A method for predicting group compliance with variable speed limits based on cross-sectional traffic flow parameters

Abstract

The present invention provides a method for predicting group compliance of variable speed limit based on cross-sectional traffic flow parameters, including: inputting a traffic flow characteristic parameter matrix to be tested into a driver group compliance prediction model based on a traffic flow characteristic parameter matrix to obtain a driver compliance grade; the method for constructing a driver group compliance prediction model based on the traffic flow characteristic parameter matrix is: setting a lane-level variable speed limit board at a first preset spacing on a high-speed road to display lane-level speed limit information; obtaining a training traffic flow characteristic parameter matrix; calculating and obtaining the compliance of the driver group to be tested; obtaining a grade compliance set; constructing a compliance original database; and constructing a driver group compliance prediction model based on the traffic flow characteristic parameter matrix based on the LGBM model. The present invention solves the problems in the prior art that speed limit optimization cannot be performed according to driver compliance and that most current roads do not have the function of vehicle trajectory collection.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent traffic control, and in particular to a method for predicting group compliance with a variable speed limit based on cross-sectional traffic flow parameters. Background Art

[0002] With the development of sensing technology, artificial intelligence, 5G and Internet of Things technology, precise and personalized vehicle command push technology is gradually accelerating towards implementation, and intelligent networked vehicle technology is constantly updated and iterated. Intelligent networked vehicles will realize the reconstruction of the relationship between people, vehicles and roads, making the perception and control of vehicles leap to a new level. With the popularization of motor vehicles and the growth of transportation demand, the static speed control method and the information release method based on variable information boards used in the current highway safety active control technology are gradually unable to meet the needs of the intelligent network environment. First, the static speed limit method cannot provide safe and reasonable speed limit values ​​for different working conditions and specific conditions under dynamic road traffic environments, and cannot optimize the speed limit according to the driver's compliance; second, most of the current roads do not have the function of vehicle trajectory collection, and the means of information release based on variable information boards cannot provide personalized speed limit guidance for specific vehicles, resulting in large differences in management effects between different individuals, which has a negative impact on highway traffic safety. Summary of the invention

[0003] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide a method for predicting group compliance with a variable speed limit based on cross-sectional traffic flow parameters. The present invention solves the problem that the prior art cannot optimize the speed limit according to the driver's compliance and that most current roads do not have the function of collecting vehicle trajectories.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] A method for predicting group compliance with variable speed limits based on cross-sectional traffic flow parameters, comprising:

[0006] Input the traffic flow characteristic parameter matrix to be tested into the driver group compliance prediction model based on the traffic flow characteristic parameter matrix to obtain the driver compliance level;

[0007] The method for constructing the driver group compliance prediction model based on the traffic flow characteristic parameter matrix is ​​as follows:

[0008] Lane-level variable speed limit signs are arranged at a first preset interval on the expressway to display lane-level speed limit information;

[0009] Setting traffic flow parameter collection devices at a second preset interval on both sides of the expressway to obtain a training traffic flow characteristic parameter matrix;

[0010] Based on the compliance calculation formula and lane-level speed limit information, the compliance of the driver group to be tested is calculated;

[0011] Differentiating the compliance levels according to a compliance level differentiation formula to obtain a level compliance set;

[0012] Constructing a compliance original database according to the grade compliance set and the training traffic flow characteristic parameter matrix;

[0013] Based on the LGBM model, a driver group compliance prediction model based on the traffic flow characteristic parameter matrix is ​​constructed according to the compliance original database and the training traffic flow characteristic parameter matrix.

[0014] Preferably, the lane-level variable speed limit signs are arranged at preset intervals on the expressway to display lane-level speed limit information, including:

[0015] A plurality of lane-level variable speed limit plates are arranged on the gantry at a first preset interval to display speed limit information of each lane, wherein each lane-level variable speed limit plate corresponds to one lane.

[0016] Preferably, the step of arranging traffic flow parameter collection devices at a second preset interval on both sides of the expressway to obtain a training traffic flow characteristic parameter matrix includes:

[0017] Traffic flow parameter collection devices are arranged at a second preset interval on both sides of the expressway to collect the flow rate of the vehicles to be tested, the density of the vehicles to be tested and the speed of the vehicles to be tested;

[0018] A training traffic flow characteristic parameter matrix is ​​constructed according to the flow rate of the vehicles to be tested, the density of the vehicles to be tested and the speed of the vehicles to be tested.

