Vehicle interior active noise reduction method and device

Abstract

The invention provides a vehicle interior active noise reduction method and device which are applied to the technical field of vehicle interior noise control, and the method comprises the steps that in the vehicle driving process, multiple types of first noise signals of a vehicle at the first moment are collected; and according to the first noise signal and the driving condition of the vehicle at the first moment, determining predicted noise information of the vehicle at the second moment. And according to the predicted noise information, determining a control parameter of the adaptive filter operating at the second moment. And at a second moment, filtering the collected second noise signal by using an adaptive filter configured with control parameters to obtain a noise suppression signal so as to actively reduce noise in the vehicle, the problems that a traditional vehicle interior active noise reduction method is uneven in space noise reduction effect, response is delayed under the dynamic working condition, the complex noise modeling capacity is insufficient, and the system robustness is poor can be solved.

Description

Technical Field

[0001] This application relates to the field of vehicle interior noise control technology, and in particular to an active noise reduction method and device for vehicle interiors. Background Technology

[0002] With the rapid development of new energy vehicles and intelligent connected vehicles, users have placed unprecedentedly high demands on the quietness and comfort of the vehicle cabin. Traditional passive noise reduction technology, which mainly blocks and absorbs noise by adding sound insulation materials and optimizing sound absorption structures, has reached inherent bottlenecks in terms of vehicle lightweighting, cost control, and low-frequency noise suppression. Specifically, passive noise reduction has little effect on suppressing major low-frequency noise sources in the vehicle, such as engine low-frequency order noise and tire noise. Moreover, the extensive use of sound insulation materials to achieve limited noise reduction significantly increases the overall vehicle weight and cost, which contradicts the lightweight and high-efficiency development requirements of new energy vehicles.

[0003] To overcome the shortcomings of passive noise cancellation, active noise cancellation technology has been introduced into the automotive field. However, current mass-produced or research-based in-vehicle active noise cancellation systems, especially those based on classic adaptive filtering algorithms, still have significant shortcomings in the complex real-world driving environment. These systems often rely on a limited number of sensors, making it difficult to fully perceive the non-uniform three-dimensional sound field within the cabin, resulting in spatial blind spots in noise cancellation and uneven passenger experience. Furthermore, when faced with rapid noise changes caused by dynamic conditions such as vehicle acceleration and deceleration, traditional algorithms have slow convergence speeds and are prone to tracking delays, leading to a deterioration in instantaneous noise cancellation performance. In addition, existing algorithms are mostly based on linear assumptions, lacking effective modeling and processing capabilities for nonlinear factors and non-stationary noise present in real-world vehicles, and their robustness is often insufficient when sensors fail or road conditions change drastically.

[0004] Therefore, there is an urgent need for an active noise reduction method for vehicle interiors to address the problems of uneven spatial noise reduction effect, slow response under dynamic conditions, insufficient ability to model complex noise, and poor system robustness of traditional active noise reduction methods for vehicle interiors. Summary of the Invention

[0005] The purpose of this application is to provide a method and device for active noise reduction inside a vehicle, which solves the problems of uneven spatial noise reduction effect, response lag under dynamic conditions, insufficient ability to model complex noise, and poor system robustness of traditional active noise reduction methods inside vehicles.

[0006] In a first aspect, embodiments of this application provide a method for active noise reduction inside a vehicle. The method includes: during vehicle operation, collecting multiple types of first noise signals of the vehicle at a first moment; determining predicted noise information of the vehicle at a second moment based on the first noise signals and the vehicle's operating conditions at the first moment; determining control parameters for an adaptive filter to operate at the second moment based on the predicted noise information; and filtering the collected second noise signals using the adaptive filter configured with the control parameters at the second moment to obtain a noise suppression signal for active noise reduction inside the vehicle.

[0007] The active noise reduction method for vehicle interiors provided in this application collects various types of first noise signals at a first moment during vehicle operation. Based on the first noise signals and the vehicle's driving conditions at the first moment, it determines the predicted noise information for the vehicle at a second moment. Furthermore, based on this predicted noise information, the control parameters of an adaptive filter are pre-optimized. This allows the adaptive filter to efficiently filter the real-time collected second noise signals under these control parameters when dealing with the actual noise at the second moment, generating a more accurate noise suppression signal. After being played through the vehicle's speakers, this noise suppression signal can achieve more complete destructive interference with the target noise within the vehicle cabin, thereby significantly reducing the noise level at the occupant's ear position and improving the quietness of the vehicle interior.

[0008] One possible implementation involves determining the predicted noise information of the vehicle at a second time step based on a first noise signal and the vehicle's driving conditions at a first time step. This includes fusing multiple types of first noise signals to obtain a fused signal of the vehicle's internal noise environment. The predicted noise information is then determined based on the vehicle's driving conditions at the first time step and the fused signal.

[0009] One possible implementation involves determining the predicted noise information based on the vehicle's driving conditions at a first moment and the fused signal, including: identifying the vehicle's dominant noise pattern based on the driving conditions; and inputting the dominant noise pattern and the fused signal into a pre-built prediction model to obtain the predicted noise information.

