Method and device for predicting sound absorption performance of helmholtz resonator material, medium and terminal

Abstract

The present application relates to a kind of Helmholtz resonance material sound absorption performance prediction method, comprising: based on the sound absorption performance database between the structure parameters of different dimensions of Helmholtz resonance material and sound absorption coefficient, obtain training set and verification set;Using the data in training set trains the Helmholtz resonance material sound absorption performance prediction network based on machine learning, test verification is carried out using verification set, obtain Helmholtz resonance material sound absorption performance prediction model;The structure parameters corresponding to different dimensions of the Helmholtz resonance material to be measured are input into Helmholtz resonance material sound absorption performance prediction model, obtain the predicted value of the sound absorption coefficient of different dimensions of Helmholtz resonance material.Compared with prior art, the present application solves the problem that it is difficult to predict sound absorption performance by simulation technology due to too many parameters of acoustic Helmholtz resonance material, solves the problem of long simulation prediction time and low efficiency, and can efficiently and accurately predict the sound absorption coefficient of different dimensions of Helmholtz resonance material.

Description

Technical Field

[0001] This invention relates to the field of sound absorption and noise reduction technology, and in particular to a method, device, medium and terminal for predicting the sound absorption performance of Helmholtz resonant materials. Background Technology

[0002] Low-frequency noise pollution poses a serious threat to people's lives, work, and studies. Acoustic metamaterials can effectively address this problem, making the design of acoustic metamaterials with superior sound absorption performance an increasingly important issue. Simulation technology can theoretically determine the structural parameters of acoustic metamaterials with optimal performance, effectively providing a theoretical basis for designing high-performance sound-absorbing materials and reducing unnecessary experimental procedures.

[0003] Due to the diversity of simulation techniques, choosing the appropriate simulation technique is extremely important for predicting the sound absorption coefficient of materials. In recent years, various simulation techniques have been widely used to predict the sound absorption coefficient of acoustic materials, but there is no systematic solution for a common method to predict the sound absorption coefficient of acoustic metamaterials.

[0004] In the prior art, Chinese patent CN113761771A discloses a method, apparatus, electronic device, and storage medium for predicting the sound absorption performance of porous materials. The method includes: acquiring an image representing the topology of the porous material and preprocessing it to obtain training samples and test samples; constructing a network for predicting the sound absorption performance of porous materials; this network includes multiple sequentially connected ResNet modules; each ResNet module includes two convolutional layers, two batch normalization layers, and two ReLU layers, with each ResNet block utilizing skip connections to improve network performance; training the network using training samples and testing it using test samples; and using the obtained model to predict the sound absorption coefficient of the porous material in the test image to obtain the predicted value. However, this method is only applicable to porous materials, and its training and test samples are not suitable for Helmholtz resonant materials. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art by providing a method, device, medium, and terminal for predicting the sound absorption performance of Helmholtz resonant materials, thereby solving the technical problems of long prediction time and difficulty in prediction due to the large number of parameters in the prior art when using simulation technology to predict the sound absorption performance of Helmholtz resonant materials.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] A method for predicting the sound absorption performance of Helmholtz resonant materials includes the following steps:

[0008] S1. Based on the sound absorption performance database of different dimensions of Helmholtz resonant materials and their sound absorption coefficients, obtain training and validation sets;

[0009] S2. Using the data in the training set, train a machine learning-based network for predicting the sound absorption performance of Helmholtz resonant materials, and use the validation set for testing and verification to obtain a prediction model for the sound absorption performance of Helmholtz resonant materials.

[0010] S3. Input the structural parameters of the Helmholtz resonant material to be tested in different dimensions into the prediction model of the sound absorption performance of the Helmholtz resonant material, and output the predicted values ​​of the sound absorption coefficient of the Helmholtz resonant material in different dimensions.

[0011] Furthermore, the sound absorption performance database of the Helmholtz resonant material in different dimensions and its sound absorption coefficient in step S1 is specifically established through the following steps:

[0012] S11. Use simulation software to establish the functional unit sequence of Helmholtz resonance materials in different dimensions;

[0013] S12. By adjusting the structural parameters of the functional primitive sequence, the sound absorption coefficient is obtained based on simulation software;

[0014] S13. Based on the correspondence between the structural parameters and sound absorption coefficients of functional primitives in different dimensions, a sound absorption performance database is established.

