Vehicle abnormal noise identification method and device, vehicle and storage medium

Abstract

The embodiments of the present application provide a vehicle abnormal noise recognition method and device, a vehicle and a storage medium, and belong to the field of vehicle fault diagnosis technology. The method includes: obtaining reference sound data of the vehicle; performing abnormal noise prediction on the reference sound data through an abnormal noise prediction model to obtain abnormal noise prediction data. The abnormal noise prediction data is verified, and if the abnormal noise verification result indicates that the abnormal noise prediction data is erroneous data, the reference sound data is corrected and uploaded to the abnormal noise database. The model parameters of the abnormal noise prediction model are adjusted based on the abnormal noise database to obtain an abnormal noise recognition model, and the abnormal noise recognition is performed on the current sound data acquired in advance according to the abnormal noise recognition model. In this way, it is possible to continuously collect sound data with prediction errors, and the model is trained in a targeted manner through these sound data to obtain an abnormal noise recognition model with higher accuracy. When the current sound data is recognized according to the abnormal noise recognition model, the accuracy of abnormal noise recognition can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle fault diagnosis, and in particular to a vehicle abnormal noise recognition method and device, a vehicle and a storage medium. Background Art

[0002] Vehicle safety issues have always been a focus of attention for users and vehicle manufacturers. When a vehicle has a mechanical failure, it is usually accompanied by an abnormal noise. By monitoring and identifying the vehicle sound, it is possible to identify the abnormal noise in the vehicle sound and determine the type of abnormal noise, so as to quickly locate the source of the fault and facilitate troubleshooting. In the related art, the vehicle sound is identified by a pre-trained recognition model to identify the type of abnormal noise, but the accuracy of abnormal noise recognition by the recognition model is low. Therefore, how to improve the accuracy of abnormal noise recognition in vehicles has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The main purpose of the embodiments of the present application is to provide a vehicle abnormal sound recognition method and device, a vehicle and a storage medium, aiming to improve the accuracy of vehicle abnormal sound recognition.

[0004] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a vehicle abnormal noise recognition method, which is applied to a cloud server and includes:

[0005] Acquiring reference sound data of the vehicle;

[0006] Performing abnormal noise prediction on the reference sound data through a preset abnormal noise prediction model to obtain abnormal noise prediction data;

[0007] Verifying the abnormal sound prediction data to obtain an abnormal sound verification result; wherein the abnormal sound verification result is used to indicate whether the abnormal sound prediction data is erroneous data;

[0008] If the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data, the reference sound data is corrected to obtain target sound data, and the target sound data is uploaded to a preset abnormal sound database;

[0009] Adjusting the model parameters of the abnormal sound prediction model based on the abnormal sound database to obtain an abnormal sound recognition model;

[0010] The abnormal sound recognition is performed on the pre-acquired current sound data according to the abnormal sound recognition model.

[0011] In some embodiments, the abnormal sound prediction data includes sound feature data, abnormal sound occurrence time and abnormal sound type, and the verifying the abnormal sound prediction data to obtain the abnormal sound verification result includes:

[0012] If the abnormal sound type is a parameter-based abnormal sound type, then the vehicle operating parameters at the time when the abnormal sound occurs are obtained; wherein the parameter-based abnormal sound type is used to characterize the abnormal sound generated by the vehicle when the vehicle operating parameters change;

[0013] The parameter-based abnormal sound type is verified according to the sound characteristic data and the vehicle operating parameters to obtain the abnormal sound verification result.

[0014] In some embodiments, the vehicle operating parameters include a first engine speed, a second engine speed, a first balance shaft frequency, and a second balance shaft frequency; the abnormal sound occurrence time includes a first time and a second time; the first engine speed is the speed of the engine at the first time, the second engine speed is the speed of the engine at the second time, the first balance shaft frequency is the frequency of the balance shaft at the first time, and the second balance shaft frequency is the frequency of the balance shaft at the second time; the verifying the parameter-based abnormal sound type according to the sound characteristic data and the vehicle operating parameters to obtain the abnormal sound verification result includes:

[0015] If the parameter-based abnormal noise type is an abnormal noise of an engine balance shaft, obtaining a spectrogram of the sound feature data;

[0016] Acquire a first abnormal sound energy corresponding to the first moment and the first balance shaft frequency on the spectrogram, and a second abnormal sound energy corresponding to the second moment and the second balance shaft frequency on the spectrogram;

[0017] When the first engine speed is greater than the second engine speed and the first abnormal sound energy is less than the second abnormal sound energy, or, the first engine speed is less than the second engine speed and the first abnormal sound energy is greater than the second abnormal sound energy, or, the first engine speed is equal to the second engine speed and the first abnormal sound energy is not equal to the second abnormal sound energy, the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data.

[0018] In some embodiments, the vehicle operating parameters include a first gearbox speed, a second gearbox speed, a first gearbox frequency, and a second gearbox frequency, the abnormal sound occurrence time includes a third time and a fourth time, the first gearbox speed is the speed of the gearbox at the third time, the second gearbox speed is the speed of the gearbox at the fourth time, the first gearbox frequency is the frequency of the gearbox at the third time, and the second gearbox frequency is the frequency of the gearbox at the fourth time; the verifying the parameter-type abnormal sound type according to the sound feature data and the vehicle operating parameters to obtain the abnormal sound verification result includes:

[0019] If the parameter-based abnormal noise type is a gearbox rotation abnormal noise, obtaining a spectrogram of the sound feature data;

[0020] Acquire a third abnormal sound energy corresponding to the third moment on the spectrogram and the first gearbox frequency, and a fourth abnormal sound energy corresponding to the fourth moment on the spectrogram and the second gearbox frequency;

[0021] When the first gearbox speed is greater than the second gearbox speed and the third abnormal sound energy is less than the fourth abnormal sound energy, or, the first gearbox speed is less than the second gearbox speed and the third abnormal sound energy is greater than the fourth abnormal sound energy, or, the first gearbox speed is equal to the second gearbox speed and the third abnormal sound energy is not equal to the fourth abnormal sound energy, the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data.

