Evaluation and quantification method, device and equipment for active safety configuration of new energy commercial vehicle based on accident cause analysis and storage medium

Abstract

The invention provides an evaluation and quantification method, device and equipment for active safety configuration of a new energy commercial vehicle based on accident cause analysis, and a storage medium. The evaluation and quantification method comprises the following steps: S1, obtaining traffic accident statistical data of the commercial vehicle; s2, extracting accident factor data, and constructing a structured accident data set; s3, processing the accident data set to obtain an accident data set based on accident cause classification; s4, various accident causes are decomposed to be matched with various active safety configurations on the new energy commercial vehicle to be evaluated; s5, determining an expected weight of each active security configuration; s6, determining the actual action score of each active safety configuration; and S7, carrying out weighted summation on the expected weight and the actual action score of each active safety configuration, and calculating an active safety score. According to the scheme, the active safety score of the new energy commercial vehicle can be obtained, and the score can be used as an actual superiority evaluation basis of the active safety configuration of the new energy commercial vehicle.

Description

Technical Field

[0001] This invention relates to the field of new energy vehicle safety technology, and in particular to a method, device, equipment and storage medium for evaluating and quantifying the active safety configuration of new energy commercial vehicles based on accident cause analysis. Background Technology

[0002] Currently, the insurance model for new energy commercial vehicles is out of sync with the market development stage. Significant pain points such as high incidence rates and high maintenance costs have led to low underwriting willingness among insurance companies and expensive premiums for users, hindering the promotion and application of new energy commercial vehicles. Therefore, it is necessary to evaluate the safety performance of new energy commercial vehicles.

[0003] Patent CN113390649A discloses a method, device, and storage medium for analyzing the performance of new energy vehicles. By adjusting the vehicle under test to operate under predetermined conditions, the method obtains the operating data of the vehicle under test, calculates the performance evaluation index of the vehicle under test based on the operating data, and generates a performance analysis report of the vehicle under test based on the performance evaluation index.

[0004] The above-mentioned evaluation method for vehicles only focuses on the performance of various functions of the vehicle, lacks an evaluation of the impact of each function on the actual traffic accident rate, and cannot well explain the actual superiority of the vehicle's active safety configuration. Summary of the Invention

[0005] Based on the problems existing in the prior art, the present invention aims to solve the technical problem that the performance analysis methods for new energy vehicles in the prior art only focus on the performance of various functions of the vehicle, lack the evaluation of the impact of various functions on the actual traffic accident rate, and cannot well explain the actual superiority of the vehicle's active safety configuration.

[0006] This invention provides a quantitative evaluation method for active safety configurations of new energy commercial vehicles based on accident cause analysis, which includes the following steps:

[0007] S1: Obtain traffic accident statistics for commercial vehicles;

[0008] S2: Extract accident factor data from the acquired traffic accident statistics and construct a structured accident dataset;

[0009] S3: Process the accident dataset to obtain an accident dataset based on accident cause classification;

[0010] S4: Decompose the various accident causes and match them with the active safety features on the new energy commercial vehicle to be evaluated;

[0011] S5: Based on the accident dataset classified according to accident causes in step S3 and expert experience, determine the expected weights of each active safety configuration.

[0012] S6: Determine the actual effectiveness score of each active safety feature;

[0013] S7: The expected weights of each active safety configuration obtained in step S5 and the actual performance scores of each active safety configuration obtained in step S6 are weighted and summed to calculate the active safety score of the new energy commercial vehicle.

[0014] Furthermore, the accident factor data extracted in step S2 includes accident type, time of occurrence, road type, driving speed, casualties, and cause of accident.

[0015] Furthermore, in step S3, the accident dataset is processed to obtain an accident dataset based on accident cause classification, including the following steps:

[0016] S31: Use the accident dataset to train a Bayesian network based on a scoring function to construct a topological map of traffic accident causes;

[0017] S32: Accident dataset based on various accident cause classifications in the topology map of traffic accident causes.

