Wind vibration active control system based on data driving and vehicle

Abstract

The invention provides a wind vibration active control system based on data driving and a vehicle, and the system comprises a vehicle engine cabin system which comprises a switch assembly with a wind vibration active control function; the signal acquisition system is used for acquiring the running speed and initial rear window opening data of the vehicle and acquiring a user window adjusting instruction after the wind vibration active control function is started; the vehicle window execution system is used for adjusting the opening degree of a vehicle window according to the target front window opening data and the window opening signal output by the controller; and the controller is used for outputting target front window opening data in combined linkage with the initial rear window opening data to the vehicle window execution system according to the running vehicle speed and the initial rear window opening data, and outputting a window opening signal according to the user window adjusting instruction and a vehicle window opening threshold value. According to the embodiment of the invention, on the premise of eliminating the wind vibration noise of the vehicle, the personalized needs of the user are considered, and the technical problem that the vehicle cannot actively control the wind vibration in the related technology is solved.

Description

Technical Field

[0001] The present invention relates to the field of NVH (Noise, Vibration, Harshness) technology, and in particular to a data-driven active wind-induced vibration control system and a vehicle. Background Art

[0002] With the continuous development and progress of the automotive industry, vehicle ride comfort has become one of the most important performance indicators. A vehicle's NVH performance significantly impacts the passenger experience, and good NVH performance can significantly increase consumer purchasing interest. With improved sound insulation, interior noise is lower when the windows are closed while driving, leading to fewer complaints. However, wind noise and buffeting caused by opening the windows have gradually become a focus of attention, with wind buffeting currently being a major user complaint. Wind buffeting noise is the aeroacoustic response of the air inside the vehicle to transient external airflow. It is caused by the self-excited oscillations of the free shear layer, which generate pressure pulsations inside the vehicle and Helmholtz resonance with the interior cavity. This produces a strong sense of pressure on the ears, significantly causing discomfort to passengers. Wind buffeting noise can be divided into sunroof buffeting and side window buffeting, the latter of which includes front and rear window buffeting. Currently, sunroof and front window buffeting can be controlled by installing spoilers, rearview mirrors, or A-pillars with added spoiler features. However, rear window spoilers affect the appearance and are not practical, making rear window buffeting a significant pain point in the industry.

[0003] Data development in related technologies requires extensive preliminary testing to obtain data on the sound pressure levels of wind buffeting noise generated by vehicle windows at varying window openings and speed. This data is inconsistent across different vehicle models, consuming significant development time and cost. Furthermore, existing wind buffeting control methods use only sound pressure level as a control target, which fails to fully and accurately reflect the human ear's subjective perception of wind buffeting noise. Summary of the Invention

[0004] The present invention provides a data-driven wind-induced vibration active control system and a vehicle to solve technical problems in related technologies.

[0005] According to one embodiment of the present invention, a data-driven active wind vibration control system is provided, comprising: a vehicle cabin system, comprising a switch assembly for an active wind vibration control function; a signal acquisition system for acquiring the vehicle's driving speed and initial rear window opening data, and acquiring user window adjustment instructions after the active wind vibration control function is enabled; a window execution system for adjusting the window opening according to target front window opening data and a window opening signal output by a controller; a controller communicatively connected to the vehicle cabin system, the signal acquisition system, and the window execution system, for outputting target front window opening data combined with the initial rear window opening data to the window execution system according to the driving speed and the initial rear window opening data, and outputting a window opening signal according to the user window adjustment instruction and the window opening threshold.

[0006] Optionally, the signal acquisition system is also used to: obtain the initial window position of the vehicle, wherein the initial window position includes at least one of the following: the left rear window and the right rear window; obtain the initial window opening of the vehicle; obtain the window thickness of the vehicle or the opening thickness of the window glass, wherein the initial rear window opening data includes: the initial window position and the initial window opening.

[0007] Optionally, the data-driven active wind vibration control system also includes: a voice broadcast module, which is communicatively connected to the controller, and is used to obtain a voice prompt signal according to the switch state of the switch component, and play the voice prompt signal, wherein the voice prompt signal is used to indicate whether the current vehicle has turned on the active wind vibration control function.

[0008] Optionally, the controller is also used to: determine whether the vehicle cabin system has turned on the active wind vibration control function; if the vehicle cabin system has turned on the active wind vibration control function, determine whether the vehicle has started the wind vibration removal mode; if the vehicle has started the wind vibration removal mode, determine the target front window opening data that is linked to the initial rear window opening data and output to the window execution system based on the driving speed and the initial rear window opening data.

[0009] Optionally, the signal acquisition system is also used to: collect the in-vehicle noise signal of the vehicle's in-vehicle microphone and the rainfall data of the rain sensor; the controller determines whether the vehicle has started the wind vibration removal mode, including: calculating the first wind vibration noise pleasantness inside the vehicle based on the in-vehicle noise signal, wherein the first wind vibration noise pleasantness is used to characterize the subjective tolerance of the passengers in the vehicle to the wind vibration noise; based on the rainfall data, the first wind vibration noise pleasantness, the driving speed, and the initial rear window opening data, determining whether the vehicle has started the wind vibration removal mode.

[0010] Optionally, the controller calculates the first wind-vibration noise pleasantness inside the vehicle based on the in-vehicle noise signal, including: parsing the noise sound quality parameters in the in-vehicle noise signal, wherein the noise sound quality parameters include sound pressure level, roughness, loudness, and sharpness; and using the following formula to calculate the first wind-vibration noise pleasantness PD inside the vehicle: PD = x1 / SPL + x2 / R + x3 / L + x4 / S, wherein SPL represents sound pressure level, R represents roughness, L represents loudness, S represents sharpness, and x1, x2, x3, and x4 represent weight coefficients of sound pressure level, roughness, loudness, and sharpness, respectively.