[0019] Preferably, the calculation formula for the compliance degree of the driver group to be tested is:

[0020] Comprate i (t)=

[0021]

[0022] Among them, Comprate i (t) is the compliance degree of the driving group at time t, is the average speed of the vehicle group at 250m upstream of the lane-level variable speed limit plate at time t, is the average speed of the vehicle group 200m downstream of the lane-level variable speed limit plate at time t, and VSL(t) is the variable speed limit value issued at time t.

[0023] Preferably, the compliance level formula is:

[0024]

[0025] Preferably, the LGBM model is based on the original compliance database and the training traffic flow characteristic parameter matrix to construct a driver group compliance prediction model based on the traffic flow characteristic parameter matrix, including:

[0026] Performing dimensionality reduction processing on the training traffic flow characteristic parameter matrix by using the importance ranking of the random forest model to obtain a training data set;

[0027] Based on the LGBM model, the training data set is used as an independent variable, and the original compliance database is used as a dependent variable to construct a driver group compliance prediction model based on the traffic flow characteristic parameter matrix.

[0028] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0029] The present invention provides a method for predicting group compliance with a variable speed limit based on cross-sectional traffic flow parameters. The present invention constructs a driver group compliance prediction model based on a traffic flow characteristic parameter matrix, and can use limited cross-sectional traffic flow characteristic parameters to predict the compliance of a group of drivers, with low cost and accurate prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0031] Figure 1 A flow chart of a method for predicting group compliance with a variable speed limit based on cross-sectional traffic flow parameters provided by an embodiment of the present invention;

[0032] Figure 2 A schematic diagram of the principle of a method for predicting group compliance with a variable speed limit based on cross-sectional traffic flow parameters provided by an embodiment of the present invention;

[0033] Figure 3 A schematic diagram of a method for deploying a variable speed limit information release device in a method for predicting group compliance with a variable speed limit based on cross-sectional traffic flow parameters provided by an embodiment of the present invention;

[0034] Figure 4 A schematic diagram of a method for deploying traffic flow parameter collection equipment for a method for predicting group compliance with a variable speed limit based on cross-sectional traffic flow parameters provided by an embodiment of the present invention;

[0035] Figure 5A schematic diagram of variable importance ranking selection for a method for predicting group compliance with a variable speed limit based on cross-sectional traffic flow parameters provided by an embodiment of the present invention;

[0036] Figure 6 A schematic diagram of a method for obtaining values ​​of traffic flow characteristic parameters of a method for predicting group compliance with a variable speed limit based on cross-sectional traffic flow parameters provided by an embodiment of the present invention;

[0037] Figure 7 A schematic diagram of a random forest parameter optimization process for a variable speed limit group compliance prediction method based on cross-sectional traffic flow parameters provided by an embodiment of the present invention;

[0038] Figure 8 AUC curve of the LGBM model of a variable speed limit group compliance prediction method based on cross-sectional traffic flow parameters provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] The purpose of the present invention is to provide a method for predicting group compliance with a variable speed limit based on cross-sectional traffic flow parameters. The present invention solves the problems in the prior art that the speed limit cannot be optimized according to the driver's compliance and that most of the current roads do not have the function of collecting vehicle trajectories.

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0042] like Figure 1 As shown, the present invention provides a method for predicting group compliance with a variable speed limit based on cross-sectional traffic flow parameters, comprising:

[0043] Step 100: inputting the traffic flow characteristic parameter matrix to be tested into the constructed driver group compliance prediction model based on the traffic flow characteristic parameter matrix to obtain the driver compliance level;

[0044] The method for constructing the driver group compliance prediction model based on the traffic flow characteristic parameter matrix is ​​as follows:

[0045] Step 101: Arranging lane-level variable speed limit signs at a first preset interval on an expressway to display lane-level speed limit information;

[0046] Step 102: Setting traffic flow parameter collection devices at a second preset interval on both sides of the expressway to obtain a training traffic flow characteristic parameter matrix;

[0047] Step 103: Based on the compliance calculation formula and the lane-level speed limit information, the compliance of the driver group to be tested is calculated and obtained;

[0048] Step 104: Differentiate the compliance levels according to the compliance level differentiation formula to obtain a level compliance set;

[0049] Step 105: constructing a compliance original database according to the grade compliance set and the training traffic flow characteristic parameter matrix;

[0050] Step 106: Based on the LGBM model, a driver group compliance prediction model based on the traffic flow characteristic parameter matrix is ​​constructed according to the compliance original database and the training traffic flow characteristic parameter matrix.

