A traffic safety evaluation method for intersections and road sections based on extension cloud model

Abstract

The present invention discloses a method for evaluating traffic safety at intersections and road sections based on an extension cloud model, comprising the following steps: Step 1: determining a standard cloud model; Step 2: calculating cloud parameters of the cloud model; Step 3: calculating an association matrix of the cloud model; Step 4: calculating the basic probability distribution of each evaluation indicator; and Step 5: calculating a judgment vector matrix to determine the evaluation results. The present invention employs an extension matter-element method for traffic safety evaluation and utilizes a cloud model to characterize the characteristics of objects in extension theory. The present invention enables timely monitoring of the traffic safety status of urban intersections and road sections, and is of great significance to current road safety management and decision-making in my country.

Description

Technical Field

[0001] The invention relates to a method for evaluating traffic safety at intersections and road sections based on an extension cloud model, and belongs to the field of traffic safety. Background Art

[0002] With the rapid development of urbanization and the increase in transportation options, motorization has significantly increased, and transportation demand is also growing. While this rapid development has greatly facilitated travel, it has also brought new challenges. Traffic accidents have caused significant casualties and property damage, significantly impacting human development. To achieve the goal of building a strong transportation nation, it is necessary to establish a comprehensive and scientific traffic safety monitoring, evaluation, and early warning system.

[0003] Traffic safety assessment evaluates road components or other factors during construction that affect traffic safety in order to identify potential risks. Numerous current traffic safety assessment methods exist, but their scope of application and applicable subjects vary, necessitating further research. In terms of their scope of application, traffic accident-based assessment methods are suitable for comparing traffic safety conditions across different regions and over time, but require a longer data collection period and are simple and intuitive. Traffic conflict-based assessment methods allow for rapid and quantitative analysis of traffic safety status and are suitable for short-term assessments of specific subjects. Comprehensive safety assessment methods are widely studied, including TOPSIS, VIKOR, fuzzy comprehensive evaluation, matter-element extension evaluation, and evidence theory. These methods, depending on their characteristics, can be applied to assess the safety status of specific intersections, roads, and regions, demonstrating their broad applicability and comprehensiveness. Comprehensive safety assessment methods consider multiple factors, including personnel, vehicles, roads, the environment, and management, to comprehensively evaluate the subject, addressing the complexity and ambiguity inherent in traffic safety assessments and yielding more scientific and rational results. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a traffic safety evaluation method for intersections and road sections based on the extension cloud model. The method of the present invention applies the cloud model to the extension matter-element method, constructs an extension cloud combination evaluation model, realizes the assessment of traffic safety risks at urban intersections and road sections, and achieves the purpose of timely grasping their traffic safety status. It is of great significance to my country's current road safety management and decision-making.

[0005] The present invention provides the following technical solutions to achieve the above research objectives:

[0006] In a first aspect, the present invention provides a method for evaluating traffic safety at intersections and road sections based on an extension cloud model, comprising the following steps:

[0007] Step 1: Determine traffic safety evaluation indicators and establish a standard cloud model;

[0008] Step 2: Calculate cloud parameters of the cloud model;

[0009] Step 3: Calculate the correlation matrix of the cloud model;

[0010] Step 4: Assign basic probability to each evaluation indicator and obtain the grade probability matrix;

[0011] Step 5: Calculate the comprehensive score of each intersection node and road section unit to obtain the final evaluation result.

[0012] Furthermore, in step 1, based on the extension theory, the object N, feature C and feature value V are described as a triple, that is, the object element R = (N, C, V), and the feature value V is replaced by the cloud representation of feature C to establish the standard cloud model; wherein, the object N refers to the intersection node and road section unit, the feature C refers to the traffic safety evaluation index, and the feature value V refers to the value range of the traffic safety evaluation index.