[0018] Furthermore, step S5 includes the following steps:

[0019] S51: Calculate the conditional probability distribution of various accident causes in step S3;

[0020] S52: Calculate the proportion of each accident cause after decomposition based on the conditional probability distribution of various accident causes obtained in step S51.

[0021] S53: Based on the theoretical role of each active safety configuration and expert experience, the theoretical weight of each active safety configuration is determined using the order relation analysis method;

[0022] S54: Combining the proportion of each active safety configuration in the various accident causes obtained in step S54 with the theoretical weight of each active safety configuration determined in step S53, the expected weight of each active safety configuration is calculated by weighted average.

[0023] Furthermore, in step S6, for active safety configurations with mature evaluation systems, a real-vehicle scenario test under closed roads is designed based on the function and theoretical effect of each active safety configuration. This test is used to evaluate the scores of each graded indicator of the active safety configuration, and then the functional score is calculated. This includes the following steps:

[0024] S61: Design real-vehicle scenario tests on closed roads to determine the function and theoretical effect of each active safety configuration, and obtain the weights and test scores of each graded indicator of each active safety configuration.

[0025] S62: Calculate the score for each graded indicator based on its weight, test score, and full score.

[0026] S63: The scores of each graded indicator of the active safety configuration are summed to obtain the actual effect score of the active safety configuration.

[0027] Furthermore, in step S6, for active safety configurations for which no evaluation system has been formed, the actual effectiveness score of the active safety configuration is determined by a fuzzy evaluation method.

[0028] This invention also provides an evaluation and quantification device for active safety configurations of new energy commercial vehicles based on accident cause analysis, comprising:

[0029] The data acquisition module is used to acquire traffic accident statistics for commercial vehicles;

[0030] The dataset construction module is used to extract accident factor data from the acquired traffic accident statistics, thereby constructing a structured accident dataset.

[0031] The processing module is used to process the accident dataset to obtain an accident dataset based on accident cause classification.

[0032] The decomposition module is used to break down various accident causes into their corresponding active safety features on the new energy commercial vehicle to be evaluated.

[0033] The weight calculation module is used to determine the expected weights of each active safety configuration based on the obtained accident dataset based on accident cause classification and expert experience.

[0034] The testing module is used to determine the actual effectiveness score of each active safety feature;

[0035] The scoring module is used to calculate the active safety score of the new energy commercial vehicle by weighting and summing the expected weights and actual performance scores of each active safety feature.

[0036] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the evaluation and quantification method for active safety configuration of new energy commercial vehicles based on accident cause analysis.

[0037] The present invention also provides a readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the aforementioned evaluation and quantification method for active safety configurations of new energy commercial vehicles based on accident cause analysis.

[0038] The beneficial effects of this invention are:

[0039] This invention provides a method, device, equipment, and storage medium for evaluating and quantifying the active safety configurations of new energy commercial vehicles based on accident cause analysis. It involves weighted summation of the expected weights of various active configurations on a new energy commercial vehicle, determined based on statistical data of commercial vehicle traffic accidents, and the actual effectiveness scores of each active safety configuration, thereby obtaining an active safety score for the new energy commercial vehicle. This score can be used to evaluate the accident rate of the new energy commercial vehicle and can serve as a basis for evaluating the actual superiority of its active safety configurations. This evaluation basis can be used to further improve the safety of new energy commercial vehicles and reduce maintenance costs through technological upgrades. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments or prior art, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a flowchart illustrating an evaluation and quantification method for active safety configurations of new energy commercial vehicles based on accident cause analysis, provided by an embodiment of the present invention. Detailed Implementation

[0042] The following descriptions of the embodiments are made with reference to the accompanying illustrations to illustrate specific embodiments in which the invention can be implemented.

