Vehicle and method for estimating emissions thereof

Abstract

This invention discloses a vehicle and its emission prediction method. The method includes: cleaning the vehicle's driving cycle data; constructing a nitrogen oxide (NOx) specific emission data set based on the cleaned driving cycle data, and performing an initial specific emission estimate by comparing the emission data set to determine whether the NOx specific emissions exceed the standard; if the NOx specific emissions exceed the standard, classifying the driving cycle data in the specific emission data set into different vehicle speed groups, extracting a preset number of data points from each vehicle speed group, and sorting all extracted data points to obtain a data point sequence; concatenating the data point sequence to construct a PEMS feature array, and performing a secondary specific emission estimate based on the PEMS feature array. Therefore, this method is not only applicable to actual user driving, but also effectively reduces the model's false alarm rate by continuously monitoring and judging vehicle emission levels and by concatenating the data.

Description

Technical Field

[0001] This invention relates to the field of vehicle emission technology, and more particularly to a vehicle and a method for predicting its emissions. Background Technology

[0002] The China VI emission standards impose strict limits on nitrogen oxide emissions from heavy-duty diesel and dual-fuel engines. The regulations clearly define the testing methods for real-world nitrogen oxide emissions from vehicles: by installing a PEMS (Portable Emission Measurement System) on the vehicle and conducting real-world driving in urban, suburban, and highway scenarios, the PEMS can collect and analyze data in real time to assess and confirm the overall vehicle's nitrogen oxide and other pollutant emission levels.

[0003] However, the high cost of PEMS (Prevention and Control of Nitrogen Oxide) emissions monitoring, requiring installation on the entire vehicle and adherence to specific driving requirements, makes this method unsuitable for real-time monitoring of nitrogen oxide emissions from a large number of real-world user vehicles. Currently, major domestic commercial vehicle manufacturers are actively deploying and developing vehicle-to-everything (V2X) big data platforms; however, there are still no effective and applicable models or methods based on actual user driving conditions for monitoring and predicting nitrogen oxide emissions from heavy-duty diesel vehicles. Summary of the Invention

[0004] This invention aims to at least partially address one of the technical problems in related technologies. To this end, the first objective of this invention is to propose a vehicle emissions prediction method that is applicable not only to actual user driving but also, through continuous monitoring and assessment of vehicle emissions levels and by stitching together data, effectively reduces the model's false alarm rate.

[0005] The second objective of this invention is to provide a vehicle.

[0006] To achieve the above objectives, a first aspect of the present invention proposes a vehicle emission prediction method. The method includes: cleaning vehicle driving cycle data, where the driving cycle data includes multiple data points, each data point including actual driving data of the vehicle at the same time; constructing a nitrogen oxide (NOx) specific emission data set based on the cleaned driving cycle data, and performing an initial specific emission estimate by comparing the emission data set to determine whether the NOx specific emissions exceed the standard; determining that the NOx specific emissions exceed the standard, classifying the driving cycle data in the specific emission data set into different vehicle speed groups, extracting a preset number of data points from each vehicle speed group, and sorting all extracted data points to obtain a data point sequence, where the data groups include a low-speed group, a medium-speed group, and a high-speed group; concatenating the data point sequence to construct a PEMS feature array, and performing a secondary specific emission estimate based on the PEMS feature array to determine the NOx specific emission level.

[0007] According to the vehicle emission prediction method of this invention, the driving cycle data of a vehicle is cleaned. The driving cycle data includes multiple data points, each including the actual driving data of the vehicle at the same moment. A specific emission data group of nitrogen oxides (NOx) is constructed based on the cleaned driving cycle data. An initial specific emission estimate is performed by comparing the emission data group to determine whether the specific emission of NOx exceeds the standard. If the specific emission of NOx exceeds the standard, the driving cycle data in the specific emission data group is classified into different vehicle speed groups, with each data point as a unit. A preset number of data points are extracted from each vehicle speed group, and all extracted data points are sorted to obtain a data point sequence. The data groups include low-speed, medium-speed, and high-speed groups. The data point sequence is spliced ​​to construct a PEMS feature array, and a secondary specific emission estimate is performed based on the PEMS feature array to determine the specific emission level of NOx. Therefore, this method is not only applicable to actual user driving, but also effectively reduces the false alarm rate of the model by continuously monitoring and judging the vehicle emission level and by splicing the data.

[0008] According to one embodiment of the present invention, performing an initial relative emission estimation by comparing emission data sets to determine whether the relative emissions of nitrogen oxides exceed the standard includes: obtaining the total mass and cumulative work of nitrogen oxides downstream of the SCR for each driving cycle data in the relative emission data set; determining the relative emission value of nitrogen oxides downstream of the SCR in the relative emission data set based on the total mass and cumulative work of nitrogen oxides downstream of the SCR for each driving cycle data; identifying that the relative emission value exceeds the relative emission threshold, and determining that the relative emissions of nitrogen oxides exceed the standard.

[0009] According to one embodiment of the present invention, extracting a preset number of data points from each vehicle speed group includes: determining that the number of data points in the vehicle speed group is greater than or equal to a preset number, and sequentially extracting the preset number of data points from the vehicle speed group; determining that the number of data points in the vehicle speed group is greater than or equal to K*a preset number and less than a preset number, and randomly extracting data points from the vehicle speed group until the number of extracted data points equals the preset number, wherein 0 < K < 1; determining that the number of data points in the vehicle speed group is less than K*a preset number, and stopping the construction of the PEMS feature array.

[0010] According to one embodiment of the present invention, splicing a data point sequence to construct a PEMS feature array includes: obtaining the vehicle speed gradient between two adjacent data points in the data point sequence; determining the upper limit and lower limit of the number of data points in the data segment to be generated; processing the data point sequence according to the vehicle speed gradient, the upper limit and the lower limit to generate multiple data segments; and generating a PEMS feature array based on the multiple data segments.

[0011] According to one embodiment of the present invention, a data point sequence is processed according to a vehicle speed gradient, an upper limit value, and a lower limit value to generate multiple data segments, including: in response to the current data point being in the same vehicle speed group as the previous data point and the vehicle speed gradient between the current data point and the previous data point being less than or equal to a gradient threshold, the following processing is performed: if the number of data points in the current data segment is less than the upper limit value, the current data point is added to the current data segment; if the number of data points in the current data segment is greater than or equal to the upper limit value, the current data segment is added to the current vehicle speed group, and the current data point is added to a new data segment.

