Vehicle emission conformity online evaluation method and device, storage medium and equipment

Abstract

The invention discloses a vehicle emission conformity online evaluation method and device, a storage medium, equipment and an evaluation method, and the method comprises the following steps: obtaining a remote monitoring data flow of a to-be-evaluated vehicle in a preset time period, carrying out the preprocessing of the remote monitoring data flow, and generating a valid data set; identifying and segmenting a plurality of independent driving cycles from the effective data set, and screening out the independent driving cycles with cold start characteristics and engine accumulated work not smaller than a preset cycle work threshold value as effective driving cycles; dividing the data of each effective driving cycle into a plurality of preset working condition partitions according to the operating characteristics; aiming at each preset working condition subarea, adopting a corresponding calculation model, and calculating a pollutant emission result of the target pollutant; and comparing the pollutant discharge result of the target pollutant in each subarea with a corresponding preset discharge limit value for judgment. By using the scheme of the invention, low-cost, large-scale and high-frequency emission supervision is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of environmental monitoring, and in particular to a vehicle emission compliance online evaluation method, device, storage medium and equipment. BACKGROUND

[0002] With the continuous growth of global vehicle ownership, pollutants such as nitrogen oxides (NOx) and particulate matter (PM) from motor vehicle exhaust emissions have become the main source of air pollution. For example, heavy-duty diesel vehicles account for more than 80% of total vehicle emissions, and their precise regulation is urgently needed. In order to truly reflect the actual emission level of vehicles, portable vehicle emission testing systems (PEMS) have been introduced into emission regulations in major global markets, which can directly obtain emission data under multiple road conditions and become the "gold standard" for regulatory compliance verification. However, PEMS testing is costly and complex to operate, and as a mandatory regulatory measure, its testing frequency is low and its coverage is limited, making it difficult to achieve large-scale, normalized full-life-cycle emission monitoring of a large number of in-use vehicles, and unable to meet the high-frequency emission screening and regulatory needs. At the same time, the development of Internet of Vehicles technology enables vehicles to collect and transmit multi-dimensional operating data such as location, engine operating conditions, and aftertreatment systems to remote monitoring platforms, providing a data basis for low-cost, efficient remote emission evaluation.

[0003] Although a large amount of remote monitoring data can be collected in real time, the current field still lacks an effective technical solution to convert these indirect emission level reflecting operating conditions and sensor data into accurate and quantitative vehicle emission evaluation results and to build a standardized online compliance evaluation process. SUMMARY

[0004] The present application aims to provide a vehicle emission compliance online evaluation method, device, storage medium and equipment, which utilizes vehicle remote monitoring data to establish an automated, standardized and high-precision online evaluation process, to solve the problem of high cost and low coverage of traditional emission testing, and to achieve low-cost, large-scale and high-frequency full-life-cycle emission compliance regulation of in-use vehicles.

[0005] To achieve the purpose of the present application, the technical solution provided by the present application is as follows: First aspect The present application provides a vehicle emission compliance online evaluation method, comprising the following steps: Step S1: Obtain a remote monitoring data stream of a vehicle to be evaluated within a preset time period, preprocess the remote monitoring data stream, and generate an effective data set; wherein the remote monitoring data stream at least includes: vehicle identification code VIN, data acquisition time, vehicle speed, engine speed, engine output torque, engine fuel flow, SCR downstream NOx sensor dew point state, SCR downstream NOx concentration, engine coolant temperature, cumulative mileage, engine rated power, atmospheric temperature, atmospheric pressure and altitude; Step S2: Identify and segment multiple independent driving cycles from the effective data set, and screen out independent driving cycles with cold start characteristics and engine cumulative work not less than a preset cycle work threshold as effective driving cycles; Step S3: Divide the data of each effective driving cycle into multiple preset working condition zones according to the operating characteristics; the preset working condition zones at least include: cold state operating zone, low power zone and medium-high power zone; the cold state operating zone is the period from the start time of the driving cycle to the time when the engine cumulative work reaches a preset reference value (such as 1 times WHTC equivalent cycle work); the low power zone and the medium-high power zone are determined by analyzing the relationship between the average engine power and the preset power percentage threshold (such as 6% of the engine rated power) through a moving time window; Step S4: For each preset working condition zone, a corresponding calculation model is used to calculate the pollutant emission result of the target pollutant; the target pollutant can include but is not limited to NOx, particulate matter mass (PM), ammonia (NH3), etc.

