Automobile dynamic wind resistance simulation method and device based on artificial intelligence

Abstract

The invention discloses an automobile dynamic wind resistance simulation method and device based on artificial intelligence, and the method comprises the steps: carrying out the wind resistance influence degree threshold analysis of a part three-dimensional parameter of a vehicle surface part, so as to determine a vehicle wind resistance influence part; component structure feature analysis is carried out on the vehicle wind resistance influence component to obtain wind resistance correlation feature parameters of the vehicle surface component; performing tire vertical deformation quantity simulation on the vehicle tire parameters to obtain vehicle wind resistance simulation height parameters; vehicle wind resistance simulation parameters are determined through vehicle wind resistance characteristic analysis; inputting the vehicle wind resistance simulation parameters into a preset wind resistance simulation model to obtain a to-be-trained vehicle dynamic wind resistance model; and carrying out dynamic loss function analysis on the to-be-trained vehicle dynamic wind resistance model to obtain vehicle wind resistance dynamic change data so as to dynamically simulate the vehicle wind resistance. According to the method, the technical problem that the simulated wind resistance of the vehicle cannot be determined directly through replacement of partial components of the vehicle in the wind resistance adjustment process is solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based automobile dynamic wind resistance simulation method and device. Background Art

[0002] In the process of automobile design and development, wind resistance is one of the key factors affecting vehicle performance, fuel economy and noise level. Traditionally, in order to evaluate and optimize the wind resistance performance of automobiles, researchers usually need to model the entire vehicle and use complex computational fluid dynamics (CFD) simulations to analyze the wind resistance performance of the vehicle under different working conditions.

[0003] In the prior art, the simulation of vehicle wind resistance is usually achieved by modeling the entire vehicle, and the wind resistance effects of various components on the surface of the vehicle are interrelated. Analyzing a certain component alone may not accurately reflect its actual performance in the entire vehicle. In the development process of multiple models of vehicles and vehicles of the same model, it is difficult to re-model the replacement or modification of some vehicle components. The amount of calculation and the calculation time are difficult to meet the production needs. It is impossible to provide wind resistance simulation data for reference in time when some vehicle components are modified during the wind resistance adjustment process. Summary of the invention

[0004] The embodiments of the present application provide a method and device for simulating dynamic wind resistance of an automobile based on artificial intelligence, which solves the technical problem that in the wind resistance adjustment process of the prior art, the simulated wind resistance of the vehicle cannot be determined directly by replacing some components of the vehicle.

[0005] In a first aspect, an embodiment of the present application provides an artificial intelligence-based method for simulating dynamic wind resistance of an automobile, characterized in that the method includes: obtaining three-dimensional parameters of component surfaces of a vehicle, and performing a threshold analysis of the wind resistance influence degree of the component surfaces of the vehicle on the three-dimensional parameters to determine the components affecting the vehicle wind resistance; performing a component structural characteristic analysis on the components affecting the vehicle wind resistance to obtain wind resistance correlation characteristic parameters of the vehicle surface components; obtaining vehicle tire parameters, and performing a tire vertical deformation simulation on the vehicle tire parameters to obtain vehicle wind resistance simulation height parameters; determining vehicle wind resistance simulation parameters through vehicle wind resistance characteristic analysis based on the vehicle component wind resistance characteristic parameters and the vehicle wind resistance simulation height parameters; 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; performing a dynamic loss function analysis on the dynamic wind resistance model of the vehicle to be trained to obtain vehicle wind resistance dynamic change data to dynamically simulate the vehicle wind resistance.

[0006] In one implementation of the present application, a threshold analysis of the degree of wind resistance influence of vehicle surface components is performed on component three-dimensional parameters to determine the vehicle wind resistance influence components, specifically including: based on the component three-dimensional parameters, determining the spatial distribution mapping of the vehicle surface parameters by dividing the spatial distribution of vehicle components; delineating the distribution range of the spatial distribution mapping to obtain the spatial distribution range of vehicle components; determining the wind resistance influence range threshold through wind resistance influence correlation evaluation based on the spatial distribution range of vehicle components; and performing model mapping configuration on the wind resistance influence range threshold to determine the vehicle wind resistance influence components.

