Method and device for obtaining high emission vehicle identification threshold based on vehicle following test

Abstract

The present application discloses a method and device for obtaining a high-emission vehicle identification threshold based on a vehicle-following test, and obtains a reliable high-emission vehicle identification threshold that can be used for high-emission vehicle identification. The obtained high-emission vehicle identification threshold provides technical support for identifying high-emission vehicles based on vehicle-following tests, making it possible to use vehicle-following tests to identify high-emission vehicles with post-treatment failures.

Description

Technical Field

[0001] The present application relates to but is not limited to environmental monitoring technology, and in particular to a threshold and device for obtaining high-emission vehicle identification information based on vehicle-following testing. Background Art

[0002] Motor vehicles, especially heavy vehicles, produce nitrogen oxides (NO X ) is an important source of emissions, which is harmful to human health. Control of heavy-duty vehicle NO X The emission is to achieve PM 2.5 The coordinated control of O3 is an important task to achieve the goal of "Beautiful China". The rapid and accurate identification of high-emission vehicles is an important prerequisite for evaluating their emissions and carrying out effective supervision.

[0003] Failure of aftertreatment devices is the main cause of high NO emission vehicles X One of the important reasons for the sharp increase in emissions, with the frequent occurrence of after-treatment failures, prioritizing the identification and supervision of high-emission vehicles caused by after-treatment failures can achieve more significant pollutant emission reduction benefits at a lower cost.

[0004] The large-sample vehicle following test on actual roads has the advantage of non-contact active measurement, which can reflect the actual post-processing status of the tested vehicle on the actual road. How to realize high-emission vehicle identification based on vehicle following test is a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present application provides a method and device for obtaining a high-emission vehicle identification threshold based on a vehicle-following test, which can provide technical support for identifying high-emission vehicles based on a vehicle-following test.

[0006] An embodiment of the present invention provides a method for obtaining a high-emission vehicle identification threshold based on a vehicle following test, and for each round of testing corresponding to a preset high-emission vehicle determination threshold, the method includes:

[0007] Carry out tail gas emission follow-up tests on a preset number of sample vehicles in two situations: normal and failed post-treatment states. According to the high-emission vehicle determination threshold corresponding to the test, count the number of samples determined as high-emission vehicles or ordinary vehicles in each test;

[0008] According to the sample size obtained by statistics, the accuracy and efficiency of identification are obtained; among them, the accuracy rate refers to the proportion of high-emission vehicles identified by the vehicle-following test that are actually in a failed post-treatment state, and the efficiency refers to the proportion of all sample vehicles with failed post-treatment that can be identified as high-emission vehicles by the vehicle-following test;

[0009] According to the obtained accuracy and efficiency, as well as the relative importance of accuracy and efficiency, the harmonic mean of accuracy and efficiency is calculated;

[0010] When the number of test rounds is reached, the high-emission vehicle identification threshold is determined according to the obtained harmonic mean and the preset high-emission vehicle determination threshold corresponding to each test round.

[0011] In an exemplary embodiment, determining the high-emission vehicle identification threshold according to the obtained harmonic mean and the preset high-emission vehicle determination threshold corresponding to each round of testing includes:

[0012] When the preset number of test rounds is reached, the harmonic mean F β-score The high-emission vehicle determination threshold corresponding to the maximum value is used as the determined high-emission vehicle identification threshold.

[0013] In an exemplary embodiment, the high emission vehicle identification threshold is NO X Decision threshold: X The threshold value is used to evaluate the NO emission of vehicles. X Emission factors.

[0014] In an exemplary embodiment, the calculating the harmonic mean of accuracy and efficiency includes:

[0015] According to the formula Calculate and obtain the harmonic mean;

[0016] Wherein, i represents the i-th round of testing, i is equal to 1 to the preset number of testing rounds; F β-score-i represents the harmonic mean calculated in the i-th round of testing; β represents the relative importance of accuracy and efficiency, and β is a pre-set value between 0 and 1; A i represents the accuracy of the i-th round of testing, R i Represents the efficiency obtained in the i-th round of testing.

[0017] In an exemplary embodiment, the sample size determined to be a high-emission vehicle or a normal vehicle includes:

[0018] The sample size of vehicles whose post-processing status is invalid are successfully determined as the high-emission vehicles, the sample size of vehicles whose post-processing status is normal are determined as the high-emission vehicles, the sample size of vehicles whose post-processing status is invalid are determined as the ordinary vehicles, and the sample size of vehicles whose post-processing status is normal are determined as the ordinary vehicles.

[0019] In an exemplary embodiment, obtaining the accuracy and efficiency of recognition includes:

[0020] Calculate the sum of the sample size of the vehicle whose post-processing status is invalid and successfully determined as a high-emission vehicle and the sample size of the vehicle whose post-processing status is normal and successfully determined as a high-emission vehicle; divide the sample size of the vehicle whose post-processing status is invalid and successfully determined as a high-emission vehicle by the calculated sum value to obtain the accuracy rate;

[0021] Calculate the sum of the sample size of vehicles whose post-processing status is invalid that are successfully determined as high-emission vehicles and the sample size of vehicles whose post-processing status is invalid that are determined as ordinary vehicles; divide the sample size of vehicles whose post-processing status is invalid that are successfully determined as high-emission vehicles by the calculated sum to obtain the efficiency.

[0022] In an exemplary embodiment, the high-emission vehicle identification threshold obtained by the method is applied to identifying high-emission vehicles based on a vehicle-following test.

[0023] An embodiment of the present application also provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute any of the above-mentioned methods for obtaining a high-emission vehicle identification threshold based on a vehicle-following test.

[0024] An embodiment of the present application further provides a device for obtaining a high-emission vehicle identification threshold based on a vehicle following test, comprising a memory and a processor, wherein the memory stores the following instructions executable by the processor: steps for executing any of the above-described methods for obtaining a high-emission vehicle identification threshold based on a vehicle following test.

[0025] The embodiment of the present application further provides a device for obtaining a high-emission vehicle identification threshold based on a vehicle following test, comprising: an acquisition module, a first calculation module, a second calculation module and a determination module; wherein,

[0026] An acquisition module is used to perform tail gas emission follow-up tests on a preset number of sample vehicles in each round of testing in two situations where the post-processing status is normal and failure, according to the number of test rounds corresponding to the preset high-emission vehicle determination threshold, and to count the number of samples determined as high-emission vehicles or ordinary vehicles in each round of testing;

[0027] The first calculation module is used to obtain the recognition accuracy and efficiency according to the sample size obtained by statistics in each round of testing; wherein the accuracy represents the proportion of high-emission vehicles that are actually in a failed post-treatment state among the high-emission vehicles identified by the vehicle-following test, and the efficiency represents the proportion of all sample vehicles with failed post-treatment that can be identified by the vehicle-following test;

[0028] The second calculation module is used to calculate the harmonic mean of the accuracy and efficiency according to the obtained accuracy and efficiency and the relative importance of the accuracy and efficiency in each round of testing;

[0029] The determination module is used to determine the high-emission vehicle identification threshold value when the number of test rounds is reached according to the obtained harmonic mean and the preset high-emission vehicle determination threshold value corresponding to each test round.

[0030] In an exemplary embodiment, the determination module is used to: when the number of test rounds is reached, use the high-emission vehicle determination threshold corresponding to when the harmonic mean reaches a maximum value as the determined high-emission vehicle identification threshold.

[0031] In an exemplary embodiment, the high emission vehicle identification threshold is NO X Decision threshold: X The threshold value is used to evaluate the NO emission of vehicles. X Emission factors.

[0032] Through the method for obtaining a high-emission vehicle identification threshold based on a vehicle-following test provided in the embodiment of the present application, a reliable high-emission vehicle identification threshold that can be used for high-emission vehicle identification is obtained. The obtained high-emission vehicle identification threshold provides technical support for identifying high-emission vehicles based on vehicle-following tests, making it possible to use vehicle-following tests to identify high-emission vehicles with post-treatment failures.

[0033] In one embodiment, the test results show that the harmonic mean of accuracy and efficiency F β-score The corresponding NO when reaching the maximum value X The judgment threshold, as the identification threshold for high-emission vehicles, can effectively realize the identification of high-emission vehicles based on vehicle following tests, and can effectively avoid missed judgments and misjudgments. It is of great significance to the emission reduction of heavy-duty vehicles and the improvement of air quality.

[0034] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings are used to provide further understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

[0036] Figure 1 A flow chart of a method for obtaining a high-emission vehicle identification threshold based on a vehicle following test in an embodiment of the present application;

[0037] FIG2( a ) is a waveform diagram showing changes in the accuracy and efficiency harmonic mean of five Chinese trucks in different test rounds according to an embodiment of the present application;

[0038] FIG2( b ) is a waveform diagram showing the changes in the accuracy rate and the harmonic mean of the efficiency of the six Chinese trucks in different test rounds according to the embodiment of the present application;

[0039] Figure 3 Schematic diagram of the composition structure of the method and device for obtaining the high-emission vehicle identification threshold based on the vehicle following test in the embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present application more clear, the embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other arbitrarily without conflict.

[0041] The steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions. Also, although a logical sequence is shown in the flowchart, in some cases, the steps shown or described can be performed in a sequence different from that shown here.

[0042] Large-sample vehicle-following tests on actual roads have the advantage of non-contact active measurement, which can reflect the actual post-processing status of the tested vehicle on the actual road. However, there is no implementation method for using vehicle-following tests to identify high-emission vehicles with post-processing failures in the related art. The embodiment of the present application aims to provide the feasibility of identifying high-emission vehicles with post-processing failures based on vehicle-following tests, and to provide important technical support for the use of vehicle-following tests for the identification and supervision of high-emission vehicles on actual roads, which is of great significance to heavy-duty vehicle emission reduction and air quality improvement.

[0043] Figure 1 Schematic diagram of the process of obtaining the high emission vehicle identification threshold based on the vehicle following test in the embodiment of the present application. Figure 1 As shown, it may include:

[0044] Step 100: For each round of testing corresponding to the preset high-emission vehicle determination threshold, a preset number of sample vehicles are subjected to a vehicle-following test of exhaust emissions in two conditions: normal and failed post-processing states, and the number of samples determined as high-emission vehicles or ordinary vehicles in each round of testing is counted.

[0045] In an exemplary embodiment, the number of test rounds and the number of sample vehicles can be determined according to the conditions of the actual test site. In one embodiment, under certain test site conditions, the sample vehicles may include a total of 7 heavy-duty vehicles such as National V (i.e. National V standard) and National VI (i.e. National VI standard), and a total of 564 vehicle follow-up tests are completed under the test site conditions. For these 564 vehicle data sets, each time a high-emission vehicle determination threshold is set, the 564 vehicle data sets can be subjected to a high-emission vehicle determination, i.e. a round of testing. For example: the number of test rounds can be set to 500 times. It should be noted that this is only an example and is not intended to limit the scope of protection of this application.

[0046] In an exemplary embodiment, according to the number of test rounds corresponding to the preset high-emission vehicle determination threshold, in each test round, according to the high-emission vehicle determination threshold corresponding to the test round, counting the number of samples determined as high-emission vehicles or ordinary vehicles in each test round may include:

[0047] The sample size of vehicles with failed post-treatment status being successfully judged as high-emission vehicles, the sample size of vehicles with normal post-treatment status being judged as high-emission vehicles, the sample size of vehicles with failed post-treatment status being judged as ordinary vehicles, and the sample size of vehicles with normal post-treatment status being judged as ordinary vehicles.

[0048] In an exemplary embodiment, the post-treatment system in the embodiment of the present application may include but is not limited to: a NO X Selective catalytic reduction (SCR) post-treatment for emission reduction, NO X Three-way catalyst (TWC) post-treatment for emission reduction, etc. In one embodiment, the way to disable the SCR post-treatment is to remove the urea injection electronic control of the SCR, and the way to disable the TWC post-treatment is to directly remove the post-treatment.

[0049] Table 1 shows the actual status of the after-treatment system and the sample situation of high-emission vehicle identification. In Table 1, TP represents the sample size of vehicles with after-treatment failure that are successfully identified as high-emission vehicles; FP represents the sample size of vehicles with normal after-treatment that are identified as high-emission vehicles; TN represents the sample size of vehicles with after-treatment failure that are identified as ordinary vehicles; FN represents the sample size of vehicles with normal after-treatment that are successfully identified as ordinary vehicles.

[0050]

[0051] Table 1

[0052] Step 101: Obtain recognition accuracy and efficiency based on the sample size obtained by statistics; wherein the accuracy represents the proportion of high-emission vehicles identified by the vehicle-following test whose post-processing status is actually failed, and the efficiency represents the proportion of all sample vehicles with post-processing failure that can be identified as high-emission vehicles by the vehicle-following test.

[0053] In an exemplary embodiment, according to a preset number of test rounds, in each test round, the sum of the number of samples of vehicles with a post-processing status of failure that are successfully determined as high-emission vehicles and the number of samples of vehicles with a post-processing status of normal that are determined as high-emission vehicles is calculated; the number of samples of vehicles with a post-processing status of failure that are successfully determined as high-emission vehicles is divided by the calculated sum value to obtain the accuracy rate A, as shown in formula (1). The sum of the number of samples of vehicles with a post-processing status of failure that are successfully determined as high-emission vehicles and the number of samples of vehicles with a post-processing status of failure that are determined as ordinary vehicles is calculated; the number of samples of vehicles with a post-processing status of failure that are successfully determined as high-emission vehicles is divided by the calculated sum value to obtain the efficiency R, as shown in formula (2).

[0054]

[0055] In formula (1) and formula (2), i represents the i-th round of testing, and i is equal to 1 to the preset number of test rounds.

[0056] Step 102: Calculate the harmonic mean of the accuracy and efficiency based on the obtained accuracy and efficiency, and the relative importance of the accuracy and efficiency.

[0057] In an exemplary embodiment, according to a preset number of test rounds, in each test round, the harmonic mean F β-score The calculation of is shown in formula (3):

[0058]

[0059] In formula (3), β is used to indicate the relative importance of accuracy and efficiency. β is any value between 0 and 1. The value of β can be set in advance according to actual needs. For example, if the accuracy and efficiency are considered to be equally important, β can be set to 1. For another example, if the efficiency is considered to be 1 / 5 of the accuracy, β can be set to 0.2.

[0060] In one embodiment, in order to reduce the possibility of misjudging a normal vehicle as a high-emission vehicle in actual applications, that is, based on the principle of avoiding missed judgments and misjudgment as much as possible, in one embodiment of the present application, accuracy is taken as the primary consideration and efficiency is taken as a secondary factor, and the value of β is selected as 0.2, which means that the importance of efficiency is considered to be 1 / 5 of the accuracy.

[0061] Step 103: When a preset number of test rounds is reached, a high-emission vehicle identification threshold is determined according to the obtained harmonic mean and a preset high-emission vehicle determination threshold corresponding to each test round.

[0062] In an exemplary embodiment, determining the high emission vehicle identification threshold according to the obtained harmonic mean and the preset high emission vehicle determination threshold corresponding to each round of testing may include:

[0063] When the preset number of test rounds is reached, the harmonic mean F β-score The high-emission vehicle determination threshold corresponding to the maximum value is used as the determined high-emission vehicle identification threshold.

[0064] In order to achieve a balance between the accuracy and efficiency of identifying high-emission vehicles, the high-emission vehicle identification threshold and the high-emission vehicle determination threshold in the embodiment of the present application can adopt NO suitable for high-emission vehicle identification and supervision. X Judgment threshold. X The threshold value is used to evaluate the NO emission of vehicles. X Emission factors.

[0065] Still taking the condition of a certain test site, the sample vehicles include 7 National Five and National Six heavy-duty vehicles, and the value of β is selected as 0.2. In each round of testing, a NO X The judgment threshold is obtained by measuring and counting the sample volume that is judged as a high-emission vehicle or a normal vehicle, calculating the recognition accuracy and efficiency, and then calculating the harmonic mean of the accuracy and efficiency. In this embodiment, the NO corresponding to the National V heavy-duty vehicle and the National VI heavy-duty vehicle is used. X The starting values ​​of the judgment thresholds are the regulatory limits for new cars, namely 2 grams per kilowatt-hour (g / kWh) and 0.46g / kWh, respectively, for NO X The end value of the judgment threshold is 14g / kWh, NO X Taking the adjustment step of the judgment threshold as 0.01 g / kWh as an example, FIG2(a) shows the different NO values ​​of a China V heavy-duty vehicle under different test rounds in the embodiment of the present application. X The waveform diagram of the change of the accuracy rate, efficiency and harmonic mean of the judgment threshold for high emission vehicle identification. Figure 2(b) shows the different NO values ​​of the China VI heavy-duty vehicle in different test rounds in the embodiment of the present application. X The waveform of the change of the judgment threshold on the accuracy and efficiency harmonic mean of high emission vehicle identification. In Figure 2(a), curve 211 is the value of the National V heavy-duty vehicle under different NO X The harmonic mean curve of recognition accuracy and efficiency under the judgment threshold, curve 212 is the national V heavy-duty vehicle under different NO X Recognition efficiency curve under judgment threshold, curve 213 is the national V heavy-duty vehicle under different NO XIn Figure 2(b), curve 221 is the recognition accuracy curve of National VI heavy-duty vehicles under different NO X The harmonic mean curve of recognition accuracy and efficiency under the judgment threshold. Curve 222 is the ... X Recognition efficiency curve under judgment threshold, curve 223 is the National VI heavy-duty vehicle under different NO X Recognition accuracy curve under the judgment threshold.

[0066] As shown in the test results of Figure 2(a) and Figure 2(b), when the National V and National VI heavy-duty vehicles NO X NO of post-treatment failure vehicle X When the judgment thresholds are 10.4g / kWh and 2.67g / kWh respectively (5.2 times and 5.8 times the corresponding new car limits respectively), the corresponding recognition accuracy of post-treatment failure high-emission vehicles is 96.8% and 98.6% respectively, and the recognition efficiency is 96.8% and 74.1% respectively. 0.2-score The test results show that F 0.2-score NO at maximum value X The optimal threshold is NO X The decision threshold, that is, F 0.2-score The corresponding NO when reaching the maximum value X The determination threshold, as a high-emission vehicle identification threshold in identifying high-emission vehicles based on a vehicle-following test, well realizes the identification of high-emission vehicles based on a vehicle-following test.

[0067] The embodiment of the present application explores the relationship between the high emission vehicle identification threshold and the identification accuracy and efficiency by setting different high emission vehicle identification thresholds, and makes good use of the harmonic mean of accuracy and efficiency F β-score Evaluated NO X Optimal NO for high emission vehicle identification X Decision threshold. Evaluate different NO by diagnostic method X The influence of emission threshold on the accuracy and efficiency of post-processing failed vehicle identification is studied, and a reliable high-emission vehicle identification threshold that can be used for high-emission vehicle identification is obtained.

[0068] The high emission vehicle identification threshold obtained by the method for obtaining the high emission vehicle identification threshold based on the vehicle following test provided in the embodiment of the present application provides a technical guarantee for identifying high emission vehicles based on the vehicle following test, making it possible to use the vehicle following test to identify high emission vehicles with post-treatment failure. In one embodiment, the test results show that the harmonic mean of accuracy and efficiency F β-score The corresponding NO when reaching the maximum value XThe judgment threshold, as the identification threshold for high-emission vehicles, can effectively realize the identification of high-emission vehicles based on vehicle following tests, and can effectively avoid missed judgments and misjudgments, which is of great significance to the emission reduction of heavy-duty vehicles and the improvement of air quality.

[0069] The high-emission vehicle identification threshold obtained based on the vehicle-following test in the embodiment of the present application can be applied to identifying high-emission vehicles based on the vehicle-following test.

[0070] The present application also provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute any of the above-mentioned methods for obtaining a high-emission vehicle identification threshold based on a vehicle-following test.

[0071] The present application further provides a device for obtaining a high-emission vehicle identification threshold based on a vehicle following test, comprising a memory and a processor, wherein the memory stores the following instructions executable by the processor: used to execute the steps of any of the above-mentioned methods for obtaining a high-emission vehicle identification threshold based on a vehicle following test.

[0072] Figure 3 Schematic diagram of the composition structure of the method and device for obtaining high-emission vehicle identification information based on vehicle following test in the embodiment of the present application, as shown in FIG. Figure 3 As shown, it may include: an acquisition module, a first calculation module, a second calculation module and a determination module, wherein:

[0073] An acquisition module is used to perform tail gas emission follow-up tests on a preset number of sample vehicles in each round of testing in two situations where the post-processing status is normal and failure, according to the number of test rounds corresponding to the preset high-emission vehicle determination threshold, and to count the number of samples determined as high-emission vehicles or ordinary vehicles in each round of testing;

[0074] The first calculation module is used to obtain the recognition accuracy and efficiency in each round of testing according to the sample size obtained by statistics; wherein the accuracy rate represents the proportion of high-emission vehicles identified by the vehicle-following test that are actually in a failed post-treatment state, and the efficiency represents the proportion of all sample vehicles with failed post-treatment that can be identified as high-emission vehicles by the vehicle-following test;

[0075] The second calculation module is used to calculate the harmonic mean of the accuracy and efficiency according to the obtained accuracy and efficiency and the relative importance of the accuracy and efficiency in each round of testing;

[0076] The determination module is used to determine the high-emission vehicle identification threshold according to the obtained harmonic mean and the preset high-emission vehicle determination threshold corresponding to each round of testing when a preset number of test rounds is reached.

[0077] In an exemplary embodiment, in each round of testing in the acquisition module, according to the high emission vehicle determination threshold corresponding to the round of testing, the number of samples determined as high emission vehicles or ordinary vehicles may include:

[0078] The sample size of vehicles with failed post-treatment status being successfully judged as high-emission vehicles, the sample size of vehicles with normal post-treatment status being judged as high-emission vehicles, the sample size of vehicles with failed post-treatment status being judged as ordinary vehicles, and the sample size of vehicles with normal post-treatment status being judged as ordinary vehicles.

[0079] In an exemplary embodiment, the first computing module may be used to:

[0080] Calculate the sum of the number of samples of vehicles with a post-processing status of invalid that are successfully identified as high-emission vehicles and the number of samples of vehicles with a post-processing status of normal that are identified as high-emission vehicles; divide the number of samples of vehicles with a post-processing status of invalid that are successfully identified as high-emission vehicles by the calculated sum to obtain the accuracy rate A;

[0081] Calculate the sum of the sample size of vehicles whose post-processing status is invalid that are successfully judged as high-emission vehicles and the sample size of vehicles whose post-processing status is invalid that are judged as ordinary vehicles; divide the sample size of vehicles whose post-processing status is invalid that are successfully judged as high-emission vehicles by the calculated sum to obtain the efficiency R.

[0082] In an exemplary embodiment, the second calculation module can be used to: set a value of the relative importance β representing the accuracy and efficiency; and calculate the harmonic mean according to the calculated accuracy A, efficiency R and the set relative importance β according to formula (3). In one embodiment, the value of β is 0.2.

[0083] In an exemplary embodiment, the determination module can be used to: when a preset number of test rounds is reached, the harmonic mean F β-score The high-emission vehicle determination threshold corresponding to the maximum value is used as the determined high-emission vehicle identification threshold.

[0084] In one exemplary embodiment, the method for evaluating NO X Emission factor of NO X The determination threshold is used as a high emission vehicle identification threshold.

[0085] The device for obtaining the high emission vehicle identification threshold based on the vehicle following test provided in the embodiment of the present application provides a technical guarantee for identifying high emission vehicles based on the vehicle following test, making it possible to use the vehicle following test to identify high emission vehicles with post-treatment failure. In one embodiment, the test results show that the harmonic mean of accuracy and efficiency F β-score The corresponding NO when reaching the maximum value XThe judgment threshold, as the identification threshold for high-emission vehicles, can effectively realize the identification of high-emission vehicles based on vehicle following tests, and can effectively avoid missed judgments and misjudgments. It is of great significance to the emission reduction of heavy-duty vehicles and the improvement of air quality.

[0086] Although the embodiments disclosed in this application are as above, the contents described are only embodiments adopted to facilitate understanding of this application and are not intended to limit this application. Any technician in the field to which this application belongs can make any modifications and changes in the form and details of implementation without departing from the spirit and scope disclosed in this application, but the scope of patent protection of this application shall still be based on the scope defined in the attached claims.

Claims

1. A method for obtaining a high emission vehicle identification threshold based on a vehicle following test, characterized in that: Each round of testing corresponding to the preset high emission vehicle determination threshold includes: Carry out tail gas emission follow-up tests on a preset number of sample vehicles in two situations: normal and failed post-treatment states. According to the high-emission vehicle determination threshold corresponding to the test, count the number of samples determined as high-emission vehicles or ordinary vehicles in each test; According to the sample size obtained by statistics, the accuracy and efficiency of identification are obtained; among them, the accuracy rate refers to the proportion of high-emission vehicles identified by the vehicle-following test that are actually in a failed post-treatment state, and the efficiency refers to the proportion of all sample vehicles with failed post-treatment that can be identified as high-emission vehicles by the vehicle-following test; According to the obtained accuracy and efficiency, as well as the relative importance of accuracy and efficiency, the harmonic mean of accuracy and efficiency is calculated; When the number of test rounds is reached, a high-emission vehicle identification threshold is determined according to the obtained harmonic mean and a preset high-emission vehicle determination threshold corresponding to each test round; The harmonic mean of the calculation accuracy and efficiency includes: According to the formula Calculate and obtain the harmonic mean; Where i represents the i-th round of testing, i is equal to 1 to the preset number of test rounds; F β-score-i represents the harmonic mean calculated in the i-th round of testing; β represents the relative importance of accuracy and efficiency, and β is a pre-set value between 0 and 1; A i represents the accuracy of the i-th round of testing, R i It represents the efficiency obtained in the i-th round of testing.

2. The method according to claim 1, wherein: The step of determining the high emission vehicle identification threshold according to the obtained harmonic mean and the preset high emission vehicle determination threshold corresponding to each round of testing includes: When the number of test rounds is reached, the harmonic mean F β-score The high-emission vehicle determination threshold corresponding to the maximum value is used as the determined high-emission vehicle identification threshold.

3. The method according to claim 2, wherein: The high emission vehicle identification threshold is nitrogen oxides NO X Decision threshold: X The threshold value is used to evaluate the nitrogen oxides (NO) emitted by vehicles. X Emission factors.

4. The method according to claim 1, wherein: The sample size determined to be high-emission vehicles or ordinary vehicles includes: The sample size of vehicles whose post-processing status is invalid are successfully determined as the high-emission vehicles, the sample size of vehicles whose post-processing status is normal are determined as the high-emission vehicles, the sample size of vehicles whose post-processing status is invalid are determined as the ordinary vehicles, and the sample size of vehicles whose post-processing status is normal are determined as the ordinary vehicles.

5. The method according to any one of claims 1 to 4, wherein: The high-emission vehicle identification threshold obtained by the method is applied to identifying high-emission vehicles based on a vehicle-following test.

6. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the method for obtaining a high-emission vehicle identification threshold based on a vehicle-following test as described in any one of claims 1 to 5.

7. A device for obtaining a high-emission vehicle identification threshold based on a vehicle following test, comprising a memory and a processor, wherein: The memory stores the following instructions executable by the processor: used to execute the steps of the method for obtaining a high-emission vehicle identification threshold based on a vehicle following test as described in any one of claims 1 to 5.

8. A device for obtaining a high emission vehicle identification threshold based on a vehicle following test, characterized in that: include: An acquisition module, a first calculation module, a second calculation module and a determination module; wherein, An acquisition module is used to perform tail gas emission follow-up tests on a preset number of sample vehicles in each round of testing in two situations where the post-processing status is normal and failure, according to the number of test rounds corresponding to the preset high-emission vehicle determination threshold, and to count the number of samples determined as high-emission vehicles or ordinary vehicles in each round of testing; The first calculation module is used to obtain the recognition accuracy and efficiency in each round of testing according to the sample size obtained by statistics; wherein the accuracy rate represents the proportion of high-emission vehicles identified by the vehicle-following test that are actually in a failed post-treatment state, and the efficiency represents the proportion of all sample vehicles with failed post-treatment that can be identified as high-emission vehicles by the vehicle-following test; The second calculation module is used to calculate the harmonic mean of accuracy and efficiency in each round of testing according to the obtained accuracy and efficiency and the relative importance of accuracy and efficiency; wherein, according to the formula The harmonic mean is calculated; wherein i represents the i-th round of testing, and i is equal to 1 to the preset number of test rounds; F β-score-i represents the harmonic mean calculated in the i-th round of testing; β represents the relative importance of accuracy and efficiency, and β is a pre-set value between 0 and 1; A i represents the accuracy of the i-th round of testing, R i represents the efficiency obtained from the i-th round of testing; The determination module is used to determine the high-emission vehicle identification threshold value when the number of test rounds is reached according to the obtained harmonic mean and the preset high-emission vehicle determination threshold value corresponding to each test round.

9. The device according to claim 8, wherein: The determination module is used to: when the number of test rounds is reached, use the high-emission vehicle determination threshold corresponding to when the harmonic mean reaches the maximum value as the determined high-emission vehicle identification threshold.

10. The device according to claim 9, wherein: The high emission vehicle identification threshold is NO X Decision threshold: X The threshold value is used to evaluate the NO emission of vehicles. X Emission factors.

Images