Acoustic packet performance prediction method and device, model training method and device and electronic equipment

Abstract

The invention discloses an acoustic packet performance prediction method and device, a model training method and device and electronic equipment. The method comprises the following steps: acquiring material-level sound absorption and insulation performance parameters of a component, wherein the material-level sound absorption and insulation performance parameters comprise a material parameter of the component, a structure parameter of the component, a parameter for characterizing the sound absorption performance of a material and / or a parameter for characterizing the sound insulation performance of the material; obtaining a pre-trained sound absorption and insulation performance prediction model, wherein the model comprises sound absorption and insulation performance prediction units of a plurality of levels of acoustic packets; and inputting the material-level sound absorption and insulation performance parameters of each component into a pre-trained sound absorption and insulation performance prediction model, and performing sound absorption and insulation performance prediction on the subsystem. According to the method, the material-level sound absorption and insulation performance parameters of the acoustic package assembly are used as basic data, and the sound absorption and insulation performance of the vehicle subsystem is predicted by using the pre-trained sound absorption and insulation performance prediction model, so that the calculation efficiency and the sound absorption and insulation performance prediction efficiency are improved, and the implementation cost is reduced.

Description

Technical Field

[0001] The present application relates to the automotive field, and in particular to an acoustic package performance prediction method, a model training method, a device and an electronic device. Background Art

[0002] With the rapid development of the automobile industry, users' requirements for vehicle comfort are constantly increasing, among which the NVH performance of vehicles has attracted much attention. The NVH performance of vehicles is affected by many factors, including the acoustic package performance of each subsystem of the vehicle.

[0003] Automobile acoustic package refers to the sound-absorbing and sound-insulating parts in the interior parts that deal with the noise of the engine compartment, passenger compartment and luggage compartment. It includes: engine compartment sound insulation pads, inner front wall sound insulation pads, passenger compartment carpets, ceilings, luggage compartment sound insulation pads, wheel cover sound insulation pads, sound-absorbing cotton, cavity sound insulation parts, etc.

[0004] As for the current traditional acoustic package performance research, most of them use a combination of experiments and simulations, through combined wall tests and the establishment of SEA or FE-SEA simulation models, on this basis, the parameters affecting the acoustic package performance are analyzed. The above methods are not good in terms of solution efficiency and computational cost. Summary of the invention

[0005] Based on this, it is necessary to provide an acoustic package performance prediction method, model training method, device and electronic equipment to address the above technical problems, so as to quickly and efficiently predict the acoustic package performance and reduce the implementation cost.

[0006] A method for predicting acoustic package performance of a vehicle subsystem, the subsystem comprising a plurality of acoustic package components, including:

[0007] Obtaining material-level sound absorption and insulation performance parameters of the component, the material-level sound absorption and insulation performance parameters including material parameters of the component, structural parameters of the component, parameters characterizing the sound absorption performance of the material, and / or parameters characterizing the sound insulation performance of the material;

[0008] The material-level sound absorption and insulation performance parameters of each component are input into a pre-trained sound absorption and insulation performance prediction model to predict the sound absorption and insulation performance of the subsystem; the model includes sound absorption and insulation performance prediction units of multiple levels of acoustic packages, and the levels are divided according to the decision-making system of the acoustic package corresponding to the subsystem.

[0009] An acoustic package performance prediction device for a vehicle subsystem, the subsystem comprising a plurality of acoustic package components, including:

[0010] An acquisition module is used to acquire material-level sound absorption and insulation performance parameters of a component, wherein the material-level sound absorption and insulation performance parameters include material parameters of the component, structural parameters of the component, parameters characterizing the sound absorption performance of the material, and / or parameters characterizing the sound insulation performance of the material;

[0011] The prediction module is used to input the material-level sound absorption and insulation performance parameters of each component into a pre-trained sound absorption and insulation performance prediction model to predict the sound absorption and insulation performance of the subsystem; the model includes sound absorption and insulation performance prediction units of multiple levels of acoustic packages, and the levels are divided according to the decision-making system of the acoustic package corresponding to the subsystem.

[0012] A vehicle subsystem sound absorption and insulation performance prediction model training device, the subsystem includes multiple acoustic package components, the prediction model includes a component-level acoustic package sound absorption and insulation performance prediction unit and a system-level acoustic package sound absorption and insulation performance prediction unit, the component level and system level levels are divided according to the decision system of the subsystem acoustic package, the device includes:

[0013] A parameter acquisition module is used to obtain material-level sound absorption and insulation performance parameters of each component, component-level sound absorption and insulation performance parameters, and system-level sound absorption and insulation performance parameters of the vehicle subsystem;

[0014] The first training module is used to train the sound absorption and insulation performance prediction unit of the component-level acoustic package corresponding to the component by using the material-level sound absorption and insulation performance parameters of each component as training samples;

[0015] The second training module is used to train the sound absorption and insulation performance prediction unit of the system-level acoustic package by using the component-level sound absorption and insulation performance parameters of each component as training samples;

[0016] The integration module is used to integrate the trained sound absorption and insulation performance prediction unit of the component-level acoustic package and the trained sound absorption and insulation performance prediction unit of the system-level acoustic package according to the decision system of the subsystem acoustic package to obtain a trained sound absorption and insulation performance prediction model.