[0022] In some embodiments, the vehicle operating parameters include a third engine speed, a fourth engine speed, a first engine frequency, and a second engine frequency, the abnormal sound occurrence time includes a fifth time and a sixth time, the third engine speed is the speed of the engine at the fifth time, the fourth engine speed is the speed of the engine at the sixth time, the first engine frequency is the frequency of the engine at the fifth time, and the second engine frequency is the frequency of the engine at the sixth time; the verifying the parameter-based abnormal sound type according to the sound characteristic data and the vehicle operating parameters to obtain the abnormal sound verification result includes:

[0023] If the parameter-based abnormal noise type is engine knocking abnormal noise, obtaining a spectrogram of the sound feature data;

[0024] Acquire a fifth abnormal sound energy corresponding to the fifth moment on the spectrogram and the first engine frequency, and a sixth abnormal sound energy corresponding to the sixth moment on the spectrogram and the second engine frequency;

[0025] When the third engine speed is greater than the fourth engine speed and the fifth abnormal sound energy is less than the sixth abnormal sound energy, or, the third engine speed is less than the fourth engine speed and the fifth abnormal sound energy is greater than the sixth abnormal sound energy, or, the third engine speed is equal to the fourth engine speed and the fifth abnormal sound energy is not equal to the sixth abnormal sound energy, then the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data.

[0026] In some embodiments, the vehicle operating parameters include a shift signal, the abnormal sound occurrence time includes a seventh time, and the shift signal information indicates whether the shift signal exists at the seventh time; the verifying the parameter-type abnormal sound type according to the sound characteristic data and the vehicle operating parameters to obtain the abnormal sound verification result includes:

[0027] The parameter type abnormal noise type is gear shift impact abnormal noise;

[0028] The abnormal noise verification result is obtained according to the gear shift signal information; wherein, if the gear shift signal does not exist at the seventh moment, the abnormal noise verification result indicates that the abnormal noise prediction data is erroneous data.

[0029] In some embodiments, the vehicle operation parameter includes an accelerator pedal signal, the abnormal sound occurrence time includes an eighth time, and the accelerator pedal signal information indicates whether the accelerator pedal signal exists at the eighth time; the abnormal sound type of the parameter is verified according to the sound characteristic data and the vehicle operation parameter to obtain the abnormal sound verification result, including:

[0030] The parameter type abnormal noise type is the supercharger whistling abnormal noise;

[0031] The abnormal sound verification result is obtained according to the accelerator pedal signal information; wherein, if the accelerator pedal signal does not exist at the eighth moment, the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data.

[0032] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides a vehicle abnormal sound recognition device, the device comprising:

[0033] An acquisition module, used for acquiring reference sound data of a vehicle;

[0034] A first recognition module, configured to perform abnormal sound prediction on the reference sound data by using a preset abnormal sound prediction model to obtain abnormal sound prediction data;

[0035] A verification module, used to verify the abnormal sound prediction data to obtain an abnormal sound verification result; wherein the abnormal sound verification result is used to indicate whether the abnormal sound prediction data is erroneous data;

[0036] a correction module, configured to correct the reference sound data to obtain target sound data if the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data, and upload the target sound data to a preset abnormal sound database;

[0037] An updating module, used for adjusting model parameters of the abnormal sound prediction model based on the abnormal sound database to obtain an abnormal sound recognition model;

[0038] The second recognition module is used to perform abnormal sound recognition on the pre-acquired current sound data according to the abnormal sound recognition model.

[0039] To achieve the above-mentioned purpose, a third aspect of an embodiment of the present application proposes a vehicle, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the method described in the first aspect when executing the computer program.

[0040] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0041] The vehicle abnormal noise identification method and device, vehicle and storage medium proposed in the present application obtain reference sound data of the vehicle; perform abnormal noise prediction on the reference sound data through an abnormal noise prediction model to obtain abnormal noise prediction data. Verify the abnormal noise prediction data to obtain an abnormal noise verification result. If the abnormal noise verification result indicates that the abnormal noise prediction data is erroneous data, the reference sound data is corrected to obtain target sound data, and the target sound data is uploaded to a preset abnormal noise database. The model parameters of the abnormal noise prediction model are adjusted based on the abnormal noise database to obtain an abnormal noise recognition model, and abnormal noise recognition is performed on the current sound data obtained in advance according to the abnormal noise recognition model. In this way, the sound data predicted incorrectly by the abnormal noise prediction model can be continuously collected, and the abnormal noise prediction model can be trained in a targeted manner through the predicted erroneous sound data to obtain an abnormal noise recognition model with higher accuracy. When the current sound data is recognized according to the abnormal noise recognition model, the accuracy of abnormal noise recognition can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is an optional flow chart of the vehicle abnormal noise recognition method provided in the embodiment of the present application;

[0043] Figure 2 yes Figure 1 Flow chart of step S103;

[0044] Figure 3 yes Figure 2 The first flow chart of step S202;

[0045] Figure 4 yes Figure 2 The second flow chart of step S202;

[0046] Figure 5 yes Figure 2 A third flow chart of step S202;

[0047] Figure 6 yes Figure 2 A fourth flow chart of step S202 in FIG.

[0048] Figure 7 yes Figure 2 A fifth flow chart of step S202;

[0049] Figure 8 is a schematic diagram of the structure of a vehicle abnormal sound recognition device provided in an embodiment of the present application;

[0050] Fig. 9 It is a schematic diagram of the hardware structure of the vehicle provided in the embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0054] By monitoring and identifying vehicle sounds, it is possible to identify abnormal sounds in the vehicle sounds and determine the type of abnormal sounds, thereby quickly locating the source of the fault and facilitating troubleshooting. In the related art, vehicle sounds are identified through a pre-trained recognition model to identify the type of abnormal sounds. However, due to the small amount of training data, the recognition accuracy of the recognition model is low.

[0055] Based on this, the embodiments of the present application provide a vehicle abnormal noise recognition method and device, a vehicle and a storage medium, which are intended to enable an abnormal noise prediction model to predict abnormal noise for reference sound data in the vehicle, and after outputting the abnormal noise prediction data, verify the abnormal noise prediction data to obtain an abnormal noise verification result. When the abnormal noise verification result characterizes that the abnormal noise prediction data is erroneous data, it means that the abnormal noise prediction model outputs an erroneous prediction result. At this time. Mark the reference sound data with the correct abnormal noise type to obtain the target sound data, and upload the target sound data to the abnormal noise database. Re-train the abnormal noise prediction model based on the abnormal noise database to obtain an abnormal noise recognition model. By continuously collecting training data and iteratively updating the model, the recognition accuracy of the abnormal noise recognition model is improved. Then, the current sound data is recognized for abnormal noise according to the abnormal noise recognition model, which improves the accuracy of abnormal noise recognition.

