Sound wave simulation method and device, storage medium and vehicle

Abstract

The invention relates to a sound wave simulation method and device, a storage medium and a vehicle. According to the sound wave simulation method, when it is determined that data missing exists in sampling data within a specified time period, historical data of vehicle kinetic parameters within a historical time period are obtained; determining a target completion model corresponding to the vehicle kinetic parameters from a plurality of preset completion models, and effectively and accurately determining completion data of the vehicle kinetic parameters according to the historical data of the vehicle kinetic parameters and the target completion model; therefore, sound wave simulation is carried out through the complemented data of the parameters with data missing and the sampling data corresponding to the parameters without data missing in the multiple vehicle dynamic parameters, sound waves can be effectively simulated, abnormal phenomena such as lagging, trailing and repetition of the simulated sound waves can be avoided, the stability of the vehicle simulated sound waves is ensured, and the vehicle simulation efficiency is improved. And the experience of the vehicle user is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of vehicles, and in particular, to a method and device for simulating engine sound, a storage medium, and a vehicle. Background Art

[0002] Due to the strong instantaneous power output characteristics of electric vehicles, electric vehicles are sought after by many vehicle users who pursue an ultimate driving experience. During the driving process of an electric vehicle, the operation of the motor does not generate noise and vibration. Driving without engine sound undoubtedly lacks a dimension of fun, which is clearly contrary to the ultimate driving experience. Summary of the Invention

[0003] To overcome the problems existing in the related art, the present disclosure provides a method and device for simulating engine sound, a storage medium, and a vehicle.

[0004] According to a first aspect of an embodiment of the present disclosure, there is provided a method for simulating engine sound, the method including:

[0005] Receiving sampling data of a plurality of vehicle dynamics parameters reported;

[0006] For each vehicle dynamics parameter among the plurality of vehicle dynamics parameters, in the case where it is determined that there is missing data in the sampling data within a specified time period, obtaining historical data of the vehicle dynamics parameter within a historical time period, and determining a target completion model corresponding to the vehicle dynamics parameter from a plurality of preset completion models, where different preset completion models correspond to different vehicle dynamics parameters;

[0007] Predicting the missing data of the vehicle dynamics parameter based on the historical data and the target completion model of the vehicle dynamics parameter to obtain completion data of the vehicle dynamics parameter;

[0008] Performing engine sound simulation based on the completion data of the parameters with missing data among the plurality of vehicle dynamics parameters and the sampling data corresponding to the parameters without missing data.

[0009] Optionally, the determining method of the preset completion model corresponding to each vehicle dynamics parameter includes:

[0010] Obtaining a training data set corresponding to each vehicle dynamics parameter among the plurality of vehicle dynamics parameters under various working conditions;

[0011] Respectively determining a plurality of candidate models through the training data set corresponding to each vehicle dynamics parameter;

[0012] Determining the preset completion model corresponding to the vehicle dynamics parameter according to the plurality of candidate models corresponding to each vehicle dynamics parameter.

[0013] Optionally, the determining the preset completion model corresponding to the vehicle dynamics parameter according to the multiple standby models corresponding to each vehicle dynamics parameter includes:

[0014] Obtaining a prediction error corresponding to each of the plurality of standby models corresponding to each of the vehicle dynamics parameters;

[0015] The model with the smallest prediction error among the multiple standby models corresponding to each of the vehicle dynamics parameters is used as the preset completion model corresponding to the vehicle dynamics parameter.

[0016] Optionally, predicting missing data of the vehicle dynamics parameters according to the historical data of the vehicle dynamics parameters and the target completion model to obtain the completion data of the vehicle dynamics parameters includes:

[0017] Inputting the historical data of the vehicle dynamics parameter into the target completion model corresponding to the vehicle dynamics parameter to obtain prediction data output by the target completion model;

[0018] Determining a target difference between the predicted data and the previously reported sampling data;

[0019] The predicted data is corrected according to the target difference to obtain corrected supplementary data.

[0020] Optionally, the correcting the predicted data according to the target difference to obtain corrected supplementary data includes:

[0021] When the target difference is greater than or equal to a first preset difference threshold, obtaining a preset upper limit value, and using the upper limit value as the supplementary data;

[0022] When the target difference is less than a second preset difference threshold, a preset lower limit is obtained and the lower limit is used as the supplementary data, wherein the first preset difference threshold is greater than the second preset difference threshold.

[0023] Optionally, determining a target completion model corresponding to the vehicle dynamics parameter from a plurality of preset completion models includes:

[0024] Determining parameter identifiers corresponding to the missing vehicle dynamics parameters;

[0025] A preset completion model whose model identifier matches the parameter identifier among the multiple preset completion models is used as the target completion model corresponding to the vehicle dynamics parameter.

[0026] Optionally, the acoustic wave simulation based on the complemented data of the parameters with missing data among the multiple vehicle dynamics parameters and the sampled data corresponding to the parameters without missing data includes:

[0027] Determine the preset weight of each vehicle dynamics parameter;

[0028] Perform weighted summation on the complemented data of the parameters with missing data among the multiple vehicle dynamics parameters and the sampled data corresponding to the parameters without missing data according to the preset weight to obtain the data to be used for simulation;

[0029] Determine the acoustic wave loudness according to the data to be used for simulation.

[0030] Optionally, the determination that the sampled data has missing data within a specified time period includes:

[0031] In the case where it is determined that the sampled data corresponding to the vehicle dynamics parameter has not been received within the specified time period, it is determined that the sampled data has missing data.

[0032] Optionally, the method further includes:

[0033] Determine the target duration of continuous missing of each vehicle dynamics parameter;

[0034] In the case where the target duration is greater than a preset duration threshold, output a preset fault prompt message.

[0035] According to the second aspect of the embodiments of the present disclosure, there is provided an acoustic wave simulation device, and the device includes:

[0036] A receiving module, configured to receive the sampled data of multiple reported vehicle dynamics parameters;

[0037] An acquisition module, configured to, for each vehicle dynamics parameter among the multiple vehicle dynamics parameters, in the case where it is determined that the sampled data has missing data within a specified time period, acquire the historical data of the vehicle dynamics parameter in a historical time period, and determine the target complementation model corresponding to the vehicle dynamics parameter from multiple preset complementation models, where different preset complementation models correspond to different vehicle dynamics parameters;

[0038] A first determination module, configured to predict the missing data of the vehicle dynamics parameter according to the historical data of the vehicle dynamics parameter and the target complementation model to obtain the complemented data of the vehicle dynamics parameter;

[0039] A simulation module, configured to perform acoustic wave simulation according to the complemented data of the parameters with missing data among the multiple vehicle dynamics parameters and the sampled data corresponding to the parameters without missing data.

