A highway accident risk assessment and dynamic control method and device

Abstract

The present invention relates to the field of traffic management, and the purpose is to provide a method and equipment for evaluating and dynamically controlling the risk of highway accidents, so as to improve the efficiency and safety of road use. The technical scheme of the present invention is: a method for evaluating and dynamically controlling the risk of highway accidents, comprising the following steps: step S1: acquiring data, acquiring real-time monitoring data and event data, and extracting risk assessment features; step S2: accident risk assessment, inputting risk assessment features into a traffic safety level classification model to classify traffic safety levels, and conducting accident risk assessment; step S3: dynamic control, dynamic control before and after the accident according to whether an accident occurs; step S4: adjusting control measures, returning to step S1 every 15 minutes, re-evaluating the accident risk and taking dynamic control. The present invention can effectively deal with highway accidents, reduce the impact of accidents on traffic, and improve road use efficiency and safety through real-time data analysis and dynamic control strategies.

Description

Technical Field

[0001] The present invention relates to the field of traffic management, and in particular to a method for risk assessment and dynamic control of highway accidents. Background Art

[0002] With the increase in traffic volume, highway accidents are frequent, which has a serious impact on traffic safety and road smoothness. The existing traffic management system has deficiencies in accident prevention and emergency response, and cannot effectively reduce the risk of accidents, nor can it quickly restore traffic order after an accident. Therefore, a system that can evaluate accident risks in real time and dynamically adjust control measures is needed to improve the safety and efficiency of highways. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies in the above-mentioned background technology and provide a method and equipment for highway accident risk assessment and dynamic control to improve road use efficiency and safety.

[0004] The technical solution of the present invention is:

[0005] A highway accident risk assessment and dynamic control method comprises the following steps:

[0006] Step S1: Get data

[0007] Obtain real-time monitoring data and event data, and extract risk assessment features;

[0008] Step S2: Accident risk assessment

[0009] Input the risk assessment characteristics into the traffic safety grade classification model to classify the traffic safety grade and conduct accident risk assessment;

[0010] Step S3: Dynamic Control

[0011] Carry out dynamic control before and after an accident based on whether an accident occurs;

[0012] Step S4: Adjust control measures

[0013] Every 15 minutes, return to step S1, re-evaluate the accident risk and take corresponding dynamic control measures.

[0014] The step S1 comprises:

[0015] S1-1: Obtain real-time monitoring data and event data;

[0016] S1-2: Extract risk assessment features from real-time monitoring data;

[0017] S1-3: Extract risk assessment features from event data;

[0018] S1-4: Determine whether an accident has occurred.

[0019] The step S2 comprises:

[0020] S2-1: Convert risk assessment characteristics into scores;

[0021] S2-2: Calculate the weights of risk assessment features;

[0022] S2-3: Calculate the traffic safety score S;

[0023] S2-4: Evaluate the traffic safety level of the road section.

[0024] The step S2-4 includes: if no accident occurs, the traffic safety score S of the road section is classified into safety, general risk, relatively high risk, and high risk; if an accident occurs, the traffic safety score S of the road section is classified into remaining risk and high risk.

[0025] The step S3 comprises:

[0026] S3-1: No accident has occurred, and dynamic control before the accident is carried out;

[0027] S3-2: When an accident occurs, dynamic management and control will be carried out after the accident.

[0028] The dynamic control before the accident includes:

[0029] 1) When the traffic safety level of a road section is safe, no control measures will be taken;

[0030] 2) When the traffic safety level of a road section is a general risk, the control measure adopts VMS dynamic speed limit;

[0031] 3) When the traffic safety level of a road section is high risk, the control measures adopt variable speed limits based on vehicle speed standard deviation for different vehicle types and lanes;

[0032] 4) When the traffic safety level of a road section is high risk, the control measures adopt variable speed limits and ramp controls based on vehicle type and lane based on speed standard deviation.

[0033] The VMS dynamic speed limit includes:

[0034] a. Speed ​​limit control

[0035] Control the speed limit value Vn of the VMS equipment in the speed limit area to ensure that the vehicle speed in the speed limit area is lower than the maximum speed limit of the highway and higher than the minimum speed limit of the highway;

[0036] b. Speed ​​limit difference control

[0037] Control the speed limit difference of adjacent VMS devices;

[0038] c. Induced speed limit control:

[0039] Control Plan 1: For sections with a traffic density of 5 vehicles / km / lane, implement three-stage speed limit measures, and issue guidance information at the 6th, 4th and 2nd VMS devices upstream of the current section, with speed limits of 110km / h, 100km / h and 90km / h respectively;

[0040] Control Plan 2: For sections where the traffic density reaches 15 vehicles / km / lane, a single-section speed limit measure is implemented, and the fifth VMS device upstream of the current section issues traffic guidance information with a speed limit of 110km / h;

[0041] Control plan 3: When the traffic density is 30 vehicles / km / lane, implement two-stage speed limit measures, and issue traffic guidance information at the 6th and 1st VMS devices upstream of the current road section, with speed limits of 90km / h and 70km / h respectively;

[0042] d. Highway entrance and exit control

[0043] When the overall traffic density reaches severe congestion, close the highway entrance where the main traffic source is located upstream of the current road section;

[0044] 3) When the traffic safety level of a road section is high risk, the control measures adopt variable speed limits based on vehicle speed standard deviation for different vehicle types and lanes;

[0045] 4) When the traffic safety level of a road section is high risk, the control measures adopt variable speed limits and ramp controls based on vehicle type and lane based on speed standard deviation.

