Method, device, processor and electronic equipment for predicting the wind area of a vehicle

Abstract

The application discloses a kind of prediction method, device, processor and electronic equipment of the wind area of vehicle.Therein, the method comprises: obtaining the size information of the vehicle to be predicted, wherein the size information of the vehicle to be predicted is used to indicate the size structure of the vehicle to be predicted;Call regression model, the wind area of the vehicle to be predicted is predicted, and the target wind area is obtained, wherein the regression model is based on the size information of multiple vehicles and the initial wind area of multiple vehicles, the regression relationship between them is fitted, the target wind area is used to indicate the predicted wind area of the vehicle to be predicted, the initial wind area is used to indicate the effective area of the front of multiple vehicles in air resistance effect, the category of the size information of the vehicle to be predicted is consistent with the category of the size information of multiple vehicles.The application solves the technical problem that the wind area of vehicle cannot be effectively predicted.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and more specifically, to a method, apparatus, processor, and electronic device for predicting the frontal area of ​​a vehicle. Background Technology

[0002] Currently, methods for estimating the frontal area of ​​vehicles typically include several different approaches: traditional measurement methods, direct acquisition from computer-aided design (CAD) models, simplified estimation formulas, and photographic estimation methods.

[0003] Among the relevant technologies, there are certain shortcomings in terms of cost, efficiency, accuracy, and applicability. In particular, in the early stages of vehicle design and in collaborations across the supply chain, it is impossible to make economical and efficient estimates of frontal area. This limits designers' ability to quickly evaluate and optimize vehicle aerodynamic performance. Therefore, the technical problem of effectively predicting the frontal area of ​​vehicles still exists.

[0004] There is currently no effective solution to the aforementioned technical problems. Summary of the Invention

[0005] This invention provides a method, apparatus, processor, and electronic device for predicting the windward area of ​​a vehicle, to at least solve the technical problem of the inability to effectively predict the windward area of ​​a vehicle.

[0006] According to one aspect of the present invention, a method for predicting the frontal area of ​​a vehicle is provided. The method may include: acquiring size information of the vehicle to be predicted, wherein the size information of the vehicle to be predicted represents the size structure of the vehicle; invoking a regression model to predict the frontal area of ​​the vehicle to be predicted, obtaining a target frontal area, wherein the regression model is obtained by fitting a regression relationship between the size information of multiple vehicles and the initial frontal areas of multiple vehicles, the target frontal area represents the predicted frontal area of ​​the vehicle to be predicted, the initial frontal areas represent the effective area of ​​the front of the multiple vehicles subjected to air resistance, and the category of the size information of the vehicle to be predicted is consistent with the category of the size information of the multiple vehicles.

[0007] Optionally, the method further includes: measuring the effective windward area of ​​multiple vehicles under air resistance at different wind speeds and directions; and based on the effective windward area, placing multiple vehicles in a wind tunnel to obtain the initial windward area of ​​multiple vehicles, wherein the wind tunnel is used to simulate the airflow around the multiple vehicles when they are moving to generate different wind speeds and directions.

[0008] Optionally, a regression model is invoked to predict the windward area of ​​the vehicle to be predicted, thereby obtaining the target windward area. This includes: determining the regression equation in the regression model using the size information of multiple vehicles as independent variables and the initial windward area of ​​multiple vehicles as dependent variables. The regression equation includes coefficients and intercepts. The coefficients represent the magnitude and direction of the influence of the size information of multiple vehicles on the initial windward area of ​​multiple vehicles, and the intercept represents the constant term of the regression equation. The regression equation is then invoked to predict the windward area of ​​the vehicle to be predicted, thereby obtaining the target windward area.

[0009] Optionally, the dimensional information of multiple vehicles includes width, height, ground clearance, tire tread width, and side window tilt angle. Using the dimensional information of multiple vehicles as independent variables and the initial frontal area of ​​multiple vehicles as dependent variables, the regression equation in the regression model is determined, including: using the dimensional information of multiple vehicles as independent variables and the initial frontal area of ​​multiple vehicles as dependent variables, determining the coefficients and intercepts, wherein the coefficients include the width coefficient, height coefficient, ground clearance coefficient, tire tread width coefficient, and side window tilt angle coefficient; determining the first product of width and width coefficient; determining the second product of height and height coefficient; determining the negative of the third product of ground clearance and ground clearance coefficient; determining the fourth product of tire tread width and tire tread width coefficient; determining the negative of the fifth product of side window tilt angle and side window tilt angle coefficient; determining the sum of the first, second, third, fourth, and fifth products, and the intercept; and using the sum as the regression equation.

[0010] Optionally, the regression equation is invoked to predict the frontal area of ​​the vehicle to be predicted, and the target frontal area is obtained. This includes inputting the width of the vehicle to be predicted, the height of the vehicle to be predicted, the ground clearance of the vehicle to be predicted, the tire tread width of the vehicle to be predicted, and the side window tilt angle of the vehicle to be predicted into the regression equation to obtain the target frontal area.

[0011] Optionally, the method further includes: comparing the target windward area with the initial windward area to obtain a comparison result, wherein the comparison result is used to represent the error between the target windward area and the initial windward area; and determining that the windward area of ​​the vehicle to be predicted has been successfully predicted in response to the error being less than or equal to an error threshold.

[0012] Optionally, the method further includes: acquiring the size information of multiple vehicles according to a time period, and updating the size information of the multiple vehicles.

[0013] According to another aspect of the present invention, a device for predicting the frontal area of ​​a vehicle is also provided. The device may include: an acquisition unit for acquiring size information of a vehicle to be predicted, wherein the size information of the vehicle to be predicted represents the size structure of the vehicle; and a prediction unit for invoking a regression model to predict the frontal area of ​​the vehicle to be predicted, obtaining a target frontal area, wherein the regression model is obtained by fitting a regression relationship between the size information of multiple vehicles and the initial frontal areas of multiple vehicles, the target frontal area represents the predicted frontal area of ​​the vehicle to be predicted, the initial frontal areas represent the effective area of ​​the front of the multiple vehicles subjected to air resistance, and the category of the size information of the vehicle to be predicted is consistent with the category of the size information of the multiple vehicles.

