Active vortex drag reduction method, system, and vehicle

Abstract

The application discloses an active vortex drag reduction method, system and vehicle. The method comprises the following steps: acquiring flow field state data collected by a sensor arranged on the vehicle; determining a control target of the vehicle under a current working condition according to a preset working condition category; processing the flow field state data by using a neural network model to obtain control parameters of an active vortex generator according to the control target, the active vortex generator adopts a piezoelectric and micro-pore array composite driving mode, and the neural network model is a model that has learned a nonlinear mapping relationship between the flow field state data and the control parameters of the active vortex generator in a training stage; and determining a control instruction according to the control parameters to control a piezoelectric driver of the active vortex generator. The application solves the technical problem that in the related art, a simple threshold control strategy based on vehicle speed is often used for the active aerodynamic components of the vehicle, fine adjustment cannot be performed according to real-time flow field states, and the drag reduction effect is limited.

Description

Technical Field

[0001] This application relates to the field of vehicle control, and more specifically, to an active eddy current drag reduction method, system, and vehicle. Background Technology

[0002] Automotive aerodynamic drag reduction technology has evolved from passive drag reduction to active control. Passive drag reduction technology mainly includes streamlined body design, optimization of frontal area, and the use of electronic rearview mirrors. As the technological boundaries approach, the space for passive optimization is gradually narrowing, and active airflow control technology has become a new development direction. Active airflow control technology achieves more refined drag reduction effect by dynamically adjusting the interaction between the vehicle and the airflow. The active aerodynamic technologies that have been applied in related technologies include: (1) Active air intake grille (AGS): By adjusting the grille opening, the airflow entering the engine compartment can be controlled, which can reduce the drag coefficient by about 30 points and save fuel by 0.15-0.2L / 100km; (2) Active rear wing / spoiler: Automatically adjusts the angle according to the vehicle speed, providing downforce at high speeds and reducing drag at low speeds; (3) Active diffuser: Adjusts the airflow under the vehicle and improves the rear flow field; (4) Active suspension adjustment: Reduces the frontal area by lowering the vehicle height. However, most active aerodynamic components for automobiles in related technologies adopt simple threshold control strategies based on vehicle speed, which cannot be finely adjusted according to the real-time flow field conditions, resulting in limited drag reduction effects.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides an active eddy current drag reduction method, system, and vehicle to at least solve the technical problem in the related art that active aerodynamic components for automobiles mostly adopt simple threshold control strategies based on vehicle speed, which cannot be finely adjusted according to the real-time flow field state, resulting in limited drag reduction effect.

[0005] According to one aspect of the embodiments of this application, an active eddy current drag reduction method is provided, comprising: acquiring flow field state data collected by sensors installed on a vehicle, wherein the flow field state data is used to represent the flow field state on the vehicle body surface; determining a control target for the vehicle under the current operating condition based on a preset operating condition category; processing the flow field state data using a neural network model based on the control target to obtain control parameters for an active eddy current generator, wherein the active eddy current generator adopts a piezoelectric and micro-hole array composite driving method, and the active eddy current generator is installed at a position on the vehicle body for controlling the flow field, and the neural network model is a model that has learned the nonlinear mapping relationship between the flow field state data and the control parameters of the active eddy current generator during the training phase; and determining a control command based on the control parameters to control the piezoelectric actuator of the active eddy current generator.

[0006] Optionally, the sensor locations include: a front bumper area for detecting the incoming flow state, a rear edge area of ​​the A-pillar for inferring the starting position of airflow separation, a C-pillar area for capturing airflow separation behavior and near-wall flow field evolution, a roof area for detecting the boundary layer state, and a wheel arch area for detecting wheel turbulence.

[0007] Optionally, based on a preset operating condition category, the control objective of the vehicle under the current operating condition is determined, including: acquiring the vehicle status and driving mode, wherein the vehicle status includes vehicle speed, acceleration and steering angle, and the driving mode includes one of the following: economy mode, comfort mode and sport mode; determining the vehicle's operating condition feature vector based on the vehicle status and driving mode; matching the operating condition feature vector with the preset operating condition category to obtain the vehicle's current operating condition, and determining the vehicle's control objective under the current operating condition.

[0008] Optionally, the control command includes at least one of the following: front-rear coordinated control, left-right coordinated control, and timing coordinated control. The front-rear coordinated control includes the coordinated control of the front active vortex generator and the rear active vortex generator, wherein the front active vortex generator is used to control the front wheel turbulence, and the rear active vortex generator is used to control the wake region. The left-right coordinated control includes the coordinated control of the left active vortex generator and the right active vortex generator, and the left active vortex generator and the right active vortex generator are activated by asymmetric control parameters. The timing coordinated control is used to indicate that multiple active vortex generators are triggered according to a specific timing sequence.

[0009] Optionally, determining control commands based on control parameters to control the piezoelectric actuator of the active eddy current generator includes: acquiring a feedforward control quantity of the piezoelectric actuator, wherein the feedforward control quantity represents an estimated value of the physical driving quantity required to achieve the control parameters; acquiring the actual output parameters of the piezoelectric actuator; comparing the actual output parameters and control parameters to obtain error parameters, and determining correction parameters for error correction after performing multidimensional operations on the error parameters; determining control commands based on the correction parameters and the feedforward control quantity, and controlling the piezoelectric actuator based on the control commands.

[0010] Optionally, the active eddy current generator includes: a micro-pore array panel, a piezoelectric drive cavity, a resonant cavity, and a flow regulating valve. The micro-pore array panel is located on the inner surface of the active eddy current generator and faces the outer surface of the vehicle. The piezoelectric drive cavity is connected to the micro-pore array panel and is used to generate periodic deformation under alternating voltage drive, driving the gas in the piezoelectric drive cavity through the micro-pore array panel to form a pulse jet. The resonant cavity is located between the micro-pore array panel and the piezoelectric drive cavity and is used to make the gas in the piezoelectric drive cavity resonate at a specific frequency to enhance the jet intensity of the pulse jet. The flow regulating valve is disposed between the gas source interface and the resonant cavity and is used to regulate the gas flow rate input from the gas source interface.

[0011] Optionally, the active vortex generator may be installed in at least one of the following locations: C-pillar, wheel arch, or rear of the vehicle, and the thickness of the active vortex generator may be less than 10 mm.

[0012] According to another aspect of the embodiments of this application, an active eddy current drag reduction system is also provided, including: a sensing layer module, a decision layer module, and an execution layer module. The sensing layer module is used to acquire flow field state data collected by sensors installed on the vehicle, wherein the flow field state data represents the flow field state on the vehicle body surface. The decision layer module is used to determine the control target of the vehicle under the current operating condition based on a preset operating condition category. Based on the control target, a neural network model is used to process the flow field state data to obtain the control parameters of the active eddy current generator. The active eddy current generator adopts a piezoelectric and micro-hole array composite driving method, and the active eddy current generator is installed at a position on the vehicle body used to control the flow field. The neural network model is a model that has learned the nonlinear mapping relationship between the flow field state data and the control parameters of the active eddy current generator during the training phase. The execution layer module is used to determine control commands based on the control parameters to control the piezoelectric actuator of the active eddy current generator.