[0046] The dynamic control after the accident includes: when the traffic safety level of the road section is high risk or other risks, the control measures all adopt VMS dynamic speed limit.

[0047] The VMS dynamic speed limit includes:

[0048] a) Speed ​​limit control

[0049] Control the speed limit value Vn of the VMS equipment in the speed limit area to ensure that the vehicle speed in the speed limit area is lower than the maximum speed limit of the highway and higher than the minimum speed limit of the highway;

[0050] b) Speed ​​limit difference control

[0051] Control the speed limit difference of adjacent VMS devices;

[0052] c) Induced speed limit control

[0053] Control Plan 1: For a road section with a lane closure time of 30 minutes and a traffic density of 5 vehicles / km / lane, a three-stage speed limit measure is implemented, and guidance information is issued at the 6th, 4th and 2nd VMS devices upstream of the current road section, with speed limits of 110km / h, 90km / h and 70km / h respectively;

[0054] Control Plan 2: For a road section with a lane closure time of 30 minutes and a traffic density of 110 vehicles / km / lane, a single-section speed limit measure is implemented, and the fifth VMS device upstream of the current road section issues traffic guidance information with a speed limit of 90km / h;

[0055] Control plan 3: When the lane closure time is 30 minutes and the traffic density is 70 vehicles / km / lane, a two-stage speed limit measure is implemented, and traffic guidance information is issued at the 6th and 1st VMS devices upstream of the current road section, with speed limits of 70km / h and 60km / h respectively;

[0056] Control Plan 4: For a road section with a lane closure time of 60 minutes and a traffic density of 5 vehicles / km / lane, a three-stage speed limit measure is implemented, and guidance information is issued at the 5th, 4th and 1st VMS devices upstream of the current road section, with speed limits of 110km / h, 100km / h and 90km / h respectively;

[0057] Control Plan 5: For sections where the lane closure time is 60 minutes and the traffic density is 110 vehicles / km / lane, a single-section speed limit measure is implemented, and the sixth VMS device upstream of the current section issues traffic guidance information with a speed limit of 90km / h;

[0058] Control Plan 6: When the lane closure time is 60 minutes and the traffic density is 70 vehicles / km / lane, a two-stage speed limit measure is implemented, and traffic guidance information is issued at the 6th and 5th VMS devices upstream of the current road section, with speed limits of 70km / h and 60km / h respectively;

[0059] d) Highway entrance and exit control

[0060] When the overall traffic density reaches severe congestion, the highway entrance that is the main source of traffic upstream of the current section will be closed.

[0061] A highway accident risk assessment and dynamic control device comprises a memory and a processor; the memory is used to store a computer program; the processor is used to implement the highway accident risk assessment and dynamic control method when executing the computer program.

[0062] The beneficial effects of the present invention are:

[0063] (1) The present invention can evaluate accident risks in real time and dynamically adjust traffic control measures, thereby improving driving safety and management efficiency on highways.

[0064] (2) The present invention can classify highway traffic safety levels through a traffic safety level classification model, providing theoretical and technical support for highway safety management departments.

[0065] (3) The present invention can dynamically adjust speed limits and highway intersection controls according to different accident situations and traffic conditions, thereby optimizing traffic flow and reducing the impact of accidents on traffic. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a flow chart of the present invention.

[0067] Figure 2 It is a comparison chart of the number of parking times and waiting time of different control measures of the present invention.

[0068] Figure 3 It is a comparison chart of average speed improvement of different control measures of the present invention. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0070] like Figure 1 As shown, a highway accident risk assessment and dynamic control method includes the following steps:

[0071] Step S1: Get data

[0072] Obtain real-time monitoring data and event data, and extract risk assessment features.

[0073] Risk assessment characteristics include traffic speed and density characteristics before the accident, traffic flow temporal and spatial characteristics, traffic flow dynamic characteristics, road section characteristics, weather characteristics, and accident possibility characteristics.

[0074] S1-1: Obtaining real-time monitoring data and event data

[0075] The real-time monitoring data includes the entrance flow data extracted from the highway entrance toll station and the gantry transaction data extracted from the gantry.

[0076] Event data is data reported by external systems.