[0011] Optionally, the controller determines whether the vehicle has turned on the wind vibration removal mode based on the rainfall data, the first wind vibration noise pleasantness, the driving speed, and the initial rear window opening data, including: if the rainfall data is less than the rainfall threshold, the first wind vibration noise pleasantness is less than the pleasantness threshold, the driving speed is greater than the speed threshold, and the initial rear window opening data is greater than the window opening threshold, it is determined that the vehicle has turned on the wind vibration removal mode.

[0012] Optionally, the controller outputs target front window opening data combined with the initial rear window opening data to the window execution system based on the driving speed and the initial rear window opening data, including: retrieving a pre-trained wind vibration active control large model; inputting the driving speed and the initial rear window opening data into the wind vibration active control large model, and outputting the target front window opening data of the vehicle, wherein the target front window opening data includes a first target window position and a window opening degree thereof, and the wind vibration active control large model is used to output optimal window opening data with the highest wind vibration noise pleasantness under the premise of maintaining the driving speed and the initial rear window opening data, and the wind vibration noise pleasantness is used to characterize the subjective tolerance of passengers in the vehicle to wind vibration noise.

[0013] Optionally, the controller is also used to: after the window execution system completes adjusting the window opening based on the target front window opening data, detect a user window adjustment instruction of the window adjustment control, wherein the user window adjustment instruction is used to indicate the window position, adjustment direction, and desired opening of the user-adjusted window; and output a window opening signal according to the user window adjustment instruction and the window opening threshold.

[0014] Optionally, after the large model for active wind vibration control outputs the front window opening data with the optimal wind vibration noise pleasantness at the target noise reduction position at the current vehicle speed and the initial rear window opening data, the controller outputs a window opening signal according to the user window adjustment instruction and the window opening threshold, including: if the user window adjustment instruction includes a front window lowering request, outputting a first window opening signal, wherein the first window opening signal is used to instruct the window to be adjusted to the desired opening corresponding to the user window adjustment instruction; if the user window adjustment instruction includes a front window raising request, determining whether the rear window opening is less than the window opening threshold; if the rear window opening is less than the window opening threshold, outputting a second window opening signal, wherein the second window opening signal is used to instruct the window to be adjusted to the desired opening corresponding to the user window adjustment instruction; if the rear window opening is greater than or equal to the window opening threshold, outputting a third window opening signal, wherein the third window opening signal is used to instruct the rear window to be raised to a first opening, the first opening being greater than the first rear window opening threshold and less than the second rear window opening threshold, and the first rear window opening threshold being the opening value when wind vibration occurs on the rear window. The second rear window opening threshold is the opening value when the pleasantness of the wind vibration noise caused by the rear window wind vibration is equal to the pleasantness threshold. If the user window adjustment command includes a rear window up request or a rear window down request, it is determined whether the user window adjustment command also includes a front window up request. If the user window adjustment command does not include a front window up request, a fourth window opening signal is output, wherein the fourth window opening signal is used to instruct the vehicle window to be adjusted to the desired opening corresponding to the user window adjustment command. If the user window adjustment command includes a front window up request, it is determined whether the rear window opening is less than the window opening threshold. If the rear window opening is less than the window opening threshold, a fifth window opening signal is output, wherein the fifth window opening signal is used to instruct the vehicle window to be adjusted to the desired opening corresponding to the user window adjustment command. If the rear window opening is greater than or equal to the window opening threshold, a sixth window opening signal is output, wherein the sixth window opening signal is used to instruct the front window to be lowered to the front window opening threshold. The front window opening threshold is the front window opening data value with the highest wind vibration noise pleasantness output by the large wind vibration active control model based on the current vehicle speed and window opening data.

[0015] Optionally, the user window adjustment instruction includes: a manual window adjustment instruction sensed by a window opener, or a voice window adjustment instruction received by the vehicle computer.

[0016] According to another embodiment of the present invention, a vehicle is provided, comprising the data-driven active wind-induced vibration control system described in the above embodiment.

[0017] An embodiment of the present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the steps in the above method.

[0018] Beneficial effects of the present invention:

[0019] 1. Users can optimize the vehicle's window opening conditions through user window adjustment commands, and output the optimal window opening signal based on the user window adjustment commands, taking into account the user's personalized needs while eliminating vehicle wind vibration noise;

[0020] 2. The window position and window opening can be predicted using a neural network model to achieve optimal wind vibration control. Furthermore, the large-scale active wind vibration control model can be autonomously optimized based on actual vehicle wind vibration data, eliminating the need for extensive and repetitive wind vibration control testing, thus saving development time and costs.

[0021] 3. The data-driven active wind vibration control system can effectively solve the wind vibration problem of the car window, and the frequency amplitude and sound pressure level of the wind vibration problem can be reduced by more than 20dB. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0023] Figure 1 is a schematic diagram of a data-driven wind-induced vibration active control system according to an embodiment of the present invention;

[0024] Figure 2 This is a structural diagram of an active wind-induced vibration control system according to an embodiment of the present invention;

[0025] Figure 3 This is an optimization flow chart of a large wind vibration control model based on feedback control in an embodiment of the present invention;

[0026] Figure 4 Execution flow chart of data-driven wind-induced vibration active control system;

[0027] Figure 5 1 is a spectrum diagram before and after the wind-induced vibration active control system is started in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order 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 in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of this application. It should be noted that, in the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Example 1

[0031] In this embodiment, a data-driven wind-induced vibration active control system is provided. Figure 1 is a schematic diagram of a data-driven wind-induced vibration active control system according to an embodiment of the present invention, such as Figure 1 As shown, the system includes:

[0032] The vehicle cockpit system 10 includes a switch assembly for the wind vibration active control function;

[0033] Optionally, the switch component may be a software switch / virtual switch or a physical button.