[0010] One possible implementation involves identifying the dominant noise pattern of the vehicle based on the current driving conditions, including: acquiring the vehicle's driving parameters under the driving conditions. These driving parameters include one or more of the following: vehicle speed, engine speed, and throttle opening. The dominant noise pattern of the vehicle is then determined based on the vehicle speed, engine speed, and throttle opening.

[0011] One possible implementation involves inputting the dominant noise pattern and the fused signal into a pre-built prediction model to obtain predicted noise information. This includes: determining a set of weight coefficients for the fused signal based on the dominant noise pattern. The set of weight coefficients includes multiple weight coefficients. Each weight coefficient corresponds to a type of noise signal in the fused signal. Based on the fused signal and the set of weight coefficients, the time-frequency spatial features of the fused signal are extracted. Based on the time-frequency spatial features and the driving parameters of the current driving condition, the predicted noise information is determined.

[0012] One possible implementation involves constructing a predictive model by using third noise signals collected from various vehicle models under different driving conditions, along with corresponding noise suppression signals, to build a general predictive model. After deploying the general predictive model to the vehicle, it is adjusted based on a fourth noise signal collected in real-time by the vehicle and the corresponding driving conditions to obtain the final predictive model.

[0013] One possible implementation involves determining the control parameters of the adaptive filter for operation at a second time step based on predicted noise information. This includes: obtaining first historical control parameters of the adaptive filter at the end of the first time step; and adjusting the first historical control parameters using the predicted noise information to obtain the control parameters for the second time step.

[0014] One possible implementation involves filtering the acquired second noise signal using an adaptive filter configured with control parameters to obtain a noise-suppressed signal. This includes: acquiring the second noise signal at a second time point. The noise signal includes a reference noise signal. The reference noise signal is then input to the adaptive filter configured with control parameters to obtain the noise-suppressed signal.

[0015] One possible implementation of the noise reduction method in a vehicle interior provided in this application embodiment further includes: when playing the noise suppression signal at the second time moment, acquiring the residual error noise signal inside the vehicle. The control parameters of the adaptive filter are updated based on the residual error noise signal to obtain the second historical control parameters at the end of the second time moment, which are then used to optimize the noise reduction effect of the adaptive filter at the next time moment.

[0016] Secondly, embodiments of this application provide an active noise reduction device for vehicle interiors, which includes a data acquisition module, a determination module, and a filtering module.

[0017] The acquisition module is used to collect various types of first noise signals of the vehicle at the first moment during the vehicle's operation.

[0018] The determination module is used to determine the predicted noise information of the vehicle at the second time based on the first noise signal and the vehicle's driving conditions at the first time.

[0019] The determination module is also used to determine the control parameters of the adaptive filter to be run at the second time step based on the predicted noise information.

[0020] The filtering module is used to filter the acquired second noise signal using an adaptive filter configured with control parameters at the second moment to obtain a noise suppression signal, so as to actively reduce noise inside the vehicle.

[0021] One possible implementation involves a determining module that, when determining the predicted noise information of the vehicle at a second time based on a first noise signal and the vehicle's driving conditions at a first time, specifically performs the following: fusing multiple types of first noise signals to obtain a fused signal of the vehicle's internal noise environment; and determining the predicted noise information based on the vehicle's driving conditions at the first time and the fused signal.

[0022] One possible implementation involves a determination module that, based on the vehicle's driving conditions at a first moment and the fused signal, determines the predicted noise information. Specifically, this module identifies the vehicle's dominant noise pattern based on the driving conditions. The dominant noise pattern and the fused signal are then input into a pre-built prediction model to obtain the predicted noise information.

[0023] One possible implementation involves a module that, when identifying the dominant noise mode of a vehicle based on current driving conditions, specifically acquires the vehicle's driving parameters under those conditions. These driving parameters include one or more of the following: vehicle speed, engine speed, and throttle opening. Based on the vehicle speed, engine speed, and throttle opening, the dominant noise mode of the vehicle is determined.

[0024] One possible implementation involves a determination module that, when inputting the dominant noise pattern and the fused signal into a pre-built prediction model to obtain predicted noise information, specifically performs the following steps: Based on the dominant noise pattern, determines a set of weight coefficients for the fused signal. The set of weight coefficients includes multiple weight coefficients. Each weight coefficient corresponds to a type of noise signal in the fused signal. Based on the fused signal and the set of weight coefficients, extracts the time-frequency spatial features of the fused signal. Based on the time-frequency spatial features and the driving parameters of the current driving condition, determines the predicted noise information.

[0025] One possible implementation involves constructing a predictive model by using third noise signals collected from various vehicle models under different driving conditions, along with corresponding noise suppression signals, to build a general predictive model. After deploying the general predictive model to the vehicle, it is adjusted based on a fourth noise signal collected in real-time by the vehicle and the corresponding driving conditions to obtain the final predictive model.

[0026] One possible implementation involves a determining module that, based on predicted noise information, determines the control parameters for the adaptive filter operating at the second time step. Specifically, this module acquires the first historical control parameters of the adaptive filter at the end of the first time step. The first historical control parameters are then adjusted using the predicted noise information to obtain the control parameters for the second time step.

