Intelligent monitoring method for vehicle carbon emission based on data processing

Abstract

The present application relates to carbon emission analysis monitoring technical field, specifically to a kind of vehicle carbon emission intelligent monitoring method and system based on data processing.The method includes: obtaining linear steady-state emission model;In current test cycle, the engine speed, engine load and intake pressure of test vehicle are collected, and then the speed straight line, load straight line and intake pressure straight line are obtained, and the overall extension slope is obtained;Engine speed, engine load and intake pressure at each time in current test cycle are mapped into rectangular coordinate system, and the convex hull wrapped all data points is obtained;Extension straight line is obtained, and the convex hull is divided into two parts;Then first compensation factor and second compensation factor are obtained;Instantaneous compensation factor is obtained based on first and second compensation factors;Carbon emission of current test cycle is obtained based on linear steady-state emission model, and then instantaneous compensation factor is used to correct carbon emission to obtain corrected carbon emission.The present application can accurately monitor vehicle carbon emission.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of carbon emission analysis and monitoring, and particularly relates to a vehicle carbon emission intelligent monitoring method and system based on data processing. BACKGROUND

[0002] Vehicle carbon emission monitoring is an important means to evaluate the amount of carbon dioxide emissions during vehicle operation, and is of great significance to achieving the goal of energy saving and emission reduction and promoting the development of green transportation. The existing mainstream direct monitoring methods include exhaust gas analyzers and portable emission measurement systems (PEMS). Compared with the exhaust gas analyzer monitoring method, PEMS has lower cost and does not require frequent operation and maintenance by professional personnel. At the same time, PEMS is an integrated monitoring device that can monitor the emission of various pollutants (including carbon dioxide) in vehicle exhaust in real time and record vehicle driving data. Therefore, PEMS is more suitable for monitoring vehicle carbon emissions under real road conditions.

[0003] The existing PEMS for vehicle carbon emission monitoring is divided into pre-preparation (selecting test vehicles and planning test routes, installing device main bodies and connecting or installing communication cables and power supplies), test performance (exhaust sampling, measuring exhaust parameters and recording engine and environmental data), and final data processing and analysis. The average emission level is calculated, and the outliers are identified to achieve intelligent monitoring of carbon emissions.

[0004] The existing PEMS monitoring algorithm is generally designed based on steady-state conditions, that is, the engine operates at a relatively stable speed and load. At this time, the engine parameters change little, the combustion process is relatively stable, and the emission characteristics are also relatively regular. However, under urban congestion conditions, the traffic conditions are complex and changeable, and the vehicle is frequently in transient conditions such as starting and stopping, accelerating and decelerating. The calculation method based on steady-state conditions cannot accurately capture the emission changes in the transient response process of the engine, resulting in deviations in the calculation results. SUMMARY

[0005] To solve the above technical problems, the purpose of the present application is to provide a vehicle carbon emission intelligent monitoring method and system based on data processing, and the technical solution adopted is as follows:

[0006] In a first aspect, an embodiment of the present application provides a vehicle carbon emission intelligent monitoring method based on data processing, which comprises:

[0007] Obtaining a linear steady-state emission model; collecting engine speed, engine load and intake pressure of the test vehicle in the current test period;

[0008] The engine speed straight line, the engine load straight line and the intake pressure straight line are obtained based on the engine speed, the engine load and the intake pressure respectively; and the overall extension slope is obtained based on the slopes of the engine speed straight line, the engine load straight line and the intake pressure straight line.

[0009] The engine speed, the engine load and the intake pressure at each time point in the current test period are mapped into a two-dimensional rectangular coordinate system, and a convex hull wrapping all data points in the two-dimensional rectangular coordinate system is obtained; the extension straight line is obtained by using the overall extension slope and the center point of the convex hull, and the convex hull is divided into two parts;

[0010] The first compensation factor is obtained according to the areas and the number of data points of the two parts in the convex hull; the second compensation factor is obtained according to the perpendicular distances from the data points in the convex hull to the extension straight line; and the instantaneous compensation factor is obtained based on the first and second compensation factors.

[0011] The average of the engine speed and the average of the engine load in the current test period are brought into the linear steady-state emission model to obtain the carbon emission of the current test period; and the instantaneous compensation factor is used to correct the carbon emission of the current test period to obtain the corrected carbon emission.

