Method and system for identifying multiple accident points of expressway

Abstract

The invention relates to a method and a system for identifying multiple accident points of an expressway. The method comprises the following steps: acquiring road section characteristic data, vehicle brake performance parameters and historical accident data of a target expressway; carrying out analogue simulation on the basis of the road section characteristic data and the vehicle brake performance parameters, calculating a brake distance and acquiring brake efficiency indexes under different road section characteristics; classifying the historical accident data based on the brake efficiency indexes, extracting brake accidents and analyzing aggregation characteristics of the brake accidents under different road section characteristics to obtain risk road sections; extracting characteristic data of the risk road sections, grouping the risk road sections with similar road section characteristics and brake efficiency reduction characteristics by adopting a clustering analysis method, and determining road section categories with common risks; key influence factors for the braking distance and high-risk road sections in each category are obtained, namely accident-prone points of the target expressway are obtained. According to the invention, the dangerous road section with reduced brake efficiency caused by road characteristics can be identified.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic safety, and in particular to a method and system for identifying high-incidence points of highway accidents. Background Art

[0002] Highway safety is a crucial research area in the transportation sector, directly impacting the safety of life and property, as well as traffic efficiency. Accurately identifying accident-prone areas can effectively reduce accident rates and provide a scientific basis for road design and safety management. However, existing methods often rely on accident statistics, overlooking the underlying causes of accidents, particularly road characteristics related to vehicle braking performance. This makes it difficult to accurately identify potential danger points and provide specific guidance for targeted improvements. This limits the effectiveness of road safety management in complex environments.

[0003] At present, the core challenge facing the identification of high-incidence points of highway accidents lies in how to effectively combine the relationship between braking performance and road section characteristics. Braking distance is significantly affected by factors such as slope, curve radius and road friction coefficient, but the dynamic interaction of these factors has not yet been fully analyzed. For example, steep slopes may cause the braking distance to be significantly extended, and at sharp bends, braking efficiency is further limited due to the decrease in vehicle stability. This complexity makes it difficult for single-factor analysis to capture the true cause of the accident. In addition, existing research lacks in-depth exploration of the spatial distribution patterns of brake-related accidents, and is unable to reveal the clustering characteristics of dangerous sections through data analysis. This not only limits the accurate identification of high-risk sections, but also makes the optimal layout of safety facilities lack targeted basis. Therefore, the present invention proposes a method and system for identifying high-incidence points of highway accidents. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for identifying high-incidence points of highway accidents. By establishing a correlation between braking distance and road section characteristics, combined with big data analysis, the spatial clustering of brake-related accidents is revealed, and based on this, dangerous sections where braking efficiency is reduced due to insufficient slope, curve radius or road friction coefficient are identified.

[0005] To achieve the above objectives, the present invention provides a method for identifying high-incidence points of highway accidents, comprising:

[0006] Obtaining target highway section characteristic data, vehicle braking performance parameters, and historical accident data;

[0007] Perform simulation based on the road section characteristic data and vehicle braking performance parameters to calculate braking distance and obtain braking efficiency indicators under different road section characteristics;

[0008] Classify the historical accident data based on the braking performance index, extract braking accidents, and analyze the clustering characteristics of the braking accidents under different road section characteristics to obtain risky road sections;

[0009] Extracting characteristic data of the risky road sections, and using a cluster analysis method to group risky road sections with similar road section characteristics and braking efficiency degradation characteristics, to determine the categories of road sections with common risks;

[0010] The key factors affecting the braking distance in each category are obtained, and the high-risk sections in each category, i.e., accident-prone points on the target highway, are determined.

[0011] Optionally, a simulation is performed based on the road section characteristic data and the vehicle braking performance parameters to calculate the braking distance and obtain braking performance indicators under different road section characteristics, including:

[0012] Performing correlation analysis on the road section characteristic data and vehicle braking performance parameters to determine correlation coefficients and influencing factors between each road section characteristic and braking performance;

[0013] Grouping the road section characteristic data based on the influencing factors to obtain road section characteristic distribution information;

[0014] The road section characteristic distribution information is input into a pre-built braking distance calculation model to simulate the braking distance changes under different scenarios, and the braking efficiency of each road section under different scenarios is determined based on the braking distance changes.