[0040] Optionally, the acquisition module is configured to:

[0041] Acquire a training data set corresponding to each of the vehicle dynamics parameters in the plurality of vehicle dynamics parameters under a plurality of working conditions;

[0042] Determine a plurality of models to be used respectively by using the training data set corresponding to each of the vehicle dynamics parameters;

[0043] The preset completion model corresponding to the vehicle dynamics parameter is determined according to the multiple standby models corresponding to each of the vehicle dynamics parameters.

[0044] Optionally, the acquisition module is configured to:

[0045] Obtaining a prediction error corresponding to each of the plurality of standby models corresponding to each of the vehicle dynamics parameters;

[0046] The model with the smallest prediction error among the multiple standby models corresponding to each of the vehicle dynamics parameters is used as the preset completion model corresponding to the vehicle dynamics parameter.

[0047] Optionally, the first determining module is configured to:

[0048] Inputting the historical data of the vehicle dynamics parameter into the target completion model corresponding to the vehicle dynamics parameter to obtain prediction data output by the target completion model;

[0049] Determining a target difference between the predicted data and the previously reported sampling data;

[0050] The predicted data is corrected according to the target difference to obtain corrected supplementary data.

[0051] Optionally, the first determining module is configured to:

[0052] When the target difference is greater than or equal to a first preset difference threshold, obtaining a preset upper limit value, and using the upper limit value as the supplementary data;

[0053] When the target difference is less than a second preset difference threshold, a preset lower limit is obtained and the lower limit is used as the supplementary data, wherein the first preset difference threshold is greater than the second preset difference threshold.

[0054] Optionally, the acquisition module is configured to:

[0055] Determining parameter identifiers corresponding to the missing vehicle dynamics parameters;

[0056] A preset completion model whose model identifier matches the parameter identifier among the multiple preset completion models is used as the target completion model corresponding to the vehicle dynamics parameter.

[0057] Optionally, the analog module is configured to:

[0058] determining a preset weight for each vehicle dynamics parameter;

[0059] performing weighted summation of the supplementary data of the parameters with missing data and the sampled data corresponding to the parameters without missing data among the plurality of vehicle dynamics parameters according to the preset weights to obtain stand-by simulation data;

[0060] The loudness of the sound wave is determined according to the simulation data to be used.

[0061] Optionally, the acquisition module is configured to:

[0062] When it is determined that the sampled data corresponding to the vehicle dynamics parameter is not received within the specified time period, it is determined that there is data missing in the sampled data.

[0063] Optionally, the method further comprises:

[0064] A second determination module is configured to determine a target duration of continuous missing of each of the vehicle dynamics parameters;

[0065] The output module is configured to output preset fault prompt information when the target duration is greater than a preset duration threshold.

[0066] According to a third aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the sound wave simulation method provided in the first aspect of the present disclosure are implemented.

[0067] According to a fourth aspect of an embodiment of the present disclosure, there is provided a vehicle, the vehicle comprising a power component, a central processing unit and an audio processor;

[0068] The central processor is connected to the power component and the audio processor, and is used to receive the sampled data of the multiple vehicle dynamics parameters reported by the power component, and forward the sampled data of the multiple vehicle dynamics parameters to the audio processor;

[0069] The audio processor is used to receive sampled data of multiple reported vehicle dynamics parameters; for each vehicle dynamics parameter among the multiple vehicle dynamics parameters, when it is determined that the sampled data has missing data within a specified time period, obtain historical data of the vehicle dynamics parameter within a historical time period, and determine a target completion model corresponding to the vehicle dynamics parameter from multiple preset completion models, wherein different vehicle dynamics parameters correspond to different preset completion models; predict the missing data of the vehicle dynamics parameter based on the historical data of the vehicle dynamics parameter and the target completion model to obtain the completed data of the vehicle dynamics parameter; and perform sound wave simulation based on the completed data of the parameter with missing data among the multiple vehicle dynamics parameters and the sampled data corresponding to the parameter without missing data.

[0070] Optionally, the power component includes a motor, a brake pedal assembly and a vehicle speed sensor;

[0071] The central processor is connected to the motor and is used to receive first collected data corresponding to the motor torque parameter and second collected data corresponding to the motor speed parameter sent by the motor;

[0072] The central processor is connected to the brake pedal assembly and is used to receive third collected data corresponding to the pedal opening parameter sent by the brake pedal assembly;

[0073] The central processing unit is connected to the vehicle speed sensor and is used to receive fourth collected data corresponding to the vehicle speed parameter sent by the vehicle speed sensor;

[0074] The audio processor is used to receive one or more of the first collected data, the second collected data, the third collected data, and the fourth collected data forwarded by the central processor, and use the first collected data, the second collected data, the third collected data, and the fourth collected data as the collected data of the multiple vehicle dynamics parameters.

[0075] Optionally, the audio processor is used to:

[0076] Determining preset weights of the motor torque parameter, the motor speed parameter, the pedal opening parameter, and the vehicle speed parameter;

[0077] The simulation data to be used is determined according to the preset weight and the first collected data, the second collected data, the third collected data, and the fourth collected data.

[0078] Optionally, the vehicle further comprises: an audio player;

[0079] The audio processor is also connected to the audio player, and is configured to determine sonic wave audio data according to the to-be-used analog data, and send the sonic wave audio data to the audio player;

[0080] The audio player is configured to play the sonic wave audio data when receiving the sonic wave audio data.

[0081] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects:

[0082] When it is determined that there is missing data in the sampled data within a specified time period, by obtaining the historical data of the vehicle dynamics parameters within a historical time period, and determining the target completion model corresponding to the vehicle dynamics parameters from multiple preset completion models, the completion data of the vehicle dynamics parameters can be effectively and accurately determined according to the historical data of the vehicle dynamics parameters and the target completion model. Thus, through the completion data of the parameters with missing data among multiple vehicle dynamics parameters and the sampled data corresponding to the parameters without missing data, sonic wave simulation can be performed, which can effectively simulate the sonic wave and avoid abnormal phenomena such as stuttering, trailing, and repetition in the simulated sonic wave, ensuring the stability of the vehicle simulated sonic wave and being beneficial to improving the experience of vehicle users.

[0083] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure and used together with the specification to explain the principles of the present disclosure.

