Curve road section risk prevention and control dynamic evaluation system and method

Abstract

The invention discloses a curve road section risk prevention and control dynamic evaluation system and method, and belongs to the field of intelligent traffic. The system comprises a SCANeR studio driving simulator, Microsoft Visual C + + software, a UDP (User Datagram Protocol) data transmission protocol and a data processing and displaying module. The system collects driver behavior information under multiple groups of prevention and control schemes in a curve road section through a driving simulator, and uploads data to a risk prevention and control effect dynamic evaluation system by using a UDP communication protocol. The system detects the behavior performance of the driver in real time, and carries out risk index extraction processing on the uploaded data so as to evaluate the risk level in the curve road section. And when the driver behavior information is judged to be a risk traffic behavior, the system generates a risk signal and displays the risk signal on an evaluation system interface in real time so as to warn a traffic control department that the road section has a traffic risk. The system can master the behavior safety of a driver driving on a curve road section in real time and prompt risk behaviors on the road section, so that traffic accidents on the curve road section are reduced.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation, and in particular to a dynamic evaluation system and method for risk prevention and control of curved road sections. Background Art

[0002] With the in-depth development of traffic accident research, risky behavior has become the entry point for accident prevention. Existing studies have proposed a variety of road-side and vehicle-side intelligent equipment or facilities for risky behavior prevention and control. However, it often takes a period of time after the implementation of the prevention and control plan to evaluate the effectiveness of the prevention and control plan. There is a large time interval between the feedback on the plan effect and the adjustment of the control measures, which leads to poor timeliness in risk prevention and control, and the control departments have fewer types of real-time control measures for risky behaviors. Therefore, the problem of lack of a dynamic feedback system for prevention and control effects needs to be solved urgently.

[0003] Due to the high costs and significant safety risks associated with real-world vehicle testing, driving simulation technology, as an effective means of studying human factors in traffic, provides a practical approach for testing driving behavior in prevention and control plans. Furthermore, with the development of data transmission and visualization technologies, the lightweight and connectionless UDP data transmission protocol offers the potential for real-time data transmission. For driving behavior data processing and visualization, C++ provides tools for converting data information into graphical images. Summary of the Invention

[0004] The purpose of this application is to provide a dynamic evaluation system for the risk prevention and control effects of curved road sections, which can display driving behaviors in curved road sections in real time, monitor driving status and risk behaviors, assist traffic management departments in obtaining real-time knowledge of drivers' risk behaviors, and visualize risk behaviors, provide effectiveness evaluation of prevention and control plans, and provide dynamic display for the optimization of prevention and control plans.

[0005] To achieve the above objectives, this application provides a dynamic evaluation system for risk prevention and control of curved road sections, including:

[0006] The SCANeR studio driving simulator collects and stores driving behavior data within a target curved road section and, based on the driving behavior data, identifies risky behaviors and their occurrence frequency within the target curved road section. Risk detection includes speeding monitoring and risky behavior monitoring; the risky behaviors monitored include sudden acceleration, sudden deceleration, and abrupt lane changes.

[0007] The UDP data transmission protocol is used to transmit driving behavior data between the source and the destination. It connects the SCANeRstudio driving simulator and Microsoft Visual C++ software, and is responsible for fast data transmission to ensure that the system front end dynamically displays driving operation indicators and risk indicators.

[0008] The data processing and display module uses Microsoft Visual C++ software to build a dynamic risk assessment system, dynamically display indicator change trends, and process data transmitted by the simulator for real-time visualization of driver behavior data and determination of speeding and risky behavior. It also displays the changing trends of each driver's indicators in each scenario in real time, and can also use the filtering function to achieve comparative analysis of driving behavior in different scenarios. Using appropriate chart libraries (such as Matplotlib or Plotly) in Microsoft Visual C++ software, it can complete the dynamic display of source data and the display of processed data results.