[0027] One possible implementation involves a filtering module that, when filtering the acquired second noise signal using an adaptive filter configured with control parameters to obtain a noise-suppressed signal, specifically: at a second time point, acquiring the second noise signal. The noise signal includes a reference noise signal. The reference noise signal is then input to the adaptive filter configured with control parameters to obtain the noise-suppressed signal.

[0028] In one possible implementation, the noise reduction device inside the vehicle provided in this application embodiment is further configured to: collect residual error noise signals inside the vehicle when playing the noise suppression signal at the second time moment; update the control parameters of the adaptive filter based on the residual error noise signals to obtain second historical control parameters at the end of the second time moment, which are then used to optimize the noise reduction effect of the adaptive filter at the next time moment.

[0029] Thirdly, embodiments of this application provide an active noise cancellation device for vehicle interiors, which has the function of implementing the active noise cancellation method for vehicle interiors according to the first aspect or any possible implementation of the first aspect. This function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described function.

[0030] Fourthly, embodiments of this application provide a computer-readable storage medium storing instructions that, when executed on a computer, enable the computer to perform the vehicle interior active noise reduction method described in the first aspect or any possible implementation thereof.

[0031] Fifthly, embodiments of this application provide a computer program product containing instructions that, when run on a computer, enable the computer to execute the active noise reduction method for vehicle interiors described in the first aspect or any possible implementation thereof.

[0032] The technical effects of any of the design methods in aspects two through five can be found in aspect one or in different possible implementations of aspect one, and will not be repeated here. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0034] Figure 1 A system structure diagram of an active noise cancellation system for vehicle interiors provided in this application embodiment; Figure 2 A specific example diagram of an output module in an active noise cancellation system inside a vehicle, provided in an embodiment of this application; Figure 3 A flowchart of an active noise reduction method for vehicle interior provided in this application embodiment; Figure 4 A specific example diagram of an active noise reduction method for vehicle interior provided in this application embodiment; Figure 5 A schematic diagram of a vehicle interior active noise reduction device provided in this application embodiment; Figure 6 Another system architecture diagram of an active noise cancellation system for vehicle interiors provided in this application embodiment. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0036] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0037] To improve cabin quietness, active noise cancellation technology has been introduced into the automotive field. However, current mass-produced and most research-based automotive active noise cancellation solutions, limited by their inherent technical architecture, still have significant shortcomings when dealing with real and complex driving scenarios. On the one hand, the systems mostly rely on sparsely deployed single-type sensors, making it difficult to build a complete and dynamic perception of the entire cabin sound field. When the vehicle accelerates, turns, or the road surface changes, the distribution and characteristics of noise change rapidly. This control strategy based on limited perception is prone to creating noise cancellation blind spots, leading to an imbalance in the experience between different seats and failing to meet users' expectations for overall quietness.

[0038] On the other hand, the system's control algorithm still largely uses the classic adaptive filtering framework, with fixed parameters and ideal model assumptions. When faced with non-stationary and nonlinear noise such as sudden changes in engine order and random wind noise, it exhibits slow convergence and poor tracking capabilities. More importantly, the simplistic approach of adding sensors to improve perception capabilities directly exacerbates the system's demanding requirements for computing power and real-time performance. Under the limited computing resources of automotive embedded platforms, traditional processing methods often face a dilemma: either sacrifice the bandwidth and effectiveness of noise reduction, or accept unacceptable latency. The latter will directly lead to system failure, or even produce the counterproductive effect of increasing noise despite noise reduction efforts.

[0039] Based on this, embodiments of this application provide a method and apparatus for active noise reduction inside a vehicle. The method includes: collecting multiple types of first noise signals from the vehicle at a first moment during vehicle operation; determining predicted noise information for the vehicle at a second moment based on the first noise signals and the vehicle's operating conditions at the first moment; determining control parameters for an adaptive filter to operate at the second moment based on the predicted noise information; and filtering the collected second noise signals using the adaptive filter configured with the control parameters at the second moment to obtain a noise suppression signal for active noise reduction inside the vehicle.

[0040] The active noise reduction method for vehicle interiors provided in this application collects various types of first noise signals at a first moment during vehicle operation. Based on the first noise signals and the vehicle's driving conditions at the first moment, it determines the predicted noise information for the vehicle at a second moment. Furthermore, based on this predicted noise information, the control parameters of an adaptive filter are pre-optimized. This allows the adaptive filter to efficiently filter the real-time collected second noise signals under these control parameters when dealing with the actual noise at the second moment, generating a more accurate noise suppression signal. After being played through the vehicle's speakers, this noise suppression signal can achieve more complete destructive interference with the target noise within the vehicle cabin, thereby significantly reducing the noise level at the occupant's ear position and improving the quietness of the vehicle interior.

[0041] The methods provided in the embodiments of this application will now be described in conjunction with the specific accompanying drawings.

[0042] On one hand, embodiments of this application provide an active noise cancellation system for vehicle interiors. For example... Figure 1 As shown, the vehicle interior active noise cancellation system 100 may include: a sensor array 101, a controller 102, and an output device 103.

[0043] The sensor array 101 is used to collect various types of noise signals from the vehicle and send the collected noise signals to the controller 102. For example, the sensor array 101 may include a microphone, an accelerometer, a fiber optic vibration sensor, and a sound pressure sensor. The microphone may be a MEMS microphone.