[0034] The signal acquisition system 12 is used to collect vehicle speed and initial rear window opening data, as well as user window adjustment instructions after the wind buffeting active control function is enabled;

[0035] Optionally, the user window adjustment instruction includes: a manual window adjustment instruction sensed by a window opener, or a voice window adjustment instruction received by the vehicle computer.

[0036] The vehicle window execution system 14 is used to adjust the opening of the vehicle window according to the target front window opening data and the window opening signal output by the controller;

[0037] a controller 16, communicatively connected to the vehicle cockpit system, the signal acquisition system, and the window actuation system, configured to output target front window opening data combined with the initial rear window opening data to the window actuation system based on the vehicle speed and the initial rear window opening data, and to output a window opening signal based on the user window adjustment command and the window opening threshold;

[0038] The target front window opening data is automatically generated by the controller 16 based on parameters such as the driving speed and the initial rear window opening data. The user window adjustment instruction is a window opening instruction directly input by the user after the vehicle completes window adjustment based on the target front window opening data.

[0039] Through the above system, the vehicle cockpit system includes a switch component of the wind vibration active control function; a signal acquisition system for collecting the vehicle's driving speed and initial rear window opening data, as well as collecting the user's window adjustment instructions after the wind vibration active control function is enabled; a window execution system for adjusting the window opening according to the target front window opening data and the window opening signal output by the controller; a controller is communicatively connected with the vehicle cockpit system, the signal acquisition system, and the window execution system, and is used to output the initial rear window opening signal to the window execution system according to the driving speed and the initial rear window opening data. The window opening data is combined with the target front window opening data of the vehicle window opening data, and the window opening signal is output according to the user window adjustment instruction and the vehicle window opening threshold, so as to realize the active control of the wind vibration when the window is opened, thereby automatically reducing the wind vibration noise inside the vehicle caused by the wind entering the window. The user can optimize the window opening situation of the vehicle through the user window adjustment instruction, and output the optimal window opening signal based on the user window adjustment instruction. It takes into account the personalized needs of the user while eliminating the vehicle wind vibration noise, solves the technical problem that the vehicle cannot actively control the wind vibration in the related technology, can eliminate or weaken the wind vibration phenomenon of the vehicle, and improve user comfort.

[0040] In an example of this embodiment, the data-driven active wind vibration control system also includes: a voice broadcast module, which is communicated with the controller, and is used to obtain a voice prompt signal according to the switch state of the switch component, and play the voice prompt signal, wherein the voice prompt signal is used to indicate whether the current vehicle has turned on the active wind vibration control function.

[0041] The vehicle cockpit system of this embodiment is used to implement the software switch, voice prompt function, and text prompt function of the wind vibration active control function. The wind vibration active control function switch is set in the vehicle software control interface of the vehicle cockpit system, and the user can control the activation and deactivation of the wind vibration active control function through this switch. When the user clicks on the switch, the wind vibration active control function is turned on, and at the same time, the vehicle pops up a text message "After the wind vibration function is turned on, the front window glass will be opened in conjunction with the occurrence of wind vibration conditions to relieve ear pressure". The corresponding voice prompt signal is transmitted to the voice broadcast module through the controller, and the controller drives the vehicle-mounted speaker of the voice broadcast module to play a voice reminder "After the wind vibration function is turned on, the front window glass will be opened in conjunction with the occurrence of wind vibration conditions to relieve ear pressure", prompting the user that the wind vibration active control function is currently turned on. When the user clicks the switch again, the active wind vibration control function is turned off, and a text message pops up on the car interface: "Wind vibration may occur after the active wind vibration control function is turned off, and there may be a noticeable pressure on the ears." At the same time, the controller drives the car speakers to play a voice reminder, "You have turned off the wind vibration removal mode, and there may be a noticeable pressure on the ears," to remind the user that the active wind vibration control function is currently turned off.

[0042] Figure 2This is a schematic diagram of the structure of the wind-induced vibration active control system in an embodiment of the present invention, comprising a vehicle cockpit system, a controller, a signal acquisition system, a window execution system, and a voice broadcast module. The vehicle cockpit system primarily includes the software switch and voice prompt function of the wind-induced vibration active control system. The signal acquisition system is primarily responsible for receiving information on vehicle speed, window position, and window opening. It is also responsible for collecting in-vehicle noise signals using an onboard microphone. The controller is primarily responsible for processing information such as vehicle speed and window opening output by the signal acquisition system, and using an integrated large model to output the optimal window position and window opening information under wind-induced vibration conditions to the window execution system. The window execution system is responsible for adjusting the corresponding window opening, and the voice broadcast module plays voice prompt information.

[0043] In one implementation of this embodiment, the signal acquisition system is also used to: obtain the initial window position of the vehicle, wherein the initial window position includes at least one of the following: the left rear window and the right rear window; obtain the initial window opening degree of the vehicle; wherein the initial rear window opening data includes: the initial window position and the initial window opening degree.

[0044] The signal acquisition system includes vehicle speed sensor, margin sensor, window opening sensor, etc. When the vehicle cabin system turns on the active wind vibration control function, the signal acquisition system collects signals and transmits them to the controller. The body domain controller (BDC) in the controller reads the vehicle speed v information through the on-board CAN bus. At the same time, the BDC also reads the rainfall f information from the rain sensor through the on-board LIN line, and reads the window opening p (percentage) and window position M information from the window motor controller. After the above information is collected in the signal acquisition system, it will be output to the controller for processing.

[0045] In an implementation scenario of this embodiment, the controller is also used to: determine whether the vehicle cabin system has turned on the active wind vibration control function; if the vehicle cabin system has turned on the active wind vibration control function, determine whether the vehicle has started the wind vibration removal mode; if the vehicle has started the wind vibration removal mode, determine the target front window opening data that is linked to the initial rear window opening data and output to the window execution system based on the driving speed and the initial rear window opening data.