[0085] Figure 1 is a flowchart of a sonic wave simulation method shown according to an exemplary embodiment;

[0086] Figure 2 is a flowchart of another sonic wave simulation method shown according to an exemplary embodiment;

[0087] Figure 3 is a flowchart of a determination method of a preset completion model shown according to an exemplary embodiment;

[0088] Figure 4 is a flowchart of yet another sonic wave simulation method shown according to an exemplary embodiment;

[0089] Figure 5 is a block diagram of a sonic wave simulation device shown according to an exemplary embodiment;

[0090] Figure 6 is a block diagram of a sonic wave simulation device shown according to an exemplary embodiment;

[0091] Figure 7 is a block diagram of a vehicle shown according to an exemplary embodiment;

[0092] Figure 8 is a block diagram of another vehicle shown according to an exemplary embodiment;

[0093] Figure 9 is a block diagram of a device for engine sound simulation shown according to an exemplary embodiment. Detailed implementation manners

[0094] Here, the exemplary embodiments will be described in detail, and examples thereof are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0095] Before detailing the specific implementation manners of the present disclosure, first, the application scenarios of the present disclosure will be described. The present disclosure can be applied to the process of vehicle engine sound simulation. Generally, a vehicle can collect vehicle dynamics parameters through sensors and convert the collected vehicle dynamics parameters into data signals and report them to a central processor. The central processor not only needs to forward the received vehicle power parameters to an audio processor, but also needs to receive other vehicle parameters other than the vehicle dynamics parameters and process the other vehicle parameters. Due to the parallel computing pressure of the central processor and the uncontrollable amount of vehicle function operations, it is easy to cause the phenomenon of data loss during the data forwarding process, and further cause abnormalities such as stuttering, tailing, and repetition in the simulated engine sound generated by the audio processor, which is not conducive to improving the experience of electric vehicle users.

[0096] To solve the above problems, the present disclosure provides a sound wave simulation method, apparatus, storage medium, and vehicle. The sound wave simulation method receives sampling data of multiple vehicle dynamics parameters reported. For each vehicle dynamics parameter among the multiple vehicle dynamics parameters, when it is determined that there is missing data in the sampling data within a specified time period, historical data of the vehicle dynamics parameter within a historical time period is obtained, and a target completion model corresponding to the vehicle dynamics parameter is determined from multiple preset completion models. Among them, the preset completion models corresponding to different vehicle dynamics parameters are different. The missing data of the vehicle dynamics parameter is predicted according to the historical data of the vehicle dynamics parameter and the target completion model to obtain the completion data of the vehicle dynamics parameter. Sound wave simulation is performed according to the completion data of the parameter with missing data among the multiple vehicle dynamics parameters and the sampling data corresponding to the parameter without missing data. In this way, when it is determined that there is missing data in the sampling data within a specified time period, by obtaining the historical data of the vehicle dynamics parameter within a historical time period, and determining the target completion model corresponding to the vehicle dynamics parameter from multiple preset completion models, the completion data of the vehicle dynamics parameter can be effectively and accurately determined according to the historical data of the vehicle dynamics parameter and the target completion model. Thus, sound wave simulation is performed according to the completion data of the parameter with missing data among the multiple vehicle dynamics parameters and the sampling data corresponding to the parameter without missing data, which can effectively simulate the sound wave and avoid abnormal phenomena such as stuttering, trailing, and repetition in the simulated sound wave, ensuring the stability of the vehicle simulated sound wave and being beneficial to improving the experience of vehicle users.

[0097] Figure 1 is a flowchart of a sound wave simulation method shown according to an exemplary embodiment, as Figure 1 shown, the sound wave simulation method may include the following steps:

[0098] In step 101, sampling data of multiple vehicle dynamics parameters reported is received.

[0099] Among them, the vehicle dynamics parameters may include but are not limited to brake pedal opening information, vehicle speed information, motor speed information, and motor torque information. The vehicle dynamics parameters can be collected by preset sensors. For example: the brake pedal opening information can be collected by a potentiometer, Hall sensor, or pressure sensor, the vehicle speed information can be collected by a wheel speed sensor or vehicle speed sensor, the motor speed information can be collected by a Hall sensor or electromagnetic speed sensor, and the motor torque information can be collected by a strain gauge torque sensor, magnetoresistive torque sensor, or Hall effect torque sensor.

[0100] In step 102, for each of the multiple vehicle dynamic parameters, when it is determined that there is missing data in the sampling data within a specified time period, historical data of the vehicle dynamic parameter within a historical time period is obtained, and a target completion model corresponding to the vehicle dynamic parameter is determined from multiple preset completion models.

[0101] Among them, the preset completion models corresponding to different vehicle dynamic parameters are different. The preset completion models can include but are not limited to linear interpolation models and autoregressive (AR) models. The specified time period can be 5ms, 10ms, 13ms, 20ms, etc., and the historical time period can be an integer multiple of the specified time period. For example: 5 times, 8 times, or 10 times, etc., and the historical time period can be 50ms, 100ms, 130ms, 200ms, etc.

[0102] The specific implementation manner of determining that there is missing data in the sampling data within the specified time period in this step can be to determine that there is missing data in the sampling data when it is determined that the sampling data corresponding to the vehicle dynamic parameter is not received within the specified time period. For example: the specified time period can be 10ms. For each of the multiple vehicle dynamic parameters, when it is determined that the sampling data corresponding to the vehicle dynamic parameter is not received within 10ms, it is determined that the sampling data is missing.

[0103] The specific implementation manner of determining the target completion model corresponding to the vehicle dynamic parameter from multiple preset completion models in this step can be to determine the parameter identifier corresponding to the missing vehicle dynamic parameter, and use the preset completion model whose model identifier matches the parameter identifier among the multiple preset completion models as the target completion model corresponding to the vehicle dynamic parameter.

[0104] Among them, the parameter identifier can be the identifier of the brake pedal opening, the identifier of the vehicle speed, the identifier of the motor speed, or the identifier of the motor torque. The model identifier can be understood as the model name, the model icon, or the model ID (identity identifier). The model identifier and the parameter identifier can be matched through a preset correspondence. For example: the model identifier of the AR model among the multiple preset completion models is AR, and the parameter identifier corresponding to the vehicle dynamic parameter is the identifier of the motor speed. If it is determined through the preset correspondence that the identifier of the motor speed corresponds to AR, then the AR model corresponding to the model identifier AR can be used as the target completion model corresponding to the vehicle dynamic parameter.

[0105] Exemplarily, the pointing time period can be 10 ms, and the historical time period can be 100 ms. For the motor speed information among multiple vehicle dynamics parameters, in the case where it is determined that the sampling data corresponding to the motor speed information is not received within 10 ms, it is determined that there is a data loss in the sampling data. If it is determined that there is a data loss in the sampling data corresponding to the motor speed information within 10 ms, obtain the historical data of the motor speed information within 100 ms, and by determining that the parameter identifier of the missing vehicle dynamics parameter is the identifier of the motor speed, use the model in multiple preset completion models whose model identifier can represent an AR model for the motor speed parameter as the target completion model corresponding to the motor speed information.