[0077] S1-2: Extracting risk assessment features from real-time monitoring data

[0078] The real-time monitoring data is input into the SUMO software to obtain the pre-accident traffic speed and density characteristics, traffic flow temporal and spatial characteristics, and traffic flow dynamic characteristics of the road section.

[0079] Specifically, it includes: extracting vehicle data (including time period, vehicle type, number of vehicles, and average vehicle speed) from real-time road monitoring data, inputting it into SUMO software to generate traffic flow files (including vehicle type, traffic flow, and time interval), and allocating it to the corresponding road section of the road network of SUMO software. SUMO software outputs three risk assessment features: traffic speed and density characteristics before the accident, spatiotemporal characteristics of traffic flow, and dynamic characteristics of traffic flow.

[0080] SUMO software analyzes the vehicle speed and density information of vehicle data and obtains the speed and density characteristics of traffic flow before the accident through statistics.

[0081] SUMO software obtains the spatiotemporal characteristics of traffic flow by analyzing the spatiotemporal grid data or spatiotemporal graph data of vehicle data.

[0082] SUMO software obtains the dynamic characteristics of traffic flow by analyzing the changes of vehicle data over time and space.

[0083] The highway is divided into several sections. The length of each section is determined by actual needs and can be tens of meters, hundreds of meters, or several kilometers.

[0084] S1-3: Extracting risk assessment features from event data

[0085] Three risk assessment features are extracted from the event data, including road section features, weather features, and accident possibility features.

[0086] The road section characteristics include the road section geometry, road surface conditions, and traffic control facilities. The road section characteristics are data reported by the external system. The road section characteristics need to be updated regularly.

[0087] Weather characteristics include temperature, humidity, precipitation, and wind speed. Weather characteristics are data reported by external systems and need to be updated in real time.

[0088] The accident probability characteristics include the probability of an accident, the probability of a rear-end collision, the probability of casualties, and the probability of only property damage. The accident probability characteristics are data reported by the external system and need to be updated regularly.

[0089] S1-4: Determine whether an accident has occurred

[0090] Determine whether an accident has occurred by manually analyzing real-time monitoring data and data reported by external systems.

[0091] Step S2: Accident risk assessment

[0092] The risk assessment characteristics are input into the traffic safety grade classification model to classify the traffic safety grade and conduct accident risk assessment.

[0093] S2-1: Convert risk assessment characteristics into scores

[0094] 1) Traffic speed and density characteristics before the accident A

[0095] The score is determined by comprehensively considering the average vehicle speed (v, unit: km / h) and traffic density (ρ, unit: vehicles / km) of the road section before the accident, and the value range is 0-100.

[0096] Set reasonable speed and density reference ranges, and score according to the actual monitoring data falling into different ranges. Taking the highway scenario as an example, when the average speed is in a reasonable high-speed range (such as 80≤v≤120) and the traffic density is at a moderate level (such as 10≤ρ≤30), A is 80 (out of 100); if the speed is too high (v>120) or too low (v<80), the density is too large (ρ>30) or too small (ρ<10), points will be deducted according to the degree of deviation.

[0097] 2) Traffic flow spatiotemporal characteristics B

[0098] Upstream and downstream speed difference b 1 : Accounts for 30% of the total score of the spatiotemporal characteristics of traffic flow, and the standardized score is b 1 (Value range 0-100). The smaller the upstream and downstream speed difference, the safer it is. For example, when the upstream and downstream speed difference is less than or equal to 10 km / h, b 1 The value is 80, and points will be deducted accordingly as the speed difference increases.

[0099] Speed ​​variation coefficient b 2 : It accounts for 20% of the total score of the spatiotemporal characteristics of traffic flow, and the standardized score is b 2 (Value range 0-100). The speed variation coefficient reflects the speed fluctuation. Generally, when the speed variation coefficient is less than or equal to 0.2, the traffic flow is considered to be relatively stable. 2 The value is 80, and the larger the coefficient of variation, the lower the score.

[0100] Minute cross-sectional flow rate ratio b 3 : It accounts for 15% of the total score of the spatiotemporal characteristics of traffic flow, and the standardized score is b 3 (Value range 0-100). The score can be set according to the reasonable flow rate ratio range under historical normal traffic flow. For example, when the flow rate ratio is maintained at 0.8-1.2, b 3 The value is 80, and points will be deducted if it deviates from this range.

[0101] Merging traffic volume 4 : It accounts for 15% of the total score of the spatiotemporal characteristics of traffic flow, and the standardized score is recorded as b4 (Value range 0-100). The merging traffic volume takes a higher value within the design capacity. For example, when the traffic volume at the merging point is less than or equal to 1,000 vehicles per hour, b 4 The value is 80. If it exceeds the limit, points will be deducted according to the degree of excess.

