A method and device for simulating dynamic wind resistance of automobiles based on artificial intelligence

Abstract

This application discloses an artificial intelligence-based method and device for simulating dynamic wind resistance in automobiles. The method includes: performing threshold analysis on the wind resistance influence of three-dimensional parameters of vehicle surface components to identify components affecting vehicle wind resistance; performing component structural feature analysis on the components affecting vehicle wind resistance to obtain wind resistance-related characteristic parameters of the vehicle surface components; simulating the vertical deformation of vehicle tires to obtain vehicle wind resistance simulation height parameters; determining vehicle wind resistance simulation parameters through vehicle wind resistance feature analysis; inputting the vehicle wind resistance simulation parameters into a preset wind resistance simulation model to obtain a dynamic wind resistance model of the vehicle to be trained; and performing dynamic loss function analysis on the dynamic wind resistance model of the vehicle to be trained to obtain dynamic wind resistance change data of the vehicle, thereby dynamically simulating vehicle wind resistance. This application solves the technical problem that the simulated wind resistance of a vehicle cannot be directly determined by replacing some vehicle components during the wind resistance adjustment process.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based method and device for simulating dynamic wind resistance of automobiles. Background Technology

[0002] In the process of automotive design and development, wind resistance is one of the key factors affecting vehicle performance, fuel economy, and noise levels. Traditionally, in order to evaluate and optimize the wind resistance performance of a vehicle, researchers usually need to perform whole-vehicle modeling and analyze the vehicle's wind resistance performance under different operating conditions through complex computational fluid dynamics (CFD) simulations.

[0003] Current technologies typically simulate vehicle drag by modeling the entire vehicle. However, the drag effects of various components on a car's surface are interconnected, and analyzing a single component may not accurately reflect its actual performance within the vehicle. Furthermore, during the development of multiple vehicle models, as well as vehicles of the same model, remodeling for replacement or modification of vehicle components is challenging. The computational load and time required are insufficient to meet production demands, making it impossible to provide timely drag simulation data for reference when modifying vehicle components during drag adjustments. Summary of the Invention

[0004] This application provides an artificial intelligence-based method and device for simulating dynamic wind resistance of automobiles, which solves the technical problem that in the existing wind resistance adjustment process, it is impossible to directly determine the simulated wind resistance of a vehicle by replacing some vehicle components.

[0005] In a first aspect, embodiments of this application provide an artificial intelligence-based method for simulating dynamic wind resistance of a vehicle. The method includes: acquiring three-dimensional parameters of vehicle surface components and performing a threshold analysis of the wind resistance influence degree of the three-dimensional parameters to determine the components affecting vehicle wind resistance; performing component structural feature analysis on the components affecting vehicle wind resistance to obtain wind resistance-related feature parameters of the vehicle surface components; acquiring vehicle tire parameters and simulating the vertical deformation of the tires to obtain vehicle wind resistance simulation height parameters; determining vehicle wind resistance simulation parameters based on the vehicle component wind resistance feature parameters and the vehicle wind resistance simulation height parameters through vehicle wind resistance feature analysis; inputting the vehicle wind resistance simulation parameters into a preset wind resistance simulation model to obtain a vehicle dynamic wind resistance model to be trained; and performing dynamic loss function analysis on the vehicle dynamic wind resistance model to obtain dynamic wind resistance change data to dynamically simulate vehicle wind resistance.

[0006] In one implementation of this application, a threshold analysis of the wind resistance influence of vehicle surface components is performed on the three-dimensional parameters of the components to determine the components that affect vehicle wind resistance. Specifically, this includes: determining the spatial distribution mapping of vehicle surface parameters based on the three-dimensional parameters of the components and dividing the spatial distribution of vehicle components; delineating the distribution range of the spatial distribution mapping to obtain the spatial range of vehicle component distribution; determining the wind resistance influence range threshold through wind resistance influence correlation assessment based on the spatial range of vehicle component distribution; and configuring the wind resistance influence range threshold by model mapping to determine the components that affect vehicle wind resistance.

[0007] In one implementation of this application, structural feature analysis is performed on components affecting vehicle wind resistance to obtain wind resistance-related characteristic parameters of vehicle surface components. Specifically, this includes: performing flow field characteristic simulation on vehicle surface components affecting wind resistance to determine the set of air resistance coefficients corresponding to the components; determining the air resistance coefficients of vehicle components based on the set of air resistance coefficients by matching key fields of components; performing correlation analysis between vehicle components on the air resistance coefficients of vehicle components to obtain the drag coefficients of vehicle components; and performing fluid characteristic change simulation on the drag coefficients of vehicle components to determine the wind resistance characteristic parameters of vehicle components.