[0012] According to one embodiment of the present invention, the data point sequence is processed according to the vehicle speed gradient, upper limit value, and lower limit value to generate multiple data segments. The process further includes: in response to the current data point being in the same vehicle speed group as the previous data point and the vehicle speed gradient between the current data point and the previous data point being greater than a gradient threshold, the following processing is performed: if the number of data points in the current data segment is determined to be greater than or equal to the lower limit value, the current data segment is added to the current vehicle speed group, and the current data point is added to a new data segment; if the number of data points in the current data segment is determined to be less than the lower limit value, the data points in the current data segment are cleared, and the current data point is added to the cleared current data segment.

[0013] According to one embodiment of the present invention, the data point sequence is processed according to the vehicle speed gradient, upper limit value, and lower limit value to generate multiple data segments. The process further includes: in response to the current data point being in a different vehicle speed group than the previous data point, the following processing is performed: if the number of data points in the current data segment is greater than or equal to the lower limit value, the current data segment is added to the vehicle speed group corresponding to the previous data point, and the current data point is added to a new data segment, and the new data segment is temporarily added to the vehicle speed group corresponding to the current data point; if the number of data points in the current data segment is less than the lower limit value, the data points in the current data segment are cleared, and the current data point is added to the cleared current data segment, and the current data segment is temporarily added to the vehicle speed group corresponding to the current data point.

[0014] According to one embodiment of the present invention, the method further includes: constructing a concentration data set of nitrogen oxides based on data-cleaned driving cycle data, and performing concentration emission estimation on the concentration data set to determine whether the concentration emission of nitrogen oxides exceeds the standard.

[0015] According to one embodiment of the present invention, a concentration emission estimation of a concentration data set to determine whether the concentration emission of nitrogen oxides exceeds the standard includes: obtaining the total number of data points for each driving cycle data in the concentration data set and the ratio of the number of data points with a concentration of nitrogen oxides downstream of the SCR greater than or equal to a preset concentration to the total number of data points; determining the proportion of the concentration of nitrogen oxides downstream of the SCR in the concentration data set that is greater than or equal to the preset concentration based on the total number of data points for each driving cycle data and the ratio; identifying that the proportion exceeds the proportion threshold, and determining that the concentration emission of nitrogen oxides exceeds the standard.

[0016] According to one embodiment of the present invention, the method further includes: based on the specific emission level, modifying at least one of the cleaning conditions corresponding to data cleaning, the data conditions corresponding to constructing the specific emission data set, the estimation conditions corresponding to the initial specific emission estimation, the data conditions corresponding to constructing the PEMS feature array, and the data conditions corresponding to constructing the concentration data set.

[0017] To achieve the above objectives, a second aspect of the present invention provides a vehicle, including: a memory, a processor, and a vehicle emission prediction program stored in the memory and executable on the processor. When the processor executes the program, it implements the above-described vehicle emission prediction method.

[0018] According to an embodiment of the present invention, the vehicle's driving cycle data is cleaned, including multiple data points, each containing actual driving data of the vehicle at the same moment. A nitrogen oxide (NOx) specific emission data set is constructed based on the cleaned driving cycle data. An initial specific emission estimate is performed by comparing the emission data set to determine if the NOx specific emission exceeds the standard. If the NOx specific emission exceeds the standard, the driving cycle data in the specific emission data set is classified into different vehicle speed groups, with each data point representing a predetermined number of data points extracted from each speed group. All extracted data points are then sorted to obtain a data point sequence, including low-speed, medium-speed, and high-speed groups. The data point sequence is then concatenated to construct a PEMS feature array, and a secondary specific emission estimate is performed based on the PEMS feature array to determine the NOx specific emission level. Therefore, this method is not only applicable to actual user driving but also allows for continuous monitoring and judgment of vehicle emission levels. Furthermore, by concatenating the data, the false alarm rate of the model can be effectively reduced.

[0019] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0020] Figure 1 A flowchart of a vehicle emission estimation method according to an embodiment of the present invention;

[0021] Figure 2 A flowchart illustrating data cleaning of vehicle driving cycle data according to an embodiment of the present invention;

[0022] Figure 3 This is a flowchart illustrating the splicing process of a data point sequence according to an embodiment of the present invention;

[0023] Figure 4 This is a flowchart illustrating quadratic emission estimation based on a PEMS feature array according to an embodiment of the present invention;

[0024] Figure 5 A flowchart illustrating quadratic emission estimation based on PEMS feature arrays according to another embodiment of the present invention;

[0025] Figure 6 This is a flowchart of concentration emission estimation and initial relative emission estimation according to an embodiment of the present invention;

[0026] Figure 7 This is a structural block diagram of a vehicle according to an embodiment of the present invention. Detailed Implementation

[0027] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0028] The following description, with reference to the accompanying drawings, describes the vehicle and its emission estimation method provided by embodiments of the present invention.

[0029] Figure 1 A flowchart of a vehicle emission prediction method according to an embodiment of the present invention is provided, with reference to... Figure 1 As shown, the vehicle emissions estimation method may include the following steps:

[0030] Step S101: Perform data cleaning on the vehicle's driving cycle data. The driving cycle data includes multiple data points, and each data point includes the vehicle's actual driving data at the same time.

[0031] Specifically, embodiments of the present invention use a driving cycle as the smallest data unit to continuously judge and monitor vehicle emission levels. A driving cycle refers to a cyclical process that begins with engine start and ends with engine shutdown. Multiple data points are collected during this process. It should be noted that the data points in this embodiment include various driving data of the vehicle at the same moment, such as: vehicle speed, nitrogen oxide concentration, engine speed, intake air volume, engine fuel flow, engine net output torque, engine actual torque, engine indicated torque, and friction torque. In specific implementation, vehicle driving data can be collected based on onboard sensors, and the acquired actual driving data at the same moment can be packaged into a single data point, thereby obtaining a series of actual driving data points of the vehicle at different times. Since these data include invalid data that does not meet the conditions, they need to be filtered.

[0032] In one specific embodiment, reference Figure 2 As shown, data cleaning of vehicle driving cycle data may include the following steps:

[0033] Step S201: Identify the VIN (Vehicle Identification Number) and vehicle type.

[0034] Step S202: Identify driving cycle.

[0035] Step S203: Obtain vehicle configuration parameters, which may include vehicle brand, vehicle type, engine model, reference torque, WHTC (World Harmonious Transient Cycle) cycle power and engine rated power.

[0036] Step S204: Obtain the data acquisition boundary, which may include engine coolant temperature, SCR (Selective Catalytic Reduction) inlet temperature, altitude, and ambient temperature.