[0106] In step 103, predict the missing data of the vehicle dynamics parameter based on the historical data of the vehicle dynamics parameter and the target completion model to obtain the completed data of the vehicle dynamics parameter.

[0107] The specific implementation of this step may include Figure 2 the steps shown, Figure 2 is a flowchart of another sound wave simulation method shown according to an exemplary embodiment, as Figure 2 shown, this step 103 may include:

[0108] In step 1031, input the historical data of the vehicle dynamics parameter into the target completion model corresponding to the vehicle dynamics parameter to obtain the predicted data output by the target completion model.

[0109] Exemplarily, in the case where the missing vehicle dynamics parameter is a motor parameter, the historical data of the motor speed information within 100 ms can be input into the AR model, and the predicted data corresponding to the missing data in the motor speed information is calculated through the AR model.

[0110] In step 1032, determine the target difference between the predicted data and the previously reported sampling data.

[0111] It should be noted that the previously reported acquisition data can be obtained from the historical data of the vehicle dynamics parameter, and the target difference is calculated through the preset data and the previously reported acquisition data.

[0112] Exemplarily, the previously reported acquisition data is obtained from the historical data of the motor speed information within 100 ms, that is, the motor speed acquisition data corresponding to the 10th 10 ms, and the target difference is calculated through the predicted data and the motor speed acquisition data.

[0113] In step 1033, correct the predicted data according to the target difference to obtain the corrected completed data.

[0114] The specific implementation of this step may be that, when the target difference is greater than or equal to a first preset difference threshold, a preset upper limit value is obtained and the upper limit value is used as the supplementary data; when the target difference is less than a second preset difference threshold, a preset lower limit value is obtained and the lower limit value is used as the supplementary data. When the target difference is less than the first preset difference threshold and greater than the second preset difference threshold, the predicted data is used as the supplementary data.

[0115] Among them, the first preset difference threshold is greater than the second preset difference threshold.

[0116] The technical solution of the above steps 1031 to 1033 can effectively determine the supplementary data by determining the target difference between the predicted data and the previously reported sampling data, and compare the target difference with the first preset difference threshold or the second preset difference threshold, so as to avoid excessively large or small abnormal values ​​in the supplementary data, thereby effectively improving the stability of the sound wave simulation and helping to improve the experience of vehicle users.

[0117] In step 104 , sound wave simulation is performed based on the supplemented data of the parameters with missing data among the plurality of vehicle dynamics parameters and the sampled data corresponding to the parameters without missing data.

[0118] A possible implementation of this step may be to determine a preset weight for each vehicle dynamics parameter, perform weighted summation of the completed data for the parameters with missing data and the sampled data corresponding to the parameters without missing data among the multiple vehicle dynamics parameters according to the preset weight to obtain stand-by simulation data, and determine the sound loudness according to the stand-by simulation data.

[0119] Another possible implementation manner may be to preset a correspondence between the standby simulation data and the sound wave loudness, and determine the sound wave loudness corresponding to the standby simulation data according to the preset correspondence.

[0120] For example, the vehicle dynamics parameters may include brake pedal opening information, vehicle speed information, motor speed information, and motor torque information. The weighted summation formula of the simulation data to be used is as follows:

[0121] A=θ1×A1+θ2×A2+θ3×A3+θ4×A4

[0122] Among them, A1 can represent the brake pedal opening information, θ1 can represent the preset weight of the brake pedal opening information, A2 can represent the vehicle speed information, θ2 can represent the preset weight of the vehicle speed information, A3 can represent the motor speed information, θ3 can represent the preset weight of the motor speed information, A4 can represent the motor speed information, θ4 can represent the preset weight of the motor torque information.

[0123] The above technical solution can, when it is determined that there is missing data in the sampled data within a specified time period, obtain the historical data of the vehicle dynamic parameters within the historical time period, determine the target completion model corresponding to the vehicle dynamic parameters from multiple preset completion models, and effectively and accurately determine the completion data of the vehicle dynamic parameters according to the historical data of the vehicle dynamic parameters and the target completion model. Therefore, by using the completion data of the parameters with missing data among multiple vehicle dynamic parameters and the sampled data corresponding to the parameters without missing data for sound wave simulation, it can effectively simulate the sound wave and avoid abnormal phenomena such as stuttering, trailing, and repetition in the simulated sound wave, ensuring the stability of the vehicle simulated sound wave and being beneficial to improving the experience of vehicle users.

[0124] Figure 3 It is a flowchart showing a method for determining a preset completion model according to an exemplary embodiment, as Figure 3 shown. The method for determining the preset completion model corresponding to each of the vehicle dynamic parameters may include the following steps:

[0125] In step 301, obtain the training data set corresponding to each of the vehicle dynamic parameters among the multiple vehicle dynamic parameters under multiple working conditions.

[0126] Among them, the working conditions may include but are not limited to standard working conditions under a preset test site (for example: full-throttle reciprocating acceleration, 50% throttle opening reciprocating acceleration, 30 kph constant speed, 50 kph constant speed, 100 kph constant speed, and 120 kph constant speed, etc.) and actual driving working conditions in the actual vehicle driving environment (for example: urban road sections, highway road sections, and indoor garage road sections, etc.).

[0127] It should be noted that, under multiple working conditions, the sample data of each vehicle dynamic parameter among the multiple vehicle dynamic parameters can be collected by a preset sensor, and the collected sample data can be divided into a training data set and a test data set according to a preset ratio.

[0128] Exemplarily, the sample data may include the vehicle dynamic parameters under 5 hours of standard working conditions and the vehicle dynamic parameters under 19 hours of free driving working conditions. 80% of the data volume in the sample data can be used as the training data set, and 20% of the data volume can be used as the test data set.

[0129] In step 302, determine multiple candidate models respectively through the training data set corresponding to each of the vehicle dynamic parameters.

[0130] The models to be used may include but are not limited to linear interpolation models, adjacent point interpolation models, AR (AutoRegression) models and MA (Moving Average) models. The training data sets corresponding to each vehicle dynamics parameter may be input into a preset initial AR model, and the initial AR model may be iteratively trained to obtain an AR model:

[0131] s p =α1x -d +α2x 1-d +…+α d x -1 +μ

[0132] Among them, the AR model is used to describe the relationship between the current value and the historical value, s p is the predicted data, x -n is the vehicle dynamics parameter reported in the previous n times, d is the AR model order, and μ is the model static bias. When the error between the prediction data set and the test data set is less than the preset ratio, the current training model is used as the AR model.