[0006] Step S5: Compare the pollutant emission results of each partition target pollutant with the corresponding preset emission limit value, when any pollutant emission result exceeds the corresponding preset emission limit value, it is determined that the emission of the target pollutant of the vehicle to be evaluated in this evaluation period is unqualified; if the pollutant emission results of all working condition zones do not exceed the corresponding preset emission limit value, it is determined to be qualified.

[0007] Further, in step S1, the preprocessing of the remote monitoring data stream includes validity cleaning, outlier processing and data repair; The validity cleaning is to eliminate data points in the remote monitoring data stream that do not meet the preset environmental boundary conditions (such as altitude, atmospheric temperature), and data points with obviously abnormal sensor readings (such as negative or far exceeding the physical upper limit of NOx concentration); The outlier processing is to identify and process outliers in key parameters (such as vehicle speed, speed, torque) using statistical algorithms (such as box plot method) or machine learning algorithms (such as isolated forest, DBSCAN clustering); The data repair is for invalid data of a post-processing system sensor (such as an NOx sensor) before reaching a working temperature (such as a dew point), and is estimated or filled according to a preset repair model to ensure data integrity.

[0008] Further, the step S2 specifically comprises: Step 2.1: identifying and segmenting multiple independent driving cycles from the effective data set, specifically: based on the time interval between the effective data points in the effective data set, the cumulative driving mileage, and the vehicle speed and engine speed data within a certain time window, multiple independent driving cycles are automatically identified and segmented; the starting time of each independent driving cycle is the time when the evaluation vehicle restarts driving (such as the vehicle speed and the speed start to increase from zero or a very low value) after a long time of not driving (such as the time interval is greater than 600 seconds, and the driving mileage changes less than 2km); Step 2.2: based on the identified and segmented independent driving cycles, independent driving cycles with cold start characteristics are screened out, the cold start characteristics being that the post-processing system does not reach the working temperature (such as the NOx sensor does not reach the dew point state) in the initial stage of the independent cycle, and the engine coolant temperature is lower than a first preset threshold (such as 40℃), and the engine exhaust temperature is lower than a second preset threshold (such as 100℃).

[0009] Step 2.3: based on the independent driving cycles with cold start characteristics screened out, the engine cumulative work of each independent driving cycle is calculated, and independent driving cycles with engine cumulative work not less than a preset cycle work threshold are screened out; the preset cycle work threshold can be associated with the equivalent cycle work based on the standard test cycle (such as WHTC) and the rated power of the vehicle engine, to ensure that the amount of data evaluated is representative enough The engine cumulative work is calculated as follows:

[0010] wherein, is the engine cumulative work, with the unit of kW·h; T is the engine torque, with the unit of N·m; n is the engine speed, with the unit of r / min; N is the total driving cycle time, with the unit of s; t is the data point time sequence number.

[0011] Further, in step S4: the pollutant emission result is a specific emission value or an emission rate; For the cold state running partition pollutant emission result, the following method is used for calculation: the total mass of the emitted pollutants in the partition is calculated, and then divided by the total cumulative engine power of the cold state running partition, to obtain the specific emission value in the unit of mass / power (mg / kWh); For the medium and high power partition pollutant emission result, the following method is used for calculation: the total mass of the emitted pollutants and the total cumulative engine power of all medium and high power partition windows are summed up, to calculate the total specific emission value (mg / kWh); For the low power partition pollutant emission result, the following method is used for calculation: the total mass of the emitted pollutants and the total time length of all low power partition windows are summed up, to calculate the emission rate in the unit of mass / time (mg / h).

