Vehicle noise reduction method and system and vehicle

Abstract

The invention discloses a vehicle noise reduction method and system and a vehicle, and belongs to the technical field of vehicle noise reduction. A specific implementation mode of the method comprises the following steps: predicting a noise spectrum of an internal space of a vehicle in a future time period based on vehicle noise evaluation data obtained in real time by utilizing a trained noise spectrum prediction model; a plurality of frequency bands are divided for the noise spectrum; for each frequency band, executing the steps of determining a sound wave signal opposite to the phase of the frequency band and controlling a noise reduction device matched with the frequency band to generate the sound wave signal; and active noise reduction is carried out on the internal space of the vehicle. According to the embodiment of the invention, by predicting the noise spectrum and generating the sound wave signals for noise reduction for different frequency bands, the accuracy and the refinement degree of active noise reduction of the vehicle are improved, and the riding experience of passengers is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle noise reduction, and in particular to a vehicle noise reduction method, system and vehicle. Background Art

[0002] When a vehicle is driving, the sound generated by the noise source will form various noises in the interior space of the vehicle, affecting the passengers' riding experience.

[0003] Currently, commonly used noise reduction methods include: 1) using additional sound-absorbing materials (such as sound-absorbing cotton and soundproofing panels) to absorb noise from within the vehicle. 2) real-time noise signal acquisition and counteracting the noise signal to achieve noise reduction. Existing methods 1) require additional components and have poor noise reduction effectiveness against high-frequency noise; and 2) fail to consider the operating parameters of the noise source and future parameter changes, resulting in low noise reduction accuracy, poor flexibility, and poor dynamic adaptability. Summary of the Invention

[0004] In light of this, the present invention provides a vehicle noise reduction method, system, and vehicle. These methods utilize a trained noise spectrum prediction model and, based on real-time vehicle noise assessment data, predict the noise spectrum of the vehicle's interior space in future time periods. The system also divides the noise spectrum into multiple frequency bands. For each frequency band, the system determines a sound wave signal with a phase opposite to that of the frequency band and controls a noise reduction device that matches the frequency band to generate a sound wave signal, thereby actively reducing noise within the vehicle's interior. By predicting the noise spectrum and generating sound wave signals for noise reduction in different frequency bands, the present invention improves the accuracy and refinement of active noise reduction in vehicles, enhancing the passenger experience.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a vehicle noise reduction method, comprising: obtaining noise assessment data of a vehicle; wherein the noise assessment data includes one or more of operating parameters of a noise source, vehicle body vibration data, and noise data inside the vehicle; using a trained noise spectrum prediction model to predict the noise spectrum of the vehicle interior space in a future time period based on the noise assessment data; dividing the noise spectrum into multiple frequency bands; and for each frequency band, executing: determining a sound wave signal with a phase opposite to the frequency band, and controlling a noise reduction device matched to the frequency band to generate a sound wave signal; thereby actively reducing noise in the vehicle interior space.

[0007] Optionally, the vehicle noise reduction method further includes: obtaining historical data used to train a noise spectrum prediction model, wherein the historical data includes: historical operating parameters of the vehicle noise source, historical vibration parameters of the vehicle body, and historical noise data inside the vehicle; adding a synchronized timestamp to each type of historical data to generate synchronized training data; using the synchronized training data to train a noise spectrum prediction model, the noise spectrum prediction model including a first correlation between the historical operating parameters of the vehicle noise source and the historical noise data; and / or a second correlation between the historical vibration parameters of the vehicle body and the historical noise data; predicting the noise spectrum of the vehicle interior space in a future time period, including: predicting the noise spectrum of the vehicle interior space in the future time period based on the first correlation and / or the second correlation.

[0008] Optionally, the vehicle noise reduction method further includes: iteratively performing the following optimization model operations for the noise spectrum prediction model: collecting the target noise spectrum after noise reduction in the vehicle interior space; using the target noise spectrum to evaluate the training effect of the noise spectrum prediction model; and adjusting the model parameters of the noise spectrum prediction model based on the evaluated training effect.

[0009] Optionally, the vehicle noise reduction method further includes: analyzing the phase difference between the signal of the noise data collected in real time and the sound wave signal; using the least mean square algorithm to dynamically superimpose the phase difference as a phase offset on the sound wave signal; and / or, for each frequency band: measuring the delay data corresponding to the frequency band; constructing a correspondence between the delay data and the frequency corresponding to the frequency band; based on the current ambient temperature of the vehicle and the correlation between the temperature and the delay data; using a Kalman filter to dynamically correct the phase difference in the correspondence; and superimposing the phase difference as a phase offset on the sound wave signal.

[0010] In a second aspect, the present invention provides a vehicle noise reduction system, comprising: a plurality of acquisition devices for acquiring noise evaluation data, a controller, and a noise reduction device; wherein the plurality of acquisition devices are used to respectively acquire a plurality of noise evaluation data of the vehicle; wherein the noise evaluation data includes one or more of operating parameters of the noise source, vehicle body vibration data, and noise data inside the vehicle; the controller is used to use a trained noise spectrum prediction model to predict the noise spectrum of the vehicle interior space in a future time period based on the noise evaluation data; divide the noise spectrum into a plurality of frequency bands; for each frequency band, perform the following: determine a sound wave signal having a phase opposite to that of the frequency band; and control the noise reduction device matched to the frequency band to generate a sound wave signal to actively reduce noise in the vehicle interior space.