[0007] In one implementation of the present application, structural feature analysis of vehicle wind resistance-affecting components is performed to obtain wind resistance-related characteristic parameters of vehicle surface components, specifically including: simulating flow field characteristics of vehicle surface wind resistance-affecting components to determine a set of air resistance coefficients corresponding to the vehicle surface wind resistance-affecting components; determining the air resistance coefficients of vehicle components by matching key fields of components based on the air resistance coefficient set; performing correlation analysis between vehicle components on the air resistance coefficients of vehicle components to obtain the drag coefficients of vehicle components; and simulating fluid feature changes on the drag coefficients of vehicle components to determine the wind resistance characteristic parameters of vehicle components.

[0008] In one implementation of the present application, the tire vertical deformation amount of the vehicle tire parameters is simulated to obtain the vehicle wind resistance simulation height parameters, specifically including: performing data preprocessing on 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 air pressure; based on the tire parameters to be simulated, the tire vertical stiffness parameters are determined through tire vertical stiffness analysis; the vehicle vertical load parameters are obtained, and based on the tire vertical stiffness parameters and the vehicle vertical load parameters, the vehicle wind resistance simulation height parameters are obtained through tire vertical deformation analysis.

[0009] In one implementation of the present application, based on the vehicle component wind resistance characteristic parameters and the vehicle wind resistance simulation height parameters, the vehicle wind resistance simulation parameters are determined through vehicle wind resistance characteristic analysis, specifically including: determining the vehicle wind resistance simulation geometry data based on the vehicle wind resistance simulation height parameters; determining the vehicle cavity geometry data based on the vehicle wind resistance simulation geometry data, and performing boundary fluid influence analysis on the vehicle cavity geometry data to obtain the cavity component wind resistance characteristic parameters; determining the vehicle wind resistance simulation parameters based on the vehicle component wind resistance characteristic parameters and the cavity component wind resistance characteristic parameters.

[0010] In one implementation of the present application, the vehicle wind resistance simulation parameters are input into a preset wind resistance simulation model to obtain a dynamic wind resistance model of the vehicle to be trained, specifically including: dividing the training data of the vehicle simulation parameters to obtain a simulation model data set; wherein the simulation model data set includes: a simulation training set and a simulation verification set; inputting the simulation training set into the 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.

[0011] In one implementation of the present application, a dynamic loss function analysis is performed on the dynamic wind resistance model of the vehicle to be trained to obtain dynamic change data of the vehicle's wind resistance so as to dynamically simulate the automobile's wind resistance, specifically including: based on a simulation verification set, training the dynamic wind resistance model of the vehicle to be trained until the model converges to obtain the vehicle's wind resistance model; iterating the loss function of the vehicle's dynamic wind resistance model to obtain the minimum loss function; according to the minimum loss function, obtaining the vehicle's dynamic wind resistance model by updating the wind resistance model weights; obtaining the current vehicle information, and inputting the vehicle information into the vehicle's dynamic wind resistance model to obtain the vehicle's wind resistance dynamic change data.

[0012] In one implementation of the present application, after performing a dynamic loss function analysis on the dynamic wind resistance model of the vehicle to be trained to determine the vehicle wind resistance coefficient data, the method also includes: obtaining wind resistance experimental data, and based on the wind resistance experimental data, determining the dynamic adjustment parameters of the loss function through simulation deviation analysis; according to the dynamic adjustment parameters of the loss function, determining the dynamic wind resistance model of the vehicle through wind resistance model optimization.

[0013] In one implementation of the present application, based on the wind resistance experimental data, the dynamic adjustment parameters of the loss function are determined through simulation deviation analysis, specifically including: comparing the wind resistance experimental data with the wind resistance experimental data to determine the wind resistance simulation deviation data; based on the wind resistance simulation deviation data, iteratively analyzing the dynamic parameters of the loss function through a genetic algorithm to determine the dynamic adjustment parameters of the loss function.

[0014] In a second aspect, an embodiment of the present application also provides an artificial intelligence-based automobile 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; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: obtain component three-dimensional parameters of vehicle surface components, and perform a threshold analysis of the wind resistance influence degree of the vehicle surface components on the component three-dimensional parameters to determine the vehicle wind resistance affecting components; perform component structural feature analysis on the vehicle wind resistance affecting components to obtain wind resistance correlation feature parameters of the vehicle surface components; obtain vehicle tire parameters, and perform tire vertical deformation simulation on the vehicle tire parameters to obtain vehicle wind resistance simulation height parameters; determine vehicle wind resistance simulation parameters through vehicle wind resistance feature analysis based on vehicle component wind resistance feature parameters and vehicle wind resistance simulation height parameters; input 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; perform a dynamic loss function analysis on the dynamic wind resistance model of the vehicle to be trained to obtain vehicle wind resistance dynamic change data to dynamically simulate the vehicle wind resistance.