[0015] Furthermore, the expression for the sound absorption coefficient is as follows:

[0016] α = 1 - T

[0017] Where T represents the reflection coefficient of the Helmholtz resonant material, expressed as:

[0018]

[0019] Among them, W in The incident sound power is the power of the sound applied to the Helmholtz resonant material, and is a known parameter; W ref This represents the reflected sound power, calculated using simulation software.

[0020] Furthermore, the functional unit structure includes a cavity, with an opening at the center of one end of the cavity, and the opening is connected to a hollow sound-absorbing pipe.

[0021] Furthermore, the structural parameters of the functional primitive sequence include any one or more combinations of cavity length, cavity width, cavity height, aperture depth, and aperture diameter.

[0022] Furthermore, step S2 specifically includes the following steps:

[0023] S21. Construct a machine learning-based network for predicting the sound absorption performance of Helmholtz resonant materials;

[0024] S22. Using the structural parameters of different dimensions of the Helmholtz resonant material as input and the sound absorption coefficient as output, train a machine learning-based prediction network for the sound absorption performance of the Helmholtz resonant material using the data in the training set.

[0025] S23. Use the data in the validation set to test and verify the prediction accuracy of the trained prediction network. After the test is passed, the prediction model of the sound absorption performance of the Helmholtz resonant material is obtained.

[0026] A device for predicting the sound absorption performance of Helmholtz resonant materials includes a data acquisition module, a model training module, and a result prediction module;

[0027] The data acquisition module is used to establish a database of sound absorption performance between structural parameters and sound absorption coefficients of Helmholtz resonance materials in different dimensions, and to obtain training and validation sets from it.

[0028] The model training module is used to train a machine learning-based Helmholtz resonant material sound absorption performance prediction network using the data in the training set, and to test and verify it using the validation set, so as to obtain the Helmholtz resonant material sound absorption performance prediction model.

[0029] The result prediction module is used to input the structural parameters of the Helmholtz resonant material under test in different dimensions into the Helmholtz resonant material sound absorption performance prediction model to obtain the predicted values ​​of the sound absorption coefficient of the Helmholtz resonant material in different dimensions.

[0030] Furthermore, the specific working process of the data acquisition module includes: establishing functional unit sequences of Helmholtz resonant materials in different dimensions using simulation software; obtaining the corresponding sound absorption coefficients based on simulation software by adjusting the structural parameters of the functional unit sequences; and establishing a sound absorption performance database based on the correspondence between the structural parameters of the functional unit sequences in different dimensions and the corresponding sound absorption coefficients.

[0031] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method for predicting the sound absorption performance of Helmholtz resonant materials.

[0032] An electronic terminal includes: a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program stored in the memory to enable the device to perform the above-described method for predicting the sound absorption performance of Helmholtz resonant materials.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] 1. This invention utilizes a database of sound absorption performance data relating structural parameters and sound absorption coefficients of Helmholtz resonant materials across different dimensions to obtain training and validation sets. It then combines this with a machine learning-based Helmholtz resonant material sound absorption performance prediction network to derive a prediction model for the sound absorption performance of Helmholtz resonant materials. This model is used to obtain predicted values ​​of the sound absorption coefficients of Helmholtz resonant materials across different dimensions. This solves the problem of difficulty in predicting the sound absorption performance of acoustic Helmholtz resonant materials through simulation techniques due to the large number of parameters, enabling rapid and accurate prediction of sound absorption coefficients across different dimensions, thereby accurately evaluating the sound absorption performance of Helmholtz resonant materials.

[0035] 2. In this invention, functional primitive sequences of different dimensions of Helmholtz resonant materials are established using simulation software; then, by adjusting the structural parameters of the functional primitive sequences, the corresponding sound absorption coefficients are obtained based on the simulation software; finally, based on the correspondence between the structural parameters of the functional primitive sequences of different dimensions and the corresponding sound absorption coefficients, a sound absorption performance database is established, from which training and validation sets are obtained. This ensures the reliability and comprehensiveness of the training and validation sets, making them well-suited for Helmholtz resonant materials and providing an effective data foundation for the training and validation of subsequent prediction models.

