Acoustic performance prediction method, device, equipment, medium and product of air bag type silencing device

Abstract

The invention discloses an acoustic performance prediction method, device and equipment of an air bag type silencing device, a medium and a product, and relates to the field of acoustic performance prediction. The method comprises the following steps: acquiring parameter data; inputting the parameter data into an equivalent impedance mathematical model, and determining equivalent impedance; the equivalent impedance mathematical model is obtained by training and fitting by adopting a deep learning method based on test data; the equivalent impedance model is a physical model which is constructed by adopting an impedance thought and is used for representing acoustic characteristics; and taking the equivalent impedance as an internal impedance boundary condition of the sound field, and performing simulation processing by adopting a finite element numerical simulation method to obtain a simulation processing result which is used for representing a relationship between the equivalent impedance and the pressure of the sound field so as to determine the acoustic performance of the air bag type silencing device under the over-pressurization working condition. The invention aims to realize rapid and accurate prediction of the acoustic performance.

Description

Technical Field

[0001] This application relates to the field of acoustic performance prediction, and in particular to a method, apparatus, equipment, medium and product for predicting the acoustic performance of an airbag-type silencer. Background Technology

[0002] Since the noise reduction performance of airbag silencers varies greatly under different working conditions, the inflation pressure inside the airbag needs to be adjusted in real time when the liquid static pressure changes. Therefore, it is crucial to quickly grasp the noise reduction performance of airbag silencers under different working conditions.

[0003] Currently, the acoustic performance prediction of airbag-type silencers under overcharge conditions mainly involves two methods: 1. Conducting whole-machine acoustic tests on the silencer; 2. Performing full-scale acoustic numerical simulations of the silencer. Method 1 suffers from low efficiency and long cycle time, and requires retesting when the airbag material and structural parameters, silencer structural parameters, or pressure difference changes under overcharge conditions, resulting in a large workload. Method 2 suffers from inaccurate numerical calculation results due to the nonlinearity of the airbag material and the geometric nonlinearity during airbag deformation. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, equipment, medium, and product for predicting the acoustic performance of an airbag-type silencer, which can achieve rapid and accurate prediction of acoustic performance.

[0005] To achieve the above objectives, this application provides the following solution:

[0006] In a first aspect, this application provides an acoustic performance prediction method for an airbag-type silencing device, wherein the acoustic performance prediction method for the airbag-type silencing device is applied to the airbag-type silencing device; the airbag-type silencing device includes: a perforated tube and an airbag; the airbag is disposed above the perforated tube; the airbag includes: an inflatable chamber and an airbag skin;

[0007] The method for predicting the acoustic performance of the airbag-type silencer includes:

[0008] Obtain parameter data; the parameter data includes: structural parameters of the perforated tube, material parameters of the perforated tube, structural parameters of the bladder, and material parameters of the bladder.

[0009] The parameter data is input into the equivalent impedance mathematical model to determine the equivalent impedance. The equivalent impedance mathematical model is obtained by training and fitting based on experimental data using deep learning methods. The experimental data includes: experimental parameter data, pressure difference, and equivalent impedance obtained by testing under different experimental parameter data and pressure differences based on the equivalent impedance model. The equivalent impedance model is a physical model constructed using the concept of impedance to characterize acoustic properties.

[0010] Using the equivalent impedance as the boundary condition of the internal impedance of the sound field, the finite element numerical simulation method is used to perform simulation processing to obtain the simulation processing results; the simulation processing results are used to characterize the relationship between the equivalent impedance and the sound field pressure, so as to determine the acoustic performance of the airbag silencer under over-pressure conditions.

[0011] Optionally, the expression for the equivalent impedance determined based on the mathematical model of equivalent impedance is:

[0012] Z1 = F(Rm,Rs,Pm,Ps,Pt);

[0013] Where Z1 is the equivalent impedance; Rm is the material parameter of the bladder; Rs is the structural parameter of the bladder; Pm is the material parameter of the perforated tube; Ps is the structural parameter of the perforated tube; Pt is the pressure difference; F() is the function corresponding to the mathematical model of the equivalent impedance.

[0014] Optionally, the expression for the equivalent impedance obtained from the test is:

[0015]

[0016] Where Z is the equivalent impedance obtained from the test; p i p is the acoustic pressure in the inflatable chamber. o The acoustic pressure in the perforated pipe; u i The sound field velocity of the inflatable chamber; u o The sound field velocity of the perforated pipe.