[0015] Optionally, judging the braking performance of each road section in different scenarios based on the change in braking distance includes:

[0016] Based on the braking distance change, a regression analysis is performed in combination with corresponding road section characteristic data to determine the main influencing factors;

[0017] Based on the main influencing factors and combined with simulation data under various scenarios, the mapping relationship between braking efficiency and performance indicators is analyzed, the braking efficiency performance level of each road section under different scenarios is determined, and the braking efficiency evaluation results of the road section are obtained.

[0018] Optionally, the historical accident data is classified based on the braking performance index to extract braking accidents, and the clustering characteristics of the braking accidents under different road section characteristics are analyzed to obtain risky road sections, including:

[0019] Setting a braking performance index threshold according to the braking performance index;

[0020] Classify and process historical accident data based on the braking performance index threshold, extract records containing braking-related information, and obtain a braking accident data set;

[0021] Obtain spatial distribution information from the brake accident dataset and use the kernel density estimation algorithm to analyze the clustering characteristics of brake accidents on different road sections to obtain the brake accident density distribution;

[0022] Correlation analysis is performed on the braking accident density distribution and the road section characteristic data to obtain a risk section characteristic set, and a risk section list is marked based on the risk section characteristic set;

[0023] Based on the risk section list, a K-means clustering algorithm is used to perform spatial clustering to determine the spatial distribution pattern of risk sections and the risk concentration areas.

[0024] Optionally, characteristic data of the risky road sections are extracted, and a cluster analysis method is used to group risky road sections with similar road section characteristics and braking efficiency degradation characteristics to determine road section categories with common risks, including:

[0025] Extracting characteristic data corresponding to the risky road section and constructing a characteristic combination data set;

[0026] Based on the characteristic combination data set, a cluster analysis method is used to group the road section characteristics and the braking efficiency degradation characteristics to determine preliminary similar road sections;

[0027] Determine the distribution of braking efficiency degradation characteristics for the preliminary similar road sections, obtain a set of risk-marked road sections, and analyze the correlation pattern between common risks and road section characteristics to determine a common risk feature set;

[0028] The common risk feature set is combined with the road section category information to perform secondary classification on the risk marked road section set to obtain road section category grouping.

[0029] Optionally, key factors influencing braking distance in each category are obtained to determine high-risk road sections in each category, including:

[0030] Extract the road section characteristic data and braking distance for each road section category, use statistical analysis methods to calculate the correlation strength between each road section characteristic parameter and braking distance, and determine the key influencing factors;

[0031] Preliminarily determine the high-risk road sections in each road section category based on the key influencing factors, and obtain a preliminary high-risk road section set;

[0032] A spatial proximity analysis is performed on the preliminary high-risk road section set to obtain the correlation of distribution characteristics between the road sections, and priority sorting is performed based on the correlation to construct a final high-risk road section set.

[0033] Optionally, after obtaining the final set of high-risk road sections, it also includes: generating a corresponding risk level assessment report for each high-risk road section in combination with historical accident aggregation characteristics, and visually presenting the spatial distribution and key influencing factors of the high-risk road sections based on the risk level assessment report.

[0034] On the other hand, the present invention also provides a highway accident-prone point identification system, comprising:

[0035] The road section data acquisition module is used to obtain the road section characteristic data, historical accident data and vehicle braking performance parameters of the target highway;

[0036] A braking performance analysis module is used to perform simulation based on the road section characteristic data and vehicle braking performance parameters, calculate the braking distance, and obtain braking performance indicators under different road section characteristics;

[0037] a risky road section extraction module, configured to classify the historical accident data based on the braking performance index, extract braking accidents, and analyze the clustering characteristics of the braking accidents under different road section characteristics to obtain risky road sections;

[0038] A risk section classification module is used to extract characteristic data of the risk sections and group risk sections with similar section characteristics and braking efficiency degradation characteristics using a cluster analysis method to determine the categories of sections with common risks;

[0039] The high-risk judgment module is used to obtain key influencing factors for braking distance in each category and judge the high-risk sections in each category, that is, the accident-prone points on the target highway.

