A carbon emission prediction method and device based on geographic information data and vehicle driving data

Abstract

The application provides a carbon emission prediction method and device based on geographic information data and vehicle driving data, which fully considers various factors and belongs to the carbon emission prediction technology based on the combination of geographic information data and actual vehicle driving data. Four typical road driving conditions are developed by using the geographic information data, then the cold start factor correction calculation is carried out based on the cold start and hot car hub test, then the road correction factor is proposed according to the actual driving data to evaluate the difference between the actual and the hub, and finally the corresponding mileage weighting of the four road types is carried out according to the user travel route, so as to realize the carbon emission prediction. The method has the advantages of high prediction accuracy and good universality, and can effectively and accurately predict the travel carbon emission.

Description

Technical Field

[0001] This application relates to the field of carbon emission prediction, specifically to a carbon emission prediction method and apparatus based on geographic information data and vehicle driving data. Background Technology

[0002] Related research indicates that emissions of greenhouse gases such as CO2 contribute to global warming, making the control of CO2 emissions an urgent matter. Therefore, my country plans to incorporate CO2 and other greenhouse gases into the next phase of its emission regulations. Consequently, forecasting carbon emissions of CO2 and other greenhouse gases from vehicles is of great significance in helping the government achieve effective carbon emission control.

[0003] Accurate prediction of vehicle carbon emissions is of great significance for environmental and economic development. However, in practice, vehicle carbon emission prediction is related to many factors. From the user's perspective, different travel routes and vehicle operating conditions vary significantly, both of which have a substantial impact on emissions. From the vehicle's perspective, emissions deteriorate during the initial cold start, showing a significant difference compared to emissions after the engine warms up. Current technologies give little consideration to these factors and lack carbon emission prediction technologies that comprehensively consider geographic information data and actual vehicle driving data. Furthermore, there is a lack of optimized methods for accurately predicting vehicle carbon emissions while fully taking these factors into account. Therefore, these aspects have become urgent problems to be solved in vehicle carbon emission prediction. Summary of the Invention

[0004] This application provides a carbon emission prediction method and apparatus based on geographic information data and vehicle driving data. The feature of this invention is that it utilizes hub test data and actual vehicle driving data to comprehensively consider multiple influencing factors such as user travel, geographic information, and cold start without relying on actual road emission testing equipment, and proposes a carbon emission prediction method based on geographic information data and actual vehicle driving data.

[0005] A carbon emission prediction method based on geographic information data and actual vehicle driving data, the method mainly includes the following steps:

[0006] Step S11: Obtain geographic information data, classify roads based on the geographic information data, and obtain road classification information. The road classification information includes four different typical road driving conditions, which are composed of multiple vehicle speed information.

[0007] Step S12: Test the vehicle's wheel emission data under the above-mentioned typical driving conditions on different roads. The vehicle wheel emission data shall include at least the marked data information for the two stages of vehicle cold start and warm-up. The marked data information shall include at least the vehicle speed, engine speed, torque and CO2 emissions per second.

[0008] Step S13: Test the CO2 emissions Gc1, Gc2, Gc3, and Gc4 under four different typical road driving conditions during the cold start phase, and the CO2 emissions Gh1, Gh2, Gh3, and Gh4 under the four different typical road driving conditions during the warm-up phase when the cold start mileage is reached. Calculate the cold start correction factor C under the four road conditions. i =G ci / G hi (i = 1, 2, 3, 4)

[0009] Step S14: Collect the actual vehicle speed, engine speed, torque, and corresponding mileage La1, La2, La3, and La4 during the cold start phase of the vehicle under four different typical road driving conditions.

[0010] Step S15: Based on the engine map, calculate the carbon emissions Grb1, Grb2, Grb3, and Grb4 of the vehicle during the actual driving process under four different typical road driving conditions after the cold start phase, and calculate the actual road correction factor R. i =G rbi / G hi (i = 1, 2, 3, 4)

[0011] Step S16: Determine the road type by selecting multiple vehicle speed information feature parameters and calculating the maximum mutual information coefficient (MIC) correlation between four different typical road driving conditions and the actual vehicle operation data of multiple corresponding roads. Determine the road threshold based on the correlation calculation results.