[0017] Optionally, the expression corresponding to the relationship between equivalent impedance and acoustic field pressure is:

[0018]

[0019] Where Z1 is the equivalent impedance; p i p is the acoustic pressure in the inflatable chamber. o The acoustic pressure in the perforated pipe; q d The source is a dipole; ρ is the density of the acoustic medium. ω represents the pressure gradient; i is the imaginary unit; ω is the angular frequency; and n is the normal vector.

[0020] Optionally, the method for determining the mathematical model of the equivalent impedance specifically includes:

[0021] Obtain a dataset; the dataset includes: experimental data and label data; the label data is the equivalent impedance corresponding to the experimental data;

[0022] The dataset is divided into a training set and a validation set;

[0023] Construct a fully connected neural network;

[0024] The training set is input into the fully connected neural network, and the hyperparameters of the fully connected neural network are trained with the goal of minimizing the loss function, resulting in a trained fully connected neural network. The loss function is determined based on the equivalent impedance in the training set and the output of the fully connected neural network. The loss function includes mean squared error.

[0025] Based on the evaluation metrics, the trained fully connected neural network is adjusted and optimized using a validation set to obtain the optimized fully connected neural network; the evaluation metrics include: loss value and accuracy.

[0026] The optimized fully connected neural network is determined as the equivalent impedance mathematical model.

[0027] Optionally, the fully connected neural network includes an input layer, a hidden layer, and an output layer connected in sequence.

[0028] Secondly, this application provides an acoustic performance prediction device for an airbag-type silencer, comprising:

[0029] The parameter data acquisition module is used to acquire parameter data; the parameter data includes: structural parameters of the perforated tube, material parameters of the perforated tube, structural parameters of the bladder, and material parameters of the bladder.

[0030] An equivalent impedance determination module is used to input the parameter data into an equivalent impedance mathematical model to determine the equivalent impedance. The equivalent impedance mathematical model is obtained by training and fitting based on experimental data using deep learning methods. The experimental data includes: experimental parameter data, pressure difference, and equivalent impedance obtained by testing under different experimental parameter data and pressure differences based on the equivalent impedance model. The equivalent impedance model is a physical model constructed using the concept of impedance to characterize acoustic properties.

[0031] The simulation processing module is used to perform simulation processing using the equivalent impedance as the internal impedance boundary condition of the sound field and the finite element numerical simulation method to obtain the simulation processing results. The simulation processing results are used to characterize the relationship between the equivalent impedance and the sound field pressure to determine the acoustic performance of the airbag silencer under over-pressure conditions.

[0032] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the acoustic performance prediction method of the airbag-type silencer described above.

[0033] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the acoustic performance prediction method for the airbag-type silencer described above.

[0034] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the acoustic performance prediction method for the airbag-type silencer described above.

[0035] According to the specific embodiments provided in this application, this application has the following technical effects:

[0036] This application provides a method, apparatus, device, medium, and product for predicting the acoustic performance of an airbag-type silencer. The method includes: acquiring parameter data; inputting the parameter data into an equivalent impedance mathematical model to determine the equivalent impedance; the equivalent impedance mathematical model is obtained by training and fitting based on experimental data using deep learning; the equivalent impedance model is a physical model constructed using the concept of impedance to characterize acoustic properties; using the equivalent impedance as the internal impedance boundary condition of the sound field, performing simulation processing using finite element numerical simulation to obtain simulation results, which characterize the relationship between the equivalent impedance and the sound field pressure, thereby determining the acoustic performance of the airbag-type silencer under over-inflation conditions. This application combines the equivalent impedance mathematical model with finite element simulation, using the equivalent impedance mathematical model as the impedance condition in the finite element simulation of the airbag-type silencer, thus avoiding the establishment of a perforated region model and improving the prediction speed; by using the concept of equivalent impedance and reflecting the influence of airbag material and airbag skin deformation on acoustic performance through experimental means, the accuracy of the prediction is improved. Therefore, this application achieves rapid and accurate prediction of acoustic performance. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 A flowchart for predicting the acoustic performance of an airbag-type silencer;

[0039] Figure 2 This is a schematic diagram of an airbag-type silencer.

[0040] Figure 3 This is a schematic diagram of an airbag-type silencer in an under-charged state.

[0041] Figure 4This is a schematic diagram of an airbag-type silencer under isobaric conditions.

[0042] Figure 5 This is a schematic diagram of an airbag-type silencer under over-inflation conditions.

[0043] Figure 6 This is a schematic diagram illustrating the operational steps of acoustic performance prediction methods in practical applications.