[0008] In one implementation of this application, the vehicle tire parameters are simulated using vertical deformation to obtain the vehicle's wind resistance simulation height parameters. Specifically, this includes: preprocessing the vehicle tire parameters to obtain the tire parameters to be simulated; wherein the tire parameters to be simulated include: tire size, tire material properties, and standard application tire pressure; determining the tire vertical stiffness parameters based on the tire parameters to be simulated through tire vertical stiffness analysis; obtaining the vehicle's vertical load parameters, and obtaining the vehicle's wind resistance simulation height parameters based on the tire vertical stiffness parameters and the vehicle's vertical load parameters through tire vertical deformation analysis.

[0009] In one implementation of this application, vehicle drag simulation parameters are determined through vehicle drag characteristic analysis based on vehicle component drag characteristic parameters and vehicle drag simulation height parameters. Specifically, this includes: determining vehicle drag simulation geometric data based on vehicle drag simulation height parameters; determining vehicle cavity geometric data based on vehicle drag simulation geometric data, and performing boundary fluid influence analysis on the vehicle cavity geometric data to obtain cavity component drag characteristic parameters; and determining vehicle drag simulation parameters based on vehicle component drag characteristic parameters and cavity component drag characteristic parameters.

[0010] In one implementation of this application, vehicle drag simulation parameters are input into a preset drag simulation model to obtain a vehicle dynamic drag model to be trained. Specifically, this includes: dividing the vehicle simulation parameters into training data to obtain a simulation model dataset; wherein the simulation model dataset includes: a simulation training set and a simulation verification set; inputting the simulation training set into the drag simulation model and configuring boundary conditions on the drag simulation model to obtain a vehicle dynamic drag model to be trained.

[0011] In one implementation of this application, a dynamic loss function analysis is performed on the dynamic drag model of the vehicle to be trained to obtain dynamic drag change data of the vehicle, so as to dynamically simulate the vehicle drag. Specifically, this includes: training the dynamic drag model of the vehicle to be trained until the model converges based on a simulation validation set to obtain the vehicle drag model; iterating the loss function of the vehicle dynamic drag model to obtain the minimum loss function; updating the drag model weights according to the minimum loss function to obtain the vehicle dynamic drag model; obtaining the current vehicle information and inputting the vehicle information into the vehicle dynamic drag model to obtain the dynamic drag change data of the vehicle.

[0012] In one implementation of this application, after performing dynamic loss function analysis on the dynamic drag model of the vehicle to be trained to determine the vehicle drag coefficient data, the method further includes: acquiring drag experiment data, and determining the dynamic adjustment parameters of the loss function based on the drag experiment data through simulation deviation analysis; and determining the dynamic drag model of the vehicle through drag model optimization based on the dynamic adjustment parameters of the loss function.

[0013] In one implementation of this application, the dynamic adjustment parameters of the loss function are determined based on wind resistance experimental data and through simulation deviation analysis. Specifically, this includes: comparing the wind resistance experimental data with the wind resistance simulation data to determine the wind resistance simulation deviation data; and using a genetic algorithm to iteratively analyze the dynamic parameters of the loss function based on the wind resistance simulation deviation data to determine the dynamic adjustment parameters of the loss function.

[0014] Secondly, embodiments of this application also provide an artificial intelligence-based vehicle dynamic drag simulation device, characterized in that the device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: acquire three-dimensional parameters of vehicle surface components, and perform a threshold analysis of the drag influence degree of the vehicle surface components on the three-dimensional parameters to determine the components affecting vehicle drag; perform component structural feature analysis on the components affecting vehicle drag to obtain drag-related feature parameters of the vehicle surface components; acquire vehicle tire parameters, and perform tire vertical deformation simulation on the vehicle tire parameters to obtain vehicle drag simulation height parameters; determine vehicle drag simulation parameters based on vehicle component drag feature parameters and vehicle drag simulation height parameters through vehicle drag feature analysis; input the vehicle drag simulation parameters into a preset drag simulation model to obtain a vehicle dynamic drag model to be trained; and perform dynamic loss function analysis on the vehicle dynamic drag model to be trained to obtain vehicle drag dynamic change data to dynamically simulate vehicle drag.

