Machine learning optimization method of low-frequency sound absorption structure based on three-dimensional printing

Abstract

The invention discloses a machine learning optimization method of a low-frequency sound absorption structure based on three-dimensional printing, and belongs to the technical field of artificial intelligence acoustics, the low-frequency sound absorption structure is prepared from a photosensitive resin material through photocuring three-dimensional printing, and comprises a side seam, an extension cavity, a circular through hole, a resonance cavity, a first partition plate, a second partition plate and a third partition plate, the method has good expansibility and can be adjusted according to different noise control requirements; through a machine learning optimization method, structure parameters can be quickly adjusted to cope with a noise control task on the premise of ensuring a small size, so that a remarkable sound absorption effect is obtained at a specific low-frequency band; according to the method, a machine learning method based on a multi-layer perceptron and a genetic algorithm is adopted, geometric parameters of the low-frequency sound absorption structure are optimized, simulation calculation is carried out by using a commercial finite element solver COMSOL Multiphysics, and the sound absorption performance of the structure is further verified and optimized.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence acoustic technology, and in particular to a machine learning optimization method for a low-frequency sound absorption structure based on three-dimensional printing. Background Art

[0002] With the acceleration of urbanization and the expansion of industrial production, noise pollution has become more and more serious, and low-frequency noise ranks first among all types of noise pollution. At present, noise suppression structures based on structures such as Helmholtz resonators have been successfully manufactured on a small scale through additive manufacturing technology, but traditional sound-absorbing structures cannot use small-sized structures to control large-wavelength sound waves, making it difficult to solve the problem of low-frequency noise control. In addition, the parameter design of sound-absorbing structures requires a lot of time and economic costs. The vigorous development of machine learning enables sound-absorbing structures to control parameter space through more effective methods to ensure the ultimate realization of ideal sound absorption effects. However, it is still difficult to select a neural network architecture that can extract data set features at a lower computational cost and faster for more effective optimization. Summary of the invention

[0003] Technical problems to be solved: In view of the technical problems that the wavelength of low-frequency noise is long and traditional material sound-absorbing structures are difficult to suppress and control large-wavelength sound waves when the size is small, the present application provides a machine learning optimization method for low-frequency sound-absorbing structures based on three-dimensional printing, which is prepared by three-dimensional printing light curing technology, and the structural parameters are easy to adjust; in view of the high time and economic cost of traditional structural parameter design, a multi-layer perceptron and a genetic algorithm are combined for machine learning optimization to optimize its structural parameters, and the sound absorption performance is calculated and verified by COMSOL Multiphysics finite element simulation; finally, the optimized structure has an advantage in the sound absorption effect in a specific low-frequency band, realizing the low-frequency noise suppression function on a smaller unit.

[0004] Technical solution: A machine learning optimization method for low-frequency sound absorption structures based on 3D printing, the steps are as follows: Step 1, constructing a low-frequency sound absorbing structure for achieving low-frequency sound absorption: the low-frequency sound absorbing structure is prepared by photosensitive resin material through photocuring three-dimensional printing, and the low-frequency sound absorbing structure consists of a side seam, an extended cavity, a circular perforation, a resonant cavity, a first baffle, a second baffle and a third baffle, wherein the side seam is arranged 1 mm above the bottom of the right side of the low-frequency sound absorbing structure, and the extended cavity extends along the side seam into the low-frequency sound absorbing structure to form an extended cavity; the resonant cavity is arranged above the extended cavity, and the bottom surface of the resonant cavity is connected to the top surface of the extended cavity through a circular perforation, and the circular perforation is arranged at an end of the extended cavity away from the side seam; the first baffle, the second baffle and the third baffle are evenly staggered in the resonant cavity, and the first baffle, the second baffle and the third baffle are relatively far away from the circular perforation in turn; the material density of the low-frequency sound absorbing structure is between 1.0g / cm³ and 1.2g / cm³, and the Young's modulus is between 2000 MPa and 4000 MPa; Step 2: Dataset Use the commercial finite element solver COMSOL Multiphysics to simulate and calculate the low-frequency sound absorption structure, set and record the lengths of the first baffle, the second baffle, and the third baffle, calculate the sound absorption performance of the low-frequency sound absorption structure from 200 Hz to 350 Hz, and record the sound absorption performance in steps of 5 Hz; record the sound absorption coefficients of 31 frequencies corresponding to each group of 3 geometric parameters to form a complete data set; the data set contains the geometric parameters of the input features and the sound absorption coefficient of the target output, which is used for the training and verification of the subsequent machine learning model; Step 3, based on the multi-layer perceptron and genetic algorithm, the machine learning optimization of the sound absorption performance of the low-frequency sound absorption structure is carried out. Specifically, it includes the following sub-steps: 3.1. Construct a multi-layer perceptron neural network model to model the mapping relationship between geometric parameters and sound absorption coefficients, train the model using the data set collected in step 2, and use cross-validation to evaluate the generalization performance of the model, thereby optimizing the prediction ability of the model; 3.2. Use genetic algorithm to optimize geometric parameters and output optimized geometric parameters; Step 4: Substitute the optimized geometric parameters into COMSOL Multiphysics for recalculation and verification, obtain the final sound absorption coefficient distribution curve, and compare it with the sound absorption performance of the initial geometric parameters to verify the optimization effect.

