Method for optimizing vehicle abnormal noise, vehicle and server

Abstract

The embodiment of the application provides a vehicle abnormal sound optimization method, a vehicle and a server. The vehicle abnormal sound optimization method is applied to the vehicle and includes the following steps: in response to receiving abnormal sound information of the vehicle, determining sensors and controllers of the vehicle according to the abnormal sound information; obtaining abnormal sound related data of the vehicle through the sensors and the controllers; performing feature extraction on the abnormal sound related data to obtain abnormal sound features of the vehicle, generating an abnormal sound optimization request instruction according to the abnormal sound features, and sending the abnormal sound optimization request instruction to the server; receiving a vibration and noise reduction strategy corresponding to the abnormal sound optimization request instruction sent by the server, and optimizing the abnormal sound of the vehicle according to the vibration and noise reduction strategy. Thus, the sensors and the controllers are dynamically determined, and the data is collected as needed, so that the system power consumption is reduced; the strategy is generated and executed by the cloud, and the precise identification and active suppression of the abnormal sound are realized.

Description

Technical Field

[0001] This application relates to the field of NVH optimization technology, and in particular to a method for optimizing vehicle abnormal noises, a vehicle, and a server. Background Technology

[0002] During vehicle operation, various abnormal noises may occur due to component vibration, friction, impact, or electromagnetic excitation, seriously affecting ride comfort and product quality reputation. Traditional methods for diagnosing abnormal noises mainly rely on engineer road tests, subjective scoring, and spectrum analysis, which have problems such as recognition lag, dependence on human experience, and inability to identify unknown types of abnormal noises.

[0003] Meanwhile, existing vehicle vibration and noise reduction controls mostly employ passive vibration isolation structures or active control strategies based on fixed operating conditions and lookup tables. These strategies cannot adapt to individualized factors such as component aging, assembly differences, and changes in road surface excitation, resulting in vehicles becoming noisier over time. Furthermore, abnormal noise diagnosis and NVH (Noise, Vibration, and Harshness) control systems are independent of each other. Diagnostic results are only used for fault alarms and cannot drive vibration and noise reduction actuators, nor do control strategies utilize diagnostic results for precise intervention. Summary of the Invention

[0004] This application aims to at least partially address one of the technical problems in the related art.

[0005] Therefore, the first objective of this application is to propose an optimization method for vehicle abnormal noises. Based on this method, by dynamically determining sensors and controllers and collecting abnormal noise data on demand, the system power consumption and computational load are reduced. By generating abnormal noise optimization request instructions through feature extraction and sending them to the server, collaborative processing between the vehicle and the cloud is realized. By receiving vibration reduction and noise reduction strategies issued by the server and executing optimization, the vibration reduction and noise reduction actions are accurately applied to the excitation source or transmission path of the abnormal noise.

[0006] The second objective of this application is to propose an optimization method for vehicle abnormal noises, using an application server.

[0007] The third objective of this application is to propose a vehicle.

[0008] The fourth objective of this application is to propose a server.

[0009] To achieve the above objectives, a first aspect of this application proposes a method for optimizing vehicle abnormal noise, applied to a vehicle, comprising: responding to receiving abnormal noise information from the vehicle, determining the vehicle's sensors and controller based on the abnormal noise information; acquiring abnormal noise-related data of the vehicle through the sensors and controller; extracting features from the abnormal noise-related data to obtain abnormal noise features of the vehicle, generating an abnormal noise optimization request instruction based on the abnormal noise features, and sending the abnormal noise optimization request instruction to a server; receiving a vibration reduction and noise reduction strategy corresponding to the abnormal noise optimization request instruction sent by the server, and optimizing the vehicle's abnormal noise based on the vibration reduction and noise reduction strategy.

[0010] In addition, the vehicle noise optimization method according to the above embodiments of this application may also have the following additional technical features: According to one embodiment of this application, the sensor includes one or more of an acceleration sensor, a sound sensor, a current sensor, a voltage sensor, a tire pressure sensor, and suspension travel, and the controller includes one or more of a domain controller, a central controller, a suspension controller, and a shock absorber actuator controller.

[0011] According to one embodiment of this application, before feature extraction of abnormal noise-related data, the optimization method for vehicle abnormal noise further includes: preprocessing the abnormal noise-related data.

[0012] According to one embodiment of this application, optimizing vehicle noise based on a vibration reduction and noise reduction strategy includes: modulating and compensating the electromagnetic excitation of the electric drive system in response to the vibration reduction and noise reduction strategy including an electric drive electromagnetic noise optimization strategy; adjusting the dynamic stiffness and damping of the chassis and / or suspension system in response to the vibration reduction and noise reduction strategy including a chassis and / or suspension vibration optimization strategy; actively controlling the in-vehicle sound field in response to the vibration reduction and noise reduction strategy including a road noise and / or wind noise optimization strategy; and actively suppressing the resonance transmission path of the battery pack and / or thermal management system in response to the vibration reduction and noise reduction strategy including a battery pack and / or thermal management system resonance optimization strategy.