[0015] The embodiment of the present application provides a method and device for simulating dynamic wind resistance of an automobile based on artificial intelligence, which solves the technical problem that the simulated wind resistance of the vehicle cannot be determined directly by replacing some components of the vehicle during the wind resistance adjustment process of the prior art through mapping the spatial range corresponding to the vehicle components, simulating the wind environment and vehicle height of different models, and dynamically modeling the vehicle wind resistance. It realizes that after replacing some vehicle surface components, the vehicle wind resistance can be simulated without re-modeling the entire vehicle, thereby improving the prediction efficiency of the vehicle wind resistance and reducing the computational requirements of vehicle wind resistance simulation during the research and development process. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 A flow chart of a method for simulating dynamic wind resistance of an automobile based on artificial intelligence provided in an embodiment of the present application;

[0018] Figure 2 A schematic diagram of the internal structure of an artificial intelligence-based automobile dynamic wind resistance simulation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0020] The embodiment of the present application provides a method and device for simulating dynamic wind resistance of an automobile based on artificial intelligence, which solves the technical problem that the simulated wind resistance of the vehicle cannot be determined directly by replacing some components of the vehicle during the wind resistance adjustment process of the prior art through mapping the spatial range corresponding to the vehicle components, simulating the wind environment and vehicle height of different models, and dynamically modeling the vehicle wind resistance. It realizes that after replacing some vehicle surface components, the vehicle wind resistance can be simulated without re-modeling the entire vehicle, thereby improving the prediction efficiency of the vehicle wind resistance and reducing the computational requirements of vehicle wind resistance simulation during the research and development process.

[0021] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0022] Figure 1 The following is a flow chart of a method for simulating dynamic wind resistance of an automobile based on artificial intelligence provided in an embodiment of the present application. Figure 1 As shown, an artificial intelligence-based automobile dynamic wind resistance simulation method provided in an embodiment of the present application specifically includes the following steps:

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

[0024] Specifically, it includes: based on the three-dimensional parameters of the components, the spatial distribution mapping of the vehicle surface parameters is determined through the spatial distribution division of the vehicle components; the distribution range of the spatial distribution mapping is circled to obtain the spatial distribution range of the vehicle components; according to the spatial distribution range of the vehicle components, the wind resistance influence range threshold is determined through the wind resistance influence correlation evaluation; the wind resistance influence range threshold is model mapped and configured to determine the vehicle wind resistance influence components.

[0025] The present application obtains the three-dimensional parameters of vehicle surface components and performs a wind resistance influence threshold analysis on the three-dimensional parameters to determine the components that influence the vehicle wind resistance, thereby realizing the influence degree and influence relationship analysis of vehicle surface components of different automobile models, and improving the accuracy of vehicle wind resistance simulation.

[0026] In the examples of the present application, a detailed explanation is given by the following Example 1.

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

[0028] First, the front part of the vehicle is the main wind resistance influencing surface, which is mainly composed of the windshield and the vehicle heat exchange part (determined by the vehicle driving mode). In order to determine the main distribution positions of various vehicle components, it is necessary to define the distribution range of the spatial distribution mapping to obtain the spatial distribution range of vehicle components. The spatial distribution range of vehicle components represents the main spatial distribution of each vehicle component. For example, the spatial distribution and connection relationship of components that mainly affect the wind resistance of the vehicle, such as the windshield and rearview mirror.

[0029] The maximum spatial range defined by the distribution range is the space formed by the outermost surfaces of all components corresponding to all currently enterable component models. When components are replaced, there will be no wind resistance simulation calculations beyond this range, and subsequent wind resistance simulations can be performed more stably. When a higher-level change is required to result in a larger distribution range, the distribution range space can be expanded.

[0030] It should be noted that spatial distribution mapping can help the model to import key fields or preset names of vehicles and vehicle components during wind resistance simulation, and then search for corresponding component data based on spatial distribution mapping.