[0012] The second aspect The application provides a vehicle emission conformity online evaluation device, which comprises the following modules: a data acquisition and preprocessing module, an effective driving cycle screening module, an operating condition partition module, a partition emission calculation module and a conformity evaluation module. The data acquisition and preprocessing module is used for acquiring a remote monitoring data stream of a vehicle to be evaluated in a preset time period, and preprocessing the remote monitoring data stream to generate an effective data set; wherein the remote monitoring data stream at least comprises a vehicle identification code VIN, a data acquisition time, a vehicle speed, an engine speed, an engine output torque, an engine fuel flow, a dew point state of an SCR downstream NOx sensor, an SCR downstream NOx concentration, an engine coolant temperature, a cumulative driving mileage, an engine rated power, an atmospheric temperature, an atmospheric pressure and an altitude. The effective driving cycle screening module is used for identifying and segmenting a plurality of independent driving cycles from the effective data set, and screening an independent driving cycle with a cold start feature and an engine cumulative power not less than a preset cycle power threshold as an effective driving cycle. The operating condition partition module is used for dividing the data of each effective driving cycle into a plurality of preset operating condition partitions according to operating characteristics; the preset operating condition partitions at least comprise a cold state running partition, a low power partition and a medium and high power partition; the cold state running partition is a time period from the start time of the driving cycle to the time when the engine cumulative power reaches a preset reference value; the low power partition and the medium and high power partition are determined by analyzing the relationship between the average engine power and a preset power percentage threshold through a moving time window. The partition emission calculation module is used for calculating the pollutant emission result of a target pollutant for each preset operating condition partition by using a corresponding calculation model. The conformity evaluation module is configured to compare the pollutant emission results of each partition target pollutant with the corresponding preset emission limit value, and determine that the emission of the target pollutant of the vehicle to be evaluated in the evaluation period is unqualified when any pollutant emission result exceeds the corresponding preset emission limit value. If the pollutant emission results of all the working condition partitions do not exceed the corresponding preset emission limit value, it is determined to be qualified.

[0013] Further, the preprocessing of the remote monitoring data stream includes validity cleaning, outlier processing and data repair. The validity cleaning is to remove data points that do not meet the preset environmental boundary conditions and sensor readings that are obviously abnormal in the remote monitoring data stream. The outlier processing is to identify and process outliers in the key parameters using a statistical algorithm or a machine learning algorithm. The data repair is to estimate or fill in invalid data of the sensor of the post-processing system before reaching the working temperature according to a preset repair model.

[0014] Further, the valid driving cycle screening module is specifically configured to perform the following steps: Step 2.1: identifying and segmenting multiple independent driving cycles from the valid data set, specifically: based on the time interval between the valid data points in the valid data set, the cumulative driving mileage and the vehicle speed and engine speed data within a specific time window, multiple independent driving cycles are automatically identified and segmented; the starting time of each independent driving cycle is the time when the vehicle to be evaluated restarts driving after a long period of non-driving; Step 2.2: based on the identified and segmented independent driving cycles, independent driving cycles with cold start characteristics are screened out, the cold start characteristics being that the post-processing system does not reach the working temperature in the initial stage of the independent cycle, and the engine coolant temperature is lower than a first preset threshold and the engine exhaust temperature is lower than a second preset threshold.

[0015] Step 2.3: based on the independent driving cycles with cold start characteristics screened out, the engine cumulative work of each independent driving cycle is calculated, and independent driving cycles with engine cumulative work not less than a preset cycle work threshold are screened out. The engine cumulative work is calculated as follows:

[0016] wherein, is the engine cumulative work, with the unit of kW·h; T is the engine torque, with the unit of N·m; n is the engine speed, with the unit of r / min; N is the total driving cycle time, with the unit of s; tTime series of data points.

[0017] Further, the pollutant emission result is a specific emission value or an emission rate; For the cold state operation partition pollutant emission result, the following method is used for calculation: the total mass of the emitted pollutants in the partition is calculated, and divided by the total cumulative engine work of the cold state operation partition, to obtain a specific emission value in mass / work unit; For the medium-high power partition pollutant emission result, the following method is used for calculation: the total mass of the emitted pollutants and the total cumulative engine work of all medium-high power partition windows are summarized, to calculate the total specific emission value; For the low power partition pollutant emission result, the following method is used for calculation: the total mass of the emitted pollutants and the total time length of all low power partition windows are summarized, to calculate an emission rate in mass / time unit.

[0018] The third aspect The application provides a storage medium, wherein at least one instruction, at least one program, a code set or an instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to realize the vehicle emission compliance online evaluation method.

[0019] The fourth aspect The application provides an electronic device (such as a server, a cloud platform and the like), which comprises a processor and a memory, wherein at least one instruction, at least one program, a code set or an instruction set is stored in the memory, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to realize the vehicle emission compliance online evaluation method.