[0037] Step S205: Obtain emission correlation analysis data, which may include vehicle speed, engine speed, engine net output torque, nitrogen oxide concentrations upstream and downstream of SCR, intake air volume, and engine fuel flow rate.

[0038] Step S206: Obtain emission impact factors, which may include urea injection volume, etc.

[0039] Step S207: Filter data based on boundary conditions to select valid vehicle driving cycle data. In a specific example, valid vehicle driving cycle data can meet the following boundary conditions: discard data frames that have lost key information; coolant temperature is below the upper limit; engine speed is above the lower limit; SCR inlet temperature is above the lower limit; SCR upstream and downstream nitrogen oxides are below the upper limit; altitude is below the upper limit; engine net output torque is above the lower limit; ambient temperature is above the lower limit and below the upper limit; driving cycle duration is above the lower limit.

[0040] It should be noted that the vehicle type can be determined based on the vehicle's VIN. Based on the vehicle type, the speed range and percentage for the three speed conditions (urban, suburban, and highway) of the PEMS test as defined in GB17691 can be queried. The model input mainly includes collected judgment condition data, computational data, emissions analysis data, and loaded vehicle configuration parameters. After data input, data cleaning can be performed, discarding data with excessively short driving times and removing invalid data. It is understood that the judgment conditions here can all be configurable parameters. The subsequent prediction performance of the reference model can iteratively optimize these configurable parameters, thereby improving the model's effective data recognition accuracy.

[0041] Step S102: Construct a set of nitrogen oxide specific emissions data based on the cleaned driving cycle data, and compare the emission data set to make an initial specific emission estimate to determine whether the specific emissions of nitrogen oxides exceed the standard.

[0042] The initial comparative emission estimation, which compares emission data sets to determine whether the specific emissions of nitrogen oxides exceed the standard, may include: obtaining the total mass and cumulative work of nitrogen oxides downstream of the SCR for each driving cycle in the comparative emission data set; determining the specific emission value of nitrogen oxides downstream of the SCR in the comparative emission data set based on the total mass and cumulative work of nitrogen oxides downstream of the SCR for each driving cycle; identifying that the specific emission value exceeds the specific emission threshold, and determining that the specific emissions of nitrogen oxides exceed the standard.

[0043] Specifically, the specific emission values ​​can be obtained in the following ways:

[0044] Q=(NOx1+...+NOxn) / (W1+...+Wn)

[0045] Where Q is the specific emission value, NOxn is the total mass of downstream nitrogen oxides in the nth driving cycle data in the specific emission data set, and Wn is the cumulative work of the nth driving cycle data.

[0046] Specifically, for the specific emission value Q, it equals the sum of the total downstream nitrogen oxide mass of the n driving cycles in the specific emission data set divided by the sum of the cumulative work of the n driving cycles. Here, the total downstream nitrogen oxide mass NOxn of the nth driving cycle refers to the total downstream nitrogen oxide mass in the data after boundary condition filtering, which can be obtained in the following way:

[0047] NOxn=0.001587*NOx conc*Gexh / 3600

[0048] Wherein, NOx conc is the instantaneous concentration of nitrogen oxide emissions, in ppm; Gexh is the instantaneous exhaust flow rate, which is equal to the product of instantaneous fuel flow rate and fuel density plus instantaneous air flow rate, in kg / h.

[0049] After obtaining the specific emission value of nitrogen oxides downstream of SCR in the specific emission data set, it is possible to identify whether the specific emission of nitrogen oxides exceeds the standard based on this specific emission value. Specifically, when the specific emission value is less than the first specific emission threshold (e.g., 5%), it can be determined that the emissions are compliant; when the specific emission value is greater than or equal to the first specific emission threshold (e.g., 5%) and less than the second specific emission threshold (e.g., 10%), it can be determined that the emissions exceed the standard; when the specific emission value is greater than or equal to the second specific emission threshold (e.g., 10%), it can be determined that the emissions are severely exceeded. It should be noted that the specific emission value of nitrogen oxides downstream of SCR is used to determine whether the specific emission of nitrogen oxides exceeds the standard, while the specific emission value of nitrogen oxides upstream of SCR in the driving cycle data is only used for statistics and comparison. When a significant abnormality (increase or decrease) occurs, it can be identified as an abnormality in the original engine emissions, and the exhaust emission level assessment can be stopped.

[0050] Step S103: Determine that the specific emissions of nitrogen oxides exceed the standard. Classify the driving cycle data in the specific emissions data group into different vehicle speed groups based on data points, extract a preset number of data points from each vehicle speed group, and sort all the extracted data points to obtain a data point sequence. The data groups include low speed group, medium speed group and high speed group.

[0051] In other words, driving cycle data with excessive nitrogen oxide emissions can be categorized by vehicle speed, and the specific speed categorization method can be adaptively adjusted according to vehicle type. For example, nitrogen oxide emission data groups with excessive nitrogen oxide emissions can be categorized by vehicle speed: 0-45 kph for urban road conditions, 45-70 kph for suburban road conditions, and nitrogen oxide emission speeds greater than 70 kph for highway road conditions. The data points within each speed group are not sorted by speed; the original arrangement order of each speed group is maintained.

[0052] The process of extracting a preset number of data points from each vehicle speed group may include: determining that the number of data points in a vehicle speed group is greater than or equal to a preset number, and sequentially extracting the preset number of data points from the vehicle speed group; determining that the number of data points in a vehicle speed group is greater than or equal to K * a preset number and less than a preset number, and randomly extracting data points from the vehicle speed group until the number of extracted data points equals the preset number, where 0 < K < 1; and determining that the number of data points in a vehicle speed group is less than K * a preset number, and stopping the construction of the PEMS feature array.

[0053] In other words, when there are enough data points in the vehicle speed group, they can be extracted sequentially from the group; when there are few data points in the group, they can be extracted randomly, and some data points may be extracted multiple times, as long as the number of extracted data points is the preset number; when there are too few data points in the vehicle speed group, the construction of the PEMS feature array is stopped. This prevents insufficient statistical validity caused by too little data from short driving cycles.

[0054] Step S104: The data point sequence is spliced ​​to construct a PEMS feature array, and a secondary specific emission estimate is performed based on the PEMS feature array to determine the specific emission level of nitrogen oxides.