[0036] 3. The machine learning-based method used in this invention constructs a prediction model for the sound absorption performance of Helmholtz resonant materials using training and validation sets. The resulting prediction model can significantly reduce the prediction time, solving the problem of long prediction time and low efficiency of simulation technology, and providing a solution for accelerating the design speed of acoustic Helmholtz resonant materials. Attached Figure Description

[0037] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0038] Figure 2(a) is a schematic diagram of the one-dimensional functional primitive sequence structure in the embodiment;

[0039] Figure 2(b) is a schematic diagram of the two-dimensional functional primitive sequence structure in the embodiment;

[0040] Figure 2(c) is a schematic diagram of the three-dimensional functional primitive sequence structure in the embodiment;

[0041] Figure 2(d) is a schematic diagram of the four-dimensional functional primitive sequence structure in the embodiment;

[0042] Figure 2(e) is a schematic diagram of the five-dimensional functional primitive sequence structure in the embodiment;

[0043] Figure 3(a) is a comparison curve of the model prediction value and the simulation value obtained based on the one-dimensional functional primitive sequence in the embodiment;

[0044] Figure 3(b) is a comparison curve of the model prediction value 1 and the simulation value 1 obtained based on the two-dimensional functional primitive sequence in the embodiment;

[0045] Figure 3(c) is a comparison curve of the model prediction value 2 and the simulation value 2 obtained based on the two-dimensional functional primitive sequence in the embodiment;

[0046] Figure 4 This is a schematic diagram of the Helmholtz resonant material sound absorption performance prediction device module in this invention;

[0047] Figure 5 This is a schematic diagram of the electronic terminal structure in this invention;

[0048] The diagram is labeled as follows: 400, prediction device; 410, data acquisition module; 420, model training module; 430, result prediction module; 500, electronic terminal; 510, memory; 520, processor. Detailed Implementation

[0049] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. These embodiments are based on the technical solution of the present invention and provide detailed implementation methods and specific operating procedures. However, the scope of protection of the present invention is not limited to the following embodiments.

[0050] like Figure 1 As shown, a method for predicting the sound absorption performance of Helmholtz resonant materials includes the following steps:

[0051] S1. Based on the sound absorption performance database of different dimensions of Helmholtz resonant materials and their sound absorption coefficients, obtain training and validation sets;

[0052] S2. Using the data in the training set, train a machine learning-based network for predicting the sound absorption performance of Helmholtz resonant materials, and use the validation set for testing and verification to obtain a prediction model for the sound absorption performance of Helmholtz resonant materials.

[0053] S3. Input the structural parameters of the Helmholtz resonant material to be tested in different dimensions into the prediction model of the sound absorption performance of the Helmholtz resonant material, and output the predicted values ​​of the sound absorption coefficient of the Helmholtz resonant material in different dimensions.

[0054] In step S1, the sound absorption performance database of the Helmholtz resonant material in different dimensions of structural parameters and sound absorption coefficients is specifically established through the following steps:

[0055] S11. Use simulation software to establish the functional unit sequence of Helmholtz resonance materials in different dimensions;

[0056] S12. By adjusting the structural parameters of the functional primitive sequence, the corresponding sound absorption coefficient is obtained based on simulation software;

[0057] S13. Based on the correspondence between the structural parameters and sound absorption coefficients of functional primitives in different dimensions, a sound absorption performance database is established.

[0058] The functional unit includes a cavity, with an opening at the center of one end of the cavity, and the opening is connected to a hollow sound-absorbing pipe.

[0059] It should be noted that the cavity is preferably designed as a cube structure because cube structures are simple to manufacture, easy to model and simulate. The cavity can also be designed as a cylinder, cone, or other structures. Among them, the sound-absorbing duct can be designed as a hollow cylindrical structure.

[0060] The structural parameters of the functional primitive sequence include any one or more combinations of cavity length, cavity width, cavity height, hole depth, and hole diameter.

[0061] Specifically, the sound absorption performance of the functional element sequence structure can be altered by adjusting structural parameters such as cavity length, width, and height, as well as pore diameter and depth of the sound-absorbing ducts. When the cavity is a non-cubic structure, the corresponding parameter settings can also be changed. For example, when the cavity is a cylindrical structure, its diameter and height can be adjusted to change the sound absorption performance of the functional element sequence structure.

[0062] In this embodiment, the simulation software used is COMSOL, which has strong integration of modeling and acoustic calculation, allows for parameter setting, and has high calculation efficiency; in addition, it has a wealth of embedded CAD modeling tools, which can be used to perform two-dimensional and three-dimensional modeling directly in the software.