[0011] Optionally, the vehicle noise reduction system includes multiple acquisition devices including: a first acquisition device for acquiring operating parameters of a noise source; a second acquisition device for acquiring body vibration data of the vehicle; and a third acquisition device for acquiring noise data inside the vehicle.

[0012] Optionally, the noise reduction device included in the vehicle noise reduction system is a ceramic pressed disc array; multiple groups of the noise reduction devices are respectively attached to the housing of the noise source; wherein each group of noise reduction devices is independently controlled by the controller.

[0013] Optionally, the spacing between adjacent ceramic press plates contained in the same group of noise reduction devices is set to 1 / 4 of the vibration wavelength, and the vibration wavelength is the dominant wavelength of the shell surface vibration of the noise source; and / or, different groups of noise reduction devices are used to generate sound wave signals required for noise reduction for different frequency bands; and / or, the stiffness or thickness of the ceramic press plate arrays configured in different frequency bands is different and / or, each group of the noise reduction devices is integrated with an independent circuit; the controller drives the noise reduction device to operate based on a target voltage that meets the operation of the noise reduction device by controlling the independent circuit, and the target voltage is obtained by boosting the original voltage of the vehicle battery through a DC voltage converter.

[0014] Optionally, for the structure in which the noise reduction device is integrated with an independent circuit, the high-voltage driving line corresponding to the independent circuit is a double-shielded coaxial line; preferably, the controller is also used to adjust the target voltage of one or more groups of noise reduction devices in real time according to the current noise evaluation data using a field programmable gate array module; preferably, each group of the independent circuits is equipped with a heat dissipation device.

[0015] In a third aspect, an embodiment of the present invention provides a vehicle noise reduction device, comprising:

[0016] A data acquisition module is used to acquire noise evaluation data of the vehicle; the noise evaluation data includes one or more of operating parameters of the noise source, vehicle body vibration data, and noise data inside the vehicle;

[0017] The spectrum prediction module is used to use the trained noise spectrum prediction model and noise assessment data to predict the noise spectrum of the vehicle interior space in the future time period;

[0018] The noise reduction module is used to divide the noise spectrum into multiple frequency bands. For each frequency band, it performs the following operations: determining a sound wave signal with a phase opposite to that of the frequency band; and controlling the noise reduction device matched to the frequency band to generate a sound wave signal to actively reduce noise in the vehicle interior space.

[0019] In a fourth aspect, an embodiment of the present invention provides a vehicle, comprising: the vehicle noise reduction system as described in the second aspect.

[0020] In a fifth aspect, an embodiment of the present invention provides an electronic device, including:

[0021] one or more processors;

[0022] a storage device for storing one or more programs,

[0023] When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle noise reduction method according to the embodiment of the present invention.

[0024] In a sixth aspect, an embodiment of the present invention provides a computer-readable storage medium on which a computer program for implementing a vehicle noise reduction method is stored. When the computer program is executed by an onboard processor, the vehicle noise reduction method of the embodiment of the present invention is implemented.

[0025] In a seventh aspect, an embodiment of the present invention provides a vehicle that can implement the vehicle noise reduction method as described above in the embodiment of the present invention.

[0026] The technical solution of the above invention has the following advantages or beneficial effects: it can use a trained noise spectrum prediction model to predict the noise spectrum of the vehicle interior space in a future time period based on real-time vehicle noise assessment data; it can also divide the noise spectrum into multiple frequency bands; for each frequency band, it executes the steps of determining a sound wave signal with a phase opposite to the frequency band and controlling a noise reduction device matched to the frequency band to generate a sound wave signal; thereby actively reducing noise in the vehicle interior space. By using the noise spectrum prediction model to predict the noise spectrum and generate sound wave signals for noise reduction in different frequency bands, the embodiments of the present invention improve the accuracy and refinement of active noise reduction in the vehicle, thereby enhancing the passenger experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a flow chart of a vehicle noise reduction method provided according to an embodiment of the present invention;

[0028] Figure 2 1 is a flow chart of a noise spectrum prediction model training method according to an embodiment of the present invention;

[0029] Figure 3 2 is a schematic structural diagram of a vehicle noise reduction system provided according to an embodiment of the present invention;

[0030] Figure 4 is a structural schematic diagram of a vehicle provided according to an embodiment of the present invention;

[0031] Figure 5 It is a schematic diagram of the structure of a computer system suitable for implementing the embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following description of exemplary embodiments of the present invention is made in conjunction with the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding. These details should be considered as merely exemplary. Therefore, it should be appreciated by those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0033] It should be pointed out that, in the absence of conflict, the embodiments of the present invention and the technical features therein may be combined with each other.

[0034] Furthermore, the terms "first," "second," and "third," etc., used in the embodiments of the present invention, are used to distinguish similar objects, and are not necessarily used to describe a specific number or order. It should be understood that such terms are interchangeable where appropriate, and are merely a means of distinguishing objects with the same attributes in the embodiments of the present invention.

[0035] Furthermore, the vehicle involved in the embodiment of the present invention may be an internal combustion engine vehicle using an engine as a power source, a hybrid vehicle using an engine and an electric motor as power sources, an electric vehicle using an electric motor as a power source, or the like.

[0036] Figure 1 The following is a schematic diagram showing the main steps of the vehicle noise reduction method provided by the embodiment of the present invention, which includes the following steps:

[0037] Step S101: Acquire noise evaluation data of a vehicle; wherein the noise evaluation data includes one or more of operating parameters of a noise source, vehicle body vibration data, and noise data inside the vehicle.