[0020] Compared with the prior art, the application has the beneficial effects that: (1) Low-cost, large-scale and high-frequency emission supervision is realized: the application directly uses the remote monitoring terminal data of a vehicle which has been compulsorily installed, without additional installation of expensive PEMS equipment, so that the cost of single vehicle test is greatly reduced; (2) The accuracy and scientificity of emission evaluation are improved: the application proposes a systematic data processing and analysis process. Through fine data preprocessing, effective driving cycle screening, innovative working condition partition and different partition pollutant emission calculation method, the emission compliance of a vehicle in different working conditions is respectively evaluated, so that the evaluation distortion caused by simple average calculation of all data is avoided, and the accuracy and reliability of the remote online evaluation result are significantly improved.

[0021] (3) A standardized and automated online evaluation system has been constructed: This invention solidifies the complex emission data analysis process into a set of clear and repeatable algorithm steps, automating the entire process from data cleaning to final compliance determination, eliminating the differences and subjectivity of human operation. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the online vehicle emission compliance evaluation method provided in an embodiment of the present invention. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0024] Figure 1 This is a flowchart of an online evaluation method for vehicle emission compliance provided in an embodiment of the present invention.

[0025] The online vehicle emission compliance evaluation method provided in this embodiment specifically includes the following steps: Step S1: Data Acquisition and Preprocessing (1) Data Acquisition: Retrieve all remote monitoring data streams of the specified Vehicle Identification Number (VIN) within a preset time period from the remote monitoring data platform of the vehicle to be evaluated. The data stream is recorded in seconds and includes, but is not limited to, the following key fields: data acquisition time, vehicle speed (km / h), engine speed (r / min), engine output torque (N·m), engine fuel flow rate (kg / h), dew point status of the NOx sensor downstream of SCR, NOx concentration downstream of SCR (ppm), engine coolant temperature (°C), cumulative mileage (km), engine rated power (kW), atmospheric temperature (°C), atmospheric pressure (kPa), and altitude (m).

[0026] (2) Data preprocessing: a1. Environmental boundary condition cleaning: Traverse all data points and delete data that meets any of the following conditions: altitude > 2400m; atmospheric temperature < -7℃ or atmospheric temperature > 40℃.

[0027] b1. Sensor data cleaning: For NOx concentration data downstream of SCR, delete points with values ​​>3000ppm (considered as extreme sensor anomalies); uniformly correct all points with values ​​<0ppm to 0ppm.

[0028] c1. Key parameter outlier processing: For key dynamic data such as vehicle speed, engine speed, engine output torque, etc., the box plot method (IQR method) is preferably used for outlier identification.

[0029] For each parameter, calculate its upper quartile Q3 and lower quartile Q1, and determine the normal range as [Q1-1.5x(Q3-Q1), Q3+1.5x(Q3-Q1)]. Mark the identified outliers as missing. For all missing values (including original missing and marked outliers), use forward filling method, i.e. fill with the previous second valid data to ensure the continuity of the time series.

[0030] d1. NOx sensor dew point pre-data repair: Identify data with NOx sensor dew point status "not reaching dew point", and use a pre-trained Gradient Boosting Decision Tree (GBDT) model to predict and fill the NOx concentration data for these data segments. The training set of this model is valid data under the condition that the sensor "has reached dew point", and the features (input) include: engine speed, engine output torque, vehicle speed, engine coolant temperature, etc., and the label (output) is the NOx concentration data downstream of the SCR. Through this model, the NOx concentration when the sensor is not working properly can be estimated based on the real-time working condition of the vehicle.

[0031] Step S2: Effective driving cycle screening (1) Independent driving cycle identification and segmentation: Traverse the pre-processed valid data set to identify all independent driving cycle start times. A time point is determined as the start time of an independent driving cycle if it meets the following four conditions: Condition a2: The time difference between this time point and the previous valid data point is > 600 seconds; Condition b2: The cumulative mileage difference between this time point and the previous valid data point is < 2 km; Condition c2: All engine speed data within 5 seconds after this time point are < 1000 rpm; Condition d2: All vehicle speed data within 5 seconds after this time point are < 5 km / h.

[0032] Define the data from each identified independent driving cycle start time to the second before the next independent driving cycle start time as a complete driving cycle segment.