[0017] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the acoustic package performance prediction method of the above-mentioned vehicle subsystem or the steps of the sound absorption and insulation performance prediction model training method of the above-mentioned vehicle subsystem are implemented.

[0018] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for predicting the acoustic package performance of a vehicle subsystem or the steps of the above-mentioned method for training a model for predicting the sound absorption and insulation performance of a vehicle subsystem.

[0019] In summary, the present application proposes an acoustic package performance prediction method, a model training method, a device and an electronic device. The present application uses the material-level sound absorption and insulation performance parameters of the acoustic package components as basic data, and uses a pre-trained sound absorption and insulation performance prediction model to predict the sound absorption and insulation performance of the vehicle subsystem, thereby achieving rapid modeling, improving the calculation efficiency and the sound absorption and insulation performance prediction efficiency, and reducing the implementation cost. The present application constructs a prediction model in a hierarchical manner through a divided acoustic package hierarchical decision system to enhance the prediction accuracy of the trained prediction model. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0021] Figure 1 is a flow chart of a method for predicting acoustic package performance of a vehicle subsystem according to an exemplary embodiment of the present application;

[0022] Figure 2 is a flow chart of a method for predicting acoustic package performance of a vehicle subsystem according to an exemplary embodiment of the present application;

[0023] Figure 3 is a flow chart of a method for predicting acoustic package performance of a vehicle subsystem according to an exemplary embodiment of the present application;

[0024] Figure 4 It is a block diagram of a multi-level target decision system of a floor acoustic package in a method for predicting acoustic package performance of a vehicle subsystem according to an exemplary embodiment of the present application;

[0025] Figure 5 is a flowchart of model training based on a floor acoustic package target decision system according to an exemplary embodiment of the present application;

[0026] Figure 6 is a flow chart of a method for training a prediction model for sound absorption and insulation performance of a vehicle subsystem according to an exemplary embodiment of the present application;

[0027] Figure 7 is a block diagram of an acoustic package performance prediction device for a vehicle subsystem according to an exemplary embodiment of the present application;

[0028] Figure 8 It is a block diagram of a vehicle subsystem sound absorption and insulation performance prediction model training device according to an exemplary embodiment of the present application;

[0029] Fig. 9 It is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. The embodiments described by reference to the drawings are exemplary and are intended to be used to explain the present application, and cannot be understood as limiting the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0031] Figure 1 is a flow chart of a method for predicting acoustic package performance of a vehicle subsystem according to an exemplary embodiment of the present application, such as Figure 1 As shown, the acoustic package performance prediction method of the vehicle subsystem includes the following steps:

[0032] S101, obtaining material-level sound absorption and insulation performance parameters of a component, wherein the material-level sound absorption and insulation performance parameters include material parameters of the component, structural parameters of the component, parameters characterizing the sound absorption performance of the material, and parameters characterizing the sound insulation performance of the material.

[0033] The acoustic package performance prediction method of the vehicle subsystem of the embodiment of the present application can be applied to the noise attenuation prediction scenario for the vehicle floor system, and the noise attenuation of the floor system is obtained by predicting the sound absorption and insulation performance of the floor system. It can be performed by the acoustic package performance prediction device of the vehicle subsystem provided by the embodiment of the present application, and the acoustic package performance prediction device of the vehicle subsystem can be set in a vehicle or other electronic equipment.

[0034] In practice, a vehicle includes multiple subsystems, and the subsystems related to acoustic performance are provided with corresponding acoustic packages, which refer to the sound-absorbing and sound-insulating parts in the vehicle interior parts (i.e., the acoustic package components mentioned in this application) that process the noise of the engine compartment, passenger compartment, and luggage compartment. For example, they include: engine compartment sound insulation pads, inner front wall sound insulation pads, passenger compartment carpets, ceilings, luggage compartment sound insulation pads, wheel cover sound insulation pads, sound-absorbing cotton, and cavity sound insulation parts.

[0035] In the embodiment of the present application, before predicting the acoustic performance of the acoustic package, it is necessary to obtain the material-level sound absorption and insulation performance parameters of each component in the acoustic package. It is not difficult to understand that the material-level sound absorption and insulation performance parameters are parameters related to the constituent materials of the components and parameters related to the acoustic performance of the material. In practice, the acoustic performance is mainly manifested in sound absorption performance and sound insulation performance. In practice, based on the properties of the material itself, the acoustic performance-related parameters corresponding to each component are sound absorption performance parameters and / or sound insulation performance parameters. For example, the material of the floor sheet metal is sheet metal. The sheet metal itself has no sound absorption coefficient. Therefore, for the sheet metal, only its sound insulation performance needs to be considered.