[0031] Then, the aerodynamic simulation can be used to simulate the various parts of the vehicle, and based on the results of the aerodynamic simulation, the wind resistance of each part of the vehicle under certain fluid configuration conditions can be determined through correlation analysis, and the wind resistance impact range threshold can be set according to actual production needs. This threshold is used to determine which parts are the key influencing parts of the vehicle's wind resistance.

[0032] Finally, the wind resistance impact range threshold is configured by model mapping to determine the wind resistance impacting components of the vehicle.

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

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

[0035] This application analyzes the structural characteristics of the components that affect the wind resistance of the vehicle to obtain the wind resistance correlation characteristic parameters of the vehicle surface components, thereby achieving

[0036] In the examples of the present application, detailed explanation is given by the following Example 2.

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

[0038] Then, according to the spatial distribution range of vehicle components, the wind resistance impact correlation evaluation is performed to determine the wind resistance impact range threshold. Since the combination of vehicle components and the protrusion of the connecting parts will affect the local airflow, the result of the impact is also affected by the three-dimensional parameters of each component.

[0039] Therefore, aerodynamic simulation can be used to simulate each vehicle component, and based on the results of aerodynamic simulation, the wind resistance influence degree between each vehicle component and the components can be determined through correlation analysis. According to the above wind resistance influence degree, the drag coefficient of each vehicle component and the aerodynamic influence between the components can be used to obtain the drag coefficient of the vehicle component.

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

[0041] Step 103: Acquire vehicle tire parameters, and simulate the tire vertical deformation amount on the vehicle tire parameters to obtain vehicle wind resistance simulation height parameters.

[0042] Specifically, it includes: performing data preprocessing on vehicle tire parameters to obtain 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, determining the tire vertical stiffness parameters through tire vertical stiffness analysis; obtaining the vehicle vertical load parameters, and obtaining the vehicle wind resistance simulation height parameters through tire vertical deformation analysis based on the tire vertical stiffness parameters and the vehicle vertical load parameters.

[0043] The present application obtains vehicle tire parameters and simulates the vertical deformation of the tire to obtain vehicle wind resistance simulation height parameters, thereby realizing height parameter analysis of vehicle-connected wind resistance simulation and improving the accuracy of wind resistance simulation.

[0044] In the examples of the present application, this is explained in detail through the following Example 3.

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

[0046] Tire material properties, including elastic modulus and Poisson's ratio, determine the degree of deformation after being subjected to force. Tire size includes tire width, thickness and tread design.

[0047] The air pressure inside the tire will also affect its deformation. Within a certain range, as the air pressure increases, the tire's lateral stiffness increases and the deformation decreases. This application is based on the tire standard application pressure of each model of tire.

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

[0049] Step 104 : determining vehicle wind resistance simulation parameters through vehicle wind resistance characteristic analysis based on vehicle component wind resistance characteristic parameters and vehicle wind resistance simulation height parameters.

[0050] Specifically, it includes: determining the vehicle wind resistance simulation geometry data based on the vehicle wind resistance simulation height parameters; determining the vehicle cavity geometry data based on the vehicle wind resistance simulation geometry data, and performing boundary fluid influence analysis on the vehicle cavity geometry data to obtain the cavity component wind resistance characteristic parameters; determining the vehicle wind resistance simulation parameters based on the vehicle component wind resistance characteristic parameters and the cavity component wind resistance characteristic parameters.

[0051] The present application determines the vehicle wind resistance simulation parameters by constructing a vehicle wind resistance characteristic model based on the wind resistance characteristic parameters of vehicle components and the vehicle wind resistance simulation height parameters, thereby realizing wind resistance parameter analysis of the vehicle wall part and non-cavity part, and improving the accuracy of the vehicle wind resistance parameters and the generalization ability of the model.

[0052] In the examples of the present application, a detailed explanation is given by the following Example 4.

[0053] Example 4: First, based on the wind resistance characteristic parameters of vehicle components and the vehicle wind resistance simulation height parameters, the cavity geometry data of the vehicle is extracted. The cavity refers to the closed or semi-enclosed space formed inside or outside the vehicle, such as the engine compartment, cooling fan, etc.