[0055] Specifically, after classifying the driving cycle data with excessive nitrogen oxide emissions by vehicle speed, the PMES feature array can be constructed by referring to the PEMS test method defined in GB17691 (i.e., sequentially arranged data for urban, suburban, and highway driving). For example, the data can be classified into three categories: 0-45 kph for urban driving, 45-70 kph for suburban driving, and greater than 70 kph for highway driving. The data points for each speed group are not sorted by speed, maintaining the original order of each speed group. Then, the data points for the corresponding speed ranges are placed into their respective data groups, and the data points for urban, suburban, and highway driving conditions are extracted according to the regulatory ratio of 4:5:11, and then concatenated sequentially to construct a PEMS feature array with a total of 7200 packets. After constructing the PMES feature array, a deep analysis and calculation of nitrogen oxide ratio emissions based on the work-based window method can be performed on the PEMS feature array. For specific algorithms and procedures, please refer to the definitions in GB17691 and HJ857 regulations.

[0056] Furthermore, Figure 3 A flowchart for splicing a data point sequence according to an embodiment of the present invention is provided, with reference to... Figure 3 As shown, concatenating a data point sequence can include the following steps:

[0057] Step S1041: Obtain the vehicle speed gradient between two adjacent data points in the data point sequence.

[0058] Specifically, after reordering the data points according to their speed from smallest to largest to form a data point sequence, the speed gradients of adjacent data points in the data point sequence are obtained sequentially according to the order of speed. It should be noted that the speed gradient is the change in the absolute value of the difference between the speeds of two data points over a certain period of time. For example, the change in the absolute value of the difference between the speed of the current data point and the speed of the previous data point over a certain period of time is the speed gradient between the current data point and the previous data point.

[0059] Step S1042: Determine the upper and lower limits of the number of data points in the data segment to be generated.

[0060] Specifically, when determining the generation of data segments, it is necessary to determine whether the number of data points in the data segment to be generated meets the division requirements. An upper limit and a lower limit of the number of data points in the data segment to be generated are preset. Under different data segment determination scenarios, the preset upper limit or lower limit of the data points is used as the basis for determining the generation of data segments.

[0061] Step S1043: Process the data point sequence according to the vehicle speed gradient, upper limit value and lower limit value to generate multiple data segments.

[0062] This may include: in response to the current data point being in the same speed group as the previous data point and the speed gradient between the current data point and the previous data point being less than or equal to the gradient threshold, the following processing is performed: if the number of data points in the current data segment is less than the upper limit, the current data point is added to the current data segment; if the number of data points in the current data segment is greater than or equal to the upper limit, the current data segment is added to the current speed group, and the current data point is added to a new data segment.

[0063] Specifically, during the generation of data segments, it is first determined whether the current data point and the previous data point are in the same speed group. That is, it is determined whether the speed of the current data point and the previous data point are in the same speed range. If the current data point and the previous data point are in the same speed group, it is determined whether the speed gradient between the current data point and the previous data point is less than or equal to the gradient threshold. If the speed gradient between the current data point and the previous data point is less than or equal to the gradient threshold, the current data segment is determined by comparing the number of data points in the data segment with the upper limit value.

[0064] As a concrete example, let's take the case where the current data point and the previous data point are both in the low-speed group, and the speed gradient between the current data point and the previous data point is less than or equal to the gradient threshold. When determining a data segment, if the number of data points recorded in the current data segment is less than the upper limit, the current data point is added to the current data segment, and the number of recorded data points is incremented by 1 using a counter. As the number of data points increases, if the number of data points in the current data segment is greater than or equal to the upper limit, it means that the current data segment is full. The current data segment is then added to the current speed group, i.e., to the low-speed group, forming a new data segment. The current data point is added to the new data segment, and the number of data points in this new data segment starts from 1. This process continues, with the counter incrementing by 1 for each data point added.

[0065] In one embodiment, processing the data point sequence according to the vehicle speed gradient, upper limit, and lower limit to generate multiple data segments further includes: in response to the current data point being in the same vehicle speed group as the previous data point and the vehicle speed gradient between the current data point and the previous data point being greater than a gradient threshold, performing the following processing: if the number of data points in the current data segment is greater than or equal to the lower limit, adding the current data segment to the current vehicle speed group and adding the current data point to a new data segment; if the number of data points in the current data segment is less than the lower limit, clearing the data points in the current data segment and adding the current data point to the cleared current data segment.

[0066] Specifically, when it is determined that the current data point and the previous data point are in the same speed group, but the speed gradient between the current data point and the previous data point is greater than the gradient threshold, the current data segment is determined by comparing the number of data points in the data segment with the lower limit value. In other words, if the speed fluctuation between the current data point and the previous data point is too large, the number of data points in the data segment is compared with the lower limit value.

[0067] As a concrete example, let's consider a scenario where the current data point and the previous data point are both in the low-speed group, and the speed gradient between them is greater than a gradient threshold. When determining a data segment, if the number of data points in the current data segment is greater than or equal to the lower limit, it means that the data points recorded in the current data segment meet the minimum requirements. To prevent excessive speed fluctuations between data points in the same data segment, no new data points are added to the current data segment. Instead, the current data segment is added to the current speed group, i.e., to the low-speed group, thus forming a new data segment. The current data point is added to this new data segment, and the number of data points in this new data segment starts from 1. This process continues, with the counter incrementing by 1 for each data point added. If the number of data points in the current data segment is less than the lower limit, it means that the current data segment does not meet the usage requirements. The data points in the current data segment are cleared, and the current data point is added to the cleared current data segment. The number of data points in the cleared current data segment starts from 1, and this process continues, with the counter incrementing by 1 for each data point added. This avoids excessive fluctuations in vehicle speed among data points in the data segment, making the data points in the data segment more consistent with the characteristic experimental data defined by regulations.

[0068] In one embodiment, the data point sequence is processed according to the vehicle speed gradient, upper limit, and lower limit to generate multiple data segments. The process further includes: in response to the current data point being in a different vehicle speed group than the previous data point, the following processing is performed: if the number of data points in the current data segment is greater than or equal to the lower limit, the current data segment is added to the vehicle speed group corresponding to the previous data point, and the current data point is added to a new data segment, and the new data segment is temporarily added to the vehicle speed group corresponding to the current data point; if the number of data points in the current data segment is less than the lower limit, the data points in the current data segment are cleared, and the current data point is added to the cleared current data segment, and the current data segment is temporarily added to the vehicle speed group corresponding to the current data point.

[0069] In other words, during the generation of data segments, if it is determined that the current data point and the previous data point are in different speed groups, it means that the speed change between the current data point and the previous data point is too large. The current data segment is determined by comparing the number of data points in the data segment with the lower limit value.