[0009] As a further improvement of the present invention, the SCANeR studio driving simulation includes a variety of typical curved traffic scenarios, traffic participants and typical traffic events; wherein, the types of typical traffic scenarios include curved road sections of different levels, the traffic participants include passenger cars, buses, emergency special vehicles, motorcycles, non-motor vehicles, pedestrians, animals and moving objects, and the typical traffic events include vehicle following, vehicle lane changing, vehicle overtaking, traffic accidents, and spillage of objects by the preceding vehicle.

[0010] As a further improvement of the present invention, the system adopts the UDP data transmission protocol to achieve rapid transmission of driving behavior data between the source and destination ends, connecting the SCANeR studio driving simulator with Microsoft Visual C++ software to ensure efficient and real-time data transmission.

[0011] As a further improvement of the present invention, this system is based on Microsoft Visual C++ software, and the layout of the visual interface of the system terminal is optimized. By referring to the standard, a reasonable warning trigger threshold is set, such as the rapid acceleration trigger threshold is 0.6m / s 2 , the rapid deceleration trigger threshold is -3m / s 2 , the front vehicle collision trigger threshold is 1s, thereby realizing the dynamic real-time display of driving operation indicators and risk indicators on the front end of the system, providing users with efficient and accurate driving risk assessment and warning information feedback.

[0012] As a further improvement of the present invention, in the SCANeR studio driving simulator, the specific steps taking driving simulation data as an example include:

[0013] Step 1: Data acquisition: Use script programming to set markers at key points on the experimental road section of the driving simulation scenario to ensure that the driving behavior data capture section covers the start and end points of the curve;

[0014] Step 2: Data transmission analysis: The program continuously listens for driving behavior data sent by a data source (such as a driving simulator) by binding to a specified IP address and port. The received data is in string format, and each driving operation indicator, such as speed, acceleration, steering wheel angle, and sudden acceleration, is extracted by comma separation.

[0015] Step 3: Data storage and processing: After the received driving metric data is parsed, it is stored in memory using a double-ended queue (deque). Each metric (such as speed, acceleration, and steering wheel angle) corresponds to a queue. The deque has a maximum length to ensure that only the latest real-time data is stored, and old data is automatically removed. The system uses a continuous judgment algorithm to calculate abnormal driving behavior, such as the number of sudden lane changes.

[0016] Step 4: Data Display and Dynamic Updates. Data display is achieved through the Tkinter graphical interface and dynamic Matplotlib charting. The system uses coordinate mapping and dynamic scaling to plot received real-time data on a Tkinter canvas as a line graph, allowing the chart to display driving metrics in real time as the data updates. Furthermore, risk indicators such as location, speeding time, and rapid acceleration are dynamically updated on the canvas via text.

[0017] Step 5: Risk analysis and evaluation. This process uses threshold judgment and continuous data statistical methods to calculate and clearly display the risk on the front-end interface. This intuitively demonstrates the risk manifestations during driving and provides data support for driving behavior assessment and optimization.

[0018] The entire interface design adopts a modular layout, including a driving indicator chart area, a risk indicator display area and an interactive button area. Users can view different data items in real time through interactive functions.

[0019] As a further improvement of the present invention, in the data processing and display module, taking the "speed" indicator as an example, the time series data of multiple sampling points are converted into the spatial series data of a single point, specifically including:

[0020] Step 1: Locate the required time series data index: travel time, travel distance, speed;

[0021] Step 2: Match “travel distance” and “speed” within the preset spatial sampling interval;

[0022] Step 3: Calculate the average speed value within the preset spatial sampling interval;

[0023] Step 4: Similarly, calculate all point-by-point spatial velocity data within the travel distance.