[0102] Gini coefficient of vehicle arrival b 5 : Accounts for 10% of the total score of traffic flow spatiotemporal characteristics, and the standardized score is b 5 (Value range 0-100). The closer the Gini coefficient is to 0, the more balanced and safer the vehicle is. For example, when the Gini coefficient is less than or equal to 0.3, b 5 The value is 80, otherwise points will be deducted.

[0103] The difference between the traffic volume flowing into and out of the road section b 6 : Accounts for 10% of the total score of traffic flow spatiotemporal characteristics, and the standardized score is b 6 (Value range 0-100). The smaller the difference between inflow and outflow traffic volume, the better. If the difference is within a reasonable range (such as -50 to 50 vehicles / hour), b 6 The value is 80, and points will be deducted if the difference is too large.

[0104] The score of the traffic flow spatiotemporal feature B is calculated as:

[0105] B=0.3b 1 +0.2b 2 +0.15b 3 +0.15b 4 +0.1b 5 +0.1b 6

[0106] 3) Traffic flow dynamic characteristics C

[0107] A standardized score (ranging from 0 to 100) is given after comprehensive evaluation from multiple dimensions such as the volatility of traffic flow and the stability of speed changes. For example, by analyzing the time series data of traffic flow and speed over a period of time, when the flow fluctuation is small and the speed changes smoothly, the C value is higher, C is 80, and if there is a large fluctuation or mutation, points will be deducted accordingly. The specific scoring rules need to be combined with actual data analysis and safety threshold setting.

[0108] 4) Road characteristics D

[0109] Road Alignmentd 1 : Accounts for 30% of the total road feature score, and the standardized score is d 1 (Value range 0-100). Comprehensively evaluate according to road design specifications (such as curve radius meets safety requirements, turning angle is reasonable, etc.). For example, when the curve radius is greater than the minimum safety radius and the turning angle is in the appropriate range, d 1The value is 80, and points will be deducted if it does not meet the design standards.

[0110] Maximum longitudinal slope of the road d 2 : Accounts for 20% of the total road feature score, standardized score d 2 (Value range 0-100). The longitudinal slope is within the design allowable range (for example, the maximum longitudinal slope of a highway generally does not exceed 3%-5%, and different grades of roads have different standards), d 2 The value is 80. If it exceeds the limit, points will be deducted according to the degree of excess.

[0111] Traffic signs and signals completeness rate d 3 : Accounts for 30% of the total road feature score, denoted as d 3 (Value range 0-100). When the completion rate reaches 95% or above, d 3 The value is 80, and points will be deducted every time it decreases by a certain percentage.

[0112] Damage rate of road ancillary facilities 4 : Accounts for 20% of the total road feature score, score d 4 (Value range 0-100). When the damage rate is less than 5%, d 4 The value is 80, and the higher the damage rate, the lower the score.

[0113] The score calculation formula of road feature D is:

[0114] D=0.3d 1 +0.2d 2 +0.3d 3 +0.2d 4

[0115] 5) Weather characteristics E

[0116] Scoring is done based on weather conditions (value range is 0-100). Specific scores are set based on the actual impact of different weather conditions on traffic safety.

[0117] For example, when it is sunny and visibility is good, the value of E is 80; when it is raining lightly, which has a certain impact on traffic, the value of E is 60; when it is foggy, snowy or other severe weather that seriously affects traffic safety, the value of E is 20.

[0118] 6) Accident probability index F

[0119] The probability of an accident occurring (P Crash )f 1 : Accounts for 40% of the total score of the accident probability index, and the standardized score is f 1 (Value range 0-100). The probability of an accident can be obtained through the relevant accident prediction model. The lower the probability, the higher the score. For example, P Crash When f is less than or equal to 0.01,1 The value is 80, and points will be deducted if the probability increases.

[0120] The probability of a rear-end collision (P RE )f 2 : Accounts for 30% of the total score of the accident probability index, and the standardized score is f 2 (Value range 0-100). When the rear-end collision probability is low, for example, P RE Less than or equal to 0.005, f 2 The value is 80, and the score is adjusted according to the probability.

[0121] The probability of casualties (P RE-I )f 3 : Accounts for 15% of the total score of the accident probability index, and the standardized score is f 3 (Value range 0-100). The probability of casualties is low, for example, P RE-I When it is less than or equal to 0.001, f 3 The value is 80, and points will be deducted as the probability increases.

[0122] The probability of property loss only (1-P RE-I )f 4 : Accounts for 15% of the total score of the accident probability index, and the standardized score is set to f 4 (Value range 0-100), the score can be determined based on the relative relationship with the probability of other accident consequences and overall safety considerations, such as comprehensive weighing with the probability of casualties, to ensure that the overall score reasonably reflects the safety situation.