[0033] (2) Cold start feature screening: From all independent driving cycles, select cycles that meet all the following conditions as effective independent driving cycles with cold start feature: Condition a3: Within the first 10 seconds after the start of the cycle, the NOx sensor dew point status is "not reaching dew point"; Condition b3: Engine coolant temperature at the beginning of the cycle ≤ 40℃ Condition c3: SCR inlet exhaust gas temperature at the beginning of the cycle < 100℃.

[0034] (3) Effective work screening: First, calculate the total cumulative work of each screened effective independent driving cycle with cold start characteristics W total The calculation method of the total cumulative work is:

[0035] Among them, W total Driving cycle engine cumulative work, kW·h; T Engine torque, N·m; n Engine speed, r / min; N Total driving cycle time, s; t Data point time sequence number; Second, calculate the WHTC cycle equivalent work of the driving cycle engine W WHTC This value is usually a known parameter or calculated according to the engine power, and the specific calculation method is:

[0036] Among them, W WHTC WHTC equivalent cycle work, kW·h; P rating Engine rated power, kW; f is the conversion coefficient; Then, calculate the preset cycle work threshold W threshold The specific calculation method is:

[0037] In this embodiment, m =4: W threshold =4× W WHTC Finally, only those W total ≥ W threshold Independent driving cycles are retained as the final effective driving cycles for emission evaluation.

[0038] Step S3: Operating condition partitioning For each screened effective driving cycle data, the following partitioning is performed: (1) Cold operation zone division: From the start time of the independent driving cycle, the data is intercepted until the cumulative work of the engine first reaches 1 x W WHTC The time. This data is divided into a cold operation zone.

[0039] (2) Low-power zone and medium-high-power zone division: all remaining data after the cold operation zone is taken as the data to be divided.

[0040] Set a moving time window with a width of 300 seconds, starting from the 1st second of the data to be divided, and slide it back second by second. For each window, calculate the average engine power P window in the window. Set the power threshold P threshold = 6% x P rating If P window > P threshold , all data points in the 300-second window are classified as medium-high-power zones. If P window ≤ P threshold , all data points in the 300-second window are classified as low-power zones.

[0041] Step S4: Zone emission calculation (1) Instantaneous mass emission calculation: First, the NOx concentration (ppm) needs to be converted to the instantaneous mass emission rate m NOx (mg / s). This requires combining the instantaneous exhaust mass flow G exh (kg / s) estimated by a model (such as calculation based on fuel flow and air-fuel ratio), and using the following formula: m NOx = NOx concentration x G exh x k NOx where k NOx is the unit conversion factor.

[0042] (2) Zone-specific emission calculation: a4. Cold operation zone NOx specific emission value is calculated as follows:

[0043] where, The total cumulative work of the cold-running zone (i.e., 1× W WHTC ); Duration of cold-state operation of partitioned data, in seconds; for t Instantaneous emission of pollutants at any given time, mg / s; Δ t The data collection interval is s.

[0044] b4. NOx emissions ratio in medium- and high-power zones:

[0045] in, The emission values ​​for pollutants in the medium-to-high power zone are expressed in mg / kW·h. na For the first na Number of moving windows; m na It is the total NOx emission mass of the nath non-idle window; Na This represents the total number of windows moved between the medium and high power zones. W na It is the first na The cumulative work done in each non-idle window, kW·h, is summed and iterated through all non-idle windows. c4. NOx emission rate in low-power zones:

[0046] in, For low-energy-density emissions of pollutants, mg / h; nb For the first nb Number of moving windows; Nb This represents the total number of windows moved in the low-power partition. For the first nb Pollutant emissions per mobile window, mg; Step S5: Compliance Assessment The calculated emission results for each zone are compared with the zoning limits stipulated by regulations, and the vehicle's emission compliance is determined based on the comparison results. If any of the three comparisons results in "exceeding the limit," the vehicle's NOx emissions for the current evaluation period are deemed non-compliant. Only when the emission results for all three zones meet the limit requirements is the vehicle deemed compliant.

[0047] Through the above specific implementation methods, the present invention can automatically and in a standardized manner complete the online evaluation of vehicle emissions.