[0013] According to one embodiment of this application, after optimizing the abnormal noise of a vehicle according to the vibration reduction and noise reduction strategy, the method for optimizing the abnormal noise of a vehicle further includes: re-acquiring the abnormal noise-related data of the vehicle through sensors and controllers; extracting features from the re-acquiring abnormal noise-related data to obtain the abnormal noise features of the vehicle; generating an abnormal noise optimization request instruction based on the re-obtained abnormal noise features; and sending the re-generated abnormal noise optimization request instruction to the server.

[0014] To achieve the above objectives, a second aspect of this application proposes a method for optimizing vehicle abnormal noises, applied to a server. The method includes receiving an abnormal noise optimization request instruction sent by a vehicle, wherein the abnormal noise optimization request instruction includes abnormal noise characteristics and vehicle information; invoking a vehicle abnormal noise diagnostic model to diagnose the abnormal noise characteristics to obtain a vehicle abnormal noise diagnostic result; in response to the abnormal noise diagnostic result not meeting preset abnormal noise conditions, obtaining a vibration reduction and noise reduction strategy for the vehicle based on the abnormal noise diagnostic result; and sending the vibration reduction and noise reduction strategy to the corresponding vehicle based on the vehicle information, so that the vehicle optimizes its abnormal noises according to the vibration reduction and noise reduction strategy.

[0015] According to one embodiment of this application, obtaining a vibration reduction and noise reduction strategy for a vehicle based on abnormal noise diagnosis results includes: in response to the existence of a vibration reduction and noise reduction strategy corresponding to the abnormal noise diagnosis results in the database, obtaining the vibration reduction and noise reduction strategy from the database based on the abnormal noise diagnosis results; in response to the absence of a vibration reduction and noise reduction strategy corresponding to the abnormal noise diagnosis results in the database, generating a vibration reduction and noise reduction strategy based on a preset vibration reduction and noise reduction algorithm and the abnormal noise diagnosis results.

[0016] According to one embodiment of this application, a vehicle abnormal noise diagnosis model is generated by: acquiring training sample data and labels corresponding to the training sample data; inputting the training sample data into the vehicle abnormal noise diagnosis model to generate a predicted abnormal noise diagnosis result; generating a loss value from the predicted abnormal noise diagnosis result and labels, and training the vehicle abnormal noise diagnosis model based on the loss value.

[0017] The vehicle noise optimization method of this application improves the objectivity and efficiency of noise identification by receiving a request command containing noise characteristics and vehicle information and calling a diagnostic model for automatic diagnosis; it also filters diagnostic results by setting preset noise conditions and triggers strategy acquisition only when intervention is needed, thus avoiding ineffective processing; and it achieves closed-loop linkage between noise diagnosis and remote optimization by accurately sending the generated vibration reduction and noise reduction strategy to the corresponding vehicle.

[0018] To achieve the above objectives, a third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the aforementioned method for optimizing vehicle noise.

[0019] According to the vehicle of this application, the processor executes a computer program stored in the memory to implement the aforementioned method for optimizing vehicle abnormal noise. By dynamically determining sensors and controllers and collecting abnormal noise data on demand, system power consumption and computational load are reduced; by generating abnormal noise optimization request instructions through feature extraction and sending them to the server, collaborative processing between the vehicle and the cloud is realized; by receiving vibration reduction and noise reduction strategies issued by the server and executing optimization, the vibration reduction and noise reduction actions are precisely applied to the excitation source or transmission path of the abnormal noise.

[0020] To achieve the above objectives, a fourth aspect of this application provides a server, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the aforementioned method for optimizing vehicle noise.

[0021] According to the server in this application, the processor executes a computer program stored in the memory to implement the aforementioned method for optimizing vehicle abnormal noises. By receiving a request command containing abnormal noise characteristics and vehicle information and calling a diagnostic model for automatic diagnosis, the objectivity and efficiency of abnormal noise identification are improved; by setting preset abnormal noise conditions to filter the diagnostic results, the strategy acquisition is triggered only when intervention is needed, avoiding ineffective processing; by accurately sending the generated vibration reduction and noise reduction strategy to the corresponding vehicle, a closed-loop linkage between abnormal noise diagnosis and remote optimization is realized. Attached Figure Description

[0022] Figure 1 Here is a flowchart of a method for optimizing vehicle noise according to some embodiments of this application; Figure 2 A flowchart of a method for optimizing vehicle noise according to other embodiments of this application; Figure 3 This is a block diagram of a vehicle according to some embodiments of this application; Figure 4 This is a block diagram of a server according to some embodiments of this application. Detailed Implementation

[0023] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0024] The following describes in detail, with reference to the accompanying drawings, a method for optimizing vehicle noise, a vehicle, and a server according to embodiments of this application.

