Acoustic metamaterial performance test method, system, equipment and medium

Abstract

The invention discloses an acoustic metamaterial performance test method, system and device and a medium. The method comprises the following steps: acquiring key attribute parameters of an acoustic metamaterial and demand parameters of a preset analogue simulation scene; constructing a multi-objective optimization function according to the key attribute parameters, and inputting a target solution output by the multi-objective optimization function and the demand parameters into simulation software for simulation; in the simulation process, screening out a key feature subset from the target solution by using a dual-stage screening mechanism; inputting the key feature subset into a pre-trained performance prediction neural network model, and outputting to obtain a test result reflecting the performance of the acoustic metamaterial; adjusting parameters in the target solution according to the test result, performing iterative simulation, and outputting to obtain a performance index value of the acoustic metamaterial; and determining the performance utility of the acoustic metamaterial according to the performance index value.

Description

Technical Field

[0001] The present invention relates to the field of acoustic material testing, and in particular, to a method, system, device and medium for testing the performance of acoustic metamaterials. Background Art

[0002] Acoustic metamaterials achieve acoustic properties that cannot be achieved by traditional materials, such as low-frequency sound absorption, negative refractive index, and acoustic wave directional control, through artificially designed microstructures such as periodically arranged resonance units, porous structures, etc. Due to these excellent properties, they are widely used in the manufacturing of high-efficiency noise reduction and sound insulation materials in the production processes of fields such as power equipment, intelligent vehicles, medical devices, and electronic devices. To meet the effects of acoustic metamaterials in practical applications and save costs and manufacturing time, it is necessary to test or simulate the performance of acoustic metamaterials.

[0003] Existing testing technologies often rely on a large number of physical experiments in a laboratory environment. However, the structure of acoustic metamaterials is highly complex, resulting in low direct experimental efficiency. Moreover, since the laboratory environment cannot reproduce real working conditions, the accuracy of test results is poor, making it difficult to confirm the true performance of acoustic materials, and thus unable to effectively optimize and adjust acoustic materials to meet the requirements of production / application in related fields.

[0004] Therefore, how to effectively test the performance of acoustic metamaterials has become a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0005] The present invention provides a method, system, device and medium for testing the performance of acoustic metamaterials, which solves the problem of how to process data reflecting the performance of acoustic materials by constructing a multi-objective optimization function and a neural network model to improve the test accuracy and efficiency.

[0006] To solve the above technical problems, an embodiment of the present invention provides a method for testing the performance of acoustic metamaterials, including: Obtaining key attribute parameters of the acoustic metamaterial and requirement parameters of a preset simulation scenario; Constructing a multi-objective optimization function according to the key attribute parameters, and inputting the target solution output by the multi-objective optimization function and the requirement parameters into simulation software for simulation; During the simulation process, using a two-stage screening mechanism to screen out a key feature subset from the target solutions; Inputting the key feature subset into a pre-trained performance prediction neural network model to output a test result reflecting the performance of the acoustic metamaterial; Adjusting the parameters in the target solution with the test result and performing iterative simulation to output the performance index value of the acoustic metamaterial; Determine the performance utility of the acoustic metamaterial according to the performance index value.

[0007] Further, constructing a multi-objective optimization function according to the key attribute parameters, and inputting the objective solution output by the multi-objective optimization function and the requirement parameters into simulation software for simulation, includes: Construct the multi-objective optimization function considering the environmental temperature constraint with the key attribute parameters as decision variables; Use a preset genetic algorithm to search the multi-objective optimization function, and output the objective solution including the microscopic pore structure, frequency response characteristics, and material thickness of the acoustic metamaterial.

[0008] Create a simulation environment in the simulation software with the objective solution and the requirement parameters to simulate the performance of the acoustic metamaterial.

[0009] Further, the multi-objective optimization function includes: The first sub-function with the maximum sound insulation of the acoustic metamaterial as the goal, the second sub-function with the maximum sound energy absorption efficiency of the acoustic metamaterial as the goal, and the third sub-function with the minimum density of the acoustic metamaterial as the goal.