[0043] This invention provides a quantitative evaluation method for active safety configurations of new energy commercial vehicles based on accident cause analysis, the structure of which is as follows: Figure 1 As shown, it includes the following steps:

[0044] Step 1: Obtain traffic accident statistics for commercial vehicles, extract accident factor data from them, and construct a structured accident dataset; the accident factor data includes accident type, time of occurrence, road type, driving speed, casualties, and causes of the accident;

[0045] Specifically, traffic accident statistics for commercial vehicles can be obtained from the accident information items in the National Vehicle Accident In-Depth Investigation System, based on the accident statistics database of commercial vehicles in provinces such as Jiangxi and Yunnan from 2016 to 2018. For example, consider a traffic accident that occurred at 10:33 AM in 2018 on an elevated road in a certain province or city, where a large truck rear-ended a commercial vehicle, resulting in one minor injury. The large truck was traveling at a speed of 70 km / h. The above information was discretized into segments to obtain the following data: accident type (0-longitudinal collision, 1-lateral scrape, 2-impact on curb facilities, 3-impact on pedestrians / cyclists), time of occurrence (0-morning, 1-afternoon, 2-night), road type (0-urban road, 1-rural road, 2-highway, 3-elevated road), driving speed (0-0~60km / h, 1-60~120km / h), injury / fatality (0-no injuries, 1-minor injury, 2-serious injury, 3-death), and cause of accident (0-insufficient braking, 1-understood steering, 2-blind spot, 3-driver violation of traffic rules). The resulting accident dataset is shown in Table 1.

[0046] Table 1 Accident Dataset

[0047]

[0048] Step 2: Use the accident dataset to train a Bayesian network based on the scoring function, construct a topological map of traffic accident causes, and calculate the conditional probability distribution of various accident causes in different accident types.

[0049] Construct a Bayesian network, and use maximum likelihood estimation to calculate the conditional probability for the discrete variable X and the parent variable Pa(X):

[0050]

[0051] Here, count(X,Pa(X)) is the number of times the discrete variable X and the parent variable Pa(X) appear simultaneously in the accident dataset; count(X′,Pa(X)) represents the total number of times the child variable X takes all possible values ​​X′ when the parent variable Pa(X) takes a specific value in the accident dataset.

[0052] For example, the causes of longitudinal collision accidents may include blind spots, delayed emergency braking, and understeer. A Bayesian network can be used to derive the probability distributions of various causes. For instance, for the discrete variable X - accident type - 0, the conditional probability of the parent variable - vehicle type 1 can be calculated.

[0053]

[0054] Similarly, the conditional probabilities of other parameters are calculated. For example, the proportion of underbraking in a longitudinal collision is 24%, i.e.

[0055]

[0056] The final result is shown in Table 2, which represents the conditional probability distribution of accident causes.

[0057] Table 2. Conditional Probability Distribution of Accident Causes

[0058]

[0059] The accident causation analysis method using Bayesian networks helps to objectively and accurately determine the probability distribution of accident causes compared to traditional manual classification.

[0060] Step 3: Based on the accident cause classification dataset obtained in Step S2 from the traffic accident cause topology map, decompose each accident cause into a matching set with the various active safety configurations on the new energy commercial vehicle to be evaluated (matching the decomposed accident causes with the various active safety configurations means that the active safety configurations on the new energy commercial vehicle, when implemented, can directly avoid the decomposed accident causes). Then, based on the conditional probability distribution of each accident cause obtained in Step S2, calculate the proportion of each decomposed accident cause. Finally, obtain the accident cause and active safety configuration correspondence table as shown in Table 3:

[0061] Table 3. Correspondence between accident causes and active safety features

[0062]

[0063] The sum of the proportional relationships in the table exceeds 1 because there are inclusion relationships between various accident types, and normalization will be performed at the end. For example, the main causes of forward collision accidents are blind spots, delayed emergency braking, and insufficient emergency steering. Active safety features such as automatic forward collision warning can help reduce accidents caused by blind spots, automatic emergency braking can help decelerate the vehicle, thus mitigating accidents caused by insufficient longitudinal braking, and automatic emergency steering can help mitigate accidents caused by insufficient emergency steering.