[0014] According to another aspect of the present invention, a processor is also provided. The processor is used to run a program, wherein the program executes the methods of the embodiments of the present invention during runtime.

[0015] According to another aspect of the present invention, an electronic device is also provided, wherein a processor is configured to run a program, wherein the program executes the method of the present invention during runtime.

[0016] According to another aspect of the present invention, a computer-readable storage medium is also provided. The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the method of the embodiments of the present invention.

[0017] According to another aspect of the present invention, a vehicle is also provided. The vehicle includes a memory and a processor. The memory stores an executable program; the processor runs the program, which, when executed, implements the methods described in the embodiments of the present invention.

[0018] In this embodiment of the invention, if it is necessary to predict the windward area of ​​a vehicle, the size information of the vehicle to be predicted can be obtained. This size information represents the vehicle's dimensional structure. A regression model can be invoked to predict the windward area of ​​the vehicle, yielding a target windward area. The regression model is obtained by fitting the regression relationship between the size information of multiple vehicles and their initial windward areas. The target windward area represents the predicted windward area of ​​the vehicle to be predicted, and the initial windward area represents the effective area of ​​the front of the multiple vehicles affected by air resistance. The category of the size information of the vehicle to be predicted is consistent with the category of the size information of the multiple vehicles. In other words, this invention only requires a few key dimensions of the vehicle and can complete the calculation in a short time by invoking a regression model, greatly improving prediction efficiency. This overcomes the limitations of related technologies that require a complete 3D CAD model or actual vehicle for design, thus solving the technical problem of ineffective prediction of vehicle windward area and achieving the technical effect of effectively predicting vehicle windward area. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0020] Figure 1 This is a flowchart of a method for predicting the windward area of ​​a vehicle according to an embodiment of the present invention;

[0021] Figure 2 This is a flowchart of a method for predicting the windward area of ​​a vehicle based on multiple linear regression according to an embodiment of the present invention;

[0022] Figure 3 This is a schematic diagram of a vehicle frontal area prediction device according to an embodiment of the present invention.

[0023] Figure 4 This is a structural block diagram of a vehicle according to an embodiment of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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 should fall within the scope of protection of the present invention.

[0025] 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 a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] According to an embodiment of the present invention, an embodiment of a method for predicting the windward area of ​​a vehicle is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] Figure 1 This is a flowchart of a method for predicting the frontal area of ​​a vehicle according to an embodiment of the present invention, such as... Figure 1 As shown, the method may include the following steps.

[0028] Step S102: Obtain the size information of the vehicle to be predicted.

[0029] In the technical solution provided by step S102 of the present invention, the size information of the vehicle to be predicted can be used to represent the size structure of the vehicle to be predicted.

[0030] In this embodiment, the dimensional information can be vehicle width A, height B, minimum ground clearance C, tire cross-section width D, and side window tilt angle E.

[0031] Optionally, vehicle width can represent the straight-line distance between the farthest points on the left and right sides of the vehicle, in meters. Vehicle width directly affects the size of the frontal area and is also an important parameter in design.

[0032] Alternatively, height B can refer to the vertical distance from the ground to the highest point of the vehicle's roof, also in meters. Vehicle height is another key factor in determining frontal area, especially for tall vehicles such as trucks and sport utility vehicles (SUVs).

[0033] Optionally, the minimum ground clearance C is the distance between the lowest point of the vehicle's underside and the road surface, measured in meters. This parameter affects the airflow distribution beneath the vehicle and also has some impact on the frontal area, especially at high speeds.

[0034] Optionally, the tire section width D is the width of the tire's contact patch with the ground, measured in meters. The shape and size of the tire have a significant impact on the overall aerodynamic characteristics of the vehicle, especially when the tire protrudes from the side of the vehicle body.

[0035] Optionally, the side window tilt angle E is the angular deviation of the window from the vertical direction, measured in degrees. The shape and angle of the windows affect airflow over the vehicle surface, especially at high speeds or in crosswinds, and have a significant impact on the calculation of the frontal area.

[0036] Optionally, these five dimensional information items together constitute the basic information describing the vehicle's dimensional structure and are indispensable inputs for predicting frontal area. Since this dimensional information is data that can be determined or easily obtained in the early stages of vehicle design, it can be effectively applied to the early stages of vehicle design, helping designers quickly evaluate the aerodynamic performance of different design schemes and thus make better design decisions.

[0037] Optionally, dimensional information can be obtained from multiple sources, including but not limited to using sketches or outline drawings from the vehicle design phase to read preliminary dimensional data; consulting publicly available vehicle technical manuals or online databases, which typically contain basic vehicle dimensional information; using modern measuring tools such as laser scanners and 3D scanners to perform non-contact dimensional measurements on vehicle models; obtaining dimensional data of key components from upstream suppliers through supply chain communication, which can be used to preliminarily calculate the overall vehicle dimensional information; and for existing vehicles, directly measuring the actual dimensions of the vehicle.

[0038] It should be noted that the above methods for obtaining size information are only illustrative examples, and no specific restrictions are imposed on the methods for obtaining size information.

[0039] Optionally, early access to dimensional information allows designers to consider aerodynamic performance during the conceptual design phase, adjusting designs promptly and optimizing frontal area to improve fuel efficiency and driving performance. Furthermore, frontal area prediction can be obtained solely from dimensional information, eliminating the need for complex software simulations and significantly reducing R&D costs and time, making the estimation process more streamlined. In supply chain management, sharing key dimensional information allows upstream and downstream companies to quickly assess vehicle performance, promoting more efficient and collaborative design and production processes. For competitor models, preliminary performance analysis can be conducted based solely on publicly available dimensional information without access to detailed CAD data, accelerating the development of market response strategies.

[0040] In this embodiment of the invention, obtaining the aforementioned dimensional information does not require complex equipment or actual vehicle testing; only design drawings or published vehicle specification sheets are needed. This significantly reduces the cost and time required for predicting the windward area, improving the efficiency and convenience of the prediction process. Simultaneously, it also makes it highly valuable for supply chain management and competitor analysis, enabling preliminary assessments of the windward area without the need for detailed CAD models or other sensitive information.