[0123] The score of the accident probability index F is calculated as:

[0124] F=0.4f 1 +0.3f 2 +0.15f 3 +0.15f 4

[0125] S2-2: Calculate weights for risk assessment characteristics

[0126] The weights of traffic flow speed and density characteristics before the accident, traffic flow spatiotemporal characteristics, traffic flow dynamic characteristics, road section characteristics, weather characteristics, and accident probability index are calculated by entropy method (existing method):

[0127] 1) Obtain historical data (historical traffic parameters and event parameters);

[0128] 2) Normalize historical data to the interval [0,1];

[0129] 3) Calculate the information entropy H of the six risk assessment features j ;

[0130]

[0131]

[0132] 4) Calculate the weights W of the six risk assessment features based on information entropy j

[0133]

[0134] S2-3: Calculate traffic safety score S

[0135] S=A×W 1 +B×W 2 +C×W 3 +D×W 4 +E×W 5 +F×W 6

[0136] Where: W 1 is the weight of the traffic speed and density characteristics before the accident, W 2 is the weight of the spatiotemporal characteristics of traffic flow, W 3 is the weight of the dynamic characteristics of traffic flow, W 4 is the weight of the road segment feature, W 5 is the weight of weather characteristics, W 6 is the weight of the accident possibility feature, and S is the traffic safety score of the road section.

[0137] S2-4: Evaluate the traffic safety level of the road section

[0138] 1) If no accident occurs, the traffic safety score S of the road section is classified into safe, general risk, relatively high risk and high risk.

[0139] When the traffic safety score is above 80 points, the traffic safety level is safe.

[0140] When the traffic safety score is between 60-80 points, the traffic safety level is general risk.

[0141] When the traffic safety score is between 40 and 60 points, the traffic safety level is a high risk.

[0142] When the traffic safety score is below 40 points, the traffic safety level is high risk.

[0143] 2) When an accident occurs, the traffic safety score S of the road section is classified into other risks and high risks.

[0144] When the traffic safety score is between 40-100 points, the traffic safety level is other risks.

[0145] When the traffic safety score is below 40 points, the traffic safety level is high risk.

[0146] Step S3: Dynamic Control

[0147] Dynamic control is carried out according to whether an accident occurs, including dynamic control before the accident and dynamic control before the accident.

[0148] S3-1: No accident has occurred, and dynamic control before the accident is carried out:

[0149] 1) When the traffic safety level of a road section is safe, no control measures will be taken.

[0150] 2) When the traffic safety level of a road section is of general risk, the control measure adopts VMS (Variable Message Signs) dynamic speed limit.

[0151] VMS dynamic speed limit includes speed limit control, speed difference control, induced speed limit control, and highway entrance and exit control. These four control measures need to be implemented simultaneously.

[0152] a. Speed ​​limit control

[0153] Control the speed limit value Vn of the VMS equipment (speed limit sign) in the speed limit area to ensure that the vehicle speed in the speed limit area is lower than the maximum speed limit of the highway and higher than the minimum speed limit of the highway.

[0154] The area between the current road section and the nth upstream VMS device is the speed limit area.

[0155] b. Speed ​​limit difference control

[0156] Control the speed limit difference of adjacent VMS devices to avoid frequent acceleration and deceleration of vehicles and ensure driving safety and stability. The speed limit difference is less than the maximum speed limit difference of 20km / h that the road can tolerate. The speed limit difference can be controlled outside the speed limit area.

[0157] c. Induced speed limit control:

[0158] Considering different situations of different traffic flows, the following control schemes are obtained after simulation and comparison with SUMO software (Table 1):

[0159] Control Plan 1: For sections with a traffic density of 5 vehicles / km / lane, a three-stage speed limit measure is implemented. Guidance information is issued at the 6th, 4th and 2nd VMS devices upstream of the current section, with speed limits of 110km / h, 100km / h and 90km / h respectively, to guide drivers.

[0160] Control Plan 2: For sections where the traffic density reaches 15 vehicles / km / lane, a single-section speed limit measure is implemented, and the fifth VMS device upstream of the current section issues traffic guidance information with a speed limit of 90km / h to guide drivers.

[0161] Control Plan 3: When the traffic density is 30 vehicles / km / lane, a two-stage speed limit measure is implemented. Traffic guidance information is issued at the 6th and 1st VMS devices upstream of the current road section, with speed limits of 90km / h and 70km / h respectively, to guide drivers.

[0162] Table 1

[0163]

[0164] Among them: σ is the traffic density, the unit is vehicle / km / lane; Vlimit is the speed limit scheme, which can represent the speed limit values ​​of single-stage speed limit, two-stage speed limit and three-stage speed limit, the unit is km / h; VMSn is the VMS device selection scheme, which means selecting the nth VMS device upstream of the current road section to publish the guidance information.

[0165] d. Highway entrance and exit control

[0166] When the overall traffic density reaches severe congestion (the average traffic speed is below 20km / h), the highway entrance of the main source of traffic upstream of the current section will be closed. There is no need to control the highway exit.