[0070] Specifically, taking the example of the current data point being in the medium-speed group and the previous data point being in the low-speed group, when determining the data segment, if the number of data points in the current data segment is greater than or equal to the lower limit, it means that the data points recorded in the current data segment have met the minimum requirements. To avoid adding the current data point to the low-speed group, no new data points are added to the current data segment. Instead, the current data segment is added to the vehicle speed group corresponding to the previous data point, i.e., added to the low-speed group, thus forming a new data segment. This new data segment is temporarily added to the vehicle speed group corresponding to the current data point, i.e., temporarily added to the medium-speed group, and the current data point is added to the new medium-speed group. The number of data points in a new data segment starts from 1 and continues sequentially. Each time a data point is added, the counter increments the count. If the number of data points in the current data segment is less than the lower limit, it means the current data segment does not meet the usage requirements. The data points in the current data segment are cleared, and the cleared data segment is temporarily added to the corresponding speed group. Specifically, the cleared data segment is added to the medium speed group, and the current data point is added to the cleared current data segment within the medium speed group. The number of data points in the cleared current data segment starts from 1 and continues sequentially. Each time a data point is added, the counter increments the count.

[0071] Furthermore, when adding the current data point to the corresponding data segment, the data point can be named in the manner of group-segment-serial number.

[0072] For example, suppose the current data point is the first data point in the low-speed group. When determining the current data segment, the first data point in the low-speed group is added to the current data segment, and the current data point can be named low-speed group-01-001. Similarly, the next data point added to the current data segment can be named low-speed group-01-002. If the current data segment is full, the data points can be recorded in a new data segment in sequence, and the data point can be named low-speed group-02-001. If the current data point is in a different data group than the previous data point, such as changing from the low-speed group to the medium-speed group, the current data point can be named medium-speed group-01-001, and so on, thus completing the naming of each data point added to the data segment.

[0073] It should be noted that when naming data points, it is necessary to determine whether the currently named data point is the last data point. If the current data point is not the last data point, the processing of the next data point continues. If the current data point is the last data point, the processing of the current data point ends.

[0074] Step S1044: Generate a PEMS feature array based on multiple data fragments.

[0075] Specifically, after processing the data point sequence according to the vehicle speed gradient, upper limit value and lower limit value, multiple data segments can be generated. The multiple data segments are added sequentially to the corresponding vehicle speed groups (low speed group, medium speed group and high speed group) to generate the PEMS feature array.

[0076] Therefore, by processing the data point sequence according to the vehicle speed gradient, upper limit value, and lower limit value, multiple data segments are formed, and a PEMS feature array is generated based on multiple data segments. This allows for the acquisition of a data set that better matches the regulatory definition, and the resulting PEMS feature array is more consistent with the regulatory definition of the feature experiment array.

[0077] In some embodiments, reference Figure 6 As shown, quadratic emission estimation based on PEMS feature arrays may include the following sub-steps:

[0078] Step S1046: Based on the instantaneous engine power of the data points, the PEMS feature array is divided into multiple power base windows.

[0079] Specifically, for the PEMS feature array, starting from the first data packet, the instantaneous power and instantaneous NOx emission mass of each data packet are calculated and summed. Multiple power base windows are then defined with the goal of the total power being greater than or equal to the WHTC cycle power of the engine corresponding to that vehicle model (this value is constant). For example, if the WHTC cycle power is 9.7 kWh, and the sum of the instantaneous power of 600 data packets is 9.72 kWh, then this length of data points is defined as the first power base window. When defining the second power base window, the data from the first power base window is first removed. It is then determined whether the sum of the instantaneous power of the remaining power base window data points still satisfies greater than or equal to 9.7 kWh. If it does, the second power base window can be defined; otherwise, new data points are added from the PEMS feature array, and the cycle power is accumulated until it is greater than or equal to 9.7 kWh, which is then defined as the second power base window. This process continues until the last data packet of the PEMS feature array is processed.

[0080] Step S1047: For each power base window, perform validity identification based on the engine average power of the power base window.

[0081] Specifically, the sum of instantaneous power in each power base window divided by the time duration yields the average power. Dividing this average power by the engine's rated power gives the average power percentage for that window. The validity of the power base window is determined by comparing this average power percentage with a preset limit (the window's average power percentage limit). If the preset limit is 15%, and the average power percentage of the window is 13%, meaning the average power percentage is less than the preset limit, the window is considered an invalid power base window. Conversely, if the average power percentage is 18%, meaning the average power percentage is greater than the preset limit, the window is considered a valid power base window.

[0082] Step S1048: When the power base window is valid, calculate the proportion of downstream nitrogen oxide emissions greater than or equal to the preset ratio emissions, the downstream nitrogen oxide emission value, and the upstream nitrogen oxide emission value based on the downstream nitrogen oxide mass, total engine power, and upstream nitrogen oxide mass of the power base window.

[0083] Specifically, the proportion of downstream N₂O₅ emissions greater than or equal to the preset ratio of N₂O₅ emissions and the downstream N₂O₅ emission value are calculated based on the downstream N₂O₅ mass of the SCR within the effective power base window and the total power within the effective power base window. The upstream N₂O₅ emission value is calculated based on the total power within the effective power base window and the upstream N₂O₅ mass. Specifically, the N₂O₅ emission value for each effective power base window is calculated by dividing the sum of instantaneous N₂O₅ emissions by the sum of instantaneous N₂O₅ power, thus allowing for the statistical calculation of the N₂O₅ emission values ​​for all effective power base windows. It should be noted that since GB17691 defines PEMS test compliance based on whether the value is greater than 690 mg / kWh, if the proportion of emission values ​​greater than 690 mg / kWh in all power base windows exceeds 10%, the emissions are considered non-compliant. Therefore, the downstream N₂O₅ emission value at the 90th percentile after sorting from smallest to largest is compared with 690 mg / kWh; if it is greater than or equal to 690 mg / kWh, the emissions are considered to exceed the standard. Furthermore, the nitrogen oxide emission ratio values ​​of all power base windows can be sorted from smallest to largest. The nitrogen oxide emission ratio threshold of the "nitrogen oxide emission ratio analysis unit" can be corrected based on the nitrogen oxide emission ratio value at the 90th position. That is, the nitrogen oxide emission ratio value at the 90th position calculated based on the PEMS feature array is divided by the emission ratio value of the "nitrogen oxide emission ratio analysis unit". This is used as a correction coefficient to correct the emission ratio threshold of the "nitrogen oxide emission ratio analysis unit". This allows the prediction and assessment of PEMS emission levels to be achieved solely through the calculation of the "nitrogen oxide emission ratio analysis unit".

[0084] The following specific example further explains and illustrates the quadratic emission ratio estimation based on PEMS feature arrays. (Reference) Figure 5 As shown, quadratic emission estimation based on PEMS feature arrays may include the following steps:

[0085] Step S301: Construct the PEMS data group.