[0024] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0025] The present application provides a dynamic evaluation system for the risk prevention and control effect of curved road sections. The driving behavior data under multiple groups of scenarios in the curved road section are collected through a driving simulator to monitor the driving status and risk behavior. When the driving behavior is determined to be a risky behavior, the system visualization interface will perform risk behavior timing and cumulative number statistics to assist the traffic management department in timely real-time regulation. The front-end driving simulator outputs the driver's behavior through operation indicators and risk indicators, and transmits the driving simulation behavior data to the data processing and display module in real time based on the UDP transmission protocol. The back-end uses Microsoft Visual C++ software to write data dynamic display and data statistical analysis programs to realize the display of dynamic evaluation of risk prevention and control effects. This application helps the traffic management department to flexibly prevent and control, issue warnings, and assist drivers to adjust risk behaviors inside the curve in a timely manner by displaying and analyzing driving behaviors in real time in curved road sections. It can avoid the occurrence of dangerous traffic incidents and thus improve the safety of road driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 The framework diagram of the dynamic evaluation system for risk prevention and control of curved road sections provided for this application;

[0027] Figure 2 Software structure diagram of the dynamic evaluation system for risk prevention and control of curved road sections provided for this application;

[0028] Figure 3 The visualization interface (main interface) of the dynamic evaluation system for risk prevention and control of curved road sections provided for this application;

[0029] Figure 4 The visualization interface (data analysis interface) of the dynamic evaluation system for risk prevention and control of curved road sections provided for this application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0031] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0032] The present application provides a dynamic evaluation system for risk prevention and control of curved road sections. The present invention is further described in detail below with reference to the accompanying drawings:

[0033] like Figure 1 As shown, the system architecture of the present invention includes: a driving simulator, a UDP transmission protocol, and a data processing and display module. The present invention provides a driving behavior testing system based on driving simulation technology, including: a driving simulation system, a data collaborative processing center, and a data extraction and determination module; wherein, the driving simulation system is used to test the impact of different prevention and control schemes on driving behavior characteristics; the data extraction and determination module is used to extract fine-grained behavior data and determine risky behaviors; the data collaborative processing center and the driving simulation cabin build a wireless local area network, and the SCANeR software and the driving simulator interact with each other through the UDP protocol. Data transmission is based on the UDP protocol, and the system's real-time results are visualized through script programming;

[0034] like Figure 2 As shown, the system of the present invention consists of a data layer, a communication layer, a front-end UI and a design layer. The data layer contains basic data such as road attributes, meteorological data, traffic events, traffic status, HMI navigation, and driving behavior data obtained through driving simulation tests. The data is input into the driving simulator data management center through the API port and output through the UDP protocol. The front-end UI calls the Tkinter, Socket, Matplotlib, Numpy, Pandas, and Queue modules in Python to respectively realize functions such as window creation, network communication, chart drawing, data call, and data processing, and perform applications such as traffic risk visualization, real-time monitoring of driving behavior, and traffic safety behavior evaluation.

[0035] like Figure 3 As shown, the main interface of the system of the present invention includes a title, a menu bar, and a data display area.

[0036] like Figure 4 As shown, the data analysis interface of the system of the present invention includes a data file selection drop-down menu and an evaluation method selection drop-down menu.

[0037] In one embodiment, the dynamic evaluation method of the curved road section risk prevention and control dynamic evaluation system specifically includes:

[0038] Step 1: Input information before driving. On the main interface of the system, complete the driver's personal information input, including the driver's gender, age, and driving experience; complete the experimental scenario selection, that is, the risk prevention and control plan selection, and turn on the first-person driving monitoring;

[0039] Step 2: Start the virtual driving scene on the road. After opening the "Record" module in the SCANeR studio driving simulator, start the virtual scene corresponding to the prevention and control plan. Vehicle information (vehicle x, y, z axis position information, vehicle real-time speed) will be automatically displayed, and the vehicle driving status and risk status will be monitored in real time. At the same time, the entire driving data will be recorded to form a source file;

[0040] Step 3: Export driving behavior data files. In the Analysis module of the SCANeR studio driving simulator, select the data source files corresponding to different prevention and control plans and use the preset data template to export the behavior data files. The files contain driving behavior indicators such as time, speed, acceleration, x-axis coordinates, y-axis coordinates, steering wheel angle, steering wheel speed, throttle efficiency, lane number, lateral deviation, turn signal usage, and mileage.

