A method and apparatus for evaluating road safety capacity of a proving ground based on micro-simulation

Abstract

This application relates to the field of electronic digital processing technology, specifically to a method and device for assessing the safety capacity of automotive test track roads based on microscopic simulation. The method includes: constructing a microscopic traffic simulation model of the road under test based on map data and vehicle operation data of the road under test in the automotive test track; in each set of simulation conditions, real-time monitoring and extraction of vehicle microscopic interaction features, and constructing multiple vehicle operation risk indicators based on the vehicle microscopic interaction features and equivalent hourly traffic flow; establishing a fuzzy comprehensive evaluation matrix that maps vehicle operation risk indicators to safety levels based on weighted weights and a two-factor entropy-driven cloud model; identifying the critical state where the safety level transitions, and determining the vehicle operation scale corresponding to the critical state as the maximum safe operating capacity of the road under test. This application can achieve a scientific assessment of the safety capacity of test track roads.

Description

Technical Field

[0001] This application relates to the field of electronic digital processing technology, and more specifically, to a method and device for assessing the road safety capacity of an automotive proving ground based on microscopic simulation. Background Technology

[0002] With the rapid development of the automotive industry towards intelligence and connectivity, automotive proving grounds, as key R&D verification platforms, are facing increasingly heavy testing tasks. Against this backdrop, a high-intensity testing environment—a multi-task parallel testing environment—has emerged, requiring proving grounds to simultaneously accommodate a large number of different types of vehicles for continuous performance verification and durability testing within limited road resources. In such an environment, proving ground managers need to utilize precise simulation and evaluation technologies to achieve efficient allocation of road resources, thereby enabling more scientific and quantitative control over the number of test vehicles deployed and scheduling schemes. Capacity analysis technology based on microscopic traffic simulation and risk quantification assessment provides technical support for formulating coordinated control of vehicle operation safety and efficiency under high-intensity testing environments. Compared to traditional management methods that rely solely on experience or simple traffic statistics, these emerging evaluation methods demonstrate significant advantages in risk identification accuracy, scientific scheduling decisions, and test resource utilization.

[0003] In the high-intensity testing environment of automotive proving grounds, road safety capacity refers to the maximum number of vehicles that a test track can accommodate while meeting specific safety level constraints (such as critical safety conditions). Current research on the evaluation of proving ground road operation efficiency and safety has the following two main shortcomings.

[0004] First, existing research indicators mostly focus on traffic efficiency, that is, they mainly focus on the changes in the operating speed of vehicles in the test field or the road congestion under different vehicle sizes, and lack special evaluation research on the core indicator of "safe capacity".

[0005] Second, existing traffic capacity analysis methods are mostly based on standard urban roads or highway scenarios, and do not fully consider the special operating conditions of automotive test tracks (especially reinforced durability roads).

[0006] In summary, existing test track operation evaluation methods are not yet fully adapted to the specific challenges and needs of refined safety management and quantitative capacity control faced by automotive test tracks in the intelligent and high-intensity testing phase.

[0007] In view of the above, this application is hereby submitted. Summary of the Invention

[0008] The purpose of this application is to provide a method and device for assessing the road safety capacity of a test track based on micro-simulation, which can accurately capture micro-conflict characteristics and transform fuzzy safety states into quantitative vehicle number limits, thereby achieving a scientific assessment of the road safety capacity of the test track.

[0009] To achieve the above objectives, this application adopts the following technical solution: Firstly, this application provides a method for assessing the road safety capacity of an automotive proving ground based on microscopic simulation, including: Based on the map data and vehicle operation data of the road to be tested in the automotive test track, a microscopic traffic simulation model of the road to be tested is constructed. Set the initial value, termination value and increment step size of the vehicle operation scale, generate multiple sets of simulation conditions under different vehicle operation scales and perform operation simulation. In each set of simulation conditions, the micro-interaction features of the vehicles are monitored and extracted in real time, and multiple vehicle operation risk indicators are constructed based on the micro-interaction features of the vehicles and the equivalent hourly traffic flow. The multiple vehicle operation risk indicators are assigned weights, and the multiple vehicle operation risk indicators are weighted and summed according to the weights obtained to obtain a comprehensive risk index. Based on the weights obtained from the weighting and the cloud model driven by the two-factor entropy, a fuzzy comprehensive evaluation matrix is ​​established to map vehicle operation risk indicators to safety levels. Based on the principle of maximum membership, the safety level of different vehicle operation scales is determined according to the fuzzy comprehensive evaluation matrix. Identify the critical state where the safety level transitions, and determine the vehicle operation scale corresponding to the critical state as the maximum safe operating capacity of the road under test.