[0040] The beneficial effects of the present invention are:

[0041] This method uses simulation analysis to analyze road section characteristics and vehicle braking performance parameters, combined with historical accident data, to identify the spatial distribution patterns of risky sections. It then extracts characteristic data sets for these risky sections and uses cluster analysis to group sections with similar characteristics, identifying common risk categories and further identifying high-risk sections within each category. This method enables the precise identification and classification of risky sections on highways, providing a detailed basis for subsequent optimization of safety facilities, helping to improve road safety and reduce traffic accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. 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 any creative work.

[0043] Figure 1 This is a flow chart of a method for identifying high-incidence points of highway accidents according to an embodiment of the present invention;

[0044] Figure 2 The figure is a schematic structural diagram of a highway accident-prone point identification system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0046] 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.

[0047] On the one hand, this embodiment provides a method for identifying high-incidence points of highway accidents, such as Figure 1 Shown, including:

[0048] Obtaining target highway section characteristic data, vehicle braking performance parameters, and historical accident data;

[0049] Perform simulation based on the road section characteristic data and vehicle braking performance parameters to calculate braking distance and obtain braking efficiency indicators under different road section characteristics;

[0050] Classify and process the historical accident data based on the braking performance index, extract braking accidents, and analyze the clustering characteristics of the braking accidents under different road section characteristics to obtain risky road sections;

[0051] Extracting characteristic data of the risky road sections, and using a cluster analysis method to group risky road sections with similar road section characteristics and braking efficiency degradation characteristics, to determine the categories of road sections with common risks;

[0052] The key factors affecting the braking distance in each category are obtained, and the high-risk sections in each category, i.e., accident-prone points on the target highway, are determined.

[0053] Specifically, this embodiment performs simulation analysis by acquiring road section characteristic data and vehicle braking performance parameters, combining them with historical accident data to identify the spatial distribution patterns of risky sections. It then extracts characteristic data sets for these risky sections and uses cluster analysis to group sections with similar characteristics, identifying common risk categories and further identifying high-risk sections within each category. This invention enables the precise identification and classification of risky sections on highways, providing a detailed basis for subsequent optimization of safety facilities, helping to improve road safety and reduce traffic accidents.

[0054] This embodiment acquires road section characteristic data, including slope, curve radius, and road friction coefficient, from highway monitoring systems and vehicle sensors, and combines this with braking performance parameters from vehicle driving records to form an initial comprehensive dataset. First, road section characteristic data is acquired from the highway monitoring system. For example, a certain highway section has a slope of 5.2%, a curve radius of 300 meters, and a road friction coefficient of 0.75. This data is collected in real time using surveillance cameras combined with image recognition algorithms and sensors, and automatically stored in a cloud database. The data collection frequency is once per minute to ensure data timeliness. Next, braking performance parameters are extracted from driving records from vehicle sensors. For example, a vehicle braking on this section has a braking force of 3200 Newtons and a braking distance of 45.6 meters. This data is uploaded to the data center every second via the vehicle's onboard optical boresight (OBD) interface, forming a time-stamped record. Subsequently, the road section characteristic data and vehicle braking parameters are integrated to form a comprehensive data set. Using data fusion algorithms such as the weighted average method, the slope, curve radius, and friction coefficient are assigned weights of 0.3, 0.3, and 0.4, respectively, and the comprehensive road section difficulty index is calculated. For example, the difficulty index = 0.3*5.2+0.3*300 / 1000+0.4*0.75=2.16, which is used for subsequent analysis.

[0055] Furthermore, simulation is performed based on the road section characteristic data and vehicle braking performance parameters to calculate the braking distance and obtain braking performance indicators under different road section characteristics, including:

[0056] Performing correlation analysis on the road section characteristic data and vehicle braking performance parameters to determine correlation coefficients and influencing factors between each road section characteristic and braking performance;

[0057] Grouping the road section characteristic data based on the influencing factors to obtain road section characteristic distribution information;

[0058] The road section characteristic distribution information is input into a pre-built braking distance calculation model to simulate the braking distance changes under different scenarios, and the braking efficiency of each road section under different scenarios is determined based on the braking distance changes.

