Vehicle bottom intelligent pneumatic suite structure arrangement optimization method, equipment, medium and product

Abstract

The invention discloses a vehicle bottom intelligent pneumatic suite structure arrangement optimization method and device, a medium and a product, and relates to the technical field of vehicle aerodynamics and optimizing.The method comprises the steps that a pneumatic suite target height prediction model corresponding to a current working mode is determined as a current pneumatic suite target height prediction model; inputting the vehicle speed, the environment wind speed and the wind direction at the current moment into a current pneumatic suite target height prediction model to obtain a target arrangement state of the pneumatic suite; and a plurality of adjustable device control modules are controlled, so that each pneumatic part in the pneumatic suite reaches the target height. The arrangement state of the vehicle bottom pneumatic suite structure is dynamically adjusted based on the vehicle speed and the wind field environment change during driving, and the operation stability and the fuel economy of the vehicle during high-speed driving are improved.

Description

Technical Field

[0001] The present application relates to the field of automobile aerodynamics and optimization technology, and in particular to a method, device, medium and product for optimizing the structural layout of an underbody intelligent aerodynamic kit. Background Art

[0002] The high-speed aerodynamic performance of a car is a key technical indicator that determines fuel economy and handling stability. Its main influencing factors include body shape and crosswind effects. The influence of the bottom structure is particularly important, and its contribution to aerodynamics is as high as about 25%. When the driving speed and wind environment change, the interaction between the car and the air changes essentially, and its influence becomes more complicated. Therefore, controlling the bottom flow structure of the car in a crosswind environment is crucial to improving the high-speed aerodynamic performance of the car.

[0003] The shape of the bottom of the car is greatly affected by the arrangement of the chassis structural parts. In order to reduce aerodynamic drag and aerodynamic lift, existing production models often design fixed air dams and side skirts at the front and sides of the bottom of the car. It can not only suppress the impact of high-speed airflow on the bottom structural parts, but also prevent excessive airflow from entering the bottom of the car to induce the bottom separation vortex. Fixed air dams and side skirts will have a good drag reduction effect under no crosswind conditions, but may cause increased aerodynamic drag when driving in a crosswind environment, and may even increase the aerodynamic lift of the entire vehicle, deteriorating the high-speed aerodynamic stability of the car. Therefore, the present application proposes a pneumatic kit structural layout and optimization method that can be dynamically adjusted according to the environmental side wind to meet the needs of different driving conditions and maximize the fuel economy and handling stability of high-speed cars. Summary of the invention

[0004] The purpose of this application is to provide a method, device, medium and product for optimizing the structural layout of an underbody intelligent aerodynamic kit, which can dynamically adjust the layout state of the underbody aerodynamic kit structure based on changes in vehicle speed and wind field environment during driving, thereby improving the vehicle's handling stability and fuel economy.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for optimizing the structural layout of an underbody intelligent pneumatic kit, wherein the method is applied to a vehicle, wherein the vehicle is provided with a wind speed and direction sensor, a plurality of adjustable devices, and a plurality of adjustable device control modules;

[0007] The adjustable device is arranged in one-to-one correspondence with a plurality of pneumatic parts in the pneumatic kit structure; any of the pneumatic parts is connected to the bottom of the vehicle through the corresponding adjustable device; the adjustable device control module is arranged in one-to-one correspondence with the adjustable device;

[0008] The adjustable device control module is used to control the extension and retraction amount of the corresponding adjustable device, thereby adjusting the height of the corresponding pneumatic part;

[0009] The wind speed sensor is used to obtain the ambient wind speed and wind direction;

[0010] The method for optimizing the structural layout of the underbody intelligent pneumatic kit comprises:

[0011] Get the current ambient wind speed and direction;

[0012] The working mode executed by the vehicle at the current moment is obtained as the current working mode; the working mode is a safety mode or an energy-saving mode;

[0013] Determine the aerodynamic kit target height prediction model corresponding to the current working mode as the current aerodynamic kit target height prediction model;

[0014] Inputting the current vehicle speed, ambient wind speed and wind direction into the current aerodynamic kit target height prediction model to obtain a target layout state of the aerodynamic kit; the target layout state includes a target height of each aerodynamic component in the aerodynamic kit;

[0015] Control multiple adjustable device control modules to achieve the target height for each pneumatic component in the pneumatic kit.