[0038] In an embodiment of the present invention, when predicting the vehicle interior noise spectrum, one or more types of data (noise assessment data, including noise source operating parameters, vehicle body vibration data, and vehicle interior noise data) are combined as vehicle noise assessment data. Specifically, for the noise source operating parameters, if the noise source is an engine, these operating parameters may include speed, load, cylinder pressure, temperature, and other data; if the noise source is a tire, these operating parameters may include speed, temperature, and other data. These multiple operating parameters representing the noise source's operating conditions provide basic data for analyzing and assessing vehicle interior noise.

[0039] For vehicle body vibration data, vehicle body vibration sensors installed in key locations such as the vehicle suspension and firewall are used to obtain vehicle body vibration data (such as vibration frequency, acceleration, etc.). Through the vehicle body vibration data, relevant data such as the noise propagation path and noise period can be analyzed.

[0040] Optionally, for the noise data inside the vehicle, a microphone array installed on the ceiling, A-pillar, etc. can be used to collect the noise data inside the vehicle (i.e., the noise spectrum), and the collected noise spectrum directly reflects the sound field environment inside the vehicle.

[0041] Step S102: Using the trained noise spectrum prediction model, based on the noise assessment data, predict the noise spectrum of the vehicle interior space in the future time period. In the description of the embodiment of the present invention, the model refers to the noise spectrum prediction model.

[0042] Step S103: Divide the noise spectrum into multiple frequency bands; for each frequency band, perform the following: determine a sound wave signal with a phase opposite to that of the frequency band, and control a noise reduction device matching the frequency band to generate a sound wave signal; thereby actively reducing noise in the vehicle interior space.

[0043] Specifically, in an embodiment of the present invention, a trained noise spectrum prediction model is used to predict the noise spectrum of the interior space of the vehicle in a future time period based on the acquired noise evaluation data, so that active noise reduction can be performed inside the vehicle at the current time. The trained noise spectrum prediction model can predict the noise spectrum of the future time period based on the noise evaluation data, the first correlation between the historical operating parameters of the vehicle noise source contained in the model and the historical noise data, and / or the second correlation between the historical vibration parameters of the vehicle body and the historical noise data; for example, the noise spectrum prediction model can analyze the noise spectrum with specific characteristics (for example, knock, turbine whine, etc.) generated by the engine in a future time period (for example, 15 seconds, 30 seconds, etc.) according to the engine's operating parameters (speed, load, temperature, pressure, etc.) (that is, through the historical operating parameters and historical noise data). and / or, based on the second correlation between the historical vibration parameters of the vehicle body and the historical noise data, the noise spectrum of the future time period is predicted by analyzing the relationship between the periodicity of the vibration and the noise, thereby performing active noise reduction in a targeted manner. This allows the vehicle to perform active noise reduction before noise occurs in various scenarios such as rapid acceleration and high-speed cruising, creating a "library-level" quiet space inside the vehicle, greatly reducing the noise inside the vehicle, suppressing the noise caused by the turbine's increased high-frequency howling or tire noise resonance peak, and improving the passenger experience.

[0044] The embodiment of the present invention dynamically and in real time predicts the noise spectrum of a future time period, and can generate a relatively opposite sound wave signal before noise is generated (eg, rapid acceleration for 30 seconds) to perform active noise reduction.

[0045] Preferably, in embodiments of the present invention, before using a trained noise spectrum prediction model to predict the noise spectrum of the vehicle interior space in a future time period based on noise assessment data, various noise assessment data can be preprocessed. For example, data synchronization (timestamp alignment) can be performed: adding precise timestamps to different sensor data to ensure temporal synchronization of multi-source data for subsequent fusion processing; data verification can be performed to detect data integrity and accuracy in real time, remove abnormal data, and ensure the reliability of preprocessed data. Furthermore, noise filtering can be performed to remove interference from irrelevant frequency bands and wavelet denoising to eliminate high-frequency noise, thereby improving data quality; and feature extraction can be performed: extracting peak factors from the time domain, performing wavelet packet decomposition, and characterizing noise characteristics in multiple dimensions, among other data preprocessing operations.

[0046] Furthermore, an embodiment of the present invention separately controls different noise reduction devices (ceramic plate arrays) for different frequency bands, performing active noise reduction by dividing the ceramic plate into independent areas corresponding to the vibration modes of the engine block. Specifically, the predicted noise spectrum of the vehicle interior space in the future time period can be divided into multiple frequency bands, such as: low frequency <500Hz, medium frequency 500-2kHz, high frequency >2kHz, etc.; for different frequency bands, ceramic plate arrays with different positions or different thicknesses (for example, thin plates for high frequency and thick plates for low frequency) are used to perform corresponding noise reduction, which improves the refinement of the noise reduction control and greatly enhances the noise reduction effect.

[0047] Furthermore, in an embodiment of the present invention, a dynamic phase compensation method is provided to correct sensor delay and improve noise reduction effect.

[0048] Specifically, possible factors causing delays include: sensor delay, such as delay in the signal transmission path of the microphone of the device that collects noise data (e.g., a delay of 1ms), ADC (analog-to-digital converter) sampling delay (e.g., a delay of 0.5ms); and / or, execution delay of the noise reduction device: switching response time of the independent circuit that drives the ceramic press, and mechanical response lag of the ceramic press itself (e.g., 1ms), etc.