[0041] Step S104: Call the regression model to predict the windward area of ​​the vehicle to be predicted, and obtain the target windward area.

[0042] In the technical solution provided in step S104 of the present invention, the regression model is obtained by fitting the regression relationship between the size information of multiple vehicles and the initial frontal area of ​​multiple vehicles. The target frontal area can be used to represent the predicted frontal area of ​​the vehicle to be predicted, and the initial frontal area can be used to represent the effective area of ​​the front of multiple vehicles subjected to air resistance. The category of the size information of the vehicle to be predicted is consistent with the category of the size information of multiple vehicles.

[0043] In this embodiment, after obtaining the size information of the vehicle to be predicted, a regression model can be invoked to predict the windward area of ​​the vehicle to be predicted, thereby obtaining the target windward area.

[0044] Optionally, the regression model can be constructed based on historical datasets, which may include the size information of multiple known vehicles and their corresponding true frontal areas (initial frontal areas). The true frontal area, obtained through wind tunnel experiments or other high-precision measurement methods, is an important indicator of vehicle aerodynamic performance. Then, using a multiple linear regression algorithm, the complex relationship between the size information and the initial frontal area is learned and fitted, ultimately yielding a mathematical model, such as a regression equation, that can accurately predict the frontal area.

[0045] Optionally, the parameters (size information) of the regression model can be obtained through optimization during training. These parameters reflect the contribution and interaction of size information to the initial windward area.

[0046] Optionally, during the prediction phase, the size information of the vehicle to be predicted (such as vehicle width A, height B, minimum ground clearance C, tire section width D, and side window tilt angle E) can be used as input to the regression model. The size information of the vehicle to be predicted should be consistent with the size information of the multiple known vehicles used in training the regression model to ensure the accuracy and effectiveness of the regression model's predictions. After calling the regression model, it can calculate the predicted frontal area (target frontal area) of the vehicle to be predicted based on the input size information of the multiple vehicles. This process is fast, automatic, and requires no professional physical simulation or complex experimental conditions, greatly simplifying the evaluation process of frontal area.

[0047] Optionally, the target frontal area is an estimate that reflects the effective area of ​​air resistance determined by the vehicle's frontal structure under ideal conditions. By comparing it with the initial frontal area used to train the regression model, the prediction accuracy of the regression model can be verified, thus providing a preliminary understanding and judgment of aerodynamic performance during vehicle design or competitor analysis.

[0048] In this embodiment of the invention, once the regression model is built, it can be directly invoked, and the prediction process is completed almost instantly, without the need for complex physical experiments or lengthy numerical simulations, greatly improving prediction speed and efficiency. Furthermore, the prediction accuracy of the regression model is higher than that of estimations based on simple empirical formulas. Especially with continuous updates and optimization of the regression model, the accuracy can be maintained at a high level, meeting the needs of engineering design. This allows the prediction process to proceed without access to detailed CAD models or actual vehicles, helping designers gain a preliminary understanding and control of vehicle performance at an early stage.

[0049] In steps S102 to S104 of this application, if it is necessary to predict the windward area of ​​a vehicle, the size information of the vehicle to be predicted can be obtained. This size information represents the vehicle's dimensional structure. A regression model can be invoked to predict the windward area of ​​the vehicle, obtaining the target windward area. The regression model is obtained by fitting the regression relationship between the size information of multiple vehicles and their initial windward areas. The target windward area represents the predicted windward area of ​​the vehicle to be predicted, and the initial windward area represents the effective area of ​​the front of multiple vehicles affected by air resistance. The category of the size information of the vehicle to be predicted is consistent with the category of the size information of multiple vehicles. In other words, this invention only requires a few key dimensions of the vehicle and can complete the calculation in a short time by invoking a regression model, greatly improving prediction efficiency. This overcomes the limitations of related technologies that require a complete 3D CAD model or actual vehicle for design, thus solving the technical problem of ineffective prediction of vehicle windward area and achieving the technical effect of effectively predicting vehicle windward area.

[0050] The method described in this embodiment will be further described below.

[0051] As an optional embodiment, the method further includes: measuring the effective windward area of ​​the front of multiple vehicles under air resistance at different wind speeds and directions; and based on the effective windward area, placing the multiple vehicles in a wind tunnel to obtain the initial windward area of ​​the multiple vehicles, wherein the wind tunnel is used to simulate the airflow around the multiple vehicles when they are moving, so as to generate different wind speeds and directions.

[0052] In this embodiment, the effective frontal area of ​​multiple vehicles under air resistance can be measured at different wind speeds and directions. Then, based on this effective frontal area, the vehicles can be placed in a wind tunnel to obtain their initial frontal areas. That is, the actual frontal area measured through wind tunnel experiments is the initial frontal area.

[0053] Optionally, during the wind tunnel test preparation phase, a series of representative vehicle samples can be selected. These samples should cover as wide a range as possible, including vehicles of different brands, models, sizes, and styles. The experiment is conducted in a wind tunnel facility, a laboratory device that can simulate the airflow environment around a vehicle while it is in motion. By adjusting the wind speed and direction, airflow conditions under various driving conditions can be simulated.

[0054] Optionally, after the wind tunnel test preparation phase is completed, each vehicle sample can be placed in the wind tunnel. Using precise measuring tools within the wind tunnel (such as pressure sensors and flow meters), data can be collected at different wind speeds and directions to measure the effective frontal area of ​​each vehicle affected by air resistance. This effective frontal area refers to the surface area affected by air resistance when the vehicle's front is facing the airflow, and it is the basis for calculating aerodynamic performance.

[0055] Optionally, the effective windward area of ​​each vehicle under different wind speeds and directions is recorded and correlated with dimensional information (vehicle width A, height B, minimum ground clearance C, tire section width D, side window tilt angle E, etc.) to construct a detailed vehicle dataset (i.e., a historical dataset).

