Material sound absorption and insulation performance prediction method and device, computer equipment and storage medium
By using deep learning models to process material parameters, predicting the sound absorption and insulation performance data of the material, the problem of low prediction accuracy of sound absorption and insulation performance in the prior art is solved, and more efficient material performance prediction is achieved.
Patent Information
- Application Number
- CN202311203599.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-18
- Publication Date
- 2025-03-25
AI Technical Summary
The existing materials' sound absorption and insulation performance prediction methods have poor accuracy and are limited to linear systems and existing sample data, so they cannot effectively predict the sound absorption and insulation performance of different materials.
By obtaining multiple material parameters of the material to be tested and inputting them into the trained sound-absorbing and insulation performance prediction model, deep learning models trained by historical data (such as one-dimensional convolutional neural networks) predict the material's sound-absorbing and insulation performance data.
It greatly reduces the complexity of noise analysis, can quantitatively extract the noise contribution of each frequency, quickly predict the sound insulation performance data of different materials, and improves the prediction ability and efficiency of the sound insulation performance of the material.
Smart Images
Figure CN119694453A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of material acoustic performance testing, and in particular to a method, device, computer equipment and storage medium for predicting material sound absorption and insulation performance. Background Art
[0002] The acoustic package is an automotive component used to reduce noise and vibration. It is composed of sound insulation and sound absorption materials, which can reduce the entry of external noise and the propagation of internal noise. As an important automotive component, the acoustic package plays a very important role in the NVH (Noise, Vibration, and Harshness) of the entire vehicle. Acoustic materials with different formulations have a significant impact on the sound absorption and insulation performance of components and the entire vehicle. The sound absorption and insulation performance of materials is mainly obtained based on testing, but the test takes a long time and cannot be exhaustively tested.
[0003] The existing prediction method of material sound absorption and insulation performance is based on the combined sound insulation theory and statistical energy method, with poor accuracy and limited to linear systems and existing sample data. Therefore, it is necessary to find a new prediction method for material sound absorption and insulation performance to improve the prediction ability of material sound absorption and insulation performance and improve the prediction efficiency. Summary of the invention
[0004] Based on this, it is necessary to provide a material sound absorption and insulation performance prediction method, device, computer equipment and storage medium to address the above technical problems, so as to improve the prediction ability of material sound absorption and insulation performance and improve the prediction efficiency.
[0005] A method for predicting the sound absorption and insulation performance of a material, comprising:
[0006] Obtain multiple material parameters of the material to be tested;
[0007] The multiple material parameters are input into a sound absorption and insulation performance prediction model to obtain sound absorption and insulation performance data of the material to be tested output by the sound absorption and insulation performance prediction model.
[0008] A device for predicting sound absorption and insulation performance of a material, comprising:
[0009] A material parameter acquisition module is used to acquire multiple material parameters of the material to be tested;
[0010] The performance prediction module is used to input the multiple material parameters into the sound absorption and insulation performance prediction model to obtain the sound absorption and insulation performance data of the material to be tested output by the sound absorption and insulation performance prediction model.
[0011] A computer device comprises a memory, a processor and computer-readable instructions stored in the memory and executable on the processor, wherein the processor implements the above-mentioned material sound absorption and insulation performance prediction method when executing the computer-readable instructions.
[0012] One or more readable storage media storing computer-readable instructions, when the computer-readable instructions are executed by one or more processors, the one or more processors execute the above-mentioned material sound absorption and insulation performance prediction method.
[0013] The above-mentioned material sound absorption and insulation performance prediction method, device, computer equipment and storage medium use the sound absorption and insulation performance prediction model obtained by training historical material sound absorption and insulation performance data to process the material parameters of the material to be tested, which greatly reduces the complexity of noise analysis, and can quantitatively extract the noise contribution of each frequency, quickly predict the sound absorption and insulation performance data of different materials, and provide assistance for the selection of acoustic package materials. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.
[0015] Figure 1 It is a schematic diagram of a process of a method for predicting the sound absorption and insulation performance of a material in one embodiment of the present invention;
[0016] Figure 2 A comparison chart of the sound absorption and insulation performance data predicted by the sound absorption and insulation performance prediction model in one embodiment of the present invention and the sound absorption and insulation performance data obtained by actual testing;
[0017] Figure 3 2 is a schematic diagram of a structure of a device for predicting sound absorption and insulation performance of a material in one embodiment of the present invention;
[0018] Figure 4 is a schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION
[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0020] In one embodiment, if Figure 1 As shown, a method for predicting the sound absorption and insulation performance of a material is provided, comprising the following steps:
[0021] S10, obtaining multiple material parameters of the material to be tested;
[0022] S20: input the plurality of material parameters into a sound absorption and insulation performance prediction model, and obtain sound absorption and insulation performance data of the material to be tested output by the sound absorption and insulation performance prediction model.