[0012] Step S17: Based on the user's travel route, perform correlation calculations on different roads, select the road with the highest maximum mutual information coefficient (MIC) for four different typical road driving conditions that also meets the road threshold condition, mark it as the current travel road, and determine the type of travel route and the corresponding mileages L1, L2, L3, and L4 for the four different typical road driving conditions.

[0013] Step S18: Perform a weighted calculation of the mileage corresponding to four different typical road driving conditions to calculate the total carbon emissions of this trip.

[0014] Furthermore, the four types of typical road driving conditions include secondary roads, main roads, expressways, and highways. The multiple vehicle speed information is divided into 14 characteristic parameters: average vehicle speed, average operating speed, speed standard deviation, idle speed ratio, acceleration ratio, deceleration ratio, constant speed ratio, average acceleration, maximum acceleration, acceleration standard deviation, average deceleration, minimum deceleration, deceleration standard deviation, and relative positive acceleration.

[0015] Furthermore, in step S16, the road type determination includes the following steps:

[0016] Step S161: Select 14 feature parameters for vehicle speed information segmentation, and determine the maximum mutual information coefficient (MIC) correlation between the actual vehicle operation data of four different road typical driving conditions and N corresponding roads. Here, N is a positive integer greater than or equal to 1000. If X represents the feature parameters of the four road conditions, Y represents the driving feature parameters of the N typical roads, and I represents the mutual information of the relationship between X and Y, the formula for calculating the maximum mutual information coefficient correlation is:

[0017]

[0018] Where a and b are the number of intervals divided based on the maximum mutual information coefficient; B is the maximum value of the interval, which is the sum of all feature parameters raised to the power of 0.6.

[0019] Step S162: Based on the correlation calculation results, the road determination threshold is determined using the normal distribution 3σ principle, i.e., the three sigma criterion, and the boundary value of 99.73% of the normal distribution is selected as the road threshold.

[0020] Furthermore, a weighted calculation using four different road mileage methods is performed to determine the total carbon emissions for this trip.

[0021] g co2 If the road segment at departure is a road of class k, where k is the road type number (k = 1, 2, 3, 4), then the total emissions are , the CO2 emissions during the warm-up phase under typical driving conditions on different roads are Gh, the actual road correction factor R is calculated, the mileage La corresponding to different typical driving conditions on different roads is , and C is the cold start correction factor defined in step S13.

[0022] g co2 =G hk ×(C k -1)×R k ×L ak +∑(G hi ×R i ×L i (i = 1, 2, 3, 4)

[0023] Furthermore, the total carbon emissions in the region can be predicted based on vehicle type, vehicle ownership, and user travel patterns.

[0024] Furthermore, actual driving data after the engine coolant temperature is reached is selected, and combined with the engine map, the fuel consumption Er is calculated based on the corresponding engine speed n, torque T, specific fuel consumption e, power P, vehicle speed v, and number of data points t during driving, as shown in the following formula:

[0025] P = T × n / 9550,

[0026]

[0027] A carbon emission prediction device based on geographic information data and actual vehicle driving data, the device mainly includes the following modules:

[0028] The geographic information acquisition module is used to acquire geographic information data, classify roads based on the geographic information data, and obtain road classification information. The road classification information includes four different typical road driving condition information, which consists of multiple vehicle speed information.

[0029] The vehicle wheel hub emission test module is used to test vehicle wheel hub emission data under the above-mentioned typical driving conditions on different roads. The vehicle wheel hub emission data includes at least the marked data information for the two stages of vehicle cold start and warm-up. The marked data information includes at least the vehicle speed, engine speed, torque and CO2 emissions per second.