[0012] Preferably, the engine speed straight line, the engine load straight line and the intake pressure straight line are obtained based on the engine speed, the engine load and the intake pressure respectively, comprising:

[0013] The engine speed, the engine load and the intake pressure in the current test period are used to form original data curves respectively, and the least square method is used for straight line fitting processing on the three original data curves respectively to obtain the engine speed straight line, the engine load straight line and the intake pressure straight line.

[0014] Preferably, the overall extension slope is obtained based on the slopes of the engine speed straight line, the engine load straight line and the intake pressure straight line, comprising:

[0015] The average of the slopes of the engine speed straight line, the engine load straight line and the intake pressure straight line is calculated, and is denoted as the overall extension slope.

[0016] Preferably, the engine speed, the engine load and the intake pressure at each time point in the current test period are mapped into a two-dimensional rectangular coordinate system, comprising:

[0017] The engine speed, the engine load and the intake pressure in the current test period are normalized, and then the normalized data are mapped into a two-dimensional rectangular coordinate system; the horizontal coordinate of a data point in the two-dimensional coordinate system is the collection time corresponding to the data point, and the vertical coordinate is the normalized value of the data value of the data point.

[0018] Preferably, the extension straight line is obtained by using the overall extension slope and the center point of the convex hull, and the convex hull is divided into two parts, comprising:

[0019] The straight line passing through the convex hull center point and having a slope of the overall extension slope is denoted as an extension straight line.

[0020] Preferably, the first compensation factor is obtained according to the area and the number of data points of the two parts in the convex hull, including:

[0021] The part with an area less than or equal to the area of the other part in the two parts divided by the convex hull is denoted as an area first part, and the other part is denoted as an area second part, and the area ratio of the area first part and the area second part is an area feature; the part with a number of data points less than or equal to the number of data points in the other part in the two parts divided by the convex hull is denoted as a data point number first part, and the other part is denoted as a data point number second part, and the ratio of the number of data points of the data point number first part and the data point number second part is a data point number feature; the difference between the first preset value and the area feature is negatively correlated mapped by using an exponential function with a natural constant as a base to obtain a first mapping result; the difference between the first preset value and the data point number feature is negatively correlated mapped by using an exponential function with a natural constant as a base to obtain a second mapping result; and the first and second mapping results are weighted and summed to obtain the first compensation factor.

[0022] Preferably, the second compensation factor is obtained according to the perpendicular distance of each data point in the convex hull to the extension straight line, including:

[0023] The variance of the perpendicular distance of each data point to the extension straight line is obtained and normalized to obtain the second compensation factor.

[0024] Preferably, the instantaneous compensation factor is obtained based on the first and second compensation factors, including:

[0025] The difference between the first preset value and the first compensation factor is calculated, and the mean value of the difference and the second compensation factor is obtained to obtain the instantaneous compensation factor.

[0026] Preferably, the corrected carbon emission amount is obtained by correcting the carbon emission amount of the current test period by using the instantaneous compensation factor, including:

[0027] The first preset value is added to the instantaneous compensation factor, and then multiplied by the carbon emission amount of the current test period to obtain the corrected carbon emission amount.

[0028] In a second aspect, the present application also provides a vehicle carbon emission intelligent monitoring system based on data processing, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the computer program is executed by the processor, the steps of a vehicle carbon emission intelligent monitoring method based on data processing are implemented.

[0029] The embodiment of the present application has at least the following beneficial effects: the present application establishes a linear steady-state emission model, collects engine speed, engine load and intake pressure of a vehicle to be tested in a current test cycle, obtains a speed straight line, a load straight line and an intake pressure straight line, then obtains an overall extension slope for representing the overall change trend of the three kinds of data; then the engine speed, the engine load and the intake pressure at each time in the current test cycle are mapped into a two-dimensional rectangular coordinate system, and a convex hull wrapping all data points in the two-dimensional rectangular coordinate system is obtained, the extension straight line is obtained by using the overall extension slope and the center point of the convex hull, and the convex hull is divided into two parts; then the instantaneous compensation factor of the current test cycle is obtained by analyzing the convex hull divided into two parts, the carbon emission of the current test cycle is corrected by using the instantaneous compensation factor, and the corrected carbon emission of the current test cycle is obtained. The transient compensation factor is introduced to optimize the existing carbon emission calculation model under steady-state condition, so as to more specifically consider the change of emission in the engine transient response process, and realize accurate and effective emission monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the drawings needed to be used in the following embodiment or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0031] Figure 1 A method flow chart of a vehicle carbon emission intelligent monitoring method based on data processing provided by the embodiment of the present application;