[0036] This application takes the floor system in the vehicle subsystem as an example. The components in the floor acoustic package include but are not limited to floor sheet metal, carpet and battery pack. The carpet is composed of carpet flat panels, and the material-level sound absorption and insulation performance parameters of the carpet flat panel include parameters related to the carpet flat panel (i.e. the above-mentioned material parameters and structural parameters), parameters characterizing the sound absorption performance of the carpet flat panel, and parameters characterizing the sound insulation performance of the carpet flat panel. In some embodiments, material parameters include but are not limited to the material name and the total area of ​​the material, etc.; structural parameters include but are not limited to the area ratio of each thickness of the material, etc.

[0037] For example, the material parameters corresponding to the floor sheet metal are: the material name is sheet metal plate, and the total material area is the total area of ​​the sheet metal plate of the whole vehicle; the structural parameters corresponding to the floor sheet metal are: the area ratio of each thickness of the floor sheet metal, that is, the ratio of the area of ​​the sheet metal plate of each thickness to the area of ​​the sheet metal plate of the whole vehicle;

[0038] Material parameters corresponding to the carpet: the material name is carpet, the total material area is the total area of ​​the vehicle carpet; the structural parameters corresponding to the carpet are the area ratio of each thickness of the carpet flat plate;

[0039] Material parameters corresponding to the battery pack: the material name is battery pack, the total material area is the total area of ​​the battery pack of the whole vehicle; the structural parameters corresponding to the battery pack are the area ratio of each thickness of the battery pack.

[0040] In practice, there are various parameters that characterize the acoustic properties of materials. For example, the parameters that characterize the sound absorption performance include the sound absorption coefficient.

[0041] The parameters characterizing the sound insulation performance include sound insulation value, sound insulation index, transmission loss and insertion loss, etc. Therefore, the parameters characterizing the sound absorption performance and the parameters characterizing the sound insulation performance mentioned in this application are not specifically limited, and appropriate parameters can be selected according to needs.

[0042] As a feasible implementation method, for floor sheet metal, transmission loss is used as a parameter to characterize the sound insulation performance of floor sheet metal; for carpet, insertion loss is used as a parameter to characterize the sound insulation performance of carpet, and sound absorption coefficient is used as a parameter to characterize the sound absorption performance of carpet; for battery pack, insertion loss is used as a parameter to characterize the sound insulation performance of battery pack, and sound absorption coefficient is used as a parameter to characterize the sound absorption performance of battery pack.

[0043] Therefore, in some embodiments, the "parameter characterizing the sound insulation performance of the material" corresponding to the above-mentioned floor sheet metal is the transmission loss of each thickness of the sheet metal flat piece;

[0044] The "parameter characterizing the sound insulation performance of the material" corresponding to the above carpet is the insertion loss of each thickness of the carpet flat piece, and the "parameter characterizing the sound absorption performance of the material" corresponding to the above carpet is the sound absorption coefficient of each thickness of the carpet flat piece;

[0045] The "parameter characterizing the sound insulation performance of the material" corresponding to the battery pack is the insertion loss of each thickness of the flat parts of the battery pack, and the corresponding "parameter characterizing the sound absorption performance of the material" is the sound absorption coefficient of each thickness of the flat parts of the battery pack.

[0046] The parameters of other possible components are set according to the above description and will not be repeated here.

[0047] This application obtains the sound absorption / insulation performance parameters of each material at different thicknesses and the proportion of the material area of ​​different thicknesses relative to the total area based on the material properties, and improves the accuracy of the sound absorption and insulation performance prediction by adding these material parameters and structural parameters.

[0048] In some embodiments, the above-mentioned sound absorption performance parameters or sound insulation performance parameters can be obtained through methods such as anechoic chamber-reverberation chamber test, reverberation box test or standing wave tube test.

[0049] S102, inputting the material-level sound absorption and insulation performance parameters of each component into a pre-trained sound absorption and insulation performance prediction model to predict the sound absorption and insulation performance of the subsystem; the model includes sound absorption and insulation performance prediction units of multiple levels of acoustic packages, and the levels are divided according to the decision system of the acoustic package corresponding to the subsystem.

[0050] In an embodiment of the present application, a sound absorption and insulation performance prediction model is pre-constructed and trained, and the prediction model includes sound absorption and insulation performance prediction units of multiple levels of acoustic packages from component level to system level, so that the sound absorption and insulation performance of the system-level acoustic package can be accurately predicted based on relevant data at the underlying material level.

[0051] In the embodiment of the present application, the sound absorption and insulation performance prediction unit of the divided hierarchical acoustic package includes a sound absorption and insulation performance prediction unit of the component-level acoustic package and a sound absorption and insulation performance prediction unit of the system-level acoustic package.

[0052] Among them, the sound absorption and insulation performance pre-charging unit of the component-level acoustic package is used to predict the sound absorption and insulation performance of each component contained in the subsystem acoustic package, such as predicting the sound absorption and insulation performance of the floor sheet metal of the whole vehicle under the floor acoustic package, predicting the sound absorption and insulation performance of the carpet of the whole vehicle, and predicting the sound absorption and insulation performance of the battery pack of the whole vehicle.

[0053] The sound absorption and insulation performance prediction unit of the system-level acoustic package is used to predict the sound absorption and insulation performance of a subsystem, such as the sound absorption and insulation performance prediction of a vehicle's floor system.