[0056] In this embodiment of the invention, the initial windward area obtained through wind tunnel experiments is used as part of the training regression model, which ensures that the prediction results of the regression model are closer to reality and improves the reliability of the regression model. It is suitable for preliminary prediction of windward area in the absence of detailed CAD models or actual vehicles, and provides an important reference for vehicle design and performance evaluation.

[0057] As an optional embodiment, step S104 involves calling a regression model to predict the windward area of ​​the vehicle to be predicted, thereby obtaining the target windward area. This includes: using the size information of multiple vehicles as independent variables and the initial windward area of ​​multiple vehicles as dependent variables, determining the regression equation in the regression model. The regression equation includes coefficients and intercepts. The coefficients represent the magnitude and direction of the influence of the size information of multiple vehicles on the initial windward area of ​​multiple vehicles, and the intercept represents the constant term of the regression equation. The regression equation is then called to predict the windward area of ​​the vehicle to be predicted, thereby obtaining the target windward area.

[0058] In this embodiment, during the process of calling the regression model to predict the windward area of ​​the vehicle to be predicted and obtaining the target windward area, the size information of multiple vehicles can be used as independent variables, and the initial windward area of ​​multiple vehicles can be used as the dependent variable to determine the regression equation in the regression model. Then, the regression equation can be called to predict the windward area of ​​the vehicle to be predicted and obtain the target windward area S.

[0059] Optionally, a multiple linear regression algorithm can be used to fit the above vehicle dataset, with the size information of multiple vehicles as independent variables and the initial windward area of ​​multiple vehicles as dependent variables, to solve for the coefficients and intercepts of the regression equation. Then, the regression equation can be called to predict the windward area of ​​the vehicle to be predicted, and the target windward area can be obtained.

[0060] Optionally, the coefficients of the regression equation reflect the linear effect of the corresponding size information on the windward area. Positive coefficients indicate that increasing size information will increase the windward area, while negative coefficients indicate that increasing size information will decrease the windward area. The intercept is a constant term in the regression equation, representing the baseline value of the estimated windward area when there is no independent variable.

[0061] Optionally, when it is necessary to predict the frontal area of ​​a vehicle, the vehicle's dimensions, namely the values ​​of A, B, C, D, and E, can be obtained. Then, this dimensional information is substituted into the regression equation to calculate the target frontal area.

[0062] In this embodiment of the invention, the regression model can accurately predict the frontal area based on vehicle size information, with an accuracy typically far exceeding that of simple estimation formulas, meeting the needs of engineering applications. Prediction can be performed using only basic size data, significantly reducing costs. It is applicable not only to vehicles in the design phase but also to competitive analysis and even to quickly assessing the impact of components on frontal area in supply chain management. As the vehicle dataset expands and vehicle models evolve, the regression model can be continuously iterated and updated, continuously improving prediction accuracy and better adapting to industry development.

[0063] As an optional implementation, the dimensional information of multiple vehicles includes width, height, ground clearance, tire tread width, and side window tilt angle. Using the dimensional information of multiple vehicles as independent variables and the initial frontal area of ​​multiple vehicles as dependent variables, the regression equation in the regression model is determined. This includes: determining coefficients and intercepts using the dimensional information of multiple vehicles as independent variables and the initial frontal area of ​​multiple vehicles as dependent variables. The coefficients include width coefficient, height coefficient, ground clearance coefficient, tire tread width coefficient, and side window tilt angle coefficient. The model then determines the first product of width and width coefficient; the second product of height and height coefficient; the negative of the third product of ground clearance and ground clearance coefficient; the fourth product of tire tread width and tire tread width coefficient; the negative of the fifth product of side window tilt angle and side window tilt angle coefficient; and the sum of the negatives of the first, second, third, fourth, and fifth products, as well as the intercept. This sum is then used to determine the regression equation.

[0064] In this embodiment, when determining the regression equation in the regression model using the size information of multiple vehicles as independent variables and the initial frontal area of ​​multiple vehicles as dependent variables, the regression equation in the regression model can be determined through multiple linear regression analysis. The size information of the multiple vehicles includes width A, height B, ground clearance C, tire tread width D, and side window tilt angle E.

[0065] Optionally, the dimensional information of multiple vehicles may include width, height, ground clearance, tire tread width, and side window tilt angle, and the corresponding coefficients may include width coefficient, height coefficient, ground clearance coefficient, tire tread width coefficient, and side window tilt angle coefficient.

[0066] Optionally, the regression equation is determined by: determining the first product of width and width coefficient; determining the second product of height and height coefficient; determining the negative of the third product of ground clearance and ground clearance coefficient; determining the fourth product of tire tread width and tire tread width coefficient; determining the negative of the fifth product of side window tilt angle and side window tilt angle coefficient; and then summing the first, second, third, fourth, and fifth products, as well as the intercept.

[0067] Alternatively, the regression equation can be determined using the following formula:

[0068] S=1.42 A+1.54 B-1.7 C+0.127848 D-0.0137 E-2.10202

[0069] Among them, 1.42 can be used to represent the width coefficient; 1.54 can be used to represent the height coefficient; 1.7 can be used to represent the ground clearance coefficient; 0.127848 can be used to represent the tire tread width coefficient; 0.0137 can be used to represent the side window tilt angle coefficient; and 2.10202 can be used to represent the intercept.

[0070] In this embodiment of the invention, multiple linear regression analysis is used to predict the windward area of ​​a vehicle based on a small amount of easily obtainable size information. This not only reduces the prediction cost and improves the prediction efficiency, but also provides strong data support for vehicle design and performance optimization. It avoids dependence on complex three-dimensional models or physical wind tunnel experiments, thus having broad application prospects in the early stages of vehicle design and supply chain management.

[0071] As an optional implementation method, the regression equation is invoked to predict the frontal area of ​​the vehicle to be predicted, and the target frontal area is obtained. This includes inputting the width of the vehicle to be predicted, the height of the vehicle to be predicted, the ground clearance of the vehicle to be predicted, the tire tread width of the vehicle to be predicted, and the side window tilt angle of the vehicle to be predicted into the regression equation to obtain the target frontal area.