[0016] Optionally, the aerodynamic parts include an air dam and side skirts.

[0017] Optionally, the adjustable device control module is a rotating motor.

[0018] Optionally, before obtaining the current ambient wind speed and wind direction, the method further includes:

[0019] Acquire a plurality of design variable groups; the design variable groups include vehicle speed, ambient wind speed and wind direction, and a height range of each pneumatic component in the pneumatic kit structure;

[0020] Determine the full factorial experimental design matrix corresponding to each design variable group;

[0021] Construct vehicle aerodynamic simulation model;

[0022] Inputting multiple full-factor experimental design matrices into the vehicle aerodynamic simulation model respectively to obtain aerodynamic simulation data corresponding to each design variable group; the aerodynamic simulation data includes aerodynamic drag and aerodynamic lift;

[0023] With the design variable group as input and the aerodynamic simulation data corresponding to the design variable group as output, the initial aerodynamic prediction model is trained and optimized to obtain the design variable group-aerodynamic data mapping relationship and the optimal design variable group; the initial aerodynamic model adopts an elliptical radial basis function neural network to establish the design variable group-aerodynamic data mapping relationship, and adopts a multi-island genetic algorithm to perform iterative optimization of the optimal combination of the aerodynamic kit.

[0024] Optionally, before obtaining the ambient wind speed at the current moment, the method further includes:

[0025] The optimal design variable group and the mapping relationship between the design variable group and aerodynamic data in the safety mode are learned and trained. The six-layer perceptron model is used as a regression analysis tool to minimize the aerodynamic lift and determine the optimal layout of the aerodynamic kit under different vehicle speeds, ambient wind speeds and wind directions in the safety mode.

[0026] The vehicle speed, ambient wind speed and wind direction are taken as input, and the optimal layout state of the aerodynamic kit under different vehicle speeds, ambient wind speeds and wind directions in safety mode is fitted as output to obtain the aerodynamic kit target height prediction model corresponding to the safety mode.

[0027] Optionally, before obtaining the ambient wind speed at the current moment, the method further includes:

[0028] The optimal design variable group and the implicit relationship between the design variable group and aerodynamic data in the energy-saving mode are learned and trained. The six-layer perceptron model is used as a regression analysis tool to minimize aerodynamic drag and determine the optimal layout of the aerodynamic kit under different vehicle speeds, ambient wind speeds and wind directions in the energy-saving mode.

[0029] The vehicle speed, ambient wind speed and wind direction are taken as input, and the optimal layout state of the aerodynamic kit under different vehicle speeds, ambient wind speeds and wind directions in energy-saving mode is fitted as output to obtain the aerodynamic kit target height prediction model corresponding to the energy-saving mode.

[0030] Optionally, controlling the plurality of adjustable device control modules so that each pneumatic component in the pneumatic kit reaches a target height includes:

[0031] Get the real-time height of each pneumatic component in the pneumatic kit;

[0032] Based on the real-time height and target height of each pneumatic component, an adjustment instruction of each adjustable device control module is generated and executed until each pneumatic component in the pneumatic kit reaches the target height.

[0033] In a second aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method for optimizing the structural layout of the underbody intelligent aerodynamic kit.

[0034] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for optimizing the structural layout of the underbody intelligent aerodynamic kit.

[0035] In a fourth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned method for optimizing the structural layout of the underbody intelligent aerodynamic kit.

[0036] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0037] The present application provides a method, device, medium and product for optimizing the structural layout of an underbody intelligent pneumatic kit, which can obtain the ambient wind speed and wind direction at the current moment; obtain the working mode executed by the vehicle at the current moment as the current working mode; and the working mode can be a safety mode or an energy-saving mode. Determine the target height prediction model of the pneumatic kit corresponding to the current working mode as the current target height prediction model of the pneumatic kit; input the vehicle speed, ambient wind speed and wind direction at the current moment into the current target height prediction model of the pneumatic kit to obtain the target layout state of the pneumatic kit; control multiple adjustable device control modules so that each pneumatic part in the pneumatic kit reaches the target height, which can meet the performance requirements of different driving conditions and maximize the fuel economy and handling stability of high-speed vehicles. The calculation method and analysis results can provide more valuable reference data for the design of future intelligent pneumatic kits. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 A schematic diagram of a vehicle using a method for optimizing the structural arrangement of an underbody intelligent aerodynamic kit in an embodiment of the present application;