[0054] Then, the boundary fluid impact analysis is performed on the vehicle cavity geometry data. This step aims to evaluate the flow characteristics of the fluid on the cavity boundary and the contribution of the cavity to the overall wind resistance. The flow of fluid around the vehicle is simulated by simulation software, especially focusing on the changes in the fluid at the cavity inlet, outlet and internal flow to obtain the wind resistance characteristic parameters of the cavity components.

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

[0056] Step 105: input 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.

[0057] Specifically, it includes: dividing the training data of vehicle simulation parameters to obtain a simulation model data set; wherein the simulation model data set 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 a dynamic wind resistance model of the vehicle to be trained.

[0058] The present application constructs a vehicle dynamic wind resistance model by inputting vehicle wind resistance simulation parameters into a preset PINN wind resistance simulation model to obtain a vehicle dynamic wind resistance model to be trained.

[0059] Step 106: Perform a dynamic loss function analysis on the dynamic wind resistance model of the vehicle to be trained to obtain dynamic change data of the vehicle wind resistance to dynamically simulate the wind resistance of the vehicle.

[0060] Specifically, the method includes: based on the simulation verification set, training the dynamic wind resistance model of the vehicle to be trained until the model converges to obtain the vehicle wind resistance model; iterating the loss function of the vehicle dynamic wind resistance model to obtain the minimum loss function; according to the minimum loss function, updating the wind resistance model weights to obtain the vehicle dynamic wind resistance model; obtaining the current vehicle information, and inputting the vehicle information into the vehicle dynamic wind resistance model to obtain the vehicle wind resistance dynamic change data.

[0061] After performing a dynamic loss function analysis on the dynamic wind resistance model of the vehicle to be trained to determine the vehicle wind resistance coefficient data, the method also includes: obtaining wind resistance experimental data, and based on the wind resistance experimental data, determining the dynamic adjustment parameters of the loss function through simulation deviation analysis; dynamically adjusting the parameters according to the loss function, and determining the dynamic wind resistance model of the vehicle through wind resistance model optimization.

[0062] Based on the wind resistance experimental data, the dynamic adjustment parameters of the loss function are determined through simulation deviation analysis, specifically including: comparing the wind resistance experimental data with the wind resistance experimental data for data deviation 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 through a genetic algorithm to determine the dynamic adjustment parameters of the loss function.

[0063] The present application determines the vehicle drag coefficient data by performing a dynamic loss function analysis on the dynamic drag model of the vehicle to be trained. This enables the vehicle drag to be simulated without remodeling the entire vehicle after some vehicle surface components have been replaced, thereby improving the efficiency of predicting vehicle drag and reducing the computational requirements for vehicle drag simulation during the research and development process.

[0064] In the examples of the present application, this is explained in detail through the following Example 5.

[0065] Example 5: First, the dynamic wind resistance model of the vehicle to be trained is trained. During the training process, the model parameters are continuously adjusted until the model converges, that is, the prediction results of the model are basically consistent with the data in the simulation verification set, thereby obtaining a preliminary vehicle wind resistance model.

[0066] Next, the loss function of the vehicle dynamic wind resistance model is iterated. The error between the model prediction value and the true value of the simulation verification set is calculated to construct the loss function, 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 the 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 wind resistance model with the minimum loss function.

[0068] In order to further improve the accuracy and generalization ability of the model, a series of wind resistance data of vehicles under different working conditions are obtained through wind tunnel experiments or actual road tests. The wind resistance experimental data is compared with the wind resistance data predicted by the model, and the deviation between the two is calculated to obtain the wind resistance simulation deviation data. This step helps to identify under which working conditions the model has a large prediction error.

[0069] Based on the drag 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 the weights, regularization terms and other parameters of the loss function to reduce the deviation between the model prediction and the experimental data.

[0070] The optimal loss function obtained by iterative analysis of the genetic algorithm is used to dynamically adjust the parameters and optimize the vehicle dynamic wind resistance model. The optimized model will have better prediction performance and generalization ability, and can more accurately reflect the wind resistance characteristics of the vehicle under different working conditions.

[0071] The optimized vehicle dynamic drag model is applied to actual vehicle design and performance evaluation. The accuracy and reliability of the model are verified by comparing the model prediction results with experimental data. At the same time, the model is continuously iterated and optimized according to new problems and challenges encountered in actual applications to continuously improve its performance.