[0064] Step 4: Based on the theoretical role of each active safety configuration and expert experience, use the order relation analysis method to determine the theoretical weight of each active safety configuration;

[0065] Based on the subjective experience and suggestions of experts in relevant fields regarding the indicator system, the evaluation indicators are ranked according to their importance, i.e., x n-1 >x n The importance ratios of adjacent evaluation indicators were assigned values, and Table 4 shows the importance assignments determined based on expert experience and the analytic hierarchy process (AHP):

[0066] Table 4 assigns importance values ​​based on expert experience and the analytic hierarchy process.

[0067]

[0068] An order relation matrix can be constructed based on the importance ratio:

[0069]

[0070] Where, r ij Indicates active safety configuration x i and active safety configuration x j The importance ratio between them.

[0071] Based on the order relation matrix, the formula for calculating the weight vector of a certain active safety configuration can be obtained as follows:

[0072]

[0073] Weights reflect the relative importance of each evaluation factor in the evaluation process, and usually satisfy the following: The final weight vector is obtained by normalizing the weight vector:

[0074]

[0075] For example, for the new energy commercial vehicles equipped with the three active safety features (ESA, ELK, AEB), the evaluation index set is X = {x1, x2, x3}, where x1 represents ESA (Emergency Stop Assist); x2 represents ELK (Emergency Lane Keeping); and x3 represents AEB (Autonomous Emergency Braking).

[0076] Based on expert experience, the importance ranking is ESA > ELK > AEB. The relative importance ratios between adjacent indicators are set as follows:

[0077] r1 = 1.8 (ESK is extremely important than ELK)

[0078] r² = 1.4 (ELK is significantly more important than AEB)

[0079] Calculate the weight vector

[0080] Normalize the weights and sum the weight vectors ∑ω. i =1 + 1.4 + 2.52 = 4.92

[0081] The normalized theoretical weights are then:

[0082] ω1=2.52 / 4.92=0.512

[0083] ω² = 1.4 / 4.9² = 0.284

[0084] ω3=1 / 4.92=0.203

[0085] Step 5: Combining the proportions of each active safety configuration in the various accident causes obtained in Step S3 and the theoretical weights of each active safety configuration determined in Step S4, the expected weights of each active safety configuration are calculated by weighted average.

[0086] For example:

[0087] Weighting of active safety features in accident causes:

[0088] Emergency Steering Assist (ESA): 0.22

[0089] Emergency Lane Keeping (ELK): 0.22

[0090] Automatic Emergency Braking (AEB): 0.776

[0091] Theoretical weights of active safety configurations in theoretical analysis:

[0092] Emergency Steering Assist (ESA): 0.512

[0093] Emergency Lane Keeping (ELK): 0.284

[0094] Automatic Emergency Braking (AEB): 0.203

[0095] Expected weight:

[0096] Emergency Steering Assist (ESA): 0.5 * 0.22 + 0.5 * 0.512 = 0.366

[0097] Emergency Lane Keeping (ELK): 0.5 * 0.22 + 0.5 * 0.284 = 0.252

[0098] Automatic Emergency Braking (AEB): 0.5 * 0.203 + 0.5 * 0.203 = 0.490

[0099] Normalization:

[0100] Emergency Steering Assist (ESA): 0.366 / (0.366+0.252+0.490) = 0.330 Emergency Lane Keeping Assist (ELK): 0.252 / (0.366+0.252+0.490) = 0.227 Automatic Emergency Braking (AEB): 0.490 / (0.366+0.252+0.490) = 0.443

[0101] Step 6: Determine the actual effectiveness score of each active safety feature:

[0102] Specifically, for relatively mature active safety features (such as AEB), real-world scenario tests under closed roads can be designed based on the operational form and theoretical function of each active safety feature. These tests will assess the scores of each level of the active safety feature and then calculate a functional score. Table 5 illustrates the AEB level score data from real-world scenario tests.