[0025] Figure 1 This is a flowchart of a method for optimizing vehicle noise according to some embodiments of this application. (Refer to...) Figure 1 Optimization methods for vehicle noises can include: S1, in response to receiving abnormal noise information from the vehicle, determines the vehicle's sensors and controllers based on the abnormal noise information.

[0026] In this context, abnormal noise information refers to unusual audible signals generated during vehicle operation due to component vibration, friction, impact, or electromagnetic excitation. These unusual audible signals are distinct from the expected noise generated during normal vehicle operation. It should be noted that the abnormal noise information described in this embodiment can be abnormal noise information detected by the vehicle itself (e.g., abnormal noise alarm information), or abnormal noise information detected and / or collected by the vehicle based on a preset abnormal noise detection strategy. The preset abnormal noise detection strategy can be calibrated according to actual conditions.

[0027] In some embodiments of this application, the sensors include one or more of an acceleration sensor, a sound sensor, a current sensor, a voltage sensor, a tire pressure sensor, and suspension travel, and the controller includes one or more of a domain controller, a central controller, a suspension controller, and a shock absorber actuator controller.

[0028] The system includes: an accelerometer to collect vibration acceleration signals from various vehicle components and the vehicle body to identify the vibration excitation source and transmission path of abnormal noises; a sound sensor to collect sound pressure signals inside and outside the vehicle to obtain the acoustic characteristics and spatial distribution of abnormal noises; a current sensor to monitor the current waveform of the motor drive circuit and actuators to identify abnormal noises caused by electromagnetic excitation or control anomalies; a voltage sensor to detect voltage fluctuations in the power supply system and control circuits to help determine the source of electrical-related abnormal noises; a tire pressure sensor to monitor tire pressure to identify changes in road excitation or tire noises caused by abnormal tire pressure; and a suspension travel sensor to collect displacement changes in the suspension system to determine abnormal noises caused by abnormal movement or limiting contact of suspension components.

[0029] The domain controller receives and processes signals from multiple sensors, running a lightweight onboard AI model to identify and classify abnormal noises online. The central controller coordinates the operating status of all control units in the vehicle, performing comprehensive scheduling of abnormal noise diagnosis and vibration reduction strategies. The mount controller adjusts the stiffness and damping parameters of active or semi-active mounts to suppress vibrations and abnormal noises transmitted through the mount system. The damper actuator controller adjusts the damping characteristics and actuator output of the dampers to actively suppress chassis and body vibrations.

[0030] Furthermore, the vehicle's sensors and controllers are identified based on the abnormal noise information.

[0031] Specifically, in response to an abnormal noise information indicating that the source of the abnormal noise is the electric drive system, the current sensor, voltage sensor, and domain controller are activated; in response to an abnormal noise information indicating that the source of the abnormal noise is the chassis or suspension system, the acceleration sensor, suspension travel sensor, domain controller, and damper actuator controller are activated; in response to an abnormal noise information indicating that the source of the abnormal noise is road surface or wind noise, the sound sensor, acceleration sensor, and central controller are activated; in response to an abnormal noise information indicating that the source of the abnormal noise is the battery pack or thermal management system, the acceleration sensor, sound sensor, and suspension controller are activated.

[0032] By dynamically determining the sensors and controllers to be activated based on abnormal noise information, on-demand configuration of abnormal noise diagnostic resources is achieved, avoiding continuous ineffective operation of all sensors and controllers, and effectively reducing the overall power consumption and computational load of the vehicle system.

[0033] S2 acquires data related to abnormal noises from the vehicle through sensors and controllers.

[0034] Among them, abnormal noise related data refers to a set of physical quantities used to characterize the occurrence state, excitation source, transmission path and response characteristics of abnormal noise in vehicles, such as time domain waveform data, frequency domain spectral data, operating condition parameter data and environmental correlation data.

[0035] Specifically, sensors (such as acceleration sensors, sound sensors, current sensors, voltage sensors, tire pressure sensors, and suspension travel) and controllers (such as domain controllers, central controllers, suspension controllers, and damper actuator controllers) are used to collect data related to abnormal noises such as vibration, sound pressure, motor speed, motor torque, inverter current, suspension status, and vehicle speed in real time.

[0036] This application embodiment uses multiple sensors and controllers to collaboratively collect abnormal noise-related data, which can obtain holographic characteristics of abnormal noise from multiple physical dimensions such as vibration, sound pressure, current, and voltage, thereby improving the data richness and information source reliability of abnormal noise diagnosis.