[0072] In this embodiment, during the process of calling the regression equation to predict the windward area of ​​the vehicle to be predicted and obtaining the target windward area, the width of the vehicle to be predicted, the height of the vehicle to be predicted, the ground clearance of the vehicle to be predicted, the tire tread width of the vehicle to be predicted, and the side window tilt angle of the vehicle to be predicted can be input into the regression equation to obtain the target windward area.

[0073] Optionally, with the regression equation determined above, for each vehicle to be predicted, the target frontal area can be quickly calculated by collecting the vehicle's size information (width, height, ground clearance, tire section width, and side window tilt angle) and substituting it into the regression equation.

[0074] For example, let's take a new electric vehicle (a benchmark model) as an example. First, obtain the dimensional information: vehicle width A = 1.96m, vehicle height B = 1.73m, minimum ground clearance C = 0.16m, tire specification 255 / 45 R20 (where "255" refers to the tire section width D = 0.255m), and side window angle E = 21.5°. Substitute the above dimensional information into the formula S = 1.42 A+1.54 B-1.7 C+0.127848 D-0.0137 E-2.10202, thus obtaining the target frontal area of ​​the vehicle to be predicted:

[0075] S=1.42 1.96 + 1.54 1.73–1.7 0.16 + 0.127848 0.255-0.0137 21.5 - 2.10202 ≈ 2.8114 ㎡

[0076] Optionally, the target frontal area reflects the effective area of ​​the vehicle's front end affected by air resistance given the size information, and is of great value for evaluating the vehicle's aerodynamic characteristics, fuel efficiency, and designing and optimizing the vehicle's shape.

[0077] In this embodiment of the invention, the windward area is estimated by using a mathematical relationship (regression equation) based on a specific combination of five easily obtainable parameters (width, height, ground clearance, tire cross-section width, and side window tilt angle), which can back-calculate the target windward area with engineering-grade accuracy (error <3%).

[0078] As an optional embodiment, the method further includes: comparing the target windward area with the initial windward area to obtain a comparison result, wherein the comparison result is used to represent the error between the target windward area and the initial windward area; and determining that the windward area of ​​the vehicle to be predicted has been successfully predicted in response to the error being less than or equal to an error threshold.

[0079] In this embodiment, the target windward area is compared with the initial windward area to calculate the error between the two. The calculated error is then compared with an error threshold. If the error is less than or equal to the preset error threshold, the regression model is considered to have successfully predicted the windward area of ​​the vehicle to be predicted, thus verifying the effectiveness and practicality of the regression model.

[0080] Optionally, the error threshold reflects the acceptable range of error in the regression model's prediction. For example, if the error threshold is set to 3%, it means that if the relative error between the target windward area and the initial windward area does not exceed 3%, the prediction is considered to be within the allowable error range, and the prediction result is successful.

[0081] Optionally, if the error exceeds the error threshold, it indicates that the current regression model fails to accurately reflect the true characteristics of the vehicle in some aspects, or that the size information on which the prediction is based is biased. In this case, the accuracy of the size information used for prediction can be checked, including data entry errors, measurement errors, or the reliability of the information source. If data problems are found, they should be corrected immediately, and the prediction should be repeated. The regression model can also be reviewed to assess its applicability and accuracy. For example, the vehicle dataset used during the regression model training can be reviewed to confirm whether it covers various types of vehicles and a sufficiently wide range of size parameters to ensure the regression model has broad applicability. The independent variables used in the regression model can be reviewed to confirm whether the size information includes the five items mentioned above.

[0082] Optionally, for certain types or design features of vehicles, specific correction factors can be introduced to fine-tune the prediction results to more accurately match the target frontal area.

[0083] In this embodiment of the invention, the above method not only verifies the accuracy of the regression model's predictions but also allows for the setting of clear performance indicators in practical applications, ensuring the prediction results have practical value in engineering design and evaluation. For vehicles under design or optimization, it provides an estimate of the frontal area in advance, helping designers adjust their designs earlier and improve overall vehicle performance. Furthermore, for supply chain management and competitor analysis, even without precise models or actual vehicles, preliminary performance assessments can be conducted based on limited dimensional information, enhancing the timeliness and effectiveness of decision-making.

[0084] As an optional embodiment, the method further includes: acquiring the size information of multiple vehicles according to a time period, and updating the size information of the multiple vehicles.

[0085] In this embodiment, a fixed time interval can be defined (e.g., quarterly, annually, or whenever a major model is released) to collect new vehicle data, i.e., size information for multiple vehicles. The choice of this time interval should take into account the update frequency of the automotive industry, the ease of data collection, and the needs of regression model optimization.

[0086] Optionally, at the end of each set time period, the latest dimensional information, including vehicle width, height, minimum ground clearance, tire section width, and side window tilt angle, can be obtained from various sources (including but not limited to new car launches, industry reports, and publicly available vehicle parameter documents). Simultaneously, the latest measured frontal area (initial frontal area) data for these vehicles is obtained as a dependent variable for regression model training.

[0087] Optionally, the collected data can be cleaned to remove outliers or incomplete samples, ensuring data quality and consistency. Data standardization or normalization can eliminate the influence of different units or magnitudes, improving the training effect of the regression model. Afterward, the latest data can be merged into the original dataset, and the regression model (e.g., a multiple linear regression model) can be retrained using the expanded dataset. This process involves recalculating coefficients and intercepts to reflect new trends in vehicle design and performance changes.

[0088] Optionally, once the regression model is validated, the updated prediction method can be extended to more vehicle design and competitor analysis scenarios, especially in the early stages of vehicle design, to help designers quickly estimate the frontal area, guide styling and overall layout design, and facilitate rapid evaluation by upstream and downstream companies in the supply chain.