[0103] Table 5. AEB rating index data under real-vehicle scenario testing.

[0104]

[0105]

[0106] After obtaining the weights and test scores of each AEB grade indicator, the score of each grade indicator is calculated by dividing the test value by the full score and multiplying by the weight. Then, the scores of each grade indicator of the active safety configuration are summed to obtain the actual effect score of the active safety configuration. Finally, the AEB score is 85.21 points.

[0107] It should be noted that for relatively mature functions (such as AEB), the function score can be calculated after testing using the grading indicators in Table 5. However, for newer functions (such as ESA), there is no readily available evaluation system, and the weight of each evaluation factor on the evaluation result is unclear. Therefore, a fuzzy evaluation method is adopted. The steps for determining the ESA function score using the fuzzy evaluation method are as follows:

[0108] Step 1: Construct a set of evaluation factors for proactive safety configuration.

[0109] In particular, for indicators that are difficult to quantify, secondary indicators are used for decomposition. For example, ① in the evaluation of mitigating blind spots in front of the vehicle, the evaluation indicators are decomposed into graded warning accuracy and false alarm rate; ② in the evaluation of the vehicle's emergency braking capability, the evaluation indicators are decomposed into the reduction of the target longitudinal vehicle speed and the lateral offset at different vehicle speeds to evaluate the vehicle's deceleration capability and braking lateral stability; ③ in the evaluation of the vehicle's emergency steering capability, the evaluation indicators are decomposed into the vehicle's response under the national standard test requirements.

[0110] Combining the above indicators at all levels, we obtain the evaluation indicator set U = {u1, u2, ..., un}, u i This represents the various graded indicators.

[0111] Step 2: Determine the comment set

[0112] The set of comments can be set as V = {v1, v2, v3, v4}, where v1 represents excellent (100 points), v2 represents good (75 points), v3 represents average (50 points), and v4 represents poor (0 points).

[0113] Taking ESA as an example, in this embodiment, a total of 5 testers were arranged to evaluate ESA according to the evaluation set V={v1,v2,v3,v4}. The evaluation results of the 5 testers on the secondary indicator "test vehicle set speed 50km / h" are shown in Table 6:

[0114] Table 6 Evaluation Results of ESA Grading Indicators

[0115]

[0116]

[0117] Step 3: Establish fuzzy membership functions

[0118] For each evaluation factor u i It is necessary to determine the membership function u. ij =Relu(i,j), which represents the evaluation factor u i The membership degree corresponds to the evaluation level vj (j=1,2,3,4). The membership function reflects the degree to which the evaluation factor belongs to different evaluation levels, and its value is in the range [0,1]. The grading threshold is set based on national standards and industry tests. For example, if the evaluation factor exceeds the first threshold, the influence value of the evaluation factor is set to the first value, such as 1. If the evaluation index exceeds the second threshold but does not exceed the first threshold, the influence value of the evaluation index is set to the second value, such as 0.

[0119] Step 4: Determine the weight of each evaluation factor.

[0120] The weight vector A = [0.125 0.125 0.25 0.25 0.125 0.125] corresponding to the weights of the secondary indicators of ESA, obtained by the analytic hierarchy process based on expert experience.

[0121] Step 5: Perform single-factor fuzzy evaluation.

[0122] Using the membership function, calculate u for each evaluation factor. i The membership degree of each evaluation result is used to obtain a single-factor fuzzy evaluation matrix R = [r ij ] n×m , where element r ij This represents the membership degree of the i-th evaluation factor to the j-th evaluation result.