[0059] The braking performance of each road section in different scenarios is determined based on the change in braking distance, including:

[0060] Based on the braking distance change, a regression analysis is performed in combination with corresponding road section characteristic data to determine the main influencing factors;

[0061] Based on the main influencing factors and combined with simulation data under various scenarios, the mapping relationship between braking efficiency and performance indicators is analyzed, the braking efficiency performance level of each road section under different scenarios is determined, and the braking efficiency evaluation results of the road section are obtained.

[0062] Specifically, this embodiment calculates the braking distance using a pre-established braking distance calculation model based on specific parameters of various road sections, such as slope, curve radius, and road friction coefficient. Assuming that the slope of a road section is 5%, the curve radius is 50 meters, and the road friction coefficient is 0.7, the formula D=v 2 / (2μg)+vt, where D is the braking distance, v is the initial velocity set to 20 m / s, μ is the friction coefficient 0.7, g is the acceleration of gravity 9.8 m / s2, and t is the reaction time set to 1 second. The calculated braking distance is approximately 32.65 meters.

[0063] Computer simulation software is used to simulate the changes in braking distance under different slopes (such as 3%, 5%, and 8%), curve radii (such as 30 meters, 50 meters, and 80 meters), and road friction coefficients (such as 0.5, 0.7, and 0.9), generating multiple sets of data. For example, when the slope is 8%, the braking distance increases to 35.12 meters, and when the friction coefficient is 0.5, the braking distance increases to 40.23 meters, forming a comparative analysis chart. The simulation data is further subjected to regression analysis through an algorithm to determine the weight of the influence of each parameter on the braking distance, such as the slope influence factor is 0.3, the friction coefficient influence factor is 0.5, and the curve radius influence factor is 0.2. Finally, based on the simulation results and weight analysis, the mapping relationship between braking efficiency and performance indicators is analyzed, the braking efficiency performance level of each road section in different scenarios is determined, and the braking efficiency evaluation results of the road section are obtained.

[0064] Furthermore, the historical accident data is classified based on the braking performance index to extract braking accidents, and the clustering characteristics of the braking accidents under different road section characteristics are analyzed to obtain risky road sections, including:

[0065] Setting a braking performance index threshold according to the braking performance index;

[0066] Classify and process historical accident data based on the braking performance index threshold, extract records containing braking-related information, and obtain a braking accident data set;

[0067] Obtain spatial distribution information from the brake accident dataset and use the kernel density estimation algorithm to analyze the clustering characteristics of brake accidents on different road sections to obtain the brake accident density distribution;

[0068] Correlation analysis is performed on the braking accident density distribution and the road section characteristic data to obtain a risk section characteristic set, and a risk section list is marked based on the risk section characteristic set;

[0069] Based on the risk section list, a K-means clustering algorithm is used to perform spatial clustering to determine the spatial distribution pattern of risk sections and the risk concentration areas.

[0070] Specifically, this embodiment first uses data mining technology to extract brake-related records from a historical accident database. Assuming that the database contains 100,000 accident data, approximately 10,000 relevant records are screened out by setting a braking performance index threshold (such as braking distance exceeding 5.5 meters or braking time exceeding 3 seconds). A decision tree algorithm is used to classify these data, based on categories such as brake failure and brake delay. The classification accuracy reaches more than 85%, ensuring data accuracy.

[0071] Next, combined with spatial distribution information, these records were associated with the geographic information system (GIS). Assuming that each record contained latitude and longitude coordinates, a spatial interpolation algorithm (such as Kriging interpolation) was used to generate an accident density heat map. It was found that the accident density of Section A (5 kilometers in length) of a certain city's main road was 30 per square kilometer, far higher than the average of 10 in other sections, and the risk sections were preliminarily identified.

[0072] Subsequently, the clustering characteristics of accidents under different road section characteristics were analyzed, and road section characteristic data (such as slope, curvature, and traffic volume) were extracted. Assuming that the slope of Section A was 5%, the curvature was 0.2, and the average daily traffic volume was 20,000 vehicles, spatial autocorrelation analysis (calculated with the Moran's I index, the result was 0.65, indicating significant clustering) was used to confirm that accidents in Section A were highly concentrated and positively correlated with steep slopes and high traffic volume.