[0056] The vehicle abnormal sound recognition method and device, vehicle and storage medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the vehicle abnormal sound recognition method in the embodiments of the present application is described.

[0057] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0058] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0059] The vehicle abnormal sound recognition method provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the vehicle abnormal sound recognition method, etc., but is not limited to the above forms.

[0060] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0061] Please refer to Figure 1 , Figure 1 is an optional flow chart of a vehicle abnormal sound recognition method provided in an embodiment of the present application, wherein the vehicle abnormal sound recognition method is applied to a cloud server. Figure 1 The method may include but is not limited to steps S101 to S106.

[0062] Step S101, obtaining reference sound data of the vehicle;

[0063] Step S102, performing abnormal sound prediction on the reference sound data using a preset abnormal sound prediction model to obtain abnormal sound prediction data;

[0064] Step S103, verifying the abnormal sound prediction data to obtain an abnormal sound verification result; wherein the abnormal sound verification result is used to indicate whether the abnormal sound prediction data is erroneous data;

[0065] Step S104, if the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data, the reference sound data is corrected to obtain target sound data, and the target sound data is uploaded to a preset abnormal sound database;

[0066] Step S105, adjusting the model parameters of the abnormal sound prediction model based on the abnormal sound database to obtain an abnormal sound recognition model;

[0067] Step S106: performing abnormal sound recognition on the pre-acquired current sound data according to the abnormal sound recognition model.

[0068] In step S101 of some embodiments, the reference sound data refers to the sound data collected by the sound collection system on the vehicle. Different sound collection systems can be selected to collect reference sound data according to different vehicle configurations. For example, for vehicles with smart cockpit functions, no additional equipment is required, and reference sound data is collected through the cockpit microphone. For vehicles without smart cockpit functions, additional microphones and audio data collectors need to be installed to collect reference sound data.

[0069] In actual applications, the abnormal sound recognition model is deployed on the cloud server. After the sound collection system on the vehicle collects the reference sound data, for vehicles with smart cockpit function, the smart cockpit uploads the reference sound data to the cloud server through the Internet of Vehicles. For vehicles without smart cockpit function, the vehicle terminal uploads the reference sound data to the cloud server.

[0070] In step S102 of some embodiments, since the collected sound data contains other sounds that do not need to be identified, such as multimedia sounds and speaking sounds. Therefore, before the reference sound data is subjected to abnormal sound identification, it is also necessary to perform speech processing on the reference sound data, and the processing process includes audio filtering, noise reduction, audio slicing, pre-emphasis, framing, windowing, Fourier transform, power spectrum calculation, Mel filter bank filtering, logarithm, discrete cosine transform and MFCC feature extraction, and finally obtains sound feature data. The abnormal sound prediction model performs abnormal sound prediction on the sound feature data to obtain abnormal sound prediction data.

[0071] Specifically, an abnormal noise database is pre-built on the cloud server, and the abnormal noise database stores abnormal noise data and corresponding abnormal noise types. Among them, the abnormal noise data is the data after voice processing, and the abnormal noise types include engine knocking noise, metal knocking noise, supercharger whistle noise, and gearbox rotation noise. The abnormal noise data is divided into a training set and a validation set. The neural network model is trained with the training set and validated with the validation set until the model progress reaches the target, and a trained abnormal noise prediction model is obtained.

[0072] In step S103 of some embodiments, the sound feature data is input into the abnormal sound prediction model for abnormal sound prediction, and the abnormal sound prediction result is output. The abnormal sound prediction result includes the abnormal sound type and the time when the abnormal sound occurs, and the abnormal sound prediction data includes the sound feature data and the corresponding abnormal sound prediction result. The after-sales personnel can judge whether the abnormal sound type corresponding to the sound of the sound feature data at the time when the abnormal sound occurs is consistent with the abnormal sound type output by the model, so as to obtain the abnormal sound verification result. And the abnormal sound verification result is uploaded to the cloud server. Or the cloud server verifies the abnormal sound prediction data according to the preset parameter judgment rule to obtain the abnormal sound verification result. When the abnormal sound type judged by the after-sales personnel is consistent with the abnormal sound type output by the model, it means that the abnormal sound type output by the abnormal sound prediction model is correct. Otherwise, it means that the abnormal sound type output by the abnormal sound prediction model is wrong, that is, the abnormal sound prediction data is wrong data. Among them, the after-sales personnel can repeatedly replace the parts to conduct experiments to obtain the correct abnormal sound type, or experienced after-sales personnel can make subjective judgments through human ears.

[0073] In step S104 of some embodiments, the abnormal sound verification result includes reference sound data and a correct abnormal sound type. When the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data, the correct abnormal sound type is marked for the reference sound data to obtain target sound data, and the target sound data is uploaded to the abnormal sound database.

[0074] In step S105 of some embodiments, after uploading the target sound data to the abnormal sound database, the model parameters of the abnormal sound prediction model are adjusted based on the sound data in the abnormal sound database to obtain the abnormal sound recognition model.

[0075] In actual applications, a preset number of target sound data may be uploaded to the abnormal sound database, and then the model parameters of the abnormal sound prediction model may be adjusted based on the sound data in the abnormal sound database to prevent wasting computing resources due to overly frequent training.

[0076] In step S106 of some embodiments, the current sound data is also sound data collected by a sound collection system on the vehicle. By performing abnormal sound recognition on the current sound data through an abnormal sound recognition model to obtain abnormal sound recognition data, the output abnormal sound recognition result can be more accurate.