[0054] In the present application, the material-level sound absorption and insulation performance parameters of each component contained in the system acoustic package are input into a pre-trained sound absorption and insulation performance prediction model, and the sound absorption and insulation performance prediction of the vehicle subsystem is finally achieved through hierarchical prediction.

[0055] The present application uses the material-level sound absorption and insulation performance parameters of the acoustic package components as basic data, and utilizes a pre-trained sound absorption and insulation performance prediction model to perform hierarchical sound absorption and insulation performance predictions on the vehicle subsystem. This method requires a simple model structure, facilitates rapid modeling, improves computational efficiency and sound absorption and insulation performance prediction efficiency, reduces implementation costs, and performs hierarchical sound absorption and insulation performance predictions based on the trained prediction model to increase prediction accuracy.

[0056] Based on the above embodiments, Figure 2 As shown, in the embodiment of the present application, the above step S102, "inputting the material-level sound absorption and insulation performance parameters of each component into a pre-trained sound absorption and insulation performance prediction model to predict the sound absorption and insulation performance of the subsystem" includes the following steps:

[0057] S201, inputting the material-level sound absorption and insulation performance parameters of each component into the sound absorption and insulation performance prediction unit of the component-level acoustic package to obtain the component-level sound absorption and insulation performance parameters, wherein the component-level sound absorption and insulation performance parameters include at least one of the following: a parameter characterizing the sound absorption performance of the component and a parameter characterizing the sound insulation performance of the component.

[0058] In the embodiment of the present application, the material-level sound absorption and insulation performance parameters of each component are respectively input into the sound absorption and insulation performance prediction unit of the component-level acoustic package to obtain the component-level sound absorption and insulation performance parameters corresponding to each component. The component-level sound absorption and insulation performance parameters include but are not limited to parameters characterizing the sound absorption performance of the component and / or parameters characterizing the sound insulation performance of the component. The setting of the parameters characterizing the sound absorption performance of the component and the parameters characterizing the sound insulation performance of the component can be referred to the description of the above embodiment, which will not be repeated here.

[0059] For example, the transmission loss of each thickness of the carpet slab is obtained through the anechoic chamber-reverberation chamber test, and the sound absorption coefficient of each thickness of the carpet slab is obtained through the reverberation box test. The transmission loss of each thickness, the sound absorption coefficient of each thickness, the total area of ​​the carpet slab of the whole vehicle and the area ratio of each thickness of the carpet parts are input into the sound absorption and insulation performance prediction unit of the component-level acoustic package to obtain the loss function and sound absorption coefficient of the carpet parts of the whole vehicle. S202, input the component-level sound absorption and insulation performance parameters into the sound absorption and insulation performance prediction unit of the system-level acoustic package to obtain the system-level sound absorption and insulation performance parameters, and the system-level sound absorption and insulation parameters include at least one of the following: a parameter characterizing the sound absorption performance of the subsystem and a parameter characterizing the sound insulation performance of the subsystem.

[0060] In the embodiment of the present application, the component-level sound absorption and insulation performance parameters corresponding to each component under the subsystem acoustic package are input into the sound absorption and insulation performance prediction unit of the system-level acoustic package to obtain the system-level sound absorption and insulation performance parameters. Among them, the system-level sound absorption and insulation performance parameters include but are not limited to parameters characterizing the sound absorption performance of the subsystem and / or parameters characterizing the sound insulation performance of the subsystem. The setting of the parameters characterizing the sound absorption performance of the subsystem and the parameters characterizing the sound insulation performance of the subsystem can be referred to the description of the above embodiment, and will not be repeated here.

[0061] For example, the transmission loss of the vehicle floor sheet metal, the insertion loss and sound absorption coefficient of the vehicle carpet, and the insertion loss and sound absorption coefficient of the battery pack are input into the prediction unit of the sound absorption and insulation performance of the system-level acoustic package to obtain the transmission loss and sound absorption coefficient of the subsystem floor system.

[0062] This application also provides a training process for the sound absorption and insulation performance prediction model. Figure 3 As shown, Figure 3 The flowchart of training a sound absorption and insulation performance prediction model in a method for predicting acoustic package performance of a vehicle subsystem according to an exemplary embodiment of the present application includes the following steps:

[0063] S301, determine a multi-level target decision system for a subsystem acoustic package.

[0064] In the embodiment of the present application, a multi-level target decision system is extracted based on the composition structure of the acoustic package of the vehicle subsystem. Figure 4 An exemplary multi-level target decision system for floor acoustics.

[0065] Combination Figure 4 The multi-level target decision-making system can be simply understood as follows: the constituent materials of the components, the total area occupied by the materials, the area proportion of materials of different thicknesses, and the sound absorption and insulation performance of different thicknesses jointly play a decisive role in the sound absorption and insulation performance of the components, and the sound absorption and insulation performance of different components plays a decisive role in the sound absorption and insulation performance of the entire subsystem.

[0066] S302: Acquire the sound absorption and insulation performance parameters corresponding to each level according to the multi-level target decision system.