[0032] Figure 2 A convex hull division schematic diagram of a vehicle carbon emission intelligent monitoring method based on data processing provided by the embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following describes the specific implementation, structure, features and effects of a vehicle carbon emission intelligent monitoring method and system according to the present application in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0035] The application provides a vehicle carbon emission intelligent monitoring method and system based on data processing.

[0036] Embodiment 1: The main application scenario of the application is that the carbon emission of a vehicle is monitored by analyzing vehicle carbon emission data.

[0037] Please refer to Figure 1 which shows a method flowchart of a vehicle carbon emission intelligent monitoring method based on data processing provided by an embodiment of the application, and the method comprises the following steps:

[0038] Step S1, a linear steady-state emission model is acquired; engine speed, engine load and intake pressure of a test vehicle are collected in a current test period.

[0039] Firstly, PEMS carbon emission data collection needs to be prepared in advance, mainly including:

[0040] 1. Select target vehicles and plan test routes: select appropriate vehicles according to test purposes, and ensure that they meet test standards. Test vehicles must be representative, and should be benchmark vehicles or mass-produced vehicles. Meanwhile, test routes containing different road conditions such as urban roads, rural roads and highways are designed. Regulations stipulate that test routes should include urban roads, suburban roads and highways, and the actual proportion of the three types of routes is allowed to deviate by ± 5%.

[0041] 2. Equipment installation: install the PEMS equipment body according to the requirements of the equipment manufacturer's manual, and avoid the adverse effects of electromagnetic interference, dust, electric shock, vibration and poor heat dissipation. Meanwhile, install an exhaust flow meter; the range of the equipment should match the expected exhaust flow range during the PEMS test process. The exhaust flow meter is tightly connected with the vehicle exhaust pipe in the manner recommended by the equipment manufacturer and is prevented from leaking. Then, install sampling pipes, satellite navigation positioning systems, weather stations and ECU communication cables (the installation process of such equipment is a known technology, and is not described here).

[0042] 3. Equipment inspection: before the instrument is powered on, check all joints by visual and tactile methods to confirm that they are not loose, and prevent the joints from being loosened due to vibration during the test process. Check the status of the PEMS power supply and perform power-on, start and preheating operations.

[0043] Next, start the test, start the vehicle and turn on the PEMS system; PEMS should start sampling before the vehicle starts, measure exhaust parameters and record engine and environmental parameters. The conditions for the formal start of the test are that the engine coolant temperature is above 70°C, or changes less than 2°C within 5 minutes (whichever comes first, but not later than 20 minutes after engine start). During the test, exhaust sampling, measuring exhaust parameters, etc. should be continuously carried out, mainly measuring carbon emissions, and exhaust parameters include engine speed, engine load and exhaust pressure.

[0044] When collecting data, the test period and the frequency of collection need to be set according to the needs, and the frequency of collection and the test period can be set according to the needs. The application gives a reference test period of 30 minutes, and the test period is also the emission result of the carbon emission output every test period. Thus, the time series data in each test period is preprocessed, including data denoising, outlier identification and missing value filling.

[0045] The existing technology uses PEMS to monitor vehicle carbon emissions, which is usually based on steady-state conditions for calculation and design; In the city congestion condition, the engine is in transient operation state for a long time, and the algorithm based on steady-state condition cannot accurately capture the emission changes in the engine transient response process, resulting in deviation of the calculation result. For example, under steady-state conditions, the algorithm may consider that the carbon emission of the engine at a certain speed and load is fixed, but under transient conditions, due to incomplete combustion, poor fuel atomization and other factors, the actual carbon emission may increase significantly, but the algorithm cannot reflect this change in time.