[0077] In one example, by continuously verifying the abnormal sound prediction data, the sound data predicted incorrectly by the abnormal sound prediction model are collected. The abnormal sound prediction model is trained again through these predicted incorrect sound data to obtain the abnormal sound recognition model, which can greatly improve the accuracy of model recognition. When the number of verifications reaches the preset number of times, or the proportion of the abnormal sound prediction data as correct data reaches the preset proportion, it means that the abnormal sound recognition model can almost correctly predict the type of abnormal sound, and no further verification is required. In another example, when the number of verifications reaches the preset number of times, or the proportion of the abnormal sound prediction data as correct data reaches the preset proportion, the abnormal sound prediction data can be verified every preset period. If at this time, the abnormal sound verification result indicates that the abnormal sound prediction data is incorrect data, the number of verifications is accumulated again, or the proportion of the abnormal sound prediction data as correct data is counted again. The abnormal sound prediction data is verified every time until the number of verifications reaches the preset number of times again, or the proportion of the abnormal sound prediction data as correct data reaches the preset proportion, and then the abnormal sound prediction data is verified every preset period.

[0078] Steps S101 to S106 shown in the embodiment of the present application are performed by obtaining reference sound data of the vehicle; performing abnormal sound prediction on the reference sound data through an abnormal sound prediction model to obtain abnormal sound prediction data. The abnormal sound prediction data is verified to obtain an abnormal sound verification result. If the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data, the reference sound data is corrected to obtain target sound data, and the target sound data is uploaded to a preset abnormal sound database. The model parameters of the abnormal sound prediction model are adjusted based on the abnormal sound database to obtain an abnormal sound recognition model, and abnormal sound recognition is performed on the current sound data obtained in advance according to the abnormal sound recognition model. In this way, it is possible to continuously collect sound data that is predicted incorrectly by the abnormal sound prediction model, and to train the abnormal sound prediction model in a targeted manner through the predicted erroneous sound data to obtain an abnormal sound recognition model with higher accuracy. When the current sound data is recognized according to the abnormal sound recognition model, the accuracy of abnormal sound recognition can be improved.

[0079] See also Figure 2 In some embodiments, the abnormal sound prediction data includes sound feature data, abnormal sound occurrence time and abnormal sound type. Step S103 may include but is not limited to steps S201 to S202:

[0080] Step S201, if the abnormal sound type is a parameter-based abnormal sound type, then obtain the vehicle operating parameters at the time when the abnormal sound occurs; wherein the parameter-based abnormal sound type is used to characterize the abnormal sound generated by the vehicle when the vehicle operating parameters change;

[0081] Step S202, verifying the parameter-based abnormal sound type according to the sound feature data and the vehicle operating parameters to obtain an abnormal sound verification result.

[0082] In step S201 of some embodiments, the parameter-based abnormal sound type is an abnormal sound generated when the vehicle operating parameters change, including engine abnormal sound, gearbox abnormal sound, steering gear abnormal sound, etc. The parameter-based abnormal sound type usually has the following characteristics: the size of the abnormal sound changes with the change of the vehicle operating parameters; when performing a certain operation, the abnormal sound is generated or the abnormal sound is amplified, such as stepping on the accelerator, turning the steering wheel, etc. Therefore, if the abnormal sound type predicted by the abnormal sound prediction model is a parameter-based abnormal sound type, the abnormal sound type predicted by the model can be verified to be correct through the sound feature data and the vehicle operating parameters at the time when the abnormal sound occurs.

[0083] In one example, the parameter-free abnormal noise type is the other abnormal noises except the parameter-based abnormal noise type, such as knocking noises caused by assembly problems, etc. If the abnormal noise type predicted by the abnormal noise prediction model is the parameter-free abnormal noise type, the after-sales personnel can continue to verify whether the abnormal noise type predicted by the model is correct.

[0084] In step S202 of some embodiments, the corresponding parameter determination rule can be obtained according to the parameter-based abnormal noise type. In one example, the parameter determination rule is set in advance according to the characteristics corresponding to the parameter-based abnormal noise type. For example, if the size of the abnormal noise corresponding to the parameter-based abnormal noise type changes with the change of the vehicle operating parameters, the corresponding parameter determination rule is that at different times when the abnormal noise occurs, the change trend of the value of the vehicle operating parameter is the same as the change trend of the size of the abnormal noise, that is, when the value of the vehicle operating parameter becomes larger, the abnormal noise also becomes larger, indicating that the parameter-based abnormal noise type predicted by the abnormal noise prediction model is correct. If the parameter-based abnormal noise type is that the abnormal noise is generated when a certain operation is performed, for example, the gear shift impact abnormal noise is an abnormal noise generated when the gear shift operation is performed. The corresponding parameter determination rule is that if the vehicle operating parameters at the time when the abnormal noise occurs indicate that the corresponding operation is being performed, it means that the parameter-based abnormal noise type predicted by the abnormal noise prediction model is correct.

[0085] In the steps S201 to S202 shown in this embodiment, when the abnormal sound type is a parameter-based abnormal sound type, the vehicle operation parameters at the time when the abnormal sound occurs are obtained. Thus, the parameter-based abnormal sound type can be verified according to the sound feature data and the vehicle operation parameters, and it can be determined whether the parameter-based abnormal sound type predicted by the abnormal sound prediction model is correct.

[0086] See also Figure 3In some embodiments, the vehicle operating parameters include a first engine speed, a second engine speed, a first balance shaft frequency, and a second balance shaft frequency. The abnormal sound occurrence time includes a first time and a second time. The first engine speed is the speed of the engine at the first time, the second engine speed is the speed of the engine at the second time, the first balance shaft frequency is the frequency of the balance shaft at the first time, and the second balance shaft frequency is the frequency of the balance shaft at the second time. Step S202 may include but is not limited to steps S301 to S303:

[0087] Step S301, if the parameter-based abnormal noise type is an abnormal noise of an engine balance shaft, a spectrogram of the sound feature data is obtained;

[0088] Step S302, obtaining a first abnormal sound energy corresponding to a first moment and a first balance axis frequency on the spectrogram, and a second abnormal sound energy corresponding to a second moment and a second balance axis frequency on the spectrogram;

[0089] Step S303, when the first engine speed is greater than the second engine speed and the first abnormal sound energy is less than the second abnormal sound energy, or, the first engine speed is less than the second engine speed and the first abnormal sound energy is greater than the second abnormal sound energy, or, the first engine speed is equal to the second engine speed and the first abnormal sound energy is not equal to the second abnormal sound energy, then the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data.