[0067] In the embodiments of the present application, methods such as anechoic chamber-reverberation chamber test, reverberation box test or standing wave tube test can be selected to obtain the sound absorption and insulation performance corresponding to each component material, the sound absorption and insulation performance corresponding to each component and the sound absorption and insulation performance corresponding to the subsystem.

[0068] For example, when obtaining the sound absorption and insulation performance corresponding to the carpet flat piece of the component, the carpet flat piece can be manufactured as required, and the transmission loss and the sound absorption coefficient of the carpet flat piece can be tested.

[0069] The above-mentioned collected data are preprocessed, and a multi-level database system is established based on the established multi-level target decision-making system of the floor acoustic package. The collected data are stored in the database, which mainly includes the floor system sound absorption and insulation performance parameter database, the acoustic package (such as floor sheet metal and carpet) component sound absorption and insulation performance parameter database, and the flat-level / material-level sound absorption and insulation performance parameter database of floor sheet metal and carpet.

[0070] S303: construct training samples based on the sound absorption and insulation performance parameters corresponding to each level, and perform model training on the sound absorption and insulation performance prediction model by training the training samples.

[0071] In an embodiment of the present application, a model training sample is constructed based on the sound absorption and insulation performance parameters corresponding to each level stored in a database, and the sample can be divided into a training set and a test set.

[0072] In some embodiments, based on a data-driven approach, an automated prediction model is formed through training and fitting based on sample data.

[0073] As a feasible implementation method, a neural network is used to build a sub-model corresponding to each level, that is, a sound absorption and insulation performance prediction unit of each level of acoustic package, and the parameters of each sub-model are trained on the training set. After several rounds of training, the sub-model is tested using the labeled data of the test set. If the prediction effect of the sub-model is unsatisfactory after the test, the training continues until the prediction effect is qualified, and the training is terminated to obtain a trained sub-model.

[0074] The various sub-models are integrated according to the multi-level target decision system of the acoustic package to obtain the overall sound absorption and insulation performance prediction model. The prediction effect of the overall sound absorption and insulation performance prediction model can also be tested again based on the label data of the test set.

[0075] For example, see Figure 5 , using the material-level sound absorption and insulation performance parameters as training samples, the sound absorption and insulation performance prediction unit of the component-level acoustic package is trained; using the component-level sound absorption and insulation performance parameters as training samples, the sound absorption and insulation performance prediction unit of the system-level acoustic package is trained.

[0076] In summary, the present application performs a multi-level target decomposition of the sound absorption and insulation performance of the subsystem acoustic package, and decomposes and quantifies it from top to bottom into system-level, component-level, and flat material-level design parameters, thereby forming a multi-level target decision system for the floor acoustic package, and uses a data-driven approach to establish a multi-level target performance prediction model for the acoustic package. There is no need to perform a large amount of modeling and correction work on the model, and there is no need to obtain too many complex modeling parameters, which achieves rapid modeling and reduces implementation costs. Through the divided acoustic package hierarchical decision system, a prediction model is constructed hierarchically, which enhances the prediction accuracy of the trained prediction model and facilitates more efficient and objective acoustic package development.

[0077] Figure 6 The present invention is a flowchart of a method for training a sound absorption and insulation performance prediction model of a vehicle subsystem according to an exemplary embodiment of the present invention. The subsystem includes multiple acoustic package components. The prediction model includes a sound absorption and insulation performance prediction unit of a component-level acoustic package and a sound absorption and insulation performance prediction unit of a system-level acoustic package. The levels of the component-level and system-level are divided according to the decision-making system of the subsystem acoustic package, such as Figure 6 As shown, the method comprises the following steps:

[0078] S601, obtaining material-level sound absorption and insulation performance parameters of each component, component-level sound absorption and insulation performance parameters, and system-level sound absorption and insulation performance parameters of the vehicle subsystem;

[0079] S602, using the material-level sound absorption and insulation performance parameters of each component as training samples, respectively, training the sound absorption and insulation performance prediction unit of the component-level acoustic package corresponding to the component;

[0080] S603, using the component-level sound absorption and insulation performance parameters of each component as training samples, training the sound absorption and insulation performance prediction unit of the system-level acoustic package;

[0081] S604, according to the decision system of the subsystem acoustic package, the trained sound absorption and insulation performance prediction unit of the component-level acoustic package and the trained sound absorption and insulation performance prediction unit of the system-level acoustic package are integrated to obtain a trained sound absorption and insulation performance prediction model.

[0082] The sound absorption and insulation performance prediction model training process of the vehicle subsystem in the embodiment of the present application is the same as the sound absorption and insulation performance prediction model training process in the above embodiment. Please refer to the description of the sound absorption and insulation performance prediction model training process in the above embodiment, which will not be repeated here.

[0083] This application is based on the multi-level target decision system of the vehicle subsystem acoustic package, and uses a data-driven method to establish a multi-level target performance prediction model for the acoustic package. It does not require a large amount of modeling and correction work on the model, and does not require the acquisition of too many complex modeling parameters. It achieves rapid modeling and reduces implementation costs. Through the divided acoustic package hierarchical decision system, the prediction model is constructed hierarchically, which enhances the prediction accuracy of the trained prediction model and facilitates more efficient and objective acoustic package development.