[0046] First of all, it needs to be clear that the method of calculating carbon emissions based on steady-state conditions is: in the automobile engine bench test, let the engine run stably at a certain speed and load for a period of time, measure and record its exhaust carbon emission data, and the emission data is usually calculated by establishing a mathematical model, which can be generally expressed as a linear steady-state emission model:

[0047] E=a×RPM+b×L+c,

[0048] Where E is the carbon emission, RPM is the engine speed, L is the engine load; a, b, c are model parameters obtained by fitting test data; the model is used to monitor and predict the carbon emissions of the vehicle.

[0049] The a, b, c parameters are usually obtained by engine bench test, measuring the emission of pollutants at different speed and load combinations, and then using mathematical methods such as least squares to fit the test data. The general operation steps are as follows (prior art):

[0050] Design experiment: set a series of different combinations of speed and load on the engine bench; record the amount of pollutant emissions under each combination.

[0051] Establish the equation set: put the data of each test point into the linear steady-state emission model; obtain a set of linear equations about a, b, c.

[0052] Solve the parameters: use the least squares method to solve the linear variance set, so that the sum of squares of errors between the model prediction value and the actual measured value is minimized; thus obtain the optimal a, b, c results. Thus the linear steady-state emission model is obtained, and the establishment of the linear steady-state emission model is prior art, which will not be described in detail here.

[0053] Step S2, based on the engine speed, engine load and intake pressure, respectively obtain the speed straight line, load straight line and intake pressure straight line; based on the slope of the speed straight line, load straight line and intake pressure straight line, obtain the overall extension slope.

[0054] The actual problem existing in the above steady-state emission model is the core of this step. Research shows that the size of vehicle carbon emissions is closely related to the speed, load and intake pressure of the vehicle; when the traffic conditions are complex and changeable, the vehicle is frequently in transient conditions such as starting and stopping, acceleration and deceleration; the speed, load and intake pressure will all change to a large extent, and such changes will further lead to an increase in carbon emissions; in fact, due to the changes in such parameters, the combustion stability is destroyed, the air-fuel ratio is mismatched, the turbocharger hysteresis effect is aggravated, and the aftertreatment efficiency is reduced, etc. Mechanisms, which together lead to a significant increase in carbon emissions. Therefore, this step combines the analysis of the change characteristics of speed, load and intake pressure; builds a transient compensation factor to optimize the above steady-state emission calculation model.

[0055] First, use the engine speed, engine load and intake pressure in the current test period to form the original data curve, and use the least squares method (WLS) to perform linear fitting processing on the three original data curves to obtain the speed straight line, load straight line and intake pressure straight line, respectively, denoted as.

[0056] Further, the average of the slopes of the speed straight line, load straight line and intake pressure straight line is calculated, denoted as the overall extension slope, which represents the overall extension direction of the three straight lines, indicating the overall change direction of the data.

[0057] Step S3, map the engine speed, engine load and intake pressure at each time in the current test period to a two-dimensional rectangular coordinate system, and obtain the convex hull that wraps all data points in the two-dimensional rectangular coordinate system; use the overall extension slope and the center point of the convex hull to obtain the extension straight line, and divide the convex hull into two parts.

[0058] In step S2, the rotation speed straight line, the load straight line and the intake pressure straight line are obtained to represent the overall trend direction of the three kinds of data. Further, the data needs to be mapped into a two-dimensional rectangular coordinate system for comprehensive analysis.

[0059] Specifically, the engine rotation speed, engine load and intake pressure in the current test period are normalized, and then the normalized data is mapped into a two-dimensional rectangular coordinate system. The abscissa of a data point in the two-dimensional coordinate system is the collection time corresponding to the data point, and the ordinate is the normalized value of the data value of the data point. Thus, a scatter plot of the engine rotation speed, engine load and intake pressure normalized and mapped into a two-dimensional rectangular coordinate system in the current test period is obtained. The fusion analysis of multiple indicators can macroscopically reflect the non-steady state change characteristics of the data in the current test period, and is more accurate than single analysis, reveals more internal change relations, and can better analyze the internal change relations between the engine rotation speed, engine load and intake pressure in the current test period. The three of engine rotation speed, engine load and intake pressure have similar change characteristics under transient conditions, that is, strong correlation. At this time, the overall extension slope obtained is more accurate (the change direction and trend are basically the same), which can ensure the accuracy of the subsequent analysis and calculation results.