[0073] Finally, the spatial distribution pattern of risky sections was determined. Based on the above analysis, the kernel density estimation (KDE) algorithm was used to further refine the heat map. It was concluded that the 2-kilometer range within Section A was the core high-incidence area of ​​accidents, with a risk value of 0.8 (out of 1.0). Combined with historical data, it was inferred that the accident rate in this area increased by 30% on rainy days, thus forming a spatial distribution pattern: high-risk sections are mostly concentrated in urban main roads with steep slopes, high curvatures, and heavy traffic.

[0074] Furthermore, characteristic data of the risky road sections are extracted, and a cluster analysis method is used to group risky road sections with similar road section characteristics and braking efficiency degradation characteristics, and determine the categories of road sections with common risks, including:

[0075] Extracting characteristic data corresponding to the risky road section and constructing a characteristic combination data set;

[0076] Based on the characteristic combination data set, a cluster analysis method is used to group the road section characteristics and the braking efficiency degradation characteristics to determine preliminary similar road sections;

[0077] Determine the distribution of braking efficiency degradation characteristics for the preliminary similar road sections, obtain a set of risk-marked road sections, and analyze the correlation pattern between common risks and road section characteristics to determine a common risk feature set;

[0078] The common risk feature set is combined with the road section category information to perform secondary classification on the risk marked road section set to obtain road section category grouping.

[0079] Specifically, this embodiment integrates the characteristic data corresponding to risky road sections to form a characteristic combination dataset. By deeply mining the characteristic combination dataset, the dataset containing road section characteristics (such as slope, curvature, and road friction coefficient) and braking efficiency degradation characteristics (such as braking distance and braking time) is first preprocessed. Assume that the dataset contains 1,000 road section records, each with five features: slope (0-15 degrees), curvature (0-0.5), friction coefficient (0.3-0.8), braking distance (10-50 meters), and braking time (1-5 seconds). Principal component analysis (PCA) is used for dimensionality reduction to compress the five-dimensional features to two dimensions, retaining 90% of the variance, to obtain the principal components PC1 and PC2.

[0080] Next, the K-means clustering algorithm was used to group the reduced-dimensional data, setting the initial number of clusters K = 3. The optimal K value was determined by the elbow rule: the within-cluster sum of squares (WSS) was calculated for K values ​​ranging from 1 to 10. When K = 3, the WSS decreased gradually, confirming that K = 3.

[0081] The clustering results divide the road segments into three groups:

[0082] The first group (400) is characterized by high slope (mean 12 degrees), low friction coefficient (mean 0.4), and long braking distance (mean 45 meters);

[0083] The second group (350) is characterized by high curvature (mean 0.4), medium friction coefficient (mean 0.6), and long braking time (mean 4 seconds);

[0084] The third group (250 items) is characterized by low slope (mean value 3 degrees), high friction coefficient (mean value 0.75), and good braking performance (mean braking distance 15 meters).

[0085] Furthermore, the key factors affecting braking distance in each category are obtained, and the high-risk sections in each category are identified, including:

[0086] Extract the road section characteristic data and braking distance for each road section category, use statistical analysis methods to calculate the correlation strength between each road section characteristic parameter and braking distance, and determine the key influencing factors;

[0087] Preliminarily determine the high-risk road sections in each road section category based on the key influencing factors, and obtain a preliminary high-risk road section set;

[0088] A spatial proximity analysis is performed on the preliminary high-risk road section set to obtain the correlation of distribution characteristics between the road sections, and priority sorting is performed based on the correlation to construct a final high-risk road section set.

[0089] Specifically, this embodiment identifies key factors contributing to significantly prolonged braking distances based on the grouping results of road section categories. A random forest regression model is then used to analyze these key factors for each road section category. Combined with spatial distribution patterns, kernel density estimation (KDE, with a bandwidth of 0.5 km) is used to analyze accident hotspots. For example, sections of urban expressways with prolonged braking distances are concentrated near intersections (density values ​​> 0.8), suburban highways are distributed along straight sections with a friction coefficient below 0.6, mountainous steep roads are concentrated on downhill slopes with a gradient greater than 8%, and rural roads are located at intersections without traffic lights.