[0084] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0085] Figure 7 is a block diagram of an acoustic packet performance prediction device for a vehicle subsystem according to an exemplary embodiment of the present application, such as Figure 7 As shown, the device 700 includes: an acquisition module 701 and a prediction module 703.

[0086] An acquisition module 701 is used to acquire material-level sound absorption and insulation performance parameters of a component, where the material-level sound absorption and insulation performance parameters include material parameters of the component, structural parameters of the component, parameters characterizing the sound absorption performance of the material, and / or parameters characterizing the sound insulation performance of the material;

[0087] The prediction module 702 is used to input the material-level sound absorption and insulation performance parameters of each component into a pre-trained sound absorption and insulation performance prediction model to predict the sound absorption and insulation performance of the subsystem; the model includes sound absorption and insulation performance prediction units of multiple levels of acoustic packages, and the levels are divided according to the decision system of the acoustic package corresponding to the subsystem.

[0088] In the embodiment of the present application, the material parameters include at least the following two types: material name and total area of ​​the material; the structural parameters include at least one of the following: the area ratio of each thickness of the material.

[0089] In the embodiment of the present application, the sound absorption and insulation performance prediction unit of the hierarchical acoustic package includes a sound absorption and insulation performance prediction unit of the component-level acoustic package and a sound absorption and insulation performance prediction unit of the system-level acoustic package.

[0090] In the embodiment of the present application, the above-mentioned prediction module 702 includes: a first prediction submodule, which is used to input the material-level sound absorption and insulation performance parameters of each component into the sound absorption and insulation performance prediction unit of the component-level acoustic package to obtain the component-level sound absorption and insulation performance parameters, and the component-level sound absorption and insulation performance parameters include at least one of the following: a parameter characterizing the sound absorption performance of the component and a parameter characterizing the sound insulation performance of the component; a second prediction submodule, which is used to input the component-level sound absorption and insulation performance parameters into the sound absorption and insulation performance prediction unit of the system-level acoustic package to obtain the system-level sound absorption and insulation performance parameters, and the system-level sound absorption and insulation parameters include at least one of the following: a parameter characterizing the sound absorption performance of the subsystem and a parameter characterizing the sound insulation performance of the subsystem.

[0091] In the embodiment of the present application, the above-mentioned device 700 further includes:

[0092] A determination module for determining a multi-level target decision system for a subsystem acoustic package;

[0093] A hierarchical parameter acquisition module is used to obtain the sound absorption and insulation performance parameters corresponding to each level according to the multi-level target decision system;

[0094] The model training module is used to construct training samples based on the sound absorption and insulation performance parameters corresponding to each level, and to train the sound absorption and insulation performance prediction model by training the training samples.

[0095] In the embodiment of the present application, the model training module is further used for:

[0096] The material-level sound absorption and insulation performance parameters of each component are used as training samples to train the sound absorption and insulation performance prediction unit of the component-level acoustic package corresponding to the component;

[0097] The component-level sound absorption and insulation performance parameters of each component are used as training samples to train the sound absorption and insulation performance prediction unit of the system-level acoustic package;

[0098] According to the multi-level target decision system, the trained component-level acoustic package's sound absorption and insulation performance prediction unit and the trained system-level acoustic package's sound absorption and insulation performance prediction unit are integrated to obtain a trained sound absorption and insulation performance prediction model.

[0099] It should be noted that the above explanation of the embodiment of the method for predicting the acoustic package performance of a vehicle subsystem is also applicable to the device for predicting the acoustic package performance of a vehicle subsystem in the embodiment of the present application, and the specific process will not be repeated here.

[0100] Each module in the acoustic package performance prediction device of the vehicle subsystem can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0101] In summary, the present application proposes a device for predicting the performance of an acoustic package of a vehicle subsystem. The present application performs a multi-level target decomposition on the sound absorption and insulation performance of the acoustic package of the subsystem, and decomposes and quantifies it from top to bottom into system-level, component-level, and flat material-level design parameters, thereby forming a multi-level target decision system for the floor acoustic package. The method of establishing a multi-level target performance prediction model for the acoustic package using a data-driven method does not require a large amount of modeling and correction work on the model, and does not require obtaining too many complex modeling parameters, thereby achieving rapid modeling and reducing implementation costs. The material-level sound absorption and insulation performance parameters of the acoustic package components are used as basic data, and a pre-trained sound absorption and insulation performance prediction model is used to predict the sound absorption and insulation performance of the vehicle subsystem, thereby improving computational efficiency. The present application uses a divided acoustic package hierarchical decision system to construct a prediction model in a hierarchical manner, thereby enhancing the prediction accuracy of the trained prediction model and facilitating more efficient and objective acoustic package development.

[0102] Figure 8 is a block diagram of a vehicle subsystem sound absorption and insulation performance prediction model training device according to an exemplary embodiment of the present application, such as Figure 8 As shown, the device 800 includes: a parameter acquisition module 801, a first training module 802, a second training module 803 and an integration module 804.