[0013] Furthermore, based on extension theory, the standard cloud model is specifically determined as follows:

[0014]

[0015] Where, j = 1, 2, ..., 5, R1 represents the matter-element at the very safe level, R2 represents the matter-element at the relatively safe level, R3 represents the matter-element at the medium safe level, R4 represents the matter-element at the relatively dangerous level, and R5 represents the matter-element at the very dangerous level; N k is the thing to be evaluated k; C i is the traffic safety evaluation index i, i=1,2,…,m; V ji is the value range of traffic safety evaluation index i under level j; (E xi ,E ni ,H ei ) is the cloud representation of evaluation index i, E xi 、E ni and H ei is the cloud parameter of evaluation index i, E xi is the expected value of the cloud model, E ni is the entropy of the cloud model, H ei is the super entropy of the cloud model.

[0016] Furthermore, the calculation expression of the cloud parameters is as follows:

[0017]

[0018]

[0019]

[0020] Where, E xi is the expected value of the cloud model; E ni is the entropy of the cloud model; H ei is the super entropy of the cloud model; c max and c min V ji The upper and lower limits of ; p is a variable constant.

[0021] Furthermore, the specific calculation formula of the correlation matrix described in step 3 is:

[0022]

[0023] Where u ij is the correlation coefficient between evaluation index i and grade j, E′ n The expected value is equal to E ni , the standard deviation is equal to H ei Random number y i is the value of the evaluation index i.

[0024] Furthermore, the specific level probability matrix described in step 4 is:

[0025]

[0026] Where, the basic probability distribution parameter

[0027] Furthermore, the specific calculation steps of the comprehensive score value described in step 5 are:

[0028] Step 5.1: Construct the judgment vector B:

[0029] B=WU * =[b1,b2,b3,b4,b5]

[0030] Where b j is the jth component of the evaluation vector B; W is the weight vector of each evaluation index;

[0031] Step 5.2: After solving the judgment vector multiple times, the weighted average is obtained to obtain B * :

[0032]

[0033] Where B t is the evaluation vector obtained by the t-th solution; l is the number of solutions;

[0034] Step 6.3: The formula for calculating the comprehensive score r is as follows:

[0035]

[0036] Where, B * The jth component of j is the score value corresponding to level j, and the integers {f1, f2, f3, f4, f5} are taken from level one to level five = {100, 80, 60, 40, 20}.

[0037] Furthermore, the method further includes calculating the credibility θ of the cloud model, which is expressed as:

[0038]

[0039]

[0040]

[0041] Where r t (y) is the comprehensive score of the object-element y obtained by the t-th calculation; E yr is the expected value of the comprehensive score calculated l times; E yn is the entropy of the comprehensive score value calculated l times.

[0042] In a second aspect, the present invention provides a computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions that, when executed by a computing device, cause the computing device to perform the method described above.

[0043] In a third aspect, the present invention provides an electronic device comprising one or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and are configured to be executed by the one or more processors, and the one or more programs include instructions for executing the method described above.

[0044] This paper uses the extension matter-element method for traffic safety assessment and utilizes a cloud model to characterize the object characteristics in extension theory. This method enables timely monitoring of the traffic safety status of urban intersections and road sections, and is of great significance to current road safety management and decision-making in my country. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is an overall flow chart of a traffic safety evaluation method for intersections and road sections based on the extension cloud model. DETAILED DESCRIPTION

[0046] The technical solution of the present invention is described in detail below through examples. This example provides a method for evaluating intersection traffic safety based on the extension cloud model. The method for evaluating road traffic safety is similar. The calculation process for evaluating intersection and road traffic safety is as follows: Figure 1 As shown, it mainly includes the following steps:

[0047] Step 1: Determine the standard cloud model. Based on the extension theory, the object N, feature C and feature value V are described as a triple, that is, the object element R = (N, C, V). If the V value is expressed as a fixed value, it lacks consideration of the uncertainty of the object. Therefore, the present invention uses (E xi ,E ni ,H ei ) instead of V value can make up for the defects of extension theory. The constructed standard cloud is as follows:

[0048]

[0049] Where j is the traffic safety level of the urban intersection and road section, j = 1, 2, ..., 5, R1 represents the matter-element at the very safe level, R2 represents the matter-element at the relatively safe level, R3 represents the matter-element at the medium safe level, R4 represents the matter-element at the relatively dangerous level, and R5 represents the matter-element at the very dangerous level; N k is the urban intersection and road section to be evaluated, k is the sequence number; C i is the traffic safety evaluation index i, i=1,2,…,m; V ji is the value range of evaluation index i under level j; (E xi ,E ni ,H ei ) is the cloud representation of evaluation index i, E xi 、E ni and H ei is the cloud parameter.