[0167] 3) When the traffic safety level of a road section is at a high risk, the control measures adopt variable speed limits based on vehicle type and lane based on the standard deviation of vehicle speed (existing control measures).

[0168] 4) When the traffic safety level of a road section is high risk, the control measures adopt variable speed limits and ramp controls based on vehicle type and lane based on speed standard deviation (existing control measures).

[0169] S3-2: When an accident occurs, dynamic control is carried out after the accident:

[0170] When the traffic safety level of a road section is high risk or other risks, the control measures include VMS (Variable Message Signs) dynamic speed limit.

[0171] VMS dynamic speed limit includes speed limit control, speed difference control, induced speed limit control, and highway entrance and exit control. These four control measures need to be implemented simultaneously.

[0172] a) Speed ​​limit control

[0173] Control the speed limit value Vn of the VMS equipment (speed limit sign) in the speed limit area to ensure that the vehicle speed in the speed limit area is lower than the maximum speed limit of the highway and higher than the minimum speed limit of the highway.

[0174] The area between the current road section and the nth upstream VMS device is the speed limit area.

[0175] b) Speed ​​limit difference control

[0176] Control the speed limit difference of adjacent VMS devices to avoid frequent acceleration and deceleration of vehicles and ensure driving safety and stability. The speed limit difference is less than the maximum speed limit difference of 20km / h that the road can tolerate. The speed limit difference can be controlled outside the speed limit area.

[0177] c) Induced speed limit control

[0178] Construct an induced speed limit control scheme suitable for various accident scenarios and traffic conditions.

[0179] Considering the accident situation of closing a single lane, different lane closure times and traffic density, the lane closure time is 60 minutes when the risk is high, and the lane closure time is 30 minutes when the risk is other. After simulation and comparison by SUMO software, the following control schemes are obtained (Table 2):

[0180] Control Plan 1: Lane closure time is 30 minutes. For road sections with a traffic density of 5 vehicles / km / lane, three-stage speed limit measures are implemented. Guidance information is issued at the 6th, 4th and 2nd VMS devices upstream of the current road section. The speed limits are 110km / h, 90km / h and 70km / h respectively to guide drivers.

[0181] Control Plan 2: For sections where the lane closure time is 30 minutes and the traffic density is 15 vehicles / km / lane, a single-section speed limit measure is implemented and the fifth VMS device upstream of the current section issues traffic guidance information with a speed limit of 90km / h to guide drivers.

[0182] Control Plan 3: When the lane closure time is 30 minutes and the traffic density is 30 vehicles / km / lane, a two-stage speed limit measure is implemented. Traffic guidance information is issued at the 6th and 1st VMS devices upstream of the current section, with speed limits of 70km / h and 60km / h respectively, to guide drivers.

[0183] Control Plan 4: Lane closure time is 60 minutes. For sections with a traffic density of 5 vehicles / km / lane, three-section speed limit measures will be implemented. Guidance information will be issued at the 5th, 4th and 1st VMS (variable message sign) facilities upstream of the current section. The speed limits are 110km / h, 100km / h and 90km / h respectively to guide drivers.

[0184] Control Plan 5: For sections where the lane closure time is 60 minutes and the traffic density is 15 vehicles / km / lane, a single-section speed limit measure is implemented and the sixth VMS device upstream of the current section issues traffic guidance information with a speed limit of 90km / h to guide drivers.

[0185] Control Plan 6: When the lane closure time is 60 minutes and the traffic density is 30 vehicles / km / lane, a two-stage speed limit measure is implemented. Traffic guidance information is issued at the 6th and 5th VMS devices upstream of the current section, with speed limits of 70km / h and 60km / h respectively, to guide drivers.

[0186] Table 2

[0187]

[0188] Among them: Tclose is the lane closure time; σ is the traffic density, the unit is vehicle / km / lane; Vlimit is the speed limit scheme, which can represent the speed limit values ​​of single-stage speed limit, two-stage speed limit and three-stage speed limit, the unit is km / h; VMSn is the VMS device selection scheme, which means selecting the nth VMS device upstream of the current road section to publish the guidance information.

[0189] When two lanes are closed, the state requires that one lane must be restored within 15 minutes, so the situation of two lane closures is not considered. When three lanes are closed, traffic is completely interrupted, so the situation of three lane closures is not considered either.

[0190] d) Highway entrance and exit control

[0191] When the overall traffic density reaches severe congestion (the average traffic speed is below 20km / h), the highway entrance of the main source of traffic upstream of the current section will be closed. There is no need to control the highway exit.

[0192] Dynamic control aims to effectively manage traffic conditions under different traffic densities and lane closure times by adjusting speed limits and publishing information using VMS equipment, in order to improve road safety and traffic efficiency.

[0193] Step S4: Adjust control measures

[0194] Every 15 minutes, return to step S1, re-evaluate the accident risk and take corresponding dynamic control measures to keep the road safe and unobstructed.