[0103] The parameter acquisition module 801 is used to acquire the material-level sound absorption and insulation performance parameters of each component, the component-level sound absorption and insulation performance parameters, and the system-level sound absorption and insulation performance parameters of the vehicle subsystem;

[0104] The first training module 802 is used to train the sound absorption and insulation performance prediction unit of the component-level acoustic package corresponding to the component by using the material-level sound absorption and insulation performance parameters of each component as training samples;

[0105] The second training module 803 is used to train the sound absorption and insulation performance prediction unit of the system-level acoustic package by using the component-level sound absorption and insulation performance parameters of each component as training samples;

[0106] The integration module 804 is used to integrate the trained sound absorption and insulation performance prediction unit of the component-level acoustic package and the trained sound absorption and insulation performance prediction unit of the system-level acoustic package according to the decision system of the subsystem acoustic package to obtain a trained sound absorption and insulation performance prediction model.

[0107] It should be noted that the above explanation of the embodiment of the vehicle subsystem sound absorption and insulation performance prediction model training method is also applicable to the vehicle subsystem sound absorption and insulation performance prediction model training device of the embodiment of the present application, and the specific process will not be repeated here.

[0108] Each module in the above-mentioned vehicle subsystem sound absorption and insulation performance prediction model training device can be fully or partially implemented by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0109] This application is based on the multi-level target decision system of the vehicle subsystem acoustic package, and uses a data-driven method to establish a multi-level target performance prediction model for the acoustic package. It does not require a large amount of modeling and correction work on the model, and does not require the acquisition of too many complex modeling parameters. It achieves rapid modeling and reduces implementation costs. Through the divided acoustic package hierarchical decision system, the prediction model is constructed hierarchically, which enhances the prediction accuracy of the trained prediction model and facilitates more efficient and objective acoustic package development.

[0110] In order to implement the above embodiment, the present application embodiment also proposes an electronic device 900, such as Fig. 9 As shown, the electronic device 900 may specifically include: a memory 901, a processor 902, and a computer program stored in the memory 901 and executable on the processor 902. When the processor 902 executes the program, the steps of the method for predicting the acoustic package performance of a vehicle subsystem or the steps of the method for training a sound absorption and insulation performance prediction model of a vehicle subsystem as shown in the above-mentioned embodiment are implemented.

[0111] In summary, the present application proposes an electronic device, which performs a multi-level target decomposition of the sound absorption and insulation performance of the subsystem acoustic package, and decomposes and quantifies it from top to bottom into system-level, component-level, and flat material-level design parameters, thereby forming a multi-level target decision system for the floor acoustic package. The method of establishing a multi-level target performance prediction model for the acoustic package using a data-driven method does not require a large amount of modeling and correction work on the model, and does not require obtaining too many complex modeling parameters, thereby achieving rapid modeling and reducing implementation costs. The material-level sound absorption and insulation performance parameters of the acoustic package components are used as basic data, and the sound absorption and insulation performance prediction model that has been pre-trained is used to predict the sound absorption and insulation performance of the vehicle subsystem, thereby improving the computational efficiency. The present application uses the divided acoustic package hierarchical decision system to construct a prediction model in a hierarchical manner, thereby enhancing the prediction accuracy of the trained prediction model, and facilitating more efficient and objective acoustic package development.

[0112] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0113] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0114] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for predicting acoustic package performance of a vehicle subsystem, wherein the subsystem comprises a plurality of acoustic package components, characterized in that: include: Acquiring material-level sound absorption and insulation performance parameters of the component, wherein the material-level sound absorption and insulation performance parameters include material parameters of the component, structural parameters of the component, parameters characterizing material sound absorption performance, and / or parameters characterizing material sound insulation performance; Inputting the material-level sound absorption and insulation performance parameters of each of the components into a pre-trained sound absorption and insulation performance prediction model to predict the sound absorption and insulation performance of the subsystem; The model includes a plurality of levels of acoustic package sound absorption and insulation performance prediction units, and the levels are divided according to the decision-making system of the subsystem corresponding to the acoustic package.

2. The method according to claim 1, characterized in that The material parameters include at least the following two: material name and total area of ​​the material; The structural parameters include at least one of the following: the area ratio of each thickness of the material.

3. The method according to claim 1, characterized in that The sound absorption and insulation performance prediction unit of the hierarchical acoustic package includes a sound absorption and insulation performance prediction unit of the component-level acoustic package and a sound absorption and insulation performance prediction unit of the system-level acoustic package.

4. The method according to claim 3, characterized in that The step of inputting the material-level sound absorption and insulation performance parameters of each of the components into a pre-trained sound absorption and insulation performance prediction model to predict the sound absorption and insulation performance of the subsystem includes: Inputting the material-level sound absorption and insulation performance parameters of each component into the sound absorption and insulation performance prediction unit of the component-level acoustic package to obtain component-level sound absorption and insulation performance parameters, wherein the component-level sound absorption and insulation performance parameters include at least one of the following: a parameter characterizing the sound absorption performance of the component and a parameter characterizing the sound insulation performance of the component; The component-level sound absorption and insulation performance parameters are input into the sound absorption and insulation performance prediction unit of the system-level acoustic package to obtain the system-level sound absorption and insulation performance parameters, wherein the system-level sound absorption and insulation parameters include at least one of the following: a parameter characterizing the sound absorption performance of the subsystem and a parameter characterizing the sound insulation performance of the subsystem.