[0015] This application provides an artificial intelligence-based method and device for simulating dynamic wind resistance in automobiles. By mapping the spatial range corresponding to vehicle components, simulating the wind environment and vehicle height of different models, and dynamically modeling vehicle wind resistance, it solves the technical problem that in the existing wind resistance adjustment process, it is impossible to directly determine the simulated wind resistance of a vehicle by replacing some vehicle components. It realizes that after replacing some surface components of the vehicle, it is not necessary to remodel the whole vehicle to simulate vehicle wind resistance, thereby improving the prediction efficiency of vehicle wind resistance and reducing the computational requirements for vehicle wind resistance simulation during the research and development process. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 A flowchart illustrating an artificial intelligence-based method for simulating dynamic wind resistance of a vehicle, as provided in this application embodiment;

[0018] Figure 2 This is a schematic diagram of the internal structure of an artificial intelligence-based vehicle dynamic wind resistance simulation device provided in an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] This application provides an artificial intelligence-based method and device for simulating dynamic wind resistance in automobiles. By mapping the spatial range corresponding to vehicle components, simulating the wind environment and vehicle height of different models, and dynamically modeling vehicle wind resistance, it solves the technical problem that in the existing wind resistance adjustment process, it is impossible to directly determine the simulated wind resistance of a vehicle by replacing some vehicle components. It realizes that after replacing some surface components of the vehicle, it is not necessary to remodel the whole vehicle to simulate vehicle wind resistance, thereby improving the prediction efficiency of vehicle wind resistance and reducing the computational requirements for vehicle wind resistance simulation during the research and development process.

[0021] The technical solutions proposed in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0022] Figure 1 This document presents a flowchart of an artificial intelligence-based method for simulating dynamic aerodynamic drag of a vehicle, as provided in an embodiment of this application. Figure 1 As shown in the figure, the vehicle dynamic drag simulation method based on artificial intelligence provided in this application embodiment specifically includes the following steps:

[0023] Step 101: Obtain the three-dimensional parameters of the vehicle surface components and perform a threshold analysis on the wind resistance influence of the three-dimensional parameters to determine the components that affect vehicle wind resistance.

[0024] Specifically, this includes: determining the spatial distribution mapping of vehicle surface parameters based on the three-dimensional parameters of the components and dividing the spatial distribution of vehicle components; delineating the distribution range of the spatial distribution mapping to obtain the spatial range of vehicle component distribution; determining the threshold of wind resistance influence range by evaluating the correlation between wind resistance influence and the spatial range of vehicle component distribution; and configuring the wind resistance influence range threshold by model mapping to identify the components that affect vehicle wind resistance.

[0025] This application obtains the three-dimensional parameters of vehicle surface components and performs threshold analysis on the wind resistance influence of these parameters to identify the components that affect vehicle wind resistance. This enables the analysis of the influence degree and relationship of vehicle surface components for different car models, thereby improving the accuracy of vehicle wind resistance simulation.

[0026] In the embodiments of this application, the following Example 1 will be explained in detail.

[0027] Example 1: Due to the significant differences in the shape of vehicle surface components, it is necessary to analyze the degree of influence of each vehicle component on wind resistance under certain simulated test conditions when simulating wind resistance.

[0028] First, the front of the vehicle, as the primary area affected by wind resistance, mainly consists of the windshield and the heat exchange components (depending on the vehicle's drive system). To determine the main distribution locations of various vehicle components, a spatial distribution mapping needs to be defined to obtain the spatial range of vehicle component distribution. This spatial range characterizes the main spatial distribution of each vehicle component. For example, this includes the spatial distribution and connection relationships of components that primarily affect vehicle wind resistance, such as the windshield and rearview mirrors.

[0029] The maximum spatial range defined by the distribution range is the space formed by the outermost surface of all currently input component models. When replacing components, the wind resistance simulation calculation will not exceed this range, which can make subsequent wind resistance simulation more stable. Furthermore, when a larger distribution range is required due to changes in height, the distribution range space can be expanded.

[0030] It is important to note that spatial distribution mapping can help the model find the corresponding component data by importing key fields or preset names of vehicles and vehicle components during wind resistance simulation.