[0046] After the vehicle turns on the active wind vibration control function, the vehicle status and external environment status need to meet certain conditions to start and enter the wind vibration elimination mode to achieve combined linkage of the windows and thus eliminate wind vibration inside the vehicle.

[0047] Because window vibration is strongly correlated with vehicle speed and window opening, a speed threshold v0 and window opening threshold P0 are initially set based on the vehicle model to reduce unnecessary window control actions. Furthermore, opening windows in rainy weather can cause water to enter the vehicle, impacting the driving experience. Therefore, rainfall is monitored and a rainfall threshold F0 is set during rainy weather.

[0048] In one example, the signal acquisition system is also used to: collect the in-vehicle noise signal of the vehicle's in-vehicle microphone and the rainfall data of the wiper; the controller determines whether the vehicle has started the wind vibration removal mode, including: calculating the first wind vibration noise pleasantness inside the vehicle based on the in-vehicle noise signal, wherein the first wind vibration noise pleasantness is used to characterize the subjective tolerance of the passengers in the vehicle to the wind vibration noise; based on the rainfall data, the first wind vibration noise pleasantness, the driving speed, and the initial rear window opening data, determining whether the vehicle has started the wind vibration removal mode.

[0049] Optionally, the controller determines whether the vehicle has turned on the wind vibration removal mode based on the rainfall data, the first wind vibration noise pleasantness, the driving speed, and the initial rear window opening data, including: determining whether the rainfall data is less than a rainfall threshold, determining whether the wind vibration noise pleasantness is less than a pleasantness threshold, determining whether the driving speed is greater than a speed threshold, and determining whether the initial rear window opening data is greater than a window opening threshold; if the rainfall data is less than the rainfall threshold, the first wind vibration noise pleasantness is less than the pleasantness threshold, the driving speed is greater than the speed threshold, and the initial rear window opening data is greater than the window opening threshold, it is determined that the vehicle has turned on the wind vibration removal mode.

[0050] The above-mentioned vehicle speed, window opening, pleasantness and rainfall are used for judgment. When the vehicle speed is greater than the vehicle speed threshold v0, the window opening is greater than the window opening threshold P0, the rainfall is less than the rainfall threshold F0, and the pleasantness is less than the pleasantness threshold T0, the control system starts the wind vibration removal mode and begins to perform linkage control of the windows.

[0051] Optionally, the controller calculates the first wind-vibration noise pleasantness inside the vehicle based on the in-vehicle noise signal, including: calculating the noise sound quality parameters in the in-vehicle noise signal, wherein the noise sound quality parameters include sound pressure level, roughness, loudness, and sharpness; using the following formula to calculate the first wind-vibration noise pleasantness PD inside the vehicle: PD = x1 / SPL + x2 / R + x3 / L + x4 / S, wherein SPL represents sound pressure level, R represents roughness, L represents loudness, S represents sharpness, and x1, x2, x3, and x4 represent weight coefficients of sound pressure level, roughness, loudness, and sharpness, respectively.

[0052] In one implementation of this embodiment, the controller calculates the first wind-vibration noise pleasantness inside the vehicle based on the in-vehicle noise signal, including: calculating the noise sound quality parameters in the in-vehicle noise signal, wherein the noise sound quality parameters include sound pressure level, roughness, loudness, and sharpness; determining the speed range in which the driving speed is located; generating a pleasantness weight coefficient of the noise sound quality parameter according to the speed range; configuring a wind-vibration noise pleasantness model based on the pleasantness weight coefficient; and using the wind-vibration noise pleasantness model to calculate the initial wind-vibration noise pleasantness inside the vehicle.

[0053] Optionally, the noise sound quality parameters include low-frequency noise parameters and high-frequency noise parameters, and the controller generates a pleasantness weight coefficient of the noise sound quality parameters according to the speed range, including: judging whether the maximum value of the speed range is less than a first threshold value; if the maximum value of the speed range is less than the first threshold value, generating a first pleasantness weight coefficient; if the maximum value of the speed range is greater than or equal to the first threshold value, judging whether the maximum value of the speed range is less than a second threshold value, wherein the second threshold value is greater than the first threshold value, and the weight of the low-frequency noise parameter in the first pleasantness weight coefficient is greater than the weight of the high-frequency noise parameter; if the maximum value of the speed range is less than the second threshold value, generating a second pleasantness weight coefficient; if the maximum value of the speed range is greater than or equal to the second threshold value, generating a third pleasantness weight coefficient, wherein the weight of the low-frequency noise parameter in the second pleasantness weight coefficient is equal to the weight of the high-frequency noise parameter, and the weight of the low-frequency noise parameter in the third pleasantness weight coefficient is less than the weight of the high-frequency noise parameter.

[0054] Optionally, the noise sound quality parameters include sound pressure level, roughness, loudness, and sharpness, among which the low-frequency noise parameters are the noise sound quality parameters that cause low-frequency wind vibration, including sound pressure level and loudness, and the high-frequency noise parameters are the noise sound quality parameters that cause high-frequency wind vibration, including roughness and sharpness.

[0055] This embodiment takes into account that when the vehicle is at low speed, low-frequency wind vibration is more prominent than high-frequency wind noise, and the human ear is more sensitive to low-frequency wind vibration. At high speeds, as the high-frequency wind noise component increases, the impact of low-frequency wind vibration decreases and the impact of high-frequency wind noise increases due to the masking effect. The impact of noise of different frequencies on sound quality parameters varies greatly. The sound pressure level and loudness are more affected by low-frequency noise, while roughness and sharpness are more sensitive to high-frequency noise. Therefore, in order to make the pleasantness model more applicable, when establishing and configuring the wind vibration noise pleasantness model, it is determined according to the speed range in which the vehicle is traveling.