[0010] Further, using a two-stage screening mechanism to screen out the key feature subset from the objective solution, includes: In the first stage, perform feature screening and optimization on each parameter data in the objective solution with the information criterion mechanism to obtain an initial feature set; In the second stage, determine the contribution degree of each feature to the performance of the acoustic metamaterial by quantifying the relative importance and category difference of each feature in the initial feature set; Screen out the key feature subset from the initial feature set with the contribution degree.

[0011] Further, performing feature screening and optimization on each parameter data in the objective solution with the information criterion mechanism to obtain an initial feature set, includes: Construct a multi-distribution function with the information criterion mechanism, and calculate the transition probability of each parameter data according to the multi-distribution function; Determine the characteristic frequency of each parameter data according to the transition probability; Under the preset frequency threshold condition, perform feature screening in the objective solution with the characteristic frequency to obtain the initial feature set.

[0012] Further, adjusting the parameters in the objective solution with the test results and performing iterative simulation, and outputting the performance index value of the acoustic metamaterial, includes: Match and analyze the test results with the optimization objectives of the multi-objective optimization function. When the matching error exceeds a preset error threshold, adjust the corresponding parameters in the target solution; Iterate the simulation process with the adjusted parameters until convergence to obtain the performance index value.

[0013] Furthermore, adjusting the parameters in the target solution with the test results and performing iterative simulation to output the performance index value of the acoustic metamaterial further includes: When the matching error exceeds the preset error threshold, introduce a temperature correction factor in the multi-objective optimization function for update, and correct the constraint conditions of the multi-objective optimization function; Iterate the simulation process with the updated multi-objective optimization function to obtain the performance index value.

[0014] Another embodiment of the present invention provides an acoustic metamaterial performance test system, including: Another embodiment of the present invention provides a computer device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the acoustic metamaterial performance test method described above is implemented.

[0015] A parameter acquisition module for acquiring the key attribute parameters of the acoustic metamaterial and the requirement parameters of the preset simulation scenario; A simulation module for constructing a multi-objective optimization function according to the key attribute parameters, and inputting the target solution output by the multi-objective optimization function and the requirement parameters into a simulation software for simulation; A feature screening module for screening out a key feature subset from the target solution by using a two-stage screening mechanism during the simulation process; A performance prediction module for inputting the key feature subset into a pre-trained performance prediction neural network model and outputting a test result reflecting the performance of the acoustic metamaterial; An iteration module for adjusting the parameters in the target solution with the test results and performing iterative simulation to output the performance index value of the acoustic metamaterial; A performance analysis module for determining the performance utility of the acoustic metamaterial according to the performance index value.

[0016] Another embodiment of the present invention provides a computer-readable storage medium storing a computer program. When the device where the computer-readable storage medium is located executes the computer program, the acoustic metamaterial performance test method described above is implemented.

[0017] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following: In the embodiments of the present invention, an optimal parameter group of the acoustic metamaterial is determined by constructing a multi-objective optimization function, and key features that fully reflect the acoustic performance are screened out from the acoustic metamaterial data by collaborating with an information criterion and a contribution degree quantification mechanism, which can avoid the influence of redundant features on the model performance, reduce the computational complexity, and enhance the interpretability of the model; by integrating a simulation tool of a deep neural network model to test the performance characteristics of the acoustic material, the complex characteristics of the acoustic material can be accurately captured, and a multi-objective genetic algorithm is used to call the simulation tool to dynamically adjust and optimize the scene parameters of the acoustic material, so as to more accurately simulate the performance of the acoustic material. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a schematic flowchart of a method for testing the performance of an acoustic metamaterial in one embodiment of the present invention; Figure 2 is a schematic structural diagram of a system for testing the performance of an acoustic metamaterial in one embodiment of the present invention; Figure 3 is a structural block diagram of a preferred embodiment of a computer device provided by the present invention; Reference numerals: M1, parameter acquisition module; M2, simulation module; M3, feature screening module; M4, performance prediction module; M5, iteration module; M6, performance analysis module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0020] In the description of the present application, the terms "first", "second", "third", etc. are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined with "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0021] In the description of the present application, it should be noted that, unless otherwise clearly specified and defined, the terms "installation", "connection", and "coupling" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be a direct connection or an indirect connection through an intermediate medium, and it may be the communication inside two components. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for the purpose of illustration, rather than indicating or implying that the device or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0022] In the description of the present application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0023] An embodiment of the present invention provides a method for testing the performance of acoustic metamaterials. Specifically, please refer to Figure 1 , Figure 1 which shows a schematic flow chart of the method for testing the performance of acoustic metamaterials in one of the embodiments of the present invention, including the following steps: S1. Obtain the key attribute parameters of the acoustic metamaterial and the requirement parameters of the preset simulation scenario.