[0031] Then, aerodynamic simulations can be performed on various vehicle components. Based on the simulation results, correlation analysis can be used to determine the wind resistance of each component under certain fluid configuration conditions. A threshold for the wind resistance impact range can then be set according to actual production needs. This threshold is used to define which components are key contributors to the vehicle's wind resistance.

[0032] Finally, model mapping configuration is performed on the threshold of wind resistance impact range to identify the components that affect vehicle wind resistance.

[0033] Step 102: Analyze the structural features of the components that affect vehicle wind resistance to obtain the wind resistance-related characteristic parameters of the vehicle surface components.

[0034] Specifically, this includes: performing flow field characteristic simulations on vehicle surface components that affect wind resistance to determine the corresponding set of air resistance coefficients; determining the air resistance coefficients of vehicle components by matching key fields of the components based on the set of air resistance coefficients; performing correlation analysis between vehicle components to obtain the drag coefficients of vehicle components; and performing fluid characteristic change simulations on the drag coefficients of vehicle components to determine the wind resistance characteristic parameters of vehicle components.

[0035] This application analyzes the structural characteristics of components affecting vehicle wind resistance to obtain wind resistance-related characteristic parameters of vehicle surface components, thus achieving...

[0036] In the embodiments of this application, the following Example 2 will be explained in detail.

[0037] Example 2: First, in order to evaluate the wind resistance of the wind resistance surface formed by each wind resistance-affecting component of the vehicle during the initial wind resistance simulation, the flow field characteristics of the wind resistance-affecting components on the vehicle surface are simulated to determine the set of air resistance coefficients corresponding to the wind resistance-affecting components on the vehicle surface.

[0038] Then, based on the spatial distribution of vehicle components, the threshold of the drag influence range is determined through a correlation assessment. Since the combination of various vehicle components and the protrusion of connecting parts affect local airflow, the resulting influence is also affected by the three-dimensional parameters of each component.

[0039] Therefore, aerodynamic simulations can be performed on various vehicle components. Based on the simulation results, correlation analysis can be used to determine the degree of wind resistance influence between the components. Based on this degree of wind resistance influence, the drag coefficient of each vehicle component can be obtained by considering its drag coefficient and the aerodynamic interactions between them.

[0040] Finally, in order to improve the accuracy of the basic data, the fluid characteristic changes of the drag coefficient of the vehicle components were simulated to determine the wind resistance characteristic parameters of the vehicle components.

[0041] Step 103: Obtain vehicle tire parameters and simulate the vertical deformation of the tires to obtain the vehicle wind resistance simulation height parameters.

[0042] Specifically, this includes: preprocessing vehicle tire parameters to obtain tire parameters to be simulated; these parameters include tire size, tire material properties, and standard application tire pressure; determining tire vertical stiffness parameters through tire vertical stiffness analysis based on these parameters; obtaining vehicle vertical load parameters; and obtaining vehicle wind resistance simulation height parameters through tire vertical deformation analysis based on the tire vertical stiffness parameters and vehicle vertical load parameters.

[0043] This application obtains vehicle tire parameters and simulates the vertical deformation of the tires to obtain vehicle wind resistance simulation height parameters, thereby realizing height parameter analysis for vehicle-to-everything (V2X) wind resistance simulation and improving the accuracy of wind resistance simulation.

[0044] In the embodiments of this application, the following Example 3 will be explained in detail.

[0045] Example 3: Obtain vehicle tire parameters, including: tire size, tire material properties, and standard application tire pressure.

[0046] Tire material properties, such as the tire's elastic modulus and Poisson's ratio, determine its degree of deformation under stress. Tire dimensions include the tire's width, thickness, and tread design.

[0047] The air pressure inside a tire also affects its deformation. Within a certain range, as the air pressure increases, the tire's lateral stiffness increases, and the deformation decreases. This application uses the standard tire pressure for each tire model as the reference.

[0048] Based on the tire parameters to be simulated, the vertical deformation of the tire under a specific pressure (vehicle vertical load parameter) is calculated using the Fiala model (a tire mechanics model).

[0049] Step 104: Based on the aerodynamic drag characteristic parameters of vehicle components and the simulated height parameters of vehicle aerodynamic drag, determine the simulated parameters of vehicle aerodynamic drag through aerodynamic drag characteristic analysis.