[0133] For example, the training dataset can be input into the initial AR model:

[0134] s p =α1x -d +α2x 1-d +…+α d x -1 +μ

[0135] The parameter α of the AR model is calculated by the gradient descent iterative algorithm n , the RMS value between the prediction data set and the test data set corresponding to each vehicle dynamics parameter is calculated according to the following formula:

[0136]

[0137] Among them, s pN is the predicted data of the Nth point, s rN is the test data of the Nth point.

[0138] When it is determined that the root mean square value R is less than 2%, the trained AR model is used as a standby model.

[0139] In addition, a linear interpolation model can be fitted through the training data set:

[0140] s p =β0+β1x -1

[0141] in, s pcan be the predicted data, d is the order of the linear interpolation model, x -i is the vehicle dynamics parameter reported in the previous i times, is the average of the vehicle dynamics parameters reported in the previous i times, and β0 and β1 are the changing trends of the discrete vehicle dynamics parameters obtained by linear regression calculation of d historical data.

[0142] The adjacent point interpolation model can also be fitted through the training data set:

[0143] s p =x -1

[0144] Among them, s p Can be the predicted data, x -1 It can be the vehicle dynamics parameters reported last time.

[0145] You can also fit the MA model with this training dataset:

[0146]

[0147] Among them, the MA model calculates the average value of the specified number of historical data as the predicted data, s p is the predicted data, x -n are the vehicle dynamics parameters reported in the previous n times, and d is the order of the MA model.

[0148] It should be noted that the specific fitting or training process of the above model is relatively common in the prior art and is not limited in this disclosure.

[0149] In step 303, the preset completion model corresponding to the vehicle dynamics parameter is determined according to the multiple standby models corresponding to each of the vehicle dynamics parameters.

[0150] The specific implementation method of this step can be: obtaining the prediction error corresponding to each of the multiple standby models corresponding to each of the vehicle dynamics parameters, and taking the model with the smallest prediction error among the multiple standby models corresponding to each of the vehicle dynamics parameters as the preset completion model corresponding to the vehicle dynamics parameter.

[0151] The prediction error may be the average value of the difference between the prediction data in the prediction data set and the test data in the test data set, the variance, square root difference or military root difference between the prediction data set and the test data set. For example, the formula for calculating the root mean square value between the prediction result data set and the test data set corresponding to each vehicle dynamics parameter is as follows:

[0152]

[0153] Among them, spN is the predicted data for the Nth point, s rN is the test data for the Nth point.

[0154] It should be noted that for each vehicle dynamics parameter corresponding to multiple candidate models, the way to obtain the prediction error corresponding to each candidate model can be as follows: By obtaining a test data set, inputting the historical data of the test data set within a historical time period into multiple candidate models, obtaining a prediction result data set corresponding to each vehicle dynamics parameter in the test data set, calculating the root mean square value between the prediction result data set corresponding to each vehicle dynamics parameter and the test data set, and taking this root mean square value as the prediction error corresponding to each candidate model for each vehicle dynamics parameter. By comparing the prediction errors of multiple candidate models corresponding to each vehicle dynamics parameter, the candidate model with the smallest prediction error among the multiple candidate models corresponding to each vehicle dynamics parameter can be used as the preset completion model corresponding to the vehicle dynamics parameter.

[0155] Exemplarily, the prediction errors of multiple candidate models corresponding to each vehicle dynamics parameter can be shown in the following table:

[0156]

[0157] As shown in the above table, the prediction error of the linear interpolation model corresponding to the motor speed information is 27.15%, the prediction error of the neighboring point interpolation model is 24.87%, the prediction error of the AR model is 0.21%, and the prediction error of the MA model is 0.25%. The prediction error of the AR model, 0.21%, is the smallest, and the AR model can be used as the preset completion model corresponding to the motor speed information; the prediction error of the linear interpolation model corresponding to the motor torque information is 0.44%, the prediction error of the neighboring point interpolation model is 1.19%, the prediction error of the AR model is 1.24%, and the prediction error of the MA model is 1.24%. The prediction error of the linear interpolation model, 0.44%, is the smallest, and the linear interpolation model can be used as the preset completion model corresponding to the motor torque information; the prediction error of the linear interpolation model corresponding to the vehicle speed information is 0.30%, the prediction error of the neighboring point interpolation model is 0.23%, the prediction error of the AR model is 0.0016%, and the prediction error of the MA model is 0.0025%. The prediction error of the AR model, 0.0016%, is the smallest, and the AR model can be used as the preset completion model corresponding to the vehicle speed information; the prediction error of the linear interpolation model corresponding to the brake pedal opening information is 0.11%, the prediction error of the neighboring point interpolation model is 0.25%, the prediction error of the AR model is 0.13%, and the prediction error of the MA model is 0.13%. The prediction error of the linear interpolation model, 0.11%, is the smallest, and the linear interpolation model can be used as the preset completion model corresponding to the brake pedal opening information.

[0158] The above technical solution can, when it is determined that there is missing data in the sampled data within a specified time period, obtain the historical data of the vehicle dynamics parameters within a historical time period, determine the target completion model corresponding to the vehicle dynamics parameters from multiple preset completion models, and effectively and accurately determine the completion data of the vehicle dynamics parameters according to the historical data of the vehicle dynamics parameters and the target completion model. Thus, by using the completion data of the parameters with missing data among multiple vehicle dynamics parameters and the sampled data corresponding to the parameters without missing data for sound wave simulation, it can effectively simulate the sound wave and avoid abnormal phenomena such as stuttering, trailing, and repetition in the simulated sound wave, ensuring the stability of the vehicle's simulated sound wave and being beneficial to improving the experience of vehicle users.

[0159] Figure 4 is a flowchart of another sound wave simulation method shown according to an exemplary embodiment, as Figure 4 shown, this sound wave simulation method may further include:

[0160] In step 105, determine the target duration of continuous missing of each of the vehicle dynamics parameters.

[0161] Among them, the target duration can be an integer multiple of the specified time period. For example: 10 times, 15 times, or 20 times, and the target duration can be 100 ms, 150 ms, or 200 ms.