[0010] Secondly, this application provides an electronic device, comprising: At least one processor, and a memory communicatively connected to at least one of the processors; The memory stores instructions that can be executed by at least one of the processors, which enable the at least one processor to perform a micro-simulation-based method for assessing the road safety capacity of a vehicle proving ground.

[0011] Compared with the prior art, this application has the following beneficial effects: This application addresses the shortcomings of existing automotive proving ground road capacity assessment methods, which often focus only on macroscopic operating speeds or congestion conditions while neglecting microscopic operational risks under multi-task parallel high-intensity testing environments. It provides a microscopic simulation-based method for assessing the safety capacity of automotive proving ground roads. Without relying on historical accident data, this method enables the scientific identification and forward-looking assessment of the operational safety capacity of proving ground roads, and identifies critical points where safety levels may abruptly change. This effectively improves the utilization efficiency of proving ground road resources while ensuring vehicle testing safety. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0013] Figure 1 This is a flowchart illustrating a method for assessing the road safety capacity of an automotive proving ground based on microscopic simulation, as provided in an embodiment of this application. Figure 2 This is a road grid and vehicle speed point distribution map provided in an embodiment of this application; Figure 3 This is a graph showing the changes in the TTC ratio, PET ratio, and parking ratio as a function of the number of vehicles, as provided in the embodiments of this application. Figure 4 It is a line graph of the comprehensive hazard index (RI) and safety level provided in the application embodiment; Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0014] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0015] Figure 1 This is a flowchart illustrating a method for assessing the road safety capacity of an automotive proving ground based on microscopic simulation, as provided in this embodiment. This embodiment is applicable to situations where the maximum number of vehicles a proving ground can accommodate is determined through simulation while ensuring driving safety. This method can be executed by electronic equipment.

[0016] like Figure 1 As shown, this embodiment provides a method for assessing the road safety capacity of an automotive proving ground based on microscopic simulation, specifically including the following steps: S110. Based on the map data and vehicle operation data of the road to be tested in the automotive test track, construct a microscopic traffic simulation model of the road to be tested.

[0017] S120. Set the initial value, termination value and increment step size of the vehicle operation scale, generate multiple sets of simulation conditions under different vehicle operation scales and perform operation simulation.

[0018] Among them, the road to be tested is a reinforced durability road, which has more than 60 types of road surface features and 10 independent lanes. The traffic flow is dense and the operation mode is 24 hours a day. It has typical characteristics of multi-task parallel and high-intensity testing.

[0019] First, high-precision map data of the road to be tested and measured vehicle operation data are acquired. Then, the measured vehicle operation data is cleaned, and a map matching algorithm is used to map discrete vehicle speed data points to road segments on the high-precision map. For example, based on existing measured vehicle operation data (including vehicle speed, acceleration, steering angle, etc.) and high-precision map data of reinforced durability roads, after cleaning the original measured data, discrete vehicle speed data points are mapped to specific road segments according to the road surface type and latitude / longitude.

[0020] Figure 2 This is a road grid and vehicle speed point distribution map provided in an embodiment of this application. Figure 2 The road types include asphalt roads, cement roads, gravel roads, and dirt roads.

[0021] Finally, based on the mapped vehicle speed data points and the operating rules of the road under test, a microscopic traffic simulation model of the road under test is constructed using microscopic traffic simulation software. Specifically, a digital simulation environment for enhanced durability roads is constructed using the microscopic traffic simulation software SUMO. The simulation vehicle scale is set from 60 to 120 vehicles, increasing in increments of 2 vehicles; for each group of vehicles, the runtime of a single simulation (i.e., one set of simulation conditions) is set to 15,000 seconds (approximately 4.17 hours).