[0040] Figure 2 This is a schematic diagram of the structure of an adjustable device in one embodiment of the present application;

[0041] Figure 3 This is a cross-sectional view of an adjustable device in one embodiment of the present application;

[0042] Figure 4 This is a flow chart of a method for optimizing the structural arrangement of an underbody intelligent pneumatic kit in one embodiment of the present application;

[0043] Figure 5 This is a schematic diagram of a method for optimizing the structural layout of an underbody intelligent pneumatic kit in one embodiment of the present application;

[0044] Figure 6 This is a model diagram for predicting the target height of the pneumatic kit in the energy-saving mode in one embodiment of the present application;

[0045] Figure 7 A model diagram for predicting the target height of the pneumatic kit in a safety mode in an embodiment of the present application;

[0046] Figure 8 A flowchart of the dynamic adjustment of the height of the intelligent pneumatic kit in one embodiment of the present application;

[0047] Fig. 9 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. 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 creative work are within the scope of protection of this application.

[0049] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0050] In an exemplary embodiment, a method for optimizing the structural layout of an underbody intelligent pneumatic kit is provided. The method for optimizing the structural layout of an underbody intelligent pneumatic kit is applied to a vehicle (such as Figure 1 ), the vehicle is provided with a wind speed and wind direction sensor, a plurality of adjustable devices and a plurality of adjustable device control modules. The adjustable devices are arranged in a one-to-one correspondence with the plurality of pneumatic parts in the pneumatic kit structure. Any pneumatic part is connected to the bottom of the vehicle through the corresponding adjustable device. The adjustable device control module is arranged in a one-to-one correspondence with the adjustable device. The plurality of adjustable device structures are as follows Figure 2 and Figure 3 The adjustable device control module is used to control the extension and contraction amount of the corresponding adjustable device, thereby adjusting the height of the corresponding pneumatic part. The adjustable device control module is a rotating motor. The wind speed and wind direction sensor is used to obtain the ambient wind speed and wind direction.

[0051] like Figure 4, the structural layout optimization method of the underbody intelligent aerodynamic kit includes:

[0052] Step 101: Obtain the current vehicle speed, ambient wind speed and wind direction.

[0053] Step 102: The working mode executed by the vehicle at the current moment is obtained as the current working mode. The working mode is a safety mode or an energy-saving mode.

[0054] Step 103: Determine the pneumatic kit target height prediction model corresponding to the current working mode as the current pneumatic kit target height prediction model.

[0055] Step 104: Input the current vehicle speed, ambient wind speed and wind direction into the current aerodynamic kit target height prediction model to obtain the target layout state of the aerodynamic kit. The target layout state includes the target height of each aerodynamic component in the aerodynamic kit.

[0056] Step 105: Control multiple adjustable device control modules so that each pneumatic component in the pneumatic kit reaches the target height. Specifically: obtain the real-time height of each pneumatic component in the pneumatic kit. Based on the real-time height and target height of each pneumatic component, generate and execute adjustment instructions for each adjustable device control module until each pneumatic component in the pneumatic kit reaches the target height.

[0057] Before step 101, the method further includes:

[0058] Step 106: Acquire multiple design variable groups, including vehicle speed, crosswind speed and direction, and a height adjustment range of each pneumatic component in the pneumatic kit structure.

[0059] Step 107: Determine the full factorial experimental design matrix corresponding to each design variable group.

[0060] Step 108: Construct a vehicle aerodynamic simulation model.

[0061] Step 109: Input multiple full-factorial experimental design matrices into the vehicle aerodynamic simulation model to obtain aerodynamic simulation data corresponding to each design variable group. The aerodynamic simulation data includes aerodynamic drag and aerodynamic lift.

[0062] Step 1010: With the design variable group as input and the aerodynamic simulation data corresponding to the design variable group as output, the initial aerodynamic model is optimized to obtain the mapping relationship between the design variable group and the aerodynamic data, and the optimal design variable group corresponding to the vehicle speed, ambient wind speed and wind direction is obtained, the corresponding aerodynamic lift is minimized in the safety mode, and the corresponding aerodynamic drag is minimized in the energy-saving mode. The initial aerodynamic optimization model uses an elliptical radial basis function neural network to establish the mapping relationship between the design variable group and the aerodynamic data, and uses a multi-island genetic algorithm to perform iterative optimization of the optimal combination of the aerodynamic kit.