[0090] Priority is given to high-risk sections, which are sorted by comprehensive scores (braking distance * 0.6 + accident density * 0.4). The top 10% sections in each category are selected, such as the 100 sections in urban expressways with scores exceeding 0.9 (for example, section ID001, braking distance 80 meters, density 0.85), to generate the final set of high-risk sections.

[0091] Furthermore, after obtaining the final set of high-risk road sections, it also includes: generating a corresponding risk level assessment report for each high-risk road section in combination with historical accident aggregation characteristics, and visually presenting the spatial distribution and key influencing factors of the high-risk road sections based on the risk level assessment report.

[0092] Specifically, this embodiment obtains the section location information and historical accident data from the dangerous section list to determine the unique identifier and accident record of each dangerous section; through cluster analysis of historical accident data, the K-means algorithm is used to extract the accident clustering characteristics to obtain the accident frequency and accident severity; based on the accident clustering characteristics, combined with the section traffic flow and section environmental factors, the risk level of each dangerous section is calculated to generate a risk level assessment; if the risk level is higher than the preset threshold, the safety facility optimization needs are determined based on the section location information and the accident severity; by analyzing the safety facility optimization needs and combining the section environmental factors, an optimization basis is generated to obtain a safety facility deployment plan; based on the safety facility deployment plan, an assessment report for each dangerous section is generated to obtain a detailed description of the optimization basis.

[0093] Using data visualization technology, based on comprehensive risk distribution data, a distribution map of high-risk sections is drawn, presenting the spatial distribution and key risk characteristics, and generating a final map; through an interactive visualization interface, the final map is loaded, dynamically displaying high-risk areas and related influencing factors to obtain a visual distribution result.

[0094] On the other hand, this embodiment also provides a highway accident-prone point identification system, such as Figure 2 Shown, including:

[0095] The road section data acquisition module is used to obtain the road section characteristic data, historical accident data and vehicle braking performance parameters of the target highway;

[0096] A braking performance analysis module is used to perform simulation based on the road section characteristic data and vehicle braking performance parameters, calculate the braking distance, and obtain braking performance indicators under different road section characteristics;

[0097] a risky road section extraction module, configured to classify the historical accident data based on the braking performance index, extract braking accidents, and analyze the clustering characteristics of the braking accidents under different road section characteristics to obtain risky road sections;

[0098] A risk section classification module is used to extract characteristic data of the risk sections and group risk sections with similar section characteristics and braking efficiency degradation characteristics using a cluster analysis method to determine the categories of sections with common risks;

[0099] The high-risk judgment module is used to obtain key influencing factors for braking distance in each category and judge the high-risk sections in each category, that is, the accident-prone points on the target highway.

[0100] The embodiments described above are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by persons skilled in the art should fall within the scope of protection defined by the claims of the present invention.

Claims

1. A method for identifying high-incidence points of highway accidents, characterized in that: include: Obtaining target highway section characteristic data, vehicle braking performance parameters, and historical accident data; Perform simulation based on the road section characteristic data and vehicle braking performance parameters to calculate braking distance and obtain braking efficiency indicators under different road section characteristics; Classify the historical accident data based on the braking performance index, extract braking accidents, and analyze the clustering characteristics of the braking accidents under different road section characteristics to obtain risky road sections; Extracting characteristic data of the risky road sections, and using a cluster analysis method to group risky road sections with similar road section characteristics and braking efficiency degradation characteristics, to determine the categories of road sections with common risks; The key factors affecting the braking distance in each category are obtained, and the high-risk sections in each category, i.e., accident-prone points on the target highway, are determined.

2. The method for identifying high-accident-prone points on highways according to claim 1, characterized in that: Based on the road section characteristic data and vehicle braking performance parameters, simulation is performed to calculate the braking distance and obtain braking performance indicators under different road section characteristics, including: Performing correlation analysis on the road section characteristic data and vehicle braking performance parameters to determine correlation coefficients and influencing factors between each road section characteristic and braking performance; Grouping the road section characteristic data based on the influencing factors to obtain road section characteristic distribution information; The road section characteristic distribution information is input into a pre-built braking distance calculation model to simulate the braking distance changes under different scenarios, and the braking efficiency of each road section under different scenarios is determined based on the braking distance changes.