[0195] The present invention also provides a highway accident risk assessment and dynamic control device, including a memory and a processor.

[0196] The memory is used to store computer programs.

[0197] The processor is used to implement the highway accident risk assessment and dynamic control method as described in S1 to S4 above when executing the computer program.

[0198] It should be noted that the above-mentioned memory may include random access memory (RAM) and non-volatile memory (NVM), such as at least one disk storage. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a neural network processor (NPU), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. Of course, the device should also have necessary components to realize program operation, such as power supply, communication bus, etc.

[0199] Example

[0200] Obtain data for the G56 Expressway (K39+100 to K42+040) from January 31 to September 30, 2024. The minimum speed limit of the expressway is 60km / h and the maximum speed limit is 110km / h. The road is divided into several sections and several VMS devices are set up.

[0201] The weights are calculated as follows: W 1 =0.2, W 2 =0.2, W 3 =0.15, W 4 =0.15, W 5 =0.1, W 6 =0.2.

[0202] A variety of traffic control measures are compared, and the results are shown in Table 3.

[0203] Table 3 Comparison of control measures

[0204]

[0205] like Figure 2 and Figure 3 As shown, after an in-depth analysis of the effects of the four traffic control measures, the following conclusions can be drawn.

[0206] Without any control measures, the average speed of traffic flow was 21.37 m / s, the average waiting time was 11,079 seconds, and the average number of waiting vehicles was 1,695. This shows that without any control measures, traffic congestion was serious, vehicles were slow, and waiting time was long.

[0207] After the implementation of VMS dynamic speed limit, the average speed increased to 23.16 m / s, the average waiting time was significantly reduced to 4055 seconds, and the average number of waiting vehicles dropped to 1029. This shows that VMS dynamic speed limit effectively alleviated traffic congestion and improved the efficiency of traffic flow.

[0208] DTC further increased the average speed to 23.33 m / s, but the average waiting time and number of waiting vehicles did not improve as significantly as the VMS dynamic speed limit, which were 11,040 seconds and 1,302 vehicles respectively. This may mean that DTC has a positive effect on controlling vehicle flow, but has limited effect on reducing waiting time.

[0209] The combined strategy CCZ (combination of VMS dynamic speed limit and entrance and exit control) adopted by the present invention performed best among all measures, with an average speed of 23.71 m / s, an average waiting time further reduced to 4767 seconds, and an average number of waiting vehicles reduced to 803. This shows that the combined strategy can most effectively improve the efficiency of traffic flow and reduce congestion.

[0210] In summary, the implementation of control measures has a significant effect on improving the efficiency of traffic flow and reducing congestion. The average vehicle speed has increased by more than 10%, and the traffic efficiency has increased by more than 40% in VMS dynamic speed limit and combination strategy. In particular, the combination strategy has performed well in increasing the average speed, reducing the waiting time and the number of waiting vehicles. Therefore, it is recommended to consider the implementation of the combination strategy in traffic management to achieve the best traffic flow efficiency and reduce congestion.

[0211] The preferred embodiments of the present invention are shown in the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described in this specification. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive.

Claims

1. A highway accident risk assessment and dynamic control method, comprising the following steps: Step S1: Get data Obtain real-time monitoring data and event data, and extract risk assessment features; Step S2: Accident risk assessment Input the risk assessment characteristics into the traffic safety grade classification model to classify the traffic safety grade and conduct accident risk assessment; Step S3: Dynamic Control Carry out dynamic control before and after an accident based on whether an accident occurs; Step S4: Adjust control measures Every 15 minutes, return to step S1, re-evaluate the accident risk and take corresponding dynamic control measures.

2. A highway accident risk assessment and dynamic control method according to claim 1, characterized in that: The step S1 comprises: S1-1: Obtain real-time monitoring data and event data; S1-2: Extract risk assessment features from real-time monitoring data; S1-3: Extract risk assessment features from event data; S1-4: Determine whether an accident has occurred.

3. A highway accident risk assessment and dynamic control method according to claim 1, characterized in that: The step S2 comprises: S2-1: Convert risk assessment characteristics into scores; S2-2: Calculate the weights of risk assessment features; S2-3: Calculate the traffic safety score S; S2-4: Evaluate the traffic safety level of the road section.

4. A highway accident risk assessment and dynamic control method according to claim 3, characterized in that: The step S2-4 includes: if no accident occurs, the traffic safety score S of the road section is classified into safe, general risk, relatively high risk, and high risk; if an accident occurs, the traffic safety score S of the road section is classified into remaining risk and high risk.

5. A highway accident risk assessment and dynamic control method according to claim 1, characterized in that: The step S3 comprises: S3-1: No accident has occurred, and dynamic control before the accident is carried out; S3-2: When an accident occurs, dynamic management and control will be carried out after the accident.