[0056] By adopting the solution of this embodiment, the pleasantness weight coefficient of the noise sound quality parameter is configured based on the actual driving speed of the vehicle, thereby calculating a more accurate pleasantness of the wind buffeting noise.

[0057] In this embodiment, the controller outputs the target front window opening data combined with the initial rear window opening data to the window execution system based on the driving speed and the initial rear window opening data, including: retrieving a pre-trained wind vibration active control large model; inputting the driving speed and the initial rear window opening data into the wind vibration active control large model, and outputting the target front window opening data of the vehicle, wherein the target front window opening data includes a first target window opening position and a window opening degree thereof, and the wind vibration active control large model is used to output the optimal window opening data with the highest wind vibration noise pleasantness under the premise of maintaining the driving speed and the initial rear window opening data, and the wind vibration noise pleasantness is used to characterize the subjective tolerance of the passengers in the vehicle to wind vibration noise.

[0058] When the system starts the wind vibration elimination mode, the controller begins to calculate the window position and opening degree with the best comfort, that is, the target front window opening data, based on the large model of active wind vibration control under the current vehicle speed, window position and window opening degree.

[0059] The neural network of the large model for active wind vibration control in this embodiment utilizes a BP (Back Propagation) neural network. Based on samples of window combination data (window opening data before adjustment and window opening data after adjustment) and wind vibration noise pleasantness data corresponding to different vehicle speeds, the samples are input into the neural network model, the BP neural network model is repeatedly trained, and the performance is evaluated using the mean square error criterion to find the active wind vibration control model structure with the best fitting effect.

[0060] To establish a large neural network model, we first used a data acquisition front-end and microphones to collect multiple sets of in-vehicle wind-induced noise data under different operating conditions in a wind tunnel environment. The test conditions included various combinations of window openings, window openings, and vehicle speeds. The specific test conditions are shown in Table 1. The vehicle speed was divided into nine levels, from 50 km / h to 130 km / h, with each level being 10 km / h. The window openings were divided into 10 levels, from 10% to 100%, with each level being 10%. Wind-induced noise data was then measured under these various operating conditions.

[0061] Table 1:

[0062]

[0063] Calculate the sound quality parameters such as sound pressure level, loudness, roughness and sharpness of the wind noise test data under the different working conditions, and use the pleasantness model to obtain the pleasantness values corresponding to the vehicle model at different vehicle speeds, different window opening combinations and different openings.

[0064] Using a BP neural network, the wind buffeting noise pleasantness data corresponding to the aforementioned window combination data was input into a neural network model. The neural network structure consists of an input layer, an output layer, and a hidden layer. The input layer uses vehicle speed v, window opening thickness d, and wind buffeting noise pleasantness PD. The output layer uses the optimal window combination data (including at least two window positions and their openings). The BP neural network model is repeatedly trained, and performance is evaluated using the mean square error criterion to identify the optimal wind buffeting active control model structure.

[0065] The controller inputs information such as the current vehicle speed, the window position and the corresponding opening of the initial rear window opening data into the large model of active wind vibration control. Based on the large model of active wind vibration control, the controller begins to calculate the window combination and its opening with the best pleasure under the current vehicle speed and the initial rear window opening data, and outputs the target front window opening data.

[0066] The controller outputs the optimal window combination and its opening to the window execution system, which then sends it to the window controller via the on-board LIN line. The window controller then adjusts the corresponding window to the required opening.

[0067] In one example, the controller is also used to: obtain a second wind vibration noise pleasantness inside the vehicle after the window execution system completes adjusting the window opening based on the target front window opening data; determine whether the second wind vibration noise pleasantness is greater than a pleasantness threshold; if the second wind vibration noise pleasantness is greater than the pleasantness threshold, determine that the wind vibration elimination mode is completed; if the second wind vibration noise pleasantness is less than or equal to the pleasantness threshold, continue to train the wind vibration active control large model until the wind vibration noise pleasantness inside the vehicle is greater than the pleasantness threshold.

[0068] The wind vibration control effect is judged. If the control target is achieved, the wind vibration control process is terminated. If not, the window position and opening degree are optimized until the wind vibration control effect reaches the target. Figure 3 As shown, Figure 3 This is an optimization flow chart of the wind vibration control large model based on feedback control in an embodiment of the present invention. The specific process is as follows:

[0069] The microphone continues to collect wind noise data after the window adjustment is completed, performs real-time signal processing, and calculates its pleasantness;

[0070] Determine whether the objective pleasantness reaches the target. If the objective pleasantness is greater than or equal to the pleasantness target threshold, the wind vibration control process ends. If the target threshold is not reached, the current vehicle speed and different window opening combinations and their opening degrees are used as the input layer, and the wind vibration noise pleasantness is used as the output layer. Use the new samples to continue training the BP neural network model to obtain a new wind vibration control model.

[0071] The processor uses the new large model to re-output the new window combination and opening. The window controller adjusts the corresponding window to the desired opening, continuously optimizing the window combination and opening until the wind vibration control effect reaches the target threshold. Once the wind vibration control effect reaches the target for all operating conditions, the control effect stabilizes and the model is no longer adjusted.

[0072] In an example of model adaptive optimization, the controller continues to train the large model of active wind vibration control until the pleasantness of the wind vibration noise inside the vehicle is greater than the pleasantness threshold, including: iteratively performing the following steps: obtaining the pleasantness of the wind vibration noise after the window adjustment is completed in the previous adjustment cycle; configuring the driving speed, initial rear window opening data, and target front window opening data of the previous adjustment cycle as input sample data of the current adjustment cycle, and configuring the pleasantness of the wind vibration noise after adjustment as output sample data of the current adjustment cycle; using the input sample data and the output sample data to continue training and optimizing the large model of active wind vibration control; inputting the driving speed and initial window opening of the current adjustment cycle into the large model of active wind vibration control to obtain the target front window opening data of the current adjustment cycle; obtaining the pleasantness of the wind vibration noise after the window adjustment is completed based on the target front window opening data in the current adjustment cycle, and judging whether the pleasantness of the wind vibration noise is greater than the pleasantness threshold.