[0050] The traffic safety levels at urban intersection nodes and road sections are divided into five levels, from Level 1 to Level 5: Very Safe, Relatively Safe, Moderately Safe, Relatively Dangerous, and Very Dangerous. Based on the definitions of specific intersection indicators and related research, and considering the specific needs of safety management, a grading interval for urban intersection safety evaluation indicators is established, as shown in Table 1.

[0051] Table 1 Intersection traffic safety evaluation index grading table

[0052]

[0053]

[0054] Step 2: The expression for calculating the model cloud parameters is:

[0055]

[0056]

[0057]

[0058] Where, E xi is the expected value of the cloud model, which is the middle value of the value interval of the evaluation index i under level j, reflecting the central value of the characteristic value V; E ni is the entropy of the cloud model, reflecting the span of the characteristic value V, that is, the distribution range of the cloud model; H ei is the super entropy of the cloud model, which measures the uncertainty, i.e. the thickness of the cloud model; c max and c min are the upper and lower limits of the interval of indicator i at level j; p is a variable constant that can be adjusted according to the uncertainty of different indicators and the actual conditions in various places to control the thickness of the cloud model.

[0059] The standard cloud model of urban intersection safety evaluation index can be obtained from the cloud parameter expression and Table 1, as shown in Table 2.

[0060] Table 2 Standard cloud model for urban intersection safety evaluation indicators

[0061]

[0062]

[0063] Step 3: Calculate the cloud model association matrix, which includes the following steps:

[0064] Step 3.1: Take the values ​​y of each evaluation index of urban intersections and road sections i As the object-element to be evaluated, the membership degree of the object-element to be evaluated and each evaluation level is calculated.

[0065] When calculating the membership, the values ​​of each evaluation index are regarded as cloud drops, and a random number E′ is generated first. n Normal distribution, E′ n The expected value is equal to E ni , the standard deviation is equal to H ei The membership calculation expression between evaluation index i and evaluation level j is as follows:

[0066]

[0067] Step 3.2: Combine the evaluation index data of urban intersections and road sections and construct the following association matrix based on the cloud model membership:

[0068]

[0069] Where u ij is the correlation coefficient between evaluation index i and security level j; j is an integer from 1 to 5; m is the number of indicators.

[0070] Step 4: Calculate the basic probability distribution of each evaluation indicator, which specifically includes the following steps:

[0071] Step 4.1: Calculate basic probability distribution parameters

[0072] The DS evidence theory (Dempster-Shafer evidence theory) is introduced. This method can be used to process incomplete and uncertain information and assign trust to evidence. Assume that there is an identification framework containing five levels of security levels. The cloud model association matrix U is used as an "evidence", and its vector components are the trust of each security level. Trust allocation methods include basic trust allocation (Basic Belief Assignment, BBA) and basic probability allocation (Basic Probability Assignment, BPA). The former relies on subjective assumptions, while the latter solves probability allocation through calculation rules. The extension cloud model constructed by the present invention is an uncertainty modeling method, so the basic probability allocation method is used to solve the trust. The BPA method is to assign trust to the interval [0,1], and the sum of the trust is 1. The larger the trust value, the greater the possibility that the indicator i belongs to this security level.