[0044] Figure 7 A schematic diagram of the acoustic equivalent impedance of the "perforated tube + bladder" region;

[0045] Figure 8 A schematic diagram of the experimental model established for testing equivalent impedance;

[0046] Figure 9 This is a schematic diagram illustrating the combination of the equivalent impedance mathematical model and the finite element numerical simulation method. Detailed Implementation

[0047] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0048] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0049] In one exemplary embodiment, such as Figure 1 As shown, a method for predicting the acoustic performance of an airbag-type silencer is provided. This method is applied to an airbag-type silencer; the airbag-type silencer includes a perforated tube and an airbag; the airbag is positioned above the perforated tube; the airbag includes an inflatable chamber and an airbag skin.

[0050] The airbag-type silencer is a widely used fluid pressure pulsation and noise suppression device in fluid-filled pipelines. When fluid passes through the device, the inflatable airbag expands or contracts according to changes in fluid pressure. This deformation helps reduce fluid pressure fluctuations, thereby reducing noise. The structure of the airbag-type silencer is as follows: Figure 2 As shown, it includes a perforated tube and an air bladder, which consists of an inflatable chamber and a bladder skin.

[0051] Based on the relationship between the pre-inflation pressure inside the airbag and the static pressure of the liquid in the filling pipeline, airbag-type silencers can be divided into three working states: under-inflation, equal-inflation, and over-inflation. When the static pressure is greater than the inflation pressure, it is in the under-inflation state; when the static pressure is equal to the inflation pressure, it is in the equal-inflation state; and when the static pressure is less than the inflation pressure, it is in the over-inflation state. In the under-inflation and equal-inflation states, the airbag skin is relaxed, resulting in low overall airbag stiffness and good expansion or contraction in response to fluid pressure changes, thus effectively absorbing fluid pressure pulsations. In the over-inflation state, the airbag skin is tense, increasing the overall stiffness of the airbag and reducing its effectiveness in absorbing fluid pressure pulsations.

[0052] In an undercharged state, such as Figure 3 As shown, the gas pressure inside the airbag is less than the hydrostatic pressure of the liquid. The airbag will be compressed under the hydrostatic pressure of the liquid in the inflation tube. The gas pressure inside the airbag will gradually increase until it is consistent with the hydrostatic pressure. At this time, the pressure on both sides of the airbag skin remains balanced, and the airbag skin will be in a relaxed state, without generating additional stiffness that would increase the stiffness of the airbag.

[0053] Under isobaric conditions, such as Figure 4 As shown, the gas pressure inside the airbag is equal to the hydrostatic pressure of the liquid. At this time, the pressure on both sides of the airbag skin remains balanced, so the airbag skin is in a relaxed state and will not generate additional stiffness that would increase the stiffness of the airbag.

[0054] Under overcharge conditions, such as Figure 5 As shown, when the gas pressure inside the airbag is greater than the hydrostatic pressure of the liquid, the airbag will gradually inflate. Due to the obstruction of the perforated tube inside the airbag-type silencer, the expansion of the airbag is limited, and the airbag skin will continue to expand in the perforated area until the tension provided by the airbag skin compensates for the expansion effect caused by the pressure difference on both sides. At this time, the airbag skin is in a taut state, generating additional stiffness and increasing the stiffness of the airbag, thus making the silencing effect of the airbag silencer worse. Furthermore, as the pressure difference increases, the silencing effect will gradually decrease.

[0055] In a publicly disclosed airbag-type seawater pipeline silencer, similar airbag-type silencers, to achieve good noise reduction and low flow resistance loss, mostly employ an airbag structure and a perforated tube structure. The airbag structure consists of a rubber bladder and internally filled gas, while the perforated tube is a porous circular tube structure. When the system pressure is greater than or equal to the airbag inflation pressure, the airbag is compressed, and the airbag skin is in a relaxed state, forming an acoustic "soft boundary" that provides a better noise reduction effect. Studies show that the airbag device achieves the best noise reduction effect when the inflation pressure is 60%-80% of the system pressure. When the system pressure is less than the airbag inflation pressure, the airbag is in an over-inflated state. At this time, the airbag will expand under inflation pressure, but due to the constraint of the perforated tube, the airbag skin will expand and deform in the perforated area of ​​the tube, and the airbag skin will be in a taut state. The airbag structure becomes a relatively hard acoustic boundary, which reduces the noise reduction effect it can provide. However, the current prediction of the noise reduction performance of the airbag structure under over-inflation conditions is still based on engineering experience and lacks accurate and rapid qualitative prediction models. This is because the nonlinearity of the airbag skin material and the geometric nonlinearity during the deformation process of the airbag skin make numerical prediction modeling difficult, which is not conducive to accurate prediction of noise reduction performance. At the same time, due to the large number of perforations and the small aperture, the calculation speed would be very slow if a numerical model is used for modeling, which is not conducive to rapid prediction of noise reduction performance.