[0063] Step 1011: Based on the mapping relationship between the design variable group and the aerodynamic data and the optimal design variable group, the optimal design variable group in the safety mode is trained and learned. The machine learning uses a six-layer perceptron model as a regression analysis tool. With the goal of minimizing aerodynamic lift, the optimal layout of the aerodynamic kit under different vehicle speeds, ambient wind speeds and wind directions in the safety mode is determined.

[0064] Step 1012: Taking the vehicle speed, ambient wind speed and wind direction as input quantities and the optimal arrangement state of the aerodynamic kit under different wind speeds in the safety mode as output quantity, fitting is performed to obtain a prediction model of the target height of the aerodynamic kit corresponding to the safety mode.

[0065] Step 1013: Based on the mapping relationship between the design variable group and the aerodynamic data and the optimal design variable group, the optimal design variable group in the energy-saving mode is trained and learned, and the machine learning uses a six-layer perceptron model as a regression analysis tool. With the goal of minimizing aerodynamic drag, the optimal layout state of the aerodynamic kit under different vehicle speeds, ambient wind speeds and wind directions in the energy-saving mode is determined.

[0066] Step 1014: With the vehicle speed, ambient wind speed and wind direction as input quantities, and with the optimal arrangement state of the aerodynamic kit under different wind speeds in the energy-saving mode as output quantity, fitting is performed to obtain a prediction model of the target height of the aerodynamic kit corresponding to the energy-saving mode.

[0067] like Figure 5 The principle of the method for optimizing the structural arrangement of the underbody intelligent pneumatic kit shown in this embodiment is as follows:

[0068] Analyze and design the adjustable device required for the vehicle. The adjustable device includes a rotating motor, a motor box, a telescopic rod and a threaded rod. The motion relationship of the adjustable device is analyzed through the transmission relationship between the threaded rod and the telescopic rod. Design the initial height of the adjustable device according to the vehicle model, and design the installation method of the air dam and side skirts with the adjustable device.

[0069] Select appropriate design variables to design the full factorial test matrix. The design variables include vehicle speed, the position and height of different aerodynamic kits, and the wind speed and direction of the natural wind field. The design variables can be divided into adjustable variables and non-adjustable variables. The adjustable variables are variables that can be changed by the driver's operation or other methods during driving, such as the position and height of different aerodynamic kits. Non-adjustable variables are objective variables during driving, such as vehicle speed, ambient wind speed and wind direction. Aerodynamic analysis is performed on specific vehicle models, and the geometric model of the corresponding vehicle model is established. The calculation domain is established according to relevant standards, and the boundary conditions are set to establish the aerodynamic simulation model of the corresponding vehicle model. During aerodynamic simulation, the relevant parameters are adjusted according to the full factorial test design matrix, and different driving speeds, the position and height of the aerodynamic kit are set, and the ambient wind speed and wind direction during driving are obtained. Multiple sets of aerodynamic simulation data with different design variables are obtained, including aerodynamic drag and aerodynamic lift. Based on the aerodynamic simulation data, the elliptical radial basis function neural network approximation model is selected to establish the mathematical relationship between the design variables and the target response. The mapping relationship between the discretized vehicle speed, the position height of different aerodynamic kits, the ambient wind speed and wind direction obtained by aerodynamic simulation and the aerodynamic simulation data is used to establish a response surface through an approximate model, thereby extending the original discrete mapping relationship to a continuous one. If the specific values ​​of a set of design variables are known, although the aerodynamic simulation of this set of design variables has not been performed, the aerodynamic simulation data of this set of design variables in the aerodynamic simulation can be inferred through the continuous mapping relationship established by the approximate model based on the existing aerodynamic simulation, thereby obtaining the optimal value of aerodynamic lift or aerodynamic drag at a specific vehicle speed, ambient wind speed and wind direction.

[0070] Learning and training are performed based on the mapping relationship between the design variable group and aerodynamic data and the optimal design variable group. The optimal design variable group is fitted under the safety mode and energy-saving mode respectively, with the goal of minimizing aerodynamic force. The target height prediction model of the aerodynamic kit under different vehicle speeds, ambient wind speeds and wind speeds in the corresponding mode is determined.