[0024] In this embodiment, the key attribute parameters of the acoustic metamaterial for performance testing will be collected. Exemplarily, in this embodiment, specific data acquisition devices such as impedance tube test devices and reverberation chamber devices will be used. The key parameters of the acoustic metamaterial include, but are not limited to: the physical properties of the material, acoustic response characteristics, and microstructure parameters, etc. These parameters can all reflect the sound insulation characteristics, the ability to hinder sound wave propagation, and the ability to absorb sound energy of the material to a certain extent. Exemplarily, the physical properties include material density, thermal conductivity, etc., as well as the thickness of the material; the microstructure parameters include porosity, pore size distribution, flow resistivity, pore connectivity, etc.; the acoustic response characteristics such as frequency response characteristics, such as resonance frequency, frequency response curve, etc. Further, the collected parameter data needs to be preprocessed, including removing outliers, missing values, removing incorrect data, data conversion, and data normalization.

[0025] In the embodiments of the present invention, it relates to the creation of a simulation environment. FOAM-X and COMSOL simulation software can be selected to create the simulation environment. For example, in this embodiment, the simulation of the noise control scenario of power equipment is preferred. It should be understood that the required parameter values for the simulation environment include, but are not limited to, the temperature, humidity, noise frequency range, and air flow velocity of the power equipment. Exemplarily, they can be collected inside the target power equipment through relevant sensor devices, anemometers, etc., or directly obtained from the equipment operation logs and real-time monitoring data.

[0026] S2. Construct a multi-objective optimization function based on the key attribute parameters, and input the target solution output by the multi-objective optimization function and the required parameter values into the simulation software for simulation.

[0027] This step is the simulation process. To ensure the accuracy of the test results, in this embodiment, a multi-objective optimization function is introduced to solve the multi-objective optimization problem. It should be understood that the performance of acoustic metamaterials is reflected in the sound insulation amount, acoustic impedance, sound absorption coefficient, sound velocity, and refractive index. For example, acoustic impedance represents the ability of a material to impede sound waves, and it is affected by fluctuations in parameters such as porosity; the sound insulation amount represents the ability of a material to block the propagation of sound waves in decibels, and it is affected by parameters such as material thickness and density, and the density itself also affects the lightweight requirement of the material; the sound absorption coefficient represents the proportion of sound energy absorbed by the material.

[0028] Considering the key performance of acoustic materials and the mapping relationship between performance and attribute parameters, in some embodiments of the present invention, a multi-objective optimization function considering environmental temperature constraints is constructed with the key attribute parameters as decision variables. This multi-objective optimization function includes multiple sub-functions: a first sub-function with the maximum sound insulation amount of acoustic metamaterials as the objective, a second sub-function with the maximum sound energy absorption efficiency of acoustic metamaterials as the objective, and a third sub-function with the minimum density of acoustic metamaterials as the objective. Preferably, the decision variables include the microscopic pore structure parameters, material density, and frequency response characteristic parameters of acoustic metamaterials.

[0029] It should be noted that in this embodiment, the influence of the simulation environment is considered, and corresponding environmental constraint conditions are set. For example, the temperature is set to ≥150 °C, and the high temperature resistance of the material is introduced into the test content. In some embodiments of the present invention, geometric constraints can also be set to limit the installation space of the material, as well as physical constraints, such as ensuring that the pore sound absorption of the material is not less than 0.3.

[0030] Furthermore, the constructed multi-objective optimization function is solved using a preset genetic algorithm. In this embodiment, the non-dominated sorting genetic algorithm (NSGA-II) is preferably used to search the multi-objective optimization function, and the Pareto solution set, that is, the target solution, is output. Exemplarily, 50 groups of candidate parameter combinations are output, including the optimal parameter groups composed of these decision variables such as the microscopic pore structure, frequency response characteristics, and material thickness.