[0044] For example, microphones can be positioned in the headliner and under the dashboard to capture airborne noise; accelerometers can be mounted on the chassis and seat frame to monitor structural vibration noise sources; and sound pressure sensors can be located inside the doors and in the trunk to detect local sound pressure changes.

[0045] The controller 102 is communicatively connected to the sensor array 101. The controller 102 receives various types of noise signals collected by the sensor array 101 and simultaneously acquires vehicle driving condition parameters in real time via the vehicle network. For example, parameters characterizing the vehicle's driving conditions can be obtained via the CAN bus. These parameters may include, but are not limited to, vehicle speed, engine speed, motor speed, throttle opening, brake pedal status, transmission gear position, steering wheel angle, and longitudinal / lateral acceleration.

[0046] After receiving various types of noise signals and driving conditions, the controller 102 uses the in-vehicle active noise reduction method provided in this application to fuse the various types of noise signals and combine them with the driving conditions to predict the predicted noise information for the next moment, i.e., the trend of unmeasured noise change for the next moment. Based on the predicted noise information, the controller calculates the optimized control parameters of the adaptive filter, finally generates a noise suppression signal, and sends the noise suppression signal to the output device 103.

[0047] The output device 103 is communicatively connected to the controller 102. The output device 103 receives a noise suppression signal sent by the controller 102 and plays the noise suppression signal to generate an active sound field that cancels out noise inside the vehicle. For example, the output device 103 can be a vehicle speaker. This vehicle speaker can be deployed in multiple preset locations inside the vehicle, such as doors, footwell, headliner, and seats.

[0048] For example, such as Figure 2 As shown, Figure 2This is a specific example diagram of an output device provided in an embodiment of this application. The output device 103 can be integrated inside a vehicle seat headrest. The output device 103 may include an actuator 201, a transmission plate 202, seat interior foam 203, seat cover 204, and a support structure 205.

[0049] The actuator 201 can be a piezoelectric ceramic actuator or a moving-coil micro actuator. The actuator is fixed to the internal support structure of the headrest and generates corresponding mechanical vibrations in response to the noise suppression signal sent by the controller 102.

[0050] The transmission plate 202, made of a rigid, lightweight material, has one side physically coupled to the vibration of the actuator, and the other side is precision-machined into a curved shape that perfectly fits the inner foam and skin surface of the headrest. The transmission plate is used to efficiently convert the point or small-area vibration of the actuator into a large-area surface vibration and transmit it to the skin.

[0051] The seat interior foam 203 has pre-reserved grooves or cavities that match the shape of the transmission plate and actuator, which are used to securely embed the transmission plate and actuator during seat assembly.

[0052] The seat cover 204 covers the foam and transmission plate, and maintains natural tension in the corresponding area of ​​the transmission plate. Driven by the transmission plate, the cover acts as a whole vibration radiation surface, directly radiating sound waves into the space around the occupant's head.

[0053] The support structure 205 is used to provide a stable mechanical mounting base and vibration isolation for the output device 103.

[0054] It should be noted that the above Figure 1 The illustrated vehicle interior active noise reduction system 100 is merely an example illustrating the application scenario of the solution in this application, and is not intended to limit the application scenario of the solution in this application.

[0055] On the one hand, embodiments of this application provide an active noise reduction method for vehicle interiors, which can be implemented by... Figure 1 The vehicle interior active noise cancellation system 100 shown is in operation. For example... Figure 3 As shown, the method may include the following steps.

[0056] S301 collects various types of first noise signals of the vehicle at the first moment during vehicle operation.

[0057] Specifically, during vehicle operation, multiple types of primary noise signals are simultaneously collected by various sensor arrays deployed at multiple locations inside and outside the vehicle.

[0058] For example, a first set of microphones positioned in the headliner captures airborne noise signals from the windshield and roof area. A second set of microphones attached below the dashboard collects engine noise signals transmitted through the front bulkhead structure from the engine and transmission. An accelerometer mounted on the chassis acquires structural vibration noise signals caused by tire and road excitation. A vibration accelerometer fixed to the seat frame monitors broadband road noise and suspension vibration signals transmitted from the chassis to the vehicle body. Sound sensors located on the inside of the doors and in the trunk detect local sound pressure fluctuation signals.

[0059] This process collects various types of first noise signals from multiple locations within the vehicle, collectively forming a panoramic perception of the three-dimensional sound field and vibration state inside the cabin. This solves the problem of inaccurate noise source localization caused by the single sensor location in related technologies, ensuring the comprehensiveness and accuracy of noise signal collection, and providing the original data foundation for subsequent prediction of noise information at the second moment.

[0060] S302, based on the first noise signal and the vehicle's driving conditions at the first moment, determine the predicted noise information of the vehicle at the second moment.

[0061] The predicted noise information may include one or more of the following: predicted spectrum, predicted amplitude, and predicted phase change trend.

[0062] Specifically, multiple types of primary noise signals are fused to obtain a fused signal of the vehicle's internal noise environment. Based on the vehicle's driving conditions at the first moment and the fused signal, the predicted noise information is determined.