[0073] Under the above assumptions, the correlation matrix U is processed and the correlation coefficients between each evaluation index and the safety level are assigned basic probabilities so that the probability mapping of each safety level is within the interval [0,1] and the sum of the probabilities is 1. The expression of the basic probability distribution is:

[0074]

[0075] Step 4.2: The level probability matrix U* after basic probability distribution is expressed as:

[0076]

[0077] Furthermore, the evaluation vector matrix is ​​calculated in step 5 to determine the evaluation result. The specific calculation steps are:

[0078] Step 5.1: Combine the indicator weight vector and the grade probability matrix U * By multiplying the values, we can find the evaluation vector B of the intersections and road sections in the evaluated city, as shown in Table 3.

[0079] B=WU * =[b1,b2,b3,b4,b5]

[0080] Where b j is the component of the evaluation vector B, j corresponds to different safety levels; W is the weight vector, the indicator weight represents the degree of influence of the indicator on the evaluation result, and the indicator weighting methods are divided into subjective, objective and combined weighting methods. Among them, the subjective weighting methods include hierarchical analysis method, expert survey method and binomial coefficient method, etc., the objective weighting methods include principal component analysis method, entropy weight method and multi-objective programming method, etc. The combined weighting method is a combination of subjective weighting method and objective weighting method.

[0081] Table 3 Evaluation vectors of each intersection

[0082]

[0083]

[0084] Step 5.2: Calculate the weighted average judgment vector B * Since random numbers E′ are generated when computing the cloud model association matrix n , which may lead to randomness of the results, so it is necessary to solve it multiple times and calculate the weighted average judgment vector B * , and then determine the evaluation level according to the maximum membership principle, that is, when the membership value of indicator i in safety level j is the largest, the safety evaluation level of this indicator is j. Evaluation vector B * The expression is:

[0085]

[0086] Where B t is the t-th evaluation vector; l is the number of calculations.

[0087] Step 5.3: For the weighted average judgment vector B * The comprehensive score r can be calculated and used to compare the comprehensive traffic safety risk status of different evaluated objects within the same evaluation period. The comprehensive score r and the determined safety evaluation level can be used to identify high-risk urban intersections and road sections. The smaller the r value, the worse the safety evaluation level, which means the risk of the evaluated object is higher. The calculation formula of the comprehensive score r is as follows:

[0088]

[0089] Where, is the weighted average judgment vector B * The weight of j is the score value corresponding to security level j, which takes integers {100, 80, 60, 40, 20} from level 1 to level 5.

[0090] Step 5.4: Calculate the credibility of the cloud model. Since the random number E′ is generated when calculating the cloud model association matrix n , which may lead to randomness in the results, so it is necessary to calculate the credibility of the comprehensive score r. The expression is:

[0091]

[0092]

[0093]

[0094] Where r t (y) is the comprehensive score of the object-element y to be evaluated for the tth time; E yr is the expected value of the comprehensive score r calculated l times; E yn is the entropy of the comprehensive score r calculated l times; θ is the credibility level of the solution.

[0095] Table 4 Traffic safety evaluation results of each intersection

[0096]

[0097] As shown in Table 4, the comprehensive scores of intersections N1, N2, N3, N4, and N6 are all less than 80 points. The safety level of N1 is level 3, which is the most dangerous among the 12 intersections and needs to be paid attention to by traffic managers.

[0098] The present invention focuses on multiple evaluation indicators of urban intersection nodes and road sections, thereby constructing a correlation coefficient matrix, combining the weight coefficients of each indicator to obtain the final evaluation vector, determining the traffic safety level according to the principle of maximum membership, and calculating the comprehensive score value of urban intersection nodes and road sections to determine the credibility of the cloud model, which helps managers to propose scientific and reasonable road traffic safety management measures in a targeted manner.

[0099] Based on the same technical solution, the present invention also discloses a computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions. When the instructions are executed by a computing device, the computing device executes the above-mentioned intersection and road section traffic safety evaluation method based on the extension cloud model.