[0056] The method mentioned in this application is executed by a computer device. Specifically, it can be executed by a computer device such as a terminal or a server alone, or it can be executed by both a terminal and a server. In this embodiment, the method is described using a server as an example, and includes the following steps.

[0057] like Figure 1 As shown, the method for predicting the acoustic performance of an airbag-type silencer includes:

[0058] Step 100: Obtain parameter data. Parameter data includes: structural parameters of the perforated tube, material parameters of the perforated tube, structural parameters of the bladder, and material parameters of the bladder.

[0059] Step 200: Input the parameter data into the equivalent impedance mathematical model to determine the equivalent impedance. The equivalent impedance mathematical model is obtained by training and fitting based on experimental data using deep learning methods; the experimental data includes: experimental parameter data, pressure difference, and equivalent impedance obtained by testing under different experimental parameter data and pressure differences based on the equivalent impedance model; the equivalent impedance model is a physical model constructed using the concept of impedance to characterize acoustic properties.

[0060] Determining the equivalent impedance is a crucial concept in circuit analysis, involving how to simplify complex circuits into a single impedance value for analysis and calculation. In this application, it refers to simplifying the acoustic characteristics of the "perforated tube + shell" region into a single impedance value.

[0061] Step 300: Using the equivalent impedance as the boundary condition for the internal impedance of the sound field, a finite element numerical simulation method is used to perform simulation processing, and the simulation results are obtained. The simulation results are used to characterize the relationship between the equivalent impedance and the sound field pressure, so as to determine the acoustic performance of the airbag silencer under over-pressure conditions.

[0062] In one embodiment, the expression for the equivalent impedance determined based on the mathematical model of equivalent impedance is:

[0063] Z1 = F(Rm,Rs,Pm,Ps,Pt).

[0064] Where Z1 is the equivalent impedance; Rm is the material parameter of the bladder; Rs is the structural parameter of the bladder; Pm is the material parameter of the perforated tube; Ps is the structural parameter of the perforated tube; Pt is the pressure difference; F() is the function corresponding to the mathematical model of the equivalent impedance.

[0065] The expression for the equivalent impedance obtained from the test is:

[0066]

[0067] Where z is the equivalent impedance obtained from the test; p i p is the acoustic pressure in the inflatable chamber. o The acoustic pressure in the perforated pipe; u i The sound field velocity of the inflatable chamber; u o The sound field velocity of the perforated pipe.

[0068] The expression corresponding to the relationship between equivalent impedance and acoustic pressure is:

[0069]

[0070] Where Z1 is the equivalent impedance; p i p is the acoustic pressure in the inflatable chamber. o The acoustic pressure in the perforated pipe; q d The source is a dipole; ρ is the density of the acoustic medium. ω represents the pressure gradient; i is the imaginary unit; ω is the angular frequency; and n is the normal vector.

[0071] As an optional implementation method, the method for determining the mathematical model of equivalent impedance specifically includes:

[0072] Obtain the dataset. The dataset includes: experimental data and label data; the label data is the equivalent impedance corresponding to the experimental data.

[0073] The dataset is divided into a training set and a validation set; a fully connected neural network is constructed; the training set is input into the fully connected neural network, and the hyperparameters of the fully connected neural network are trained with the goal of minimizing the loss function, resulting in the trained fully connected neural network; the loss function is determined based on the equivalent impedance in the training set and the output of the fully connected neural network; the loss function includes: mean squared error.

[0074] Based on the evaluation metrics, the trained fully connected neural network was adjusted and optimized using a validation set to obtain the optimized fully connected neural network. The evaluation metrics included loss value and accuracy. The optimized fully connected neural network was determined as the equivalent impedance mathematical model.

[0075] Specifically, a fully connected neural network consists of an input layer, a hidden layer, and an output layer connected in sequence.