[0060] Further, a convex hull algorithm (Graham Scan algorithm) is used to obtain a feature polygon, that is, a convex hull, in all data points in the two-dimensional rectangular coordinate system. The convex hull represents the smallest area polygon that encloses all data points, which needs to be divided and analyzed later, as shown in Figure 2 .

[0061] Specifically, the center point of the convex hull is determined, and a straight line passing through the center point of the convex hull and having a slope of the overall extension slope is determined, which is denoted as an extension straight line. The extension straight line divides the convex hull into two parts, and then subsequent feature analysis is performed based on the two parts. The divided convex hull is shown in Figure 2 . Figure 2 In the formula, K represents the overall extension slope. By placing various data in the same coordinate system for analysis, the efficiency is higher than that of single curve local analysis, the time complexity is low, and it is more intuitive and visual, which can meet the real-time and rapid monitoring requirements.

[0062] In step S4, a first compensation factor is obtained according to the area and the number of data points of the two parts in the convex hull, a second compensation factor is obtained according to the perpendicular distance of each data point in the convex hull to the extension straight line, and a transient compensation factor is obtained based on the first and second compensation factors.

[0063] Based on the divided convex hull in step S3, the transient compensation factor is analyzed. The first compensation factor is obtained according to the area and the number of data points of the two parts in the convex hull.

[0064] Specifically, a part with an area less than or equal to the area of the other part in the two parts of the convex hull division is recorded as an area first part, and the other part is recorded as an area second part. The area ratio of the area first part and the area second part is an area feature. A part with a data point quantity less than or equal to the data point quantity of the other part in the two parts of the convex hull division is recorded as a data point quantity first part, and the other part is recorded as a data point quantity second part. The ratio of the data point quantity of the data point quantity first part and the data point quantity second part is a data point quantity feature. A first mapping result is obtained by using an exponential function with a natural constant as a base to negatively correlate the difference between the first preset value and the area feature. A second mapping result is obtained by using an exponential function with a natural constant as a base to negatively correlate the difference between the first preset value and the data point quantity feature. A first compensation factor is obtained by weighted sum of the first and second mapping results.

[0065] The calculation model of the first compensation factor is specifically:

[0066]

[0067] Among them, represents the first compensation factor, exp represents the exponential function with the natural constant as the base, and 1 represents the first preset value; represents the area of the area first part in the two parts of the convex hull division, represents the area of the area second part in the two parts of the convex hull division, represents the area feature, less than or equal to , represents the first mapping result; represents the data point quantity of the data point quantity first part in the two parts of the convex hull division, represents the data point quantity of the data point quantity second part, less than or equal to , represents the data point quantity feature, represents the second mapping result; , is the weight size, and since the two terms are analyzed from different dimensions; therefore, the scheme gives a reference weight of 0.5.

[0068] Further, a second compensation factor is obtained according to the perpendicular distance of each data point in the convex hull to the extended straight line. Specifically, the variance of the perpendicular distance of each data point to the extended straight line is obtained and normalized to obtain the second compensation factor. The smaller the value of the second compensation factor, the more stable it represents, and vice versa.

[0069] ​Finally, the first compensation factor and the second compensation factor are integrated to obtain an instantaneous compensation factor. Specifically, a difference between the first preset value and the first compensation factor is calculated, and a mean value of the difference and the second compensation factor is obtained to obtain the instantaneous compensation factor.

[0070] The purpose of calculating the difference between the first preset value and the first compensation factor is to unify the linear change relationship of the first compensation factor and the second compensation factor, so that the difference between the first preset value and the first compensation factor and the linear change relationship of the second compensation factor are unified, and both satisfy that the greater the value is, the higher the non-steady-state intensity is.

[0071] Through the division of the convex hull in step S3, the influence of other directions can be effectively weakened by using discrete analysis and variance calculation. Since the processed data is time series data, there is a collection interval in two-dimensional space, and if the distribution characteristics are directly calculated, the collection interval will cause physical influence. Therefore, the calculation of this step is more reasonable and innovative based on the division processing; the two calculations in the first compensation factor calculation can reflect the real dispersion of the data; and the vertical distance in the second compensation factor calculation can directly weaken the influence of the collection interval on the analysis of the spatial data points, and accurately analyze the data distribution characteristics. Therefore, the instantaneous compensation factor corresponding to the current test period can be obtained.