[0089] In this embodiment of the invention, if it is necessary to predict the windward area of ​​a vehicle, the size information of the vehicle to be predicted can be obtained. This size information represents the vehicle's dimensional structure. A regression model can be invoked to predict the windward area of ​​the vehicle, yielding a target windward area. The regression model is obtained by fitting the regression relationship between the size information of multiple vehicles and their initial windward areas. The target windward area represents the predicted windward area of ​​the vehicle to be predicted, and the initial windward area represents the effective area of ​​the front of the multiple vehicles affected by air resistance. The category of the size information of the vehicle to be predicted is consistent with the category of the size information of the multiple vehicles. In other words, this invention only requires a few key dimensions of the vehicle and can complete the calculation in a short time by invoking a regression model, greatly improving prediction efficiency. This overcomes the limitations of related technologies that require a complete 3D CAD model or actual vehicle for design, thus solving the technical problem of ineffective prediction of vehicle windward area and achieving the technical effect of effectively predicting vehicle windward area.

[0090] The technical solutions of the embodiments of the present invention will be illustrated below with reference to preferred embodiments.

[0091] Currently, a vehicle's frontal area is a key parameter for calculating air resistance, assessing fuel economy, optimizing vehicle design, and estimating the driving range of new energy vehicles.

[0092] Existing calculation methods in related technologies include traditional field measurement, direct acquisition from CAD models, simplified estimation formulas, and photographic estimation. Traditional field measurement involves wind tunnel testing using projection or direct measurement methods. However, these methods are costly, time-consuming, and dependent on specialized equipment, making them unsuitable for widespread application in the early stages of vehicle design. Direct acquisition from CAD models utilizes accurate 3D CAD models of the entire vehicle, allowing for direct projection calculations within software. However, this method relies on a complete, high-precision model, making it inconvenient for rapid estimation by upstream and downstream companies in the supply chain or for competitor analysis. Simplified estimation formulas, such as frontal area ≈ vehicle width × vehicle height × coefficient (e.g., 0.81), have poor accuracy and cannot meet the needs of engineering applications. Photographic estimation uses digital cameras to capture images of the actual vehicle and processes the data to measure its frontal area. This method requires actual vehicle photography and is unsuitable for the vehicle design stage. Therefore, the technical problem of effectively predicting a vehicle's frontal area remains.

[0093] This invention proposes a method for estimating vehicle frontal area based on a multiple linear regression model. This method, by inputting five easily obtainable key vehicle parameters, can directly calculate a high-precision estimate of the frontal area using a specific multiple linear regression formula, making it suitable for vehicle concept design and competitor analysis.

[0094] The embodiments of the present invention will be further described below.

[0095] Figure 2 This is a flowchart of a vehicle frontal area prediction method based on multiple linear regression according to an embodiment of the present invention, as shown below. Figure 2 As shown, the method may include the following steps.

[0096] Step S201: Construct the parameter database.

[0097] In this embodiment, a large amount of sample data from different vehicle models can be collected. Each sample data includes: vehicle width A (in meters), height B (in meters), minimum ground clearance C (in meters), tire section width D (in meters), side window tilt angle E (in degrees), and the actual frontal area (in square meters) measured through wind tunnel experiments, to construct a parameter database (vehicle dataset).

[0098] Step S202: Train the regression model.

[0099] In this embodiment, a multiple linear regression algorithm can be used to fit the above parameter database, with A, B, C, D, and E as independent variables and the actual windward area as the dependent variable, to solve for the coefficients and intercept of the regression equation, resulting in the following core calculation formula:

[0100] S=1.42 A+1.54 B-1.7 C+0. 127848 D-0.0137 E-2.10202

[0101] Optionally, the goodness of fit R² of the regression model is 0.98808, and the error between the estimated windward area and the actual area is within 3%.

[0102] Step S203: Estimate the windward area.

[0103] In this embodiment, for the vehicle to be estimated (whether it is a model under design or a benchmark model), only its five corresponding parameters (A, B, C, D, E) need to be obtained and substituted into the above regression equation formula to calculate the target frontal area S.

[0104] In this embodiment of the invention, if it is necessary to predict the windward area of ​​a vehicle, the size information of the vehicle to be predicted can be obtained. This size information represents the vehicle's dimensional structure. A regression model can be invoked to predict the windward area of ​​the vehicle, yielding a target windward area. The regression model is obtained by fitting the regression relationship between the size information of multiple vehicles and their initial windward areas. The target windward area represents the predicted windward area of ​​the vehicle to be predicted, and the initial windward area represents the effective area of ​​the front of the multiple vehicles affected by air resistance. The category of the size information of the vehicle to be predicted is consistent with the category of the size information of the multiple vehicles. In other words, this invention only requires a few key dimensions of the vehicle and can complete the calculation in a short time by invoking a regression model, greatly improving prediction efficiency. This overcomes the limitations of related technologies that require a complete 3D CAD model or actual vehicle for design, thus solving the technical problem of ineffective prediction of vehicle windward area and achieving the technical effect of effectively predicting vehicle windward area.

[0105] The following explanation will be further illustrated using a new type of electric vehicle (the benchmark model).

[0106] Parameters obtained: According to publicly available information, the vehicle width A=1.96m, vehicle height B=1.73m, minimum ground clearance C=0.16m, tire specifications are 255 / 45 R20 (where "255" means tire section width D=0.255m), and side window tilt angle E=21.5°.

[0107] To calculate the windward area: Substitute the parameters into the formula:

[0108] S=1.42 1.96 + 1.54 1.73–1.7 0.16 + 0.127848 0.255-0.0137 21.5-2.10202

[0109] S≈2.8114㎡

[0110] Results verification: The estimated value was compared with the wind tunnel measured value of the model later (e.g., 2.8787㎡), with an error of 2.4%, which is within a reasonable range, thus verifying the effectiveness of the method.

[0111] In this embodiment of the invention, the following beneficial effects are achieved through the above steps: (1) Extreme simplicity and efficiency: No complex software, hardware or image processing is required, only a regression equation formula and five parameters (size information) are needed, and the calculation can be completed in seconds. (2) Extremely low cost: All input parameters are the basic dimensions of the vehicle, which can be initially determined in the design sketch stage or easily found from public information. (3) Significantly higher accuracy than the empirical coefficient method: By introducing key detail parameters such as ground clearance, tire width, and side window tilt angle, the huge error of the simple "width × height × coefficient" method is effectively corrected, and the accuracy can reach within 3%, which meets the requirements of engineering estimation. (4) Foresight and confidentiality: Estimation can be performed before the full-size model or CAD data is generated, guiding the early styling and overall layout design. At the same time, benchmarking analysis can be performed without contacting the core CAD model of competitors. (5) Iterative optimization: As a basic model, this formula can be continuously iterated and updated as the sample database expands and the vehicle model evolves, so that the estimation accuracy can be continuously improved.