[0048] Corresponding to the above method, the embodiment also provides a vehicle emission conformity online evaluation device, comprising the following modules: a data acquisition and preprocessing module, an effective driving cycle screening module, an operating condition partition module, a partition emission calculation module, and a conformity evaluation module. The data acquisition and preprocessing module is configured to acquire a remote monitoring data stream of a vehicle to be evaluated within a preset time period, pre-process the remote monitoring data stream, and generate an effective data set; wherein the remote monitoring data stream at least comprises a vehicle identification code VIN, a data acquisition time, a vehicle speed, an engine speed, an engine output torque, an engine fuel flow, a dew point state of a NOx sensor downstream of an SCR, a NOx concentration downstream of the SCR, an engine coolant temperature, a cumulative mileage, an engine rated power, an atmospheric temperature, an atmospheric pressure, and an altitude. The effective driving cycle screening module is configured to identify and segment a plurality of independent driving cycles from the effective data set, and screen an independent driving cycle with a cold start feature and an engine cumulative work not less than a preset cycle work threshold as an effective driving cycle. The operating condition partition module is configured to divide data of each effective driving cycle into a plurality of preset condition partitions according to operating characteristics; the preset condition partitions at least comprise a cold operating partition, a low work partition, and a medium-high work partition; the cold operating partition is a time period from a starting time of the driving cycle to a time when the engine cumulative work reaches a preset reference value; the low work partition and the medium-high work partition are determined by moving a time window to analyze a relationship between an average engine power and a preset power percentage threshold. The partition emission calculation module is configured to calculate a target pollutant emission result by using a corresponding calculation model for each preset condition partition. The conformity evaluation module is configured to compare the target pollutant emission result of each condition partition with a corresponding preset emission limit value, and determine that the emission of the target pollutant of the vehicle to be evaluated in this evaluation period is unqualified when any pollutant emission result exceeds the corresponding preset emission limit value; if the pollutant emission results of all condition partitions do not exceed the corresponding preset emission limit values, it is determined to be qualified.

[0049] The embodiment also provides a storage medium, wherein the storage medium stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the vehicle emission conformity online evaluation method.

[0050] It is noted that the computer-readable storage medium can take any combination of one or more computer-readable media. The computer-readable media can be a computer-readable storage medium or a computer-readable signal medium. The computer-readable storage medium can include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the above. More specific examples (a non-exhaustive list) of the computer-readable storage medium include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0051] The embodiments also provide an electronic device including a processor and a memory, the memory storing at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by the processor to implement the vehicle emission conformity online evaluation method It is noted that the processor can be a central processing unit (CPU) or other forms of processing units having data processing and / or instruction execution capabilities, and can control other components in the electronic device to perform desired functions.

[0052] The memory can include one or more computer program products, which can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory can include, for example, random access memory (RAM), cache memory, and / or the like. The non-volatile memory can include, for example, read-only memory (ROM), hard disk, flash memory, and / or the like. One or more computer program instructions can be stored on the computer-readable storage medium, and the processor can run the program instructions to implement the vehicle emission remote evaluation method of any embodiment of the application described above and / or other desired functions. Various contents such as initial extrinsic parameters, threshold values, and the like can also be stored in the computer-readable storage medium.

[0053] In addition to the above method and device, the embodiments of the application can also be a computer program product including computer program instructions, which, when run by a processor, cause the processor to perform the steps of the vehicle emission remote evaluation method provided by any embodiment of the application.

[0054] The computer program product can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. It will be appreciated that the program code can be implemented in any combination of languages including one or more compiled languages, interpreted languages, declarative languages, procedural languages, object oriented languages, and the like.

[0055] It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that those skilled in the art will be able to design many alternative embodiments without departing from the scope of the application. The word "comprising" does not exclude the presence of elements or steps other than those listed in a claim. In addition, the word "comprising" itself does not exclude a process of optional selection of integers essential for the technical result to be achieved. The word "comprising" thus indicates the inclusion of whole or parts of the specified steps or integers. The use of any form of "comprising", "including", "containing", "having" or "including" and / or the like shall thus not be interpreted as implying any element or step not strictly described as such.