[0049] Furthermore, in the embodiments of the present invention, there may be multiple methods for delaying dynamic phase compensation to correct sensor delay.

[0050] The first method: adaptive phase correction algorithm.

[0051] Step 1: Real-time acquisition of the sensor signal (i.e., the noise data signal) and the actuator feedback signal (i.e., the acoustic signal) and analysis of their phase difference. Step 2: Dynamically adjust the acoustic signal's phase offset using a least mean square algorithm (LMS). Specifically, the phase difference between the real-time acquired noise data signal and the acoustic signal is analyzed; the LMS algorithm is used to dynamically adjust the phase difference as a phase offset and add it to the acoustic signal.

[0052] The second method involves measuring the delay of each frequency band in a laboratory environment and creating a phase-frequency lookup table. Specifically, for each frequency band, the corresponding delay data is measured and a corresponding relationship is established between the delay data and the corresponding frequency. Based on this relationship, dynamic phase compensation is applied to correct for sensor delay.

[0053] Specifically, the ambient temperature of the vehicle may cause the characteristics of the components (capacitors, resistors, crystal oscillators, etc.) of the vehicle's equipment (such as ADC, sensors, etc.) to change with temperature, resulting in changes in signal delay time, which in turn causes phase shift; therefore, in order to achieve dynamic phase compensation for delay based on this correspondence, the embodiment of the present invention can also perform online fine-tuning of the dynamic phase of delay according to the current ambient temperature of the vehicle. Specifically, during the noise reduction process, the parameters included in the correspondence between the delay data and the frequency corresponding to the frequency band are further dynamically corrected by the Kalman filter to adapt to the temperature drift effect. That is, for each frequency band: measure the delay data corresponding to the frequency band; construct a correspondence between the delay data and the frequency corresponding to the frequency band; based on the current ambient temperature of the vehicle and the correlation between the temperature and the delay data; use the Kalman filter to dynamically correct the phase difference in the correspondence; and superimpose the phase difference on the sound wave signal as a phase shift.

[0054] The third method: a combination of the first and second methods.

[0055] The embodiments of the present invention further improve the accuracy and real-time performance of generating the sound wave signal used for noise reduction through multiple methods of correcting sensor delays through dynamic phase compensation, thereby further improving the accuracy of noise reduction.

[0056] Figure 2 A schematic diagram of a process for training a noise spectrum prediction model provided by an embodiment of the present invention is shown, which includes the following steps:

[0057] Step S201: Acquire historical data used for training a noise spectrum prediction model, wherein the historical data includes: historical operating parameters of the vehicle noise source, historical vibration parameters of the vehicle body, and historical noise data inside the vehicle.

[0058] In an embodiment of the present invention, a noise spectrum prediction model is trained using historical noise assessment data, wherein the historical data used for training includes: historical operating parameters of the vehicle noise source, historical vibration parameters of the vehicle body, and historical noise data inside the vehicle. When the noise source is an engine, the historical operating parameters of the vehicle noise source may include data such as speed, load, cylinder pressure, and temperature; when the noise source is a tire, its historical operating parameters may include data such as speed and temperature; multiple operating parameters representing the working conditions of the noise source can provide basic data for analyzing and evaluating the noise conditions inside the vehicle; for the historical vibration parameters of the vehicle body, the vehicle body vibration data (such as vibration frequency, acceleration, etc.) obtained can be used as historical vibration data by using vehicle body vibration sensors installed in key locations such as the vehicle suspension and firewall. For the noise data inside the vehicle: the noise data inside the vehicle is collected as historical noise data using a microphone array installed in locations such as the vehicle ceiling and A-pillars.

[0059] Step S202: adding a synchronization timestamp to each type of historical data to generate synchronized training data.

[0060] Specifically, the noise spectrum prediction model provided by the embodiment of the present invention is a prediction model associated with time features. It can perform feature fusion in a multimodal fusion manner: the temporal feature spatial features of historical data related to noise are spliced ​​and integrated with multi-source information, thereby performing preprocessing on the historical data used for training; the specific preprocessing methods include: noise filtering, that is, using filtering to remove interference from irrelevant frequency bands, and wavelet denoising to eliminate high-frequency noise and improve data quality. Feature extraction, that is, extracting peak factors from the time domain, performing wavelet packet decomposition, and characterizing noise features in multiple dimensions; data synchronization, that is, adding precise timestamps to different sensor data so that multi-source data are synchronized in time, which is convenient for subsequent fusion processing. Data verification: that is, real-time detection of data integrity and accuracy, elimination of abnormal data, and ensuring the reliability of preprocessed data.

[0061] The training effect and efficiency of model training are improved through data preprocessing.

[0062] Step S203: Training a noise spectrum prediction model using the synchronized training data, where the noise spectrum prediction model includes a first correlation between historical operating parameters of the vehicle noise source and historical noise data, and a second correlation between historical vibration parameters of the vehicle body and historical noise data; predicting the noise spectrum of the vehicle interior space in a future time period includes predicting the noise spectrum of the vehicle interior space in the future time period based on the first correlation and the second correlation.