[0005] Preferably, the length of the resonant cavity in the low-frequency sound absorbing structure is L =40-45mm, width W =23-25mm, height H =23-25mm, height of side seam t =1-2mm, the wall thickness of the resonant cavity b =1mm, circular perforation distance from side seam DL =30-40mm, diameter of circular perforation D n =1-2mm.

[0006] Preferably, the length of the resonant cavity in the low-frequency sound absorbing structure is L =42mm, width W =24mm, height H =24mm, height of side seam t =2mm, the wall thickness of the resonant cavity b =1mm, circular perforation distance from side seam D L =35mm, diameter of circular perforation D n =2mm.

[0007] Preferably, the top surface and the bottom surface of the first partition plate, the second partition plate and the third partition plate are fixedly connected to the top surface and the bottom surface inside the resonance cavity respectively.

[0008] Preferably, the right side surfaces of the first partition plate and the third partition plate are fixedly connected to the right side surface inside the resonance cavity, and the left side surface of the second partition plate is fixedly connected to the left side surface inside the resonance cavity.

[0009] Preferably, the first partition, the second partition and the third partition have adjustable extension lengths in the resonance cavity.

[0010] Preferably, during the calculation process of the commercial finite element solver COMSOL Multiphysics in step 2, the entire model uses hard boundaries to limit the air domain, the side seams and circular perforations are selected as narrow areas, and the circular perforations use a thermoviscous acoustic interface, and a plane wave with an amplitude of 1 Pa is used to simulate the incident harmonics, and the Young's modulus attenuation coefficient of the metamaterial is adjusted between 0.02 and 0.3.

[0011] Preferably, the model structure of the multi-layer perceptron neural network model in step 3.1 includes: Input layer: The input data contains three features, namely, the extension lengths of the first partition, the second partition, and the third partition in the resonant cavity; Hidden layer: Two hidden layers are set, and ReLU activation function is used after each hidden layer. The first hidden layer contains 64 neurons and the second hidden layer contains 128 neurons. Dropout layer: A Dropout layer is set after each hidden layer with a Dropout probability of 0.5 to reduce overfitting; Output layer: The final output is 31 values, representing the sound absorption performance in the range of 200Hz to 350Hz, with a step size of 5Hz.

[0012] Preferably, the model training and verification process of the multi-layer perceptron neural network model in step 3.1 includes: Use mean square error MSE as the loss function: ; in, n is the total number of samples in the data set, taking n =9540; y i is the actual value, is the predicted value; is the L2 regularization term, which is used to prevent overfitting. l is the regularization coefficient, oh Represents the weight parameters in the neural network; The L2 regularization formula is as follows: ; in, R (ω) represents the regularization term, oh Represents the weight parameters in the neural network; l is the regularization coefficient, and its value is l =10 -5 ; oh j For the j Weight parameters; p is the total number of parameters; The Adam optimizer is used to optimize the parameters of the neural network. The update formula includes: (1) Calculation of first-order and second-order momentum estimates of gradients: m t =β 1 m t-1 +(1 -β 1) g t v t =β 2 v t-1 +(1 -β 2) g t 2 in, t is the number of iterations; m t For the t The first-order momentum estimate of the gradient of the iteration, representing the moving average; v t For the t The second-order momentum estimate of the gradient of the iteration, which represents the moving average of the square; m t-1 ,v t-1 The first t -1 iteration of gradient first-order momentum estimation and gradient second-order momentum estimation; β 1 and β 2 is the attenuation coefficient, which is β 1=0.9, β 2=0.999; g t For the t The gradient at iteration ; (2) Deviation correction: , ; in, is the first-order momentum after bias correction; is the bias-corrected second-order momentum; and They are β 1 and β 2 of t The second square represents β 1 and β 2 Pass t The attenuation effect of the iterations; (3) Parameter update rules: ; in, i t It is t Update the model parameters of the iteration, i t+1 The t +1 update iteration of model parameters; or is the learning rate, set to or =0.001; is a smoothing term, and its value is = 10 -8 , used to avoid the denominator being zero; The model validation uses the KFold cross-validation method, which divides the data set into 5 subsets and uses 5-fold cross-validation for training and validation. The cross-validation calculation formula is as follows: ; in, K Indicates the number of cross-validation folds, value K =5, score k For the k The verification score of the fold.