[0022] S130. In each set of simulation conditions, the micro-interaction features of the vehicles are monitored and extracted in real time, and multiple vehicle operation risk indicators are constructed based on the micro-interaction features of the vehicles and the equivalent hourly traffic flow.

[0023] In each simulation scenario, the number of vehicles involved in a potential collision risk event, the number of vehicles involved in a merging conflict event, and the number of vehicles involved in a parking interference event are monitored and extracted in real time. Based on the number of vehicles involved in the first scenario and the equivalent hourly traffic flow, the Time-to-Collision (TTC) ratio is obtained; based on the number of vehicles involved in the second scenario and the equivalent hourly traffic flow, the Petty-to-Peak (PET) ratio is obtained; and based on the number of vehicles involved in the third scenario and the equivalent hourly traffic flow, the parking ratio is obtained. The equivalent hourly traffic flow (PCU) is the total number of vehicles passing through in one hour, calculated by uniformly converting the actual mixed traffic flow (including passenger cars, trucks, motorcycles, etc.) into standard passenger car values ​​according to their road resource occupancy. Post-Encroachment Time (PET) refers to the time difference from the moment the first vehicle (or pedestrian) leaves a conflict area (i.e., the "encroached" area) to the moment the second vehicle (or pedestrian) enters the same area.

[0024] See the following formula:

[0025] in, yes ratio, For simulation The number of vehicles (i.e., the first vehicle number). It is the equivalent hourly traffic flow. yes ratio, For simulation The number of vehicles (i.e., the second number of vehicles). It is the parking ratio. This represents the total number of parked vehicles in the intersection area (i.e., the number of third vehicles).

[0026] Statistical and regression fitting were performed on the above three ratios for vehicles ranging from 60 to 120. The fitting results are as follows: Figure 3 As shown; Figure 3 This is a graph showing the TTC ratio, PET ratio, and parking ratio as a function of the number of vehicles, provided in the embodiments of this application. The coefficient of determination for each ratio was calculated. All ratios are greater than 0.94, indicating a significant positive correlation between each ratio and traffic flow intensity.

[0027] S140. Assign weights to multiple vehicle operation risk indicators, and sum the weights of the multiple vehicle operation risk indicators according to the weights assigned to obtain a comprehensive risk index.

[0028] Based on the analytic hierarchy process (AHP), the various vehicle operation risk indicators are weighted and then summed to obtain the comprehensive risk index (RI). The comprehensive risk index (RI) aims to reflect the potential collision risk, safe distance between vehicles, and congestion during vehicle operation in weaving zones, thereby providing a unified evaluation standard to comprehensively assess the traffic safety of weaving zones and road sections on enhanced durability roads.

[0029] Optionally, firstly, in order to eliminate the differences in the dimensions of different indicators, the TTC ratio, PET ratio, and parking ratio are normalized so that all indicators are within the range of [0,1]. ; in, and These represent the minimum and maximum values ​​of each ratio in the simulation data. These are the values ​​after normalization of each ratio.

[0030] The weights of the TTC ratio, PET ratio, and parking ratio are determined using the Analytic Hierarchy Process (AHP). The core of AHP lies in establishing a hierarchical structure model and having experts conduct pairwise comparisons of the importance of each ratio to ultimately calculate the numerical weights reflecting their relative importance. See the following formula: ; in, , and These are weights, and when added together they equal 1. RI is the comprehensive risk index.

[0031] For example, the weights are [0.4, 0.2, 0.4]. Each vehicle count scenario can yield an RI.

[0032] S150. Based on the weights obtained from the weighting and the cloud model driven by the two-factor entropy, a fuzzy comprehensive evaluation matrix is ​​established to map vehicle operation risk indicators to safety levels.

[0033] First, a set of safety rating criteria is set, which includes multiple safety levels, and the number of vehicles corresponding to each safety level is divided for the road to be tested.