[0023] Understandably, the material to be tested may be a material used as an acoustic bag. Appropriate material parameters are selected based on the characteristics of the material to be tested. Different materials to be tested may have the same or different corresponding material parameters. In some examples, the material parameters may be material thickness, surface density, hard layer material, number of composite layers, and the like.
[0024] The sound absorption and insulation performance prediction model can be used to process multiple material parameters of the material to be tested to generate the sound absorption and insulation performance data of the material to be tested. Here, the sound absorption and insulation performance prediction model is a deep learning model trained using the sound absorption and insulation performance data of the tested material. The sound absorption and insulation performance data includes the sound absorption and insulation performance of multiple frequencies. The sound absorption and insulation performance data quantitatively analyzes the noise contribution of each frequency, making the noise diagnosis more targeted.
[0025] This embodiment uses the sound absorption and insulation performance prediction model obtained by training the historical material sound absorption and insulation performance data to process the material parameters of the material to be tested, which greatly reduces the complexity of noise analysis, and can quantitatively extract the noise contribution of each frequency, quickly predict the sound absorption and insulation performance data of different materials, and provide assistance for the selection of acoustic package materials.
[0026] Optionally, the sound absorption and insulation performance prediction model is a one-dimensional convolutional neural network.
[0027] Understandably, a suitable neural network algorithm can be selected according to actual needs to construct a sound absorption and insulation performance prediction model. In some examples, the sound absorption and insulation performance prediction model can be a one-dimensional convolutional neural network. One-dimensional convolutional neural network (1D Convolutional Neural Network, 1D CNN) is a neural network model for processing sequence data (material parameters). One-dimensional convolutional neural networks are used to process time series data or data with sequential structures. One-dimensional convolutional neural networks use convolutional layers and pooling layers to extract features from input sequences, similar to the process of feature extraction of images in two-dimensional convolutional neural networks. It can automatically learn different levels of abstract features from the input sequence, thereby realizing classification, regression or other tasks of sequence data. In a one-dimensional convolutional neural network, the convolution operation is usually applied to a local window of the sequence data, and the entire sequence is traversed by sliding the window. Each window extracts a new feature value, and then different features are extracted through multiple such convolution kernels. Then, the extracted features are downsampled through the pooling layer to reduce the dimension of the features and retain important information. One-dimensional convolutional neural networks increase the complexity and expressiveness of the model by stacking multiple convolutional layers and pooling layers. Finally, the output features can be input into a fully connected layer or other types of layers for final classification, regression, or other tasks. By taking advantage of convolution operations and parameter sharing, one-dimensional convolutional neural networks can effectively extract key features from sequence data with fewer parameters and computational complexity.
[0028] Optionally, the sound absorption and insulation performance prediction model includes a convolution layer, and the built-in parameters of the convolution layer include:
[0029] Input signal channels (in_channels) is 1;
[0030] The convolution kernel size (kernel_size) is 2*2;
[0031] The stride is 2;
[0032] The learning rate is 0.1.
[0033] The number of paddings for each edge is 0;
[0034] Add bias to False;
[0035] The channels produced by the convolution (out_channels) are 1.
[0036] Understandably, if the material to be tested is a flat material, the corresponding sound absorption and insulation performance prediction model can use the above convolution layer built-in parameters. In one example, the material to be tested includes seven material parameters, which is an array of 1 row and 7 columns for each sample. The output layer of the sound absorption and insulation performance prediction model outputs sound absorption and insulation performance data from 200Hz to 6300Hz, which is represented by an array of 1 row and 32 columns, with the first 16 columns being sound insulation data and the last 16 columns being sound absorption data; the size of the convolution kernel can be set to 2, the step size can be set to 2, and the learning rate can be set to 0.1; 80% of the sound absorption and insulation performance data of the tested materials in the database can be divided into a training set, and a one-dimensional convolutional neural network is used for training for 50 rounds, the trained model is saved, and the remaining 20% of the samples are used as a test set. This realizes the prediction of the sound absorption and insulation performance of acoustic material parameters to flat material.
[0037] This embodiment uses special convolution layer built-in parameters, which is conducive to improving the training efficiency of the sound absorption and insulation performance prediction model.
[0038] Optionally, the material to be tested includes EVA1200+PU foamed acoustic material.