Claims

1. A method for on-line evaluation of vehicle emission conformity, characterized by, The method comprises the following steps: Step S1: obtaining a remote monitoring data stream of a vehicle to be evaluated within a preset time period, preprocessing the remote monitoring data stream, and generating an effective data set; wherein the remote monitoring data stream at least comprises a vehicle identification code VIN, a data acquisition time, a vehicle speed, an engine speed, an engine output torque, an engine fuel flow, a dew point state of an SCR downstream NOx sensor, an SCR downstream NOx concentration, an engine coolant temperature, a cumulative mileage, an engine rated power, an atmospheric temperature, an atmospheric pressure, and an altitude; Step S2: identifying and segmenting a plurality of independent driving cycles from the effective data set, and screening out an independent driving cycle with a cold start feature and an engine cumulative work not less than a preset cycle work threshold as an effective driving cycle; Step S3: dividing the data of each effective driving cycle into a plurality of preset working condition zones according to operating characteristics; the preset working condition zones at least comprise a cold state operating zone, a low work zone, and a medium-high work zone; the cold state operating zone is a time period from the start time of the driving cycle to the time when the engine cumulative work reaches a preset reference value; the low work zone and the medium-high work zone are determined by analyzing the relationship between the average engine power and the preset power percentage threshold through a moving time window; Step S4: calculating a target pollutant emission result by using a corresponding calculation model for each preset working condition zone; Step S5: comparing the target pollutant emission result of each zone with a corresponding preset emission limit value, and determining that the emission of the target pollutant of the vehicle to be evaluated in this evaluation period is unqualified when any pollutant emission result exceeds the corresponding preset emission limit value; if the pollutant emission results of all working condition zones do not exceed the corresponding preset emission limit value, it is determined to be qualified.

2. The method of claim 1, wherein In step S1, the preprocessing of the remote monitoring data stream comprises validity cleaning, abnormal value processing, and data repair; The validity cleaning is to remove data points that do not meet the preset environmental boundary conditions and sensor readings that are obviously abnormal in the remote monitoring data stream; The abnormal value processing is to identify and process abnormal values in key parameters by using a statistical algorithm or a machine learning algorithm; The data repair is to estimate or fill in invalid data of the aftertreatment system sensor before reaching the working temperature according to a preset repair model.

3. The method of claim 1, wherein The step S2 specifically comprises: Step 2.1: identifying and segmenting a plurality of independent driving cycles from the effective data set, specifically: based on the time interval between the effective data points in the effective data set, the cumulative mileage, and the vehicle speed and engine speed data within a certain time window, a plurality of independent driving cycles are automatically identified and segmented; the start time of each independent driving cycle is the time when the vehicle to be evaluated restarts driving after a long period of non-driving; Step 2.2: based on the identified and segmented independent driving cycles, screening out an independent driving cycle with a cold start feature, wherein the independent driving cycle with a cold start feature is an independent cycle in which the aftertreatment system does not reach the working temperature in the initial stage, and the engine coolant temperature is lower than a first preset threshold and the engine exhaust temperature is lower than a second preset threshold; Step 2.3: Based on the screened independent driving cycles with cold start characteristics, the engine cumulative work of the whole process of each independent driving cycle is calculated, and independent driving cycles with engine cumulative work not less than a preset cycle work threshold are screened out; The engine cumulative work is calculated as follows: ； wherein, is the cumulative engine work in kW·h; T is the engine torque in N·m; n is the engine speed in r / min; N is the total driving cycle time in s; t is the data point time index.

4. The method of claim 1, wherein In step S4: the pollutant emission result is specific emission value or emission rate; For the pollutant emission result of the cold state operation partition, the following method is used for calculation: the total mass of the emitted pollutants in the partition is calculated, and then divided by the total cumulative work of the engine in the cold state operation partition, to obtain the specific emission value in mass / power unit; For the pollutant emission result of the medium-high power partition, the following method is used for calculation: the total mass of pollutants and the total cumulative work of the engine of all medium-high power partition windows are summarized, and the total specific emission value is calculated; For the pollutant emission result of the low power partition, the following method is used for calculation: the total mass of pollutants and the total time length of all low power partition windows are summarized, and the emission rate in mass / time unit is calculated.