[0013] According to another aspect of the embodiments of this application, a vehicle is also provided, including: a memory for storing program instructions; and a processor connected to the memory for executing program instructions to perform the following functions: acquiring flow field state data collected by sensors installed on the vehicle, wherein the flow field state data is used to represent the flow field state on the vehicle body surface; determining the control target of the vehicle under the current working condition according to a preset working condition category; processing the flow field state data using a neural network model according to the control target to obtain control parameters of an active eddy current generator, wherein the active eddy current generator adopts a piezoelectric and micropore array composite driving method, and the active eddy current generator is installed at a position on the vehicle body for controlling the flow field, and the neural network model is a model that has learned the nonlinear mapping relationship between the flow field state data and the control parameters of the active eddy current generator during the training phase; and determining control instructions based on the control parameters to control the piezoelectric actuator of the active eddy current generator.

[0014] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored computer program, wherein the device containing the non-volatile storage medium executes the above-described active eddy current drag reduction method by running the computer program.

[0015] In this embodiment, flow field state data collected by sensors mounted on the vehicle is acquired, whereby the flow field state data represents the flow field state on the vehicle body surface. Based on a preset operating condition category, a control target for the vehicle under the current operating condition is determined. According to the control target, a neural network model is used to process the flow field state data to obtain control parameters for an active vortex generator. The active vortex generator employs a piezoelectric and micro-pore array composite drive method and is mounted on the vehicle body at a location used to control the flow field. The neural network model is a model that has learned the nonlinear mapping relationship between the flow field state data and the control parameters of the active vortex generator during the training phase. Based on the control parameters, control commands are determined to control the piezoelectric actuator of the active vortex generator, achieving the goal of multi-point coordinated intervention of the flow field on the vehicle body surface. This realizes the technical effect of adaptive active drag reduction and stable control based on flow field perception, thereby solving the technical problem in related technologies where active aerodynamic components for automobiles often adopt simple threshold control strategies based on vehicle speed, which cannot be finely adjusted according to the real-time flow field state, resulting in limited drag reduction effects. Attached Figure Description

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

[0017] Figure 1 This is a hardware structure block diagram of a computer terminal for implementing an active eddy current drag reduction method according to an embodiment of this application.

[0018] Figure 2 This is a flowchart of an active eddy current drag reduction method according to an embodiment of this application;

[0019] Figure 3 This is a cross-sectional view of an active eddy current generator according to an embodiment of this application;

[0020] Figure 4 This is a schematic diagram showing the arrangement of an active eddy current generator according to an embodiment of this application;

[0021] Figure 5 This is a flowchart of a control algorithm according to an embodiment of this application;

[0022] Figure 6 This is a comparison image of a vehicle before and after adjustment, corresponding to an example of an embodiment of this application;

[0023] Figure 7 This is a comparison image of a vehicle before and after adjustment, corresponding to Example 2 of an embodiment of this application;

[0024] Figure 8 This is a schematic diagram of an active eddy current drag reduction system according to an embodiment of this application;

[0025] Figure 9 This is a schematic diagram of the overall architecture of an active eddy current drag reduction system according to an embodiment of this application. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] The active aerodynamics technology used in related technologies has the following problems:

[0029] (1) Insufficient control precision: Most existing active aerodynamic components adopt a simple threshold control strategy based on vehicle speed, which cannot be finely adjusted according to the real-time flow field state, resulting in limited drag reduction effect. For example, the active aerodynamic system of some models mainly adjusts according to vehicle speed, lacking the ability to perceive and respond to local flow field characteristics in real time;

[0030] (2) Poor system coordination: Each active aerodynamic component works independently, lacking unified and coordinated control. Components such as active grilles, active tail wings, and active diffusers operate independently, failing to form an optimal airflow control strategy at the system level, and may even interfere with each other;

[0031] (3) Slow response speed: The response time of existing mechanical actuators (such as motor-driven and hydraulic-driven actuators) is usually more than 100 milliseconds, which is difficult to adapt to rapidly changing driving conditions. For example, the response time of the active rear wing system of a certain car model is 500 milliseconds, which cannot meet the requirements of transient flow field control;

[0032] (4) Energy consumption and noise issues: Although active blowing / inhalation drag reduction technologies (such as synthetic jet and pulse jet) have significant drag reduction effects, they have problems such as high energy consumption and high noise, which limits their application in mass-produced vehicles. Studies have shown that the noise generated by traditional synthetic jet exciters can reach more than 80dB;

[0033] (5) Poor environmental adaptability: Active aerodynamic systems in related technologies lack the ability to perceive and adapt to external environments (such as crosswinds, rain and snow, and road conditions), resulting in poor control performance under complex working conditions.

[0034] To address the aforementioned problems, this application provides an active eddy current drag reduction method, which can be applied to... Figure 1 The computer terminal shown is explained below.

[0035] The active eddy current drag reduction method embodiments provided in this application can be executed in mobile terminals, computer terminals or similar computing devices. Figure 1 A hardware block diagram of a computer terminal for implementing an active eddy current drag reduction method is shown. Figure 1 As shown, the computer terminal 10 may include one or more processors (shown as 102a, 102b, ..., 102n in the figure) (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission module 106 for communication functions connected via wired and / or wireless networks. In addition, it may also include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, and a BUS bus. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0036] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0037] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the active eddy current drag reduction method in this embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the above-mentioned active eddy current drag reduction method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0038] The transmission module 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission module 106 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission module 106 may be a radio frequency (RF) module, used for wireless communication with the Internet.

[0039] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0040] It should be noted here that, in some optional embodiments, the above... Figure 1 The computer terminal shown may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that... Figure 1 This is only one instance of a specific particular instance, and is intended to illustrate the types of components that may exist in the aforementioned computer terminal.

[0041] In the above operating environment, this application provides an embodiment of an active eddy current drag reduction method. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than that shown here.

[0042] Figure 2 This is a flowchart of an active eddy current drag reduction method according to an embodiment of this application, such as... Figure 2 As shown, the method includes the following steps:

[0043] Step S202: Obtain flow field state data collected by sensors installed on the vehicle, wherein the flow field state data is used to represent the flow field state on the vehicle body surface.

[0044] In step S202 above, the sensor type may include, for example, a miniature pressure sensor, a shear stress sensor, and an optical flow velocity sensor, used to collect the physical parameters of the airflow on the vehicle surface in real time, i.e., the aforementioned flow field state data. The flow field state data may include, but is not limited to, key flow field characteristics such as local static pressure distribution, airflow tangential velocity gradient, vortex intensity, and separation point location. By collecting the flow field state data, the transient evolution process of the airflow on the vehicle surface can be obtained, such as whether airflow separation is about to occur in the C-pillar area, whether strong vortex structures are formed in the wheel arch turbulence, and whether the boundary layer on the roof tends towards turbulence.

[0045] Step S204: Determine the control target of the vehicle under the current working condition based on the preset working condition category.