[0072] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, the embodiment of this application also provides an artificial intelligence-based automobile dynamic wind resistance simulation device, whose structure is as follows: Figure 2 shown.

[0073] Figure 2 The internal structure diagram of an artificial intelligence-based vehicle dynamic wind resistance simulation device provided in the embodiment of the present application is shown in FIG. Figure 2 As shown, the device includes:

[0074] at least one processor 201;

[0075] and, a memory 202 communicatively connected to the at least one processor;

[0076] The memory 202 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 201 to enable at least one processor 201 to:

[0077] The three-dimensional parameters of the vehicle surface components are obtained, and the wind resistance influence threshold analysis of the three-dimensional parameters of the components is performed on the vehicle surface components to determine the vehicle wind resistance influence components; the component structure characteristics analysis is performed on the vehicle wind resistance influence components to obtain the wind resistance correlation characteristic parameters of the vehicle surface components; the vehicle tire parameters are obtained, and the tire vertical deformation simulation is performed on the vehicle tire parameters to obtain the vehicle wind resistance simulation height parameters; based on the vehicle component wind resistance characteristic parameters and the vehicle wind resistance simulation height parameters, the vehicle wind resistance simulation parameters are determined through the vehicle wind resistance characteristic analysis; the vehicle wind resistance simulation parameters are input into the preset wind resistance simulation model to obtain the dynamic wind resistance model of the vehicle to be trained; the dynamic loss function analysis is performed on the dynamic wind resistance model of the vehicle to be trained to obtain the dynamic change data of the vehicle wind resistance to dynamically simulate the wind resistance of the vehicle. .

[0078] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0079] The system and medium provided in the embodiments of the present application correspond one-to-one to the method. Therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0080] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may 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 may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include 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 generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. 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 memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0083] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

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

[0085] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0086] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules 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 technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0087] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0088] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for simulating dynamic wind resistance of an automobile based on artificial intelligence, characterized in that: The method comprises: Acquiring three-dimensional parameters of vehicle surface components, and performing wind resistance influence threshold analysis of the vehicle surface components on the three-dimensional parameters of the components to determine the vehicle wind resistance influence components; Performing component structural characteristic analysis on the vehicle wind resistance-affecting component to obtain wind resistance-related characteristic parameters of the vehicle surface component; Acquiring vehicle tire parameters, and simulating the tire vertical deformation amount on the vehicle tire parameters to obtain vehicle wind resistance simulation height parameters; Based on the vehicle component wind resistance characteristic parameters and the vehicle wind resistance simulation height parameters, determining the vehicle wind resistance simulation parameters through vehicle wind resistance characteristic 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; A dynamic loss function analysis is performed on the dynamic wind resistance model of the vehicle to be trained to obtain dynamic change data of the vehicle wind resistance to dynamically simulate the vehicle wind resistance.

2. The method for simulating dynamic wind resistance of an automobile based on artificial intelligence according to claim 1, characterized in that: The wind resistance influence threshold analysis of the vehicle surface components is performed on the three-dimensional parameters of the components to determine the wind resistance influence components of the vehicle, specifically including: Based on the three-dimensional parameters of the components, determining a spatial distribution map of the vehicle surface parameters by dividing the spatial distribution of the vehicle components; Delineating the distribution range of the spatial distribution map to obtain the spatial distribution range of vehicle components; According to the spatial distribution range of the vehicle components, a wind resistance impact range threshold is determined by evaluating the wind resistance impact correlation; The wind resistance influence range threshold is configured by model mapping to determine the wind resistance influence component of the vehicle.

3. The method for simulating dynamic wind resistance of an automobile based on artificial intelligence according to claim 1, characterized in that: The component structure characteristics of the vehicle wind resistance influencing component are analyzed to obtain wind resistance correlation characteristic parameters of the vehicle surface component, specifically including: Performing flow field characteristic simulation on the wind resistance influencing component on the vehicle surface to determine an air resistance coefficient set corresponding to the wind resistance influencing component on the vehicle surface; Based on the air resistance coefficient set, determining the air resistance coefficient of the vehicle component by matching the key fields of the component; Performing correlation analysis between vehicle components on the air drag coefficient of the vehicle components to obtain the drag coefficient of the vehicle components; The fluid characteristic change simulation is performed on the drag coefficient of the vehicle component to determine the wind resistance characteristic parameters of the vehicle component.