[0086] Specifically, to construct the PEMS data set, first, driving cycle data with nitrogen oxide emissions exceeding the standard are imported and classified into three categories: high-speed range with vehicle speed greater than v2, medium-speed range with vehicle speed greater than v1 and less than or equal to v2, and low-speed range with vehicle speed less than or equal to v1. Then, N1 data points are extracted from the high-speed range, N2 data points are extracted from the medium-speed range, and N3 data points are extracted from the low-speed range. The extracted data points are then arranged in the order of urban, suburban, and highway road condition data to construct the PEMS data set.

[0087] Step S302: Identify the valid power base window based on the PEMS data set.

[0088] Specifically, when identifying the effective power base window, first determine whether the cumulative instantaneous power of m data points is greater than or equal to the power of one WHTC cycle. If it is, increment the power base window counter by 1. Then, determine whether the ratio of the average power of the window to the rated power is greater than p%. If it is, it is determined to be an effective power base window, and the nitrogen oxide emission ratio is calculated for the effective power base window; if not, it is determined to be an ineffective power base window, and the calculation is abandoned.

[0089] Step S303: Calculate the nitrogen oxide emission ratio for the effective power base window.

[0090] Specifically, after identifying the effective power base window, the NOx emission ratio is calculated based on the downstream NOx mass of the SCR within the effective power base window, the total power of the effective power base window (i.e., the total engine power), and the upstream NOx mass of the SCR. Specifically, the downstream NOx emission ratio can be calculated by dividing the downstream NOx mass of the SCR within the effective power base window by the total power of the effective power base window; the upstream NOx emission ratio can be calculated by dividing the upstream NOx mass of the SCR within the effective power base window by the total power of the effective power base window.

[0091] According to the vehicle emission prediction method of this invention, the driving cycle data of a vehicle is cleaned. The driving cycle data includes multiple data points, each including the actual driving data of the vehicle at the same moment. A specific emission data group of nitrogen oxides (NOx) is constructed based on the cleaned driving cycle data. An initial specific emission estimate is performed by comparing the emission data group to determine whether the specific emission of NOx exceeds the standard. If the specific emission of NOx exceeds the standard, the driving cycle data in the specific emission data group is classified into different vehicle speed groups, with each data point as a unit. A preset number of data points are extracted from each vehicle speed group, and all extracted data points are sorted to obtain a data point sequence. The data groups include low-speed, medium-speed, and high-speed groups. The data point sequence is spliced ​​to construct a PEMS feature array, and a secondary specific emission estimate is performed based on the PEMS feature array to determine the specific emission level of NOx. Therefore, this method is not only applicable to actual user driving, but also effectively reduces the false alarm rate of the model by continuously monitoring and judging the vehicle emission level and by splicing the data.

[0092] In one embodiment, the method further includes: constructing a nitrogen oxide concentration data set based on data-cleaned driving cycle data, and performing a concentration emission estimate on the concentration data set to determine whether the nitrogen oxide concentration emission exceeds the standard.

[0093] Specifically, for valid driving cycle data filtered by data boundary conditions, a nitrogen oxide concentration data set can be generated. For example, a nitrogen oxide concentration data set can be formed by 5,000 valid data points, and a nitrogen oxide ratio emission data set can be formed by 6 nitrogen oxide concentration data sets, so as to facilitate the assessment of nitrogen oxide concentration emission level and nitrogen oxide ratio emission level.

[0094] Furthermore, for the nitrogen oxide concentration data set, the minimum calibrable effective data duration can be set to t, referencing the duration of the PEMS test, to evaluate the nitrogen oxide concentration emission level. This can prevent insufficient statistical validity due to the limited data volume of short driving cycles.

[0095] For example, in a specific case, for a Class N2 heavy-duty commercial diesel vehicle, a driving cycle data set is imported, totaling 2400 data packets. After filtering the data based on boundary conditions, 1800 packets remain as valid data points. If the minimum valid data duration for the nitrogen oxide concentration data set is set to 3000 packets, and the current 1800 packets do not meet this requirement, data from the next driving cycle is added until the required 3000 packets of valid data are reached, thus providing data for subsequent assessment of nitrogen oxide concentration emission levels. Then, six nitrogen oxide concentration data sets are combined to form a nitrogen oxide ratio emission data set, providing data for subsequent assessment of nitrogen oxide ratio emission levels.

[0096] In one embodiment, estimating the concentration emissions of a concentration data set to determine whether the concentration emissions of nitrogen oxides exceed the standard includes: obtaining the total number of data points for each driving cycle in the concentration data set and the ratio of the number of data points with a concentration of nitrogen oxides downstream of the SCR greater than or equal to a preset concentration to the total number of data points; determining the proportion of the concentration of nitrogen oxides downstream of the SCR in the concentration data set that is greater than or equal to a preset concentration based on the total number of data points for each driving cycle and the ratio; identifying that the proportion exceeds a proportion threshold, and determining that the concentration emissions of nitrogen oxides exceed the standard.

[0097] For example, taking a preset concentration of 500 ppm as an example, the proportion of data in the concentration data set where the downstream nitrogen oxide concentration of SCR is greater than or equal to 500 ppm is obtained, and the concentration of nitrogen oxides is used to identify whether the emission of nitrogen oxides exceeds the standard. Specifically, when the proportion is less than the first concentration proportion threshold (e.g., 5%), it can be determined that the emission is qualified; when the proportion is greater than or equal to the first concentration proportion threshold (e.g., 5%) and less than the second concentration proportion threshold (e.g., 10%), it can be determined that the emission exceeds the standard; when the proportion is greater than or equal to the second concentration proportion threshold (e.g., 10%), it can be determined that the emission is seriously exceeded. It should be noted that the nitrogen oxide concentration downstream of SCR is used to determine whether the nitrogen oxide concentration emission exceeds the standard, while the nitrogen oxide concentration upstream of SCR in the driving cycle data is only used for statistics and comparison. When a significant abnormality (increase or decrease) occurs, it can be identified as an abnormality in the original engine exhaust, and the exhaust level assessment can be discontinued.

[0098] In one embodiment, the above concentration ratio is obtained in the following manner:

[0099] K=(t1*p1+...+tn*pn) / (t1+...+tn)

[0100] Where K is the concentration ratio, tn is the total number of data points in the nth driving cycle data in the concentration data group, and pn is the ratio of the number of data points in the nth driving cycle data whose downstream nitrogen oxide concentration of SCR is greater than or equal to the preset concentration to the total number of data points in the nth driving cycle data.