[0046] In step S204 above, the system automatically matches the vehicle to one of several predefined typical operating condition categories based on the vehicle's comprehensive operating status information, such as vehicle speed, longitudinal acceleration, steering angle, crosswind intensity, environmental signals such as rain or snow, and the driving mode selected by the driver (such as economy, comfort, sport). Each operating condition category corresponds to a control objective. For example, when cruising at high speed without crosswinds, the system determines it as a "high-speed drag reduction priority" condition, where the primary control objective is to minimize the drag coefficient. When encountering strong crosswinds, the system classifies it as a "crosswind stability priority" condition, and the control objective shifts to suppressing vehicle yaw and improving lateral stability.

[0047] Step S206: Based on the control objective, the flow field state data is processed using a neural network model to obtain the control parameters of the active vortex generator. The active vortex generator adopts a piezoelectric and micro-hole array composite drive method and is set at the position on the vehicle body used to control the flow field. The neural network model is a model that has learned the nonlinear mapping relationship between the flow field state data and the control parameters of the active vortex generator during the training phase.

[0048] In step S206 above, based on the determined control objective, the system takes the real-time collected flow field state data of the vehicle surface as input and feeds it into the pre-trained neural network model. This model is not a physical model derived from traditional fluid dynamics equations, but rather learns end-to-end through massive wind tunnel test data and high-precision CFD simulation data to autonomously discover the implicit nonlinear relationship between complex flow field characteristics and optimal control parameters.

[0049] During the training phase, the neural network model has learned various flow field states (such as the offset of the C-pillar separation point, the fluctuation of the vortex frequency in the wake region, and the enhancement of the turbulence intensity of the wheel cover) and the corresponding optimal combination of piezoelectric driving parameters (i.e. the control parameters mentioned above). The control parameters include jet frequency, intensity coefficient, phase difference, etc., and a mapping relationship between these two types of data has been established.

[0050] When the vehicle is running, the neural network model receives real-time flow field data, identifies abnormal airflow trends, and directly outputs a set of specific control parameters for each active vortex generator. For example, the C-pillar vortex generator operates at 48Hz, intensity 0.65, and phase lag of 15° behind the front wheels, while the left wheel arch enhances the jet intensity to 0.8 to counteract crosswind disturbances. Furthermore, because the active vortex generator employs a piezoelectric and microporous array composite drive structure, it has a fast response speed and precise control, accurately executing microsecond-level dynamic commands output by the neural network model. This enables active intervention in the flow field of key areas of the vehicle body, including delayed separation, suppression of vortex shedding, and optimization of pressure distribution.

[0051] Step S208: Determine control commands based on control parameters to control the piezoelectric actuator of the active eddy current generator.

[0052] In step S208 above, based on the control parameters output by the neural network model, the system further generates executable control commands to directly drive the piezoelectric actuator in the active eddy current generator. The control parameters represent abstract aerodynamic control targets, and the control commands are used to convert these parameters into specific numerical values ​​of electrical signals that the piezoelectric ceramic can respond to. For example, "frequency 50Hz, intensity 0.7" is converted into "applying an alternating square wave voltage with an amplitude of ±95V, a frequency of 50Hz, and a duty cycle of 42%, and activating the resonant drive mode." This conversion process is based on the calibration characteristic curves of the piezoelectric actuator under different operating conditions, combined with the acoustic response characteristics of the resonant cavity and the aerodynamic efficiency model of the micro-hole array, to achieve the conversion of control commands.

[0053] In some embodiments of this application, control commands can be generated, for example, by a high-speed embedded controller, amplified by a power amplifier circuit, and applied to both ends of the piezoelectric ceramic stack with microsecond precision, driving it to produce periodic deformation, thereby pushing the gas in the piezoelectric drive cavity through the micro-hole array to form a high-frequency, controllable pulse jet. Simultaneously, the system also synchronously adjusts the gas flow rate of each micro-hole group according to the opening setting of the flow regulating valve, ensuring that the spatially distributed control parameters are realized. The entire control command generation and issuance process is completed at the execution layer with a 0.1 millisecond cycle, ensuring that the response of the piezoelectric actuator and the decision-making of the neural network model are synchronized.

[0054] Through steps S202 to S208, the goal of multi-point coordinated intervention on the flow field of the vehicle body surface is achieved, thereby realizing the technical effect of adaptive active drag reduction and stability control based on flow field perception. This solves the technical problem in related technologies where active aerodynamic components for automobiles often adopt simple threshold control strategies based on vehicle speed, which cannot be finely adjusted according to the real-time flow field state, resulting in limited drag reduction effects. The following is a further explanation.

[0055] In the above-mentioned active eddy current drag reduction method, the sensor placement locations include: the front bumper area for detecting the incoming flow state, the rear edge area of ​​the A-pillar for inferring the starting position of airflow separation, the C-pillar area for capturing airflow separation behavior and near-wall flow field evolution, the roof area for detecting the boundary layer state, and the wheel arch area for detecting wheel turbulence.

[0056] In some embodiments of this application, sensors are arranged in the front bumper area, primarily to capture the characteristics of free-flowing air before it is disturbed by the vehicle body, including parameters such as flow velocity, static pressure, and turbulence intensity. Sensors are placed in the rear edge area of ​​the A-pillar to indirectly infer the precise starting point of airflow detaching from the vehicle body surface by monitoring typical pre-separation warning signals such as sudden drops in surface pressure, shear stress approaching zero, and abnormal changes in velocity gradient, thereby providing early warning of separation risks. Sensors are arranged in the C-pillar area to focus on capturing airflow changes due to geometrical abrupt changes and intensified adverse pressure gradients at this location. Significant separation behavior occurs, and sensors simultaneously record turbulent fluctuations, reattachment trends, and lateral flow evolution in the near-wall region, providing relevant data for wake prediction. Sensors in the roof region are used to continuously monitor the boundary layer development process, including its thickness growth, transition point location, and transition state from laminar to turbulent flow. In the wheel arch region, sensors are used to directly sense complex turbulence characteristics caused by high-speed rotating wheels, such as tire wake vortex intensity, ground-based flow interference, and unsteady aerodynamic phenomena like low-pressure fluctuations within the wheel arch. These turbulences not only significantly increase drag but may also interfere with rear airflow stability. Sensors deployed at key locations on the vehicle body can have sampling frequencies, for example, 1000 Hz, to capture transient changes in the flow field.

[0057] In step S204 above, the control target of the vehicle under the current operating condition is determined according to the preset operating condition category, including: acquiring the vehicle status and driving mode, wherein the vehicle status includes vehicle speed, acceleration and steering angle, and the driving mode includes one of the following: economy mode, comfort mode and sport mode; determining the vehicle's operating condition feature vector according to the vehicle status and driving mode; matching the operating condition feature vector with the preset operating condition category to obtain the vehicle's current operating condition, and determining the control target of the vehicle under the current operating condition.