[0071] In the actual driving process, the environmental variables during the driving process of the car, namely wind speed and wind direction, are obtained through the sensors on the car body. Combined with the current vehicle speed, the control variables such as the position and height of different pneumatic kits are optimized in real time according to the working mode selected by the user, and the relevant instructions are transmitted to each actuator through the bus to realize the dynamic adjustment of the pneumatic kit parameters during driving. The active underbody pneumatic kit is designed according to the prediction model, and the environmental variables are collected through sensors and used as the input parameters of the control system. The user selects the mode and inputs it to the controller, and the controller sends instructions to the actuator, and the actuator responds to the instructions.

[0072] Next, taking the aerodynamic parts including the air dam and the side skirts as an example, the method for optimizing the structural arrangement of the underbody intelligent aerodynamic kit shown in this embodiment is specifically described.

[0073] Step 1: Select the telescopic rod lengths d1 and d2, the threaded rod heights l1 and l2, the motor box and the rotary motor model according to the vehicle model. The device adjusts the height of the telescopic rod by controlling the transmission of the threaded rod to achieve the purpose of controlling the height of the air dam and the side skirt. Assume that the initial height of the adjustable device is h, and it is connected to the bottom and top of the vehicle's air dam and side skirt respectively through screws and studs.

[0074] Step 2: The design variables are selected as air dam height h1, side skirt height h2, vehicle speed v x , ambient wind speed v y , the ambient wind speed is perpendicular to the direction of vehicle travel, the analysis range of the air dam height h1 and the side skirt height h2 is 0-80mm, and the analysis is performed every 20mm. There are 25 groups according to the different height combinations of the air dam and the side skirt. The vehicle speed is set to 120km / h, the crosswind speed is 0-30m / s, and the calculation is performed every 2.5m / s, for a total of 13 crosswind conditions. The orthogonal experimental method is used to design the full factorial experimental design matrix of the air dam and side skirt height combination schemes under different crosswind conditions. There are 325 groups of experimental data in this case, of which the adjustable variables are the air dam height h1 and the side skirt height h2, and the non-adjustable variable is the vehicle speed v x and ambient wind speed v y ,Table 1 is the full factorial experimental design matrix under a certain vehicle speed and wind speed.

[0075] Table 1 Full factorial experimental design matrix

[0076]

[0077]

[0078] Step 3: Perform aerodynamic analysis on specific vehicle models, establish a geometric model of the corresponding vehicle model, establish a calculation domain according to relevant standards, set boundary conditions, and establish an aerodynamic simulation model of the corresponding vehicle model. During aerodynamic simulation, adjust relevant parameters according to the full factorial experimental design matrix, set different air dam heights, side skirt heights, crosswind speeds, and vehicle speeds, and obtain multiple sets of aerodynamic simulation data with different design variables.

[0079] Step 4: Select an approximate model based on the aerodynamic simulation data to establish a mathematical relationship between the design variables and the target response. In this embodiment, the air dam height h1, side skirt height h2 and vehicle speed v need to be established. x and ambient wind speed v y and aerodynamic drag F D and aerodynamic lift F L The input conditions of the approximate model are the air dam height h1, the side skirt height h2 and the vehicle speed v x and ambient wind speed v y , the output is the aerodynamic drag F on the car Dand aerodynamic lift F L , select the radial basis function neural network model to establish the mapping relationship, and use the elliptical radial basis function to construct the nonlinear mapping of the network. According to the elliptical radial basis function neural network model, the air dam height h1, side skirt height h2 and vehicle speed v can be obtained. x and ambient wind speed v y and aerodynamic drag F D and aerodynamic lift F L The mapping relationship between them is thus extended from the original discrete mapping relationship to the continuous one. The specific values ​​of a set of design variables are known. Although the set of design variables has not been simulated by aerodynamic simulation, the aerodynamic simulation data of the set of design variables in the aerodynamic simulation can be inferred through the continuous mapping relationship established by the existing aerodynamic simulation according to the approximate model.

[0080] Step 5: In this embodiment, the optimization objectives are divided into energy-saving mode and safety mode. The optimization objective of energy-saving mode is to minimize aerodynamic drag, and the optimization objective of safety mode is to minimize aerodynamic lift. The multi-island genetic algorithm is used to iterate the optimal combination of design variables in energy-saving mode and safety mode, and the optimal height combination of air dam and side skirt under different vehicle speeds and wind speeds is obtained according to the multi-island genetic optimization algorithm. There are 13 groups of optimization results for energy-saving mode and safety mode under different wind speeds.