[0100] Based on the same technical solution, the present invention also discloses a computing device, including one or more processors, one or more memories and one or more programs, wherein the one or more programs are stored in the one or more memories and are configured to be executed by the one or more processors, and the one or more programs include instructions for executing the above-mentioned intersection and road section traffic safety evaluation method based on the extension cloud model.

[0101] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0102] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0103] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0105] The above is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with this technical field within the technical scope disclosed in the present invention should be covered by the scope of protection of the present invention.

Claims

1. A method for evaluating traffic safety at intersections and road sections based on an extension cloud model, characterized in that: The following steps are involved: Step 1: Determine traffic safety evaluation indicators and establish a standard cloud model; Step 2: Calculate cloud parameters of the cloud model; Step 3: Calculate the correlation matrix of the cloud model; Step 4: Assign basic probability to each evaluation indicator and obtain the grade probability matrix; Step 5: Calculate the comprehensive score of each intersection node and road section unit to obtain the final evaluation result; In step 1, based on extension theory, the object N, feature C, and feature value V are described as a triple, that is, the object R = (N, C, V), and the feature value V is replaced by the cloud representation of feature C to establish the standard cloud model; wherein, the object N refers to the intersection node and road section unit, the feature C refers to the traffic safety evaluation index, and the feature value V refers to the value range of the traffic safety evaluation index; The standard cloud model described above is determined based on extension theory as follows: Where, j = 1, 2, ..., 5, R1 represents the matter-element at the very safe level, R2 represents the matter-element at the relatively safe level, R3 represents the matter-element at the medium safe level, R4 represents the matter-element at the relatively dangerous level, and R5 represents the matter-element at the very dangerous level; N k is the thing to be evaluated k; C i is the traffic safety evaluation index i, i=1,2,…,m; V ji is the value range of traffic safety evaluation index i under level j; (E xi ,E ni ,H ei ) is the cloud representation of evaluation index i, E xi 、E ni and H ei is the cloud parameter of evaluation index i, E xi is the expected value of the cloud model, E ni is the entropy of the cloud model, H ei is the super entropy of the cloud model; The calculation expressions of the cloud parameters are as follows: Where, E xi is the expected value of the cloud model; E ni is the entropy of the cloud model; H ei is the super entropy of the cloud model; c max and c min V ji The upper and lower limits of ; p is a variable constant; The specific calculation formula of the correlation matrix described in step 3 is: Where u ij is the correlation coefficient between evaluation index i and grade j, E′ n The expected value is equal to E ni , the standard deviation is equal to H ei Random number y i is the value of evaluation index i; The specific level probability matrix described in step 4 is: Where, the basic probability distribution parameter The specific calculation steps for the comprehensive score value described in step 5 are: Step 5.1: Construct the judgment vector B: <h2 style=";text-align:left;direction:ltr">B=WU<h2 style=";text-align:left;direction:ltr"> * <h2 style=";text-align:left;direction:ltr"> (b1,b2,b3,b4,b5) Where b j is the jth component of the evaluation vector B, j = 1, 2, ..., 5; W is the weight vector of each evaluation index; Step 5.2: After solving the judgment vector multiple times, the weighted average is obtained to obtain B * : Where B t is the evaluation vector obtained by the t-th solution; l is the number of solutions; Step 6.3: The formula for calculating the comprehensive score r is as follows: Where, B * The jth component of j is the score value corresponding to level j, and the integers {f1, f2, f3, f4, f5} are taken from level one to level five = {100, 80, 60, 40, 20}.

2. The method for evaluating traffic safety at intersections and road sections based on an extension cloud model according to claim 1, characterized in that: The method further includes calculating the credibility θ of the cloud model, which is expressed as: Where r t (y) is the comprehensive score of the object-element y obtained by the t-th calculation; E yr is the expected value of the comprehensive score calculated once; E yn is the entropy of the comprehensive score value calculated l times.

3. A computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions, characterized in that When the instructions are executed by a computing device, the computing device is caused to perform the method according to claim 1 or 2.

4. An electronic device, characterized in that: The method comprises one or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for executing the method according to claim 1 or 2.

Images