[0013] Preferably, the genetic algorithm in step 3.2 sets the initial population size to 100 and the number of genetic iterations to 40 generations, and uses the following steps to optimize the geometric parameter data: (1) Constructing fitness function The extended lengths of the first baffle, the second baffle and the third baffle of the low-frequency sound absorption structure in the resonant cavity are used as input, and the sound absorption coefficient of the low-frequency sound absorption structure at multiple frequencies is predicted using the trained multi-layer perceptron model; the fitness value is determined by calculating the total sound absorption coefficient and combining the sound absorption performance near the target low frequency of 200 Hz; the fitness value is expressed by the following formula: ; in, m is the number of frequency points, and the frequency points are selected in the range of 200Hz to 350Hz with a step size of 5Hz. m =31; a i It is i The sound absorption coefficient of each frequency; f peak is the frequency Hz corresponding to the maximum sound absorption coefficient; f target is the target frequency, i.e. 200Hz; d is the penalty factor, with a value of d =0.2, used to adjust the trade-off between the total sound absorption coefficient and the target frequency deviation; The sound absorption coefficient is calculated using the following formula: ; Among them, the reflection coefficient R Defined as ; Z H is the acoustic impedance of the sound absorbing structure; Z 0= r 0 c 0 is the characteristic impedance of air, where the density of air r 0=1.21 kg / m 3 , the speed of sound in air c 0=343 m / s ; (2) Based on the fitness function, simulate the natural selection process for optimization, including: Crossover operation: The two-point crossover operation cxTwoPoint is used to cross the individuals, with a crossover probability of 0.5; two crossover points are randomly selected c 1 and c 2 pairs of offspring O 1 and O The gene expression of 2 is updated as follows: O 1= P 1[: c 1]+ P 2[ c 1: c 2]+ P1[ c 2:] O 2= P 2[: c 1]+ P 1[ c 1: c 2]+ P 2[ c 2:] in, P 1 and P 2 is the gene sequence of two parent individuals, [: c 1] is from the beginning of the sequence to the intersection point c 1 before the part; [ c 1: c 2] For the sequence from the intersection c 1 to the intersection c 2 part between; [ c 2:] is the sequence from the intersection c 2 to the end of the sequence; Mutation operation: The individual is mutated through the Gaussian mutation operation mutGaussian, with a mutation probability of 0.2; for individual I =[ x 1, x 2, x 3], each gene x i Gaussian mutation occurs with probability 0.2: x’ = x + N (0, s 2 ) in, N (0, s 2 ) has a mean of 0 and a variance of s 2 Gaussian distributed noise; Selection operation: Through the tournament selection operation selTournament, the tournament size is 3, and 3 individuals are randomly selected from the population { I 1, I 2, I 3}, calculate its fitness value F , and select the one with the highest fitness: I selected =arg max i∈{1,2,3} F ( I i ) in, I i Indicates the extracted i individual; F ( I i ) is the fitness function; I i The fitness value is determined by the fitness function F ( I i ) is calculated, arg max i∈{1,2,3} F ( I i ) means in the set { I 1, I 2, I 3} Select the function F ( I i ) The individual index with the maximum value i .

[0014] Compared with the prior art, the present invention has at least the following beneficial effects: 1. The low-frequency sound-absorbing structure of the present invention can quickly adjust the structural parameters to cope with different noise control tasks while ensuring a small size. Aiming at the problem that the wavelength of low-frequency noise is long and the traditional sound-absorbing material has a small structure size and cannot effectively control the large-wavelength sound wave, compared with the traditional sound-absorbing structure, the low-frequency sound-absorbing structure of the present invention is prepared by photosensitive resin metamaterials through three-dimensional printing photocuring technology, which can effectively suppress low-frequency noise in a small size and achieve better low-frequency noise control. At the same time, the low-frequency sound-absorbing structure of the present invention has good scalability, and the parameters of the three partitions can be flexibly adjusted, which is convenient for parameter design and optimization through machine learning and other methods to cope with different applications that meet different frequency bands and different noise control requirements. 2. The present invention uses a machine learning optimization method that combines a multi-layer perceptron with a genetic algorithm, which can effectively optimize the geometric parameters of the sound-absorbing structure in a relatively short time. Through the prediction of the neural network model and the adaptive optimization of the genetic algorithm, the time and economic costs in the traditional design method are reduced, and the efficiency and accuracy of the design process are improved. Combined with the commercial finite element solver COMSOL Multiphysics for simulation calculations, the performance of the designed sound-absorbing structure is further verified and optimized. The optimization scheme integrating the algorithm and the simulation calculation can ensure the reliability of the optimization results, avoiding the uncertainty and high cost brought by the method that relies purely on experiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a schematic diagram of the low-frequency sound absorption structure of an embodiment of the present application.