[0041] Step 4: Select data files and evaluation methods. In the system data analysis interface, first click "Select data file" and select the behavioral data file to be compared from the drop-down menu; then click "Select evaluation method";

[0042] Step 5: Spatial Data Significance Analysis. First, the data file for the scenarios to be compared is read. The distribution of indicator values ​​(such as speed and acceleration) along the mileage is plotted as a curve to observe the spatial trend of change. Second, a one-way analysis of variance (ANOVA) is used to test whether the differences in the indicators at multiple mileage points are significant. To avoid data noise, a smoothing algorithm is used to process the spatially distributed data. Finally, the user selects the indicator on the system interface, and the results of the significance analysis (such as the changes in the indicators at different spatial points and the significant differences) are displayed on a curve chart.

[0043] Step 6: Data mean significance analysis. First, read the data files of the scenarios to be compared and average the indicators under different scenarios. Second, perform a one-way variance analysis on the indicators under different scenarios to calculate the significant differences between multiple scenarios. Finally, plot the mean of each scenario as a bar chart and annotate the statistical test results (F, P-value) in the chart. The user selects an indicator on the system interface, and the difference performance of the indicator between the selected scenarios will be displayed.

[0044] Step 7: Comprehensive evaluation of the schemes. First, based on the data file, the evaluation system collects the mean values ​​of the behavioral indicators of each scheme to form a decision matrix m×n (m schemes, n indicators). The decision matrix is ​​standardized so that each indicator is within the same dimensional range. Then, the standardized matrix is ​​converted into a proportional matrix and the information entropy of each indicator is calculated to determine the weight of each indicator. Secondly, the standardized matrix is ​​multiplied by the weight to obtain a weighted standardized matrix. The ideal solution and the negative ideal solution are constructed. The ideal solution is the maximum value of the indicator, and the negative ideal solution is the minimum value of the indicator. The Euclidean distance is used to calculate the distance between each scheme and the ideal solution and the negative ideal solution to obtain the degree of proximity of each scheme. Finally, the schemes are ranked according to the calculated degree of proximity. The greater the degree of proximity, the better the scheme. The system will display the degree of proximity of different schemes in the form of a bar chart.

[0045] In one embodiment, the dynamic evaluation method of the curved road section risk prevention and control dynamic evaluation system specifically includes:

[0046] Step 1: Input information before driving. On the main interface of the system, complete the driver's personal information input, including the driver's gender, age, and driving experience; complete the experimental scenario selection, that is, the risk prevention and control plan selection, and turn on the first-person driving monitoring;

[0047] Step 2: Start the virtual driving scene on the road. After opening the "Record" module in the SCANeR studio driving simulator, start the virtual scene corresponding to the prevention and control plan. Vehicle information (vehicle x, y, z axis position information, vehicle real-time speed) will be automatically displayed, and the vehicle driving status and risk status will be monitored in real time. At the same time, the entire driving data will be recorded to form a source file;

[0048] Step 3: Export driving behavior data files. In the Analysis module of the SCANeR studio driving simulator, select the data source files corresponding to different prevention and control plans, and export the behavior data files using the preset data template.

[0049] Step 4: Select data files and evaluation methods. In the system data analysis interface, first click "Select data file" and select the behavioral data file to be compared from the drop-down menu; then click "Select evaluation method";

[0050] Step 5: Spatial Data Significance Analysis. First, the data file for the scenarios to be compared is read. The distribution of indicator values ​​(such as speed and acceleration) along the mileage is plotted as a curve to observe the spatial trend of change. Second, a one-way analysis of variance (ANOVA) is used to test whether the differences in the indicators at multiple mileage points are significant. To avoid data noise, a smoothing algorithm is used to process the spatially distributed data. Finally, the user selects the indicator on the system interface, and the results of the significance analysis (such as the changes in the indicators at different spatial points and the significant differences) are displayed on a curve chart.