[0031] Create a simulation environment in the simulation software with the target solution and requirement parameters to simulate the performance of the acoustic metamaterial and verify the actual performance of the parameters. For example, by setting the values of the requirement parameters, simulate the internal environment of the power equipment in the simulation software, such as simulating the noise reduction control in the power transformer room and testing the sound insulation performance of the acoustic material in this scenario.

[0032] S3. During the simulation process, use a two-stage screening mechanism to screen out the key feature subset from the target solution.

[0033] It can be understood that the target solution contains multiple optimized combinations of key attribute parameters. These parameter combinations can be first parsed and structured. They affect the feature screening direction. For example, if the optimized low-frequency performance becomes the focus, the two-stage screening mechanism will be used to screen out the features related to low frequency from them, such as pore connectivity.

[0034] In the first stage, considering the role of the information criterion mechanism in model optimization, use the information criterion mechanism to optimize the features of each parameter data in the target solution to obtain the initial feature set.

[0035] Specifically, construct a multi-distribution function with the information criterion mechanism, calculate the transition probability of each parameter data according to the multi-distribution function, and determine the characteristic frequency of each parameter data according to the transition probability.

[0036] Exemplarily, in this embodiment, probability distribution functions are constructed through the AIC criterion and the BIC criterion respectively, that is, calculate the conditional probability that each feature in the solution set is selected. Combining the two criteria can avoid the deviation of a single criterion and improve the robustness of feature selection.

[0037] Among them, the function constructed by the AIC criterion is expressed as: By weighting the AIC value, the balance between the goodness of fit and complexity of the model can be achieved for the current feature.

[0038] In the formula, represents the probability that the feature s is selected based on the AIC criterion; represents the distribution probability of AIC; represents whether the s-th feature is included in the feature subset, represents the state combination of all other features except the s-th feature.

[0039] The function constructed by the BIC criterion is expressed as: The BIC criterion imposes a heavier penalty on the model complexity. In the formula, Denotes the probability that feature s is selected based on the BIC criterion; Denotes the distribution probability of BIC.

[0040] According to the calculated transition probability, perform cyclic sampling to determine the number of times each feature is selected. By calculating the ratio of this number to the preset number of repeated samplings, the feature frequency is obtained. Exemplarily, if the feature porosity is selected 600 times in 1000 repeated samplings, then the feature frequency = 0.6.

[0041] Under the preset frequency threshold condition, perform feature screening in the target solution based on the feature frequency to obtain the initial feature set. Exemplarily, the threshold can be set to 0.5. Then, during the screening process, features with a feature frequency greater than this threshold need to be retained and incorporated into the initial feature subset. In some embodiments of the present invention, during the sampling process, significance error control is also introduced, which is expressed as follows: In the formula, The standard deviation of the feature frequency; q is the correlation significance of the variable; t is the number of samplings.

[0042] This embodiment realizes efficient and robust feature selection by constructing a transition probability function based on the information criterion and combining it with sampling, providing high-quality input for the subsequent neural network model.

[0043] Well, next is the second stage. In this stage, by quantifying the relative importance and category differences of each feature in the initial feature set, the contribution degree of each feature to the performance of the acoustic metamaterial is determined, that is, this stage is used to quantify the contribution degree of different features to the material performance (such as sound insulation amount, sound absorption coefficient), so as to screen out the key features. Specifically, the screening formula constructed in this embodiment is expressed as follows: Where, Is the matching importance of feature f, that is, the contribution degree; U is the feature set; Is the representation of the i-th feature in U; Is the information gain function; c is the number of features; Is the gain deviation; Is the weight coefficient; Is the number of times of randomly extracting acoustic features; Is the r-th randomly selected acoustic feature set; Is the feature set in the r-th sampling Of the nearest neighbor feature; Is the prior probability of category g; Set Of the prior probability; Is the feature f in The difference function between the medium and the nearest neighbor features.

[0044] It can be seen from the above screening formula that is the information gain term, which measures the relative importance of the information gain of the feature in all features. represents the information gain of the feature The larger the value, the stronger the ability of the feature to distinguish the target variable (such as sound insulation).