[0162] It should be noted that when it is determined that there is missing data in the sampled data corresponding to the vehicle dynamics parameters within a specified time period, the target duration of continuous missing of each vehicle dynamics parameter can be determined by determining the number of specified time periods corresponding to the continuous missing of the vehicle dynamics parameters. For example: the specified time period can be 10 ms, and the target duration can be 100 ms. When it is determined that the number of specified time periods corresponding to the continuous missing of the vehicle dynamics parameters is 2, the target duration of continuous missing of each vehicle dynamics parameter can be determined to be 20 ms. When it is determined that the number of specified time periods corresponding to the continuous missing of the vehicle dynamics parameters is 5, the target duration of continuous missing of each vehicle dynamics parameter can be determined to be 50 ms. When it is determined that the number of specified time periods corresponding to the continuous missing of the vehicle dynamics parameters is 10, the target duration of continuous missing of each vehicle dynamics parameter can be determined to be 100 ms.

[0163] In step 106, when the target duration is greater than the preset duration threshold, output a preset fault prompt message.

[0164] Among them, the preset fault prompt message can be an audible and visual alarm message, or can also be a prompt message such as voice, image, or text.

[0165] Exemplarily, the preset duration threshold can be 80 ms. When it is determined that the number of specified time periods during which the vehicle dynamics parameters are continuously missing is 9, the target duration for each continuously missing vehicle dynamics parameter can be determined to be 90 ms. Since the target duration of 90 ms is greater than the preset duration threshold of 80 ms, a preset fault prompt message can be output.

[0166] The above technical solution can, when it is determined that there is missing data in the sampled data within a specified time period, obtain the historical data of the vehicle dynamics parameters in the historical time period, determine the target completion model corresponding to the vehicle dynamics parameters from multiple preset completion models, and effectively and accurately determine the completion data of the vehicle dynamics parameters based on the historical data of the vehicle dynamics parameters and the target completion model. Then, through the completion data of the parameters with missing data among multiple vehicle dynamics parameters and the sampled data corresponding to the parameters without missing data, sound wave simulation can be performed, which can effectively simulate the sound wave and avoid abnormal phenomena such as stuttering, trailing, and repetition in the simulated sound wave, ensuring the stability of the vehicle's simulated sound wave and being beneficial to improving the experience of vehicle users.

[0167] Figure 5 is a block diagram of a sound wave simulation device shown according to an exemplary embodiment, as Figure 5 shown. The sound wave simulation device includes:

[0168] A receiving module 501, configured to receive the sampled data of multiple vehicle dynamics parameters reported;

[0169] An obtaining module 502, configured to, for each vehicle dynamics parameter among the multiple vehicle dynamics parameters, when it is determined that there is missing data in the sampled data within a specified time period, obtain the historical data of the vehicle dynamics parameter in the historical time period, and determine the target completion model corresponding to the vehicle dynamics parameter from multiple preset completion models, where different preset completion models correspond to different vehicle dynamics parameters;

[0170] A first determination module 503, configured to predict the missing data of the vehicle dynamics parameter based on the historical data of the vehicle dynamics parameter and the target completion model to obtain the completion data of the vehicle dynamics parameter;

[0171] A simulation module 504, configured to perform sound wave simulation based on the completion data of the parameters with missing data among the multiple vehicle dynamics parameters and the sampled data corresponding to the parameters without missing data.

[0172] Optionally, the obtaining module 502 is configured to:

[0173] Obtain a training dataset corresponding to each of the multiple vehicle dynamics parameters under multiple working conditions;

[0174] Determine multiple candidate models respectively through the training datasets corresponding to each of the vehicle dynamics parameters;

[0175] Determine the preset completion model corresponding to the vehicle dynamics parameter according to the multiple candidate models corresponding to each of the vehicle dynamics parameters.

[0176] Optionally, the obtaining module 502 is configured to:

[0177] Obtain the prediction error corresponding to each candidate model among the multiple candidate models corresponding to each of the vehicle dynamics parameters;

[0178] Take the candidate model with the minimum prediction error among the multiple candidate models corresponding to each of the vehicle dynamics parameters as the preset completion model corresponding to the vehicle dynamics parameter.

[0179] Optionally, the first determination module 503 is configured to:

[0180] Input the historical data of the vehicle dynamics parameter into the target completion model corresponding to the vehicle dynamics parameter to obtain the prediction data output by the target completion model;

[0181] Determine the target difference between the prediction data and the sampled data reported last time;

[0182] Correct the prediction data according to the target difference to obtain the completed data after correction.

[0183] Optionally, the first determination module 503 is configured to:

[0184] When the target difference is greater than or equal to the first preset difference threshold, obtain a preset upper limit value and use the upper limit value as the completed data;

[0185] When the target difference is less than the second preset difference threshold, obtain a preset lower limit value and use the lower limit value as the completed data, where the first preset difference threshold is greater than the second preset difference threshold.

[0186] Optionally, the obtaining module 502 is configured to:

[0187] Determine the parameter identifier corresponding to the missing vehicle dynamics parameter;

[0188] Take the preset completion model whose model identifier matches the parameter identifier among the multiple preset completion models as the target completion model corresponding to the vehicle dynamics parameter.

[0189] Optionally, the simulation module 504 is configured to:

[0190] determining a preset weight for each vehicle dynamics parameter;

[0191] performing weighted summation of the supplementary data of the parameters with missing data and the sampled data corresponding to the parameters without missing data among the plurality of vehicle dynamics parameters according to the preset weights to obtain stand-by simulation data;

[0192] The loudness of the sound wave is determined according to the simulation data to be used.

[0193] Optionally, the acquisition module 502 is configured to:

[0194] When it is determined that the sampled data corresponding to the vehicle dynamics parameter is not received within the specified time period, it is determined that there is data missing in the sampled data.

[0195] Figure 6 is a block diagram of a sound wave simulation device according to an exemplary embodiment. Figure 6 As shown, the sound wave simulation device may also include:

[0196] A second determination module 505 is configured to determine a target duration of continuous missing of each of the vehicle dynamics parameters;

[0197] The output module 506 is configured to output preset fault prompt information when the target duration is greater than a preset duration threshold.

[0198] The above technical scheme can, when it is determined that there are missing data in the sampled data within a specified time period, obtain the historical data of the vehicle dynamics parameters within the historical time period, and determine the target completion model corresponding to the vehicle dynamics parameters from multiple preset completion models. The completion data of the vehicle dynamics parameters can be effectively and accurately determined according to the historical data of the vehicle dynamics parameters and the target completion model, so that sound wave simulation can be performed through the completion data of the parameters with missing data and the sampled data corresponding to the parameters without missing data among the multiple vehicle dynamics parameters. The sound waves can be effectively simulated, and abnormal phenomena such as jamming, tailing, and repetition in the simulated sound waves can be avoided, thereby ensuring the stability of the simulated sound waves of the vehicle, which is beneficial to improving the experience of vehicle users.