[0051] Step 6: Data mean significance analysis. First, read the data files of the scenarios to be compared and average the indicators under different scenarios. Second, perform a one-way variance analysis on the indicators under different scenarios to calculate the significant differences between multiple scenarios. Finally, plot the mean of each scenario as a bar chart and annotate the statistical test results (F, P-value) in the chart. The user selects an indicator on the system interface, and the difference performance of the indicator between the selected scenarios will be displayed.

[0052] Step 7: Comprehensive evaluation of the scheme. First, the system goal layer is to select the most comprehensive prevention and control scheme. The criterion layer includes speed stability, acceleration comfort, lateral offset stability, brake stability, throttle stability, and steering wheel stability. The scheme layer is the different schemes selected by the user. The importance of each indicator in the criterion layer is compared to construct a judgment matrix. Secondly, the consistency index (CI) and consistency ratio (CR) are calculated by the matrix dimension and the maximum eigenvalue. A consistency test is performed based on the CR (if CR ≥ 0.1, the judgment matrix needs to be adjusted). The matrix that passes the consistency test is normalized, and the average value of the primary color of each row corresponding to each criterion in the matrix is ​​calculated to obtain the weight of the indicator. Finally, the comprehensive score of each scheme is obtained by summing the product of the criterion weight and the score of the scheme under each criterion. The higher the comprehensive score, the better the scheme. The system presents the comprehensive scores of different schemes in the form of a bar chart.

[0053] In one embodiment, the dynamic evaluation method of the curved road section risk prevention and control dynamic evaluation system specifically includes:

[0054] Step 1: Input information before driving. On the main interface of the system, complete the driver's personal information input, including the driver's gender, age, and driving experience; complete the experimental scenario selection, that is, the risk prevention and control plan selection, and turn on the first-person driving monitoring;

[0055] Step 2: Start the virtual driving scene on the road. After opening the "Record" module in the SCANeR studio driving simulator, start the virtual scene corresponding to the prevention and control plan. Vehicle information (vehicle x, y, z axis position information, vehicle real-time speed) will be automatically displayed, and the vehicle driving status and risk status will be monitored in real time. At the same time, the entire driving data will be recorded to form a source file;

[0056] Step 3: Export driving behavior data files. In the Analysis module of the SCANeR studio driving simulator, select the data source files corresponding to different prevention and control plans, and export the behavior data files using the preset data template.

[0057] Step 4: Select data files and evaluation methods. In the system data analysis interface, first click "Select data file" and select the behavioral data file to be compared from the drop-down menu; then click "Select evaluation method";

[0058] Step 5: Spatial Data Significance Analysis. First, the data file for the scenarios to be compared is read. The distribution of indicator values ​​(such as speed and acceleration) along the mileage is plotted as a curve to observe the spatial trend of change. Second, a one-way analysis of variance (ANOVA) is used to test whether the differences in the indicators at multiple mileage points are significant. To avoid data noise, a smoothing algorithm is used to process the spatially distributed data. Finally, the user selects the indicator on the system interface, and the results of the significance analysis (such as the changes in the indicators at different spatial points and the significant differences) are displayed on a curve chart.

[0059] Step 6: Data mean significance analysis. First, read the data files of the scenarios to be compared and average the indicators under different scenarios. Second, perform a one-way variance analysis on the indicators under different scenarios to calculate the significant differences between multiple scenarios. Finally, plot the mean of each scenario as a bar chart and annotate the statistical test results (F, P-value) in the chart. The user selects an indicator on the system interface, and the difference performance of the indicator between the selected scenarios will be displayed.