[0045] is the category difference term, which is used to evaluate the discrimination ability of the feature between different categories.

[0046] According to the value, features that contribute greatly to the performance of acoustic materials are screened out from the initial feature set and incorporated into the key feature subset. In this embodiment, by quantifying the information gain (reflecting the prediction ability of the feature for the target) and the category difference (reflecting the contribution of the feature to category discrimination), the importance of the feature can be accurately evaluated, and the reliability of the screening result can be improved.

[0047] S4. Input the key feature subset into the pre-trained performance prediction neural network model, and output the test results reflecting the performance of the acoustic metamaterial.

[0048] This step is the process of inputting the screened key feature subset into the pre-trained performance prediction neural network model for performance prediction.

[0049] In order to further improve the generalization ability of the model while reducing computational redundancy, the embodiment of the present invention uses the total cost minimization algorithm to cluster the data. Exemplarily, algorithms such as the K-means clustering algorithm and the improved K-Medoids algorithm can be selected. Specifically, corresponding data is selected as the initial central data in the pre-created sample dataset, the central distance between the remaining data and the dataset center is obtained, the remaining data is assigned to the dataset center with the shortest central distance, non-central data is randomly selected, and the total cost of the central data is calculated according to the non-central data, which is expressed as follows: where S is the total cost; the i-th central data, the i-th non-central data; m is the number of central data; n is the number of non-central data; is the distance between the central data and the non-central data .

[0050] It can be understood that if the total cost is less than or equal to zero, the non-central data replaces the central data to form new central data until no change occurs; otherwise, the central data remains unchanged. According to the theory of minimum total cost, the key feature subsets are clustered to obtain clustering clusters, and the training set and test set are divided. Preferably, the data of the clustering clusters is divided into a training set and a test set according to a ratio of 7:3.

[0051] Further, the deep neural network model is trained with the training set. Specifically, a convolutional layer, a pooling layer, and a fully connected layer are added to the deep neural network, and a loss function is introduced to optimize the parameters of the deep neural network. In some embodiments of the present invention, the momentum algorithm can be selected as the optimizer of the model to update the hyperparameters of the deep neural network, and learn the characteristics of acoustic material simulation and the laws of acoustic materials. Or a regularization technique is introduced to prevent overfitting of the model, such as adding batch normalization and Dropout operators.

[0052] Finally, a performance prediction neural network model is trained. The key feature subsets are input into the performance prediction neural network model for analysis, and the test results reflecting the performance of the acoustic metamaterial are output.

[0053] S5~S6: Adjust the parameters in the target solution with the test results and perform iterative simulation, and output the performance index value of the acoustic metamaterial.

[0054] This step is a parameter correction process. It can be understood that the model outputs the test results reflecting the performance of the acoustic metamaterial, and it should be understood that the multi-objective optimization function can reflect the relationship between the performance and attribute parameters of the acoustic material by analyzing the mapping relationship between the decision variables and the optimization objectives.

[0055] The test results are matched and analyzed with the optimization objectives of the multi-objective optimization function. When the matching error exceeds the preset error threshold, the corresponding parameters in the target solution are adjusted. Exemplarily, if the set optimization objectives include: the target requirement for the sound insulation amount at 100 Hz is ≥ 35 dB, the material density ρ ≤ 800 kg / m³, and the target requirement for the sound absorption coefficient α at a frequency of 300 Hz is ≥ 0.8. If the error between the calculated test results and these target values exceeds the error threshold, such as setting the threshold to 5%, the parameters are optimized, such as screening out unnecessary features and reducing redundancy.

[0056] In addition to optimizing the parameters, the embodiments of the present invention can also optimize the objective function. A temperature correction factor is introduced to update the multi-objective optimization function. The constraint conditions of the multi-objective optimization function can also be corrected. For example, if there is a material density constraint, the material density is appropriately tightened or relaxed; or the parameters of the genetic algorithm are adjusted, such as increasing the population size and adjusting the crossover rate / mutation rate.

[0057] Then, similarly, the simulation process is iterated with the updated multi-objective optimization function to obtain the performance index values. For example, the sound insulation amount of the output is 35 dB, and the sound absorption coefficient is 0.8.