[0030] The CO2 emission module for driving conditions is used to test the CO2 emissions (Gc1, Gc2, Gc3, Gc4) under four different typical road driving conditions during the cold start phase, and the CO2 emissions (Gh1, Gh2, Gh3, Gh4) under the four different typical road driving conditions during the warm-up phase when the cold start mileage is reached. The module also calculates the cold start correction factor for the four road conditions.

[0031] C i =G ci / G hi (i = 1, 2, 3, 4)

[0032] The mileage acquisition module is used to collect the actual vehicle speed, engine speed, torque, and corresponding mileage La1, La2, La3, and La4 during the cold start phase of the vehicle under four different typical road driving conditions.

[0033] The carbon emission calculation module, combined with the engine map, calculates the carbon emissions Grb1, Grb2, Grb3, and Grb4 of the vehicle during actual driving under four different typical road driving conditions after the cold start phase, and calculates the actual road correction factor R. i =G rbi / G hi (i = 1, 2, 3, 4)

[0034] The road type determination module is used to determine the road type. It selects multiple vehicle speed information feature parameters to calculate the maximum mutual information coefficient (MIC) correlation between four different typical road driving conditions and the actual vehicle operation data of multiple corresponding roads. Based on the correlation calculation results, the road threshold is determined.

[0035] The road correlation calculation module is used to calculate the correlation of different roads based on the user's travel route. It selects the road with the highest maximum mutual information coefficient (MIC) under four different typical road driving conditions, which must also meet the road threshold conditions, and marks it as the current travel road. It also determines the type of road in the travel route and the corresponding mileages L1, L2, L3, and L4 for the four different typical road driving conditions.

[0036] The mileage-weighted calculation module performs mileage-weighted calculations for four different typical road driving conditions to calculate the total carbon emissions for this trip.

[0037] Furthermore, the device can predict the total carbon emissions in a region based on vehicle type, vehicle ownership, and user travel patterns.

[0038] This invention discloses a carbon emission prediction method based on geographic information data and actual vehicle driving data. This method fully considers various factors and belongs to a comprehensive carbon emission prediction technology that combines geographic information data and actual vehicle driving data. First, it develops four typical road driving conditions using geographic information data. Then, it calculates a cold start factor correction based on cold start and hot-vehicle wheel rotation tests. Next, it proposes a road correction factor based on actual driving data to assess the difference between actual and wheel rotation data. Finally, it applies a corresponding mileage weighting to the four road types based on the user's travel route to achieve carbon emission prediction. This method has advantages such as high prediction accuracy and good versatility, and can effectively and accurately predict travel carbon emissions. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a flowchart of the prediction method of the present invention;

[0041] Figure 2 This is a technical roadmap for the prediction method of the present invention;

[0042] Figure 3 This is a schematic diagram of the driving conditions of the secondary branch road in this invention;

[0043] Figure 4 This is a schematic diagram of engine speed and torque under secondary branch road driving conditions in one embodiment of the present invention;

[0044] Figure 5 This is an engine map diagram in one embodiment of the present invention;

[0045] Figure 6 This is a schematic diagram of MIC analysis for each road in one embodiment of the present invention; Figure 7 This is a schematic diagram of the normal distribution of MIC analysis in one embodiment of the present invention; Detailed Implementation

[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0048] In one embodiment, a carbon emission prediction method based on geographic information data and actual vehicle driving data mainly includes the following steps:

[0049] Step S11: Obtain geographic information data, classify roads according to the geographic information data, and obtain road classification information. The road classification information includes four different typical road driving conditions. The typical road driving conditions information consists of multiple vehicle speed information. The four different typical road driving conditions information include secondary roads, main roads, expressways, and highways. The multiple vehicle speed information is divided into 14 feature parameters, namely: average vehicle speed, average operating vehicle speed, speed standard deviation, idle speed ratio, acceleration ratio, deceleration ratio, constant speed ratio, average acceleration, maximum acceleration, acceleration standard deviation, average deceleration, minimum deceleration, deceleration standard deviation, and relative positive acceleration.