[0101] In other words, taking a preset concentration of 500 ppm as an example, for the concentration ratio K of nitrogen oxides with a concentration greater than or equal to 500 ppm, it is equal to the sum of the products of the total number of data points tn in the corresponding driving cycle data and the proportion of data points with nitrogen oxide concentrations greater than 500 ppm pn, divided by the total number of data points in the driving cycle data in the concentration data group.

[0102] In one embodiment, the method further includes: based on the specific emission level, modifying at least one of the cleaning conditions corresponding to data cleaning, the data conditions corresponding to constructing the specific emission data set, the estimation conditions corresponding to the initial specific emission estimation, the data conditions corresponding to constructing the PEMS feature array, and the data conditions corresponding to constructing the concentration data set.

[0103] In specific examples, the number of data points extracted for different vehicle speed ranges (N1, N2, N3), the numerical values ​​for each speed range (v1, v2, v3), and the window average power percentage limit (p%) in the effective power base window calculation module can all be made configurable parameters. This facilitates adaptive adjustments during model trial runs to iteratively improve model prediction accuracy. It should be noted that when modifying the data conditions corresponding to the construction of the PEMS feature array, the specific numerical values ​​or upper and lower limits of the numerical ranges specified in relevant regulations (such as GB17691 and HJ857) are not modified. Modifications can only be made based on the relevant regulations, such as within the specified numerical ranges.

[0104] The following specific example will further explain and illustrate the estimation of vehicle nitrogen oxide concentration emissions and initial relative emissions.

[0105] Figure 6 A flowchart of concentration emission estimation and initial relative emission estimation according to a specific embodiment of the present invention is provided, with reference to... Figure 6 As shown, concentration emission estimation and initial ratio emission estimation may include the following steps:

[0106] Step S401: Construct a nitrogen oxide concentration dataset based on driving cycle data.

[0107] Step S402: Perform nitrogen oxide concentration analysis based on the concentration data set. This may include: statistically analyzing the proportion of downstream nitrogen oxide concentrations greater than or equal to 500 ppm; calculating the average upstream nitrogen oxide concentration; calculating the average downstream nitrogen oxide concentration; and calculating the urea / fuel consumption ratio.

[0108] Step S403: Estimate whether nitrogen oxide emissions exceed the standard based on the concentration ratio. This may include: when the concentration ratio K is less than the first concentration ratio threshold x1, the emissions can be determined to be compliant; when the concentration ratio K is greater than or equal to the first concentration ratio threshold x1 and less than the second concentration ratio threshold x2, the emissions can be determined to exceed the standard; when the concentration ratio K is greater than or equal to the second concentration ratio threshold x2, the emissions can be determined to be severely exceeded.

[0109] Step S404: Construct a nitrogen oxide ratio emission data set based on the concentration data set.

[0110] Specifically, for constructing specific emission data sets, the total work done in the PEMS test can be referenced, and a concentration data set (where N can be set between 1 and 10) can be set as the minimum effective data volume to evaluate the specific emission levels of nitrogen oxides. This can prevent insufficient statistical validity caused by the small amount of data from short driving cycles.

[0111] Step S405: Perform specific emission analysis of nitrogen oxides based on the comparative emission data set. This may include: calculating the urea / fuel consumption ratio; calculating upstream specific nitrogen oxide emissions by calculating the upstream nitrogen oxide emission mass and the total work done in the technical driving cycle; and calculating downstream specific nitrogen oxide emissions by calculating the downstream nitrogen oxide emission mass and the total work done in the technical driving cycle.

[0112] Step S406: Initially estimate whether the nitrogen oxide emission ratio exceeds the standard based on the downstream emission ratio. This may include: when the downstream emission ratio Q is less than the first emission ratio threshold y1, it can be determined that the emission is compliant; when the downstream emission ratio Q is greater than or equal to the first emission ratio threshold y1 and less than the second emission ratio threshold y2, it can be determined that the emission exceeds the standard; when the downstream emission ratio Q is greater than or equal to the second emission ratio threshold y2, it can be determined that the emission is severely exceeded.

[0113] It should be noted that the urea / fuel consumption ratio is only used for statistics and comparison. When there is a significant abnormality (increase or decrease), it can be identified as an engine exhaust abnormality, and exhaust level assessment can be discontinued.

[0114] In summary, the vehicle emission prediction method according to embodiments of the present invention cleans the vehicle's driving cycle data, which includes multiple data points, each containing actual driving data of the vehicle at the same time. A specific emission data set of nitrogen oxides (NOx) is constructed based on the cleaned driving cycle data. An initial specific emission estimate is performed by comparing the emission data set to determine if the NOx specific emission exceeds the standard. If the NOx specific emission exceeds the standard, the driving cycle data in the specific emission data set is classified into different vehicle speed groups, with each data point representing a predetermined number of data points extracted from each speed group. All extracted data points are then sorted to obtain a data point sequence, including low-speed, medium-speed, and high-speed groups. The data point sequence is then concatenated to construct a PEMS feature array, and a secondary specific emission estimate is performed based on the PEMS feature array to determine the NOx specific emission level. Therefore, this method is not only applicable to actual user driving but also effectively reduces the model's false alarm rate by continuously monitoring and judging vehicle emission levels and by concatenating the data.

[0115] Figure 7 A structural block diagram of a vehicle according to an embodiment of the present invention is shown below. Figure 7As shown, the vehicle 600 includes: a memory 601, a processor 602, and a vehicle emission prediction program stored in the memory 601 and executable on the processor 602. When the processor 602 executes the program, it implements the vehicle emission prediction method described above.

[0116] According to an embodiment of the present invention, the vehicle's driving cycle data is cleaned, including multiple data points, each containing actual driving data of the vehicle at the same moment. A nitrogen oxide (NOx) specific emission data set is constructed based on the cleaned driving cycle data. An initial specific emission estimate is performed by comparing the emission data set to determine if the NOx specific emission exceeds the standard. If the NOx specific emission exceeds the standard, the driving cycle data in the specific emission data set is classified into different vehicle speed groups, with each data point representing a predetermined number of data points extracted from each speed group. All extracted data points are then sorted to obtain a data point sequence, including low-speed, medium-speed, and high-speed groups. The data point sequence is then concatenated to construct a PEMS feature array, and a secondary specific emission estimate is performed based on the PEMS feature array to determine the NOx specific emission level. Therefore, this method is not only applicable to actual user driving but also allows for continuous monitoring and judgment of vehicle emission levels. Furthermore, by concatenating the data, the false alarm rate of the model can be effectively reduced.