[0058] The adjusted parameters are re-input into the simulation software for iteration until convergence, so as to obtain the final required index values reflecting the true performance of the acoustic material. That is, according to the performance index values, the performance utility of the acoustic metamaterial can be determined. Exemplarily, if the structure of the material needs to be improved, an adjustment strategy can be formulated in time before production to optimize the material performance, such as increasing the percentage of the sound insulation amount of the material, so that the material meets the requirements of a specific field, saving time and cost.

[0059] In summary, the embodiment of the present invention realizes the accurate test of the performance of the acoustic material by creating a simulation environment and combining the trained neural network model; in the test process, a multi-objective function with the performance parameters of the acoustic material as the optimization problem is constructed, and various key attribute parameters affecting the performance of the acoustic material are defined as decision variables, which can realize the efficient optimization of the acoustic performance parameters and improve the test efficiency; a two-stage feature screening mechanism involving information criterion screening and feature contribution degree quantification is adopted to screen out the key feature set from the feature parameter group included in the optimal solution output by the objective function, which can balance the model complexity and the fitting degree and ensure the strong correlation between the key features and the acoustic performance.

[0060] An embodiment of the present invention provides an acoustic metamaterial performance test system. Specifically, please refer to Figure 2 , Figure 2 which shows a schematic structural diagram of the acoustic metamaterial performance test system in one of the embodiments of the present invention, including: A parameter acquisition module M1, configured to acquire the key attribute parameters of the acoustic metamaterial and the requirement parameters of the preset simulation scenario; A simulation module M2, configured to construct a multi-objective optimization function according to the key attribute parameters, and input the objective solution output by the multi-objective optimization function and the requirement parameters into the simulation software for simulation; A feature screening module M3, configured to screen out the key feature subset from the objective solution by using a two-stage screening mechanism during the simulation process; A performance prediction module M4, configured to input the key feature subset into the pre-trained performance prediction neural network model, and output the test result reflecting the performance of the acoustic metamaterial; An iteration module M5, configured to adjust the parameters in the objective solution with the test result and perform iterative simulation, and output the performance index value of the acoustic metamaterial; A performance analysis module M6, configured to determine the performance utility of the acoustic metamaterial according to the performance index value.

[0061] As shown in Figure 3 the following figure, an embodiment of the present invention further provides a computer device, Figure 3 which is a structural block diagram of a preferred embodiment of a computer device provided by the present invention. The computer device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the above-mentioned method is implemented.

[0062] Preferably, the computer program can be divided into one or more modules / units (such as computer program 1, computer program 2,...). The one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.

[0063] The processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor. The processor is the control center of the terminal device and connects various parts of the terminal device through various interfaces and lines.

[0064] The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function, etc., and the data storage area can store relevant data, etc. In addition, the memory may be a high-speed random access memory, or may also be a non-volatile memory, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., or the memory may also be other volatile solid-state storage devices.

[0065] It should be noted that the above-mentioned terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that Figure 3The block diagram is only an example of the terminal device, which does not constitute a limitation on the terminal device. It may include more or fewer components than those shown, or combine some components, or different components. Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it may include the processes of the embodiments of the above methods. Among them, the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0066] Correspondingly, an embodiment of the present invention provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the steps in the method of the above embodiment, for example Figure 1 the steps S1 to S6 described above.

[0067] The technical features and technical effects of the acoustic metamaterial performance testing system proposed in the embodiment of the present invention are the same as those of the acoustic metamaterial performance testing method proposed in the embodiment of the present invention, and will not be elaborated here.

[0068] The above embodiments only represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

Claims

1. A method for testing the performance of acoustic metamaterials, characterized in that: include: Obtain key property parameters of acoustic metamaterials and required parameters of preset simulation scenarios; Constructing a multi-objective optimization function according to the key attribute parameters, and inputting the target solution output by the multi-objective optimization function and the demand parameters into a simulation software for simulation; During the simulation process, a two-stage screening mechanism is used to screen out a subset of key features from the target solution; Inputting the key feature subset into a pre-trained performance prediction neural network model, and outputting a test result reflecting the performance of the acoustic metamaterial; Adjusting the parameters in the target solution according to the test results and performing iterative simulation to output the performance index value of the acoustic metamaterial; The performance utility of the acoustic metamaterial is determined according to the performance indicator value.