[0050] Step S12: Test the vehicle's wheel emission data under the above-mentioned typical driving conditions on different roads. The vehicle wheel emission data shall include at least the marked data information for the two stages of vehicle cold start and warm-up. The marked data information shall include at least the vehicle speed, engine speed, torque and CO2 emissions per second.

[0051] Step S13: Test the CO2 emissions Gc1, Gc2, Gc3, and Gc4 under four different typical road driving conditions during the cold start phase, and the CO2 emissions Gh1, Gh2, Gh3, and Gh4 under the four different typical road driving conditions during the warm-up phase when the cold start mileage is reached. Calculate the cold start correction factor C under the four road conditions. i =G ci / G hi (i = 1, 2, 3, 4)

[0052] Step S14: Collect the actual vehicle speed, engine speed, torque, and corresponding mileage La1, La2, La3, and La4 during the cold start phase of the vehicle under four different typical road driving conditions.

[0053] Step S15: Based on the engine map, calculate the carbon emissions Grb1, Grb2, Grb3, and Grb4 of the vehicle during the actual driving process under four different typical road driving conditions after the cold start phase, and calculate the actual road correction factor R. i =G rbi / G hi (i = 1, 2, 3, 4)

[0054] Step S16: Determine the road type by selecting multiple vehicle speed information feature parameters and calculating the maximum mutual information coefficient (MIC) correlation between four different typical road driving conditions and the actual vehicle operation data of multiple corresponding roads. Determine the road threshold based on the correlation calculation results.

[0055] Step S17: Based on the user's travel route, perform correlation calculations on different roads, select the road with the highest maximum mutual information coefficient (MIC) for four different typical road driving conditions that also meets the road threshold condition, mark it as the current travel road, and determine the type of travel route and the corresponding mileages L1, L2, L3, and L4 for the four different typical road driving conditions.

[0056] Step S18: Perform a weighted calculation of the mileage corresponding to four different typical road driving conditions to calculate the total carbon emissions of this trip.

[0057] In another embodiment, reference Figure 1-6 A carbon emission prediction method based on geographic information data and actual vehicle driving data mainly includes the following steps:

[0058] 1. Based on the classification of roads using geographic information data, four different typical driving conditions for roads—secondary roads, main roads, expressways, and highways—are developed and divided into 14 characteristic parameters: average vehicle speed, average operating speed, speed standard deviation, idling ratio, acceleration ratio, deceleration ratio, constant speed ratio, average acceleration, maximum acceleration, acceleration standard deviation, average deceleration, minimum deceleration, deceleration standard deviation, and relative positive acceleration.

[0059] 2. Drum emissions tests were conducted for cold start and warm-up conditions under four different operating conditions, and vehicle speed, engine speed, torque and CO2 emissions (g / km) were collected every second.

[0060] 3. Statistical analysis of CO2 emissions G during the cold start phase of the cold start test. c1 G c2 G c3 G c4 And the corresponding CO2 emissions G during the warm-up test when the cold start mileage is reached. h1 G h2 G h3 G h4 Calculate the cold start correction factor C under four road conditions. i =G ci / G hi (i = 1, 2, 3, 4).

[0061] 4. Conduct real-world road tests on the vehicle under four different road conditions, collecting data on actual vehicle speed, engine speed, torque, and mileage (L) during the cold start phase. a1 L a2 L a3 L a4 .

[0062] 5. Calculate the carbon emissions G during the actual driving process after the cold start phase, based on the engine map. rb1 G rb2 G rb3 G rb4 Calculate the actual road correction factor R i =G rbi / G hi (i = 1, 2, 3, 4).

[0063] 6. Determine the road type.