[0081] Step 6: Establish a prediction model based on the mapping relationship between the design variable group and aerodynamic data in step 4 and the aerodynamic kit optimization plan in step 5, select the six-layer perceptron model as a regression analysis tool, predict the optimal height combination of the air dam and side skirts in the energy-saving mode and safety mode under different wind speeds and vehicle speeds, and determine the target height prediction model of the aerodynamic kit under different vehicle speeds, ambient wind speeds and wind speeds in the corresponding mode. When driving, according to the wind field data around the vehicle body sensed by the sensor, combined with the current vehicle speed, the height of the aerodynamic kit is dynamically adjusted according to the working mode requirements, and the adjustment amount is transmitted to each actuator through the bus to adjust the height of the aerodynamic kit in real time to ensure that the aerodynamic response under different vehicle speeds and wind speeds is closer to the optimization target. According to the prediction model, when the vehicle speed is 120km / h and the crosswind speed varies from 0m / s to 30m / s, the optimal air dam and side skirt combination height corresponding to the energy-saving mode under different working conditions and the optimal air dam and side skirt combination height corresponding to the safety mode are obtained to achieve the maximum reduction in aerodynamic force. Figure 6 and Figure 7 Predict results for the aerodynamic kit target height.

[0082] Step 7: Design an active underbody aerodynamic kit based on the prediction model. The wind speed sensor collects real-time data on external wind speed and direction and uses it as input parameters of the control system. The user then selects safety mode or energy-saving mode according to performance requirements. The controller calls the corresponding aerodynamic kit target height prediction model, outputs the air dam height and side skirt height in the corresponding mode, and sends adjustment instructions to the adjustable mechanism. The adjustable mechanism adjusts the height of the spiral rod by controlling the power-on time and rotation direction of the rotating motor. The threaded rod drives the telescopic rod to move to achieve control of the air dam height and side skirt height. The design framework is as follows: Figure 8 shown.

[0083] Fixed underbody aerodynamic kits will increase the aerodynamic drag and lift of the vehicle in a crosswind environment, affecting the fuel economy and handling stability of high-speed vehicles. To achieve the optimal aerodynamic effect, the layout height of the vehicle aerodynamic kit is different in different wind field environments. Traditional analysis methods are labor-intensive and inefficient, and can only simulate and optimize discrete wind field data. However, the wind field environment changes continuously during actual driving, and traditional methods cannot cover all possible operating conditions. The method proposed in the present invention performs machine learning on discrete simulation results, thereby extrapolating unsimulated operating conditions and realizing continuous optimization prediction of aerodynamic kits.

[0084] The aerodynamic kit includes different components such as side skirts, air dams, and rear wings. The layout parameters of each component have a set of optimal values ​​for a specific optimization target under a certain wind field environment. However, the existing aerodynamic kit has different components that are independently set, and the comprehensive impact of the coupling between different components on the aerodynamic force of the vehicle is not comprehensively considered. The method proposed in the present invention can comprehensively consider the coupling between different components of the aerodynamic kit, and coordinate the layout parameters of different components of the aerodynamic kit according to the wind field data during driving, so as to achieve the optimal drag reduction or safety effect.

[0085] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Fig. 9As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for optimizing the structural layout of an underbody intelligent pneumatic kit is implemented.

[0086] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0087] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0088] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0089] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0090] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0091] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0092] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0093] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for optimizing the structural layout of an underbody intelligent pneumatic kit, characterized in that: The method for optimizing the structural layout of the underbody intelligent aerodynamic kit is applied to a vehicle, wherein the vehicle is provided with a wind speed and wind direction sensor, a plurality of adjustable devices, and a plurality of adjustable device control modules; The adjustable device is arranged in one-to-one correspondence with a plurality of pneumatic parts in the pneumatic kit structure; any of the pneumatic parts is connected to the bottom of the vehicle through the corresponding adjustable device; the adjustable device control module is arranged in one-to-one correspondence with the adjustable device; The adjustable device control module is used to control the extension and retraction amount of the corresponding adjustable device, thereby adjusting the height of the corresponding pneumatic kit; The wind speed and wind direction sensor is used to obtain the wind speed and wind direction of the vehicle driving environment; The method for optimizing the structural layout of the underbody intelligent pneumatic kit comprises: Get the current ambient wind speed and direction; The working mode executed by the vehicle at the current moment is obtained as the current working mode; the working mode is a safety mode or an energy-saving mode; Determine the aerodynamic kit target height prediction model corresponding to the current working mode as the current aerodynamic kit target height prediction model; Inputting the current vehicle speed, ambient wind speed and wind direction into the current aerodynamic kit target height prediction model to obtain a target layout state of the aerodynamic kit; the target layout state includes a target height of each aerodynamic component in the aerodynamic kit; Control multiple adjustable device control modules to achieve the target height for each pneumatic component in the pneumatic kit.