[0060] Step 7: Comprehensive evaluation of the schemes. First, based on the data file, the evaluation system collects the mean values ​​of the behavioral indicators of each scheme to form a decision matrix m×n (m schemes, n indicators). The decision matrix is ​​standardized so that each indicator is within the same dimensional range. Second, the positive indicators are sorted from large to small, with the rank value of the largest value being 1, the second largest value being 2, and so on. The negative indicators are sorted from small to large, with the rank value of the smallest value being 2, the second smallest value being 2, and so on. The ranks of all columns are combined into a rank value matrix. Finally, the rank sum of all indicators of each scheme is calculated. The smaller the rank sum value, the better the overall performance of the scheme. After standardizing the rank sum value, the RSR value is obtained. The closer the RSR value is to 1, the better the overall performance of the scheme. The closer the RSR value is to 0, the worse the overall performance of the scheme. The system presents the RSR values ​​of different schemes in the form of a bar chart.

[0061] In one embodiment, the dynamic evaluation method of the curved road section risk prevention and control dynamic evaluation system specifically includes:

[0062] Step 1: Input information before driving. On the main interface of the system, complete the driver's personal information input, including the driver's gender, age, and driving experience; complete the experimental scenario selection, that is, the risk prevention and control plan selection, and turn on the first-person driving monitoring;

[0063] Step 2: Start the virtual driving scene on the road. After opening the "Record" module in the SCANeR studio driving simulator, start the virtual scene corresponding to the prevention and control plan. Vehicle information (vehicle x, y, z axis position information, vehicle real-time speed) will be automatically displayed, and the vehicle driving status and risk status will be monitored in real time. At the same time, the entire driving data will be recorded to form a source file;

[0064] Step 3: Export driving behavior data files. In the Analysis module of the SCANeR studio driving simulator, select the data source files corresponding to different prevention and control plans, and export the behavior data files using the preset data template.

[0065] Step 4: Select data files and evaluation methods. In the system data analysis interface, first click "Select data file" and select the behavioral data file to be compared from the drop-down menu; then click "Select evaluation method";

[0066] Step 5: Spatial Data Significance Analysis. First, the data file for the scenarios to be compared is read. The distribution of indicator values ​​(such as speed and acceleration) along the mileage is plotted as a curve to observe the spatial trend of change. Second, a one-way analysis of variance (ANOVA) is used to test whether the differences in the indicators at multiple mileage points are significant. To avoid data noise, a smoothing algorithm is used to process the spatially distributed data. Finally, the user selects the indicator on the system interface, and the results of the significance analysis (such as the changes in the indicators at different spatial points and the significant differences) are displayed on a curve chart.

[0067] Step 6: Data mean significance analysis. First, read the data files of the scenarios to be compared and average the indicators under different scenarios. Second, perform a one-way variance analysis on the indicators under different scenarios to calculate the significant differences between multiple scenarios. Finally, plot the mean of each scenario as a bar chart and annotate the statistical test results (F, P-value) in the chart. The user selects an indicator on the system interface, and the difference performance of the indicator between the selected scenarios will be displayed.

[0068] Step 7: Comprehensive Evaluation of Schemes. First, the system selects speed, acceleration, lateral offset, throttle efficiency, brake efficiency, and steering wheel angle as the indicator set. Based on the mean and standard deviation of the indicator data, the system classifies the evaluation into five levels (poor, relatively poor, moderate, relatively good, and excellent), assigning a weight of 16.7% to each indicator. Second, the system calculates the membership degree of each indicator at each evaluation level using membership functions, forming a fuzzy evaluation matrix R: m×n (m represents the indicator, which is 6 in this system, and n represents the evaluation level, which is 5 in this system). Finally, the fuzzy evaluation matrix R is multiplied by the weight vector W to obtain the comprehensive evaluation result B, which is the final evaluation result for each scheme. The evaluation level corresponding to the maximum value of the element in B is the evaluation level of that scheme. Similarly, the other schemes will also obtain comprehensive evaluation results B through the same calculation. The level with the highest membership degree represents the final evaluation level of the scheme. The system will present the five evaluation levels of different schemes in the form of a bar chart. The higher the level, the better the overall performance of the scheme.