[0034] For example, five safety levels are set, corresponding to five levels: safe, generally safe, critically safe, generally dangerous, and dangerous. The range of vehicle numbers corresponding to each level is shown in Table 1. Table 1 Safety Level Ranges

[0035] Note that Table 1 is only a preliminary division of the number of vehicles within the safety level intervals. In the fuzzy comprehensive evaluation method, the intervals corresponding to each safety level (Table 1) usually need to be pre-defined based on the characteristics of the research object. This application combines the operational characteristics of reinforced durable roads and the data obtained from the simulation process to reasonably segment the intervals. Based on the pre-defined safety level intervals, corresponding membership functions are constructed, and the membership value of each vehicle at each safety level is calculated to obtain the membership vector; then, based on the principle of maximum membership, the safety level to which the sample belongs is determined, that is, the interval to which it most likely corresponds is determined. That is, Table 1 is a static boundary, while the traffic flow in the simulation process is a dynamic random process, which may lead to different divisions of the safety intervals. Therefore, the fluctuations of real data in the simulation process are introduced into the membership calculation to obtain refined results.

[0036] Then, the cloud membership function is used to calculate the first membership vector of any number of vehicles belonging to each safety level.

[0037] This application characterizes the uncertain mapping relationship between qualitative concepts and quantitative data using expectation, entropy, and hyperentropy features. It also characterizes the coexistence of fuzziness and randomness between vehicle numbers and safety levels, introducing a normal cloud model to describe each safety level. First, define the feature parameters of the cloud model. For the i-th security level, construct a ternary feature parameter: ; in, Let be the expected value of the i-th safety level, representing the typical number of vehicles at that safety level (e.g., the median). The two-factor entropy of the i-th safety level reflects the ambiguity and allowable fluctuation range of the number of vehicles within the safety level range. Hyperentropy is used to characterize the uncertainty of entropy. It is the set of ternary feature parameters for the i-th security level.

[0038] The two-factor entropy for each security level is calculated using the following formula: ; in, It is a two-factor entropy of the security level. M L is the upper limit of the range of the number of vehicles corresponding to the safety level, and L is the lower limit of the range of the number of vehicles corresponding to the safety level. This represents the statistical standard deviation of vehicle operation risk indicators under the current vehicle count and operating conditions. The sample volatility coefficient, This is the interval width coefficient.

[0039] The following formula is used to calculate the first membership vector of any number of vehicles belonging to each safety level: ; ; in, To randomly generate entropy, It is the two-factor entropy of the i-th security level. For hyperentropy, Let be the expected value of the i-th security level. x It is the number of vehicles. yes x The first membership vector belonging to the i-th security level.

[0040] Then, a fuzzy comprehensive evaluation matrix R is constructed based on the first membership vector. For a specific number of vehicles on the road under test, the membership degree of each ratio relative to each safety level is calculated. A fuzzy comprehensive evaluation matrix R is constructed for this number of vehicles. Each row of the matrix corresponds to a membership vector of a ratio, and each column corresponds to a safety level, thus systematically mapping multi-dimensional micro-risk characteristics to a unified evaluation space.

[0041] S160. Based on the principle of maximum membership, determine the safety level of different vehicle operation scales using the fuzzy comprehensive evaluation matrix.

[0042] Weights obtained by weighting Fuzzy synthesis operation is performed with the fuzzy comprehensive evaluation matrix R to obtain the second membership vector of vehicle operation risk index (i.e. ratio) belonging to different safety levels.

[0043] Specifically, using the neighborhood smoothing fuzzy synthesis operator, the pre-set weights W and the fuzzy comprehensive evaluation matrix R are combined to obtain the comprehensive evaluation result vector under the specific number of vehicles. Considering the certain fuzzy transition relationship between safety levels, the smoothing effect of adjacent levels is introduced during fuzzy synthesis, and its calculation formula is as follows: ; in, The vector representing the comprehensive evaluation result is in the th order. The second membership degree at each security level; Indicates the first The weight of each vehicle operation risk indicator; Indicates the first The vehicle operation risk index is for the first Membership degree of each security level; This is the neighborhood smoothing coefficient, used to characterize the degree of influence between adjacent security levels; n This represents the total number of security levels.