[0058] In some embodiments of this application, before determining the control objective of the vehicle under the current operating condition, it is necessary to first determine the vehicle state and driving mode. The vehicle state includes, but is not limited to, current speed, longitudinal acceleration, and steering angle. These three parameters reflect the vehicle's macroscopic motion trend, power change trend, and trajectory intention, respectively. The driving mode includes Eco mode, Comfort mode, or Sport mode, used to determine the user's preference for energy consumption, ride smoothness, or handling response. Based on the parameters of the vehicle state and driving mode, the vehicle's operating condition feature vector is determined. The current operating condition of the vehicle is then determined based on the matching relationship between the operating condition feature vector and a preset operating condition category. For example, when the vehicle speed is 120 km / h, acceleration is close to zero, steering angle is less than 3°, and the driving mode is Eco mode, according to the preset operating condition category, the operating condition feature vector is parsed as a "high-speed constant speed cruise + energy saving priority" scenario. Therefore, the current operating condition of the vehicle is "high-speed drag reduction priority," and the corresponding control objective under this condition is to minimize the drag coefficient. If the current operating condition is "enhanced crosswind stability," the corresponding control objective is to suppress vehicle yaw and balance the aerodynamic torques on both sides. This process does not rely on external cloud computing; it is entirely completed by the onboard edge controller within milliseconds, ensuring a high degree of synchronization between control decisions and driving behavior.

[0059] In the above-mentioned active eddy current drag reduction method, the control command includes at least one of the following: front-rear coordinated control, left-right coordinated control, and timing coordinated control. The front-rear coordinated control includes the coordinated control of the front active eddy current generator and the rear active eddy current generator, wherein the front active eddy current generator is used to control the front wheel turbulence, and the rear active eddy current generator is used to control the wake region. The left-right coordinated control includes the coordinated control of the left active eddy current generator and the right active eddy current generator, and the left and right active eddy current generators are activated by asymmetric control parameters. The timing coordinated control is used to indicate that multiple active eddy current generators are triggered according to a specific timing sequence.

[0060] In some embodiments of this application, the control commands incorporate a multi-dimensional collaborative control strategy, achieving three-dimensional active intervention in complex flow fields through precise spatial and temporal coordination. Specifically, front-rear collaborative control refers to the system simultaneously regulating active vortex generators located at the front (e.g., front wheel arches, lower front bumper) and rear (e.g., C-pillar, rear window, rear diffuser area) of the vehicle, creating aerodynamic linkage between the two: the front active vortex generator suppresses the strong turbulence and vortex nucleus generation caused by front wheel rotation through directional jets, reducing its interference with the airflow on the vehicle's sidewalls and chassis; the rear active vortex generator actively injects energy into the wake separation zone, reshaping the separation streamline shape, compressing the wake width, and increasing the static pressure at the rear. The synergistic effect of these two generators forms a continuous flow field guide chain from the front to the rear of the vehicle, effectively blocking the rearward transmission of turbulence energy and significantly reducing pressure drag.

[0061] Left-right coordinated control is an asymmetric control mechanism designed for crosswind, yaw, or cornering conditions. The system determines the direction of wind pressure source based on crosswind sensors or steering angle information and applies differentiated control parameters to the vortex generators on the left and right sides of the vehicle. For example, when the wind comes from the left, the intensity of the left jet is enhanced to counteract the lateral aerodynamic torque, while the right jet is moderately weakened to avoid excessive intervention that could cause the vehicle to deviate in the opposite direction. Thus, active yaw suppression and enhanced driving stability at the aerodynamic level are achieved without relying on the mechanical stability system.

[0062] Timing-coordinated control optimizes the action rhythm of multiple generators from a time dimension, causing multiple vortex generators to be triggered sequentially according to a preset time delay sequence. For example, vortex pulses from column A to column C are excited step by step at 10ms intervals, causing the generated vortex rings to induce each other, merge and evolve stably downstream. This not only enhances the continuity and control efficiency of the vortex structure, but also suppresses the periodic shedding of large-scale wake vortices, reducing drag fluctuations and wind noise.

[0063] The three collaborative control strategies described above are dynamically combined and cross-called based on real-time operating conditions to jointly control the active eddy current generator. It should be noted that the control commands not only include the aforementioned control strategies but may also include specific numerical values ​​that convert control parameters into electrical signals that the piezoelectric ceramic can respond to, based on these strategies.

[0064] In step S208 above, determining the control command based on the control parameters to control the piezoelectric actuator of the active eddy current generator includes: obtaining the feedforward control quantity of the piezoelectric actuator, wherein the feedforward control quantity is used to represent the estimated value of the physical driving quantity required to achieve the control parameters; obtaining the actual output parameters of the piezoelectric actuator; comparing the actual output parameters and the control parameters to obtain the error parameters, and determining the correction parameters used to correct the error after performing multi-dimensional operations on the error parameters; determining the control command based on the correction parameters and the feedforward control quantity, and controlling the piezoelectric actuator based on the control command.

[0065] In some embodiments of this application, the physical driving quantity necessary to achieve the control parameters, i.e., the feedforward control quantity, is estimated through a preset physical model (such as a piezoelectric-micro-orifice pneumatic mapping model). This feedforward control quantity represents the voltage amplitude, frequency, and waveform morphology applied to the piezoelectric ceramic stack to achieve the target jet characteristics under ideal operating conditions. It is a priori prediction of the system based on physical characteristics and historical calibration data. In addition, the system collects the actual output parameters of the piezoelectric actuator in real time, including the actual displacement amplitude, cavity pressure fluctuation frequency, micro-orifice outlet jet velocity, or momentum coefficient indirectly inferred from the pressure sensor. These actual output parameters truly reflect the actual response capability of the piezoelectric actuator under non-ideal conditions such as current temperature, aging, and gas supply pressure fluctuations.

[0066] The actual output parameters are compared with the control parameters to calculate error parameters, such as the actual frequency deviating from the target value by 2Hz or the jet intensity being 15% lower than expected. Real-time dynamic calculations are performed on errors across multiple dimensions, employing adaptive PID or online learning compensation algorithms. Combining historical error trends with system dynamic characteristics, precise correction parameters are generated, representing the actual compensation amount. The specific numerical value of the electrical signal representing the piezoelectric ceramic's responsiveness is obtained from the feedforward control quantity and correction parameters, for example, by weighted summation, thus ensuring control accuracy.

[0067] In the above-mentioned active eddy current drag reduction method, the active eddy current generator includes: a micro-orifice array panel, a piezoelectric drive cavity, a resonant cavity, and a flow regulating valve. The micro-orifice array panel is located on the inner surface of the active eddy current generator and faces the outer surface of the vehicle. The piezoelectric drive cavity is connected to the micro-orifice array panel and is used to generate periodic deformation under alternating voltage drive, driving the gas in the piezoelectric drive cavity to pass through the micro-orifice array panel to form a pulse jet. The resonant cavity is located between the micro-orifice array panel and the piezoelectric drive cavity and is used to make the gas in the piezoelectric drive cavity resonate at a specific frequency to enhance the jet intensity of the pulse jet. The flow regulating valve is connected to the gas source interface and is used to regulate the gas flow rate input from the gas source interface.

[0068] In the above-mentioned active eddy current drag reduction method, the active eddy current generator is installed in at least one of the following locations: C-pillar, wheel arch, or rear of vehicle, and the thickness of the active eddy current generator is less than 10mm.