[0199] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0200] The present disclosure also provides a computer-readable storage medium, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the sound wave simulation method provided by the present disclosure are implemented.

[0201] Figure 7 is a block diagram of a vehicle shown according to an exemplary embodiment, as Figure 7 shown. The vehicle may include a power component 701, a central processing unit 702, and an audio processor 703;

[0202] The central processing unit 702 is connected to the power component 701 and the audio processor 703, and is configured to receive sampling data of a plurality of vehicle dynamics parameters reported by the power component, and forward the sampling data of the plurality of vehicle dynamics parameters to the audio processor 703. The audio processor 703 is configured to receive the sampling data of the plurality of vehicle dynamics parameters reported; for each vehicle dynamics parameter among the plurality of vehicle dynamics parameters, in the case where it is determined that there is missing data in the sampling data within a specified time period, obtain historical data of the vehicle dynamics parameter within a historical time period, and determine a target completion model corresponding to the vehicle dynamics parameter from a plurality of preset completion models, where different preset completion models correspond to different vehicle dynamics parameters; predict the missing data of the vehicle dynamics parameter according to the historical data of the vehicle dynamics parameter and the target completion model to obtain completion data of the vehicle dynamics parameter; perform sound wave simulation according to the completion data of the parameter with missing data among the plurality of vehicle dynamics parameters and the sampling data corresponding to the parameter without missing data.

[0203] Optionally, the power component includes a motor, a brake pedal assembly, and a vehicle speed sensor;

[0204] The central processing unit 702 is connected to the motor and is configured to receive first acquisition data corresponding to a motor torque parameter and second acquisition data corresponding to a motor speed parameter sent by the motor;

[0205] The central processing unit 702 is connected to the brake pedal assembly and is configured to receive third acquisition data corresponding to a pedal opening parameter sent by the brake pedal assembly;

[0206] The central processing unit 702 is connected to the vehicle speed sensor and is configured to receive fourth acquisition data corresponding to a vehicle speed parameter sent by the vehicle speed sensor;

[0207] The audio processor 703 is used to receive one or more of the first collected data, the second collected data, the third collected data, and the fourth collected data forwarded by the central processor 702, and use the first collected data, the second collected data, the third collected data, and the fourth collected data as sampling data of the multiple vehicle dynamics parameters.

[0208] Optionally, the audio processor 703 is used to:

[0209] Determining preset weights of the motor torque parameter, the motor speed parameter, the pedal opening parameter, and the vehicle speed parameter;

[0210] The simulation data to be used is determined according to the preset weight and the first collected data, the second collected data, the third collected data, and the fourth collected data.

[0211] Optionally, the vehicle further comprises: an audio player 704;

[0212] The audio processor 703 is also connected to the audio player 704, and is used to determine the sound wave audio data according to the standby analog data, and send the sound wave audio data to the audio player. The audio player 704 is used to play the sound wave audio data when receiving the sound wave audio data.

[0213] Figure 8 800 is a block diagram of another vehicle according to an exemplary embodiment. For example, vehicle 800 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicles. Vehicle 800 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0214] Reference Figure 8 , the vehicle 800 may include various subsystems, for example, an infotainment system 810, a perception system 820, a decision control system 830, a drive system 840, and a computing platform 850. The vehicle 800 may also include more or fewer subsystems, and each subsystem may include multiple components. In addition, each subsystem and each component of the vehicle 800 may be interconnected by wire or wireless means.

[0215] In some embodiments, the infotainment system 810 may include a communication system, an entertainment system, and a navigation system, etc.

[0216] The perception system 820 may include several types of sensors for sensing information about the environment around the vehicle 800. For example, the perception system 820 may include a global positioning system (the global positioning system may be a GPS system, a Beidou system, or other positioning systems), an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device.

[0217] The decision-making and control system 830 may include a computing system, a vehicle controller, a steering system, an accelerator, and a braking system.

[0218] The drive system 840 may include components that provide motive power for the vehicle 800. In one embodiment, the drive system 840 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of an internal combustion engine, an electric motor, and an air compression engine. The engine is capable of converting the energy provided by the energy source into mechanical energy.

[0219] Some or all of the functions of the vehicle 800 are controlled by the computing platform 850. The computing platform 850 may include at least one processor 851 and a first memory 852, and the processor 851 may execute instructions 853 stored in the first memory 852.

[0220] The processor 851 may be any conventional processor, such as a commercially available CPU. The processor may also include, for example, a Graphic Process Unit (GPU), a Field Programmable Gate Array (FPGA), a System on Chip (SOC), an Application Specific Integrated Circuit (ASIC), or a combination thereof.

[0221] The first memory 852 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk.

[0222] In addition to the instructions 853, the first memory 852 may also store data, such as road maps, route information, data on the position, direction, speed, etc. of the vehicle. The data stored in the first memory 852 can be used by the computing platform 850.

[0223] In an embodiment of the present disclosure, the processor 851 may execute instructions 853 to complete all or part of the steps of the above-described sound wave simulation method.

[0224] Figure 9 FIG. is a block diagram of an apparatus for sound wave simulation according to an exemplary embodiment. For example, the apparatus 900 may be provided as a server. Referring to Figure 9 , the apparatus 900 includes a processing component 922, which further includes one or more processors, and memory resources represented by a second memory 932 for storing instructions executable by the processing component 922, such as application programs. The application programs stored in the second memory 932 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 922 is configured to execute instructions to perform the above-described sound wave simulation method.

[0225] The apparatus 900 may further include a power supply component 926 configured to perform power management of the apparatus 900, a wired or wireless network interface 950 configured to connect the apparatus 900 to a network, and an input / output interface 958. The apparatus 900 may operate based on an operating system stored in the second memory 932.

[0226] In another exemplary embodiment, a computer program product is also provided, which includes a computer program executable by a programmable device. The computer program has a code portion for performing the above-described sound wave simulation method when executed by the programmable device.

[0227] Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the specification and practicing the present disclosure. This application is intended to cover any variations, uses, or adaptations of the present disclosure, which follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0228] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A sound wave simulation method, characterized in that, The method includes: Receiving the sampled data of multiple vehicle dynamics parameters reported; For each vehicle dynamics parameter among the multiple vehicle dynamics parameters, when it is determined that there is missing data in the sampled data within a specified time period, obtaining the historical data of the vehicle dynamics parameter within a historical time period, and determining the target completion model corresponding to the vehicle dynamics parameter from multiple preset completion models, where the preset completion models corresponding to different vehicle dynamics parameters are different; Predicting the missing data of the vehicle dynamics parameter based on the historical data of the vehicle dynamics parameter and the target completion model to obtain the completion data of the vehicle dynamics parameter; Performing sound wave simulation based on the completion data of the parameters with missing data among the multiple vehicle dynamics parameters and the sampled data corresponding to the parameters without missing data.