[0063] For example, the various types of first noise signals collected are first synchronized and preprocessed in the time domain. For instance, microphone signals, accelerometer signals, and sound sensor signals from different locations are time-aligned and then converted to the frequency domain for feature extraction. The extracted features are then weighted and fused to obtain a fused signal of the vehicle's internal noise environment. This fused signal, along with the vehicle's driving parameters at the first moment, is then input into a pre-trained prediction model to obtain predicted noise information.

[0064] Among them, driving condition parameters can be obtained through the CAN bus. These driving condition parameters may include, but are not limited to: vehicle speed, engine speed, motor speed, throttle opening, brake pedal status, transmission gear, steering wheel angle, longitudinal / lateral acceleration, etc.

[0065] One possible implementation, the step of determining the predicted noise information based on the vehicle's driving conditions at a first moment and the fused signal, may include: identifying the dominant noise pattern of the vehicle based on the driving conditions; and inputting the dominant noise pattern and the fused signal into a pre-built prediction model to obtain the predicted noise information.

[0066] The step of identifying the dominant noise mode of the vehicle based on the current driving conditions includes: acquiring the vehicle's driving parameters under the driving conditions. These driving parameters include one or more of the following: vehicle speed, engine speed, and throttle opening. The dominant noise mode of the vehicle is determined based on the vehicle speed, engine speed, and throttle opening.

[0067] For example, when the engine speed is approximately 800 rpm and the vehicle speed is 0 km / h, the current driving condition can be determined to be idling, with the dominant noise mode being low-frequency engine noise. When the vehicle speed is approximately 40 km / h and the throttle is applied smoothly, the current driving condition can be determined to be low-speed cruising, with the dominant noise mode being tire noise and road noise. When the vehicle speed is approximately 100 km / h and the driving is stable, the current driving condition can be determined to be high-speed cruising, with the dominant noise mode being a mixture of broadband wind noise and tire noise. When the vehicle speed rapidly increases and the engine load changes drastically, the current driving condition can be determined to be acceleration, with the noise mode being a rapidly evolving non-stationary mixed noise.

[0068] The step of inputting the dominant noise pattern and the fused signal into a pre-built prediction model to obtain predicted noise information may include determining a set of weight coefficients for the fused signal based on the dominant noise pattern. The set of weight coefficients includes multiple weight coefficients. Each weight coefficient corresponds to a type of noise signal in the fused signal. Based on the fused signal and the set of weight coefficients, the time-frequency spatial features of the fused signal are extracted. Based on the time-frequency spatial features and the driving parameters of the current driving condition, the predicted noise information is determined.

[0069] For example, under idling conditions, the weight of airborne noise signals collected by the second set of microphones attached to the lower part of the instrument panel can be increased; at the same time, the weight of broadband road noise and suspension vibration signals collected by the vibration accelerometer fixed to the seat frame can be increased; and the weight of noise signals collected by other sensors that are sensitive to wind noise and road noise (such as roof microphones and chassis accelerometers) can be reduced accordingly.

[0070] Under low-speed cruising conditions, the weight of structural vibration noise signals collected by the accelerometer mounted on the chassis is increased; the weight of broadband road noise and suspension vibration signals transmitted from the chassis to the vehicle body collected by the vibration accelerometer fixed to the seat frame is increased; and the fusion weight of sensors sensitive to wind noise and engine noise (such as the first set of microphones in the headliner, the second set of microphones attached to the lower part of the instrument panel, and the sound sensors on the inside of the doors and the trunk) is reduced.

[0071] Under high-speed cruising conditions, the weight of airborne noise signals collected by the first set of microphones installed in the roof liner is increased; the weight of local sound pressure fluctuation signals of sound sensors installed on the inside of the doors and in the trunk is increased; and the weight of broadband road noise and suspension vibration signals transmitted from the chassis to the vehicle body collected by the vibration accelerometer fixed to the seat frame is maintained.

[0072] During acceleration, engine speed, engine load, and vehicle speed all change rapidly and non-linearly, resulting in significant non-stationary characteristics of in-vehicle noise. The dominant noise pattern quickly shifts from engine-order noise to a complex mixture of engine, intake / exhaust, tire, and wind noise. A prediction model based on a CNN-RNN hybrid network is used for processing in this scenario. Real-time signals from all sensors and acceleration parameters (such as engine speed and its rate of change, instantaneous vehicle speed, and throttle opening) are synchronously input into the prediction model. The CNN extracts transient features strongly correlated with acceleration from the multi-sensor fused signals, such as the growth patterns of engine harmonic energy, broadband noise characteristics caused by turbocharger intervention, and the transmission characteristics of chassis vibration energy as a function of vehicle speed. The RNN part analyzes the changing trends of these transient features based on time series data, predicting the changing trends of major noise components (such as engine second and fourth harmonics) over the next few hundred milliseconds, thus obtaining the predicted noise signal.

[0073] Furthermore, in order to achieve cross-vehicle versatility and rapid deployment capability, this application adopts a pre-built general prediction model, which is then deployed to the vehicle and fine-tuned to obtain a prediction model suitable for the specific vehicle to be deployed.