[0037] S3 extracts features from the abnormal noise-related data to obtain the abnormal noise characteristics of the vehicle, generates an abnormal noise optimization request instruction based on the abnormal noise characteristics, and sends the abnormal noise optimization request instruction to the server.

[0038] In some embodiments of this application, before feature extraction is performed on the abnormal noise-related data, the method further includes: preprocessing the abnormal noise-related data.

[0039] Preprocessing of abnormal noise-related data refers to the process of organizing the raw acquired signals. Preprocessing includes one or more of the following: filtering and noise reduction, outlier removal, missing value interpolation, signal normalization, timestamp alignment, and frame synchronization.

[0040] Furthermore, feature extraction is performed on the preprocessed abnormal noise-related data to obtain the abnormal noise characteristics of the vehicle.

[0041] Feature extraction refers to the process of extracting quantitative indicators that characterize the essential attributes of abnormal noises from preprocessed abnormal noise-related data. Vehicle abnormal noise characteristics refer to a set of parameters used to characterize the type, location, severity, dominant frequency, excitation source level, and operating condition of the abnormal noise. The abnormal noise optimization request command is a data message used to trigger the server to generate vibration reduction and noise reduction strategies; this command must at least include abnormal noise characteristic parameters, vehicle identification information, and the current operating condition label.

[0042] Specifically, firstly, time-domain statistical features, frequency-domain spectral features, and time-frequency-domain transient features are extracted from the preprocessed vibration data, sound pressure data, current data, voltage data, and operating parameters. These extracted multi-dimensional features are then fused into an abnormal noise feature vector, which characterizes the type, location, severity, and dominant frequency of the abnormal noise. Next, the abnormal noise feature vector, along with vehicle identification, operating condition tags, and a timestamp, is encapsulated into a data message and encrypted and compressed to obtain an abnormal noise optimization request command. Finally, the abnormal noise optimization request command is uploaded to a cloud server via the vehicle communication module, requesting the server to generate a matching vibration reduction and noise reduction strategy.

[0043] This application embodiment extracts multi-dimensional features from abnormal noise-related data and generates abnormal noise optimization request instructions, which are then uploaded to the server. This separates the lightweight computing on the vehicle end from the deep inference of large models in the cloud, reducing the computational burden on the vehicle controller and making full use of the computing resources in the cloud for complex abnormal noise identification and strategy generation.

[0044] S4 receives the vibration reduction and noise reduction strategy corresponding to the abnormal noise optimization request command sent by the server, and optimizes the abnormal noise of the vehicle according to the vibration reduction and noise reduction strategy.

[0045] Among them, the vibration reduction and noise reduction strategy refers to the set of control parameters and execution logic generated by the server based on the characteristics of abnormal noise, which is used to suppress or eliminate specific abnormal noise. The strategy includes the target abnormal noise type, the execution object identifier, the control parameter value, and the effective operating conditions.

[0046] In some embodiments of this application, the optimization of vehicle noise reduction based on vibration reduction and noise reduction strategies includes: modulating and compensating the electromagnetic excitation of the electric drive system in response to the vibration reduction and noise reduction strategy including an electric drive electromagnetic noise optimization strategy; adjusting the dynamic stiffness and damping of the chassis and / or suspension system in response to the vibration reduction and noise reduction strategy including a chassis and / or suspension vibration optimization strategy; actively controlling the in-vehicle sound field in response to the vibration reduction and noise reduction strategy including a road noise and / or wind noise optimization strategy; and actively suppressing the resonance transmission path of the battery pack and / or thermal management system in response to the vibration reduction and noise reduction strategy including a battery pack and / or thermal management system resonance optimization strategy.

[0047] Among these, the electric drive electromagnetic noise optimization strategy refers to a control scheme that reduces electromagnetic radiation noise by adjusting the electromagnetic excitation parameters of the electric drive system. The chassis and / or suspension vibration optimization strategy refers to a control scheme that suppresses structural vibration propagation by adjusting the transmission characteristics of the chassis and suspension system. The road noise and / or wind noise optimization strategy refers to a control scheme that cancels out target noise energy within the vehicle through active sound field control. The battery pack and / or thermal management resonance optimization strategy refers to a control scheme that disrupts resonance conditions or blocks vibration transmission by altering the dynamic characteristics of additional structures.

[0048] As a specific embodiment of this example, when the abnormal noise of the vehicle is diagnosed as electromagnetic noise from the electric drive, the vehicle controller optimizes the PWM (Pulse Width Modulation) carrier frequency, injects harmonic compensation current, performs torque smoothing and electromagnetic force compensation to reduce the intensity of electromagnetic excitation; when the abnormal noise is diagnosed as chassis or suspension vibration, the vehicle controller adjusts the CDC (Continuous Damping Control) damping, adjusts the stiffness and damping of the active suspension, and optimizes the TMD (Tuned Mass Damper) parameters to change the vibration transmission path; when the abnormal noise is diagnosed as road noise or wind noise, the vehicle controller activates the multi-channel ANC (Active Noise Control) system, performs feedforward and feedback coordinated control, and adjusts the phase and gain of the error microphone and speaker to cancel the target noise inside the vehicle; when the abnormal noise is diagnosed as battery pack or thermal management resonance, the vehicle controller adjusts the excitation parameters of the active actuator, adjusts the hydraulic resistance characteristics, and performs pipeline vibration reduction control to disrupt the resonance conditions or block vibration transmission.