[0051] Furthermore, the lane-level variable speed limit signs are arranged at preset intervals on the expressway to display lane-level speed limit information, including:

[0052] A plurality of lane-level variable speed limit plates are arranged on the gantry at a first preset spacing to display the speed limit information of each lane, wherein each lane-level variable speed limit plate corresponds to one lane. The lane-level variable speed limit plates are information instruction issuing devices for the lane-level variable speed limit control system, and are arranged on the gantry at a spacing of 750m. Each lane-level variable speed limit plate issues variable speed limit information for one lane, and the lane-level speed limit instructions on different lanes and upstream and downstream can have different speed limit values.

[0053] Traffic flow parameter collection devices such as coils, radars, and cameras are deployed with a spacing of 600 meters to 800 meters. The output data type is in the form of traffic flow parameters to realize the collection and analysis of traffic flow characteristic parameters of driver groups.

[0054] Traffic flow parameters and lane-level speed limit information are all collected in real time and use UTC time. The locations where the data is released use unified stake number coordinates.

[0055] Furthermore, the step of setting up traffic flow parameter collection devices at a second preset interval on both sides of the expressway to obtain a training traffic flow characteristic parameter matrix includes:

[0056] Traffic flow parameter collection devices are arranged at a second preset interval on both sides of the expressway to collect the flow rate of the vehicles to be tested, the density of the vehicles to be tested and the speed of the vehicles to be tested;

[0057] A training traffic flow characteristic parameter matrix is ​​constructed according to the flow rate of the vehicles to be tested, the density of the vehicles to be tested and the speed of the vehicles to be tested.

[0058] Specifically, the training traffic flow characteristic parameter data characteristics of different speed limit combinations and different compliance levels are analyzed, and specific lanes are selected to extract traffic flow parameters, including: flow, density, and speed collected every 30 seconds. Traffic flow characteristic parameters are calculated, including: maximum, minimum, mean, variance, and coefficient of variation of flow collected every 5 minutes, maximum, minimum, mean, variance, and coefficient of variation of density collected every 5 minutes, and maximum, minimum, mean, variance, and coefficient of variation of speed collected every 5 minutes. According to the high, medium, and low compliance levels of the driver group, three traffic flow characteristic parameter databases are finally obtained.

[0059] Furthermore, the calculation formula for the compliance of the driver group to be tested is:

[0060]

[0061] Among them, Comprate i (t) is the compliance degree of the driving group at time t, is the average speed of the vehicle group at 250m upstream of the lane-level variable speed limit plate at time t, is the average speed of the vehicle group 200m downstream of the lane-level variable speed limit plate at time t, and VSL(t) is the variable speed limit value issued at time t.

[0062] Furthermore, the driver and vehicle are defined with compliance levels of 1 and 0.8 as boundaries, and high, medium and low compliance levels are defined. The compliance level formula is:

[0063]

[0064] According to the compliance levels of drivers and vehicles, the training traffic flow characteristic parameters are divided into three data sets, namely high compliance data set, medium compliance data set and low compliance data set.

[0065] Furthermore, the LGBM model is based on the original compliance database and the training traffic flow characteristic parameter matrix to construct a driver group compliance prediction model based on the traffic flow characteristic parameter matrix, including:

[0066] The parameters in the traffic flow parameter matrix are used as input variables and data standardization is performed, and the importance ranking of the random forest model is used to reduce the dimension of the training traffic flow characteristic parameter matrix to obtain a training data set;

[0067] Based on the LGBM model, the training data set is used as an independent variable, and the original compliance database is used as a dependent variable to construct a driver group compliance prediction model based on the traffic flow characteristic parameter matrix.