[0069] In some embodiments of this application, the active eddy current generator adopts an integrated structure, which is composed of four core functional components that work together to achieve efficient, low-noise, and fast-response active flow field control. Figure 3This is a cross-sectional view of an active vortex generator according to an embodiment of this application. The micropore array panel is located on the outermost side of the active vortex generator, closely attached to the inner surface of the vehicle body panel, and facing the external airflow environment. The micropore array panel is a silicon-based micropore array manufactured using MEMS technology, with pore diameters of 50-200 micrometers and pore spacing of 0.5-2 mm. The pore diameter distribution can be flexibly designed according to control requirements to form a uniform and dense gas jet interface. It is the only outlet for airflow from the internal drive mechanism into the external flow field, and its geometric distribution directly determines the spatial coverage and disturbance morphology of the jet. The surface of the micropore array panel is coated with a hydrophobic and oleophobic nano-coating to prevent dust from clogging the micropores.

[0070] The piezoelectric drive cavity is directly connected to the microporous array panel, for example, via a connecting component. The piezoelectric drive cavity is filled with compressible gas and encapsulated with a multilayer piezoelectric ceramic stack structure (i.e., a piezoelectric actuator). When an alternating voltage is applied, the piezoelectric ceramic generates high-frequency micro-displacement deformation, causing the gas inside the cavity to periodically compress and expand, thereby creating pulsating gas pressure inside the cavity. This pressure propels the gas inside the cavity to be ejected outward through the microporous array panel, forming a series of pulse jets with clear timing and intensity, achieving energy injection and momentum exchange at the boundary layer. The piezoelectric ceramic uses PZT-5H material, the drive voltage is ±100V, and the operating frequency is adjustable from 10-1000Hz.

[0071] The resonant cavity located between the piezoelectric drive chamber and the micro-pore array panel employs a Helmholtz resonance structure design, and its inherent resonant frequency matches the piezoelectric drive frequency. By optimizing the cavity geometry, the airflow resonates at a specific frequency, enhancing the jet intensity. For example, when the pulsating airflow generated by the piezoelectric drive chamber enters the resonant cavity, the gas undergoes acoustic resonance within the cavity, significantly amplifying the pressure fluctuation amplitude. This, without increasing the drive voltage, greatly enhances the momentum flux and jet velocity at the jet outlet, achieving efficient energy amplification and focusing.

[0072] A flow control valve is positioned between the gas source interface and the resonant cavity to regulate the gas flow rate input from the gas source interface. The valve is manufactured using microelectromechanical systems (MEMS) technology, with a response time of less than 1 millisecond.

[0073] The four components in the active vortex generator form a complete closed loop through energy conversion, resonant amplification, flow distribution and precise injection. Specifically, the piezoelectric drive cavity provides the power source, the resonant cavity improves efficiency, the flow regulating valve regulates the gas flow, and the micro-pore array panel completes the final aerodynamic intervention.

[0074] The placement of the active vortex generator has undergone systematic aerodynamic optimization, focusing on key areas on the vehicle surface where airflow is most prone to separation, turbulence enhancement, or wake expansion, including typical high-drag sensitive areas such as the C-pillar, wheel arches, and rear of the vehicle. In some embodiments of this application, a schematic diagram of the placement of the active vortex generator is shown below. Figure 4 As shown, the active vortex generator includes a rear active vortex generator, a right C-pillar active vortex generator, and a right rear wheel arch active vortex generator. In the C-pillar area, the active vortex generator is longitudinally arranged along the rear edge of the side window to actively intervene in boundary layer separation caused by abrupt changes in body curvature and adverse pressure gradients. By injecting high-momentum jets, it delays the rearward movement of the separation point and significantly reduces the width of the wake region. In the wheel arch area, the active vortex generator is installed close to the inner wall of the wheel arch to locally intervene in the strong vortices caused by the high-speed rotating wheel, ground flow interference, and low-pressure areas in the wheel cavity. This effectively suppresses the intensity of the tire wake vortex and balances the aerodynamic forces on the left and right sides, reducing induced drag and wind noise. At the rear of the vehicle, the active vortex generator is laterally distributed along the lower edge of the rear window or the edge of the trunk lid to reconstruct the separation streamline shape of the rear of the vehicle, causing the separation area to be concave inward, increasing the static pressure at the rear of the vehicle, and thus significantly reducing differential drag.

[0075] The entire active vortex generator has a flat structure with no moving mechanical parts and a thickness of less than 10 mm. It can be seamlessly embedded inside the body panels, meeting aerodynamic shape requirements without affecting the appearance. It achieves the engineering goals of millisecond-level response, low energy consumption, and low noise.

[0076] The technical mechanisms involved in the control process of an active eddy current generator include:

[0077] (1) Boundary layer energy injection mechanism: High-energy fluid is injected into the boundary layer through the micro-pore array panel to enhance the boundary layer's ability to resist adverse pressure gradient and delay airflow separation. The pulse jet of the piezoelectric driven cavity can form a series of vortex rings at the micro-pore outlet. These vortex rings mix with the boundary layer as they move downstream, entraining the mainstream high-momentum fluid into the boundary layer, thereby energizing the boundary layer;

[0078] (2) Wake region pressure recovery mechanism: A vortex generator is placed near the tail separation line. By blowing air, the shape of the separation streamline is changed, causing the separation streamline to be concave towards the inside of the wake, reducing the width of the wake region, increasing the static pressure at the tail, and thus reducing pressure drag. Studies have shown that by optimizing the blowing position and intensity, the static pressure coefficient at the tail can be increased from -0.2 to -0.05, corresponding to a drag reduction of about 10%.

[0079] (3) Vortex interaction mechanism: By controlling the phase relationship of multiple active vortex generators, the generated vortices interact in the flow field to form large-scale vortex structures that are beneficial to drag reduction. For example, by using an anti-phase drive strategy, symmetrical vortex pairs can be formed in the wake region to suppress the shedding of large-scale vortices and reduce drag fluctuations;

[0080] (4) Intelligent optimization mechanism: The neural network model establishes a nonlinear mapping relationship between the flow field state and control parameters by learning from a large amount of CFD simulation and wind tunnel test data. Compared with traditional physical model-based control methods, intelligent control can discover optimization strategies that are difficult for humans to perceive, and achieve better control effects.

[0081] Figure 5 This is a flowchart of a control algorithm according to an embodiment of this application, such as... Figure 5 As shown, the process includes the following:

[0082] 1. Based on vehicle status (such as vehicle speed, acceleration, steering angle) and driving mode (economy / comfort / sport), determine the control objective under the current operating condition (drag reduction priority / stability enhancement priority / noise reduction priority). The execution cycle of this step can be, for example, 100 milliseconds.

[0083] 2. Based on the flow field state data collected by sensors, a deep reinforcement learning algorithm (such as Proximal Policy Optimization, PPO) is used to calculate the control parameters (jet frequency, intensity, and phase) of each active vortex generator in real time within a neural network model architecture. The input to the neural network model is the flow field state data, and the output is a vector corresponding to the control parameters. The execution cycle of this step can be, for example, 10 milliseconds.