[0123] Based on the evaluation results shown in Table 5, the distribution of various evaluation results for each secondary indicator is calculated. For example, in the first row of data, the proportion of evaluation results of "Excellent" is 2 / 5 = 0.4, the proportion of evaluation results of "Good" is 2 / 5 = 0.4, the proportion of evaluation results of "Average" is 1 / 5 = 0.2, and the proportion of evaluation results of "Poor" is 0. The distribution of various evaluation results for all secondary indicators is statistically analyzed, and a single-factor fuzzy evaluation matrix is ​​finally constructed.

[0124] Step 7, Comprehensive Evaluation

[0125]

[0126] Step 8: Make an evaluation decision

[0127] According to the principle of maximum membership, the highest membership is 0.48, and the corresponding evaluation set is v1: Excellent (100 points); therefore, the ESA function of this new energy commercial vehicle scores 100 points.

[0128] The above describes the scoring process for AEB and ESA. Similarly, the ELK score is 85.0 points. The final scores for the various active safety features of this new energy commercial vehicle are shown in Table 6.

[0129] Table 6: Scores of various active safety features for a certain new energy commercial vehicle

[0130]

[0131] Step 7: The expected weights of each active safety configuration obtained in step S5 and the actual performance scores of each active safety configuration obtained in step S6 are weighted and summed to calculate the active safety score of the new energy commercial vehicle.

[0132] Combining the weights of each active safety configuration obtained in step S5 with the scores of each active safety configuration in Table 6, the final score is calculated:

[0133] S=W*X=0.330*100+0.227*85+0.443*85.2=90.04

[0134] The final conclusion is that this model's active safety score is 90.04.

[0135] This solution also provides an evaluation and quantification device for active safety configurations of new energy commercial vehicles based on accident cause analysis. The device includes: a data acquisition module, a dataset construction module, a processing module, a decomposition module, a weight calculation module, a verification module, and a scoring module. The data acquisition module acquires traffic accident statistics for commercial vehicles. The dataset construction module extracts accident factor data from the acquired traffic accident statistics to construct a structured accident dataset. The processing module processes the accident dataset to obtain an accident dataset based on accident cause classification. The decomposition module decomposes various accident causes to match them with the active safety configurations on the new energy commercial vehicle to be evaluated. The weight calculation module determines the expected weights of each active safety configuration based on the obtained accident dataset based on accident cause classification and expert experience. The verification module determines the actual effectiveness score of each active safety configuration. The scoring module calculates the active safety score of the new energy commercial vehicle by weighted summation of the expected weights and actual effectiveness scores of each active safety configuration.

[0136] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the evaluation and quantification method for active safety configuration of new energy commercial vehicles based on accident cause analysis.

[0137] The present invention also provides a readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the aforementioned evaluation and quantification method for active safety configurations of new energy commercial vehicles based on accident cause analysis.

[0138] In summary, the present invention provides a method, device, equipment, and storage medium for evaluating and quantifying the active safety configurations of new energy commercial vehicles based on accident cause analysis. This method involves weighted summation of the expected weights of various active configurations on a new energy commercial vehicle, determined based on statistical data of commercial vehicle traffic accidents, and the actual effectiveness scores of each active safety configuration. This summation yields an active safety score for the new energy commercial vehicle. This score can be used to evaluate the accident rate of the new energy commercial vehicle and serve as a basis for evaluating the actual superiority of its active safety configurations. This evaluation basis can be used to further enhance the safety of new energy commercial vehicles and reduce maintenance costs through technological upgrades.

[0139] It should be noted that although the present invention has been disclosed above with specific embodiments, the above embodiments are not intended to limit the present invention. Those skilled in the art can make various modifications and refinements without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the scope defined in the claims.

Claims

1. A quantitative evaluation method for active safety configurations of new energy commercial vehicles based on accident cause analysis, characterized in that, Includes the following steps: S1: Obtain traffic accident statistics for commercial vehicles; S2: Extract accident factor data from the acquired traffic accident statistics and construct a structured accident dataset; S3: Process the accident dataset to obtain an accident dataset based on accident cause classification; S4: Decompose the various accident causes and match them with the active safety features on the new energy commercial vehicle to be evaluated; S5: Based on the accident dataset classified according to accident causes in step S3 and expert experience, determine the expected weights of each active safety configuration. S6: Determine the actual effectiveness score of each active safety feature; S7: The expected weights of each active safety configuration obtained in step S5 and the actual performance scores of each active safety configuration obtained in step S6 are weighted and summed to calculate the active safety score of the new energy commercial vehicle.