[0063] Specifically, the noise spectrum prediction model of the embodiment of the present invention can capture the temporal dependency between engine operating conditions (historical operating parameters) and historical noise (i.e., the first correlation between the historical operating parameters of the vehicle noise source and the historical noise data) based on the input historical operating parameters, historical vibration parameters, and historical noise data. For example, this model can detect the impact of sudden speed changes on noise, providing time dimension information for noise prediction. It can also construct a correlation between the acoustic signals of vehicle body vibration and noise data (i.e., the second correlation between the historical vibration parameters of the vehicle body and the historical noise data), thereby exploring the periodic characteristics of knock noise and improving the model's ability to understand complex signals.

[0064] Furthermore, the noise spectrum prediction model is trained to predict the noise spectrum of the vehicle interior space in a future time period based on the first correlation relationship and / or the second correlation relationship.

[0065] Step S204: For the noise spectrum prediction model, perform the following iterative operations of optimizing the model: collect the target noise spectrum after noise reduction in the vehicle interior space; use the target noise spectrum to evaluate the training effect of the noise spectrum prediction model; and adjust the model parameters of the noise spectrum prediction model based on the evaluated training effect.

[0066] Specifically, in the embodiment of the present invention, an iterative optimization operation is performed on the noise spectrum prediction model.

[0067] Specific optimization methods include: real-time monitoring of the microphone array inside the vehicle to collect the target noise spectrum after noise reduction, and real-time feedback on the noise reduction effect (i.e., using the target noise spectrum to evaluate the training effect of the noise spectrum prediction model); further, dynamically adjusting the model parameters based on the feedback of the noise reduction effect (i.e., adjusting the model parameters of the noise spectrum prediction model based on the evaluated training effect) to continuously optimize the noise reduction effect. Natural noise data from vehicle driving can also be used for model pre-training to enhance model capabilities. Through self-supervised learning, the model is continuously optimized so that it can adapt to different driving scenarios.

[0068] This embodiment of the present invention trains a noise spectrum prediction model using various types of noise-related training data and dynamically iteratively optimizes the model to account for the impact of factors such as engine aging and ambient temperature fluctuations on noise frequency domain prediction. This improves the prediction performance of the noise spectrum prediction model, thereby enhancing the noise reduction effect within the vehicle and the passenger experience. Furthermore, by acquiring the operating parameters of the noise source, it can cover a variety of scenarios (e.g., cold starts, air pressure fluctuations, frequent acceleration and deceleration), and can also provide personalized noise reduction methods based on driver preferences (e.g., the degree of engine noise preservation in sport mode).

[0069] Figure 3A schematic diagram of the structure of a vehicle noise reduction system to which an embodiment of the present invention can be applied is shown. The system includes: a noise source housing S, multiple noise sources M1-Mn disposed within the noise source housing, a controller A, multiple acquisition devices E1-E3, and multiple groups of noise reduction devices (one group represented by C). Specifically, a vehicle noise reduction system includes: multiple acquisition devices for collecting noise assessment data, a controller, and noise reduction devices; the multiple acquisition devices are used to respectively collect multiple noise assessment data from the vehicle; the noise assessment data includes one or more of the following: operating parameters of the noise source, vehicle body vibration data, and noise data within the vehicle; the controller is used to use a trained noise spectrum prediction model to predict the noise spectrum of the vehicle interior space in a future time period based on the noise assessment data; the noise spectrum is divided into multiple frequency bands; and for each frequency band, the system performs the following steps: determining a sound wave signal with a phase opposite to that of the frequency band; and controlling the noise reduction device matched to the frequency band to generate a sound wave signal to actively reduce noise within the vehicle interior space.

[0070] Among them, the multiple collection devices include a first collection device for collecting operating parameters of the noise source; wherein the first collection device can be a variety of sensors arranged at the ECU (on-board control unit) interface in the engine compartment, for collecting engine operating parameters such as speed, load, cylinder pressure, etc.; a second collection device for collecting vehicle body vibration data (for example: a vibration sensor installed at a suspension, firewall, etc. on the vehicle body, for collecting vibration frequency and acceleration contained in the vehicle body vibration data); a third collection device for collecting noise data inside the vehicle (for example, a microphone array installed on the roof or A-pillar inside the vehicle, for real-time collection of the vehicle interior noise spectrum, for noise prediction and for feedback optimization of the model). The present invention does not limit the specific models, specific locations and quantities of the various sensors.

[0071] Furthermore, in an embodiment of the present invention, the noise reduction device is a ceramic pressed disc array. The ceramic pressed discs, for example, measure 10mm x 10mm x 1mm and can be paired with an aluminum alloy substrate to achieve both high-frequency response and broadband coverage. The ceramic pressed disc array rapidly responds to high-frequency noise, achieving precise cancellation, while its broadband coverage can address wide-band noise, adapting to the noise reduction requirements of various engine operating conditions. By employing a ceramic pressed disc array for noise reduction, the use of traditional sound insulation materials is reduced, thereby reducing vehicle weight and saving energy.

[0072] Furthermore, the ceramic pressed sheet arrays are respectively installed at key positions of the housings of multiple noise sources (such as multiple engine cylinders or turbochargers) to directly act on the noise sources. Figure 3As shown, each rectangle filled by the grid represents a group of ceramic plate arrays (i.e., noise reduction devices), and multiple groups of the noise reduction devices are respectively attached to the outer shell of the noise source (i.e., different groups of ceramic plate arrays are attached to different areas of the outer shell of the noise source, for example: different areas in one or more directions of different directions such as front, back, left, and right); wherein, each group of noise reduction devices is independently controlled by the controller; wherein, each group of noise reduction devices is independently controlled by the controller.