[0084] 3. A PID+feedforward composite control algorithm is employed to accurately track the control parameters output by the neural network model. The piezoelectric actuator uses a resonant drive mode, operating near the resonant frequency to achieve maximum output efficiency. The execution cycle of this step can be, for example, 0.1 milliseconds. A cooperative control strategy can be used to control the piezoelectric actuator, including: front-rear cooperative control, where the front active vortex generator controls the front wheel turbulence, and the rear active vortex generator controls the wake region, with both working together to form a complete flow field control chain; left-right cooperative control, where, under crosswind conditions, the left and right active vortex generators employ an asymmetric control strategy to counteract the crosswind effect; and timing cooperative control, where multiple active vortex generators are triggered according to a specific timing sequence to create a traveling wave effect, enhancing the control effect. The control commands for controlling the piezoelectric actuator are determined based on the cooperative control strategy.

[0085] Combining the above control algorithm, the active eddy current drag reduction method provided in this application has the following beneficial effects:

[0086] (1) Significant drag reduction effect: By actively intervening in the flow field of key areas of the vehicle body (C-pillar, rear window, wheel arches, etc.) through the array in the active vortex generator, the airflow separation can be delayed, the area of ​​the wake zone can be reduced, and the drag coefficient can be reduced by 8%-15%. For models with a drag coefficient of 0.20, it can be reduced to 0.17-0.18.

[0087] (2) Improved driving range: For pure electric vehicles, the driving range can be increased by about 3%-5% for every 0.01 reduction in drag coefficient. The embodiments of this application can reduce the drag coefficient by 0.02-0.03, corresponding to a 6%-15% increase in driving range, which can increase the driving range by 36-90km for a 600km driving range model;

[0088] (3) Reduced energy consumption: Compared with traditional synthetic jet technology, the embodiment of this application adopts a piezoelectric-micropore array composite driving method, which reduces energy consumption by about 60% and controls noise below 60dB, meeting the NVH requirements of mass-produced vehicles;

[0089] (4) Fast response speed: The response time of the piezoelectric actuator can reach 5-10 milliseconds, which is 1-2 orders of magnitude faster than the traditional motor drive (more than 100 milliseconds), and can realize real-time control of transient flow field;

[0090] (5) Multi-objective collaborative optimization: The system can simultaneously achieve multiple objectives such as drag reduction, noise reduction, and stability enhancement. By reducing turbulence disturbance through eddy current control, wind noise can be reduced by 2-3 dB; by controlling the wake morphology, high-speed driving stability can be improved;

[0091] (6) High level of intelligence: The system has self-learning ability and can continuously optimize control strategies according to driving habits and road conditions.

[0092] The following explanation uses specific scenarios and examples:

[0093] Example 1: High-speed cruise drag reduction mode, application scenario: the vehicle is traveling at a constant speed of 120km / h on the highway.

[0094] In Example 1, the vehicle's current operating condition is determined to be "drag reduction priority" based on a preset operating condition category. The control parameters output by the neural network model are: C-pillar vortex generator jet frequency 50Hz, intensity coefficient 0.6; rear window vortex generator jet frequency 30Hz, intensity coefficient 0.4; and a phase difference of 180 degrees between the two. During the precise tracking of control parameters, fine-tuning can be performed based on feedback from pressure sensors. The expected effect is a 12% reduction in drag coefficient, corresponding to an approximately 8% reduction in energy consumption per 100 kilometers. A comparison of the vehicle's airflow before and after adjustment is provided. Figure 6 As shown.

[0095] Example 2: Crosswind stability enhancement mode, application scenario: a vehicle is traveling at 100km / h and encounters a crosswind (wind speed 15m / s).

[0096] In Example 2, the control strategy is as follows: the crosswind sensor detects crosswinds coming from the left; based on the preset operating condition category, the vehicle's current operating condition is determined to be "stability enhancement priority"; the neural network model outputs asymmetrical control parameters: the intensity coefficient of the left vortex generator is 0.8, and the intensity coefficient of the right vortex generator is 0.3, producing an effect that counteracts the crosswind aerodynamic torque. The control parameters are adjusted in a closed loop by real-time detection of the vehicle's yaw rate. The expected results are: a 30% reduction in crosswind sensitivity, a reduction in peak yaw rate of approximately 35%, and improved driving safety. The diagrams before and after adjustment illustrate the side airflow, yaw torque, and vehicle yaw rate. Figure 7 As shown.

[0097] Figure 8 This is a schematic diagram of an active eddy current drag reduction system according to an embodiment of this application, as shown below. Figure 8 As shown, the active eddy current drag reduction system 60 includes: a sensing layer module 62, a decision layer module 64, and an execution layer module 66. The sensing layer module acquires flow field state data collected by sensors mounted on the vehicle, which represents the flow field state on the vehicle's surface. The decision layer module determines the vehicle's control objective under the current operating condition based on a preset operating condition category. Based on the control objective, a neural network model processes the flow field state data to obtain the control parameters of the active eddy current generator. The active eddy current generator employs a piezoelectric and micro-pore array composite drive method and is mounted on the vehicle body at a location used to control the flow field. The neural network model is a model that has learned the nonlinear mapping relationship between the flow field state data and the control parameters of the active eddy current generator during the training phase. The execution layer module determines control commands based on the control parameters to control the piezoelectric actuator of the active eddy current generator.

[0098] The following combination Figure 9 The various modules of the above-described active eddy current drag reduction system will be explained. Figure 9 This is a schematic diagram of the overall architecture of an active eddy current drag reduction system according to an embodiment of this application, as shown below. Figure 9 As shown, vehicle status monitoring is achieved through feedback information from the perception layer module, decision layer module, and execution layer module.

[0099] Specifically, the perception layer module can be, for example, a distributed flow field sensor network, including different types of sensors such as miniature pressure sensors, shear stress sensors, and optical flow velocity sensors. These sensors can be distributed in areas such as the front bumper (incoming flow state), A-pillar (separation point location), roof (boundary layer state), C-pillar / rear window (wake region), and wheel arches (wheel turbulence) to collect the physical parameters of the airflow on the vehicle surface in real time, i.e., the aforementioned flow field state data. The sensors have a sampling frequency of 1000Hz, which can capture transient changes in the flow field.

[0100] The decision-making layer module can be an intelligent collaborative control unit, such as a processor, employing an edge computing architecture and incorporating a deep learning inference engine. The intelligent collaborative control unit receives data collected from the perception layer module, performs data preprocessing, and uses a pre-trained neural network model (such as a deep learning inference engine) to predict optimal control parameters in real time, implementing the optimal control strategy and coordinating the actions of the execution layer module with the control coordinator. Furthermore, the decision-making layer module can perform health monitoring and fault diagnosis via a communication interface (CAN / FlexRay). The control cycle can be, for example, 10 milliseconds, meeting real-time requirements.