[0090] In step S301 of some embodiments, the abnormal noise of the engine balance shaft is a common abnormal noise in vehicles. The size of the abnormal noise usually changes with the change of the engine speed, resulting in the periodic generation of abnormal noise. Therefore, there will be multiple abnormal noise occurrence times in the sound feature data. The first moment and the second moment are different abnormal noise occurrence times. In order to obtain the engine speed and the frequency of the balance shaft when the abnormal noise occurs, the frequency of the balance shaft and the engine speed at the first moment are obtained to obtain the first balance shaft frequency and the first engine speed. The frequency of the balance shaft and the engine speed at the second moment are obtained to obtain the second balance shaft frequency and the second engine speed.

[0091] In one example, the frequency of the balance shaft can be calculated using the following formulas (1)-(2):

[0092] Nb=Na×t, (1)

[0093] fb=Nb / 60, (2)

[0094] Among them, Nb represents the rotation speed of the balance shaft, Na represents the rotation speed of the engine, t represents the transmission ratio of the balance shaft, and fb represents the frequency of the balance shaft.

[0095] Specifically, when the abnormal sound type of the parameter class is the abnormal sound of the engine balance shaft, the corresponding abnormal sound volume usually changes with the change of the engine speed. Therefore, by obtaining the spectrogram of the sound feature data, the change of the abnormal sound volume is judged. Among them, the graph displayed by the Fourier analysis of the voice signal is called a spectrogram. A spectrogram is a three-dimensional frequency spectrum, representing the graph of the voice spectrum changing with time. The abscissa of the spectrogram is time, the ordinate is frequency, and the coordinate point value represents the voice data energy (unit: decibel). In this embodiment, the coordinate point value represents the abnormal sound energy, and the greater the abnormal sound energy, the greater the abnormal sound volume.

[0096] In step S302 of some embodiments, in order to obtain the sound volume generated by the abnormal sound of the engine balance shaft at the moment when the abnormal sound occurs, the abnormal sound energy corresponding to the first moment on the abscissa and the first balance shaft frequency on the ordinate of the spectrogram is obtained to obtain the first abnormal sound energy. The abnormal sound energy corresponding to the second moment on the abscissa and the second balance shaft frequency on the ordinate of the spectrogram is obtained to obtain the second abnormal sound energy.

[0097] In step S303 of some embodiments, the first engine speed is represented as Na1, the second engine speed is represented as Na2, the first abnormal sound energy is represented as P1, and the first abnormal sound energy is represented as P2. When Na1 > Na2 and P1 < P2, or Na1 < Na2 and P1 > P2, or Na1 = Na2 and P1 ≠ P2, it indicates that the change trend of the abnormal sound volume is not the same as the change trend of the engine speed, indicating that the abnormal sound type is not the abnormal sound of the engine balance shaft, that is, the abnormal sound verification result indicates that the abnormal sound prediction data is incorrect data.

[0098] In an example, if there is Na1 = Na2 and P1 = P2, the engine speed at the moment when the abnormal sound occurs in the next cycle can be obtained until the engine speeds at different moments when the abnormal sound occurs are different, and then the abnormal sound verification result is obtained through the above method. Among them, since there may be errors in the calculated abnormal sound energy, when the difference between the first abnormal sound energy P1 and the second abnormal sound energy P2 is within a certain range, P1 = P2 can be considered.

[0099] Steps S301 to S303 illustrated in this embodiment can accurately judge whether the parameter type abnormal sound predicted by the abnormal sound prediction model is the abnormal sound of the engine balance shaft is predicted incorrectly.

[0100] Please refer to Figure 4In some embodiments, the vehicle operating parameters include a first gearbox speed, a second gearbox speed, a first gearbox frequency, and a second gearbox frequency. The abnormal sound occurrence time includes a third time and a fourth time. The first gearbox speed is the speed of the gearbox at the third time. The second gearbox speed is the speed of the gearbox at the fourth time. The first gearbox frequency is the frequency of the gearbox at the third time. The second gearbox frequency is the frequency of the gearbox at the fourth time. Step S202 may include but is not limited to steps S401 to S403:

[0101] Step S401, if the parameter class abnormal sound type is the abnormal sound of the gearbox rotation, then obtain the spectrogram of the sound feature data;

[0102] Step S402, obtaining a third abnormal sound energy corresponding to a third moment on the spectrogram and a first gearbox frequency, and a fourth abnormal sound energy corresponding to a fourth moment on the spectrogram and a second gearbox frequency;

[0103] Step S403, when the first gearbox speed is greater than the second gearbox speed and the third abnormal sound energy is less than the fourth abnormal sound energy, or, the first gearbox speed is less than the second gearbox speed and the third abnormal sound energy is greater than the fourth abnormal sound energy, or, the first gearbox speed is equal to the second gearbox speed and the third abnormal sound energy is not equal to the fourth abnormal sound energy, then the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data.

[0104] In step S401 of some embodiments, the abnormal noise caused by the gearbox rotation is a common abnormal noise in vehicles. The size of the abnormal noise usually changes with the change of the gearbox speed, resulting in periodic abnormal noise. Therefore, there will be multiple abnormal noise occurrence times in the sound feature data. The third moment and the fourth moment are different abnormal noise occurrence times. In order to obtain the frequency and speed of the gearbox when the abnormal noise occurs, the frequency and speed of the gearbox at the third moment are obtained to obtain the first gearbox frequency and the first gearbox speed. The frequency and speed of the gearbox at the fourth moment are obtained to obtain the second gearbox frequency and the second gearbox speed.

[0105] In one example, the frequency of the gearbox can be calculated by the following formula (3):

[0106] fc=Nc / 60, (3)

[0107] Among them, Nc represents the speed of the gearbox, and fc represents the frequency of the gearbox.

[0108] Specifically, when the parameter-based abnormal noise type is the abnormal noise of the gearbox rotation, the corresponding abnormal noise volume usually changes with the change of the gearbox speed. Therefore, by obtaining the spectrogram of the sound feature data, the change of the abnormal noise volume is determined.