[0072] In step S5, the mean value of the engine speed and the mean value of the engine load in the current test period are brought into the linear steady-state emission model to obtain the carbon emission amount of the current test period; and the instantaneous compensation factor is used to correct the carbon emission amount of the current test period to obtain a corrected carbon emission amount.

[0073] In step S4, the instantaneous compensation factor corresponding to the current test period is obtained, and then the average carbon emission amount in a test period is calculated to represent the carbon emission condition of the vehicle in the period.

[0074] Therefore, the mean value of the engine speed and the mean value of the engine load in the current test period are obtained, which are brought into the linear steady-state emission model obtained in step S1 to obtain the carbon emission amount E of the current test period, which can be used to represent the average level of carbon emission of the vehicle in the current test period.

[0075] Finally, the instantaneous compensation factor is used to correct the carbon emission amount of the current test period to obtain a corrected carbon emission amount. Specifically, the first preset value is added to the instantaneous compensation factor, and then multiplied by the carbon emission amount of the current test period to obtain the corrected carbon emission amount.

[0076] The calculation model of the corrected carbon emission amount is specifically:

[0077] ,

[0078] wherein, Indicates the corrected carbon emissions for the current test cycle. The unit is usually used to measure the total amount of carbon dioxide emissions. The output data unit of PEMS monitoring vehicle carbon emissions is usually tons of carbon dioxide equivalent ( ), kg CO2 equivalent ( ), grams of carbon dioxide equivalent ( ); P represents the transient compensation factor for the current test cycle, obtained by calculating the non-steady-state characteristics of the distribution; 1 represents the first preset value, and E represents the carbon emissions for the current test cycle. The result obtained by the algorithm under steady-state conditions is multiplied by the transient compensation factor to obtain the optimized and compensated carbon emissions result. This allows the calculation process to more specifically consider changes in emissions during the engine's transient response, achieving accurate and effective emissions monitoring.

[0079] By following the above steps to obtain the vehicle's carbon emission results during each test cycle and setting emission thresholds based on specific scenarios or industry standards, intelligent monitoring of vehicle carbon emissions can be achieved. The subsequent basic operations are:

[0080] Calculate corrected carbon emissions for each test cycle and save all collected data to a local hard drive or cloud server for subsequent analysis. Export all raw data collected during the test from the PEMS system. Utilize specialized software tools to conduct in-depth analysis of the data, calculate average emissions, identify outliers, and assess compliance with emission standards.

[0081] In summary, this application optimizes the existing carbon emission calculation model under steady-state conditions by introducing a transient compensation factor, thereby more specifically considering the changes in emissions during the transient response of the engine and achieving accurate and effective emission monitoring.

[0082] Example 2: This example provides a data-processing-based intelligent vehicle carbon emissions monitoring system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When executed by the processor, the computer program implements the steps of a data-processing-based intelligent vehicle carbon emissions monitoring method. Since Example 1 has already described a data-processing-based intelligent vehicle carbon emissions monitoring method in detail, it will not be further elaborated here.

[0083] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0084] The various embodiments in the specification are described in progressive manner, and the same or similar parts between the various embodiments can be mutually referred to, and each embodiment focuses on the difference from other embodiments.