[0073] In this embodiment, the controller is also used to: after the window execution system completes the adjustment of the window opening based on the target front window opening data, detect the user window adjustment instruction of the window adjustment control, wherein the user window adjustment instruction is used to indicate the window position, adjustment direction, and desired opening of the user-adjusted window; and output a window opening signal according to the user window adjustment instruction and the window opening threshold.

[0074] Optionally, based on different user window adjustment scenarios, after the front window opening data with the optimal wind vibration noise pleasantness at the target noise reduction position is output according to the large wind vibration active control model at the current vehicle speed and the initial rear window opening data, the controller outputs a window opening signal according to the user window adjustment instruction and the window opening threshold, including: if the user window adjustment instruction includes a front window lowering request, outputting a first window opening signal, wherein the first window opening signal is used to instruct the window to be adjusted to the desired opening corresponding to the user window adjustment instruction; if the user window adjustment instruction includes a front window raising request, determining whether the rear window opening is less than the window opening threshold; if the rear window opening is less than the window opening threshold, outputting a second window opening signal, wherein the second window opening signal is used to instruct the window to be adjusted to the desired opening corresponding to the user window adjustment instruction; if the rear window opening is greater than or equal to the window opening threshold, outputting a third window opening signal, wherein the third window opening signal is used to instruct the rear window to be raised to a first opening, the first opening being greater than the first rear window opening threshold and less than the second rear window opening threshold, the first rear window opening threshold being the rear window opening. The second rear window opening threshold is the opening value when the wind vibration noise caused by the wind vibration of the rear window is the pleasantness threshold; if the user window adjustment instruction includes a rear window rising request or a rear window lowering request, it is determined whether the user window adjustment instruction also includes a front window rising request; if the user window adjustment instruction does not include a front window rising request, a fourth window opening signal is output, and the fourth window opening signal is used to instruct the vehicle window to be adjusted to the desired opening corresponding to the user window adjustment instruction; if the user window adjustment instruction includes a front window rising request, the rear window opening is determined. Whether it is less than the window opening threshold. If the rear window opening is less than the window opening threshold, a fifth window opening signal is output, wherein the fifth window opening signal is used to instruct the window to be adjusted to the desired opening corresponding to the user window adjustment instruction; if the rear window opening is greater than or equal to the window opening threshold, a sixth window opening signal is output, wherein the sixth window opening signal is used to instruct the front window to be lowered to the front window opening threshold, and the front window opening threshold is the front window opening data value with the highest wind vibration noise pleasantness output by the large wind vibration active control model according to the current vehicle speed and window opening data.

[0075] After the neural network model outputs the window opening adjustment, if there is human intervention in the window opening, the following window adjustment logic is used for control:

[0076] Scenario 1: When the front window is requested to be lowered, regardless of whether the rear window has no request, is requested to be raised, or is requested to be lowered, both the front and rear windows are adjusted to the desired opening according to the user's needs;

[0077] Scenario 2: When a window raise request is received, the rear window is first checked. If the rear window opening is less than the window opening threshold P0, the front window is adjusted to the desired opening according to the user's needs. If the rear window opening is greater than or equal to the window opening threshold P0, the rear window is raised to an opening of P2 where wind buffeting occurs but is acceptable.

[0078] Scenario 3: When the rear window receives a request to raise or lower, the front window is first judged. If there is no request or a request to lower the front window, the front and rear windows are adjusted to the desired opening according to user needs. If the front window is requested to rise, it is determined according to the degree of raising or lowering of the rear window glass. If the rear window opening is less than the window opening threshold P0, the front and rear windows are adjusted to the desired opening according to user needs. If the rear window opening is greater than or equal to the window opening threshold P0, the rear window is given priority and the front window is lowered to the opening P1 without wind vibration.

[0079] Figure 4 The execution flow chart of the data-driven wind-induced vibration active control system is as follows:

[0080] S41 turns on the wind vibration active control system. The car cockpit system mainly includes the software switch and voice prompt function of the wind vibration active control system. Set the wind vibration active control function switch in the car software control interface. The user can control the activation and deactivation of the wind vibration active control function through this switch. When the user clicks the switch, the wind vibration active control function is turned on. At this time, the car pops up a text message. At the same time, the controller drives the on-board speakers to play a voice reminder, reminding the user that the wind vibration active control function is currently turned on. When the user clicks to turn off the switch, the wind vibration active control function is turned off. The car interface pops up a text message. At the same time, the controller drives the on-board speakers to play a voice reminder, reminding the user that the wind vibration active control function is currently turned off.

[0081] S42 When the active wind vibration control function is turned on in the cockpit system of the vehicle, the body domain controller BDC in the controller reads the vehicle speed v information through the on-board CAN bus. At the same time, BDC also reads the rainfall f information from the rain sensor through the on-board LIN line, and reads the window opening p (percentage) and window position M information from the window motor controller. After the above information is collected in the signal acquisition system, it will be output to the controller for processing.

[0082] The S43 signal acquisition system also needs to use the on-board microphone to collect the current state of the vehicle's interior noise information and provide it to the controller. After data processing, the controller converts the wind vibration noise signal into sound quality parameters such as sound pressure level, roughness, loudness, and sharpness, and obtains the pleasantness value corresponding to the vehicle model at different vehicle speeds, different window positions, and different window openings based on the pleasantness model.