[0049] In some embodiments of this application, after optimizing the abnormal noise of the vehicle according to the vibration reduction and noise reduction strategy, the method further includes: re-acquiring the abnormal noise-related data of the vehicle through the sensors and controller; extracting features from the re-acquiring abnormal noise-related data to obtain the abnormal noise features of the vehicle; generating an abnormal noise optimization request instruction based on the re-obtained abnormal noise features; and sending the re-generated abnormal noise optimization request instruction to the server.

[0050] Specifically, since the actual implementation effect of vibration reduction and noise reduction strategies may be affected by factors such as individual vehicle differences, component aging, changes in ambient temperature and fluctuations in road conditions, there may be a deviation between the noise reduction effect after the strategy is implemented and the expected target. Therefore, closed-loop verification is required to evaluate the effectiveness of the strategy and trigger iterative optimization.

[0051] Within the preset time window after the vibration reduction and noise reduction strategy is completed, steps S2 to S3 are restarted to collect abnormal noise-related data again and extract features. The abnormal noise features obtained after the strategy is executed are compared with the abnormal noise features before the strategy is executed. An iterative optimization request instruction containing noise reduction effect indicators and residual abnormal noise features is generated and sent to the server for it to determine whether a new round of vibration reduction and noise reduction strategy needs to be generated.

[0052] This application embodiment achieves a direct mapping from abnormal noise diagnosis results to control execution by receiving and optimizing the vibration reduction and noise reduction strategy issued by the server, enabling the vibration reduction and noise reduction actions to accurately act on the excitation source or transmission path of the abnormal noise; furthermore, by re-collecting data after optimization and uploading it to the server to form a closed-loop verification, the effectiveness of the strategy can be automatically evaluated and iterative optimization can be triggered, solving the problem that the strategy deviation cannot be corrected under open-loop control, and realizing continuous improvement and adaptability of the abnormal noise suppression effect.

[0053] Figure 2 This is a flowchart of a method for optimizing vehicle noise according to other embodiments of this application. (Refer to...) Figure 2 Optimization methods for addressing vehicle-related noises when applied to servers may include: S210, receive the abnormal noise optimization request instruction sent by the vehicle, wherein the abnormal noise optimization request instruction includes the abnormal noise characteristics and vehicle information.

[0054] Specifically, the server receives the abnormal noise optimization request command uploaded by the vehicle terminal through the cloud communication interface. After decrypting and decompressing the abnormal noise optimization request command, it parses out the abnormal noise feature vector and vehicle information. Among them, the abnormal noise feature vector includes at least the abnormal noise type code, abnormal noise location code, dominant frequency value, severity index, and operating condition label; the vehicle information includes at least the vehicle unique identifier, hardware configuration code, current software version number, and geographical location information.

[0055] By receiving abnormal noise optimization request instructions sent by the vehicle, which contain abnormal noise characteristics and vehicle information, the server can obtain the correlation between abnormal noise diagnosis results and individual vehicle attributes. This provides a data foundation for generating targeted vibration reduction and noise reduction strategies, avoids repeated identification of vehicle models and configurations, and improves the efficiency and accuracy of strategy generation.

[0056] S220: Call the vehicle abnormal noise diagnosis model to diagnose the abnormal noise characteristics and obtain the vehicle abnormal noise diagnosis results.

[0057] Among them, the vehicle abnormal noise diagnosis model refers to a pre-trained deep learning network or machine learning model used to identify and classify input abnormal noise features. This model can output the abnormal noise type, abnormal noise location, confidence score, and recommendation strategy label.

[0058] For example, a vehicle abnormal noise diagnosis model can use a convolutional neural network model, which performs deep feature extraction on the abnormal noise feature vector through multi-layer convolution and pooling operations, and outputs the probability distribution of abnormal noise type via a fully connected layer and a Softmax classifier.

[0059] In some embodiments of this application, the vehicle abnormal noise diagnosis model is generated by: acquiring training sample data and the labels corresponding to the training sample data; inputting the training sample data into the vehicle abnormal noise diagnosis model to generate a predicted abnormal noise diagnosis result; generating a loss value from the predicted abnormal noise diagnosis result and the labels, and training the vehicle abnormal noise diagnosis model based on the loss value.