[0050] Specifically, this includes: determining the vehicle's aerodynamic simulation geometric data based on the vehicle's aerodynamic simulation height parameters; determining the vehicle's cavity geometric data based on the vehicle's aerodynamic simulation geometric data, and performing boundary fluid influence analysis on the vehicle's cavity geometric data to obtain the cavity component's aerodynamic drag characteristic parameters; and determining the vehicle's aerodynamic simulation parameters based on the vehicle component's aerodynamic drag characteristic parameters and the cavity component's aerodynamic drag characteristic parameters.

[0051] This application determines vehicle drag simulation parameters by constructing a vehicle drag characteristic model based on the drag characteristic parameters of vehicle components and the vehicle drag simulation height parameters. This enables the analysis of drag parameters for both the wall and non-cavity parts of the vehicle, improving the accuracy of vehicle drag parameters and the generalization ability of the model.

[0052] In the embodiments of this application, the following Example 4 will be explained in detail.

[0053] Example 4: First, based on the aerodynamic drag characteristic parameters of vehicle components and the simulated aerodynamic drag height parameters, extract the cavity geometry data of the vehicle. A cavity refers to a closed or semi-closed space formed inside or outside the vehicle, such as the engine compartment or cooling fan.

[0054] Next, boundary fluid influence analysis is performed on the vehicle cavity geometry data. This step aims to evaluate the fluid flow characteristics at the cavity boundaries and the cavity's contribution to overall drag. Simulation software is used to model the fluid flow around the vehicle, focusing particularly on changes in fluid flow at the cavity inlet, outlet, and interior to obtain drag characteristic parameters of the cavity components.

[0055] After obtaining the drag characteristic parameters of vehicle components (such as pressure distribution and flow velocity distribution on the vehicle body surface) and the drag characteristic parameters of cavity components, these parameters are integrated into the vehicle drag simulation model. These parameters provide key input information for the simulation, enabling the simulation results to more accurately reflect the vehicle's drag performance during actual driving.

[0056] Step 105: Input the vehicle drag simulation parameters into the preset drag simulation model to obtain the dynamic drag model of the vehicle to be trained.

[0057] Specifically, this includes: dividing the vehicle simulation parameters into training data to obtain a simulation model dataset; wherein, the simulation model dataset includes: a simulation training set and a simulation verification set; inputting the simulation training set into the PINN wind resistance simulation model, and configuring the boundary conditions of the wind resistance simulation model to obtain the dynamic wind resistance model of the vehicle to be trained.

[0058] This application achieves the construction of a vehicle dynamic drag model by inputting vehicle drag simulation parameters into a preset PINN drag simulation model to obtain a vehicle dynamic drag model to be trained.

[0059] Step 106: Perform dynamic loss function analysis on the dynamic drag model of the vehicle to be trained to obtain dynamic drag change data of the vehicle, so as to dynamically simulate the vehicle's drag.

[0060] Specifically, this includes: training the vehicle dynamic drag model to convergence based on the simulation validation set to obtain the vehicle drag model; iterating the loss function of the vehicle dynamic drag model to obtain the minimum loss function; updating the drag model weights according to the minimum loss function to obtain the vehicle dynamic drag model; acquiring the current vehicle information and inputting the vehicle information into the vehicle dynamic drag model to obtain the dynamic change data of vehicle drag.

[0061] After performing dynamic loss function analysis on the dynamic drag model of the vehicle to be trained to determine the vehicle drag coefficient data, the method also includes: acquiring drag experiment data, and determining the dynamic adjustment parameters of the loss function based on the drag experiment data through simulation deviation analysis; and determining the dynamic drag model of the vehicle through drag model optimization based on the dynamic adjustment parameters of the loss function.

[0062] Based on wind resistance experimental data, the dynamic adjustment parameters of the loss function are determined through simulation deviation analysis. Specifically, this includes: comparing the wind resistance experimental data with the wind resistance simulation data to determine the wind resistance simulation deviation data; and using a genetic algorithm to iteratively analyze the dynamic parameters of the loss function based on the wind resistance simulation deviation data to determine the dynamic adjustment parameters of the loss function.

[0063] This application uses dynamic loss function analysis on the dynamic drag model of the vehicle to be trained to determine the vehicle drag coefficient data. This enables the simulation of vehicle drag without remodeling the entire vehicle after replacing some surface parts of the vehicle. This improves the prediction efficiency of vehicle drag and reduces the computational requirements for vehicle drag simulation during the research and development process.

[0064] In the embodiments of this application, the following Example 5 will be explained in detail.