[0085] The above description is merely preferred embodiments of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A vehicle carbon emission intelligent monitoring method based on data processing, characterized in that: The method includes: Obtain a linear steady-state emission model; collect the engine speed, engine load, and intake pressure of the test vehicle during the current test cycle; A speed straight line, a load straight line, and an intake pressure straight line are obtained based on the engine speed, the engine load, and the intake pressure, respectively; and an overall extension slope is obtained based on the slopes of the speed straight line, the load straight line, and the intake pressure straight line; The engine speed, engine load, and intake pressure at each moment in the current test cycle are mapped into a two-dimensional rectangular coordinate system, and the convex hull enclosing all data points in the two-dimensional rectangular coordinate system is obtained. The extension line is obtained using the overall extension slope and the center point of the convex hull, and the convex hull is divided into two parts. Obtaining a first compensation factor based on the areas of the two parts and the number of data points in the convex hull; obtaining a second compensation factor based on the perpendicular distance between each data point in the convex hull and the extended straight line; and obtaining an instantaneous compensation factor based on the first and second compensation factors; Substituting the mean value of the engine speed and the mean value of the engine load in the current test cycle into the linear steady-state emission model to obtain the carbon emissions of the current test cycle; using the instantaneous compensation factor to correct the carbon emissions of the current test cycle to obtain the corrected carbon emissions; The linear steady-state emission model is: E=a×RPM+b×L+c, Where E is carbon emissions, RPM is engine speed, L is engine load; a, b, c are model parameters obtained by fitting the test data; Obtaining the first compensation factor according to the areas of the two parts and the number of data points in the convex hull includes: Obtain the part of the two parts divided by the convex hull whose area is less than or equal to the area of ​​the other part, record it as the first area part, then record the other part as the second area part, and the area ratio of the first area part to the second area part is the area feature; obtain the part of the two parts divided by the convex hull whose number of data points is less than or equal to the number of data points in the other part, record it as the first data point number part, then record the other part as the second data point number part, and the ratio of the number of data points in the first data point number part to the second data point number part is the data point number feature; use an exponential function with a natural constant as the base to negatively correlate the difference between the first preset value and the area feature to obtain a first mapping result; use an exponential function with a natural constant as the base to negatively correlate the difference between the first preset value and the data point number feature to obtain a second mapping result; perform weighted summation on the first and second mapping results to obtain a first compensation factor; Obtaining the second compensation factor according to the vertical distance between each data point in the convex hull and the extended straight line includes: Obtain the variance of the vertical distance from each data point to the extended straight line and normalize it to obtain a second compensation factor; The acquiring of the instantaneous compensation factor based on the first and second compensation factors includes: calculating a difference between the first preset value and the first compensation factor, and obtaining the average of the difference and the second compensation factor to obtain the instantaneous compensation factor.

2. The method for intelligent monitoring of vehicle carbon emissions based on data processing according to claim 1, characterized in that: The obtaining of the speed straight line, the load straight line and the intake pressure straight line based on the engine speed, the engine load and the intake pressure respectively includes: The engine speed, engine load and intake pressure in the current test cycle are used to construct original data curves respectively, and the three original data curves are respectively subjected to linear fitting processing using the least squares method to obtain the speed straight line, load straight line and intake pressure straight line.

3. The method for intelligent monitoring of vehicle carbon emissions based on data processing according to claim 1, characterized in that: The obtaining of the overall extension slope based on the slopes of the speed line, the load line, and the intake pressure line includes: The average of the slopes of the speed line, the load line, and the intake pressure line is calculated and recorded as the overall extension slope.

4. The method for intelligent monitoring of vehicle carbon emissions based on data processing according to claim 1, characterized in that: The mapping of the engine speed, engine load, and intake pressure at each moment in the current test cycle into a two-dimensional rectangular coordinate system includes: The engine speed, engine load and intake pressure in the current test cycle are normalized, and then the normalized data are mapped to a two-dimensional rectangular coordinate system. The horizontal coordinate of a data point in the two-dimensional coordinate system is the collection time corresponding to the data point, and the vertical coordinate is the normalized value of the data value of the data point.

5. The method for intelligent monitoring of vehicle carbon emissions based on data processing according to claim 1, characterized in that: The extended straight line is obtained by using the overall extended slope and the center point of the convex hull, and the convex hull is divided into two parts, including: The straight line passing through the center point of the convex hull and having a slope equal to the overall extension slope is recorded as the extension line; the extension line divides the convex hull into two parts.

6. The method for intelligent monitoring of vehicle carbon emissions based on data processing according to claim 1, characterized in that: The method of correcting the carbon emissions of the current test period using the instantaneous compensation factor to obtain the corrected carbon emissions includes: The first preset value is added to the instantaneous compensation factor and then multiplied by the carbon emissions of the current test cycle to obtain the corrected carbon emissions.

7. A vehicle carbon emission intelligent monitoring system based on data processing, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by a processor, the steps of the vehicle carbon emission intelligent monitoring method based on data processing are implemented as described in any one of claims 1 to 6.

Images