[0076] The technical concept of the method mentioned in this application is as follows:

[0077] First, the research model was mathematically simplified, and acoustic impedance tests were conducted on the "perforated tube + bladder" region under different parameters. Second, deep learning was used to analyze the experimental data, resulting in mathematical models of the equivalent impedance of the "perforated tube + bladder" under different parameters. Finally, the mathematical models of the equivalent impedance were combined with numerical simulations to achieve rapid and accurate prediction of acoustic performance. This method significantly improves the speed and accuracy of acoustic performance prediction under over-inflation conditions for airbag-type silencers, and has guiding significance for the design and application of airbag-type silencers. Figure 6 As shown, the specific operation steps are as follows:

[0078] S1. Simplify the acoustic characteristic calculation model of the airbag silencer under over-pressurization conditions and establish an equivalent impedance acoustic prediction model.

[0079] The structure of the overcharged airbag silencer is as follows: Figure 5 As shown, traditional methods require the establishment of a complex structural model including the shell and perforated tube when calculating acoustic performance. Due to the material nonlinearity of the shell and the geometric nonlinearity during the deformation process of the shell, the traditional method has low calculation accuracy and slow calculation speed.

[0080] This application utilizes the concept of impedance to express the contribution of the shell and perforated tube to the sound field of the device using acoustic equivalent impedance. Acoustic impedance refers to the acoustic characteristics exhibited when sound waves pass through perforated materials or structures. It is commonly used to describe the interaction between sound waves and solid interfaces or porous media, and is defined as the ratio of sound pressure to vibration velocity. Figure 7 As shown, the acoustic equivalent impedance of the "perforated tube + shell" region consists of two parts, one of which is the impedance Z of the shell. R Part of it is the impedance Z of the perforated tube. P Defined as:

[0081]

[0082] Where u is the sound field vibration velocity.

[0083] The impedance of the air bladder skin is related not only to its own material parameters Rm and structural parameters Rs, but also to the pressure difference Pt across the air bladder skin. For example, the greater the elastic modulus of the air bladder skin, the thicker it is, and the greater the pressure difference across it, the greater the impedance Z of the air bladder skin. R The larger it will be.

[0084] The impedance of a perforated tube is related to its structural parameters Ps and material parameters Pm. For example, the elastic modulus of the perforated tube material, the thickness of the perforated tube, and the size of the perforation aperture all affect the impedance Z of the perforated tube. P .

[0085] S2. Using an acoustic impedance experimental platform, test the equivalent impedance characteristics under different perforation parameters, different airbag skin structure parameters and material parameters, and different pressure differences.

[0086] S2. Using an acoustic impedance experimental platform, test the acoustic equivalent impedance characteristics of the "perforated tube + bladder" region under different parameters Rm, Rs, Pt, Ps, and Pt.

[0087] In this example, the method used to test the equivalent impedance is similar to the method used to test the through-hole impedance. The established experimental model is as follows: Figure 8 As shown, the sound source (sound signal) is set at the inlet of the pipe, and the outlet of the pipe is the non-reflective end. Two sound pressure measurement points are arranged on each side of the test piece, and their sound pressure values ​​are p1, p2, p3, and p4, respectively.

[0088] The specific principle is as follows:

[0089] For the acoustic field of the pipe on the left side of the test piece: applying the transfer matrix method, we have:

[0090] The sound field relationship between points 1 and 2:

[0091]

[0092] The sound field relationship between point 2 and point i:

[0093]

[0094] From formula (1), we get:

[0095]

[0096] Substituting formula (3) into formula (2) yields the sound pressure and particle velocity on the left side of the test specimen, represented by p1 and p2:

[0097]

[0098] Similarly, applying the same method to the sound field of the pipe on the right side of the test specimen, we can obtain the sound pressure and particle velocity on the right side of the test specimen, represented by p3 and p4:

[0099]

[0100] The acoustic equivalent impedance of the test specimen is expressed as:

[0101]

[0102] Substituting formulas (5) and (6) into formula (7) yields the acoustic equivalent impedance of the test specimen.

[0103] Where p1 is the sound pressure at measurement point 1; u1 is the sound field velocity at measurement point 1; p2 is the sound pressure at measurement point 2; u2 is the sound field velocity at measurement point 2; p i The acoustic pressure of the inflatable chamber; u i p represents the sound field vibration velocity of the inflatable chamber. o The acoustic pressure in the perforated pipe; u o p0 is the sound field velocity of the perforated pipe; p3 is the sound pressure corresponding to measurement point 3; p4 is the sound pressure corresponding to measurement point 4; k0 is the sound field wavenumber; l1 is the distance between measurement point 1 and measurement point 2; Y0 is the characteristic impedance of the sound field; j is the imaginary unit; l2 is the distance between measurement point 2 and the test piece; l3 is the distance between measurement point 3 and the test piece; l4 is the distance between measurement point 3 and measurement point 4.