[0065] Example 5: First, train the dynamic drag model of the vehicle to be trained. During the training process, continuously adjust the model parameters until the model converges, that is, the model's prediction results are basically consistent with the data in the simulation validation set, thus obtaining a preliminary vehicle drag model.

[0066] Next, the loss function of the vehicle dynamic drag model is iterated. By calculating the error between the model's predicted values ​​and the actual values ​​on the simulation validation set, a loss function is constructed, and the gradient descent optimization algorithm is used to iteratively adjust the model parameters to minimize the loss function value.

[0067] When the loss function value reaches a preset threshold or no longer decreases significantly, the model is considered to have been trained to the optimal state. The model obtained at this time is the vehicle dynamic drag model with the minimum loss function.

[0068] To further improve the model's accuracy and generalization ability, a series of wind resistance data for vehicles under different operating conditions were obtained through wind tunnel experiments or real-world road tests. The experimental wind resistance data was compared with the model's predicted wind resistance data, and the deviation between the two was calculated to obtain the wind resistance simulation deviation data. This step helps identify under which operating conditions the model has significant prediction errors.

[0069] Based on wind resistance simulation deviation data, a genetic algorithm is used to iteratively analyze the dynamic parameters of the loss function. The genetic algorithm is a global optimization algorithm that searches for the optimal solution in the parameter space by simulating natural selection and genetic mechanisms. In this embodiment, the genetic algorithm is used to adjust parameters such as the weights and regularization terms of the loss function to reduce the deviation between model predictions and experimental data.

[0070] The vehicle's dynamic drag model is optimized by dynamically adjusting parameters based on the optimal loss function obtained through iterative analysis using a genetic algorithm. The optimized model will have better predictive performance and generalization ability, and can more accurately reflect the vehicle's drag characteristics under different operating conditions.

[0071] The optimized vehicle dynamic drag model was applied to actual vehicle design and performance evaluation. The accuracy and reliability of the model were verified by comparing the model's predictions with experimental data. Furthermore, the model was continuously iterated and optimized based on new problems and challenges encountered in practical applications to continuously improve its performance.

[0072] The above are embodiments of the method proposed in this application. Based on the same inventive concept, embodiments of this application also provide an artificial intelligence-based vehicle dynamic wind resistance simulation device, the structure of which is as follows: Figure 2 As shown.

[0073] Figure 2 This is a schematic diagram of the internal structure of an artificial intelligence-based vehicle dynamic drag simulation device provided in an embodiment of this application. Figure 2 As shown, the device includes:

[0074] At least one processor 201;

[0075] And a memory 202 that is communicatively connected to at least one processor;

[0076] The memory 202 stores instructions executable by at least one processor, which are executed by at least one processor 201 to enable at least one processor 201 to:

[0077] The process involves acquiring the three-dimensional parameters of vehicle surface components and performing a threshold analysis of their drag influence to identify components that affect vehicle drag. Structural feature analysis is then performed on these components to obtain drag-related characteristic parameters. Vehicle tire parameters are acquired, and their vertical deformation is simulated to obtain the vehicle drag simulation height parameters. Based on the vehicle component drag characteristic parameters and the vehicle drag simulation height parameters, vehicle drag simulation parameters are determined through drag feature analysis. These parameters are then input into a pre-defined drag simulation model to obtain a dynamic drag model for the vehicle to be trained. Finally, dynamic loss function analysis is performed on the dynamic drag model to obtain dynamic drag change data, thus dynamically simulating vehicle drag.

[0078] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for IoT devices and media are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0079] The systems, media, and methods provided in this application are one-to-one correspondences. Therefore, the systems and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be repeated here.

