-Patent Citations (1)
| Title |
|---|
| 郭晓澎等: "高速公路团雾预警与主动诱导系统研究", 《电子测量技术》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117275250A (en) * | 2023-09-20 | 2023-12-22 | 南京鑫荣汇信息科技有限公司 | Early warning device and method for induction of expressway fog area |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112863201B (en) | Guiding method based on expressway agglomerate fog area multi-stage early warning system | |
| CN103895649B (en) | A kind of driver safety driving warning method | |
| CN104867327B (en) | Driving safety monitoring method and device | |
| CN106127586A (en) | Vehicle insurance rate aid decision-making system under big data age | |
| CN111477005B (en) | Intelligent perception early warning method and system based on vehicle state and driving environment | |
| CN107730937A (en) | The tunnel gateway dynamic vehicle speed abductive approach that a kind of street accidents risks minimize | |
| CN113257024B (en) | V2I-based rear-end collision prevention early warning method and system for expressway rain and fog environment | |
| CN109408557B (en) | Traffic accident cause analysis method based on multiple correspondences and K-means clustering | |
| CN111563555A (en) | Driver driving behavior analysis method and system | |
| CN114822024A (en) | Active safety guidance system for expressway agglomerate fog road section | |
| CN110239559B (en) | Dangerous driving vehicle detection method and device based on new energy vehicle data | |
| CN113129610A (en) | Unfavorable weather expressway self-adaptive variable speed limit and information cooperative control system | |
| CN114169444A (en) | Driving style classification method considering risk potential field distribution under vehicle following working condition | |
| CN111009125B (en) | Urban intersection pedestrian and vehicle collision probability calculation method | |
| CN115641736B (en) | Intelligent guidance system and method for special road section of expressway | |
| CN117292540A (en) | Vehicle sideslip and rollover early warning system and method in bridge crosswind environment | |
| CN116229762A (en) | Intersection right-turning collision early warning method based on intelligent luminous line | |
| CN105608315A (en) | Quantitative evaluation method and system of safety service level of bus stop | |
| CN109910865A (en) | A kind of vehicle early warning brake method based on Internet of Things | |
| CN112070419B (en) | Method for quantifying risk of potential dangerous situation of automobile driving | |
| CN108638954B (en) | Vehicle headlamp turning angle control method based on safety equation | |
| CN113378479A (en) | Intelligent standard method and system based on automatic driving test intelligent platform vehicle | |
| CN114882710A (en) | Intelligent automobile early warning system based on real-time monitoring of visibility in foggy weather | |
| CN112590791A (en) | Intelligent vehicle lane change gap selection method and device based on game theory | |
| CN112036709A (en) | Random forest based rainfall weather expressway secondary accident cause analysis method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |