Method and device for judging cheating behavior in tail gas detection, medium and equipment
By analyzing the vehicle characteristics and exhaust gas collection pipeline pressure, and automatically judging the cheating behavior of exhaust gas detection, the shortcomings of manual observation in the existing technology are solved, and the accuracy and efficiency of detection are improved.
Patent Information
- Application Number
- CN202411104069.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-13
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the existing environmental protection inspection of motor vehicles, relying on manual observation and on-site monitoring video to determine that cheating behavior has insufficient clarity, poor timeliness and the inability to accurately judge part of the pipeline.
By determining the fitting model based on the vehicle characteristics of the target vehicle, obtaining and analyzing the sampling data at the engine speed, combining the pressure value in the exhaust gas collection pipeline, determining whether there is cheating, and using statistics and trend analysis to automatically determine the abnormality of the sampling data .
It realizes automatic, real-time and accurate judgment of cheating behaviors in exhaust gas detection, avoids the shortcomings of manual observation, improves detection efficiency and accuracy, and saves manual resources.
Smart Images

Figure CN119086814A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of motor vehicle testing, and in particular to a method and device, medium and equipment for judging cheating behavior in exhaust gas testing. Background Art
[0002] In the process of motor vehicle environmental protection testing, in order to make motor vehicles that do not meet the exhaust emission standards illegally pass the exhaust test, cheaters will try to use some cheating methods. For example: the probe connection of the exhaust gas detection instrument is not standardized and not in place, resulting in insufficient collection of exhaust emission gases; bending or stepping on the exhaust gas collection pipeline, so that the motor vehicle exhaust gas cannot fully reach the analyzer; deliberately extending the length of the exhaust gas collection pipeline, extending the time for the exhaust gas to reach the analyzer, and due to the increase in the internal volume of the pipeline, it has a dilution effect on the emission concentration; blocking the exhaust gas collection pipeline with foreign objects to prevent the exhaust gas from reaching the analyzer; causing the pipeline to leak, thereby diluting the emission concentration reaching the analyzer, etc.
[0003] At present, during the environmental protection inspection of motor vehicles, it is usually checked through the on-site video surveillance screen to see if the operator has cheated. However, this method of relying on on-site camera image observation and judgment has the following problems: the clarity of the image depends on the camera specifications and the on-site lighting conditions, and the clarity is difficult to guarantee; judging the connection status relies on observing the video with the human eye, which is laborious; the camera observes from a fixed position and cannot detect the situation of obstructed pipelines; after the video is saved, it relies on manual inspection, and the timeliness is too poor. Summary of the invention
[0004] In view of this, the present application provides a method and device, medium and equipment for judging cheating behavior in exhaust gas detection, which solves the problem caused by the existing method of judging whether cheating occurs by manually observing the on-site monitoring screen.
[0005] According to one aspect of the present application, a method for judging cheating behavior in exhaust gas detection is provided, comprising:
[0006] According to the vehicle characteristics of the target vehicle, the model of the target vehicle is determined as the target model, and in the preset fitting model, the fitting model corresponding to the target model is determined as the target fitting model;
[0007] When the engine speed reaches a preset minimum speed threshold, multiple groups of sampling data corresponding to the target vehicle are obtained, and the statistical value of each group of the sampling data is determined to be within the statistical value range corresponding to the target vehicle model, so as to obtain the statistical value judgment result corresponding to the sampling data;
[0008] Determine whether each group of the sampled data conforms to the data change trend corresponding to the target fitting model, and obtain a trend determination result corresponding to the sampled data;
[0009] Obtaining a sampling data judgment result corresponding to the target vehicle based on the statistical judgment results and trend judgment results corresponding to all the sampling data;
[0010] Reading the pressure value collected by the pressure sensor, if the pressure value is not less than the lower pressure limit corresponding to the target vehicle model, determining that the pressure judgment result is normal, otherwise determining that the pressure judgment result is abnormal, wherein the pressure sensor is arranged in the exhaust gas collection pipeline;
[0011] According to the sampling data judgment result and the pressure judgment result, it is judged whether the target vehicle has cheating behavior.
[0012] Optionally, respectively judging whether the statistics of each group of the sampled data are within the statistical range corresponding to the target vehicle model, and obtaining the statistical judgment result corresponding to the sampled data, comprises:
[0013] In each group of the sampling data, respectively calculate the statistics of the sampling data corresponding to each pollutant, wherein the statistics include mean, standard deviation and variance;
[0014] Obtaining a statistical range corresponding to the target vehicle model, wherein the statistical range includes a statistical lower limit corresponding to each of the pollutants;
[0015] If the statistics of the sampling data corresponding to each of the pollutants are not less than the lower limit of the statistics corresponding to the pollutants, the statistical judgment result corresponding to the sampling data is determined to be normal, otherwise the statistical judgment result is determined to be abnormal;
[0016] Determining whether each group of the sampled data conforms to the data change trend corresponding to the target fitting model, and obtaining the trend determination result corresponding to the sampled data, including:
[0017] Determine a sampling data fitting curve corresponding to each pollutant according to the sampling data corresponding to each pollutant;
[0018] If the sampling data fitting curves corresponding to each of the pollutants conform to the data change trend corresponding to the target fitting model, the trend judgment result corresponding to the sampling data is determined to be normal, otherwise the trend judgment result corresponding to the sampling data is determined to be abnormal.
[0019] Optionally, obtaining the sampled data judgment result corresponding to the target vehicle according to the statistical judgment results and trend judgment results corresponding to all the sampled data includes:
[0020] If at least one of the statistic judgment result and the trend judgment result corresponding to the sampling data is abnormal, determining that the sampling data is abnormal;
[0021] If all the sampled data are abnormal, it is determined that the sampled data judgment result corresponding to the target vehicle is abnormal.
[0022] Optionally, before determining the model of the target vehicle as the target model according to the vehicle characteristics of the target vehicle, the method further includes:
[0023] Acquire historical exhaust gas sampling data and historical vehicle characteristics corresponding to the historical exhaust gas sampling data, and pre-process the historical exhaust gas sampling data, wherein the vehicle characteristics corresponding to the historical exhaust gas sampling data include vehicle type, total mileage, emission standards, inspection time, factory time, and fuel specifications;
[0024] Determining the historical vehicle model corresponding to the historical exhaust gas sampling data according to the historical vehicle characteristics;
[0025] Obtain a sampling value range corresponding to each of the historical vehicle models, and remove historical exhaust gas sampling data that are not within the sampling value range from the historical exhaust gas sampling data corresponding to the historical vehicle models, and use the remaining historical exhaust gas sampling data to determine a fitting model corresponding to each of the historical vehicle models.
[0026] Optionally, before obtaining the statistical range corresponding to the sampled vehicle model, the method further includes:
[0027] The statistics of the historical exhaust gas sampling data corresponding to each of the historical vehicle models are calculated, and the statistical range corresponding to the historical vehicle models is determined according to the statistics of the historical exhaust gas sampling data.
[0028] Optionally, the distance between the pressure sensor and the connection point between the exhaust gas detector and the exhaust gas collection pipeline is less than a preset distance threshold;
[0029] The pressure sensor is arranged at the elbow of the exhaust gas collecting pipeline and is located on a side close to the exhaust gas detector.
[0030] Optionally, the data to be detected include non-methane hydrocarbon concentration, nitrogen oxide concentration and carbon monoxide concentration.
[0031] According to another aspect of the present application, a device for judging cheating behavior in exhaust gas detection is provided, the device comprising:
[0032] A vehicle type determination module is used to determine the vehicle type of the target vehicle as a target vehicle type according to the vehicle characteristics of the target vehicle, and determine the fitting model corresponding to the target vehicle type as a target fitting model in a preset fitting model;
[0033] A sampling data judgment module is used to obtain sampling data corresponding to a target vehicle when the engine speed reaches a preset minimum speed threshold, and to judge whether the statistics of the sampling data are within the statistical range corresponding to the target vehicle model, and obtain the statistical judgment results corresponding to the sampling data; and to judge whether each group of the sampling data conforms to the data change trend corresponding to the target fitting model, and obtain the trend judgment results corresponding to the sampling data; and, based on the statistical judgment results and trend judgment results corresponding to all the sampling data, obtain the sampling data judgment results corresponding to the target vehicle;
[0034] A pressure judgment module is used to read the pressure value collected by the pressure sensor. If the pressure value is not less than the lower pressure limit corresponding to the target vehicle model, the pressure judgment result is determined to be normal; otherwise, the pressure judgment result is determined to be abnormal, wherein the pressure sensor is arranged in the exhaust gas collection pipeline;
[0035] The cheating behavior judgment module is used to judge whether the target vehicle has cheating behavior according to the sampling data judgment result and the pressure judgment result.
[0036] Optionally, the sampling data judgment module is used to:
[0037] In each group of the sampling data, respectively calculate the statistics of the sampling data corresponding to each pollutant, wherein the statistics include mean, standard deviation and variance;
[0038] Obtaining a statistical range corresponding to the target vehicle model, wherein the statistical range includes a statistical lower limit corresponding to each of the pollutants;
[0039] If the statistics of the sampling data corresponding to each of the pollutants are not less than the lower limit of the statistics corresponding to the pollutants, the statistical judgment result corresponding to the sampling data is determined to be normal, otherwise the statistical judgment result is determined to be abnormal;
[0040] Determining whether each group of the sampled data conforms to the data change trend corresponding to the target fitting model, and obtaining the trend determination result corresponding to the sampled data, including:
[0041] Determine a sampling data fitting curve corresponding to each pollutant according to the sampling data corresponding to each pollutant;
[0042] If the sampling data fitting curves corresponding to each of the pollutants conform to the data change trend corresponding to the target fitting model, the trend judgment result corresponding to the sampling data is determined to be normal, otherwise the trend judgment result corresponding to the sampling data is determined to be abnormal.
[0043] Optionally, the sampling data judgment module is used to:
[0044] If at least one of the statistic judgment result and the trend judgment result corresponding to the sampling data is abnormal, determining that the sampling data is abnormal;
[0045] If all the sampled data are abnormal, it is determined that the sampled data corresponding to the target vehicle is abnormal.
[0046] Optionally, the device further includes an initialization module, configured to:
[0047] Acquire historical exhaust gas sampling data and historical vehicle characteristics corresponding to the historical exhaust gas sampling data, and pre-process the historical exhaust gas sampling data, wherein the vehicle characteristics corresponding to the historical exhaust gas sampling data include vehicle type, total mileage, emission standards, inspection time, factory time, and fuel specifications;
[0048] Determining the historical vehicle model corresponding to the historical exhaust gas sampling data according to the historical vehicle characteristics;
[0049] Obtain a sampling value range corresponding to each of the historical vehicle models, and remove historical exhaust gas sampling data that are not within the sampling value range from the historical exhaust gas sampling data corresponding to the historical vehicle models, and use the remaining historical exhaust gas sampling data to determine a fitting model corresponding to each of the historical vehicle models.
[0050] Optionally, the initialization module is used to:
[0051] The statistics of the historical exhaust gas sampling data corresponding to each of the historical vehicle models are calculated, and the statistical range corresponding to the historical vehicle models is determined according to the statistics of the historical exhaust gas sampling data.
[0052] Optionally, the distance between the pressure sensor and the connection point between the exhaust gas detector and the exhaust gas collection pipeline is less than a preset distance threshold;
[0053] The pressure sensor is arranged at the elbow of the exhaust gas collecting pipeline and is located on a side close to the exhaust gas detector.
[0054] Optionally, the data to be detected include non-methane hydrocarbon concentration, nitrogen oxide concentration and carbon monoxide concentration.
[0055] According to another aspect of the present application, a medium is provided, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the above-mentioned method for determining cheating behavior in exhaust gas detection is implemented.
[0056] According to another aspect of the present application, a device is provided, including a storage medium and a processor, wherein the storage medium stores a computer program and the processor implements the above-mentioned method for determining cheating behavior in exhaust gas detection when executing the computer program.
[0057] By means of the above technical solution, the present application comprehensively analyzes the sampling data generated by the target vehicle during the exhaust gas detection process and the real-time pressure in the exhaust gas collection pipeline, automatically analyzes from multiple angles, and obtains the final cheating behavior judgment result. Compared with the traditional method of manually observing the monitoring video, this embodiment is not affected by the on-site light and the camera installation position, and solves the defects of the existing method that the clarity is insufficient or the pipeline is blocked and the cheating behavior cannot be accurately judged. In addition, the method can use the server side to automatically perform real-time analysis without manual inspection, saving labor resources and improving timeliness.
[0058] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0059] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0060] Figure 1 A schematic diagram of a flow chart of a method for judging cheating behavior in exhaust gas detection provided in an embodiment of the present application is shown;
[0061] Figure 2 A flow chart of another method for judging cheating behavior in exhaust gas detection provided in an embodiment of the present application is shown;
[0062] Figure 3 A structural block diagram of a device for determining cheating behavior in exhaust gas detection provided in an embodiment of the present application is shown. DETAILED DESCRIPTION
[0063] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.
[0064] In this embodiment, a method for judging cheating behavior in exhaust gas detection is provided, such as Figure 1 As shown, the method includes:
[0065] Step 101, according to the vehicle characteristics of the target vehicle, determine the model of the target vehicle as the target model, and determine the fitting model corresponding to the target model as the target fitting model in the preset fitting models.
[0066] Step 102, when the engine speed reaches a preset minimum speed threshold, multiple groups of sampling data corresponding to the target vehicle are obtained, and the statistics of each group of sampling data are determined to be within the statistical range corresponding to the target vehicle model, so as to obtain the statistical judgment results corresponding to the sampling data.
[0067] Step 103, respectively judging whether each group of sampling data conforms to the data variation trend corresponding to the target fitting model, and obtaining the trend judgment result corresponding to the sampling data.
[0068] Step 104 , obtaining a sampled data judgment result corresponding to the target vehicle based on the statistical judgment results and trend judgment results corresponding to all the sampled data.
[0069] Step 105, read the pressure value collected by the pressure sensor. If the pressure value is not less than the lower pressure limit corresponding to the target vehicle model, the pressure judgment result is determined to be normal, otherwise the pressure judgment result is determined to be abnormal, wherein the pressure sensor is set in the exhaust gas collection pipeline.
[0070] Step 106, judging whether the target vehicle has cheating behavior according to the sampling data judgment result and the pressure judgment result.
[0071] The method for judging cheating behavior in exhaust gas detection provided in the embodiment of the present application is used to automatically judge whether cheating behavior exists in the exhaust gas detection process. Specifically, the embodiment detects cheating behavior from three perspectives: the range of sampling data, the trend of value change, and the internal pressure of the exhaust gas collection pipeline.
[0072] It is understandable that since different models may use different emission technologies, their emission control effects and performances may vary, and emission standards may also be different. Therefore, the target vehicle can be judged based on the model. In actual application, the model of the target vehicle can be judged based on vehicle characteristics, such as brand, model, technical specifications, VIN code, etc., which can all be used as vehicle characteristics.
[0073] After the model of the target vehicle is determined based on the vehicle characteristics, the fitting model and statistical range corresponding to the target model can be determined. The fitting model and statistical range are pre-set, and each model corresponds to its own fitting model and statistical range. Therefore, it is only necessary to determine the target model corresponding to the target vehicle, and the fitting model and statistical range corresponding to the target model can be screened out from the pre-set fitting model and statistical range.
[0074] In the specific judgment process, the sampling data corresponding to the target vehicle is first obtained, wherein the sampling data includes the real-time concentration of various pollutants, etc. It is understandable that in order to ensure the accuracy of the judgment, multiple sets of sampling data can be obtained and comprehensively analyzed to obtain the final cheating behavior judgment result. Among them, exhaust gas sampling can be performed at multiple time points under different stages and conditions of engine operation. For example, multiple samplings can be performed at the idling stage, acceleration stage, uniform speed stage, etc. to obtain multiple sets of different sampling data.
[0075] This embodiment analyzes whether there is cheating from three aspects: sampling data statistics, sampling data trends, and the internal pressure of the exhaust gas collection pipeline. First, the analysis is based on the statistics of the sampling data. Specifically, if cheating occurs during the exhaust target process, such as improper probe connection of the exhaust gas detection instrument or pipeline leakage, the value of the acquired sampling data will deviate from the normal value. Based on this, the statistics of the sampling data can be compared with the statistical range corresponding to the vehicle model to determine whether the value of the sampling data is abnormal, and obtain the statistical judgment result.
[0076] Secondly, judge whether there is cheating based on the changing trend of the sampled data. Specifically, in the exhaust gas target process, the sampled data at different stages have different changing trends. For example, in the idling stage, the engine of the vehicle is in an idling state, and its emission data is relatively unstable, and usually there will be periodic fluctuations; in the acceleration stage, the engine of the vehicle is in a high-load state, the emission data is relatively high, and the emission data usually shows a trend of rapid change; in the stable stage, the vehicle emission data is relatively stable, and the change trend is relatively mild. Based on this, the changing trend of the sampled data can be compared with the target fitting model corresponding to the vehicle model to determine whether the changing trend of the sampled data is abnormal and obtain the trend judgment result. For example, each data point can be compared with the previous moment or the adjacent data point, the change amplitude or difference value can be calculated, and the current data point can be judged based on the threshold or statistical method (such as the Z score method) to determine whether it is consistent with the trend. Data exceeding the threshold can be regarded as abnormal in the change trend.
[0077] By comprehensively analyzing the statistical judgment results and the trend judgment results, we can get the sampling data judgment results from the perspective of sampling data. For example, if the statistical judgment is normal and the trend judgment is normal, then the sampling data judgment can be considered normal.
[0078] After that, the internal pressure of the pipeline is used to determine whether there is cheating. Specifically, if the probe connection of the exhaust gas detection instrument is not standardized or the pipeline leaks, the pressure in the exhaust gas collection pipeline will be low. Based on this, a pressure sensor can be installed in the exhaust gas collection pipeline, and the pressure sensor can be used to collect the real-time pressure value inside the pipeline. According to the relationship between the pressure value and the pressure range corresponding to the target vehicle model, it is determined whether the pressure in the pipeline is abnormal, and the pressure judgment result can be obtained.
[0079] Finally, the sampling data judgment results and the pressure judgment results are comprehensively analyzed to determine whether the target vehicle has cheated. For example, if both the sampling data judgment results and the pressure judgment results are abnormal, it can be considered that cheating exists; if one of the sampling data judgment results and the pressure judgment results is abnormal, it can be considered that the behavior is suspicious, and further cheating analysis can be performed using surveillance video; if both the sampling data judgment results and the pressure judgment results are normal, it can be considered that there is no cheating.
[0080] This embodiment comprehensively analyzes the sampling data generated by the target vehicle during the exhaust gas detection process and the real-time pressure in the exhaust gas collection pipeline, automatically analyzes from multiple angles, and obtains the final cheating behavior judgment result. Compared with the traditional method of manually observing the monitoring video, this embodiment is not affected by the on-site light and the camera installation position, and solves the defects of the existing method that the clarity is insufficient or the pipeline is blocked and the cheating behavior cannot be accurately judged. In addition, this method can use the server side to automatically perform real-time analysis without manual inspection, saving labor resources and improving timeliness.
[0081] Further, as a refinement and expansion of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, another method for judging cheating behavior in exhaust gas detection is provided, such as Figure 2 As shown, the method comprises the following steps:
[0082] Step 201, obtaining historical exhaust gas sampling data and historical vehicle characteristics corresponding to the historical exhaust gas sampling data, and preprocessing the historical exhaust gas sampling data; according to the historical vehicle characteristics, determining the historical vehicle model corresponding to the historical exhaust gas sampling data.
[0083] In step 201, historical exhaust gas detection data of different motor vehicles are collected and preprocessed, and then the vehicle model corresponding to the historical sampling data is determined according to the vehicle characteristics, and then the historical exhaust gas detection data is classified, and the historical exhaust gas detection data generated by motor vehicles of the same model are classified into the same category. Specifically, during the preprocessing process, the data integrity and consistency can be checked, and possible missing data, outliers or duplicate data can be processed, and the timestamps can be formatted and unified to ensure the correctness and comparability of the time series.
[0084] Among them, the vehicle characteristics corresponding to the historical exhaust gas sampling data include vehicle type, total mileage, emission standards, target time, factory time and fuel specifications. The model of each motor vehicle can be determined based on these vehicle characteristics, and then in the subsequent judgment of the cheating behavior of the target vehicle, the historical exhaust gas sampling data generated by the motor vehicle of the same model can be used for analysis.
[0085] Step 202, obtain the sampling value range corresponding to each historical vehicle model, and remove the historical exhaust gas sampling data that is not within the sampling value range from the historical exhaust gas sampling data corresponding to the historical vehicle model, and use the remaining historical exhaust gas sampling data to determine the fitting model corresponding to each historical vehicle model.
[0086] In step 202, a target value range is set for each historical vehicle model with reference to the standards of different judgment methods, wherein the target value range includes the upper and lower limits of each pollutant. Thereafter, a range check is performed on the historical exhaust sampling data corresponding to the historical vehicle model. Data points that exceed the target value range may be abnormal values and can be marked or removed to avoid abnormal historical data from affecting the judgment of cheating behavior.
[0087] Step 203, calculating the statistics of the historical exhaust gas sampling data corresponding to each historical vehicle model, and determining the statistical range corresponding to the historical vehicle model according to the statistics of the historical exhaust gas sampling data.
[0088] In step 203, for each historical vehicle model, the corresponding statistics of each pollutant are calculated, such as mean, standard deviation, variance, etc., and then the corresponding statistical range is determined based on the calculated statistics. It can be understood that the larger the statistical range, the greater the probability that the statistics corresponding to the sampled data are within the statistical range, so the probability of misjudgment of cheating behavior is lower, but the probability of missed judgment is higher; conversely, the smaller the statistical range, the higher the probability of misjudgment of cheating behavior, but the probability of missed judgment is lower.
[0089] Step 204 , according to the vehicle characteristics of the target vehicle, the model of the target vehicle is determined as the target model, and in the preset fitting models, the fitting model corresponding to the target model is determined as the target fitting model.
[0090] Step 205, when the engine speed reaches a preset minimum speed threshold, multiple groups of sampling data corresponding to the target vehicle are obtained; in each group of sampling data, the statistics of the sampling data corresponding to each pollutant are calculated respectively; the statistical range corresponding to the target vehicle model is obtained; if the statistics of the sampling data corresponding to each pollutant are not less than the lower limit of the statistics corresponding to the pollutant, the statistical judgment result corresponding to the sampling data is determined to be normal, otherwise the statistical judgment result is determined to be abnormal.
[0091] In step 205, when the engine speed reaches the preset minimum speed threshold, the exhaust gas target is performed, and sampling data is collected at this time, and then the statistical amount of the sampling data is used to determine whether there is cheating behavior. Specifically, the sampling data includes real-time concentration data of various pollutants, such as non-methane hydrocarbon (HC) concentration, nitrogen oxide (NOx) concentration, and carbon monoxide (CO) concentration.
[0092] Among them, the statistics may include mean, standard deviation and variance, and may also include median, skewness, kurtosis, range, interquartile range, etc. The statistical range includes at least the lower limit of the statistics corresponding to each pollutant. For example, for the pollutant carbon monoxide, the statistical range of carbon monoxide concentration corresponding to the target vehicle model can be obtained, including the mean range of carbon monoxide concentration, the standard deviation range of carbon monoxide concentration, etc. The carbon monoxide concentration mean and the carbon monoxide concentration variance are calculated using the carbon monoxide concentration in the sampled data, and then the carbon monoxide concentration mean is compared with the carbon monoxide concentration mean range, and the carbon monoxide concentration variance is compared with the carbon monoxide concentration variance range, and the statistical value judgment result corresponding to the carbon monoxide pollutant in the group of sampled data is determined according to the comparison result. If the carbon monoxide concentration mean is not less than the lower limit of the carbon monoxide concentration mean, and the carbon monoxide concentration mean is not less than the lower limit of the carbon monoxide concentration mean, the statistical value judgment result corresponding to the carbon monoxide pollutant is considered normal, otherwise the statistical value judgment result corresponding to the carbon monoxide pollutant is considered abnormal. If the statistical value judgment results corresponding to all pollutants in this group of sampling data are normal, then the statistical value judgment results corresponding to this group of sampling data are considered normal; otherwise, the statistical value judgment results corresponding to this group of sampling data are considered abnormal.
[0093] Step 206, determining the sampling data fitting curve corresponding to the pollutant based on the sampling data corresponding to each pollutant; if the sampling data fitting curve corresponding to each pollutant conforms to the data change trend corresponding to the target fitting model, then determining that the trend judgment result corresponding to the sampling data is normal, otherwise determining that the trend judgment result corresponding to the sampling data is abnormal.
[0094] In step 206, it is determined whether there is cheating behavior based on the changing trend of the sampling data. Specifically, based on the sampling data corresponding to each pollutant, the sampling data fitting curve corresponding to the pollutant is determined, and then the fitting curve is used to analyze whether the changing trend of the sampling data corresponding to the pollutant is abnormal. Specifically, the sampling data fitting curve can be obtained by polynomial fitting, spline interpolation, and piecewise function fitting, and then the normal changing trend of each pollutant is determined according to the target fitting model corresponding to the target vehicle model. Finally, the actual changing trend obtained based on the sampling data is compared with the normal changing trend. According to the comparison result, it is determined whether the sampling data corresponding to the pollutant changes abnormally. If the changing trend of each pollutant is normal, the trend judgment result is determined to be normal, otherwise the trend judgment result is determined to be abnormal.
[0095] Step 207: If at least one of the statistic judgment result and the trend judgment result corresponding to the sampled data is abnormal, the sampled data is determined to be abnormal; if all the sampled data are abnormal, the sampled data judgment result corresponding to the target vehicle is determined to be abnormal.
[0096] In addition, statistical methods (such as box plots) can be used to detect anomalies in sampled data, or machine learning or artificial intelligence technology can be applied to use anomaly detection algorithms (such as isolated forests, outlier detection, etc.) for automated anomaly detection, and the automated anomaly detection results can be analyzed together with the statistical judgment results and trend judgment results to obtain the final sampled data judgment results to further improve the judgment accuracy. In practical applications, it is necessary to select appropriate modeling methods and mathematical tools based on different detection equipment and detection data from different periods.
[0097] Step 208, reading the pressure value collected by the pressure sensor, if the pressure value is not less than the lower pressure limit corresponding to the target vehicle model, then determining that the pressure judgment result is normal, otherwise determining that the pressure judgment result is abnormal.
[0098] Among them, the pressure sensor is arranged in the exhaust gas collection pipeline; the distance between the pressure sensor and the connection point between the exhaust gas detector and the exhaust gas collection pipeline is less than a preset distance threshold; the pressure sensor is arranged at the elbow of the exhaust gas collection pipeline and is located on the side close to the exhaust gas detector.
[0099] Specifically, the exhaust gas detector is connected to the exhaust gas collection pipeline, the exhaust gas reaches the exhaust gas detector through the exhaust gas collection pipeline, and the corresponding sampling data is obtained through the exhaust gas detector. The pressure sensor is arranged near the connection between the exhaust gas detector and the exhaust gas collection pipeline. If the pressure value detected by the pressure sensor is too small, it can be considered that the gas efficiency and flow rate reaching the exhaust gas detector are low, and thus cheating may exist. Furthermore, considering factors such as pipeline layout, pipe diameter and flow rate, the sensor can be placed at the elbow above or below the pipeline to ensure that the flow direction of the exhaust gas will not affect the measurement result of the pressure sensor. Specifically, the pressure sensor can be arranged at the elbow of the pipeline and close to one side of the exhaust gas detector. The exhaust gas flows in from the side away from the exhaust gas detector, passes through the elbow to reach the pressure sensor, so as to avoid the exhaust gas flow affecting the measurement accuracy of the pressure value.
[0100] Step 209, judging whether the target vehicle has cheating behavior according to the sampling data judgment result and the pressure judgment result.
[0101] This embodiment uses historical data of different models as a basis for judgment, and assists in pressure judgment and other methods to comprehensively analyze whether there is cheating during the exhaust gas detection process, thereby realizing automatic detection of cheating behavior without the need to manually view the on-site monitoring video, so it is more timely, not limited by manpower, and has a wider coverage. This embodiment analyzes whether the sampled data is abnormal from two aspects: the range of statistical values such as mean and variance, and the trend of the sampled data. The judgment method is simple and fast. On this basis, statistical methods or artificial intelligence methods can be used to perform further abnormal detection of sampled data, further improving the accuracy of judgment. In addition, this embodiment sets a pressure judgment mechanism, and specifically sets the pressure sensor at the elbow of the pipeline and away from the side of the exhaust gas tester to avoid the pressure value collection affected by gas flow, resulting in inaccurate pressure judgment results.
[0102] In another embodiment, a method for identifying cheating behavior is provided. Specifically, the method includes the following steps:
[0103] Step 1: Data collection and preprocessing
[0104] The information of the inspected motor vehicles, that is, the information of historical vehicles, is collected. The data table is expressed in the database model definition language DDL (Data Definition Language). The motor vehicle inspection record table includes the following fields: inspection business number, license plate number, license plate type, inspection unit name, vehicle brand, vehicle model, maximum design gross weight, engine model, engine displacement, drive type, vehicle factory date, inspection unit number, inspection date, inspector, inspection line number, final judgment result, inspection start time, inspection end time, inspection type, and inspection method.
[0105] The process data of the collected inspection is also the historical exhaust gas sampling data. The data table is expressed in the database model definition language DDL (Data Definition Language). Among them, the motor vehicle inspection process data table includes the following fields: inspection business number, total number of sampling points, HC real-time value (original concentration), NOx real-time value (original concentration), vehicle speed, engine speed, CO real-time value (original concentration).
[0106] Step 2: Feature Engineering
[0107] It is characterized by "vehicle brand, vehicle model, maximum gross mass, engine model, engine displacement, and drive type" to identify a type of motor vehicle model with specific specifications.
[0108] Step 3: Set a reasonable range for the pollutant emission data of vehicles with the same characteristics and store them in a new data table "Vehicle Emission Extreme Value Table".
[0109] Step 4: Perform a range check on the data of the new input test record
[0110] According to the characteristic fields in the new input data, find the extreme value records of motor vehicle exhaust emissions with the same characteristics, and determine whether the process data are all within the range. The result is represented by the variable Result. Among them, the new input data includes the vehicle characteristics of the target vehicle and the sampling data of the target vehicle.
[0111] Step 5: Determine whether the new input data is abnormal
[0112] According to step 4, if the range judgment results of the CO real-time values at each sampling point are all "less than the range", it is judged that the sampled exhaust gas has not fully reached the analyzer, and therefore it is considered that cheating has occurred.
[0113] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0114] Furthermore, as a specific implementation of the above-mentioned method for judging cheating behavior in exhaust gas detection, the embodiment of the present application provides a device for judging cheating behavior in exhaust gas detection, such as Figure 3 As shown, the device includes: a vehicle type determination module, a sampling data judgment module, a pressure judgment module and a cheating behavior judgment module.
[0115] A vehicle model determination module is used to determine the vehicle model of the target vehicle as the target vehicle model according to the vehicle characteristics of the target vehicle, and determine the fitting model corresponding to the target vehicle model as the target fitting model in the preset fitting model;
[0116] The sampling data judgment module is used to obtain the sampling data corresponding to the target vehicle when the engine speed reaches a preset minimum speed threshold, and judge whether the statistics of the sampling data are within the statistical range corresponding to the target vehicle model, and obtain the statistical judgment results corresponding to the sampling data; and respectively judge whether each group of sampling data conforms to the data change trend corresponding to the target fitting model, and obtain the trend judgment results corresponding to the sampling data; and, according to the statistical judgment results and trend judgment results corresponding to all the sampling data, obtain the sampling data judgment results corresponding to the target vehicle;
[0117] The pressure judgment module is used to read the pressure value collected by the pressure sensor. If the pressure value is not less than the lower pressure limit corresponding to the target vehicle model, the pressure judgment result is determined to be normal, otherwise the pressure judgment result is determined to be abnormal. The pressure sensor is set in the exhaust gas collection pipeline;
[0118] The cheating behavior judgment module is used to judge whether the target vehicle has cheating behavior based on the sampling data judgment result and the pressure judgment result.
[0119] In a specific application scenario, optionally, the sampling data judgment module is used to:
[0120] In each set of sampling data, the statistics of the sampling data corresponding to each pollutant are calculated respectively, where the statistics include mean, standard deviation and variance;
[0121] Obtain the statistical range corresponding to the target vehicle model, where the statistical range includes the statistical lower limit corresponding to each pollutant;
[0122] If the statistics of the sampling data corresponding to each pollutant are not less than the lower limit of the statistics corresponding to the pollutant, the statistical judgment result corresponding to the sampling data is determined to be normal, otherwise the statistical judgment result is determined to be abnormal;
[0123] Determine whether each set of sampling data conforms to the data change trend corresponding to the target fitting model, and obtain the trend judgment results corresponding to the sampling data, including:
[0124] According to the sampling data corresponding to each pollutant, a sampling data fitting curve corresponding to the pollutant is determined;
[0125] If the sampling data fitting curves corresponding to each pollutant are consistent with the data change trend corresponding to the target fitting model, the trend judgment result corresponding to the sampling data is determined to be normal, otherwise the trend judgment result corresponding to the sampling data is determined to be abnormal.
[0126] In a specific application scenario, optionally, the sampling data judgment module is used to:
[0127] If at least one of the statistical judgment result and the trend judgment result corresponding to the sampling data is abnormal, the sampling data is determined to be abnormal;
[0128] If all the sampled data are abnormal, the sampled data corresponding to the target vehicle is determined to be abnormal.
[0129] In a specific application scenario, optionally, the device further includes an initialization module, which is used to:
[0130] Obtaining historical exhaust gas sampling data and historical vehicle characteristics corresponding to the historical exhaust gas sampling data, and preprocessing the historical exhaust gas sampling data, wherein the vehicle characteristics corresponding to the historical exhaust gas sampling data include vehicle type, total mileage, emission standards, inspection time, factory time, and fuel specifications;
[0131] According to historical vehicle characteristics, determine the historical vehicle model corresponding to the historical exhaust sampling data;
[0132] The sampling value range corresponding to each historical vehicle model is obtained, and the historical exhaust gas sampling data that are not within the sampling value range are eliminated from the historical exhaust gas sampling data corresponding to the historical vehicle model, and the remaining historical exhaust gas sampling data are used to determine the fitting model corresponding to each historical vehicle model.
[0133] In a specific application scenario, optionally, the initialization module is used to:
[0134] The statistics of the historical exhaust sampling data corresponding to each historical vehicle model are calculated, and the statistical range corresponding to the historical vehicle model is determined based on the statistics of the historical exhaust sampling data.
[0135] In a specific application scenario, optionally, the distance between the pressure sensor and the connection point between the exhaust gas detector and the exhaust gas collection pipeline is less than a preset distance threshold;
[0136] The pressure sensor is arranged at the elbow of the exhaust gas collection pipeline and is located on the side close to the exhaust gas detector.
[0137] In a specific application scenario, optionally, the data to be detected includes non-methane hydrocarbon concentration, nitrogen oxide concentration, and carbon monoxide concentration.
[0138] Based on the above method, accordingly, an embodiment of the present application further provides a storage medium on which a computer program is stored, and when the program is executed by a processor, the above method for determining cheating behavior in exhaust gas detection is implemented.
[0139] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), and includes a number of instructions for enabling an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.
[0140] Based on the above Figure 1 , Figure 2 The method shown, and Figure 3 In order to achieve the above-mentioned purpose, the embodiment of the present application further provides a device, which can be a personal computer, a server, a network device, etc. The electronic device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 1 , Figure 2 The method for judging cheating in exhaust gas testing is shown.
[0141] Optionally, the electronic device may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a Bluetooth interface, a WI-FI interface), etc.
[0142] Those skilled in the art will appreciate that the electronic device structure provided in this embodiment does not limit the electronic device, and may include more or fewer components, or a combination of certain components, or different component arrangements.
[0143] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages and saves the hardware and software resources of the electronic device, and supports the operation of information processing programs and other software and / or programs. The network communication module is used to realize communication between the various controls inside the storage medium, and communication with other hardware and software in the physical device.
[0144] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform, or by hardware.
[0145] Those skilled in the art will appreciate that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the units or processes in the accompanying drawings are not necessarily necessary for implementing the present application. Those skilled in the art will appreciate that the units in the devices in the implementation scenario can be distributed in the devices of the implementation scenario according to the description of the implementation scenario, or can be changed accordingly and located in one or more devices different from the present implementation scenario. The units of the above-mentioned implementation scenarios can be combined into one unit, or can be further split into multiple sub-units.
[0146] The above serial numbers of this application are only for description and do not represent the advantages and disadvantages of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of this application, but this application is not limited to them, and any changes that can be thought of by technicians in this field should fall within the scope of protection of this application.
Claims
1. A method for judging cheating behavior in exhaust gas detection, characterized in that: The method comprises: According to the vehicle characteristics of the target vehicle, the model of the target vehicle is determined as the target model, and in the preset fitting model, the fitting model corresponding to the target model is determined as the target fitting model; When the engine speed reaches a preset minimum speed threshold, multiple groups of sampling data corresponding to the target vehicle are obtained, and the statistical value of each group of the sampling data is determined to be within the statistical value range corresponding to the target vehicle model, so as to obtain the statistical value judgment result corresponding to the sampling data; Determine whether each group of the sampled data conforms to the data change trend corresponding to the target fitting model, and obtain a trend determination result corresponding to the sampled data; Obtaining a sampling data judgment result corresponding to the target vehicle based on the statistical judgment results and trend judgment results corresponding to all the sampling data; Reading the pressure value collected by the pressure sensor, if the pressure value is not less than the lower pressure limit corresponding to the target vehicle model, determining that the pressure judgment result is normal, otherwise determining that the pressure judgment result is abnormal, wherein the pressure sensor is arranged in the exhaust gas collection pipeline; According to the sampling data judgment result and the pressure judgment result, it is judged whether the target vehicle has cheating behavior.