[0044] Then, select the safety level corresponding to the largest membership degree from the second membership degree vector as the safety level to which the vehicle operation scale belongs.

[0045] For example, with For example, select the number of vehicles The simulation data is used for calculations, and the steps are as follows: The ratio vector for this vehicle count condition is calculated, with values ​​of [0.014103, 0.003867, 0.003378], representing the TTC ratio, PET ratio, and parking ratio, respectively. To characterize the random fluctuations in vehicle operating status, the statistical standard deviation of the vehicle operating risk indicators under the current vehicle count condition is first calculated: ; in, This refers to the i-th vehicle operation risk indicator; The average of the indicators; For the number of indicators; This represents the statistical standard deviation of vehicle operation risk indicators.

[0046] The calculation yielded: ; According to Table 1, the number of vehicles If the value falls within the "critical safety" interval [86, 92], the corresponding cloud model feature parameters are: expect: ; Two-factor entropy: ; Hyperentropy: ; Substituting the membership function into the cloud membership function, we can obtain its membership degree to the "critical security" level. : ; This leads to the first membership vector of the vehicle's operating conditions belonging to each safety level: ; Since the consistency of the operational risk indicators of each vehicle is relatively high, a fuzzy comprehensive evaluation matrix R is established to map the vehicle operational risk indicators to safety levels based on the weights obtained by weighting and the two-factor entropy-driven cloud model: ; Combined with the preset weight vector The second membership vector is obtained by performing fuzzy synthesis operation:

[0047] Based on the calculated vector The maximum value is Based on the principle of maximum membership, it is determined that in The road was at a "critical safety" level at the time.

[0048] S170. Identify the critical state in which the safety level changes, and determine the vehicle operation scale corresponding to the critical state as the maximum safe operating capacity of the road under test.

[0049] Repeat the above calculation steps, using 2 vehicles as the step size, to iterate through all vehicle count scenarios from 60 to 120 vehicles, and plot a line graph of the comprehensive hazard index (RI) versus the safety level. See [link / reference]. Figure 4 .

[0050] Specifically, the slope of the comprehensive hazard index RI as a function of the number of vehicles is calculated for each safety level; the target safety level with the largest slope change is selected; and the lower limit of the number of vehicles for the target safety level is taken as the maximum safe operating capacity of the road under test.

[0051] Figure 4 In the test, the Comprehensive Hazard Index (RI) showed a significant upward trend with the increase in the number of vehicles, and the slope changed the most within the "critical safety" range, indicating a rapid accumulation of risk. Combining expert evaluation and fuzzy calculation results, it was identified that when the number of vehicles exceeded 86, the status underwent a qualitative leap from "safe / generally safe" to "critical safety / dangerous." Therefore, this embodiment ultimately determined the maximum safe operating capacity of the reinforced durability road under the current test conditions to be 86 vehicles. This quantitative result provides clear data support for vehicle scheduling and risk warning at the test site.

[0052] This application overcomes the shortcomings of existing assessment methods that neglect micro-level operational risk characteristics and struggle to characterize the uncertainty of safety status. By constructing a multi-dimensional risk indicator system including TTC ratio, PET ratio, and parking ratio, it can accurately capture the micro-level conflict behavior characteristics under the high-intensity testing environment of automotive proving grounds. Based on this, a two-factor entropy-driven cloud model is introduced, combining safety level intervals with the fluctuation characteristics of risk indicators. By simultaneously considering the standard deviation of indicator samples and the width of the safety level interval, the entropy parameter of the cloud model is determined, enabling the evaluation model to more realistically reflect the randomness and fuzziness of traffic operation status. Furthermore, by constructing a neighborhood smoothing fuzzy synthesis operator, a smooth transition mechanism between adjacent safety levels is introduced during the comprehensive evaluation process, allowing the evaluation results to reflect the continuous changes in safety status, thereby improving the stability and rationality of safety level determination. Based on the above methods, this application can achieve scientific identification and forward-looking assessment of the operational safety capacity of proving ground roads without relying on historical accident data, and identify the key critical points where safety levels change abruptly, effectively improving the utilization efficiency of proving ground road resources while ensuring vehicle testing safety.