3. The method for identifying high-accident-prone points on highways according to claim 2, characterized in that: The braking performance of each road section in different scenarios is determined based on the braking distance change, including: Based on the braking distance change, a regression analysis is performed in combination with corresponding road section characteristic data to determine the main influencing factors; Based on the main influencing factors and combined with simulation data under various scenarios, the mapping relationship between braking efficiency and performance indicators is analyzed, the braking efficiency performance level of each road section under different scenarios is determined, and the braking efficiency evaluation results of the road section are obtained.

4. The method for identifying high-accident-prone points on highways according to claim 1, characterized in that: The historical accident data is classified based on the braking performance index to extract braking accidents, and the clustering characteristics of the braking accidents under different road section characteristics are analyzed to obtain risky road sections, including: Setting a braking performance index threshold according to the braking performance index; Classify and process historical accident data based on the braking performance index threshold, extract records containing braking-related information, and obtain a braking accident data set; Obtain spatial distribution information from the brake accident dataset and use the kernel density estimation algorithm to analyze the clustering characteristics of brake accidents on different road sections to obtain the brake accident density distribution; Correlation analysis is performed on the braking accident density distribution and the road section characteristic data to obtain a risk section characteristic set, and a risk section list is marked based on the risk section characteristic set; Based on the risk section list, a K-means clustering algorithm is used to perform spatial clustering to determine the spatial distribution pattern of risk sections and the risk concentration areas.

5. The method for identifying high-accident-prone points on expressways according to claim 1, characterized in that: Extract the characteristic data of the risky road sections, and use cluster analysis to group the risky road sections with similar road section characteristics and braking efficiency degradation characteristics, and determine the categories of road sections with common risks, including: Extracting characteristic data corresponding to the risky road section and constructing a characteristic combination data set; Based on the characteristic combination data set, a cluster analysis method is used to group the road section characteristics and the braking efficiency degradation characteristics to determine preliminary similar road sections; Determine the distribution of braking efficiency degradation characteristics for the preliminary similar road sections, obtain a set of risk-marked road sections, and analyze the correlation pattern between common risks and road section characteristics to determine a common risk feature set; The common risk feature set is combined with the road section category information to perform secondary classification on the risk marked road section set to obtain road section category grouping.

6. The method for identifying high-accident-prone points on expressways according to claim 1, characterized in that: Obtain the key factors affecting braking distance in each category and identify high-risk sections in each category, including: Extract the road section characteristic data and braking distance for each road section category, use statistical analysis methods to calculate the correlation strength between each road section characteristic parameter and braking distance, and determine the key influencing factors; Preliminarily determine the high-risk road sections in each road section category based on the key influencing factors, and obtain a preliminary high-risk road section set; A spatial proximity analysis is performed on the preliminary high-risk road section set to obtain the correlation of distribution characteristics between the road sections, and priority sorting is performed based on the correlation to construct a final high-risk road section set.

7. The method for identifying high-accident-prone points on expressways according to claim 6, characterized in that: After obtaining the final set of high-risk road sections, it also includes: generating a corresponding risk level assessment report for each high-risk road section in combination with historical accident aggregation characteristics, and visually presenting the spatial distribution and key influencing factors of the high-risk road sections based on the risk level assessment report.

8. A highway accident-prone point identification system, characterized in that: include: The road section data acquisition module is used to obtain the road section characteristic data, vehicle braking performance parameters and historical accident data of the target highway; A braking performance analysis module is used to perform simulation based on the road section characteristic data and vehicle braking performance parameters, calculate the braking distance, and obtain braking performance indicators under different road section characteristics; a risky road section extraction module, configured to classify the historical accident data based on the braking performance index, extract braking accidents, and analyze the clustering characteristics of the braking accidents under different road section characteristics to obtain risky road sections; A risk section classification module is used to extract characteristic data of the risk sections and group risk sections with similar section characteristics and braking efficiency degradation characteristics using a cluster analysis method to determine the categories of sections with common risks; The high-risk judgment module is used to obtain key influencing factors for braking distance in each category and judge the high-risk sections in each category, that is, the accident-prone points on the target highway.

Images