[0083] The objective pleasantness model is obtained by performing a subjective evaluation test on the corresponding wind-induced noise signal using a subjective scoring method, and fitting the calculated sound quality parameters and the subjective pleasantness score to obtain the objective pleasantness model.

[0084] Because window vibration is strongly correlated with vehicle speed and window opening, S44 initially sets a speed threshold v0 and an opening threshold P0 based on the vehicle model to reduce unnecessary window openings. Furthermore, opening windows in the rain can cause water to enter the vehicle, impacting the driving experience. Therefore, rainfall is monitored and a rainfall threshold F0 is set during rainy days.

[0085] The above-mentioned vehicle speed, window opening, pleasantness and rainfall are used for judgment. When the vehicle speed is greater than the vehicle speed threshold v0, the window opening is greater than the window opening threshold P0, the rainfall is less than the rainfall threshold F0, and the pleasantness is less than the pleasantness threshold T0, the control system starts the wind vibration removal mode.

[0086] S45 When the system starts the wind vibration elimination mode, the controller starts to calculate the window position and opening degree that are most pleasant for the vehicle type under the current vehicle speed, window position and window opening degree based on the wind vibration active control large model.

[0087] The large model for active wind vibration control uses the wind vibration noise pleasantness data corresponding to the above-mentioned window opening combinations and different vehicle speeds, inputs them into the large model for training, and obtains the large model for active wind vibration control with the best effect.

[0088] The S46 controller outputs the optimal window position and its opening degree signal to the window execution system, which then sends it to the window controller via the vehicle's LIN line. The window controller then adjusts the corresponding window to the desired opening degree.

[0089] S47 determines the wind vibration control effect. If the control target is achieved, the wind vibration control process ends. If not, the window position and opening degree are optimized until the wind vibration control effect reaches the target. The process is as follows:

[0090] S471 uses the microphone to continue collecting wind vibration noise data inside the car after S6 completes adjusting the window opening, performs real-time signal processing, and calculates its pleasantness.

[0091] S472 determines whether the current wind noise pleasantness level is greater than a threshold. If so, the control process ends. If not, the vehicle speed, window position, window opening, and current pleasantness level in that state are used as new sample inputs to continue training the large model.

[0092] S473 reuses the optimized large model to output the window position and opening corresponding to the current vehicle speed, window position and window opening, and gives it to the window controller in S6 to control the window and the corresponding opening.

[0093] S48 After the neural network large model outputs the window opening adjustment, if there is human intervention in the window opening, adaptive adjustment is also performed.

[0094] Figure 5Figure 2 shows the spectrum of the FLL (driver's left ear position) before and after the active wind vibration control system is activated. The vehicle speed is 60 km / h, and the initial rear window opening data is with the left rear window fully open. The solid line represents the original state, and the dashed line represents the state after the active wind vibration control system is activated. It can be seen that there is a significant low-frequency peak before the active wind vibration control system is activated. This peak is the main cause of ear discomfort. After the active wind vibration control system is activated, this peak disappears, and the subjective experience is significantly improved, achieving the control target.

[0095] The large model is used to optimize the window position and window opening, realize the control of window opening wind vibration, eliminate the vehicle's wind vibration phenomenon, and improve user comfort. The large model of active wind vibration control can be independently optimized based on the actual vehicle wind vibration data and can be adapted between different models. There is no need for repeated wind vibration noise testing, saving development time and cost.

[0096] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the system described in each embodiment of the present invention.

[0097] Example 2

[0098] An embodiment of the present invention further provides a storage medium storing a computer program, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0099] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0100] S1, outputs target front window opening data combined with the initial rear window opening data to the window execution system according to the vehicle speed and the initial rear window opening data, and outputs a window opening signal according to the user window adjustment instruction and the window opening threshold.

[0101] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0102] An embodiment of the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0103] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0104] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0105] S1, outputs target front window opening data combined with the initial rear window opening data to the window execution system according to the vehicle speed and the initial rear window opening data, and outputs a window opening signal according to the user window adjustment instruction and the window opening threshold.

[0106] Optionally, specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0107] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and 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 network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0108] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the relevant technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the system described in each embodiment or certain parts of the embodiment.

[0109] It should be understood that the terms used herein are for the purpose of describing specific example embodiments only and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "comprise", "include", "contain" and "have" are inclusive and therefore specify the presence of stated features, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not to be construed as necessarily requiring them to be performed in the specific order described or illustrated, unless the order of execution is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0110] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is intended to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A data-driven wind-induced vibration active control system, characterized in that: include: The vehicle cockpit system, including the switch components for the active wind vibration control function; A signal acquisition system is used to collect vehicle speed and initial rear window opening data, as well as user window adjustment commands after the active wind buffeting control function is enabled; A window execution system is used to adjust the opening of the window according to the target front window opening data and the window opening signal output by the controller; The controller is communicatively connected to the vehicle cabin system, the signal acquisition system, and the window execution system, and is used to output target front window opening data combined with the initial rear window opening data to the window execution system based on the vehicle speed and the initial rear window opening data, and to output a window opening signal based on the user window adjustment instruction and the window opening threshold.

2. The system according to claim 1, wherein: The controller is also used for: After the window execution system completes adjusting the window opening based on the target front window opening data, detecting a user window adjustment instruction of the window adjustment control, wherein the user window adjustment instruction is used to indicate the window position, adjustment direction, and desired opening of the window to be adjusted by the user; A window opening signal is output according to the user window adjustment instruction and the window opening threshold.