[0064] (1) Fourteen feature parameters were selected to calculate the maximum mutual information coefficient (MIC) correlation between four operating conditions and 1000 corresponding road vehicle actual operation data. Let X be the feature parameters of the four road operating conditions, and Y be the driving feature parameters of 1000 typical roads, where a and b are the number of intervals divided based on the maximum mutual information coefficient; B is the maximum value of the interval, i.e., the sum of all feature parameters raised to the power of 0.6. The maximum mutual information coefficient correlation was calculated as follows:

[0065] (2) Based on the correlation calculation results, the road judgment threshold is determined using the normal distribution “3σ” three sigma principle, and the boundary value (small value) of 99.73% of the normal distribution is selected as the road threshold.

[0066] 7. Based on the user's route for this trip, perform correlation calculations on different roads, select the road with the highest MIC correlation among the four types of roads that meets the threshold conditions and record it as the current driving road, and determine the types of roads and corresponding mileages L1, L2, L3, and L4 for this trip.

[0067] 8. Perform weighted calculations based on four different road distances to calculate the total carbon emissions (g) for this trip. co2 (g) If the road segment at departure is a road of class k, where k is the road type number (k = 1, 2, 3, 4), and C is the cold start correction factor defined in step S13, then the total emissions are:

[0068] g co2 =G hk ×(C k -1)×R k ×L ak +∑(G hi ×R i ×L i (i = 1, 3, 3, 4).

[0069] 9. Predict the total carbon emissions of cities and regions based on vehicle types, vehicle ownership, and user travel patterns.

[0070] This invention discloses a carbon emission prediction method based on geographic information data and actual vehicle driving data. First, it develops four typical road driving conditions using geographic information data. Then, it calculates a cold start factor correction based on cold start and hot-vehicle wheel rotation tests. Next, it proposes a road correction factor based on actual driving data to assess the difference between actual and wheel rotation data. Finally, it applies a corresponding mileage weighting to the four road types based on the user's travel route to achieve carbon emission prediction. This method has advantages such as high prediction accuracy and good versatility, and can effectively predict travel carbon emissions.

[0071] In another embodiment, reference Figure 1-6The carbon emission prediction method based on geographic information data and actual vehicle driving data described in this invention adopts the following steps:

[0072] 1. Based on the classification of roads using geographic information data, develop typical driving conditions for four different types of roads: secondary roads, arterial roads, expressways, and highways. The driving conditions for secondary roads are as follows: Figure 2 As shown in Table 1, the 14 characteristic parameters for the four road conditions are as follows.

[0073] Table 1. 14 characteristic parameters for four road conditions

[0074]

[0075] 2. Select typical vehicles and conduct drum emission tests for cold start and warm-up on four road conditions: secondary roads, main roads, expressways and highways. Collect data on vehicle speed, engine speed, torque, CO2 emissions (g / km) and engine coolant temperature every second.

[0076] 3. Calculate the cold start correction factor. During the cold start test, the cold start ends when the engine coolant temperature reaches 70℃. The mileage during the cold start phase is collected, and the CO2 emissions (G) during the cold start phase are calculated. c1 G c2 G c3 G c4 The warm-up test involves raising the engine coolant temperature to 70°C before the test begins, and then calculating the CO2 emissions (G) at the corresponding cold start mileage during the warm-up test. h1 G h2 G h3 G h4 Meanwhile, since the operating characteristics of each stage are basically consistent under the same working conditions, it can be calculated that the overall carbon emissions after the cold start stage mileage in both the cold start test and the warm-up test are G. h1 G h2 G h3 G h4 Calculate the cold start correction factors C1, C2, C3, and C4 under the four operating conditions according to equation (1):

[0077] C i =G ci / G hi (i = 1, 2, 3, 4) (1)

[0078] 4. Cold start real-world road tests were conducted on the same vehicle model under four road conditions: secondary roads, main roads, expressways, and highways. Given the high cost of installing RDE / PEMS emission testing equipment, CO2 emissions were calculated by reading vehicle speed, engine speed, torque, and coolant temperature data second-by-second via the OBD interface. Mileage (L) was also collected when the coolant temperature reached 70℃. a1 L a2 L a3 L a4 Engine speed-torque, such as Figure 3 As shown.