[0074] Specifically, the prediction model construction process includes: constructing a general prediction model using third noise signals collected from various vehicle models under various driving conditions and corresponding noise suppression signals. After deploying the general prediction model to the vehicle, the general prediction model is adjusted based on the fourth noise signal collected in real time by the vehicle and the corresponding driving conditions to obtain the prediction model.

[0075] One possible implementation involves collecting massive amounts of noise data from various vehicle types (such as sedans, SUVs, MPVs, and commercial vehicles) under diverse driving conditions (e.g., urban roads, highway cruising, rough roads, rapid acceleration / deceleration) as training samples, i.e., the third noise signal. Simultaneously, the optimal noise suppression signal generated under each driving condition, after being debugged by a professional ANC system, is recorded as a supervision label. Using this large-scale dataset, the prediction model is trained to obtain a general prediction model. This general prediction model can accurately predict the noise change trend in the near future based on multimodal noise signals and driving condition parameters, demonstrating generalization ability.

[0076] It should be noted that the acquisition method of the third noise signal is the same as that of the acquisition method of the first noise signal, and this application will not elaborate on it.

[0077] When deploying an in-vehicle active noise cancellation system to a new target vehicle model, the pre-sequenced general predictive model is directly loaded into the target vehicle's controller. During the initial use phase, while providing normal active noise cancellation, the system collects a vehicle-specific fourth noise signal and corresponding driving conditions. This fourth noise signal and corresponding driving conditions reflect the target vehicle's unique body structure, engine characteristics, and user driving habits. The general predictive model is then fine-tuned online using this fourth noise signal and corresponding driving conditions, achieving efficient active noise cancellation without requiring extensive algorithm calibration for each vehicle model.

[0078] S303 determines the control parameters of the adaptive filter to be used for operation at the second time step based on the predicted noise information.

[0079] One possible implementation involves obtaining the first historical control parameters of the adaptive filter at the end of the first time step. The first historical control parameters are then adjusted using the predicted noise information to obtain the control parameters for the second time step.

[0080] Another possible implementation is that the controller directly inputs the predicted noise information into a pre-trained parameter mapping model and directly outputs the control parameters at the second time step, without relying on historical control parameters.

[0081] S304, at the second moment, the acquired second noise signal is filtered using an adaptive filter configured with control parameters to obtain a noise suppression signal, so as to actively reduce noise inside the vehicle.

[0082] Specifically, at the second time point, a second noise signal is acquired. This noise signal includes a reference noise signal. The reference noise signal is then input to an adaptive filter configured with control parameters to obtain a noise suppression signal.

[0083] One possible implementation involves acquiring a second noise signal in real time at a second moment via a sensor array. This signal includes a reference noise signal acquired by sensors positioned near the noise source and an error noise signal acquired by sensors positioned in the occupant's ear region. The reference noise signal is extracted from this mixed signal. This extracted reference noise signal is then input to an adaptive filter configured with control parameters. The filter performs forward filtering calculations on the input reference noise signal and outputs a noise suppression signal. Finally, the noise suppression signal is converted from digital to analog and amplified before being played through a speaker or actuator, thereby generating an active sound field within the cabin that cancels out the target noise.

[0084] Furthermore, when the noise suppression signal is played at the second time point, the residual error noise signal inside the vehicle is collected. The control parameters of the adaptive filter are updated based on the residual error noise signal to obtain the second historical control parameters at the end of the second time point, which are then used to optimize the noise reduction effect of the adaptive filter at the next time point.

[0085] Specifically, while playing the noise suppression signal, residual error noise signals inside the vehicle are continuously collected via an error microphone. This signal characterizes the deviation between the actual noise reduction effect and the ideal state. Based on this error signal, the control parameters of the filter are iteratively updated online using a preset adaptive algorithm (e.g., filter x least mean square algorithm). This update process continues throughout the second time interval, allowing the filter to fine-tune its output in real time to minimize residual noise. When the second time interval ends, the updated parameters of the filter are saved as the second historical control parameters. These second historical control parameters will serve as the initial historical control parameters for the next noise reduction cycle.

[0086] The active noise reduction method for vehicle interiors provided in this application actively reduces noise signals after receiving multiple types of noise signals, and outputs the results to an algorithm simulation process. A comparison of the signals before and after noise reduction is shown in the figure. Figure 4 As shown, the simulation is based on the MATLAB / Simulink environment to simulate a 50Hz low-frequency noise input. The peak amplitude of the signal before noise reduction is 80dB, and after noise reduction, it drops to below 25dB. The curve shows that the inverted signal effectively cancels the original noise waveform, improves the quietness inside the vehicle, and reduces the impact of noise generated by the vehicle itself on the user.

[0087] The above primarily describes the solutions provided in this application from the perspective of the device's working principle. It is understood that, to achieve the aforementioned functions, the in-vehicle active noise cancellation device includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, based on the algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0088] This application embodiment can divide the vehicle interior active noise cancellation device into functional modules according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module.

[0089] It should be noted that the module division in this embodiment is illustrative and represents only one logical functional division; in actual implementation, other division methods may be used. When dividing functional modules according to their respective functions, Figure 5 A schematic diagram illustrating a possible configuration of the active noise cancellation device for the vehicle interior involved in the above and embodiments is shown. Figure 5 As shown, the active noise reduction device 500 inside the vehicle may include: a data acquisition module 501, a determination module 502, and a filtering module 503.