[0104] S3. Based on deep learning methods, experimental data are used to fit and obtain an equivalent impedance mathematical model that considers different parameters.

[0105] The general process includes the following steps: 1. Collect experimental data for S2. This data will serve as the input and output for training the deep learning model. The experimental data needs to be cleaned and preprocessed to ensure its quality. 2. Design a deep learning model that can capture complex nonlinear relationships in the data. The model can be a fully connected neural network, such as a nonlinear regression model created using TensorFlow. The model architecture may include an input layer, multiple hidden layers (such as hidden layers with the ReLU activation function), and an output layer. 3. Before training the model, it needs to be compiled, and the optimizer (such as Adam) and loss function (such as mean squared error, MSE) need to be set. 4. Train the deep learning model using the prepared data. During training, the model learns the mapping relationship between the input and output data. Model performance can be optimized by adjusting the model architecture and hyperparameters. 5. Evaluate the model's performance, usually using a validation set or test set. Evaluation metrics may include loss value, accuracy, etc.

[0106] By fitting experimental data using deep learning, a multi-parameter equivalent impedance model function can be obtained, which includes the shell material parameter Rm, the shell structural parameter Rs, the perforated tube material parameter Pm, the perforated tube structural parameter Ps, and the pressure difference Pt. The equivalent impedance is then expressed as:

[0107] Z1 = F(Rm,Rs,Pm,Ps,Pt).

[0108] S4. Use experimental data to verify whether the obtained equivalent impedance mathematical model meets the accuracy requirements. If it does, proceed to the next step; otherwise, return to S3 and correct the equivalent impedance mathematical model.

[0109] S5. By combining the mathematical model of equivalent impedance with the finite element numerical simulation method, the equivalent impedance under the solved parameters is used as the impedance boundary condition in the finite element simulation, thereby replacing the modeling of the "perforated tube + cladding" region structure. For example... Figure 9 As shown.

[0110] In the simulation model, the equivalent impedance Z1 and the acoustic pressure p of the inflatable chamber are... i The acoustic pressure p0 in the perforated pipe has the following relationship:

[0111]

[0112] Where, q d ρ is the dipole source, and ρ is the density of the acoustic medium.

[0113] S6. Improve the structural modeling of the airbag-type silencer and perform acoustic performance calculations.

[0114] Furthermore, in practical applications, the system for implementing the method includes a module for establishing an equivalent impedance mathematical model, a module for acquiring experimental data of a multi-parameter equivalent impedance mathematical model, a module for fitting a multi-parameter equivalent impedance mathematical model based on deep learning, a module for judging the accuracy of a multi-parameter equivalent impedance mathematical model, a module for coupling a multi-parameter equivalent impedance mathematical model with finite element simulation, and a module for calculating the acoustic performance of an airbag-type silencer under over-inflation conditions.

[0115] The module for establishing the equivalent impedance mathematical model simplifies the calculation process of the acoustic characteristics of the airbag silencer under over-inflation conditions. It simplifies the previous problem of solving the acoustic characteristics of the airbag skin and the perforated area into the problem of solving the equivalent impedance of the "perforated tube + airbag skin" structure, thereby avoiding the difficulties in numerical calculation caused by the material nonlinearity of the airbag skin and the geometric nonlinearity during the deformation process of the airbag skin.

[0116] The experimental data acquisition module of the multi-parameter equivalent impedance mathematical model is used to obtain the equivalent impedance data of the "perforation + bladder skin" structure under different structural and material parameters of the perforated tube and the structural and material parameters of the air bladder skin.

[0117] The deep learning-based multi-parameter equivalent impedance mathematical model fitting module is used to fit experimental data into the equivalent impedance mathematical model, thereby obtaining a multi-parameter equivalent impedance mathematical model that can consider different structural and material parameters of the perforated tube and the airbag skin.

[0118] The accuracy judgment module for the multi-parameter equivalent impedance mathematical model is used to determine whether the obtained model meets the accuracy requirements. If it does not meet the requirements, the accuracy of the model needs to be improved.

[0119] The multi-parameter equivalent impedance mathematical model coupled with finite element simulation module is used to combine the multi-parameter equivalent impedance mathematical model with finite element simulation.

[0120] The benefits of this application are:

[0121] 1. Simplify the acoustic characteristic calculation model of the airbag silencer under over-pressure conditions and establish an equivalent impedance acoustic prediction model.