[0068] Specifically, the parameter selection rules of the trajectory characteristic parameter matrix are as follows: the extraction position is 200m, 800m, 1400m, 2000m upstream of the position where the vehicle receives the variable speed limit instruction, and 400m and 1000m downstream of the position where the vehicle receives the variable speed limit instruction. The extraction time granularity is 5min, and the extraction time is 5min, 10min, 15min, 20min, 25min, and 30min before the vehicle receives the variable speed limit instruction. The characteristic parameters include the maximum, minimum, mean, variance, and coefficient of variation of the flow rate collected every 5 minutes, the maximum, minimum, mean, variance, and coefficient of variation of the density collected every 5 minutes, and the maximum, minimum, mean, variance, and coefficient of variation of the speed collected every 5 minutes. The top 20 most important variables are selected by using the random forest variable importance ranking, and the LGBM is adjusted to finally obtain the driver group compliance prediction model based on the traffic flow characteristic parameter matrix with the highest prediction accuracy.

[0069] The present invention also provides a specific embodiment 1:

[0070] 1) If Figure 2 As shown, a series of lane-level variable speed limit information release devices are arranged at certain intervals on a high-speed expressway section with free flow status.

[0071] The alignment of the road needs to comply with the requirements of the Highway Alignment Design Specifications (JTG D20-2017); the setting of signs and markings in the scene needs to comply with the requirements of the Road Traffic Signs and Markings (GB 5768-2009) and the Highway Speed ​​Limit Sign Design Specifications (JTG / T 3381-02-2020). Figure 3 shown.

[0072] 2) Deploy traffic flow parameter collection devices at certain intervals on the road to collect and analyze traffic flow characteristic parameters such as flow rate, density, and speed.

[0073] The collection equipment can collect the flow, density, and speed every 30 seconds. Calculate traffic flow characteristic parameters, including: the maximum, minimum, mean, variance, and coefficient of variation of the flow collected every 5 minutes, the maximum, minimum, mean, variance, and coefficient of variation of the density collected every 5 minutes, and the maximum, minimum, mean, variance, and coefficient of variation of the speed collected every 5 minutes. The layout of the collection equipment is as follows: Figure 4 As shown, the data format Table 1 is a variable description table of the collected traffic flow characteristic parameters, and Table 1 is as follows:

[0074] Table 1. Variable description of collected traffic flow characteristic parameters

[0075]

[0076]

[0077] 3) According to the preset control strategy, the variable information system is used to issue and control the corresponding lane-level speed limit control instructions, adjust the speed limit value of the lane-level variable speed limit plate, and export the traffic flow parameters and lane-level speed limit information release data in real time.

[0078] The lane-level variable speed limit board is an information instruction issuing device for the variable speed limit control system. It is arranged on the gantry at a spacing of 750m. Each lane-level variable speed limit board issues variable speed limit information for one lane. The lane-level speed limit instructions on different lanes and upstream and downstream can have different speed limit values. By changing and adjusting the speed limit value of the variable speed limit sign in real time, the operating state of the road traffic flow can be changed in real time. Table 2 is a statistical table of lane-level speed limit information release, as shown below:

[0079] Table 2 Statistics of lane-level speed limit information release

[0080]

[0081]

[0082] At the same time, traffic flow characteristic parameters and driving group compliance indicators are counted after each speed limit information is released. The traffic flow characteristic parameters include cross-sectional flow (mean value, variance, maximum value, minimum value, coefficient of variation), speed (mean value, variance, maximum value, minimum value, coefficient of variation), and density (mean value, variance, maximum value, minimum value, coefficient of variation) at 200m, 800m, 1400m, and 2000m upstream of a specific location, and 400m and 1000m downstream of a specific location. The statistical time granularity is 5 minutes, and the statistical time is 5 minutes, 10 minutes, 15 minutes, 20 minutes, 25 minutes, and 30 minutes before each dangerous driving behavior, that is, a total of 540 traffic flow parameters;

[0083] According to the compliance levels of drivers and vehicles, the traffic flow characteristic parameters are divided into three data sets, namely high compliance data set, medium compliance data set and low compliance data set.

[0084] 4) The driver's compliance level is used as the dependent variable and the traffic flow characteristic parameter matrix is ​​used as the independent variable. The XGBoost model is trained. The original data set is established using the compliance level obtained in 3), and the data dimension is reduced by using the importance ranking of the XGBoost model to obtain the training data set.