[0109] In step S402 of some embodiments, in order to obtain the sound volume generated by the abnormal noise of the transmission during rotation at the moment when the abnormal noise occurs, the abnormal noise energy corresponding to the third moment on the abscissa and the first transmission frequency on the ordinate of the spectrogram is obtained to obtain the third abnormal noise energy. The abnormal noise energy corresponding to the fourth moment on the abscissa and the second transmission frequency on the ordinate of the spectrogram is obtained to obtain the fourth abnormal noise energy.

[0110] In step S403 of some embodiments, the rotational speed of the first transmission is denoted as Nc1, the rotational speed of the second transmission is denoted as Nc2, the third abnormal noise energy is denoted as P3, and the fourth abnormal noise energy is denoted as P4. When Nc1 > Nc2 and P3 < P4, or Nc1 < Nc2 and P3 > P4, or Nc1 = Nc2 and P3 ≠ P4, it indicates that the changing trend of the sound volume of the abnormal noise is not the same as the changing trend of the rotational speed of the transmission, indicating that the type of the abnormal noise is not the abnormal noise of the transmission rotation, that is, the abnormal noise verification result indicates that the abnormal noise prediction data is incorrect data.

[0111] In an example, if Nc1 = Nc2 and P3 = P4 exist, the rotational speed of the transmission at the moment when the abnormal noise occurs in the next cycle can be obtained until the rotational speeds of the transmission at different moments when the abnormal noise occurs are different, and then the abnormal noise verification result is obtained through the above method. Among them, since there may be errors in the calculated abnormal noise energy, when the difference between the third abnormal noise energy P3 and the fourth abnormal noise energy P4 is within a certain range, P3 = P4 can be considered.

[0112] Steps S401 to S403 illustrated in this embodiment can accurately determine whether the parameter type of abnormal noise predicted by the abnormal noise prediction model as the abnormal noise of the transmission rotation is predicted incorrectly.

[0113] Please refer to Figure 5 , in some embodiments, the vehicle operating parameters include the third engine rotational speed, the fourth engine rotational speed, the first engine frequency, and the second engine frequency. The moments when the abnormal noise occurs include the fifth moment and the sixth moment. The third engine rotational speed is the rotational speed of the engine at the fifth moment, the fourth engine rotational speed is the rotational speed of the engine at the sixth moment, the first engine frequency is the frequency of the engine at the fifth moment, and the second engine frequency is the frequency of the engine at the sixth moment. Step S202 includes but is not limited to steps S501 to S503:

[0114] Step S501, if the parameter type of the abnormal noise is the engine knocking abnormal noise, then obtain the spectrogram of the sound feature data;

[0115] Step S502, obtain the fifth abnormal noise energy corresponding to the fifth moment and the first engine frequency on the spectrogram, and the sixth abnormal noise energy corresponding to the sixth moment and the second engine frequency on the spectrogram;

[0116] Step S503: When the rotational speed of the third engine is greater than that of the fourth engine and the abnormal sound energy of the fifth is less than that of the sixth, or when the rotational speed of the third engine is less than that of the fourth engine and the abnormal sound energy of the fifth is greater than that of the sixth, or when the rotational speed of the third engine is equal to that of the fourth engine and the abnormal sound energy of the fifth is not equal to that of the sixth, the abnormal sound verification result indicates that the abnormal sound prediction data is incorrect data.

[0117] In step S501 of some embodiments, engine knocking abnormal sound is a common abnormal sound in vehicles. The magnitude of this abnormal sound usually changes with the change of the engine rotational speed, resulting in the periodic generation of abnormal sounds. Therefore, there will be multiple moments when the abnormal sound occurs in the sound feature data. The fifth moment and the sixth moment are respectively different moments when the abnormal sound occurs. In order to obtain the frequency and rotational speed of the engine when the abnormal sound occurs, the frequency and rotational speed of the engine at the fifth moment are obtained, resulting in the first engine frequency and the rotational speed of the third engine. The frequency and rotational speed of the engine at the sixth moment are obtained, resulting in the second engine frequency and the rotational speed of the fourth engine.

[0118] In one example, the frequency of the engine can be calculated by the following formula (4):

[0119] fa = Na / 60, (4)

[0120] where Na represents the rotational speed of the engine and fa represents the frequency of the engine.

[0121] Specifically, when the parameter type of the abnormal sound is engine knocking abnormal sound, the corresponding magnitude of the abnormal sound usually changes with the change of the engine rotational speed. Therefore, by obtaining the spectrogram of the sound feature data, the change of the magnitude of the abnormal sound is judged.

[0122] In step S502 of some embodiments, in order to obtain the magnitude of the sound generated by the engine knocking abnormal sound at the moment when the abnormal sound occurs, the abnormal sound energy corresponding to the fifth moment on the abscissa and the first engine frequency on the ordinate of the spectrogram is obtained, resulting in the abnormal sound energy of the fifth. The abnormal sound energy corresponding to the sixth moment on the abscissa and the second engine frequency on the ordinate of the spectrogram is obtained, resulting in the abnormal sound energy of the sixth.

[0123] In step S503 of some embodiments, the rotational speed of the third engine is denoted as Na3, the rotational speed of the fourth engine is denoted as Na4, the abnormal sound energy of the fifth is denoted as P5, and the abnormal sound energy of the sixth is denoted as P6. When Na3 > Na4 and P5 < P6, or when Na3 < Na4 and P5 > P6, or when Na3 = Na4 and P5 ≠ P6, it indicates that the change trend of the magnitude of this abnormal sound is not the same as the change trend of the engine rotational speed, indicating that this type of abnormal sound is not engine knocking abnormal sound, that is, the abnormal sound verification result indicates that the abnormal sound prediction data is incorrect data.

[0124] In one example, if Na3=Na4 and P5=P6, the engine speed at the time when the abnormal sound occurs in the next cycle can be obtained, until the engine speed is different at different times when the abnormal sound occurs, and then the abnormal sound verification result is obtained by the above method. Among them, since the calculated abnormal sound energy may have errors, when the difference between the fifth abnormal sound energy P5 and the sixth abnormal sound energy P6 is within a certain range, it can be considered that P5=P6.

[0125] Steps S501 to S503 shown in this embodiment can accurately determine whether the parameter-based abnormal noise type predicted by the abnormal noise prediction model as engine knocking abnormal noise is predicted incorrectly.