2. The method according to claim 1, characterized in that Determining whether the statistics of each group of the sampled data are within the statistical range corresponding to the target vehicle model, and obtaining the statistical judgment result corresponding to the sampled data, including: In each group of the sampling data, respectively calculate the statistics of the sampling data corresponding to each pollutant, wherein the statistics include mean, standard deviation and variance; Obtaining a statistical range corresponding to the target vehicle model, wherein the statistical range includes a statistical lower limit corresponding to each of the pollutants; If the statistics of the sampling data corresponding to each of the pollutants are not less than the lower limit of the statistics corresponding to the pollutants, the statistical judgment result corresponding to the sampling data is determined to be normal, otherwise the statistical judgment result is determined to be abnormal; Determining whether each group of the sampled data conforms to the data change trend corresponding to the target fitting model, and obtaining the trend determination result corresponding to the sampled data, including: Determine a sampling data fitting curve corresponding to each pollutant according to the sampling data corresponding to each pollutant; If the sampling data fitting curves corresponding to each of the pollutants conform to the data change trend corresponding to the target fitting model, the trend judgment result corresponding to the sampling data is determined to be normal, otherwise the trend judgment result corresponding to the sampling data is determined to be abnormal.
3. The method according to claim 1, characterized in that According to the statistical judgment results and trend judgment results corresponding to all the sampled data, the sampled data judgment results corresponding to the target vehicle are obtained, including: If at least one of the statistic judgment result and the trend judgment result corresponding to the sampling data is abnormal, determining that the sampling data is abnormal; If all the sampled data are abnormal, it is determined that the sampled data judgment result corresponding to the target vehicle is abnormal.
4. The method according to claim 2, characterized in that: Before determining the model of the target vehicle as the target model according to the vehicle characteristics of the target vehicle, the method further includes: Acquire historical exhaust gas sampling data and historical vehicle characteristics corresponding to the historical exhaust gas sampling data, and pre-process the historical exhaust gas sampling data, wherein the vehicle characteristics corresponding to the historical exhaust gas sampling data include vehicle type, total mileage, emission standards, inspection time, factory time, and fuel specifications; Determining the historical vehicle model corresponding to the historical exhaust gas sampling data according to the historical vehicle characteristics; Obtain a sampling value range corresponding to each of the historical vehicle models, and remove historical exhaust gas sampling data that are not within the sampling value range from the historical exhaust gas sampling data corresponding to the historical vehicle models, and use the remaining historical exhaust gas sampling data to determine a fitting model corresponding to each of the historical vehicle models.
5. The method according to claim 4, characterized in that Before obtaining the statistical range corresponding to the sampled vehicle model, the method further includes: The statistics of the historical exhaust gas sampling data corresponding to each of the historical vehicle models are calculated, and the statistical range corresponding to the historical vehicle models is determined according to the statistics of the historical exhaust gas sampling data.
6. The method according to claim 1, characterized in that The distance between the pressure sensor and the connection point between the exhaust gas detector and the exhaust gas collection pipeline is less than a preset distance threshold; The pressure sensor is arranged at the elbow of the exhaust gas collecting pipeline and is located on a side close to the exhaust gas detector.
7. The method according to claim 1, characterized in that The data to be detected include the concentration of non-methane hydrocarbons, the concentration of nitrogen oxides, and the concentration of carbon monoxide.
8. A device for judging cheating behavior in exhaust gas detection, characterized in that: The device comprises: A vehicle type determination module is used to determine the vehicle type of the target vehicle as a target vehicle type according to the vehicle characteristics of the target vehicle, and determine the fitting model corresponding to the target vehicle type as a target fitting model in a preset fitting model; A sampling data judgment module is used to obtain sampling data corresponding to a target vehicle when the engine speed reaches a preset minimum speed threshold, and to judge whether the statistics of the sampling data are within the statistical range corresponding to the target vehicle model, and obtain the statistical judgment results corresponding to the sampling data; and to judge whether each group of the sampling data conforms to the data change trend corresponding to the target fitting model, and obtain the trend judgment results corresponding to the sampling data; and, based on the statistical judgment results and trend judgment results corresponding to all the sampling data, obtain the sampling data judgment results corresponding to the target vehicle; A pressure judgment module is used to read the pressure value collected by the pressure sensor. If the pressure value is not less than the lower pressure limit corresponding to the target vehicle model, the pressure judgment result is determined to be normal; otherwise, the pressure judgment result is determined to be abnormal, wherein the pressure sensor is arranged in the exhaust gas collection pipeline; The cheating behavior judgment module is used to judge whether the target vehicle has cheating behavior according to the sampling data judgment result and the pressure judgment result.
9. A medium having a program or instruction stored thereon, characterized in that: When the program or instruction is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
10. A device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Anti-cheating detection station for automobile exhaust detection
CN106932539A
Tail gas detection cheating supervision system and method
CN108763966A
Cited By
Method, device and equipment for identifying annual inspection abnormity of heavy vehicle based on remote OBD monitoring and medium
CN122654926A