[0063] By using COMSOL for modeling and simulation analysis, functional primitive sequences of different dimensions of Helmholtz resonant materials were established according to preset parameters, as shown in Figure 2. (a) to (e) represent structural schematic diagrams of one-dimensional to five-dimensional functional primitive sequences, respectively. A cube with a square top cross-section represents the substrate of the functional primitive sequence established through simulation software and does not participate in sound absorption prediction. The cavities of the functional primitive sequence are preferably cubes; the sound-absorbing ducts are preferably cylinders, which are simple in structure and easy to control in parameter setting. The openings of the cavities in the functional primitive sequence are uniformly located at one end near the substrate. The functional primitive sequences of different dimensions include N×N cavities.

[0064] For example, the Helmholtz resonant material sound absorption performance prediction method provided in this application can calculate up to 5*N2 sets of input parameters through simulation software, where 5 represents the structural parameters of 5 adjustable functional primitives; N represents the dimension, that is, the N×N cavities of the functional primitives.

[0065] In addition, a theoretical calculation formula for the sound absorption coefficient can be established in the variable settings of COMSOL software to solve for the predicted value of the sound absorption coefficient of the model.

[0066] The corresponding sound absorption coefficient is obtained based on simulation software. The expression for the sound absorption coefficient is:

[0067] α = 1 - T

[0068] Where T represents the reflection coefficient of the Helmholtz resonant material, and its value ranges from (0,1); the expression for the reflection coefficient is:

[0069]

[0070] Among them, W in The incident sound power is the power of the sound applied to the Helmholtz resonant material, and is a known parameter; W ref The reflected sound power, W, is calculated using simulation software. in and ref The unit for all values ​​is watts.

[0071] Step S2 specifically includes the following steps:

[0072] S21. Construct a machine learning-based network for predicting the sound absorption performance of Helmholtz resonant materials;

[0073] S22. Using the structural parameters of different dimensions of the Helmholtz resonant material as input and the sound absorption coefficient as output, train a machine learning-based prediction network for the sound absorption performance of the Helmholtz resonant material using the data in the training set.

[0074] S23. Use the data in the validation set to test and verify the prediction accuracy of the trained prediction network. After the test is passed, the prediction model of the sound absorption performance of the Helmholtz resonant material is obtained.

[0075] It should be noted that, based on the sound absorption performance database of Helmholtz resonant materials across different dimensions of structural parameters and sound absorption coefficients, all data corresponding to a specific dimension are obtained and split into a training set and a validation set. The training set is used to train a machine learning-based Helmholtz resonant material sound absorption performance prediction network; the validation set is used to test and validate the Helmholtz resonant material sound absorption performance prediction model. The training set contains more samples than the validation set.

[0076] For example, the ratio of data samples in the training set to those in the validation set can be 9:1, 8:2, or 7:3.

[0077] It's important to note that machine learning is a general term for a class of algorithms that attempt to extract hidden patterns from large amounts of historical data for prediction or classification. More specifically, machine learning can be viewed as finding a function whose input is sample data and whose output is the desired result, albeit one that is too complex to be easily formalized. It's crucial to understand that the goal of machine learning is to make the learned function perform well on "new samples," not just on the training samples. The ability of a learned function to apply to new samples is called generalization ability. Higher generalization ability indicates a better fit for new samples.

[0078] In this embodiment, the random forest algorithm is used to train the prediction model for the sound absorption performance of the Helmholtz resonant material. This is because the random forest algorithm can handle high-dimensional data (with many features) without requiring feature selection, and it is highly adaptable to various datasets: it can handle both discrete and continuous data, and the dataset does not need to be normalized. Furthermore, the random forest algorithm has good noise resistance, fast training speed, and is relatively simple to implement.

[0079] Random forests utilize a bootstrap resampling technique to repeatedly and randomly sample k samples with replacement from the original training sample set M to generate a new training sample set. Then, k classification trees are generated from the bootstrap sample set to form a random forest. The classification result of the new data is determined by the score formed by the number of votes cast by each classification tree. Essentially, it's an improvement on the decision tree algorithm, merging multiple decision trees together. Each tree's construction depends on an independently sampled tree, and each tree in the forest has the same distribution. The classification error depends on the classification ability of each tree and the correlation between them. Feature selection uses a random method to split each node, then compares the errors generated under different conditions. The detectable inherent estimation error, classification ability, and correlation determine the number of features selected. While the classification ability of a single tree may be small, after randomly generating a large number of decision trees, a test sample can be statistically classified based on the classification results of each tree to select the most likely classification.