3. The system according to claim 2, characterized in that After outputting the target front window opening data, the controller outputs a window opening signal according to the user window adjustment instruction and the window opening threshold, including: If the user window adjustment instruction includes a front window lowering request, outputting a first window opening signal, wherein the first window opening signal is used to instruct the vehicle window to be adjusted to the desired opening corresponding to the user window adjustment instruction; If the user window adjustment instruction includes a front window raising request, determine whether the rear window opening is less than the window opening threshold; if the rear window opening is less than the window opening threshold, output a second window opening signal, wherein the second window opening signal is used to instruct the window to be adjusted to the desired opening corresponding to the user window adjustment instruction; if the rear window opening is greater than or equal to the window opening threshold, output a third window opening signal, wherein the third window opening signal is used to instruct the rear window to be raised to a first opening, the first opening being greater than the first rear window opening threshold and less than the second rear window opening threshold, the first rear window opening threshold being the opening value when wind vibration occurs on the rear window, and the second rear window opening threshold being the opening value when the pleasantness of the wind vibration noise caused by the wind vibration of the rear window is the pleasantness threshold; If the user window adjustment instruction includes a rear window raising request or a rear window lowering request, determine whether the user window adjustment instruction also includes a front window raising request; if the user window adjustment instruction does not include a front window raising request, output a fourth window opening signal, the fourth window opening signal being used to instruct the vehicle window to be adjusted to the desired opening corresponding to the user window adjustment instruction; if the user window adjustment instruction includes a front window raising request, determine whether the rear window opening is less than the vehicle window opening threshold, if the rear window opening is less than the vehicle window opening threshold, output a fifth window opening signal, wherein the fifth window opening signal is used to instruct the vehicle window to be adjusted to the desired opening corresponding to the user window adjustment instruction; if the rear window opening is greater than or equal to the vehicle window opening threshold, output a sixth window opening signal, wherein the sixth window opening signal is used to instruct the front window to be lowered to the front window opening threshold, the front window opening threshold being the front window opening data value with the highest wind vibration noise pleasantness output by the large wind vibration active control model according to the current vehicle speed and window opening data.

4. The system according to claim 1, wherein: The signal acquisition system is also used for: Acquiring an initial window opening position of the vehicle, wherein the initial window opening position includes at least one of the following: a left rear window and a right rear window; Acquire the initial window opening of the vehicle, wherein the initial rear window opening data includes: the initial window position and the initial window opening.

5. The system according to claim 1, wherein: The data-driven active wind vibration control system also includes: a voice broadcast module, which is communicated with the controller and is used to obtain a voice prompt signal according to the switch state of the switch component and play the voice prompt signal, wherein the voice prompt signal is used to indicate whether the current vehicle has turned on the active wind vibration control function.

6. The system according to claim 1, wherein: The controller is also used to: Determining whether the vehicle cockpit system has activated the wind vibration active control function; If the vehicle cockpit system turns on the wind vibration active control function, determining whether the vehicle is in a wind vibration elimination mode; If the vehicle starts a wind buffeting elimination mode, it is determined that target front window opening data linked with the initial rear window opening data is output to the window execution system according to the vehicle speed and the initial rear window opening data.

7. The system according to claim 6, characterized in that The signal acquisition system is further used to: collect the vehicle interior noise signal from the vehicle interior microphone and the rainfall data from the rain sensor; The controller determines whether the vehicle starts the wind vibration elimination mode, including: calculating a first wind buffeting noise pleasantness level inside the vehicle based on the in-vehicle noise signal, wherein the first wind buffeting noise pleasantness level is used to represent a subjective tolerance of a passenger in the vehicle to wind buffeting noise; Whether the vehicle is in a wind buffeting noise elimination mode is determined based on the rainfall data, the first wind buffeting noise pleasantness, the vehicle speed, and the initial rear window opening data.

8. The system according to claim 7, characterized in that The controller calculating a first wind buffeting noise pleasantness level inside the vehicle based on the vehicle interior noise signal includes: Calculating noise sound quality parameters in the in-vehicle noise signal, wherein the noise sound quality parameters include sound pressure level, roughness, loudness, and sharpness; The first wind buffeting noise pleasantness level PD of the vehicle interior is calculated using the following formula: PD=x1 / SPL+x2 / R+x3 / L+x4 / S, where SPL represents sound pressure level, R represents roughness, L represents loudness, and S represents sharpness. x1, x2, x3, and x4 represent the weight coefficients of sound pressure level, roughness, loudness, and sharpness, respectively.

9. The system according to claim 7, wherein: The controller determines whether the vehicle is in a wind buffeting noise elimination mode based on the rainfall data, the first wind buffeting noise pleasantness, the vehicle speed, and the initial rear window opening data, including: If the rainfall data is less than a rainfall threshold, the first wind vibration noise pleasantness is less than a pleasantness threshold, the driving speed is greater than a speed threshold, and the initial rear window opening data is greater than a window opening threshold, it is determined that the vehicle is in wind vibration removal mode.

10. The system according to claim 1, wherein: The controller outputs target front window opening data combined with the initial rear window opening data to the window execution system according to the vehicle speed and the initial rear window opening data, including: Retrieve the pre-trained large model for active wind vibration control; The driving speed and the initial rear window opening data are imported into the large model of active wind vibration control, and the target front window opening data of the vehicle is output, wherein the target front window opening data includes a first target window position and a window opening degree. The large model of active wind vibration control is used to output the optimal window opening data with the highest wind vibration noise pleasantness while maintaining the driving speed and the initial rear window opening data. The wind vibration noise pleasantness is used to characterize the subjective tolerance of passengers in the vehicle to wind vibration noise.

11. The system according to claim 1, wherein: The user window adjustment instruction includes: a manual window adjustment instruction sensed by a window opener, or a voice window adjustment instruction received by a vehicle computer.

12. A vehicle, characterized in that: The vehicle data-driven wind-induced vibration active control system comprises the vehicle data-driven wind-induced vibration active control system according to any one of claims 1 to 11.

Images