[0085] like Figure 5-6As shown, the obtained data is preprocessed, and each characteristic index is normalized, and all characteristic indicators are normalized to the interval of [-1,1]. The parameter value rules of the characteristic parameter matrix are as follows: the extraction positions are 200m, 800m, 1400m, and 2000m upstream of the position where the vehicle receives the variable speed limit instruction, and 400m and 1000m downstream of the position where the vehicle receives the variable speed limit instruction. The extraction time granularity is 5min, and the extraction time is 5min, 10min, 15min, 20min, 25min, and 30min before the vehicle receives the variable speed limit instruction. The characteristic parameters include the maximum value, minimum value, mean value, variance, and coefficient of variation of the flow rate collected every 5 minutes, the maximum value, minimum value, mean value, variance, and coefficient of variation of the density collected every 5 minutes, and the maximum value, minimum value, mean value, variance, and coefficient of variation of the speed collected every 5 minutes. The top 20 most important variables were selected by random forest variable importance ranking, and the parameters of LGBM were adjusted to finally obtain the driver group compliance prediction model based on the traffic flow characteristic parameter matrix with the highest prediction accuracy.

[0086] The traffic flow characteristic parameter matrix database is as follows:

[0087]

[0088]

[0089]

[0090] Among them, a 1j (i) is the maximum flow rate of the i-th section at time j, a 2j (i) is the minimum flow rate at the i-th section at time j, a 3j (i) is the mean flow rate of the i-th section at time j, a 4j (i) is the flow variance of the i-th section at time j, a 5j (i) is the flow variation coefficient of the i-th section at time j; b 1j (i) is the maximum density value of the i-th section at time j, b 2j (i) is the minimum density value of the i-th section at time j, b 3j (i) is the mean density of the i-th section at time j, b 4j (i) is the density variance of the i-th section at time j, b 5j (i) Density variation coefficient of the i-th section at time j; c 1j (i) Maximum velocity of the i-th section at time j, c 2j (i) is the minimum velocity of the i-th section at time j, c 3j (i) is the mean velocity of the i-th section at time j, c 4j(i) is the velocity variance of the i-th section at time j, c 5j (i) is the velocity variation coefficient of the i-th section at time j.

[0091] The traffic flow characteristic parameter matrix is:

[0092]

[0093] Compliance_1_2, VSL_0, VSL_1, and VSL_1_2 are added as environmental parameters to the independent variables, where Compliance_1_2 is the compliance of the driving group, VSL_0 is the speed limit of the left lane, VSL_1 is the speed limit of the middle lane, and VSL_1_2 is the speed limit of the lane.

[0094] 5) Use random forest variable importance ranking to select the top 20 most important variables. First, find the number of trees with the smallest out-of-bag error of random forest to optimize the random forest parameters, and finally obtain the number of trees with the highest prediction accuracy. Use the LGBM model to build a driver group compliance prediction model based on the traffic flow characteristic parameter matrix.

[0095] The random forest out-of-bag error optimization process is as follows: Figure 7 As shown, the final number of trees selected is 37, and the final selection of independent variables is Cvdensity_2000_1, Averagespeed_1400_1, Varspeed_800_1, Vardensity_800_1, Varflow_800_1, Maxflow_800_1, Minflow_800_1, Cvflow_800_1, Maxdensity_800_1, Mindensity_800_1, Cvdensity_800_1, Maxspeed_200_1, Cvspeed_200_1, Averageflow_200_1, Averagedensity_200_1, Minspeed_400_2, Vardensity_400_2, Maxdensity_400_2, Mindensity_400_2, Averagedensity_400_2.

[0096] The final prediction of the constructed LGBM model is as follows Figure 8 As shown in Table 3, the prediction indicators are ACC 94.44%, NPV 97.39%, PPV 91.83%, TPR 97.55%, TNR 91.34%, and F1 Score 94.60%, with good prediction performance. The confusion matrix is ​​used to verify the prediction performance of the LGBM model. Table 3 is the confusion matrix table of the LGBM model. Table 3 is as follows:

[0097]

[0098] The beneficial effects of the present invention are as follows:

[0099] By finding a high-speed expressway with a free flow period and a lane-level variable speed limit plate; laying out a cross-section traffic flow data collection device at a certain interval on the roadside; according to the preset control strategy, using the variable information system to issue and control the corresponding lane-level speed limit control command, adjusting the speed limit value of the lane-level variable speed limit plate; using the traffic flow data collection device to collect and analyze the traffic flow characteristic parameters, analyze the traffic flow data characteristics under different speed limit combinations, extract cross-section flow, density, speed and other traffic flow characteristic data, and construct a lane-level variable speed limit group compliance prediction model based on cross-section driving trajectory data. The lane-level variable speed limit group compliance prediction method of cross-section traffic flow parameters provided by the present invention uses cross-section traffic flow characteristic data to realize the downstream driver group compliance prediction, solves the problem that the traditional traffic variable speed limit control cannot optimize the speed limit according to the driver's compliance, and solves the problem that most of the current roads do not have the function of vehicle trajectory collection but only have the function of cross-section traffic flow data collection, and can use limited cross-section traffic flow characteristic parameters to predict compliance, with low cost, accurate prediction, and the characteristics of replicability and strong robustness.

[0100] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0101] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for predicting group compliance with variable speed limits based on cross-sectional traffic flow parameters, characterized in that: include: Input the traffic flow characteristic parameter matrix to be tested into the driver group compliance prediction model based on the traffic flow characteristic parameter matrix to obtain the driver compliance level; The method for constructing the driver group compliance prediction model based on the traffic flow characteristic parameter matrix is ​​as follows: Lane-level variable speed limit signs are arranged at first preset intervals on the expressway to display lane-level speed limit information; Setting traffic flow parameter collection devices at a second preset interval on both sides of the expressway to obtain a training traffic flow characteristic parameter matrix; Based on the compliance calculation formula and lane-level speed limit information, the compliance of the driver group to be tested is calculated; Differentiating the compliance levels according to a compliance level differentiation formula to obtain a level compliance set; Constructing a compliance original database according to the grade compliance set and the training traffic flow characteristic parameter matrix; Based on the LGBM model, a driver group compliance prediction model based on the traffic flow characteristic parameter matrix is ​​constructed according to the compliance original database and the training traffic flow characteristic parameter matrix; The LGBM model is based on the original compliance database and the training traffic flow characteristic parameter matrix to construct a driver group compliance prediction model based on the traffic flow characteristic parameter matrix, including: Performing dimensionality reduction processing on the training traffic flow characteristic parameter matrix by using the importance ranking of the random forest model to obtain a training data set; Based on the LGBM model, the training data set is used as an independent variable, and the original compliance database is used as a dependent variable to construct a driver group compliance prediction model based on the traffic flow characteristic parameter matrix.

2. The method for predicting group compliance with variable speed limit based on cross-sectional traffic flow parameters according to claim 1, characterized in that: Lane-level variable speed limit signs are set at preset intervals on expressways to display lane-level speed limit information, including: A plurality of lane-level variable speed limit plates are arranged on the gantry at a first preset interval to display speed limit information of each lane, wherein each lane-level variable speed limit plate corresponds to one lane.

3. The method for predicting group compliance with variable speed limit based on cross-sectional traffic flow parameters according to claim 1, characterized in that: The step of setting up traffic flow parameter collection devices at a second preset interval on both sides of the expressway to obtain a training traffic flow characteristic parameter matrix includes: Traffic flow parameter collection devices are arranged at a second preset interval on both sides of the expressway to collect the flow rate of the vehicles to be tested, the density of the vehicles to be tested and the speed of the vehicles to be tested; A training traffic flow characteristic parameter matrix is ​​constructed according to the flow rate of the vehicles to be tested, the density of the vehicles to be tested and the speed of the vehicles to be tested.

4. The method for predicting group compliance with variable speed limit based on cross-sectional traffic flow parameters according to claim 1, characterized in that: The calculation formula of the compliance degree of the driver group to be tested is: = in, is the compliance degree of the driving group at time t, is the average speed of the vehicle group at 250m upstream of the lane-level variable speed limit plate at time t, is the average speed of the vehicle group at 200m downstream of the lane-level variable speed limit plate at time t, is the variable speed limit value published at time t, and i is a natural number, indicating the i-th one.

5. The method for predicting group compliance with variable speed limit based on cross-sectional traffic flow parameters according to claim 4, characterized in that: The compliance level formula is: .

Images