[0060] As a specific embodiment of this example, historically collected vibration data, sound pressure data, and current data are acquired as training sample data, and each training sample is labeled with an abnormal noise type label and an abnormal noise location label. The training sample data is input into the constructed convolutional neural network model, and the model outputs the predicted abnormal noise diagnosis result after forward calculation. The predicted abnormal noise diagnosis result and the labeled labels are input into the cross-entropy loss function to calculate the loss value. Based on the loss value, the model weight parameters are adjusted through the backpropagation algorithm, and iterative training is performed until the loss value converges to below the preset threshold, thus obtaining the trained vehicle abnormal noise diagnosis model.

[0061] The embodiments of this application automatically identify and classify abnormal noise features by calling a pre-trained vehicle abnormal noise diagnosis model. It can quickly output the type, location, and confidence level of abnormal noise, avoiding the reliance on human experience in traditional methods and improving the objectivity and consistency of abnormal noise diagnosis. By using deep learning models such as convolutional neural networks and combining them with a large number of labeled samples for iterative training, the model can continuously accumulate knowledge of abnormal noise features, continuously improve its ability to identify unknown abnormal noise types, and achieve accurate diagnosis of complex abnormal noise scenarios.

[0062] S230, in response to the abnormal noise diagnosis result not meeting the preset abnormal noise conditions, obtains the vehicle's vibration reduction and noise reduction strategy based on the abnormal noise diagnosis result.

[0063] The preset abnormal noise conditions can refer to the criteria for determining whether an abnormal noise is within an acceptable range. For example, the preset abnormal noise conditions may be that the abnormal noise type belongs to a preset set of negligible types, the abnormal noise severity index is lower than a preset threshold, the abnormal noise confidence score is lower than a preset confidence threshold, or the abnormal noise occurrence frequency is lower than a preset frequency threshold.

[0064] Understandably, the preset abnormal noise conditions can be set by technicians according to the actual situation, and there are no specific restrictions.

[0065] When the abnormal noise diagnosis result meets the preset abnormal noise conditions, it is determined that the current abnormal noise does not require intervention; when the abnormal noise diagnosis result does not meet the preset abnormal noise conditions, the process of obtaining vibration reduction and noise reduction strategies is triggered.

[0066] In some embodiments of this application, obtaining a vibration reduction and noise reduction strategy for a vehicle based on the abnormal noise diagnosis result includes: in response to the existence of a vibration reduction and noise reduction strategy corresponding to the abnormal noise diagnosis result in the database, obtaining the vibration reduction and noise reduction strategy from the database based on the abnormal noise diagnosis result; in response to the absence of a vibration reduction and noise reduction strategy corresponding to the abnormal noise diagnosis result in the database, generating a vibration reduction and noise reduction strategy based on a preset vibration reduction and noise reduction algorithm and the abnormal noise diagnosis result.

[0067] The database stores the mapping relationship between historically generated abnormal noise diagnosis results and vibration reduction and noise reduction strategies. By querying this mapping relationship, pre-configured or historically optimized strategy data packages can be quickly obtained.

[0068] Specifically, in response to the existence of vibration reduction and noise reduction strategies corresponding to the abnormal noise diagnosis results in the database, the corresponding vibration reduction and noise reduction strategies are directly matched and read from the database based on the abnormal noise diagnosis results.

[0069] Preset vibration reduction and noise reduction algorithms can refer to computational logic or mathematical transformation methods used to map abnormal noise diagnosis results to a set of control parameters. Examples include control parameter matching algorithms based on rule engines, control parameter solving algorithms based on optimization theory, or policy generation algorithms based on reinforcement learning. It is understood that preset vibration reduction and noise reduction algorithms can be set by relevant technical personnel according to actual conditions, and there are no specific restrictions.

[0070] Abnormal noise diagnosis results refer to a set of information used to characterize the attributes and status of abnormal noises. This may include a structured data set containing the type of abnormal noise, its location, dominant frequency value, severity index, and operating condition labels.

[0071] Furthermore, when no matching mapping record is found in the database that matches the current abnormal noise diagnosis result, the server calls a preset vibration reduction and noise reduction algorithm. The abnormal noise type, abnormal noise location, dominant frequency value and severity index in the abnormal noise diagnosis result are used as input parameters. The algorithm calculates and generates a corresponding set of control parameters and execution logic to form a new vibration reduction and noise reduction strategy. The newly generated strategy is then associated with the current abnormal noise diagnosis result and stored in the database for subsequent reuse.

[0072] This application embodiment filters abnormal noise diagnosis results by setting preset abnormal noise conditions, triggering the strategy acquisition process only when the abnormal noise reaches the level requiring intervention. This avoids invalid calculations and unnecessary strategy issuance, reducing system overhead. By prioritizing matching historical strategies from the database, it can quickly respond to common abnormal noise types, reducing strategy generation delays. When no matching strategy is available, new strategies are dynamically generated and stored for reuse, enabling the self-expansion and accumulation of the strategy library, gradually improving the system's response speed to recurring abnormal noises.