[0080] This embodiment uses the random forest algorithm, taking the structural parameters of the functional primitive sequence of Helmholtz resonant materials in different dimensions as input and the sound absorption coefficient as output, to train the machine learning-based Helmholtz resonant material sound absorption performance prediction network using the data in the training set; and uses the data in the validation set to test and verify the prediction accuracy of the trained prediction network. After passing the test, the Helmholtz resonant material sound absorption performance prediction model is obtained.

[0081] It should be noted that the prediction accuracy of the Helmholtz resonant material sound absorption performance prediction model is evaluated using the coefficient of determination; the expression for the coefficient of determination is:

[0082]

[0083] Among them, y i Represents the simulation values ​​in the validation set; This represents the predicted value obtained using the Helmholtz resonant material sound absorption performance prediction model. The average simulation value is represented by the following formula:

[0084] When the determination coefficient exceeds a preset value, the trained Helmholtz resonant material sound absorption performance prediction model achieves the best prediction effect. For example, in this embodiment, the preset value is 0.8, meaning the prediction effect of the Helmholtz resonant material sound absorption performance prediction model must satisfy R... 2 >0.8.

[0085] In step S3, the structural parameters of the Helmholtz resonant material to be tested in different dimensions are input into the prediction model of the sound absorption performance of the Helmholtz resonant material, so as to obtain the predicted values ​​of the sound absorption coefficient of the Helmholtz resonant material in different dimensions.

[0086] In this embodiment, based on the Helmholtz resonant material sound absorption performance prediction model provided in this application, R is obtained by training 1120 sets of one-dimensional (i.e., 1×1 type) functional primitive sequence structures with their structural parameters and corresponding sound absorption coefficients. 2 The prediction performance was 0.87, as shown in Figure 3(a), where the coefficient of determination R0 was... 2 This indicates the deviation between the simulated values ​​obtained through simulation software and the predicted values ​​obtained through the Helmholtz resonant material sound absorption performance prediction model.

[0087] By training on the structural parameters and corresponding sound absorption coefficients of 5000 sets of two-dimensional (i.e., 2×2 type) functional primitive sequences, R was obtained. 2 The prediction result of 0.83 is shown in Figures 3(b) and 3(c), which correspond to the prediction results of any two functional primitive sequences, respectively.

[0088] Figure 4 The diagram shown is a schematic of the module of the Helmholtz resonant material sound absorption performance prediction device in the embodiment: The Helmholtz resonant material sound absorption performance prediction device 400 includes: a data acquisition module 410, a model training module 420 and a result prediction module 430.

[0089] The data acquisition module 410 is used to establish a database of sound absorption performance between structural parameters and sound absorption coefficients of Helmholtz resonant materials in different dimensions, and to obtain training and validation sets from it.

[0090] The data acquisition module 410 establishes functional unit sequences of Helmholtz resonant materials in different dimensions using simulation software; by adjusting the structural parameters of the functional unit sequences, the corresponding sound absorption coefficients are obtained based on the simulation software; and a sound absorption performance database is established based on the correspondence between the structural parameters of the functional unit sequences in different dimensions and the corresponding sound absorption coefficients.

[0091] The model training module 420 is used to train a machine learning-based Helmholtz resonant material sound absorption performance prediction network using data in the training set, and to test and verify it using the validation set, so as to obtain the Helmholtz resonant material sound absorption performance prediction model.

[0092] The result prediction module 430 is used to input the structural parameters of the Helmholtz resonant material to be tested in different dimensions into the Helmholtz resonant material sound absorption performance prediction model to obtain the predicted values ​​of the sound absorption coefficient of the Helmholtz resonant material in different dimensions.

[0093] The division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. For example, the result prediction module 430 can be a separate processing element, or it can be integrated into a chip in the above device. Alternatively, it can be stored as program code in the memory of the above device, and its function can be called and executed by a processing element of the device. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element mentioned here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0094] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more digital signal processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together to form a system-on-a-chip (SOC).