4. The method for simulating dynamic wind resistance of an automobile based on artificial intelligence according to claim 1, characterized in that: The tire vertical deformation amount simulation is performed on the vehicle tire parameters to obtain the vehicle wind resistance simulation height parameters, specifically including: Performing data preprocessing on the vehicle tire parameters to obtain 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, determining tire vertical stiffness parameters through tire vertical stiffness analysis; The vehicle vertical load parameter is obtained, and the vehicle wind resistance simulation height parameter is obtained through tire vertical deformation analysis based on the tire vertical stiffness parameter and the vehicle vertical load parameter.

5. The method for simulating dynamic wind resistance of an automobile based on artificial intelligence according to claim 1, characterized in that: Based on the vehicle component wind resistance characteristic parameter and the vehicle wind resistance simulation height parameter, the vehicle wind resistance simulation parameter is determined by analyzing the vehicle wind resistance characteristic, specifically including: Determining vehicle wind resistance simulation geometric data based on the vehicle wind resistance simulation height parameter; Determining vehicle cavity geometry data according to the vehicle wind resistance simulation geometry data, and performing boundary fluid influence analysis on the vehicle cavity geometry data to obtain cavity component wind resistance characteristic parameters; The vehicle wind resistance simulation parameters are determined according to the vehicle component wind resistance characteristic parameters and the cavity component wind resistance characteristic parameters.

6. The method for simulating dynamic wind resistance of an automobile based on artificial intelligence according to claim 1, characterized in that: Inputting the vehicle wind resistance simulation parameters into a preset PINN wind resistance simulation model to obtain a dynamic wind resistance model of the vehicle to be trained, specifically including: Performing training data division on the vehicle simulation parameters to obtain a simulation model data set; wherein the simulation model data set includes: a simulation training set and a simulation verification set; The simulation training set is input into the wind resistance simulation model, and boundary conditions are configured for the wind resistance simulation model to obtain the dynamic wind resistance model of the vehicle to be trained.

7. The method for simulating dynamic wind resistance of an automobile based on artificial intelligence according to claim 6, characterized in that: Performing a dynamic loss function analysis on the dynamic wind resistance model of the vehicle to be trained to obtain dynamic change data of the vehicle wind resistance to dynamically simulate the wind resistance of the vehicle, specifically including: Based on the simulation verification set, the dynamic wind resistance model of the vehicle to be trained is trained until the model converges to obtain a vehicle wind resistance model; Iterating the loss function of the vehicle dynamic wind resistance model to obtain a minimum loss function; According to the minimum loss function, the vehicle dynamic wind resistance model is obtained by updating the wind resistance model weight; The current vehicle information is acquired, and the vehicle information is input into the vehicle dynamic wind resistance model to obtain the vehicle wind resistance dynamic change data.

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

9. The method for simulating dynamic wind resistance of an automobile based on artificial intelligence according to claim 8, characterized in that: Based on the wind resistance test data, the loss function dynamic adjustment parameters are determined through simulation deviation analysis, specifically including: Comparing the wind resistance test data with the wind resistance experimental data for data deviation to determine wind resistance simulation deviation data; Based on the wind resistance simulation deviation data, the dynamic parameters of the loss function are iteratively analyzed through a genetic algorithm to determine the dynamic adjustment parameters of the loss function.

10. An artificial intelligence-based vehicle dynamic wind resistance simulation device, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Acquiring three-dimensional parameters of vehicle surface components, and performing wind resistance influence threshold analysis of the vehicle surface components on the three-dimensional parameters of the components to determine the vehicle wind resistance influence components; Performing component structural characteristic analysis on the vehicle wind resistance-affecting component to obtain wind resistance-related characteristic parameters of the vehicle surface component; Acquiring vehicle tire parameters, and simulating the tire vertical deformation amount on the vehicle tire parameters to obtain vehicle wind resistance simulation height parameters; Based on the vehicle component wind resistance characteristic parameters and the vehicle wind resistance simulation height parameters, determining the vehicle wind resistance simulation parameters through vehicle wind resistance characteristic 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; A dynamic loss function analysis is performed on the dynamic wind resistance model of the vehicle to be trained to obtain dynamic change data of the vehicle wind resistance to dynamically simulate the vehicle wind resistance.

Images