5. An apparatus for on-line evaluation of vehicle emission conformity, characterized by comprising: It comprises the following modules: data acquisition and preprocessing module, effective driving cycle screening module, operation condition partition module, partition emission calculation module and conformity evaluation module; The data acquisition and preprocessing module is used for acquiring remote monitoring data stream of the vehicle to be evaluated in a preset time period, pre-processing the remote monitoring data stream, and generating an effective data set; wherein the remote monitoring data stream at least includes: vehicle identification code VIN, data acquisition time, vehicle speed, engine speed, engine output torque, engine fuel flow, SCR downstream NOx sensor dew point state, SCR downstream NOx concentration, engine coolant temperature, cumulative mileage, engine rated power, atmospheric temperature, atmospheric pressure and altitude; The effective driving cycle screening module is used for identifying and segmenting multiple independent driving cycles from the effective data set, and screening out independent driving cycles with cold start characteristics and engine cumulative work not less than a preset cycle work threshold as effective driving cycles; The operation condition partition module is used for dividing the data of each effective driving cycle into multiple preset working condition partitions according to the operation characteristics; the preset working condition partitions at least include: cold state operation partition, low power partition and medium-high power partition; the cold state operation partition is the time period from the start time of the driving cycle to the time when the engine cumulative work reaches a preset reference value; the low power partition and the medium-high power partition are determined by analyzing the relationship between the average engine power and the preset power percentage threshold through a moving time window; The partition emission calculation module is used for calculating the pollutant emission result of the target pollutant for each preset working condition partition by using the corresponding calculation model; The conformity evaluation module is used for comparing the pollutant emission result of each partition target pollutant with the corresponding preset emission limit value, and when any pollutant emission result exceeds the corresponding preset emission limit value, it is determined that the emission of the target pollutant of the vehicle to be evaluated in this evaluation period is unqualified; if the pollutant emission results of all working condition partitions do not exceed the corresponding preset emission limit value, it is determined to be qualified.

6. The apparatus according to claim 5, wherein The preprocessing of the remote monitoring data stream comprises validity cleaning, outlier processing and data repair; The validity cleaning is to remove data points that do not meet the preset environmental boundary conditions and sensor readings that are obviously abnormal in the remote monitoring data stream; The outlier processing is to identify and process outliers in the key parameters by using a statistical algorithm or a machine learning algorithm; The data repair is to estimate or fill in invalid data of the sensor of the post-processing system before reaching the working temperature according to a preset repair model.

7. The apparatus according to claim 5, wherein The valid driving cycle screening module is specifically configured to perform the following steps: Step 2.1: identifying and segmenting multiple independent driving cycles from the valid data set, specifically, based on the time interval between valid data points in the valid data set, the cumulative driving mileage and the vehicle speed and engine speed data within a specific time window, multiple independent driving cycles are automatically identified and segmented; the starting time of each independent driving cycle is the time when the vehicle to be evaluated restarts driving after a long period of non-driving; Step 2.2: based on the identified and segmented independent driving cycles, independent driving cycles with cold start characteristics are screened out, the cold start characteristics being that the post-processing system does not reach the working temperature in the initial stage of the independent cycle, and the engine coolant temperature is lower than a first preset threshold and the engine exhaust temperature is lower than a second preset threshold; Step 2.3: based on the independent driving cycles with cold start characteristics screened out, the engine cumulative work of each independent driving cycle is calculated, and independent driving cycles with engine cumulative work not less than a preset cycle work threshold are screened out; The engine cumulative work is calculated as follows: ； wherein, is the cumulative engine work in kW·h; T is the engine torque in N·m; n is the engine speed in r / min; N is the total driving cycle time in s; t is the data point time index.

8. The apparatus for on-line evaluation of vehicle emission conformity according to claim 5, wherein The pollutant emission result is a specific emission value or an emission rate; For the pollutant emission result of the cold state operation partition, the following method is used for calculation: the total mass of the emitted pollutants in the partition is calculated, and then divided by the total cumulative work of the engine in the cold state operation partition to obtain a specific emission value in mass / power units; For the pollutant emission result of the medium-high power partition, the following method is used for calculation: the total mass of the emitted pollutants and the total cumulative work of the engine in all medium-high power partition windows are summed up to calculate the total specific emission value; For the pollutant emission result of the low power partition, the following method is used for calculation: the total mass of the emitted pollutants and the total time length in all low power partition windows are summed up to calculate an emission rate in mass / time units.

9. A storage medium, characterized by The storage medium stores at least one instruction, at least one program, a code set or an instruction set, which are loaded and executed by the processor to realize the vehicle emission conformity online evaluation method according to any one of claims 1-4.

10. An electronic device, comprising: The electronic device comprises a processor and a memory, and the memory stores at least one instruction, at least one program, a code set or an instruction set, which are loaded and executed by the processor to realize the vehicle emission conformity online evaluation method according to any one of claims 1-4.

Images