[0079] 5. Select actual driving data after the engine coolant temperature reaches 70℃, and combine it with the engine map, such as... Figure 4 As shown. Fuel consumption E is calculated based on the corresponding engine speed n (r / min), torque T (N·m), specific fuel consumption e (g / kWh), power P (kW), vehicle speed v (km / h), and number of data points t during the driving process. r (g / km), as shown in equations (2) and (3):

[0080] P = T × n / 9550 (2)

[0081]

[0082] Similarly, the fuel consumption E during engine warm-up can be calculated. h Therefore, based on the principle of energy consumption equivalence, the carbon emissions G after the water temperature of the four types of roads meets the standards can be calculated. rb1 G rb2 G rb3 G rb4 As shown in equation (4):

[0083] G rbi =E ri / E hi ×G hi (i = 1, 2, 3, 4) (4)

[0084] Therefore, the difference in carbon emissions between the actual road and the hub can be calculated and denoted as the actual road correction factor, as shown in equation (5):

[0085] R i =G ｒｂi / G hi (i = 1, 2, 3, 4) (5)

[0086] During the cold start phase, the engine combustion process is complex; therefore, a cold start correction factor and a real-road correction factor are used to calculate the carbon emissions G during the actual road cold start phase. ra1 G ra2 G ra3 G ra4calculate:

[0087] G rai =G rbi ×C i =G hi ×C i ×R i (i = 1, 2, 3, 4) (6)

[0088] 6. During actual driving, users may find themselves traveling on main roads or similar types of roads, but environmental factors, vehicle conditions, or other factors can cause their speed to be lower or higher than normal, resulting in their current travel characteristics matching other road types, such as secondary roads. Therefore, road type determination is necessary.

[0089] (1) Using remote monitoring data, select 1,000 actual vehicle operation data for each of the four types of typical roads, calculate the 14 feature values ​​in Table 1, and perform correlation analysis on the four road conditions in step 1 using the maximum mutual information coefficient (MIC) algorithm.

[0090] Taking the MIC analysis of 1000 typical secondary roads under four road conditions as an example, the MIC calculation principle is as follows:

[0091] Let X in the dataset represent the characteristic parameters of four road conditions, and Y represent the driving characteristic parameters of 1000 typical sub-roads. Then there exists D = {X, Y|(x...} i y i ,i=1,2,…,n)},D∈R 2 The mutual information between X and Y is defined as follows:

[0092]

[0093] In the formula, p(x, y) is the joint probability density between X and Y, and p(x) and p(y) are the marginal probability densities of X and Y, respectively. If variables X and Y are independent, the result of I is 0, indicating that the two variables are unrelated. However, in practice, it is difficult to solve the joint probability density. To solve this problem, the maximum information coefficient is proposed.

[0094] The maximum mutual information coefficient (MIC) is represented by a scatter plot in a two-dimensional space, dividing the space into *a* and *b* intervals in the x and y directions, respectively. The joint probability between variables X and Y is determined by calculating the number of scatter points within each interval, thus effectively solving the aforementioned problem. The maximum mutual information value is selected as the MIC under different interval division criteria, and the calculation formula is as follows:

[0095]

[0096] The correlation coefficient analysis results of MIC for four operating conditions based on actual driving data of vehicles on typical secondary roads are as follows: Figure 5 As shown.

[0097] (2) According to Figure 5 Correlation analysis results show that the average MIC value for the secondary road condition is 0.79, significantly higher than that for other road conditions. Furthermore, the MIC analysis results for the secondary road exhibit a normal distribution. Therefore, the "3σ" principle of normal distribution is used to determine the road judgment threshold, such as... Figure 6 As shown, when the MIC value is greater than 0.61, it can be determined that the current driving road is actually a secondary road. Similarly, it can be determined whether the current driving road is a main road, expressway, or highway.

[0098] 7. Based on the user's actual travel data, perform MIC road correlation analysis, select the road type with the highest MIC correlation among the four types of roads that meets the threshold requirements and record it as the current travel road, and determine the mileage L1, L2, L3, and L4 of the secondary roads, main roads, expressways and highways passed through during the trip in sequence.