Claims

1. A dynamic evaluation system for risk prevention and control of curved road sections, characterized in that: The dynamic evaluation system for the risk prevention and control effect of curved road sections includes: SCANeR studio driving simulator, UDP data transmission protocol and data processing and conversion module; wherein: The SCANeR studio driving simulator is used to collect and store driving behavior data in the target curved road section, and determine the risk behavior and its occurrence frequency in the target curved road section according to the driving behavior data; risk detection includes speeding monitoring and risk behavior monitoring; the risk behavior monitoring includes rapid acceleration, rapid deceleration and rapid lane change behavior; The UDP data transmission protocol is used for driving behavior data transmission between the source and the destination, connecting the SCANeRstudio driving simulator and Microsoft Visual C++ software to ensure that the system front end dynamically displays driving operation indicators and risk indicators; The data processing and display module uses Microsoft Visual C++ software to build a dynamic risk evaluation system, dynamically display the indicator change trend, and process the data transmitted by the simulator for real-time visualization of driver behavior data and determination of speeding behavior and risky behavior; it displays the change trend of each indicator of each driver in each scene in real time, realizes comparative analysis of driving behavior in different scenes through the screening function, and uses the chart library to complete the dynamic display of source data and the display of processed data results.

2. The curve road section risk prevention and control dynamic evaluation system according to claim 1 is characterized in that: The traffic risk prevention and control effect evaluation interface of the curved road section risk prevention and control dynamic evaluation system specifically includes: a main interface, a data screening interface, and a data analysis interface; The main interface is used to realize the functions of data display, data selection and data analysis of this system, including system title, system menu bar and data display area; Data screening interface, used to select test data files, select evaluation methods, and provide a drop-down menu for selection; The data analysis interface is used for spatial significance analysis, mean significance analysis and comprehensive evaluation, and the results are displayed in a bar chart.

3. The curve road section risk prevention and control dynamic evaluation system according to claim 2 is characterized in that: The traffic risk prevention and control effect evaluation interface of the curve section risk prevention and control dynamic evaluation system also includes: Driver information module, used to display driver's personal information, including gender, age, and driving experience; The experimental scene information module is used to display the driving simulation road section information. The text information includes the road type, road speed limit and experimental variables of the prevention and control plan. The video information is the driver's virtual driving first-person perspective monitoring video. Vehicle information module, used to display vehicle location information and real-time speed; The driving behavior display module is used to display the lateral and longitudinal driving operation information of the accelerator pedal, brake pedal, steering wheel angle, running speed, acceleration and lateral deviation, with the mileage as the horizontal axis and the indicator value as the vertical axis, forming a curve chart to show the real-time changes of driving behavior; The risk detection module is used to monitor the driver's risky behavior, including the number of speeding times and speeding time, as well as the cumulative number of sudden acceleration, sudden deceleration, and sudden lane changes.

4. The curve road section risk prevention and control dynamic evaluation system according to claim 2 is characterized in that: The traffic risk prevention and control effect evaluation interface of the curve section risk prevention and control dynamic evaluation system also includes: Data file selection module, used for selecting data files of different schemes in analysis; Evaluation method selection module is used to select evaluation methods in data statistical analysis.

5. The curve road section risk prevention and control dynamic evaluation system according to claim 2 is characterized in that: The traffic risk prevention and control effect evaluation interface of the curve section risk prevention and control dynamic evaluation system also includes: Spatial significance analysis module, which is used to evaluate whether there are statistically significant differences between data of different spatial locations. It uses the one-way analysis of variance method to determine whether there are significant differences between two or more groups. Mean significance analysis module, used to compare whether the mean differences between different groups or different schemes are statistically significant, and use repeated measures analysis of variance to compare the mean differences under different conditions; The comprehensive evaluation module is used for comprehensive scoring of different schemes with multiple indicators and dimensions, and for overall evaluation and ranking of multiple alternative schemes, objects or systems through scientific methods.