[0080] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0081] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0082] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0083] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0084] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0085] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0086] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0087] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0088] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for simulating dynamic wind resistance of a car based on artificial intelligence, characterized in that, The method includes: The three-dimensional parameters of the vehicle surface components are obtained, and the three-dimensional parameters of the components are subjected to threshold analysis of the degree of wind resistance influence of the vehicle surface components in order to determine the components that affect vehicle wind resistance. The structural features of the vehicle's wind resistance-affecting components are analyzed to obtain the wind resistance-related characteristic parameters of the vehicle surface components. Obtain vehicle tire parameters and simulate tire vertical deformation based on the vehicle tire parameters to obtain vehicle wind resistance simulation height parameters. Based on the aerodynamic drag characteristic parameters of the vehicle components and the aerodynamic drag simulation height parameters of the vehicle, the aerodynamic drag simulation parameters of the vehicle are determined through aerodynamic drag characteristic analysis. The vehicle drag simulation parameters are input into a preset drag simulation model to obtain the dynamic drag model of the vehicle to be trained. Dynamic loss function analysis is performed on the vehicle dynamic drag model to be trained to obtain dynamic change data of vehicle drag, so as to dynamically simulate vehicle drag. A threshold analysis of the wind resistance influence of the three-dimensional parameters of the components on the vehicle surface is performed to determine the components that affect vehicle wind resistance, specifically including: Based on the three-dimensional parameters of the component, the spatial distribution mapping of the vehicle surface component is determined by dividing the vehicle component into spatial distributions. The spatial distribution mapping is delineated to obtain the spatial distribution range of vehicle components; Based on the spatial distribution range of the vehicle components, the threshold of the wind resistance influence range is determined through a correlation assessment of wind resistance influence. Model mapping configuration is performed on the wind resistance influence range threshold to determine the vehicle wind resistance-affecting components; The structural characteristics of the vehicle's aerodynamic drag-affecting components are analyzed to obtain aerodynamic drag-related characteristic parameters of the vehicle surface components, specifically including: Flow field characteristics simulation is performed on the vehicle drag-affecting components to determine the air resistance coefficient set corresponding to the vehicle drag-affecting components; Based on the aforementioned set of air drag coefficients, the air drag coefficients of vehicle components are determined by matching key fields of the components. Correlation analysis between vehicle components is performed on the air drag coefficients of the aforementioned vehicle components to obtain the drag coefficients of the vehicle components; Fluid characteristic variation simulation was performed on the drag coefficient of the vehicle component to determine the wind resistance characteristic parameters of the vehicle component; Based on the aerodynamic drag characteristic parameters of the vehicle components and the simulated aerodynamic drag height parameters of the vehicle, the simulated aerodynamic drag parameters of the vehicle are determined through aerodynamic drag characteristic analysis, specifically including: Based on the vehicle drag simulation height parameters, determine the vehicle drag simulation geometric data; Based on the vehicle aerodynamic drag simulation geometric data, the vehicle cavity geometric data are determined, and boundary fluid influence analysis is performed on the vehicle cavity geometric data to obtain the aerodynamic drag characteristic parameters of the cavity components. Based on the wind resistance characteristic parameters of the vehicle components and the wind resistance characteristic parameters of the cavity components, the vehicle wind resistance simulation parameters are determined.

2. The method for simulating dynamic wind resistance of a car based on artificial intelligence according to claim 1, characterized in that, The vehicle tire parameters are simulated using vertical deformation modeling to obtain the vehicle's wind resistance simulation height parameters, specifically including: The vehicle tire parameters are preprocessed to obtain the tire parameters to be simulated; wherein, the tire parameters to be simulated include: tire size, tire material properties, and standard application air pressure; Based on the tire parameters to be simulated, the tire vertical stiffness parameters are determined through tire vertical stiffness analysis. Obtain the vehicle's vertical load parameters, and based on the tire's vertical stiffness parameters and the vehicle's vertical load parameters, obtain the vehicle's wind resistance simulation height parameters through tire vertical deformation analysis.

3. The method for simulating dynamic wind resistance of a car based on artificial intelligence according to claim 1, characterized in that, The vehicle drag simulation parameters are input into a preset PINN drag simulation model to obtain the dynamic drag model of the vehicle to be trained, specifically including: The vehicle aerodynamic drag simulation parameters are divided into training data to obtain a simulation model dataset; wherein, the simulation model dataset includes: a simulation training set and a simulation validation set; The simulation training set is input into the PINN drag simulation model, and boundary conditions are configured for the PINN drag simulation model to obtain the dynamic drag model of the vehicle to be trained.

4. The method for simulating dynamic wind resistance of a car based on artificial intelligence according to claim 3, characterized in that, Dynamic loss function analysis is performed on the dynamic drag model of the vehicle to be trained to obtain dynamic drag change data, so as to dynamically simulate the vehicle's drag. Specifically, this includes: Based on the simulation verification set, the vehicle dynamic drag model to be trained is trained until the model converges to obtain the vehicle drag model. The loss function is iterated on the vehicle dynamic drag model to obtain the minimum loss function; Based on the minimum loss function, the vehicle dynamic drag model is obtained by updating the drag model weights. Obtain current vehicle information and input the vehicle information into the vehicle dynamic drag model to obtain the dynamic change data of vehicle drag.