[0073] S240 sends vibration reduction and noise reduction strategies to the corresponding vehicles based on vehicle information, so that the vehicles can optimize abnormal noises according to the vibration reduction and noise reduction strategies.

[0074] Specifically, the server determines the identity and communication link of the target vehicle based on the vehicle's unique identifier and network address information in the vehicle information. After encrypting and encapsulating the vibration reduction and noise reduction strategy, it sends it to the vehicle's onboard controller through the OTA (Over-The-Air) push channel, so that the onboard controller can parse and execute the control parameters and execution logic in the strategy.

[0075] This application embodiment achieves precise distribution of vibration reduction and noise reduction strategies by sending them to the corresponding vehicles based on vehicle information. This avoids invalid pushes to irrelevant vehicles and reduces communication bandwidth consumption. Combined with the OTA encrypted distribution mechanism, vehicle control parameters can be updated remotely and securely without requiring vehicles to enter the store or manual intervention, improving the timeliness and convenience of strategy deployment.

[0076] As a specific embodiment of this application, when a vehicle experiences a whistling noise at speeds between 60 km / h and 80 km / h and a motor speed between 1800 rpm and 2500 rpm, the onboard controller uses sensors to collect current harmonics, stator vibration, and in-vehicle sound pressure signals for noise diagnosis. The noise is determined to be a coupling noise between electric drive electromagnetic excitation and suspension resonance, located in the electric drive system and suspension system, with dominant frequencies of 320 Hz and 480 Hz, and a severity index exceeding a preset threshold. Upon receiving a noise optimization request, the server calls the vehicle noise diagnosis model to output the noise diagnosis result. If the noise diagnosis result does not meet the preset noise conditions and no corresponding strategy exists in the database, a vibration reduction and noise reduction strategy is generated based on a preset vibration reduction and noise reduction algorithm. This strategy adjusts the PWM carrier frequency to avoid 320 Hz and 480 Hz, injects compensation current to counteract radial electromagnetic force, and increases the damping value of the active suspension in the 300 Hz to 500 Hz frequency band. The server sends vibration reduction and noise reduction strategies to the corresponding vehicles via OTA based on vehicle information. The vehicle controller receives and executes the strategies, reducing in-vehicle noise by 6dB to 10dB and eliminating whistling noises. After the strategies are executed, the vehicle controller re-collects noise-related data and uploads it to the server. The server then iteratively optimizes the vehicle noise diagnosis model and vibration reduction and noise reduction strategy library based on the returned data.

[0077] The method for optimizing vehicle abnormal noises in this application has the following technical advantages compared to related technologies: 1. Reduce system power consumption and computational load: By dynamically determining which sensors and controllers need to be activated in response to abnormal noise information, data acquisition resources can be configured on demand, avoiding continuous ineffective operation of all sensors and controllers.

[0078] 2. Improve the objectivity and accuracy of abnormal noise diagnosis: By collecting multi-dimensional data such as vibration, sound pressure and current through multi-source sensors, and combining them with cloud-based deep learning models for automatic identification and classification, the reliance on human experience is avoided.

[0079] 3. Achieve deep coupling between abnormal noise diagnosis and vibration reduction: Directly map the abnormal noise diagnosis results to control parameters, so that the vibration reduction and noise reduction actions are precisely applied to the excitation source or transmission path of the abnormal noise, breaking the traditional situation where diagnosis and control are independent of each other.

[0080] 4. Supports continuous optimization throughout the entire lifecycle: By re-collecting data after optimization and uploading it to the server to form a closed-loop verification, combined with the OTA remote distribution mechanism, the system can automatically evaluate the effectiveness of the strategy and iteratively improve it, so that the vehicle's NVH performance can remain in a superior state for a long time.

[0081] 5. Improve the timeliness and convenience of strategy deployment: Vibration reduction and noise reduction strategies are transmitted via OTA encryption, eliminating the need for vehicles to enter the store or manual intervention, and allowing for remote and secure updates of vehicle control parameters.

[0082] Corresponding to the above embodiments, this application also provides a vehicle, referring to... Figure 3 The vehicle 300 includes: a memory 310, a processor 320, and a computer program stored on the memory 310 and executable on the processor 320. The processor 320 executes the program to implement the aforementioned optimization method for vehicle abnormal noise.

[0083] This application also provides a server, as shown in the reference. Figure 4 The server 400 includes: a memory 410, a processor 420, and a computer program stored on the memory 410 and executable on the processor 420. The processor 420 executes the program to implement the aforementioned optimization method for vehicle abnormal noise.