[0122] 2. Using an acoustic impedance experimental platform, the equivalent impedance characteristics under different perforated tube parameters, different bladder structure parameters and material parameters, and different pressure differences were tested.

[0123] 3. Based on deep learning methods, experimental data are used to fit and obtain an equivalent impedance mathematical model that considers different parameters.

[0124] 4. Use experimental data to verify whether the obtained equivalent impedance mathematical model meets the accuracy requirements. If it does, proceed to the next step; otherwise, return to S3 to revise the equivalent impedance mathematical model.

[0125] 5. By combining the mathematical model of equivalent impedance with the finite element numerical simulation method, the equivalent impedance under the solved parameters is used as the impedance boundary condition in the finite element simulation, thereby replacing the modeling of the "perforated pipe + airbag" regional structure.

[0126] This application proposes a simplified research model, establishing an equivalent impedance mathematical model of the airbag skin and perforated area under overinflation, and conducting a finite number of acoustic impedance tests. This experimental approach addresses the difficulties in modeling caused by the nonlinearity of the airbag skin material and the geometric nonlinearity during skin deformation. Furthermore, by combining machine learning with experimental data analysis, a universally applicable overinflation equivalent impedance mathematical model is obtained. This process utilizes the concept of equivalent impedance to reflect the influence of airbag material and airbag skin deformation on acoustic performance through experimental means, thus improving the accuracy of predictions.

[0127] This application combines the equivalent impedance mathematical model with the finite element simulation model, using the equivalent impedance mathematical model as the impedance condition in the finite element model of the airbag-type silencer, thereby avoiding the establishment of a perforated region model and improving the prediction speed.

[0128] The method described in this application greatly improves the accuracy and speed of predicting the acoustic performance of airbag silencers under overcharge conditions, and has guiding significance for the study of the performance of airbag silencers under overcharge conditions.

[0129] Based on the same inventive concept, this application also provides an acoustic performance prediction device for an airbag-type silencer to implement the acoustic performance prediction method of the airbag-type silencer described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the acoustic performance prediction device for an airbag-type silencer provided below can be found in the limitations of the acoustic performance prediction method for the airbag-type silencer described above, and will not be repeated here.

[0130] In one exemplary embodiment, an acoustic performance prediction device for an airbag-type silencing device is provided, comprising:

[0131] The parameter data acquisition module is used to acquire parameter data. The parameter data includes: structural parameters of the perforated tube, material parameters of the perforated tube, structural parameters of the bladder, and material parameters of the bladder.

[0132] The equivalent impedance determination module is used to input parameter data into the equivalent impedance mathematical model to determine the equivalent impedance. The equivalent impedance mathematical model is trained and fitted using deep learning methods based on experimental data. The experimental data includes: experimental parameter data, pressure difference, and equivalent impedance obtained by testing under different experimental parameter data and pressure differences based on the equivalent impedance model. The equivalent impedance model is a physical model constructed using the concept of impedance to characterize acoustic properties.

[0133] The simulation processing module is used to perform simulation processing using the equivalent impedance as the internal impedance boundary condition of the sound field, and employs the finite element numerical simulation method to obtain the simulation results. The simulation results are used to characterize the relationship between the equivalent impedance and the sound field pressure, so as to determine the acoustic performance of the airbag-type silencer under over-pressure conditions.

[0134] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for predicting the acoustic performance of an airbag-type silencing device.

[0135] Those skilled in the art will understand that the structures shown above are merely partial structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than described above, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0136] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0137] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0138] In this application, all actions involving the acquisition of signals, information, or data are carried out in compliance with the relevant data protection laws and regulations of the country where the application is located, and with the authorization granted by the owner of the relevant device. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with relevant regulations.

[0139] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0140] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0141] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0142] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for predicting the acoustic performance of an airbag-type silencer, characterized in that, The acoustic performance prediction method of the airbag-type silencer is applied to the airbag-type silencer. The airbag-type silencer includes: a perforated tube and an airbag; the airbag is disposed above the perforated tube; the airbag includes: an inflation chamber and an airbag skin; The method for predicting the acoustic performance of the airbag-type silencer includes: Obtain parameter data; the parameter data includes: structural parameters of the perforated tube, material parameters of the perforated tube, structural parameters of the bladder, and material parameters of the bladder. The parameter data is input into the equivalent impedance mathematical model to determine the equivalent impedance. The equivalent impedance mathematical model is obtained by training and fitting based on experimental data using deep learning methods. The experimental data includes: experimental parameter data, pressure difference, and equivalent impedance obtained by testing under different experimental parameter data and pressure differences based on the equivalent impedance model. The equivalent impedance model is a physical model constructed using the concept of impedance to characterize acoustic properties. Using the equivalent impedance as the boundary condition of the internal impedance of the sound field, the finite element numerical simulation method is used to perform simulation processing to obtain the simulation processing results; the simulation processing results are used to characterize the relationship between the equivalent impedance and the sound field pressure, so as to determine the acoustic performance of the airbag silencer under over-pressure conditions.