5. The method for simulating dynamic wind resistance of a car based on artificial intelligence according to claim 1, characterized in that, After performing dynamic loss function analysis on the vehicle's dynamic drag model to determine the vehicle's drag coefficient data, the method further includes: Obtain wind resistance experimental data, and based on the wind resistance experimental data, determine the dynamic adjustment parameters of the loss function through simulation deviation analysis; The parameters are dynamically adjusted based on the loss function, and the dynamic drag model of the vehicle is determined through wind resistance model optimization.

6. The method for simulating dynamic wind resistance of a car based on artificial intelligence according to claim 5, characterized in that, Based on the aforementioned wind resistance experimental data, the dynamic adjustment parameters of the loss function are determined through simulation deviation analysis, specifically including: The wind resistance experimental data is compared with the wind resistance simulation data to determine the wind resistance simulation deviation data. Based on the wind resistance simulation deviation data, the dynamic parameters of the loss function are iteratively analyzed using a genetic algorithm to determine the dynamic adjustment parameters of the loss function.

7. An artificial intelligence-based vehicle dynamic wind resistance simulation device, characterized in that, The device includes: at least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to: The three-dimensional parameters of the vehicle surface components are obtained, and the three-dimensional parameters of the components are subjected to threshold analysis of the degree of wind resistance influence of the vehicle surface components in order to determine the components that affect vehicle wind resistance. The structural features of the vehicle's wind resistance-affecting components are analyzed to obtain the wind resistance-related characteristic parameters of the vehicle surface components. Obtain vehicle tire parameters and simulate tire vertical deformation based on the vehicle tire parameters to obtain vehicle wind resistance simulation height parameters. Based on the aerodynamic drag characteristic parameters of the vehicle components and the aerodynamic drag simulation height parameters of the vehicle, the aerodynamic drag simulation parameters of the vehicle are determined through aerodynamic drag characteristic analysis. The vehicle drag simulation parameters are input into a preset drag simulation model to obtain the dynamic drag model of the vehicle to be trained. Dynamic loss function analysis is performed on the vehicle dynamic drag model to be trained to obtain dynamic change data of vehicle drag, so as to dynamically simulate vehicle drag. A threshold analysis of the wind resistance influence of the three-dimensional parameters of the components on the vehicle surface is performed to determine the components that affect vehicle wind resistance, specifically including: Based on the three-dimensional parameters of the component, the spatial distribution mapping of the vehicle surface component is determined by dividing the vehicle component into spatial distributions. The spatial distribution mapping is delineated to obtain the spatial distribution range of vehicle components; Based on the spatial distribution range of the vehicle components, the threshold of the wind resistance influence range is determined through a correlation assessment of wind resistance influence. Model mapping configuration is performed on the wind resistance influence range threshold to determine the vehicle wind resistance-affecting components; The structural characteristics of the vehicle's aerodynamic drag-affecting components are analyzed to obtain aerodynamic drag-related characteristic parameters of the vehicle surface components, specifically including: Flow field characteristics simulation is performed on the vehicle drag-affecting components to determine the air resistance coefficient set corresponding to the vehicle drag-affecting components; Based on the aforementioned set of air drag coefficients, the air drag coefficients of vehicle components are determined by matching key fields of the components. Correlation analysis between vehicle components is performed on the air drag coefficients of the aforementioned vehicle components to obtain the drag coefficients of the vehicle components; Fluid characteristic variation simulation was performed on the drag coefficient of the vehicle component to determine the wind resistance characteristic parameters of the vehicle component; Based on the aerodynamic drag characteristic parameters of the vehicle components and the simulated aerodynamic drag height parameters of the vehicle, the simulated aerodynamic drag parameters of the vehicle are determined through aerodynamic drag characteristic analysis, specifically including: Based on the vehicle drag simulation height parameters, determine the vehicle drag simulation geometric data; Based on the vehicle aerodynamic drag simulation geometric data, the vehicle cavity geometric data are determined, and boundary fluid influence analysis is performed on the vehicle cavity geometric data to obtain the aerodynamic drag characteristic parameters of the cavity components. Based on the wind resistance characteristic parameters of the vehicle components and the wind resistance characteristic parameters of the cavity components, the vehicle wind resistance simulation parameters are determined.

Images