[0090] The acquisition module 501 is used to support the execution of the vehicle's in-vehicle active noise reduction device 500. Figure 3 S301 is shown in the diagram of an active noise cancellation method inside a vehicle.

[0091] Module 502 is used to support the execution of the vehicle interior active noise cancellation device 500. Figure 3 S302 and S303 are illustrated in the active noise cancellation method for the vehicle interior.

[0092] Filtering module 503 is used to support the execution of the vehicle's in-vehicle active noise cancellation device 500. Figure 3 S304 is shown in the illustration of an active noise cancellation method inside a vehicle.

[0093] One possible implementation involves a determining module that, when determining the predicted noise information of the vehicle at a second time based on a first noise signal and the vehicle's driving conditions at a first time, specifically performs the following: fusing multiple types of first noise signals to obtain a fused signal of the vehicle's internal noise environment; and determining the predicted noise information based on the vehicle's driving conditions at the first time and the fused signal.

[0094] One possible implementation involves a determination module that, based on the vehicle's driving conditions at a first moment and the fused signal, determines the predicted noise information. Specifically, this module identifies the vehicle's dominant noise pattern based on the driving conditions. The dominant noise pattern and the fused signal are then input into a pre-built prediction model to obtain the predicted noise information.

[0095] One possible implementation involves a module that, when identifying the dominant noise mode of a vehicle based on current driving conditions, specifically acquires the vehicle's driving parameters under those conditions. These driving parameters include one or more of the following: vehicle speed, engine speed, and throttle opening. Based on the vehicle speed, engine speed, and throttle opening, the dominant noise mode of the vehicle is determined.

[0096] One possible implementation involves a determination module that, when inputting the dominant noise pattern and the fused signal into a pre-built prediction model to obtain predicted noise information, specifically performs the following steps: Based on the dominant noise pattern, determines a set of weight coefficients for the fused signal. The set of weight coefficients includes multiple weight coefficients. Each weight coefficient corresponds to a type of noise signal in the fused signal. Based on the fused signal and the set of weight coefficients, extracts the time-frequency spatial features of the fused signal. Based on the time-frequency spatial features and the driving parameters of the current driving condition, determines the predicted noise information.

[0097] One possible implementation involves constructing a predictive model by using third noise signals collected from various vehicle models under different driving conditions, along with corresponding noise suppression signals, to build a general predictive model. After deploying the general predictive model to the vehicle, it is adjusted based on a fourth noise signal collected in real-time by the vehicle and the corresponding driving conditions to obtain the final predictive model.

[0098] One possible implementation involves a determining module that, based on predicted noise information, determines the control parameters for the adaptive filter operating at the second time step. Specifically, this module acquires the first historical control parameters of the adaptive filter at the end of the first time step. The first historical control parameters are then adjusted using the predicted noise information to obtain the control parameters for the second time step.

[0099] One possible implementation involves a filtering module that, when filtering the acquired second noise signal using an adaptive filter configured with control parameters to obtain a noise-suppressed signal, specifically: at a second time point, acquiring the second noise signal. The noise signal includes a reference noise signal. The reference noise signal is then input to the adaptive filter configured with control parameters to obtain the noise-suppressed signal.

[0100] In one possible implementation, the noise reduction device inside the vehicle provided in this application embodiment is further configured to: collect residual error noise signals inside the vehicle when playing the noise suppression signal at the second time moment; update the control parameters of the adaptive filter based on the residual error noise signals to obtain second historical control parameters at the end of the second time moment, which are then used to optimize the noise reduction effect of the adaptive filter at the next time moment.

[0101] It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0102] The vehicle interior active noise cancellation device 500 provided in this application embodiment is used to perform the above-mentioned... Figure 3 The active noise cancellation method for vehicle interiors shown can therefore achieve the same effect as the active noise cancellation method for vehicle interiors described above.

[0103] This application also provides an active noise cancellation device for vehicle interiors, which can perform the active noise cancellation method and related steps for vehicle interiors described in the above method embodiments.

[0104] This application also provides a computer-readable storage medium storing instructions that, when executed, perform the vehicle interior active noise reduction method and related steps in the above method embodiments.

[0105] This application also provides a computer program product that, when run on a computer, causes the computer to execute the active noise reduction method and related steps inside the vehicle described in the above method embodiments.

[0106] In some embodiments, the methods shown in this application can be implemented as computer program instructions encoded in a machine-readable format on a computer-readable storage medium or on other non-transitory media or articles of art.

[0107] This application also provides an active noise cancellation system 100 for vehicle interiors, such as... Figure 6 As shown, the vehicle interior active noise cancellation system 100 includes at least one processor 601 and at least one interface circuit 602.