2. The method for predicting the acoustic performance of the airbag-type silencer according to claim 1, characterized in that, The expression for the equivalent impedance, determined based on the mathematical model of equivalent impedance, is as follows: Z1 = F(Rm,Rs,Pm,Ps,Pt); Where Z1 is the equivalent impedance; Rm is the material parameter of the bladder; Rs is the structural parameter of the bladder; Pm is the material parameter of the perforated tube; Ps is the structural parameter of the perforated tube; Pt is the pressure difference; and F() is the function corresponding to the mathematical model of the equivalent impedance.

3. The method for predicting the acoustic performance of the airbag-type silencer according to claim 1, characterized in that, The expression for the equivalent impedance obtained from the test is: Where Z is the equivalent impedance obtained from the test; p i p is the acoustic pressure in the inflatable chamber. o The acoustic pressure in the perforated pipe; u i The sound field vibration velocity of the inflatable chamber; u o The sound field velocity of the perforated pipe.

4. The method for predicting the acoustic performance of the airbag-type silencer according to claim 1, characterized in that, The expression corresponding to the relationship between equivalent impedance and acoustic pressure is: Where Z1 is the equivalent impedance; p i p is the acoustic pressure in the inflatable chamber. o The acoustic pressure in the perforated pipe; q d The source is a dipole; ρ is the density of the acoustic medium. ω represents the pressure gradient; i is the imaginary unit; ω is the angular frequency; and n is the normal vector.

5. The method for predicting the acoustic performance of the airbag-type silencer according to claim 1, characterized in that, The method for determining the mathematical model of the equivalent impedance specifically includes: Obtain a dataset; the dataset includes: experimental data and label data; the label data is the equivalent impedance corresponding to the experimental data; The dataset is divided into a training set and a validation set; Construct a fully connected neural network; The training set is input into the fully connected neural network, and the hyperparameters of the fully connected neural network are trained with the goal of minimizing the loss function, resulting in a trained fully connected neural network. The loss function is determined based on the equivalent impedance in the training set and the output of the fully connected neural network. The loss function includes mean squared error. Based on the evaluation metrics, the trained fully connected neural network is adjusted and optimized using a validation set to obtain the optimized fully connected neural network; the evaluation metrics include: loss value and accuracy. The optimized fully connected neural network is determined as the equivalent impedance mathematical model.

6. The method for predicting the acoustic performance of the airbag-type silencer according to claim 5, characterized in that, The fully connected neural network includes an input layer, a hidden layer, and an output layer connected in sequence.

7. An acoustic performance prediction device for an airbag-type silencing device, characterized in that, The acoustic performance prediction device for the airbag-type silencer includes: The parameter data acquisition module is used to acquire parameter data; the parameter data includes: structural parameters of the perforated tube, material parameters of the perforated tube, structural parameters of the bladder, and material parameters of the bladder. An equivalent impedance determination module is used to input the parameter data into an equivalent impedance mathematical model to determine the equivalent impedance. The equivalent impedance mathematical model is obtained by training and fitting based on experimental data using deep learning methods. The experimental data includes: experimental parameter data, pressure difference, and equivalent impedance obtained by testing under different experimental parameter data and pressure differences based on the equivalent impedance model. The equivalent impedance model is a physical model constructed using the concept of impedance to characterize acoustic properties. The simulation processing module is used to perform simulation processing using the equivalent impedance as the internal impedance boundary condition of the sound field and the finite element numerical simulation method to obtain the simulation processing results. The simulation processing results are used to characterize the relationship between the equivalent impedance and the sound field pressure to determine the acoustic performance of the airbag silencer under over-pressure conditions.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the method for predicting the acoustic performance of the airbag-type silencing device according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the method for predicting the acoustic performance of the airbag-type silencer according to any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the method for predicting the acoustic performance of the airbag-type silencer according to any one of claims 1-6.

Images