[0073] In an embodiment of the present invention, a ceramic pressing plate array is used to divide the coverage area according to the noise mode, that is, the ceramic pressing plates are divided into independent areas corresponding to the vibration mode of the engine cylinder. For example, four groups of ceramic pressing plates are set for a four-cylinder engine, and each group covers noise in a specific frequency band (such as low frequency <500Hz, medium frequency 500-2kHz, and high frequency >2kHz). Furthermore, different types of ceramic pressing plates are used in different frequency bands (that is, different groups of noise reduction devices are used to generate the sound wave signals required for noise reduction for different frequency bands), further improving the noise reduction effect. Among them, different types of ceramic pressing plates include piezoelectric ceramic plates of different stiffness or thickness (that is, the stiffness or thickness of the ceramic pressing plate arrays configured in different frequency bands is different); for example: thin plates are set for high frequencies, thick plates are set for low frequencies, etc.

[0074] In one embodiment of the present invention, the grouping and number of ceramic platen arrays can be grouped according to the vibration source. For example, each cylinder of a four-cylinder engine corresponds to one group of platens (a total of four groups), each group contains three platens (covering multiple positions in the front, back, left and right of the cylinder body), and the number of platens in a single group is 3-5, and the spacing is 1 / 4 of the vibration wavelength (that is, the spacing between adjacent ceramic platens in the same group is set to 1 / 4 of the vibration wavelength, and the vibration wavelength is the dominant wavelength of the shell surface vibration of the noise source); it can also be grouped according to frequency, for example: low-frequency group (<500Hz): 2 groups, using thick platens (for example: thickness of about 5mm); high-frequency group (>2kHz): 4 groups, using thin platens (for example: thickness of about 1mm).

[0075] By setting the ceramic pressing array into different areas and different groups, the system bandwidth is improved, thereby improving the response speed of the ceramic pressing array; by activating only the group corresponding to the main frequency of the noise (for example, turning off the high-frequency group when the vehicle is idling), energy consumption is reduced; when a single group fails, the other groups can still maintain basic noise reduction, which increases the redundancy of the noise reduction and improves the reliability of the noise reduction; through distributed pressing, mechanical stress is dispersed, local overload is avoided, and the service life of the ceramic pressing array is extended.

[0076] Furthermore, in an embodiment of the present invention, different independent driving circuits are used to drive the ceramic pressing arrays in different partitions (i.e., each group of noise reduction devices is integrated with an independent circuit); for each independent driving circuit, a multi-channel isolated driving method is adopted, for example: each group of pressing is configured with an independent DC-DC boost circuit (i.e., a power conversion circuit that converts a low DC voltage into a high DC voltage), and supports 100-500Vpp (vpp represents peak-to-peak voltage) output, and the vehicle battery boosts the 12V voltage (i.e., the original voltage) through a DC-DC converter to meet the driving requirements of the ceramic pressing actuator (i.e., the vehicle battery boosts the original voltage to a target voltage that meets the working requirements of the noise reduction device through a DC voltage converter), avoiding crosstalk between channels; a dynamic power allocation method is also adopted, such as using an FPGA (i.e., a field programmable gate array) to adjust the voltage amplitude and phase of each channel in real time to match the engine operating conditions (such as increasing the high-frequency channel power during rapid acceleration). An anti-interference design can also be adopted, and the high-voltage drive line uses a double-layer shielded coaxial line to minimize the grounding line area to suppress common-mode noise. Thermal management can also be employed: each set of drive circuits (i.e., independent circuits) is equipped with an independent heat sink (e.g., aluminum fins) to prevent high temperatures from degrading the performance of the piezoelectric ceramics. Specifically, the controller controls the independent circuits to drive the noise reduction device based on a target voltage that satisfies the device's operation. The target voltage is obtained by boosting the vehicle battery's original voltage via a DC voltage converter. For structures where the noise reduction device integrates independent circuits, the high-voltage drive lines corresponding to the independent circuits are double-shielded coaxial cables. Preferably, the controller is further configured to adjust the target voltage of one or more noise reduction devices in real time using a field-programmable gate array module based on current noise assessment data. Preferably, each set of independent circuits is equipped with a heat sink.

[0077] By driving the ceramic pressing array connected to each independent circuit using different independent circuits, independent control of the ceramic pressing array is achieved. This improves the refined management of the acoustic signal generated by the control ceramic pressing array, thereby enhancing the noise reduction effect inside the vehicle. When executing communication between different components, embodiments of the present invention can use the CAN bus to control sensors and transmit AI chip data, thereby improving the efficient and stable communication effects.

[0078] It is understandable that Figure 3 The number of noise sources, the position and the number of ceramic plate arrays shown are only examples, and the present application does not limit the number of noise sources, the position and the number of ceramic plate arrays.

[0079] Figure 4 An exemplary vehicle system architecture 400 is shown to which a vehicle noise reduction method or a vehicle noise reduction system according to an embodiment of the present invention may be applied.

[0080] like Figure 4As shown, the vehicle system architecture 400 may include various systems, such as a vehicle noise reduction system 401, a power system 402, a sensor system 403, a control system 404, one or more peripheral devices 405, a power supply 406, a computer system 407, and a user interface 408. Optionally, the vehicle system architecture 400 may include more or fewer systems, and each system may include multiple components. In addition, each system and component of the vehicle system architecture 400 may be interconnected via wired or wireless connections.