[0101] The execution layer module can, for example, consist of an array of active vortex generators (multiple active vortex generators) forming the actuator. These active vortex generators are positioned on the vehicle body where the flow field needs to be controlled, such as C-pillar vortex generator arrays, rear window vortex generator arrays, roof vortex generator arrays, wheel arch vortex generator arrays, and front bumper vortex generator arrays. Each active vortex generator can be independently controlled, actively intervening in the local flow field through methods such as blowing / inhaling / synthetic jets. The active vortex generators employ piezoelectric-micropore array composite drive technology, resulting in fast response, low energy consumption, and low noise. The actuator's response time can, for example, be 5-10 ms.

[0102] Through the perception layer module 62, decision layer module 64 and execution layer module 66 in the above-mentioned active eddy current drag reduction system, the purpose of multi-point coordinated intervention of the flow field on the vehicle surface is achieved, thereby realizing the technical effect of adaptive active drag reduction and stable control based on flow field perception. This solves the technical problem in related technologies where active aerodynamic components for automobiles mostly adopt simple threshold control strategies based on vehicle speed, which cannot be finely adjusted according to the real-time flow field state, resulting in limited drag reduction effect.

[0103] In the aforementioned active eddy current drag reduction system, the sensor locations include: the front bumper area for detecting the incoming flow state, the rear edge area of ​​the A-pillar for inferring the starting position of airflow separation, the C-pillar area for capturing airflow separation behavior and near-wall flow field evolution, the roof area for detecting the boundary layer state, and the wheel arch area for detecting wheel turbulence.

[0104] In the aforementioned decision-making module, the control objective of the vehicle under the current operating condition is determined based on the preset operating condition category. This includes: acquiring the vehicle's status and driving mode, where the vehicle status includes vehicle speed, acceleration, and steering angle, and the driving mode includes one of the following: economy mode, comfort mode, and sport mode; determining the vehicle's operating condition feature vector based on the vehicle status and driving mode; matching the operating condition feature vector with the preset operating condition category to obtain the vehicle's current operating condition, and determining the vehicle's control objective under the current operating condition.

[0105] In the aforementioned active eddy current drag reduction system, the control commands include at least one of the following: front-rear coordinated control, left-right coordinated control, and timing coordinated control. The front-rear coordinated control includes the coordinated control of the front active eddy current generator and the rear active eddy current generator, wherein the front active eddy current generator is used to control the front wheel turbulence, and the rear active eddy current generator is used to control the wake region. The left-right coordinated control includes the coordinated control of the left active eddy current generator and the right active eddy current generator, and the left and right active eddy current generators are activated by asymmetric control parameters. The timing coordinated control is used to indicate that multiple active eddy current generators are triggered according to a specific timing sequence.

[0106] In the aforementioned execution layer module, the control command is determined based on the control parameters to control the piezoelectric actuator of the active eddy current generator. This includes: acquiring the feedforward control quantity of the piezoelectric actuator, wherein the feedforward control quantity is used to represent an estimated value of the physical driving quantity required to achieve the control parameters; acquiring the actual output parameters of the piezoelectric actuator; comparing the actual output parameters and the control parameters to obtain error parameters, and performing multi-dimensional operations on the error parameters to determine correction parameters used to correct the error; determining the control command based on the correction parameters and the feedforward control quantity, and controlling the piezoelectric actuator based on the control command.

[0107] In the aforementioned active eddy current drag reduction system, the active eddy current generator includes: a micro-aperture array panel, a piezoelectric drive cavity, a resonant cavity, and a flow regulating valve. The micro-aperture array panel is located on the inner surface of the active eddy current generator and faces the outer surface of the vehicle. The piezoelectric drive cavity is connected to the micro-aperture array panel and is used to generate periodic deformation under alternating voltage drive, driving the gas in the piezoelectric drive cavity to pass through the micro-aperture array panel to form a pulse jet. The resonant cavity is located between the micro-aperture array panel and the piezoelectric drive cavity and is used to make the gas in the piezoelectric drive cavity resonate at a specific frequency to enhance the jet intensity of the pulse jet. The flow regulating valve is connected to the micro-aperture array panel and is used to regulate the gas flow distribution through the micro-aperture array panel.

[0108] In the above-mentioned active eddy current drag reduction system, the active eddy current generator is installed in at least one of the following locations: C-pillar, wheel arch, or rear of the vehicle, and the thickness of the active eddy current generator is less than 10 mm.

[0109] The typical range of key design parameters in the embodiments of this application is as follows: (1) Micropore array: pore diameter 80-150 micrometers, pore spacing 1-1.5mm, opening rate 10%-20%; (2) Piezoelectric drive: drive voltage ±80V-±120V, working frequency 20-500Hz, displacement amplitude 5-20 micrometers; (3) Jet intensity: jet velocity 5-30m / s, momentum coefficient 0.001-0.01; (4) Sensor: pressure sensor accuracy ±10Pa, sampling frequency 1000Hz.

[0110] In some embodiments of this application, alternatives to the active eddy current controller include: plasma exciter: which uses plasma to induce airflow, requires no mechanical moving parts, has a faster response speed, but consumes more energy; magnetohydrodynamic drive: which uses a magnetic field to control a conductive fluid, suitable for special working conditions; shape memory alloy drive: which uses the thermal deformation of SMA to generate drive, has a simple structure but a slower response.

[0111] Alternatives to the control algorithms in the embodiments of this application include: Model Predictive Control (MPC): based on a physical model for predictive optimization, which is highly interpretable but requires precise modeling; Adaptive PID Control: a traditional control method that is simple to implement but has limited optimization effect; Genetic Algorithm Optimization: offline optimization of control parameters, suitable for static operating conditions.

[0112] Alternative sensors to those described in this application include: fiber optic pressure sensors, which have strong anti-electromagnetic interference capabilities and are suitable for electric vehicle environments; hot-film flow velocity sensors, which can measure the magnitude and direction of flow velocity, providing richer information; and computer vision-based flow field measurement, which is non-contact measurement but has poor real-time performance.

[0113] It should be noted that, Figure 8 The active eddy current drag reduction system shown is used to perform Figure 2 The active eddy current drag reduction method shown above is also applicable to this active eddy current drag reduction system, and will not be repeated here.

[0114] This application embodiment also provides a vehicle, which includes a memory and a processor. The memory stores program instructions, and the processor is connected to the memory to execute program instructions that perform the following functions: acquiring flow field state data collected by sensors installed on the vehicle, wherein the flow field state data represents the flow field state on the vehicle body surface; determining the control target of the vehicle under the current operating condition based on a preset operating condition category; processing the flow field state data using a neural network model based on the control target to obtain control parameters of an active eddy current generator, wherein the active eddy current generator adopts a piezoelectric and micropore array composite driving method, and the active eddy current generator is installed at a position on the vehicle body for controlling the flow field; the neural network model is a model that has learned the nonlinear mapping relationship between the flow field state data and the control parameters of the active eddy current generator during the training phase; and determining control instructions based on the control parameters to control the piezoelectric actuator of the active eddy current generator.

[0115] It should be noted that the above-mentioned vehicles are used for execution Figure 2 The active eddy current drag reduction method shown above also applies to this vehicle, and will not be repeated here.