[0108] As an example, when the in-vehicle active noise cancellation system 100 includes a processor and an interface circuit, the processor can be... Figure 6 The processor 601 shown in the solid box (or the processor 601 shown in the dashed box) can be an interface circuit. Figure 6 The interface circuit 602 is shown in the solid box (or the interface circuit 602 shown in the dashed box). When the vehicle interior active noise cancellation system 100 includes two processors and two interface circuits, then the two processors include... Figure 6 The processor 601 shown in the solid box and the processor 601 shown in the dashed box, these two interface circuits include Figure 6 Interface circuit 602 is shown in both solid and dashed boxes. No limitations are imposed on this.

[0109] Processor 601 and interface circuit 602 can be interconnected via a line. For example, interface circuit 602 can be used to receive signals. Alternatively, interface circuit 602 can be used to send signals to other devices (e.g., processor 601). For instance, interface circuit 602 can read computer instructions stored in memory and send those instructions to processor 601. Processor 601 executes the instructions and, in conjunction with input / output devices, implements the various steps in the above embodiments, such as implementing... Figure 3 and Figure 4 The methods illustrated are the steps performed in the embodiments shown. Of course, the in-vehicle active noise cancellation system may also include other discrete components, and this application embodiment does not specifically limit this.

[0110] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0111] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0112] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0113] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0114] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, or the part that contributes to it, or all or part of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0115] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for active noise reduction inside a vehicle, characterized in that, The method includes: During vehicle operation, multiple types of first noise signals of the vehicle are collected at a first moment; Based on the first noise signal and the vehicle's driving conditions at the first moment, the predicted noise information of the vehicle at the second moment is determined; Based on the predicted noise information, control parameters for the adaptive filter to operate at the second time point are determined; At the second moment, the acquired second noise signal is filtered using an adaptive filter configured with the control parameters to obtain a noise suppression signal, thereby performing active noise reduction inside the vehicle.

2. The method according to claim 1, characterized in that, The step of determining the predicted noise information of the vehicle at the second time moment based on the first noise signal and the vehicle's driving conditions at the first time moment includes: The first noise signals of various types are fused to obtain the fused signal of the vehicle interior noise environment; The predicted noise information is determined based on the vehicle's driving conditions at the first moment and the fused signal.

3. The method according to claim 2, characterized in that, The step of determining the predicted noise information based on the vehicle's driving conditions at the first moment and the fused signal includes: Based on the driving conditions, identify the dominant noise pattern of the vehicle; The dominant noise pattern and the fused signal are input into a pre-built prediction model to obtain the predicted noise information.

4. The method according to claim 3, characterized in that, The step of identifying the dominant noise pattern of the vehicle based on the driving conditions includes: The vehicle's driving parameters under the driving conditions are obtained; the driving parameters include one or more of the following: vehicle speed, engine speed, and throttle opening. The dominant noise mode of the vehicle is determined based on the vehicle speed, the engine speed, and the throttle opening.

5. The method according to claim 3, characterized in that, The step of inputting the dominant noise mode and the fused signal into a pre-built prediction model to obtain the predicted noise information includes: Based on the dominant noise pattern, a set of weighting coefficients for the fused signal is determined; the set of weighting coefficients includes multiple weighting coefficients; each weighting coefficient corresponds to a type of noise signal in the fused signal. Based on the fused signal and the set of weight coefficients, the time-frequency spatial features of the fused signal are extracted. The predicted noise information is determined based on the time-frequency domain spatial characteristics and the driving parameters of the driving conditions.

6. The method according to claim 3, characterized in that, The process of constructing the prediction model includes: A general prediction model is constructed by using third noise signals collected from various vehicle models under various driving conditions and corresponding noise suppression signals. After the general prediction model is deployed to the vehicle, the general prediction model is adjusted based on the fourth noise signal collected by the vehicle in real time and the driving conditions corresponding to the fourth noise signal to obtain the prediction model.

7. The method according to claim 1, characterized in that, The step of determining the control parameters for the adaptive filter to operate at the second time moment based on the predicted noise information includes: Obtain the first historical control parameters of the adaptive filter at the end of the first time step; The first historical control parameters are adjusted using the predicted noise information to obtain the control parameters at the second time point.

8. The method according to claim 1, characterized in that, The step of filtering the acquired second noise signal using an adaptive filter configured with the control parameters to obtain a noise suppression signal includes: At the second moment, the second noise signal is acquired; the noise signal includes a reference noise signal; The reference noise signal is input to the adaptive filter configured with the control parameters to obtain the noise suppression signal.

9. The method according to claim 1, characterized in that, The method further includes: When the noise suppression signal is played at the second moment, the residual error noise signal inside the vehicle is collected; The control parameters of the adaptive filter are updated based on the residual error noise signal to obtain the second historical control parameters at the end of the second time moment, which are then used to optimize the noise reduction effect of the adaptive filter in the next time moment.

10. An active noise reduction device for vehicle interiors, characterized in that, The device includes: The acquisition module is used to acquire multiple types of first noise signals of the vehicle at a first moment during the vehicle's operation. The determination module is used to determine the predicted noise information of the vehicle at a second time based on the first noise signal and the vehicle's driving conditions at the first time. The determining module is further configured to determine the control parameters of the adaptive filter to be run at the second time step based on the predicted noise information. The filtering module is used to filter the acquired second noise signal using an adaptive filter configured with the control parameters at the second time point to obtain a noise suppression signal, so as to actively reduce noise inside the vehicle.

Images