[0095] For specific limitations regarding the Helmholtz resonator material sound absorption performance prediction device, please refer to the above limitations regarding the Helmholtz resonator material sound absorption performance prediction method. Each module in the aforementioned Helmholtz resonator material sound absorption performance prediction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in an electronic device, or stored in the memory of an electronic device as software, so that the processor can call and execute the corresponding operations of each module.

[0096] Figure 5 The diagram shown is a structural schematic of the electronic terminal 500 in the embodiment. The electronic terminal 500 includes: a memory 510 and a processor 520; the memory 510 stores computer instructions; the processor 520 executes the computer instructions to implement, for example... Figure 1 The steps are shown.

[0097] In some embodiments, the number of the memory 510 and the processor 520 in the electronic terminal 500 can be one or more, while Figure 5 Each example is taken as an instance.

[0098] In the embodiments of this application, the processor 520 in the electronic terminal 500 will perform as follows: Figure 1 The method steps involve loading one or more instructions corresponding to the process of an application into memory 510, and having the processor 520 run the application stored in memory 510, thereby achieving the following: Figure 1 The method steps are described below.

[0099] The memory 510 may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. The memory 510 stores an operating system and operating instructions, executable modules or data structures, or subsets thereof, or extended sets thereof. The operating instructions may include various operation instructions for implementing various operations. The operating system may include various system programs for implementing various basic services and handling hardware-based tasks.

[0100] The processor 520 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0101] In some specific applications, the various components of the electronic terminal 500 are coupled together through a bus system, which may include not only a data bus but also a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in... Figure 5 All kinds of buses are referred to as bus systems.

[0102] Furthermore, this embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements as follows: Figure 1 The method steps are described below.

[0103] At any possible level of technical detail, this application can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this application.

[0104] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example, (but not limited to) electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0105] The computer-readable program described herein can be downloaded from a computer-readable storage medium to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer-readable program instructions from the network and forwards those instructions to the computer-readable storage medium stored in the respective computing / processing device.

[0106] The computer program instructions used to perform the operations of this application may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, integrated circuit configuration data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer, for example, via the Internet using an Internet service provider. In some embodiments, electronic circuits, such as programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), are personalized by utilizing the status information of the computer-readable program instructions. These electronic circuits can execute the computer-readable program instructions to implement various aspects of this application.

[0107] In summary, this technical solution provides a method, device, medium, and terminal for predicting the sound absorption performance of Helmholtz resonant materials. The method includes: obtaining a training set and a validation set based on a database of sound absorption performance between structural parameters and sound absorption coefficients of Helmholtz resonant materials in different dimensions; training a machine learning-based Helmholtz resonant material sound absorption performance prediction network using the data in the training set, and testing and validating it using the validation set to obtain a Helmholtz resonant material sound absorption performance prediction model; and inputting the structural parameters of the Helmholtz resonant material to be tested in different dimensions into the Helmholtz resonant material sound absorption performance prediction model to obtain predicted values ​​of the sound absorption coefficients of the Helmholtz resonant material in different dimensions.

[0108] This technical solution utilizes machine learning to not only solve the problem of predicting the sound absorption performance of acoustic Helmholtz resonator materials through simulation due to the numerous parameters, but also to address the inefficiency and long prediction time associated with traditional simulation techniques. Experimental verification shows that the prediction time can be reduced from 3-8 minutes to less than one second. Furthermore, this solution can obtain highly accurate predicted values ​​of the sound absorption coefficients of Helmholtz resonator materials in different dimensions, thereby achieving the goal of efficiently and accurately evaluating the sound absorption performance of Helmholtz resonator materials. This also provides a new approach to accelerating the design speed of acoustic Helmholtz resonator materials in the future. Therefore, this technical solution effectively overcomes the various shortcomings of existing technologies and has high industrial application value.