[0112] According to embodiments of the present invention, a device for predicting the frontal area of ​​a vehicle is also provided. It should be noted that this device for predicting the frontal area of ​​a vehicle can be used to execute the method for predicting the frontal area of ​​a vehicle in the embodiments.

[0113] Figure 3 This is a schematic diagram of a vehicle frontal area prediction device according to an embodiment of the present invention. Figure 3 As shown, the vehicle's frontal area prediction device 300 may include an acquisition unit 302 and a prediction unit 304.

[0114] The acquisition unit 302 is used to acquire the size information of the vehicle to be predicted, wherein the size information of the vehicle to be predicted is used to represent the size structure of the vehicle to be predicted.

[0115] Prediction unit 304 is used to call a regression model to predict the windward area of ​​the vehicle to be predicted and obtain the target windward area. The regression model is obtained by fitting the regression relationship between the size information of multiple vehicles and the initial windward area of ​​multiple vehicles. The target windward area is used to represent the predicted windward area of ​​the vehicle to be predicted, and the initial windward area is used to represent the effective area of ​​the front of multiple vehicles under air resistance. The category of the size information of the vehicle to be predicted is consistent with the category of the size information of multiple vehicles.

[0116] Optionally, the vehicle frontal area prediction device 300 may further include: a measurement subunit for measuring the effective frontal area of ​​multiple vehicles under air resistance at different wind speeds and directions; and a first acquisition subunit for placing multiple vehicles in a wind tunnel based on the effective frontal area to acquire the initial frontal area of ​​the multiple vehicles, wherein the wind tunnel is used to simulate the airflow around the multiple vehicles as they travel to generate different wind speeds and directions.

[0117] Optionally, the prediction unit 304 includes: a first determining subunit, used to determine the regression equation in the regression model using the size information of multiple vehicles as independent variables and the initial windward area of ​​multiple vehicles as dependent variables, wherein the regression equation includes coefficients and intercepts, the coefficients are used to represent the magnitude and direction of the influence of the size information of multiple vehicles on the initial windward area of ​​multiple vehicles, and the intercepts are used to represent the constant term of the regression equation; and a prediction subunit, used to call the regression equation to predict the windward area of ​​the vehicle to be predicted, and obtain the target windward area.

[0118] Optionally, the dimensional information of multiple vehicles includes width, height, ground clearance, tire tread width, and side window tilt angle. The first determining subunit includes: a second determining subunit, used to determine coefficients and intercepts using the dimensional information of multiple vehicles as independent variables and the initial frontal area of ​​multiple vehicles as dependent variables, wherein the coefficients include width coefficient, height coefficient, ground clearance coefficient, tire tread width coefficient, and side window tilt angle coefficient; a third determining subunit, used to determine the first product of width and width coefficient; and a fourth determining subunit, used to determine the product of height and height coefficient. The second product of the ground clearance coefficient; the fifth determining subunit, used to determine the negative of the third product of ground clearance and ground clearance coefficient; the sixth determining subunit, used to determine the fourth product of tire tread width and tire tread width coefficient; the seventh determining subunit, used to determine the negative of the fifth product of side window tilt angle and side window tilt angle coefficient; the eighth determining subunit, used to determine the negatives of the first, second, third, fourth, and fifth products, as well as the sum of the intercepts; the ninth determining subunit, used to determine the sum as a regression equation.

[0119] Optionally, the prediction subunit includes an input subunit, used to input the width of the vehicle to be predicted, the height of the vehicle to be predicted, the ground clearance of the vehicle to be predicted, the tire tread width of the vehicle to be predicted, and the side window tilt angle of the vehicle to be predicted into the regression equation to obtain the target frontal area.

[0120] Optionally, the vehicle's frontal area prediction device 300 may further include: a comparison subunit for comparing the target frontal area with the initial frontal area to obtain a comparison result, wherein the comparison result is used to represent the error between the target frontal area and the initial frontal area; and a tenth subunit for determining that the prediction of the vehicle's frontal area has been successful in response to the error being less than or equal to an error threshold.

[0121] Optionally, the vehicle frontal area prediction device 300 may further include: a second acquisition subunit, used to acquire the size information of multiple vehicles according to a time period and update the size information of the multiple vehicles.

[0122] In this embodiment of the invention, the size information of the vehicle to be predicted is obtained by the acquisition unit 302, wherein the size information of the vehicle to be predicted is used to represent the size structure of the vehicle to be predicted; the windward area of ​​the vehicle to be predicted is predicted by the prediction unit 304 through calling the regression model to obtain the target windward area, wherein the regression model is obtained by fitting the regression relationship between the size information of multiple vehicles and the initial windward area of ​​multiple vehicles. The target windward area is used to represent the predicted windward area of ​​the vehicle to be predicted, and the initial windward area is used to represent the effective area of ​​the front of multiple vehicles subjected to air resistance. The category of the size information of the vehicle to be predicted is consistent with the category of the size information of multiple vehicles, thereby solving the technical problem of not being able to effectively predict the windward area of ​​the vehicle and achieving the technical effect of effectively predicting the windward area of ​​the vehicle.

[0123] Figure 4 This is a structural block diagram of a vehicle according to an embodiment of the present invention, such as... Figure 4 As shown, the components of the vehicle 400 include, but are not limited to, a memory 410 and a processor 420. The processor 420 and the memory 410 are connected via a bus 430, and the database 460 is used to store data.

[0124] Vehicle 400 may also include access device 440, which enables vehicle 400 to communicate via one or more networks 450. Examples of these networks include Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or combinations of communication networks such as the Internet. Access device 440 may include one or more of any type of wired or wireless network interface (e.g., network interface controller (NIC)), such as an IEEE 402.11 Wireless Local Area Network (WLAN) interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, and so on.