[0081] Among them, the vehicle system architecture 400 includes a vehicle noise reduction system 401, which includes: multiple collection devices, a controller and a noise reduction device for collecting noise evaluation data; the multiple collection devices are used to respectively collect multiple noise evaluation data of the vehicle; the controller is used to use a trained noise spectrum prediction model to predict the noise spectrum of the vehicle interior space in a future time period based on the noise evaluation data; the noise spectrum is divided into multiple frequency bands; for each frequency band, the following are performed: determining a sound wave signal with a phase opposite to the frequency band; and controlling the noise reduction device matched to the frequency band to generate a sound wave signal to actively reduce noise in the vehicle interior space.

[0082] The power system 402 may include components that provide power and movement for the vehicle. For example, the power system 402 may include an engine, an energy source, a transmission, wheels, tires, etc. The engine may be an internal combustion engine, an electric motor, an air compression engine, or a combination of other types of engines, such as a hybrid engine consisting of a gasoline engine and an electric motor, or a hybrid engine consisting of an internal combustion engine and an air compression engine. The engine converts the energy source into mechanical energy and provides it to the transmission. Examples of energy sources may include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electricity. The energy source may also provide energy to other systems of the vehicle. In addition, the transmission may include a gearbox, a differential, a drive shaft, a clutch, etc.

[0083] The sensor system 403 may include sensors inside the vehicle, and may acquire engine operating parameters, vehicle body vibration data, and vehicle interior noise data through the sensor system 403 .

[0084] Control system 404 may include a vehicle control unit and a software system that implements the vehicle noise reduction method. Control system 404 may also include hardware systems such as a throttle, steering wheel, and seat belt system. Furthermore, control system 404 may include additional or alternative components other than those shown and described. Alternatively, some of the components shown above may be reduced.

[0085] Control system 404 interacts with internal vehicle sensors, external sensors, other computer systems, or users via peripheral devices 405. Peripheral devices 405 may include a wireless communication system, an onboard computer, a microphone, and / or a speaker.

[0086] In some embodiments, peripheral devices 405 provide a means for a user of control system 404 to interact with a user interface. For example, an onboard computer can send prompts to the vehicle's user. The user interface can also operate the onboard computer to receive user input. The onboard computer can be operated via a touch screen. In other cases, peripheral devices can provide a means for communicating with other devices located within the vehicle. For example, a microphone can receive audio (e.g., voice commands or other audio input) from a user of control system 404. Similarly, a speaker can output audio to the user of control system 404.

[0087] A wireless communication system can communicate wirelessly with one or more devices directly or via a communication network. For example, a wireless communication system can communicate using a cellular network, WiFi, or a wireless local area network (WLAN), or can directly communicate with devices using an infrared link, Bluetooth, or ZigBee.

[0088] The power supply 406 can provide power to various components of the vehicle. The power supply 406 can be a rechargeable lithium-ion or lead-acid battery.

[0089] Some or all functions of the vehicle noise reduction method are controlled by a computer system 407. The computer system 407 may include at least one processor that executes instructions stored in a non-transitory computer-readable medium such as a memory. The computer system 407 provides execution code for implementing the vehicle noise reduction method.

[0090] The processor can be any conventional processor, such as a commercially available central processing unit (CPU). Alternatively, the processor can be a dedicated device such as an application specific integrated circuit (ASIC) or other hardware-based processor. Those skilled in the art will appreciate that the processor, computer, or memory can actually include multiple processors, computers, or memories that may or may not be stored in the same physical housing. For example, the memory can be a hard drive or other storage medium that is located in a housing different from the computer. Therefore, references to processors or computers will be understood to include references to a collection of processors or computers or memories that may or may not operate in parallel. Different from using a single processor to perform the steps described herein, each of some components such as a steering assembly and a deceleration assembly can have its own processor, and the processor only performs calculations related to the functions specific to the component.

[0091] User interface 408 is used to provide information to or receive information from a user of the vehicle. Optionally, user interface 408 may include one or more input / output devices within the set of peripheral devices 405, such as a wireless communication system, an onboard computer, a microphone, and a speaker.

[0092] It should be understood that the above components are only examples. In actual applications, components in the above modules or systems may be added or deleted according to actual needs. Figure 4 It should not be understood as limiting the embodiments of the present application.

[0093] Reference below Figure 5 , which shows a schematic structural diagram of a computer system 500 suitable for implementing an embodiment of the present invention. Figure 5 The computer system shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0094] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage unit 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the system 500 are also stored in the RAM 503. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0095] The following components are connected to the I / O interface 505: an input section 506; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 508 including a hard disk; and a communication section 509 including a network interface card such as a LAN card or a modem. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 510 as needed, so that a computer program read therefrom can be installed in the storage section 508 as needed.

[0096] In particular, according to the embodiments disclosed in the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 509, and / or installed from a removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, the above-mentioned functions defined in the system of the present invention are performed.

[0097] It should be noted that the computer-readable medium described in the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media can include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, or any suitable combination thereof.

[0098] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0099] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment, or may exist independently and not be incorporated into the device. The computer-readable medium carries one or more programs. When executed by a device, the device causes the device to: obtain noise assessment data of a vehicle; wherein the noise assessment data includes one or more of operating parameters of noise sources, vehicle body vibration data, and noise data within the vehicle; use a trained noise spectrum prediction model to predict the noise spectrum of the vehicle interior space in a future time period based on the noise assessment data; divide the noise spectrum into multiple frequency bands; and for each frequency band, perform the following: determine a sound wave signal with a phase opposite to that of the frequency band, and control a noise reduction device matched to the frequency band to generate a sound wave signal, thereby performing active noise reduction on the vehicle interior space.