[0126] See also Figure 6 In some embodiments, the vehicle operation parameter includes a shift signal, the abnormal sound occurrence time includes the seventh time, and the shift signal information indicates whether there is a shift signal at the seventh time. Step S202 may include but is not limited to steps S601 to S602:

[0127] Step S601, the parameter type abnormal noise is a gear shift impact abnormal noise;

[0128] Step S602, obtaining an abnormal sound verification result according to the gear shift signal information; wherein, if there is no gear shift signal at the seventh moment, the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data.

[0129] In steps S601 to S602 illustrated in the present embodiment, the gear shift shock abnormal noise is a common abnormal noise in vehicles, and the abnormal noise is usually generated at the time of gear shifting. If the gear shift shock abnormal noise occurs at the seventh moment, and there is a gear shift signal at the seventh moment, it means that the parameter-type abnormal noise type predicted by the abnormal noise prediction model as the gear shift shock abnormal noise is correct. If the gear shift shock abnormal noise occurs at the seventh moment, and there is no gear shift signal at the seventh moment, it means that the parameter-type abnormal noise type predicted by the abnormal noise prediction model as the gear shift shock abnormal noise is wrong, that is, the abnormal noise verification result characterizes that the abnormal noise prediction data is erroneous data. The present embodiment can accurately determine whether the parameter-type abnormal noise type predicted by the abnormal noise prediction model as the gear shift shock abnormal noise is predicted incorrectly.

[0130] See also Figure 7 In some embodiments, the vehicle operation parameter includes an accelerator pedal signal, the abnormal sound occurrence time includes the eighth time, and the accelerator pedal signal information indicates whether there is an accelerator pedal signal at the eighth time. Step S202 may include but is not limited to steps S701 to S702:

[0131] Step S701, the parameter type abnormal sound type is the abnormal sound of the supercharger whistle;

[0132] Step S702, obtaining an abnormal sound verification result according to the accelerator pedal signal information; wherein, if there is no accelerator pedal signal at the eighth moment, the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data.

[0133] In steps S701 to S702 illustrated in this embodiment, the supercharger whistle abnormal sound is a common abnormal sound in vehicles, and the abnormal sound usually produces a sharp whistle when the accelerator is quickly released. If the supercharger whistle abnormal sound occurs at the eighth moment, and there is a throttle pedal signal at the eighth moment, it means that the parameter type abnormal sound type predicted by the abnormal sound prediction model as the supercharger whistle abnormal sound is correct. If the supercharger whistle abnormal sound occurs at the eighth moment, and there is no throttle pedal signal at the eighth moment, it means that the parameter type abnormal sound type predicted by the abnormal sound prediction model as the supercharger whistle abnormal sound is wrong, that is, the abnormal sound verification result characterizes that the abnormal sound prediction data is erroneous data. This embodiment can accurately determine whether the parameter type abnormal sound type predicted by the abnormal sound prediction model as the supercharger whistle abnormal sound is predicted incorrectly.

[0134] See also Figure 8 The embodiment of the present application also provides a vehicle abnormal sound recognition device, which can implement the above-mentioned vehicle abnormal sound recognition method, and the device includes:

[0135] An acquisition module 801 is used to acquire reference sound data of a vehicle;

[0136] The first recognition module 802 is used to perform abnormal sound prediction on the reference sound data by using a preset abnormal sound prediction model to obtain abnormal sound prediction data;

[0137] The verification module 803 is used to verify the abnormal sound prediction data and obtain an abnormal sound verification result; wherein the abnormal sound verification result is used to indicate whether the abnormal sound prediction data is erroneous data;

[0138] The correction module 804 is used to correct the reference sound data to obtain target sound data if the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data, and upload the target sound data to a preset abnormal sound database;

[0139] An updating module 805 is used to adjust the model parameters of the abnormal sound prediction model based on the abnormal sound database to obtain an abnormal sound recognition model;

[0140] The second recognition module 806 is used to perform abnormal sound recognition on the pre-acquired current sound data according to the abnormal sound recognition model.

[0141] The specific implementation of the vehicle abnormal sound recognition device is basically the same as the specific implementation of the above-mentioned vehicle abnormal sound recognition method, and will not be repeated here.

[0142] An embodiment of the present application also provides a vehicle, the vehicle includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned vehicle abnormal sound recognition method when executing the computer program.

[0143] See also Fig. 9 , Fig. 9 The hardware structure of a vehicle of another embodiment is illustrated, and the vehicle includes:

[0144] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0145] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the vehicle abnormal sound recognition method of the embodiment of this application;

[0146] Input / output interface 903, used to implement information input and output;

[0147] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0148] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0149] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0150] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned vehicle abnormal sound recognition method is implemented.

[0151] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0152] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0153] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0154] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0156] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0157] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0158] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0159] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0160] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0161] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0162] The preferred embodiments of the present application are described above with reference to the accompanying drawings, but the scope of the rights of the present application is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present application should be within the scope of the rights of the present application.

Claims

1. A vehicle abnormal noise recognition method, characterized in that: The method is applied to a cloud server, and the method includes: Acquiring reference sound data of the vehicle; Performing abnormal noise prediction on the reference sound data through a preset abnormal noise prediction model to obtain abnormal noise prediction data; Verifying the abnormal sound prediction data to obtain an abnormal sound verification result; wherein the abnormal sound verification result is used to indicate whether the abnormal sound prediction data is erroneous data; If the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data, the reference sound data is corrected to obtain target sound data, and the target sound data is uploaded to a preset abnormal sound database; Adjusting the model parameters of the abnormal sound prediction model based on the abnormal sound database to obtain an abnormal sound recognition model; The abnormal sound recognition is performed on the pre-acquired current sound data according to the abnormal sound recognition model.

2. The method according to claim 1, characterized in that The abnormal sound prediction data includes sound feature data, abnormal sound occurrence time and abnormal sound type, and the abnormal sound prediction data is verified to obtain an abnormal sound verification result, including: If the abnormal sound type is a parameter-based abnormal sound type, then the vehicle operating parameters at the time when the abnormal sound occurs are obtained; wherein the parameter-based abnormal sound type is used to characterize the abnormal sound generated by the vehicle when the vehicle operating parameters change; The parameter-based abnormal sound type is verified according to the sound characteristic data and the vehicle operating parameters to obtain the abnormal sound verification result.