[0053] In terms of constructing cloud model feature parameters, this application proposes a dual-factor entropy-driven calculation method to improve the traditional method of determining entropy parameters based solely on interval width. This method introduces information on risk indicator fluctuations and level intervals to enhance the ability to characterize uncertainty. In the fuzzy comprehensive evaluation stage, in order to address the problem that traditional weighted synthesis operators do not consider the transition between levels, this application designs a neighborhood smoothing fuzzy synthesis operator, which introduces the influence between adjacent security levels in the evaluation process, thereby improving the stability and rationality of the results.

[0054] This application also provides an electronic device, see [link to relevant documentation] Figure 5 It includes at least one processor 301 and a memory 302 communicatively connected to at least one of the processors 301.

[0055] The memory 302 stores instructions that can be executed by at least one of the processors 301, which enable at least one of the processors 301 to perform the above-described micro-simulation-based method for assessing the road safety capacity of automotive test tracks, thus having at least the same advantages as the described method.

[0056] Optionally, the electronic device also includes interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The components are interconnected using different buses and can be mounted on a common motherboard or otherwise installed as needed. The processor can process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of a GUI (Graphical User Interface) on an external input / output device (such as a display device coupled to the interface). In other embodiments, multiple processors can be used with multiple memories, and / or multiple buses can be used with multiple memories, if desired. Similarly, multiple electronic devices (e.g., as a server array, a group of blade servers, or a multiprocessor system) can be connected, each providing some of the necessary operations.

[0057] The memory 302, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the micro-simulation-based automotive proving ground road safety capacity assessment method in this embodiment. The processor 301 executes various functional applications and data processing of the device by running the software programs, instructions, and modules stored in the memory 302, thereby realizing the aforementioned micro-simulation-based automotive proving ground road safety capacity assessment method.

[0058] The memory 302 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function; the data storage area may store data created based on terminal usage. Furthermore, the memory 302 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory, or other non-volatile solid-state storage device. In some instances, the memory 302 may further include memory remotely configured relative to the processor, which can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0059] The electronic device may also include an input device 303 and an output device 304. The processor 301, memory 302, input device 303, and output device 304 may be connected via a bus or other means.

[0060] Input device 303 can receive input digital or character information, and output device 304 may include a display device, an auxiliary lighting device (e.g., an LED), and a haptic feedback device (e.g., a vibration motor). The display device may include, but is not limited to, a liquid crystal display (LCD), a light-emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touchscreen.

[0061] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this application can be achieved, and this is not limited herein.

[0062] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for assessing the road safety capacity of an automotive proving ground based on microscopic simulation, characterized in that, include: Based on the map data and vehicle operation data of the road to be tested in the automotive test track, a microscopic traffic simulation model of the road to be tested is constructed. Set the initial value, termination value and increment step size of the vehicle operation scale, generate multiple sets of simulation conditions under different vehicle operation scales and perform operation simulation. In each set of simulation conditions, the micro-interaction features of the vehicles are monitored and extracted in real time, and multiple vehicle operation risk indicators are constructed based on the micro-interaction features of the vehicles and the equivalent hourly traffic flow. The multiple vehicle operation risk indicators are assigned weights, and the multiple vehicle operation risk indicators are weighted and summed according to the weights obtained to obtain a comprehensive risk index. Based on the weights obtained from the weighting and the cloud model driven by the two-factor entropy, a fuzzy comprehensive evaluation matrix is ​​established to map vehicle operation risk indicators to safety levels. Based on the principle of maximum membership, the safety level of different vehicle operation scales is determined according to the fuzzy comprehensive evaluation matrix. Identify the critical state where the safety level transitions, and determine the vehicle operation scale corresponding to the critical state as the maximum safe operating capacity of the road under test.

2. The method of claim 1, wherein, Based on map data and vehicle operation data of the road to be tested in the automotive proving ground, a microscopic traffic simulation model of the road to be tested is constructed, including: Acquire high-precision map data of the road to be tested and measured vehicle operation data; The measured vehicle operation data is cleaned, and the discrete vehicle speed data points are mapped to road segments on a high-precision map using a map matching algorithm. Based on the mapped vehicle speed data points and the operating rules of the road under test, a microscopic traffic simulation model of the road under test is constructed using microscopic traffic simulation software.