2. The evaluation and quantification method for active safety configuration of new energy commercial vehicles based on accident cause analysis according to claim 1, characterized in that, The accident factor data extracted in step S2 includes accident type, time of occurrence, road type, driving speed, casualties, and cause of accident.

3. The evaluation and quantification method for active safety configurations of new energy commercial vehicles based on accident cause analysis according to claim 1, characterized in that, In step S3, the accident dataset is processed to obtain an accident dataset based on accident cause classification, including the following steps: S31: Use the accident dataset to train a Bayesian network based on a scoring function to construct a topological map of traffic accident causes; S32: Accident dataset based on various accident cause classifications in the topology map of traffic accident causes.

4. The evaluation and quantification method for active safety configurations of new energy commercial vehicles based on accident cause analysis according to claim 1, characterized in that, Step S5 includes the following steps: S51: Calculate the conditional probability distribution of various accident causes in step S3; S52: Calculate the proportion of each accident cause after decomposition based on the conditional probability distribution of various accident causes obtained in step S51. S53: Based on the theoretical role of each active safety configuration and expert experience, the theoretical weight of each active safety configuration is determined using the order relation analysis method; S54: Combining the proportions of each active safety configuration in the various accident causes obtained in step S54 with the theoretical weights of each active safety configuration determined in step S53, the expected weights of each active safety configuration are calculated by weighted average.

5. The evaluation and quantification method for active safety configuration of new energy commercial vehicles based on accident cause analysis according to claim 1, characterized in that, In step S6, for active safety configurations with mature evaluation systems, a real-vehicle scenario test under closed roads is designed based on the function and theoretical effect of each active safety configuration. This test evaluates the scores of each graded indicator of the active safety configuration and then calculates the functional score. This includes the following steps: S61: Design real-vehicle scenario tests on closed roads to determine the function and theoretical effect of each active safety configuration, and obtain the weights and test scores of each graded indicator of each active safety configuration. S62: Calculate the score for each graded indicator based on its weight, test score, and full score. S63: The scores of each graded indicator of the active safety configuration are summed to obtain the actual effect score of the active safety configuration.

6. The evaluation and quantification method for active safety configuration of new energy commercial vehicles based on accident cause analysis according to claim 1, characterized in that, In step S6, for active safety configurations for which no evaluation system has been formed, the actual effectiveness score of the active safety configuration is determined by using a fuzzy evaluation method.

7. A quantitative evaluation device for active safety configurations of new energy commercial vehicles based on accident cause analysis, characterized in that, include: The data acquisition module is used to acquire traffic accident statistics for commercial vehicles; The dataset construction module is used to extract accident factor data from the acquired traffic accident statistics, thereby constructing a structured accident dataset. The processing module is used to process the accident dataset to obtain an accident dataset based on accident cause classification. The decomposition module is used to break down various accident causes into their corresponding active safety features on the new energy commercial vehicle to be evaluated. The weight calculation module is used to determine the expected weights of each active safety configuration based on the obtained accident dataset based on accident cause classification and expert experience. The testing module is used to determine the actual effectiveness score of each active safety feature; The scoring module is used to calculate the active safety score of the new energy commercial vehicle by weighting and summing the expected weights and actual performance scores of each active safety feature.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the evaluation and quantification method for active safety configuration of new energy commercial vehicles based on accident cause analysis as described in any one of claims 1 to 6.

9. A readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the evaluation and quantification method for active safety configuration of new energy commercial vehicles based on accident cause analysis as described in any one of claims 1 to 6.

Images