2. The method for optimizing the structural layout of the underbody intelligent aerodynamic kit according to claim 1, characterized in that: The aerodynamic parts include an air dam and side skirts.

3. The method for optimizing the structural layout of the underbody intelligent aerodynamic kit according to claim 1, characterized in that: The adjustable device control module is a rotating motor.

4. The method for optimizing the structural layout of the underbody intelligent aerodynamic kit according to claim 1, characterized in that: Before obtaining the current ambient wind speed and direction, it also includes: Acquire a plurality of design variable groups; the design variable groups include vehicle speed, ambient wind speed and wind direction, and a height range of each pneumatic component in the pneumatic kit structure; Determine the full factorial experimental design matrix corresponding to each design variable group; Construct vehicle aerodynamic simulation model; Inputting multiple full-factor experimental design matrices into the vehicle aerodynamic simulation model respectively to obtain aerodynamic simulation data corresponding to each design variable group; the aerodynamic simulation data includes aerodynamic drag and aerodynamic lift; With the design variable group as input and the aerodynamic simulation data corresponding to the design variable group as output, the initial aerodynamic model is trained and optimized to obtain the design variable group-aerodynamic data mapping relationship and the optimal design variable group; the initial aerodynamic model uses an elliptical radial basis function neural network to establish the design variable group-aerodynamic data mapping relationship, and uses a multi-island genetic algorithm to iterate the optimal combination of the aerodynamic kit.

5. The method for optimizing the structural layout of the underbody intelligent aerodynamic kit according to claim 4, characterized in that: Before obtaining the current ambient wind speed and direction, it also includes: The optimal design variable group and the mapping relationship between the design variable group and aerodynamic data in the safety mode are learned and trained. The six-layer perceptron model is used as a regression analysis tool to minimize the aerodynamic lift and determine the optimal layout of the aerodynamic kit under different vehicle speeds, ambient wind speeds and wind directions in the safety mode. The vehicle speed, ambient wind speed and wind direction are taken as input, and the optimal layout state of the aerodynamic kit under different vehicle speeds, ambient wind speeds and wind directions in safety mode is fitted as output to obtain the aerodynamic kit target height prediction model corresponding to the safety mode.

6. The method for optimizing the structural layout of the underbody intelligent aerodynamic kit according to claim 4, characterized in that: Before obtaining the current ambient wind speed and direction, it also includes: The optimal design variable group and the mapping relationship between the design variable group and aerodynamic data in the energy-saving mode are learned and trained. The six-layer perceptron model is used as a regression analysis tool to minimize aerodynamic drag and determine the optimal layout of the aerodynamic kit under different vehicle speeds, ambient wind speeds and wind directions in the energy-saving mode. The vehicle speed, ambient wind speed and wind direction are taken as input, and the optimal layout state of the aerodynamic kit under different vehicle speeds, ambient wind speeds and wind directions in energy-saving mode is fitted as output to obtain the aerodynamic kit target height prediction model corresponding to the energy-saving mode.

7. The method for optimizing the structural layout of the underbody intelligent aerodynamic kit according to claim 1, characterized in that: Control multiple adjustable device control modules to make each pneumatic part in the pneumatic kit reach the target height, including: Get the real-time height of each pneumatic component in the pneumatic kit; Based on the real-time height and target height of each pneumatic component, an adjustment instruction of each adjustable device control module is generated and executed until each pneumatic component in the pneumatic kit reaches the target height.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for optimizing the structural layout of the underbody intelligent aerodynamic kit according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for optimizing the structural layout of the underbody intelligent aerodynamic kit according to any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for optimizing the structural layout of the underbody intelligent aerodynamic kit according to any one of claims 1 to 7 is implemented.

Images