[0109] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A method of predicting the sound absorption performance of a Helmholtz resonator material, characterized by, The method comprises the following steps: S1, obtaining a training set and a verification set based on an absorption performance database between structural parameters of different dimensions of Helmholtz resonance materials and sound absorption coefficients; S2, training a Helmholtz resonance material sound absorption performance prediction network based on machine learning by using data in the training set, and testing and verifying by using the verification set to obtain a Helmholtz resonance material sound absorption performance prediction model; S3, inputting structural parameters corresponding to different dimensions of a to-be-tested Helmholtz resonance material into the Helmholtz resonance material sound absorption performance prediction model to obtain sound absorption coefficient prediction values of the Helmholtz resonance material of different dimensions; The absorption performance database between structural parameters of different dimensions of Helmholtz resonance materials and sound absorption coefficients in step S1 is obtained by the following steps: S11, establishing a functional element sequence structure of different dimensions of Helmholtz resonance materials by using simulation software, wherein the functional element sequence structure comprises a cavity, an opening is arranged at the center of one end of the cavity, and a sound absorption pipeline with a hollow structure is connected to the opening; S12, obtaining a sound absorption coefficient based on the simulation software by adjusting the structural parameters of the functional element sequence structure, wherein the expression of the sound absorption coefficient is: α＝1-T wherein T represents a reflection coefficient of the Helmholtz resonance material, and the expression is: wherein W in represents the incident sound power, is the power of the sound applied to the Helmholtz resonant material, and is a known parameter; W ref represents the reflected sound power, which is calculated by simulation software; S13, establishing an absorption performance database according to the corresponding relationship between the structural parameters of the functional element sequence structure of different dimensions and the sound absorption coefficient, wherein the structural parameters of the functional element sequence structure include any one or a combination of cavity length, cavity width, cavity height, hole depth and hole diameter.

2. The method of claim 1, wherein, The step S2 specifically comprises the following steps: S21, constructing a Helmholtz resonance material sound absorption performance prediction network based on machine learning; S22, using the data in the training set to train the Helmholtz resonance material sound absorption performance prediction network by taking the structural parameters of different dimensions of Helmholtz resonance materials as input and taking the sound absorption coefficient as output; S23, testing and verifying by using the data in the verification set to determine the prediction accuracy of the trained prediction network, and obtaining a Helmholtz resonance material sound absorption performance prediction model after the test is passed.

3. A device for predicting sound-absorbing performance of a Helmholtz resonator material using the method for predicting sound-absorbing performance of a Helmholtz resonator material according to claim 1, characterized by, The method comprises a data acquisition module, a model training module and a result prediction module; The data acquisition module is used to establish an absorption performance database between structural parameters of different dimensions of Helmholtz resonance materials and sound absorption coefficients, and obtain a training set and a verification set therefrom; The model training module is used to train a Helmholtz resonance material sound absorption performance prediction network based on machine learning by using data in the training set, and test and verify by using the verification set to obtain a Helmholtz resonance material sound absorption performance prediction model; The result prediction module is used to input structural parameters corresponding to different dimensions of a to-be-tested Helmholtz resonance material into the Helmholtz resonance material sound absorption performance prediction model, and output to obtain sound absorption coefficient prediction values of the Helmholtz resonance material of different dimensions.

4. The apparatus for predicting sound absorption performance of a Helmholtz resonator material according to claim 3, wherein The specific working process of the data acquisition module comprises: establishing a functional cell sequence structure of different dimensions of the Helmholtz resonance material by using simulation software; obtaining corresponding sound absorption coefficients based on the simulation software by adjusting structure parameters of the functional cell sequence structure; and establishing a sound absorption performance database based on a corresponding relationship between the structure parameters of the functional cell sequence structure of different dimensions and the corresponding sound absorption coefficients.

5. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the Helmholtz resonance material sound absorption performance prediction method in any one of claims 1-2.

6. An electronic terminal, characterized in that The program is executed by the processor to implement the Helmholtz resonance material sound absorption performance prediction method in any one of claims 1-2. The program is executed by the processor to implement the Helmholtz resonance material sound absorption performance prediction method in any one of claims 1-2. The program is executed by the processor to implement the Helmholtz resonance material sound absorption performance prediction method in any one of claims 1-2. The program is executed by the processor to implement the Helmholtz resonance material sound absorption performance prediction method in any one of claims 1-2. The program is executed by the processor to implement the Helmholtz resonance material sound absorption performance prediction method in any one of claims 1-2. The program is executed by the processor to implement the Helmholtz resonance material sound absorption performance prediction method in any one of claims 1-2. The program is executed by the processor to implement the Helmholtz resonance material sound absorption performance prediction method in any one of claims 1-2. The program is executed by the processor to implement the Helmholtz resonance material sound absorption performance prediction method in any one of claims 1-2. The program is executed by the processor to implement the Helmholtz resonance material sound absorption performance prediction method in any one of claims 1-2.

Images