2. The method according to claim 1, characterized in that The determination method of the preset completion model corresponding to each vehicle dynamics parameter includes: Obtaining the training data set corresponding to each vehicle dynamics parameter among the multiple vehicle dynamics parameters under various working conditions; Respectively determining multiple candidate models through the training data set corresponding to each vehicle dynamics parameter; Determining the preset completion model corresponding to the vehicle dynamics parameter according to the multiple candidate models corresponding to each vehicle dynamics parameter.

3. The method according to claim 2, wherein The determining the preset completion model corresponding to the vehicle dynamics parameter according to the multiple candidate models corresponding to each vehicle dynamics parameter includes: Obtaining the prediction error corresponding to each candidate model among the multiple candidate models corresponding to each vehicle dynamics parameter; Taking the candidate model with the minimum prediction error among the multiple candidate models corresponding to each vehicle dynamics parameter as the preset completion model corresponding to the vehicle dynamics parameter.

4. The method according to claim 1, wherein The predicting the missing data of the vehicle dynamics parameter based on the historical data of the vehicle dynamics parameter and the target completion model to obtain the completion data of the vehicle dynamics parameter includes: Inputting the historical data of the vehicle dynamics parameter into the target completion model corresponding to the vehicle dynamics parameter to obtain the prediction data output by the target completion model; Determining the target difference between the prediction data and the sampled data reported last time; Correcting the prediction data according to the target difference to obtain the corrected completion data.

5. The method according to claim 4, characterized in that The correcting the prediction data according to the target difference to obtain the corrected completion data includes: When the target difference is greater than or equal to the first preset difference threshold, obtaining the preset upper limit value and taking the upper limit value as the completion data; When the target difference is less than the second preset difference threshold, obtaining the preset lower limit value and taking the lower limit value as the completion data, where the first preset difference threshold is greater than the second preset difference threshold.

6. The method according to claim 1, wherein The determining the target completion model corresponding to the vehicle dynamics parameter from multiple preset completion models includes: Determining the parameter identifier corresponding to the missing vehicle dynamics parameter; Select the preset completion model among the multiple preset completion models whose model identifier matches the parameter identifier as the target completion model corresponding to the vehicle dynamics parameter.

7. The method according to claim 1, characterized in that, The acoustic wave simulation based on the completion data of the parameter with missing data and the sampling data corresponding to the parameter without missing data among the multiple vehicle dynamics parameters includes: Determine the preset weight of each vehicle dynamics parameter; Perform weighted summation on the completion data of the parameter with missing data and the sampling data corresponding to the parameter without missing data among the multiple vehicle dynamics parameters according to the preset weight to obtain the data to be simulated; Determine the acoustic wave loudness according to the data to be simulated.

8. The method according to claim 1, wherein The determination that there is missing sampling data within a specified time period includes: When it is determined that no sampling data corresponding to the vehicle dynamics parameter is received within the specified time period, it is determined that there is missing sampling data.

9. The method according to claim 1, wherein The method further includes: Determine the target duration of continuous missing of each vehicle dynamics parameter; When the target duration is greater than the preset duration threshold, output a preset fault prompt message.

10. An acoustic wave simulation device, characterized in that, The device includes: A receiving module, configured to receive the sampling data of multiple vehicle dynamics parameters reported; An obtaining module, configured to, for each vehicle dynamics parameter among the multiple vehicle dynamics parameters, when it is determined that there is missing sampling data within a specified time period, obtain the historical data of the vehicle dynamics parameter in the historical time period, and determine the target completion model corresponding to the vehicle dynamics parameter from multiple preset completion models, where different preset completion models correspond to different vehicle dynamics parameters; A first determination module, configured to predict the missing data of the vehicle dynamics parameter according to the historical data and the target completion model of the vehicle dynamics parameter to obtain the completion data of the vehicle dynamics parameter; A simulation module, configured to perform acoustic wave simulation according to the completion data of the parameter with missing data and the sampling data corresponding to the parameter without missing data among the multiple vehicle dynamics parameters.

11. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the program instruction is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

12. A vehicle, characterized in that, The vehicle includes a power component, a central processor, and an audio processor; The central processor is connected to the power component and the audio processor, and is configured to receive the sampling data of multiple vehicle dynamics parameters reported by the power component and forward the sampling data of the multiple vehicle dynamics parameters to the audio processor; The audio processor is used to receive sampled data of multiple reported vehicle dynamics parameters; for each vehicle dynamics parameter among the multiple vehicle dynamics parameters, when it is determined that the sampled data has missing data within a specified time period, obtain historical data of the vehicle dynamics parameter within a historical time period, and determine a target completion model corresponding to the vehicle dynamics parameter from multiple preset completion models, wherein different vehicle dynamics parameters correspond to different preset completion models; predict the missing data of the vehicle dynamics parameter based on the historical data of the vehicle dynamics parameter and the target completion model to obtain the completed data of the vehicle dynamics parameter; and perform sound wave simulation based on the completed data of the parameter with missing data among the multiple vehicle dynamics parameters and the sampled data corresponding to the parameter without missing data.

13. The vehicle according to claim 12, characterized in that, The power components include a motor, a brake pedal assembly and a vehicle speed sensor; The central processor is connected to the motor and is used to receive first collected data corresponding to the motor torque parameter and second collected data corresponding to the motor speed parameter sent by the motor; The central processor is connected to the brake pedal assembly and is used to receive third collected data corresponding to the pedal opening parameter sent by the brake pedal assembly; The central processing unit is connected to the vehicle speed sensor and is used to receive fourth collected data corresponding to the vehicle speed parameter sent by the vehicle speed sensor; The audio processor is used to receive one or more of the first collected data, the second collected data, the third collected data, and the fourth collected data forwarded by the central processor, and use the first collected data, the second collected data, the third collected data, and the fourth collected data as sampling data of the multiple vehicle dynamics parameters.

14. The vehicle according to claim 13, characterized in that, The audio processor is used for: Determining preset weights of the motor torque parameter, the motor speed parameter, the pedal opening parameter, and the vehicle speed parameter; The simulation data to be used is determined according to the preset weight and the first collected data, the second collected data, the third collected data, and the fourth collected data.

15. The vehicle according to claim 14, characterized in that, The vehicle further comprises: an audio player; The audio processor is also connected to the audio player, and is used to determine the sound wave audio data according to the standby analog data, and send the sound wave audio data to the audio player; The audio player is used to play the sound audio data when the sound audio data is received.

Images