[0116] This application embodiment also provides a non-volatile storage medium, which includes a stored computer program. The device containing the non-volatile storage medium executes the following active eddy current drag reduction method by running the computer program: acquiring flow field state data collected by sensors installed on the vehicle, wherein the flow field state data represents the flow field state on the vehicle body surface; determining the control target of the vehicle under the current operating condition based on a preset operating condition category; processing the flow field state data using a neural network model based on the control target to obtain control parameters for an active eddy current generator, wherein the active eddy current generator employs a piezoelectric and micro-pore array composite drive method, and the active eddy current generator is installed at a location on the vehicle body used to control the flow field; the neural network model is a model that has learned the nonlinear mapping relationship between the flow field state data and the control parameters of the active eddy current generator during the training phase; and determining control commands based on the control parameters to control the piezoelectric actuator of the active eddy current generator.

[0117] It should be noted that the aforementioned non-volatile storage media is used for execution. Figure 2 The active eddy current drag reduction method shown above also applies to this non-volatile storage medium, and will not be repeated here.

[0118] This application also provides a computer program product, including computer instructions that, when executed by a processor, implement the steps of the active eddy current drag reduction method in various embodiments of this application.

[0119] This application also provides a computer program that, when executed by a processor, implements the steps of the active eddy current drag reduction method in various embodiments of this application.

[0120] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0121] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0122] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0123] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0124] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0125] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0126] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. An active eddy current drag reduction method, characterized in that, include: Acquire flow field state data collected by sensors installed on the vehicle, wherein the flow field state data is used to represent the flow field state on the vehicle body surface; Based on the preset operating condition category, determine the control target of the vehicle under the current operating condition; Based on the control objective, a neural network model is used to process the flow field state data to obtain the control parameters of the active vortex generator. The active vortex generator adopts a piezoelectric and micro-pore array composite drive method and is installed on the vehicle body at the position used to control the flow field. The neural network model is a model that has learned the nonlinear mapping relationship between the flow field state data and the control parameters of the active vortex generator during the training phase. Based on the control parameters, control commands are determined to control the piezoelectric actuator of the active eddy current generator.

2. The method according to claim 1, characterized in that, The sensor locations include: the front bumper area for detecting the incoming flow state, the rear edge area of ​​the A-pillar for inferring the starting position of airflow separation, the C-pillar area for capturing airflow separation behavior and near-wall flow field evolution, the roof area for detecting the boundary layer state, and the wheel arch area for detecting wheel turbulence.

3. The method according to claim 1, characterized in that, Based on preset operating condition categories, the control objective of the vehicle under the current operating condition is determined, including: The vehicle status and driving mode of the vehicle are obtained, wherein the vehicle status includes vehicle speed, acceleration and steering angle, and the driving mode includes one of the following: economy mode, comfort mode and sport mode; Based on the vehicle status and the driving mode, determine the vehicle's operating condition feature vector; The operating condition feature vector is matched with the preset operating condition category to obtain the current operating condition of the vehicle, and the control target of the vehicle under the current operating condition is determined.

4. The method according to claim 1, characterized in that, The control commands include at least one of the following: front-back coordinated control, left-right coordinated control, and timing coordinated control. The front and rear coordinated control includes the coordinated control of the front active vortex generator and the rear active vortex generator, wherein the front active vortex generator is used to control the front wheel turbulence, and the rear active vortex generator is used to control the wake region. The left-right coordinated control includes the coordinated control of the left active eddy current generator and the right active eddy current generator, which are activated by asymmetric control parameters. The timing coordination control is used to indicate that multiple active eddy current generators are triggered according to a specific timing sequence.

5. The method according to claim 1, characterized in that, Determining control commands based on the control parameters to control the piezoelectric actuator of the active eddy current generator includes: Obtain the feedforward control quantity of the piezoelectric actuator, wherein the feedforward control quantity is used to represent an estimated value of the physical drive quantity required to achieve the control parameters; Obtain the actual output parameters of the piezoelectric actuator; The actual output parameters and the control parameters are compared to obtain the error parameters. After performing multidimensional operations on the error parameters, the correction parameters used to correct the error are determined. The control command is determined based on the correction parameters and the feedforward control quantity, and the piezoelectric actuator is controlled according to the control command.

6. The method according to claim 1, characterized in that, The active eddy current generator includes: a microporous array panel, a piezoelectric driving cavity, a resonant cavity, and a flow regulating valve, wherein... The microporous array panel is located on the inner surface of the active eddy current generator and faces the outer surface of the vehicle; The piezoelectric drive cavity is connected to the microporous array panel and is used to generate periodic deformation under alternating voltage drive, thereby driving the gas in the piezoelectric drive cavity to pass through the microporous array panel to form a pulse jet; The resonant cavity is located between the micro-hole array panel and the piezoelectric driving cavity, and is used to make the gas in the piezoelectric driving cavity resonate at a specific frequency to enhance the jet intensity of the pulse jet; The flow regulating valve is located between the gas source interface and the resonant cavity, and is used to regulate the gas flow rate input from the gas source interface.

7. The method according to claim 6, characterized in that, The active vortex generator is located at least one of the following positions: C-pillar, wheel arch, or rear of the vehicle, and the thickness of the active vortex generator is less than 10 mm.

8. An active eddy current drag reduction system, characterized in that, include: The module consists of a perception layer, a decision-making layer, and an execution layer. The perception layer module is used to acquire flow field state data collected by sensors installed on the vehicle, wherein the flow field state data is used to represent the flow field state on the vehicle body surface. The decision layer module is used to determine the control target of the vehicle under the current working condition based on the preset working condition category; based on the control target, the flow field state data is processed by a neural network model to obtain the control parameters of the active vortex generator. The active vortex generator adopts a piezoelectric and micro-pore array composite driving method, and the active vortex generator is set at the position on the vehicle body for controlling the flow field. The neural network model is a model that has learned the nonlinear mapping relationship between the flow field state data and the control parameters of the active vortex generator during the training phase. The execution layer module is used to determine control commands based on the control parameters to control the piezoelectric actuator of the active eddy current generator.

9. A vehicle, characterized in that, include: Memory, used to store program instructions; A processor, connected to the memory, is configured to execute program instructions to perform the following functions: acquiring flow field state data collected by sensors mounted on the vehicle, wherein the flow field state data represents the flow field state on the vehicle body surface; determining the control target of the vehicle under the current operating condition based on a preset operating condition category; processing the flow field state data using a neural network model based on the control target to obtain control parameters for an active vortex generator, wherein the active vortex generator employs a piezoelectric and micropore array composite drive method, and the active vortex generator is mounted on the vehicle body at a location used to control the flow field; the neural network model is a model that has learned the nonlinear mapping relationship between the flow field state data and the control parameters of the active vortex generator during the training phase; and determining control commands based on the control parameters to control the piezoelectric actuator of the active vortex generator.

10. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored computer program, wherein the device containing the non-volatile storage medium executes the active eddy current drag reduction method according to any one of claims 1 to 7 by running the computer program.

Images