6. A highway accident risk assessment and dynamic control method according to claim 5, characterized in that: The dynamic control before the accident includes: 1) When the traffic safety level of a road section is safe, no control measures will be taken; 2) When the traffic safety level of a road section is a general risk, the control measure adopts VMS dynamic speed limit; 3) When the traffic safety level of a road section is high risk, the control measures adopt variable speed limits based on vehicle speed standard deviation for different vehicle types and lanes; 4) When the traffic safety level of a road section is high risk, the control measures adopt variable speed limits and ramp controls based on vehicle type and lane based on speed standard deviation.

7. A highway accident risk assessment and dynamic control method according to claim 6, characterized in that: The VMS dynamic speed limit includes: a. Speed ​​limit control Control the speed limit value Vn of the VMS equipment in the speed limit area to ensure that the vehicle speed in the speed limit area is lower than the maximum speed limit of the highway and higher than the minimum speed limit of the highway; b. Speed ​​limit difference control Control the speed limit difference of adjacent VMS devices; c. Induced speed limit control: Control Plan 1: For sections with a traffic density of 5 vehicles / km / lane, implement three-stage speed limit measures, and issue guidance information at the 6th, 4th and 2nd VMS devices upstream of the current section, with speed limits of 110km / h, 100km / h and 90km / h respectively; Control Plan 2: For sections where the traffic density reaches 15 vehicles / km / lane, a single-section speed limit measure is implemented, and the fifth VMS device upstream of the current section issues traffic guidance information with a speed limit of 110km / h; Control plan 3: When the traffic density is 30 vehicles / km / lane, implement two-stage speed limit measures, and issue traffic guidance information at the 6th and 1st VMS devices upstream of the current road section, with speed limits of 90km / h and 70km / h respectively; d. Highway entrance and exit control When the overall traffic density reaches severe congestion, close the highway entrance where the main traffic source is located upstream of the current road section; 3) When the traffic safety level of a road section is high risk, the control measures adopt variable speed limits based on vehicle speed standard deviation for different vehicle types and lanes; 4) When the traffic safety level of a road section is high risk, the control measures adopt variable speed limits and ramp controls based on vehicle type and lane based on speed standard deviation.

8. A highway accident risk assessment and dynamic control method according to claim 5, characterized in that: The dynamic control after the accident includes: when the traffic safety level of the road section is high risk or other risks, the control measures all adopt VMS dynamic speed limit.

9. A highway accident risk assessment and dynamic control method according to claim 8, characterized in that: The VMS dynamic speed limit includes: a) Speed ​​limit control Control the speed limit value Vn of the VMS equipment in the speed limit area to ensure that the vehicle speed in the speed limit area is lower than the maximum speed limit of the highway and higher than the minimum speed limit of the highway; b) Speed ​​limit difference control Control the speed limit difference of adjacent VMS devices; c) Induced speed limit control Control Plan 1: For a road section with a lane closure time of 30 minutes and a traffic density of 5 vehicles / km / lane, a three-stage speed limit measure is implemented, and guidance information is issued at the 6th, 4th and 2nd VMS devices upstream of the current road section, with speed limits of 110km / h, 90km / h and 70km / h respectively; Control Plan 2: For a road section with a lane closure time of 30 minutes and a traffic density of 110 vehicles / km / lane, a single-section speed limit measure is implemented, and the fifth VMS device upstream of the current road section issues traffic guidance information with a speed limit of 90km / h; Control plan 3: When the lane closure time is 30 minutes and the traffic density is 70 vehicles / km / lane, a two-stage speed limit measure is implemented, and traffic guidance information is issued at the 6th and 1st VMS devices upstream of the current road section, with speed limits of 70km / h and 60km / h respectively; Control Plan 4: For a road section with a lane closure time of 60 minutes and a traffic density of 5 vehicles / km / lane, a three-stage speed limit measure is implemented, and guidance information is issued at the 5th, 4th and 1st VMS devices upstream of the current road section, with speed limits of 110km / h, 100km / h and 90km / h respectively; Control Plan 5: For sections where the lane closure time is 60 minutes and the traffic density is 110 vehicles / km / lane, a single-section speed limit measure is implemented, and the sixth VMS device upstream of the current section issues traffic guidance information with a speed limit of 90km / h; Control Plan 6: When the lane closure time is 60 minutes and the traffic density is 70 vehicles / km / lane, a two-stage speed limit measure is implemented, and traffic guidance information is issued at the 6th and 5th VMS devices upstream of the current road section, with speed limits of 70km / h and 60km / h respectively; d) Highway entrance and exit control When the overall traffic density reaches severe congestion, the highway entrance that is the main source of traffic upstream of the current section will be closed.

10. A highway accident risk assessment and dynamic control device, comprising a memory and a processor; characterized in that: The memory is used to store computer programs; the processor is used to implement the highway accident risk assessment and dynamic control method as described in any one of claims 1 to 9 when executing the computer program.

Images