[0039] Understandably, the material to be tested can be selected according to actual needs, such as EVA1200+PU foam acoustic material. EVA1200+PU foam acoustic material is a composite material of ethylene-vinyl acetate copolymer (Ethylene-Vinyl AcetateCopolymer) and polyurethane (Polyurethane). EVA is an elastic plastic whose characteristics include good softness, chemical corrosion resistance and low temperature performance. EVA1200 is one of the models, usually made of ethylene and vinyl acetate in a copolymerized manner. Polyurethane is a multifunctional polymer material that can exist in different forms, such as hard polyurethane, soft polyurethane, foamed polyurethane, etc. It has excellent wear resistance, puncture resistance, chemical corrosion resistance and mechanical strength, while also providing good weather resistance and aging resistance.
[0040] Optionally, the plurality of material parameters include hard layer material, hard layer thickness, hard layer surface density, soft layer material, soft layer surface density, number of composite layers and soft layer thickness.
[0041] Understandably, when the material to be tested is EVA1200+PU foamed acoustic material, the material parameters may be hard layer material, hard layer thickness, hard layer density, soft layer material, soft layer density, composite layer number and soft layer thickness. As shown in Table 1, Table 1 is the material parameters of various acoustic materials in an example.
[0042] Table 1 Material parameters of various acoustic materials
[0043]
[0044] It can be seen from Table 1 that different acoustic materials can be selected according to actual needs and corresponding material parameters can be obtained.
[0045] Optionally, the frequency range of the sound absorption and insulation performance data includes 200 Hz to 6300 Hz.
[0046] It is understandable that the frequency range of the sound absorption and insulation performance data can be set according to actual needs. In some examples, the frequency range of the sound absorption and insulation performance data includes 200Hz to 6300Hz. Within this frequency range, 32 frequency points can be included, the first 16 columns are sound insulation data, and the last 16 columns are sound absorption data.
[0047] As shown in Table 2, Table 2 is the sound absorption and insulation performance data of various acoustic materials in an example.
[0048] Table 2 Sound absorption and insulation performance data of various acoustic materials
[0049]
[0050] It can be seen from Table 2 that with the increase in the thickness of EVA1200+PU foam material, the sound insulation values at 200Hz and 250Hz generally show a downward trend; the sound insulation values at 315Hz and 400Hz first decrease and then increase; the sound insulation values at 500Hz and higher frequencies generally show an upward trend.
[0051] Optionally, the relative error of the sound absorption and insulation performance prediction model is 10%, and the absolute error is 3 dB.
[0052] It is understandable that the relative error and absolute error of the sound absorption and insulation performance prediction model can be set according to actual needs, such as the relative error can be 10%, and the absolute error can be 3dB.
[0053] like Figure 2 As shown, Figure 2 The following is a comparison chart of the sound absorption and insulation performance data predicted by the sound absorption and insulation performance prediction model and the sound absorption and insulation performance data obtained from the actual test in an example. Figure 2 It can be seen that the sound absorption and insulation performance data predicted by the sound absorption and insulation performance prediction model (CNN calculation results, the broken line is above) is close to the sound absorption and insulation performance data obtained by the actual test (original data results, the broken line is below), indicating that the sound absorption and insulation performance data predicted by the sound absorption and insulation performance prediction model is more accurate.
[0054] It should be understood that the order of execution of the steps in the above embodiment does not necessarily 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 embodiment of the present invention.
[0055] In one embodiment, a device for predicting the sound absorption and insulation performance of a material is provided, and the device for predicting the sound absorption and insulation performance of a material corresponds one-to-one to the method for predicting the sound absorption and insulation performance of a material in the above embodiment. Figure 3 As shown, the device for predicting the sound absorption and insulation performance of a material includes a material parameter acquisition module 10 and a performance prediction module 20. The detailed description of each functional module is as follows:
[0056] A material parameter acquisition module 10 is used to acquire multiple material parameters of the material to be tested;
[0057] The performance prediction module 20 is used to input the multiple material parameters into the sound absorption and insulation performance prediction model, and obtain the sound absorption and insulation performance data of the material to be tested output by the sound absorption and insulation performance prediction model.
[0058] Optionally, the sound absorption and insulation performance prediction model is a one-dimensional convolutional neural network.
[0059] Optionally, the material to be tested includes EVA1200+PU foamed acoustic material.
[0060] Optionally, the plurality of material parameters include hard layer material, hard layer thickness, hard layer surface density, soft layer material, soft layer surface density, number of composite layers and soft layer thickness.