3. The method according to claim 2, characterized in that The vehicle operation parameters include a first engine speed, a second engine speed, a first balance shaft frequency, and a second balance shaft frequency. The abnormal sound occurrence time includes a first time and a second time. The first engine speed is the speed of the engine at the first time, the second engine speed is the speed of the engine at the second time, the first balance shaft frequency is the frequency of the balance shaft at the first time, and the second balance shaft frequency is the frequency of the balance shaft at the second time. The abnormal sound type of the parameter is verified according to the sound characteristic data and the vehicle operation parameters to obtain the abnormal sound verification result, including: If the parameter-based abnormal noise type is an abnormal noise of an engine balance shaft, obtaining a spectrogram of the sound feature data; Acquire a first abnormal sound energy corresponding to the first moment and the first balance shaft frequency on the spectrogram, and a second abnormal sound energy corresponding to the second moment and the second balance shaft frequency on the spectrogram; When the first engine speed is greater than the second engine speed and the first abnormal sound energy is less than the second abnormal sound energy, or, the first engine speed is less than the second engine speed and the first abnormal sound energy is greater than the second abnormal sound energy, or, the first engine speed is equal to the second engine speed and the first abnormal sound energy is not equal to the second abnormal sound energy, the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data.

4. The method according to claim 2, characterized in that: The vehicle operation parameters include a first gearbox speed, a second gearbox speed, a first gearbox frequency, and a second gearbox frequency. The abnormal sound occurrence time includes a third time and a fourth time. The first gearbox speed is the speed of the gearbox at the third time, the second gearbox speed is the speed of the gearbox at the fourth time, the first gearbox frequency is the frequency of the gearbox at the third time, and the second gearbox frequency is the frequency of the gearbox at the fourth time. The parameter-type abnormal sound type is verified according to the sound feature data and the vehicle operation parameters to obtain the abnormal sound verification result, including: If the parameter-based abnormal noise type is a gearbox rotation abnormal noise, obtaining a spectrogram of the sound feature data; Acquire a third abnormal sound energy corresponding to the third moment on the spectrogram and the first gearbox frequency, and a fourth abnormal sound energy corresponding to the fourth moment on the spectrogram and the second gearbox frequency; When the first gearbox speed is greater than the second gearbox speed and the third abnormal sound energy is less than the fourth abnormal sound energy, or, the first gearbox speed is less than the second gearbox speed and the third abnormal sound energy is greater than the fourth abnormal sound energy, or, the first gearbox speed is equal to the second gearbox speed and the third abnormal sound energy is not equal to the fourth abnormal sound energy, the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data.

5. The method according to claim 2, characterized in that: The vehicle operation parameters include a third engine speed, a fourth engine speed, a first engine frequency, and a second engine frequency. The abnormal sound occurrence time includes a fifth time and a sixth time. The third engine speed is the speed of the engine at the fifth time. The fourth engine speed is the speed of the engine at the sixth time. The first engine frequency is the frequency of the engine at the fifth time. The second engine frequency is the frequency of the engine at the sixth time. The parameter-based abnormal sound type is verified according to the sound characteristic data and the vehicle operation parameters to obtain the abnormal sound verification result, including: If the parameter-based abnormal noise type is engine knocking abnormal noise, obtaining a spectrogram of the sound feature data; Acquire a fifth abnormal sound energy corresponding to the fifth moment on the spectrogram and the first engine frequency, and a sixth abnormal sound energy corresponding to the sixth moment on the spectrogram and the second engine frequency; When the third engine speed is greater than the fourth engine speed and the fifth abnormal sound energy is less than the sixth abnormal sound energy, or, the third engine speed is less than the fourth engine speed and the fifth abnormal sound energy is greater than the sixth abnormal sound energy, or, the third engine speed is equal to the fourth engine speed and the fifth abnormal sound energy is not equal to the sixth abnormal sound energy, then the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data.

6. The method according to claim 2, characterized in that The vehicle operation parameters include a shift signal, the abnormal sound occurrence time includes a seventh time, and the shift signal information indicates whether the shift signal exists at the seventh time; the abnormal sound type of the parameter is verified according to the sound characteristic data and the vehicle operation parameters to obtain the abnormal sound verification result, including: The parameter type abnormal noise type is gear shift impact abnormal noise; The abnormal noise verification result is obtained according to the gear shift signal information; wherein, if the gear shift signal does not exist at the seventh moment, the abnormal noise verification result indicates that the abnormal noise prediction data is erroneous data.

7. The method according to claim 2, characterized in that The vehicle operation parameters include an accelerator pedal signal, the abnormal sound occurrence time includes an eighth time, and the accelerator pedal signal information indicates whether the accelerator pedal signal exists at the eighth time; the abnormal sound type of the parameter is verified according to the sound characteristic data and the vehicle operation parameters to obtain the abnormal sound verification result, including: The parameter type abnormal noise type is the supercharger whistling abnormal noise; The abnormal sound verification result is obtained according to the accelerator pedal signal information; wherein, if the accelerator pedal signal does not exist at the eighth moment, the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data.

8. A vehicle abnormal noise recognition device, characterized in that: The device comprises: An acquisition module, used for acquiring reference sound data of a vehicle; A first recognition module, configured to perform abnormal sound prediction on the reference sound data by using a preset abnormal sound prediction model to obtain abnormal sound prediction data; A verification module, used to verify the abnormal sound prediction data to obtain an abnormal sound verification result; wherein the abnormal sound verification result is used to indicate whether the abnormal sound prediction data is erroneous data; a correction module, configured to correct the reference sound data to obtain target sound data if the abnormal sound verification result indicates that the abnormal sound prediction data is erroneous data, and upload the target sound data to a preset abnormal sound database; An updating module, used for adjusting model parameters of the abnormal sound prediction model based on the abnormal sound database to obtain an abnormal sound recognition model; The second recognition module is used to perform abnormal sound recognition on the pre-acquired current sound data according to the abnormal sound recognition model.

9. A vehicle, characterized in that: The vehicle includes a memory and a processor, the memory stores a computer program, and the processor implements the vehicle abnormal sound recognition method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the vehicle abnormal noise recognition method according to any one of claims 1 to 7 is implemented.

Images