[0125] In one embodiment of this disclosure, the aforementioned components of vehicle 400 and Figure 4 Other components not shown can also be connected to each other, for example, via a bus. It should be understood that... Figure 4 The illustrated block diagram of an autonomous vehicle is for illustrative purposes only and is not intended to limit the scope of this disclosure. Those skilled in the art can add or replace other components as needed.

[0126] According to another aspect of the present invention, a processor is also provided. The processor is used to run a program, wherein the program executes the methods of the embodiments of the present invention during runtime.

[0127] According to another aspect of the present invention, an electronic device is also provided, wherein a processor is configured to run a program, wherein the program executes the method of the present invention during runtime.

[0128] According to another aspect of the present invention, a computer-readable storage medium is also provided. The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the method of the embodiments of the present invention.

[0129] Embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0130] Embodiments of this application also provide a computer program product, including a non-volatile computer-readable storage medium for storing a computer program that, when executed by a processor, implements the methods in various embodiments of this application.

[0131] Embodiments of this application also provide a computer program that, when executed by a processor, implements the methods described in the various embodiments of this application. In the above embodiments of this application, the descriptions of each embodiment have different focuses; parts not described in detail in a certain embodiment can be referred to in the relevant descriptions of other embodiments.

[0132] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0133] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0134] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0135] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0136] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0137] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for predicting the frontal area of ​​a vehicle, characterized in that, include: Obtain the size information of the vehicle to be predicted, wherein the size information of the vehicle to be predicted is used to represent the size structure of the vehicle to be predicted; A regression model is invoked to predict the windward area of ​​the vehicle to be predicted, thereby obtaining the target windward area. The regression model is obtained by fitting the regression relationship between the size information of multiple vehicles and the initial windward area of ​​the multiple vehicles. The target windward area is used to represent the predicted windward area of ​​the vehicle to be predicted, and the initial windward area is used to represent the effective area of ​​the front of the multiple vehicles affected by air resistance. The category of the size information of the vehicle to be predicted is consistent with the category of the size information of the multiple vehicles.

2. The method according to claim 1, characterized in that, The method further includes: The effective frontal area of ​​the front of the multiple vehicles under air resistance was measured at different wind speeds and wind directions. Based on the effective windward area, the multiple vehicles are placed in a wind tunnel to obtain the initial windward area of ​​the multiple vehicles. The wind tunnel is used to simulate the airflow around the multiple vehicles when they are driving, so as to generate the different wind speeds and wind directions.

3. The method according to claim 2, characterized in that, The regression model is invoked to predict the windward area of ​​the vehicle to be predicted, resulting in the target windward area, including: Using the size information of the multiple vehicles as independent variables and the initial frontal area of ​​the multiple vehicles as dependent variables, the regression equation in the regression model is determined. The regression equation includes coefficients and intercepts. The coefficients are used to represent the magnitude and direction of the influence of the size information of the multiple vehicles on the initial frontal area of ​​the multiple vehicles. The intercept is used to represent the constant term of the regression equation. The regression equation is used to predict the windward area of ​​the vehicle to be predicted, thus obtaining the target windward area.

4. The method according to claim 3, characterized in that, The dimensional information of the multiple vehicles includes width, height, ground clearance, tire tread width, and side window tilt angle. Using the dimensional information of the multiple vehicles as independent variables and the initial frontal area of ​​the multiple vehicles as dependent variables, the regression equation in the regression model is determined, including: Using the size information of the multiple vehicles as independent variables and the initial frontal area of ​​the multiple vehicles as dependent variables, the coefficients and the intercepts are determined, wherein the coefficients include width coefficient, height coefficient, ground clearance coefficient, tire tread width coefficient, and side window tilt angle coefficient. Determine the first product of the width and the width coefficient; Determine the second product of the height and the height coefficient; Determine the negative of the third product of the ground clearance and the ground clearance coefficient; Determine the fourth product of the tire tread width and the tire tread width coefficient; Determine the negative of the fifth product of the side window tilt angle and the side window tilt angle coefficient; Determine the sum of the first product, the second product, the negative of the third product, the negative of the fourth product, the negative of the fifth product, and the intercept; The sum is determined as the regression equation.

5. The method according to claim 4, characterized in that, The regression equation is used to predict the windward area of ​​the vehicle to be predicted, resulting in the target windward area, including: The width, height, ground clearance, tire tread width, and side window tilt angle of the vehicle to be predicted are input into the regression equation to obtain the target frontal area.

6. The method according to claim 5, characterized in that, The method further includes: The target windward area is compared with the initial windward area to obtain a comparison result, wherein the comparison result is used to represent the error between the target windward area and the initial windward area; If the error is less than or equal to the error threshold, it is determined that the prediction of the frontal area of ​​the vehicle to be predicted has been successful.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: The size information of the multiple vehicles is obtained according to a time period, and the size information of the multiple vehicles is updated.

8. A device for predicting the frontal area of ​​a vehicle, characterized in that, include: An acquisition unit is used to acquire the size information of the vehicle to be predicted, wherein the size information of the vehicle to be predicted is used to represent the size structure of the vehicle to be predicted; The prediction unit is used to call a regression model to predict the windward area of ​​the vehicle to be predicted, and obtain the target windward area. The regression model is obtained by fitting the regression relationship between the size information of multiple vehicles and the initial windward area of ​​the multiple vehicles. The target windward area is used to represent the predicted windward area of ​​the vehicle to be predicted, and the initial windward area is used to represent the effective area of ​​the front of the multiple vehicles affected by air resistance. The category of the size information of the vehicle to be predicted is consistent with the category of the size information of the multiple vehicles.

9. A processor, characterized in that, The processor is used to run a program, wherein the program executes the method according to any one of claims 1 to 7 when it runs.

10. An electronic device, characterized in that, The processor is used to run a program, wherein the program executes the method according to any one of claims 1 to 7 when it runs.

11. A vehicle, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method according to any one of claims 1 to 7.

Images