[0061] Optionally, the frequency range of the sound absorption and insulation performance data includes 200 Hz to 6300 Hz.
[0062] Optionally, the sound absorption and insulation performance prediction model includes a convolution layer, and the built-in parameters of the convolution layer include:
[0063] The input signal channel is 1;
[0064] The convolution kernel size is 2*2;
[0065] The step size is 2;
[0066] The learning rate is 0.1;
[0067] The number of layers of each edge supplemented with 0 is 0;
[0068] Add bias to False;
[0069] The channel produced by the convolution is 1.
[0070] Optionally, the relative error of the sound absorption and insulation performance prediction model is 10%, and the absolute error is 3 dB.
[0071] The specific definition of the material sound absorption and insulation performance prediction device can be found in the definition of the material sound absorption and insulation performance prediction method mentioned above, which will not be repeated here. Each module in the above-mentioned material sound absorption and insulation performance prediction device can be implemented in whole or in part by software, hardware and a combination thereof. 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.
[0072] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium and an internal memory. The readable storage medium stores an operating system, computer-readable instructions and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The database of the computer device is used to store data involved in the material sound absorption and insulation performance prediction method. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer-readable instructions are executed by the processor, a material sound absorption and insulation performance prediction method is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.
[0073] In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the processor executes the computer-readable instructions to implement the following steps:
[0074] Obtain multiple material parameters of the material to be tested;
[0075] The multiple material parameters are input into a sound absorption and insulation performance prediction model to obtain sound absorption and insulation performance data of the material to be tested output by the sound absorption and insulation performance prediction model.
[0076] In one embodiment, one or more computer-readable storage media storing computer-readable instructions are provided. The readable storage media provided in this embodiment include non-volatile readable storage media and volatile readable storage media. The readable storage media store computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the following steps are implemented:
[0077] Obtain multiple material parameters of the material to be tested;
[0078] The multiple material parameters are input into a sound absorption and insulation performance prediction model to obtain sound absorption and insulation performance data of the material to be tested output by the sound absorption and insulation performance prediction model.
[0079] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through computer-readable instructions, and the computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they may 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 may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of 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), etc.
[0080] 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.
[0081] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those 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 invention, and should all be included in the protection scope of the present invention.
Claims
1. A method for predicting the sound absorption and insulation performance of a material, characterized in that: include: Obtain multiple material parameters of the material to be tested; The multiple material parameters are input into a sound absorption and insulation performance prediction model to obtain sound absorption and insulation performance data of the material to be tested output by the sound absorption and insulation performance prediction model.
2. The method for predicting the sound absorption and insulation performance of a material according to claim 1, characterized in that: The sound absorption and insulation performance prediction model is a one-dimensional convolutional neural network.
3. The method for predicting the sound absorption and insulation performance of a material according to claim 1, characterized in that: The material to be tested includes EVA1200+PU foamed acoustic material.
4. The method for predicting the sound absorption and insulation performance of a material according to claim 3, characterized in that: The plurality of material parameters include hard layer material, hard layer thickness, hard layer surface density, soft layer material, soft layer surface density, composite layer number and soft layer thickness.
5. The method for predicting the sound absorption and insulation performance of a material according to claim 1, characterized in that: The frequency range of the sound absorption and insulation performance data includes 200 Hz to 6300 Hz.
6. The method for predicting the sound absorption and insulation performance of a material according to claim 1, characterized in that: The sound absorption and insulation performance prediction model includes a convolution layer, and the built-in parameters of the convolution layer include: The input signal channel is 1; The convolution kernel size is 2*2; The step size is 2; The learning rate is 0.1; The number of layers of each edge supplemented with 0 is 0; Add bias to False; The channel produced by the convolution is 1.
7. The method for predicting the sound absorption and insulation performance of a material according to claim 1, characterized in that: The relative error of the sound absorption and insulation performance prediction model is 10%, and the absolute error is 3dB.
8. A device for predicting the sound absorption and insulation performance of a material, characterized in that: include: A material parameter acquisition module is used to acquire multiple material parameters of the material to be tested; The performance prediction module is used to input the multiple material parameters into the sound absorption and insulation performance prediction model to obtain the sound absorption and insulation performance data of the material to be tested output by the sound absorption and insulation performance prediction model.
9. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, characterized in that: When the processor executes the computer-readable instructions, the method for predicting the sound absorption and insulation performance of a material as described in any one of claims 1 to 7 is implemented.
10. One or more readable storage media storing computer-readable instructions, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors execute the material sound absorption and insulation performance prediction method according to any one of claims 1 to 7.