5. The method according to claim 4, characterized in that The sound absorption and insulation performance prediction model is trained in the following way: Determine the multi-level target decision system for the subsystem acoustic package; According to the multi-level target decision system, the sound absorption and insulation performance parameters corresponding to each level are obtained; A training sample is constructed based on the sound absorption and insulation performance parameters corresponding to each level, and the sound absorption and insulation performance prediction model is trained by training the training sample.

6. The method according to claim 5, characterized in that The step of constructing training samples based on the sound absorption and insulation performance parameters corresponding to each level, and training the sound absorption and insulation performance prediction model by training the training samples, includes: Using the material-level sound absorption and insulation performance parameters of each component as training samples, respectively, training the sound absorption and insulation performance prediction unit of the component-level acoustic package corresponding to the component; The component-level sound absorption and insulation performance parameters of each component are used as training samples to train the sound absorption and insulation performance prediction unit of the system-level acoustic package; According to the multi-level target decision system, the trained sound absorption and insulation performance prediction unit of the component-level acoustic package and the trained sound absorption and insulation performance prediction unit of the system-level acoustic package are integrated to obtain a trained sound absorption and insulation performance prediction model.

7. A method for training a prediction model for the sound absorption and insulation performance of a vehicle subsystem, wherein the subsystem includes a plurality of acoustic package components, characterized in that: The prediction model includes a component-level acoustic package sound absorption and insulation performance prediction unit and a system-level acoustic package sound absorption and insulation performance prediction unit. The component-level and system-level levels are divided according to the decision system of the subsystem acoustic package. The method includes: Obtain material-level sound absorption and insulation performance parameters of each component, component-level sound absorption and insulation performance parameters, and system-level sound absorption and insulation performance parameters of the vehicle subsystem; Using the material-level sound absorption and insulation performance parameters of each component as training samples, respectively, training the sound absorption and insulation performance prediction unit of the component-level acoustic package corresponding to the component; Using the component-level sound absorption and insulation performance parameters of each component as training samples, training the sound absorption and insulation performance prediction unit of the system-level acoustic package; According to the decision system of the subsystem acoustic package, the trained sound absorption and insulation performance prediction unit of the component-level acoustic package and the trained sound absorption and insulation performance prediction unit of the system-level acoustic package are integrated to obtain a trained sound absorption and insulation performance prediction model.

8. An acoustic package performance prediction device for a vehicle subsystem, the subsystem comprising a plurality of acoustic package components, characterized in that: include: An acquisition module is used to acquire material-level sound absorption and insulation performance parameters of the component, wherein the material-level sound absorption and insulation performance parameters include material parameters of the component, structural parameters of the component, parameters characterizing the sound absorption performance of the material, and / or parameters characterizing the sound insulation performance of the material; A prediction module is used to input the material-level sound absorption and insulation performance parameters of each of the components into a pre-trained sound absorption and insulation performance prediction model to predict the sound absorption and insulation performance of the subsystem; the model includes sound absorption and insulation performance prediction units of multiple levels of acoustic packages, and the levels are divided according to the decision system of the acoustic package corresponding to the subsystem.

9. A vehicle subsystem sound absorption and insulation performance prediction model training device, the subsystem comprising a plurality of acoustic package components, characterized in that: The prediction model includes a component-level acoustic package sound absorption and insulation performance prediction unit and a system-level acoustic package sound absorption and insulation performance prediction unit. The component-level and system-level levels are divided according to the decision system of the subsystem acoustic package. The device includes: A parameter acquisition module is used to obtain material-level sound absorption and insulation performance parameters of each component, component-level sound absorption and insulation performance parameters, and system-level sound absorption and insulation performance parameters of the vehicle subsystem; The first training module is used to train the sound absorption and insulation performance prediction unit of the component-level acoustic package corresponding to the component by using the material-level sound absorption and insulation performance parameters of each component as training samples; A second training module is used to train the sound absorption and insulation performance prediction unit of the system-level acoustic package by using the component-level sound absorption and insulation performance parameters of each component as training samples; An integration module is used to integrate the trained sound absorption and insulation performance prediction unit of the component-level acoustic package and the trained sound absorption and insulation performance prediction unit of the system-level acoustic package according to the decision system of the subsystem acoustic package to obtain a trained sound absorption and insulation performance prediction model.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for predicting the acoustic package performance of a vehicle subsystem as described in any one of claims 1 to 6 or the steps of the method for training a model for predicting the sound absorption and insulation performance of a vehicle subsystem as described in claim 7 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method for predicting the acoustic package performance of a vehicle subsystem as described in any one of claims 1 to 6 or the steps of the method for training a model for predicting the sound absorption and insulation performance of a vehicle subsystem as described in claim 7 are implemented.

Images