[0084] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0085] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0086] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0087] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

[0088] Any process or method described in the flowchart or otherwise herein is to be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0089] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0090] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0091] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0092] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0093] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

[0094] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0095] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for optimizing abnormal noises in vehicles, characterized in that, Applied to vehicles, including: In response to receiving abnormal noise information from the vehicle, the sensors and controllers of the vehicle are determined based on the abnormal noise information; The sensor and controller acquire data related to abnormal noises from the vehicle. Feature extraction is performed on the abnormal noise-related data to obtain the abnormal noise characteristics of the vehicle, and an abnormal noise optimization request instruction is generated based on the abnormal noise characteristics and sent to the server. The system receives a vibration reduction and noise reduction strategy corresponding to the abnormal noise optimization request instruction sent by the server, and optimizes the abnormal noise of the vehicle according to the vibration reduction and noise reduction strategy.

2. The method for optimizing vehicle abnormal noise according to claim 1, characterized in that, The sensors include one or more of an acceleration sensor, a sound sensor, a current sensor, a voltage sensor, a tire pressure sensor, and suspension travel, and the controller includes one or more of a domain controller, a central controller, a suspension controller, and a shock absorber actuator controller.

3. The method for optimizing vehicle abnormal noise according to claim 1, characterized in that, Before performing feature extraction on the abnormal noise-related data, the method further includes: The abnormal noise-related data are preprocessed.

4. The method for optimizing vehicle abnormal noise according to claim 1, characterized in that, The optimization of abnormal noises in the vehicle based on the vibration reduction and noise reduction strategy includes: In response to the vibration reduction and noise reduction strategy, which includes an electric drive electromagnetic noise optimization strategy, the electromagnetic excitation of the electric drive system is modulated and compensated. In response to the vibration reduction and noise reduction strategy, which includes a chassis and / or suspension vibration optimization strategy, the dynamic stiffness and damping of the chassis and / or suspension system are adjusted. In response to the vibration reduction and noise reduction strategies, including road noise and / or wind noise optimization strategies, active noise control is performed on the in-vehicle sound field; In response to the vibration reduction and noise reduction strategy, which includes a battery pack and / or thermal management resonance optimization strategy, the resonance transmission path of the battery pack and / or thermal management system is actively suppressed.

5. The method for optimizing vehicle abnormal noise according to claim 1, characterized in that, After optimizing the abnormal noise of the vehicle according to the vibration reduction and noise reduction strategy, the method further includes: The abnormal noise data of the vehicle are reacquired through the sensors and the controller; Feature extraction is performed on the reacquired abnormal noise-related data to obtain the abnormal noise characteristics of the vehicle. An abnormal noise optimization request instruction is generated based on the reacquired abnormal noise characteristics and sent to the server.

6. A method for optimizing abnormal noises in vehicles, characterized in that, Applied to servers, including: Receive a noise optimization request instruction sent by the vehicle, wherein the noise optimization request instruction includes noise characteristics and vehicle information; The vehicle abnormal noise diagnosis model is invoked to diagnose the abnormal noise characteristics in order to obtain the vehicle abnormal noise diagnosis results; In response to the abnormal noise diagnosis result not meeting the preset abnormal noise conditions, the vibration reduction and noise reduction strategy of the vehicle is obtained based on the abnormal noise diagnosis result; The vibration reduction and noise reduction strategy is sent to the corresponding vehicle based on the vehicle information, so that the vehicle can optimize the abnormal noise of the vehicle according to the vibration reduction and noise reduction strategy.

7. The method for optimizing vehicle abnormal noise according to claim 6, characterized in that, The step of obtaining the vehicle's vibration reduction and noise reduction strategy based on the abnormal noise diagnosis results includes: In response to the existence of a vibration reduction and noise reduction strategy corresponding to the abnormal noise diagnosis result in the database, the vibration reduction and noise reduction strategy is obtained from the database according to the abnormal noise diagnosis result; In response to the absence of a vibration reduction and noise reduction strategy corresponding to the abnormal noise diagnosis result in the database, the vibration reduction and noise reduction strategy is generated based on the preset vibration reduction and noise reduction algorithm and the abnormal noise diagnosis result.

8. The method for optimizing vehicle abnormal noise according to claim 6, characterized in that, The vehicle abnormal noise diagnostic model is generated in the following ways: Obtain training sample data and the labels corresponding to the training sample data; The training sample data is input into the vehicle abnormal noise diagnosis model to generate the predicted abnormal noise diagnosis result; The predicted abnormal noise diagnosis result and the label generate a loss value, and the vehicle abnormal noise diagnosis model is trained based on the loss value.

9. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the optimization method for vehicle noise as described in any one of claims 1-5.

10. A server, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the vehicle noise optimization method as described in any one of claims 6-8.

Images