3. The method of claim 2, wherein, In each simulation scenario, the micro-interaction characteristics of vehicles are monitored and extracted in real time. Based on these micro-interaction characteristics and equivalent hourly traffic flow, multiple vehicle operation risk indicators are constructed, including: In each set of simulation conditions, the number of the first vehicle that has a potential collision risk event, the number of the second vehicle that has a merging conflict event, and the number of the third vehicle that has a parking interference event are monitored and extracted in real time. The TTC ratio is obtained based on the first number of vehicles and the equivalent hourly traffic flow. The PET ratio is obtained based on the second number of vehicles and the equivalent hourly traffic flow. The parking ratio is obtained based on the number of third vehicles and the equivalent hourly traffic flow.

4. The method according to claim 3, characterized in that, Weighting is applied to the aforementioned multiple vehicle operation risk indicators, including: The multiple vehicle operation risk indicators are weighted according to the analytic hierarchy process.

5. The method of claim 4, wherein, Based on the weights obtained through weighting and the two-factor entropy-driven cloud model, a fuzzy comprehensive evaluation matrix is ​​established to map vehicle operation risk indicators to safety levels, including: Set up a set of safety ratings that includes multiple safety levels, and divide the number of vehicles corresponding to each safety level for the road to be tested; Calculate the first membership vector of any number of vehicles belonging to each safety level using cloud membership functions; Construct a fuzzy comprehensive evaluation matrix based on the first membership vector.

6. The method of claim 5, wherein, Based on the principle of maximum membership, the safety level of different vehicle operation scales is determined according to the fuzzy comprehensive evaluation matrix, including: Fuzzy synthesis operation is performed on the weights obtained by weighting and the fuzzy comprehensive evaluation matrix to obtain the second membership vector of the vehicle operation risk index belonging to different safety levels; Select the safety level corresponding to the largest membership degree from the second membership vector as the safety level to which the vehicle operation scale belongs.

7. The method of claim 6, wherein, Identifying the critical state where the safety level transitions, and determining the vehicle operation scale corresponding to the critical state as the maximum safe operating capacity of the road under test, including: Calculate the slope of the overall hazard index as a function of the number of vehicles for each safety level; Select the target safety level with the largest slope change; The lower limit of the target safety level is taken as the maximum safe operating capacity of the road under test.

8. The method of claim 7, wherein, The cloud membership function is used to calculate the first membership vector of any number of vehicles belonging to each safety level, including: Define the characteristic parameters of the cloud membership function, including: expected value, two-factor entropy and hyperentropy; where the expected value is the typical number of vehicles at the safety level, the two-factor entropy is used to describe the fuzziness and allowable fluctuation range of the number of vehicles within the level range, and the hyperentropy is used to describe the uncertainty of the two-factor entropy. The first membership vector of any number of vehicles belonging to each safety level is calculated using the following formula: ； ； in, To randomly generate entropy, It is the two-factor entropy of the i-th security level. For hyperentropy, Let be the expected value of the i-th security level. x It is the number of vehicles. yes x The first membership vector belonging to the i-th security level.

9. The method of claim 8, wherein, The two-factor entropy for each security level is calculated using the following formula: ； in, It is a two-factor entropy of the security level. M It is the upper limit of the range of the number of vehicles corresponding to the safety level. L It is the lower limit of the range of vehicle numbers corresponding to the safety level. This represents the statistical standard deviation of vehicle operation risk indicators under the current vehicle count and operating conditions. The sample volatility coefficient, This is the interval width coefficient.

10. An electronic device, comprising: include: At least one processor, and a memory communicatively connected to at least one of the processors; The memory stores instructions that can be executed by at least one of the processors, which are executed by at least one of the processors to enable the at least one of the processors to perform the micro-simulation-based road safety capacity assessment method for automotive test tracks according to any one of claims 1-9.

Images