[0117] It should be understood that, although Figure 1-6 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1-6 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0118] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a processor-included system or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0119] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0120] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0121] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0122] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0123] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method of estimating vehicle emissions, characterized by, The method includes: The driving cycle data of the vehicle is cleaned. The driving cycle data includes multiple data points, and each data point includes the actual driving data of the vehicle at the same time. A set of nitrogen oxide specific emissions data is constructed based on the cleaned driving cycle data, and an initial specific emission estimate is performed on the set of specific emissions data to determine whether the specific emissions of nitrogen oxides exceed the standard. To determine that the specific emissions of nitrogen oxides exceed the standard, the driving cycle data in the specific emission data group is classified into different vehicle speed groups based on the data points. A preset number of data points are extracted from each vehicle speed group, and all extracted data points are sorted to obtain a data point sequence. The data groups include low-speed group, medium-speed group and high-speed group. The data point sequence is spliced ​​to construct a PEMS feature array, and a secondary specific emission estimation is performed based on the PEMS feature array to determine the specific emission level of nitrogen oxides. Specifically, the PEMS feature array is divided into multiple power base windows based on the engine instantaneous power of the data points. For each power base window, validity is identified based on the engine average power of the power base window. When a power base window is identified as valid, the specific emission of nitrogen oxides is calculated based on the downstream nitrogen oxide mass of the SCR in the valid power base window, the total power of the valid power base window, and the upstream nitrogen oxide mass of the SCR in the valid power base window.

2. The vehicle emission estimation method according to claim 1, characterized by, Performing an initial specific emission estimate on the specific emission data set to determine whether the specific emissions of nitrogen oxides exceed the limit includes: Obtain the total mass and cumulative work of downstream nitrogen oxides from the SCR for each driving cycle in the specific emission data set; The specific emission value of nitrogen oxides downstream of SCR in the specific emission data set is determined based on the total mass and cumulative work of nitrogen oxides downstream of SCR in each driving cycle data set; The specific emission value is identified as exceeding the specific emission threshold, thus determining that the specific emission of nitrogen oxides exceeds the standard.

3. The vehicle emission estimation method according to claim 1, characterized by, Extract a preset number of data points from each of the vehicle speed groups, including: If the number of data points in the vehicle speed group is greater than or equal to the preset number, extract the preset number of data points sequentially from the vehicle speed group. Determine that the number of data points in the vehicle speed group is greater than or equal to K * the preset number and less than the preset number, and randomly extract data points from the vehicle speed group until the number of extracted data points equals the preset number, where 0 < K < 1; If the number of data points for the vehicle speed group is less than K * the preset number, stop constructing the PEMS feature array.

4. The vehicle emission estimation method according to claim 1, characterized by, The data point sequence is concatenated to construct a PEMS feature array, including: Obtain the vehicle speed gradient between two adjacent data points in the data point sequence; Determine the upper and lower limits of the number of data points in the data segment to be generated; The data point sequence is processed according to the vehicle speed gradient, the upper limit value, and the lower limit value to generate multiple data segments; The PEMS feature array is generated based on multiple data fragments.

5. The vehicle emission estimation method according to claim 4, characterized by, The data point sequence is processed according to the vehicle speed gradient, the upper limit value, and the lower limit value to generate multiple data segments, including: If the current data point and the previous data point are in the same vehicle speed group, and the vehicle speed gradient between the current data point and the previous data point is less than or equal to the gradient threshold, then the following processing is performed: If the number of data points in the current data segment is less than the upper limit value, add the current data point to the current data segment. If the number of data points in the current data segment is greater than or equal to the upper limit value, the current data segment is added to the current vehicle speed group, and the current data point is added to a new data segment.

6. The vehicle emission estimation method according to claim 5, characterized by, The data point sequence is processed according to the vehicle speed gradient, the upper limit value, and the lower limit value to generate multiple data segments, and the process further includes: If the current data point and the previous data point are in the same vehicle speed group, and the vehicle speed gradient between the current data point and the previous data point is greater than the gradient threshold, then the following processing is performed: If the number of data points in the current data segment is greater than or equal to the lower limit value, the current data segment is added to the current vehicle speed group, and the current data point is added to a new data segment. If the number of data points in the current data segment is determined to be less than the lower limit, then the data points in the current data segment are cleared, and the current data points are added to the cleared current data segment.

7. The vehicle emission estimation method according to claim 6, characterized by, The data point sequence is processed according to the vehicle speed gradient, the upper limit value, and the lower limit value to generate multiple data segments, and the process further includes: If the current data point and the previous data point are in different speed groups, the following processing is performed: If the number of data points in the current data segment is greater than or equal to the lower limit value, the current data segment is added to the vehicle speed group corresponding to the previous data point, the current data point is added to a new data segment, and the new data segment is temporarily added to the vehicle speed group corresponding to the current data point. If the number of data points in the current data segment is less than the lower limit, the data points in the current data segment are cleared, the current data points are added to the cleared current data segment, and the current data segment is temporarily added to the vehicle speed group corresponding to the current data points.

8. The vehicle emission estimation method according to any one of claims 1-7, characterized by, The method further includes: A concentration data set of nitrogen oxides is constructed based on the cleaned driving cycle data, and the concentration emission is estimated based on the concentration data set to determine whether the concentration emission of nitrogen oxides exceeds the standard.

9. The vehicle emission prediction method according to claim 8, characterized in that, Estimating the concentration emissions from the concentration data set to determine whether the nitrogen oxide concentration emissions exceed the limits includes: Obtain the total number of data points for each driving cycle in the concentration data group and the ratio of the number of data points with a nitrogen oxide concentration greater than or equal to a preset concentration downstream of the SCR to the total number of data points; The proportion of downstream nitrogen oxide concentrations in the concentration data group that are greater than or equal to the preset concentration is determined based on the total number and ratio of data points for each driving cycle. If the ratio exceeds a ratio threshold, it is determined that the concentration of nitrogen oxides emitted exceeds the standard.

10. The vehicle emission prediction method according to claim 8, characterized in that, The method further includes: Based on the specific emission level, at least one of the following is corrected: the cleaning conditions corresponding to the data cleaning, the data conditions corresponding to the construction of the specific emission data set, the estimation conditions corresponding to the initial specific emission estimation, the data conditions corresponding to the construction of the PEMS feature array, and the data conditions corresponding to the construction of the concentration data set.

11. A vehicle, characterized in that, include: A memory, a processor, and a vehicle emissions prediction program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the vehicle emissions prediction method according to any one of claims 1-10.

Images