2. The method for testing the performance of acoustic metamaterials according to claim 1, characterized in that: The step of constructing a multi-objective optimization function according to the key attribute parameters and inputting the target solution output by the multi-objective optimization function and the demand parameters into a simulation software for simulation includes: Constructing the multi-objective optimization function taking into account the ambient temperature constraint by taking the key attribute parameters as decision variables; Using a preset genetic algorithm to search the multi-objective optimization function, and outputting the target solution including the microscopic pore structure, frequency response characteristics and material thickness of the acoustic metamaterial; A simulation environment is created in the simulation software with the target solution and the required parameters to simulate the performance of the acoustic metamaterial.

3. The acoustic metamaterial performance testing method according to claim 1, characterized in that: The multi-objective optimization function comprises: A first sub-function aims at maximizing the sound insulation of the acoustic metamaterial, a second sub-function aims at maximizing the sound energy absorption efficiency of the acoustic metamaterial, and a third sub-function aims at minimizing the density of the acoustic metamaterial.

4. The method for testing the performance of acoustic metamaterials according to claim 1, characterized in that: The method of using a two-stage screening mechanism to screen out a subset of key features from the target solution includes: In the first stage, the information criterion mechanism is used to perform feature screening on each parameter data in the target solution to obtain an initial feature set; In the second stage, the contribution of each feature to the performance of the acoustic metamaterial is determined by quantifying the relative importance and category differences of each feature in the initial feature set; The key feature subset is selected from the initial feature set according to the contribution degree.

5. The method for testing the performance of acoustic metamaterials according to claim 4, characterized in that: The information criterion mechanism is used to perform feature screening on each parameter data in the target solution to obtain an initial feature set, including: Constructing a multi-distribution function using the information criterion mechanism, and calculating the transition probability of each of the parameter data according to the multi-distribution function; Determining a characteristic frequency of each of the parameter data according to the transition probability; Under a preset frequency threshold condition, feature screening is performed in the target solution with the feature frequency to obtain the initial feature set.

6. The method for testing the performance of acoustic metamaterials according to claim 1, characterized in that: The step of adjusting the parameters in the target solution based on the test results and performing iterative simulation to output the performance index value of the acoustic metamaterial includes: Matching and analyzing the test result with the optimization target of the multi-objective optimization function, and when the matching error exceeds a preset error threshold, adjusting the corresponding parameters in the target solution; The simulation process is iterated with the adjusted parameters until convergence to obtain the performance indicator value.

7. The method for testing the performance of acoustic metamaterials according to claim 6, characterized in that: The method of adjusting the parameters in the target solution according to the test results and performing iterative simulation to output the performance index value of the acoustic metamaterial also includes: When the matching error exceeds a preset error threshold, a temperature correction factor is introduced into the multi-objective optimization function for updating, and the constraint conditions of the multi-objective optimization function are corrected; The simulation process is iterated using the updated multi-objective optimization function to obtain the performance indicator value.

8. An acoustic metamaterial performance testing system, characterized in that: include: A parameter acquisition module is used to obtain key attribute parameters of acoustic metamaterials and required parameters of preset simulation scenarios; A simulation module, used for constructing a multi-objective optimization function according to the key attribute parameters, and inputting the target solution output by the multi-objective optimization function and the demand parameters into a simulation software for simulation; A feature screening module, used to screen out a subset of key features from the target solution using a two-stage screening mechanism during the simulation process; A performance prediction module, used for inputting the key feature subset into a pre-trained performance prediction neural network model, and outputting a test result reflecting the performance of the acoustic metamaterial; An iteration module, used to adjust the parameters in the target solution according to the test results and perform iterative simulation, and output a performance index value of the acoustic metamaterial; A performance analysis module is used to determine the performance utility of the acoustic metamaterial according to the performance indicator value.

9. A computer device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method for testing the performance of an acoustic metamaterial as claimed in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the acoustic metamaterial performance testing method according to any one of claims 1 to 7 is implemented.

Images