6. The curve road section risk prevention and control dynamic evaluation system according to claim 3 is characterized in that: The dynamic evaluation indicators of the curved road section risk prevention and control dynamic evaluation system specifically include: The accelerator pedal is used to indicate the degree to which the driver operates the accelerator pedal. It is the product of the depth and duration of the driver's depression of the accelerator pedal. The brake pedal is used to indicate the vehicle kinetic energy that the braking system can consume per unit time, reflecting the effectiveness of the brakes and the driver's braking intention; Steering wheel angle, used to indicate the angle at which the driver turns the steering wheel, and is directly related to the change in the vehicle's driving direction; Running speed is used to indicate the driving speed of the driver on the road section, which is divided into two types: along the driving direction and perpendicular to the driving direction; Acceleration is used to indicate how fast the speed of a car changes. It has two types: along the direction of travel and perpendicular to the direction of travel. It often reflects the longitudinal stability of the vehicle. Lateral offset is used to describe the lateral displacement of a vehicle relative to a predetermined path or lane centerline during driving, and often reflects the lateral stability of the vehicle.

7. The curve road section risk prevention and control dynamic evaluation system according to claim 3 is characterized in that: The monitoring indicators of the dynamic evaluation system for risk prevention and control of curved road sections specifically include: Speeding behavior monitoring is used to reflect the number and duration of speeding behavior. The data source is Speed_X in the data uploaded by the driving simulator. Risk behavior monitoring is used to extract three types of risk behaviors in the horizontal and vertical directions: rapid acceleration, rapid deceleration, and rapid lane change. Rapid acceleration refers to acceleration in the direction of vehicle travel exceeding 3m / s 2 The behavior of rapid deceleration is that the acceleration along the direction of vehicle travel is less than -3.3m / s 2 The behavior of sudden lane change refers to the acceleration perpendicular to the direction of vehicle travel exceeding 1.8m / s 2 , and the absolute value of the lateral displacement exceeds 0.975m.

8. A dynamic evaluation system and method for risk prevention and control of curved road sections, characterized in that: Use SCANeR studio driving simulator to collect and store driving behavior data in the target curved road section, and determine the risk behaviors and their occurrence frequency in the target curved road section based on the driving behavior data; Risk detection includes speeding monitoring and risky behavior monitoring; The risk behavior monitoring includes sudden acceleration, sudden deceleration and sudden lane change; Use UDP data transmission protocol to transmit driving behavior data between source and destination, connect SCANeR studio driving simulator and Microsoft Visual C++ software, and ensure that the system front end dynamically displays driving operation indicators and risk indicators; Use Microsoft Visual C++ software to build a dynamic risk assessment system, dynamically display indicator change trends, and process the data transmitted by the simulator for real-time visualization of driver behavior data and determination of speeding and risky behavior; The changing trends of each indicator of each driver in each scenario are displayed in real time. The comparative analysis of driving behaviors in different scenarios is realized through the filtering function. The dynamic display of source data and the display of processed data results are completed using the chart library.

9. The method according to claim 8, characterized in that Dynamic evaluation indicators include: The accelerator pedal is used to indicate the degree to which the driver operates the accelerator pedal. It is the product of the depth and duration of the driver's depression of the accelerator pedal. The brake pedal is used to indicate the vehicle kinetic energy that the braking system can consume per unit time, reflecting the effectiveness of the brakes and the driver's braking intention; Steering wheel angle, used to indicate the angle at which the driver turns the steering wheel, and is directly related to the change in the vehicle's driving direction; Running speed is used to indicate the driving speed of the driver on the road section, which is divided into two types: along the driving direction and perpendicular to the driving direction; Acceleration is used to indicate how fast the speed of a car changes. It has two types: along the direction of travel and perpendicular to the direction of travel. It often reflects the longitudinal stability of the vehicle. Lateral offset is used to describe the lateral displacement of a vehicle relative to a predetermined path or lane centerline during driving, and often reflects the lateral stability of the vehicle.

Images