[0100] It should be understood by those skilled in the art that various modifications, combinations, sub-combinations, and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A vehicle noise reduction method, characterized in that: include: Acquiring noise evaluation data of the vehicle; wherein the noise evaluation data includes one or more of operating parameters of the noise source, vehicle body vibration data, and noise data inside the vehicle; Using the trained noise spectrum prediction model and based on the noise assessment data, predict the noise spectrum of the vehicle interior space in a future time period; Dividing the noise spectrum into multiple frequency bands; For each frequency band, the following steps are performed: determining a sound wave signal with a phase opposite to that of the frequency band, and controlling a noise reduction device matched to the frequency band to generate the sound wave signal; so as to perform active noise reduction on the interior space of the vehicle.

2. The vehicle noise reduction method according to claim 1, characterized in that: Further including: Acquiring historical data used for training the noise spectrum prediction model, wherein the historical data includes: historical operating parameters of the vehicle noise source, historical vibration parameters of the vehicle body, and historical noise data inside the vehicle; Add synchronized timestamps to each type of historical data to generate synchronized training data; The noise spectrum prediction model is trained using synchronized training data, wherein the noise spectrum prediction model includes a first correlation between the historical operating parameters of the vehicle noise source and the historical noise data; and / or a second correlation between the historical vibration parameters of the vehicle body and the historical noise data; The predicting the noise spectrum of the vehicle interior space in the future time period includes: predicting the noise spectrum of the vehicle interior space in the future time period based on the first association relationship and / or the second association relationship.

3. The vehicle noise reduction method according to claim 2, characterized in that: Further including: For the noise spectrum prediction model, perform the following iterative operations of optimizing the model: Collect the target noise spectrum after noise reduction in the vehicle interior space; evaluating a training effect of the noise spectrum prediction model using the target noise spectrum; And based on the evaluated training effect, the model parameters of the noise spectrum prediction model are adjusted.

4. The vehicle noise reduction method according to claim 1, characterized in that: Further including: Analyzing the phase difference between the noise data signal collected in real time and the acoustic wave signal; dynamically superimposing the phase difference as a phase offset on the acoustic wave signal using a least mean square algorithm; and / or, For each of the frequency bands: measuring the delay data corresponding to the frequency band; establishing a correspondence between the delay data and the frequency corresponding to the frequency band; based on the current ambient temperature of the vehicle and the correlation between the temperature and the delay data; using a Kalman filter to dynamically correct the phase difference in the correspondence; and superimposing the phase difference as a phase offset on the sound wave signal.

5. A vehicle noise reduction system, characterized in that: include: A variety of collection devices, controllers and noise reduction devices for collecting noise assessment data; among them, The multiple acquisition devices are used to respectively acquire multiple noise evaluation data of the vehicle; wherein the noise evaluation data includes one or more of operating parameters of the noise source, vehicle body vibration data, and noise data inside the vehicle; The controller is configured to use a trained noise spectrum prediction model to predict the noise spectrum of the vehicle interior space in a future time period based on the noise assessment data; divide the noise spectrum into multiple frequency bands; and, for each frequency band, perform the following operations: determining a sound wave signal having a phase opposite to that of the frequency band; and controlling a noise reduction device matched to the frequency band to generate the sound wave signal, thereby performing active noise reduction on the vehicle interior space.

6. The vehicle noise reduction system according to claim 5, characterized in that: A variety of acquisition devices include: a first collecting device for collecting operating parameters of the noise source; a second collecting device for collecting body vibration data of the vehicle; A third collecting device is used to collect noise data inside the vehicle.

7. The vehicle noise reduction system according to claim 5, characterized in that: The noise reduction device is a ceramic pressed disc array; A plurality of groups of the noise reduction devices are respectively attached to the housing of the noise source; wherein each group of the noise reduction devices is independently controlled by the controller.

8. The vehicle noise reduction system according to claim 7, characterized in that: The spacing between adjacent ceramic pressing plates included in the same set of noise reduction devices is set to 1 / 4 of the vibration wavelength, where the vibration wavelength is the dominant wavelength of the vibration of the housing surface of the noise source; and / or, Different groups of noise reduction devices are used to generate sound wave signals required for noise reduction for different frequency bands; and / or, The stiffness or thickness of ceramic pressed disc arrays configured in different frequency bands is different; and / or, Each group of the noise reduction devices is integrated with an independent circuit; The controller drives the noise reduction device to operate based on a target voltage that satisfies the operation of the noise reduction device by controlling the independent circuit. The target voltage is obtained by boosting the original voltage of the vehicle battery through a DC voltage converter.

9. The vehicle noise reduction system according to claim 8, characterized in that: Regarding the structure in which the noise reduction device is integrated with an independent circuit, the high-voltage driving line corresponding to the independent circuit is a double-shielded coaxial line; Preferably, The controller is further configured to adjust the target voltage of one or more groups of noise reduction devices in real time using a field programmable gate array module based on current noise evaluation data; Preferably, Each group of independent circuits is equipped with a heat dissipation device.

10. A vehicle, characterized in that: The vehicle noise reduction system comprises the vehicle noise reduction system according to any one of claims 5 to 9.

Images