[0099] 8. Based on the road types and mileages along the route, as shown in Tables 2 and 3, perform a weighted calculation of road distribution.

[0100] Table 2 Distribution of Travel Routes 1

[0101] 1 Secondary branch road L1 2 Main road L2 3 expressway L3 4 highway L4

[0102] Calculate the total carbon emissions (g) of this trip. co2 (g) If the starting road segment is a secondary road, then the total emissions are

[0103] g co2 =G h1 ×(C1-1)×R1×L a1 +∑(G hi ×R i ×L i (i = 1, 2, 3, 4).

[0104] Table 3 Distribution of Travel Routes 2

[0105]

[0106]

[0107] If the starting point is a main road, then the total emissions are:

[0108] g co2 =G h2 ×(C2-1)×R2×L a2 +∑(C hi ×R i ×Li (i = 1, 2, 3, 4).

[0109] 9. Analyze the travel patterns of different users, calculate the total monthly carbon emissions of users of this type of vehicle, and finally predict the total carbon emissions of cities and regions based on vehicle type and vehicle ownership.

[0110] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0111] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0112] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. For example, the functional modules in the various embodiments of this application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0113] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A carbon emission prediction method based on geographic information data and actual vehicle driving data, the method mainly includes the following steps: Step S11: Obtain geographic information data, classify roads based on the geographic information data, and obtain road classification information. The road classification information includes four different typical road driving conditions, which are composed of multiple vehicle speed information. Step S12: Test the vehicle's wheel emission data under the above-mentioned typical driving conditions on different roads. The vehicle wheel emission data shall include at least the marked data information for the two stages of vehicle cold start and warm-up. The marked data information shall include at least the vehicle speed, engine speed, torque and CO2 emissions per second. Step S13: Test the CO2 emissions Gc1, Gc2, Gc3, and Gc4 under four different typical road driving conditions during the cold start phase, and the CO2 emissions Gh1, Gh2, Gh3, and Gh4 under the four different typical road driving conditions during the warm-up phase when the cold start mileage is reached. Calculate the cold start correction factor under the four road conditions. , Step S14: Collect the actual vehicle speed, engine speed, torque, and corresponding mileage La1, La2, La3, and La4 during the cold start phase of the vehicle under four different typical road driving conditions. Step S15: Based on the engine map, calculate the carbon emissions Grb1, Grb2, Grb3, and Grb4 of the vehicle during the actual driving process under four different typical road driving conditions after the cold start phase, and calculate the actual road correction factor. , Step S16 involves determining the road type by selecting multiple vehicle speed information feature parameters and calculating the maximum mutual information coefficient (MIC) correlation between four different typical road driving conditions and the actual vehicle operation data of multiple corresponding roads. Based on the correlation calculation results, a road threshold is determined. Step S16 includes the following steps: Step S161: Select 14 feature parameters for vehicle speed information segmentation, and determine the maximum mutual information coefficient (MIC) correlation between the actual vehicle operation data of four different road typical driving conditions and N corresponding roads. Here, N is a positive integer greater than or equal to 1000. If X represents the feature parameters of the four road conditions, Y represents the driving feature parameters of the N typical roads, and I represents the mutual information of the relationship between X and Y, the formula for calculating the maximum mutual information coefficient correlation is: ， Where a and b are the number of intervals divided based on the maximum mutual information coefficient; B is the maximum value of the interval, which is the sum of all feature parameters raised to the power of 0.6; Step S162: Based on the correlation calculation results, the road determination threshold is determined using the normal distribution 3σ principle, i.e., the three sigma criterion, and the boundary value of 99.73% of the normal distribution is selected as the road threshold. Step S17: Based on the user's travel route, perform correlation calculations on different roads, select the road with the highest maximum mutual information coefficient (MIC) for four different typical road driving conditions that also meets the road threshold condition, mark it as the current travel road, and determine the type of travel route and the corresponding mileages L1, L2, L3, and L4 for the four different typical road driving conditions. Step S18: Perform a weighted calculation of the mileage corresponding to four different typical road driving conditions to calculate the total carbon emissions of this trip.

2. The method according to claim 1, characterized in that, The four types of typical road driving conditions include secondary roads, main roads, expressways, and highways. The multiple vehicle speed information is divided into 14 characteristic parameters: average vehicle speed, average operating speed, speed standard deviation, idle speed ratio, acceleration ratio, deceleration ratio, constant speed ratio, average acceleration, maximum acceleration, acceleration standard deviation, average deceleration, minimum deceleration, deceleration standard deviation, and relative positive acceleration.

3. The method according to claim 1, characterized in that, The total carbon emissions for this trip were calculated by weighting the trip using four different road distances. If the road segment at departure is a road of class k, where k is the road type number (k=1,2,3,4), then the total emissions are calculated as follows: CO2 emissions during the warm-up phase under typical driving conditions on different roads are Gh; the actual road correction factor R is calculated; the mileage La corresponding to typical driving conditions on different roads is calculated; and C is the cold start correction factor defined in step S13. 。 4. The method according to claim 1, characterized in that, The total carbon emissions in the region are predicted based on vehicle type, vehicle ownership, and user travel patterns.

5. The method according to any one of claims 1 to 4, characterized in that, Based on actual driving data after the engine coolant temperature is reached, combined with the engine map, fuel consumption Er is calculated according to the corresponding engine speed n, torque T, specific fuel consumption e, power P, vehicle speed v, and number of data points t during driving, as shown in the following formula: ， 。 6. A carbon emission prediction device based on geographic information data and actual vehicle driving data, the device mainly includes the following modules: The geographic information acquisition module is used to acquire geographic information data, classify roads based on the geographic information data, and obtain road classification information. The road classification information includes four different typical road driving condition information, which consists of multiple vehicle speed information. The vehicle wheel emission test module is used to test vehicle wheel emission data under the above-mentioned typical driving conditions on different roads. The vehicle wheel emission data includes at least marked data information for two stages: cold start and warm-up. The marked data information includes at least vehicle speed, engine speed, torque, and CO2 emissions per second. The CO2 emission module for driving conditions is used to test the CO2 emissions (Gc1, Gc2, Gc3, Gc4) under four different typical road driving conditions during the cold start phase, and the CO2 emissions (Gh1, Gh2, Gh3, Gh4) under the four different typical road driving conditions during the warm-up phase when the cold start mileage is reached. The module also calculates the cold start correction factor for the four road conditions. , The mileage acquisition module is used to collect the actual vehicle speed, engine speed, torque, and corresponding mileage La1, La2, La3, and La4 during the cold start phase of the vehicle under four different typical road driving conditions. The carbon emission calculation module, combined with the engine map, calculates the carbon emissions Grb1, Grb2, Grb3, and Grb4 of the vehicle during actual driving under four different typical road driving conditions after the cold start phase, and calculates the actual road correction factor. , The road type determination module is used to determine the road type. It selects multiple vehicle speed information feature parameters to calculate the maximum mutual information coefficient (MIC) correlation between four different typical road driving conditions and the actual vehicle operation data of multiple corresponding roads. Based on the correlation calculation results, the road threshold is determined. The road correlation calculation module is used to calculate the correlation of different roads based on the user's travel route. It selects the road with the highest maximum mutual information coefficient (MIC) under four different typical road driving conditions, which must also meet the road threshold conditions, and marks it as the current travel road. It also determines the type of road in the travel route and the corresponding mileages L1, L2, L3, and L4 for the four different typical road driving conditions. The mileage-weighted calculation module performs mileage-weighted calculations for four different typical road driving conditions to calculate the total carbon emissions for this trip.

7. The apparatus according to claim 6, characterized in that, This device can predict the total carbon emissions in a region based on vehicle type, vehicle ownership, and user travel patterns.

Images