[0016] Figure 2 Figure 2 is a structural diagram of the neural network model used to predict sound absorption performance.

[0017] Figure 3 for Figure 1 Sound pressure level diagram of a low- and medium-frequency sound-absorbing structure calculated using the commercial finite element solver COMSOL Multiphysics, at a frequency of 265 Hz.

[0018] Figure 4 This is a comparison chart of the sound absorption coefficient before and after optimization.

[0019] Explanation of the accompanying drawings: 100, low-frequency sound absorbing structure; 1, side seam; 2, extended cavity; 3, circular perforation; 4, resonant cavity; 5, first partition; 6, second partition; 7, third partition. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, Figure 1~4 The technical solutions of the embodiments of the present invention are described clearly and completely.

[0021] Example 1: Figure 1 As shown, the present invention provides a three-dimensionally printed low-frequency sound absorbing structure, the low-frequency sound absorbing structure 100 is a related structure for realizing low-frequency noise suppression, and is prepared by photosensitive resin material through photocuring three-dimensional printing, the low-frequency sound absorbing structure 100 is composed of a side seam 1, an extension cavity 2, a circular perforation 3, a resonance cavity 4, a first baffle 5, a second baffle 6 and a third baffle 7, wherein the side seam 1 is arranged 1 mm above the bottom of the right side of the low-frequency sound absorbing structure 100, and the extension cavity 2 extends along the side seam 1 into the low-frequency sound absorbing structure 100 to form an extension cavity 2; the resonance cavity 4 is arranged above the extension cavity 2, and the bottom surface of the resonance cavity 4 is connected to the top surface of the extension cavity 2 through a circular perforation 3, and the circular perforation 3 is arranged at the end of the extension cavity 2 away from the side seam 1; A partition plate 5, a second partition plate 6 and a third partition plate 7 are evenly and staggeredly arranged in the resonance cavity 4, and the top and bottom surfaces of the first partition plate 5, the second partition plate 6 and the third partition plate 7 are fixedly connected to the top and bottom surfaces inside the resonance cavity 4 respectively, the right side surfaces of the first partition plate 5 and the third partition plate 7 are fixedly connected to the right side surfaces inside the resonance cavity 4, and the left side surface of the second partition plate 6 is fixedly connected to the left side surface inside the resonance cavity 4. The extension lengths of the first partition plate 5, the second partition plate 6 and the third partition plate 7 in the resonance cavity 4 are adjustable, and the first partition plate 5, the second partition plate 6 and the third partition plate 7 are relatively far away from the circular perforation 3 in sequence; the material density of the low-frequency sound absorbing structure 100 is between 1.0g / cm³ and 1.2g / cm³ to increase sound damping, and the Young's modulus is between 2000 MPa and 4000 MPa.

[0022] The length of the resonant cavity 4 in the low-frequency sound absorbing structure 100 isL =40-45mm, width W =23-25mm, height H =23-25mm, height of side seam 1 t =1-2mm, the wall thickness of the resonance cavity 4 b =1mm, round perforation 3, distance from side seam 1 D L =30-40mm, diameter of circular perforation 3 D n =1-2mm.

[0023] The parameters of the first baffle 5, the second baffle 6 and the third baffle 7 in the low-frequency sound absorption structure 100 of the present invention are easy to adjust, which is conducive to optimization using a machine learning method. Combined with parameter optimization, a low-frequency sound absorption structure provided by the present invention can achieve the control of large-wavelength sound waves in a relatively small size, and effectively suppress low-frequency noise.

[0024] Embodiment 2: The present invention also discloses a machine learning optimization method for a low-frequency sound absorption structure based on three-dimensional printing, comprising the following steps: Step 1: Based on the parameters of Example 1, a low-frequency sound absorbing structure 100 for achieving low-frequency sound absorption is constructed. The length of the resonant cavity 4 in the low-frequency sound absorbing structure 100 is L =42mm, width W =24mm, height H =24mm, height of side seam 1 t =2mm, the wall thickness of the resonance cavity 4 b =1mm, round perforation 3, distance from side seam 1 D L =35mm, diameter of circular hole 3 D n =2mm.

[0025] Step 2, finite element calculation and data set collection: The data set uses the commercial finite element solver COMSOL Multiphysics to simulate and calculate the low-frequency sound absorption structure 100. The entire model uses hard boundaries to limit the air domain. The side seam 1 and the circular perforation 3 are selected as narrow areas. At the same time, the circular perforation 3 uses the thermoviscous acoustic interface, and a plane wave with an amplitude of 1 Pa is used to simulate the incident harmonic. The Young's modulus attenuation coefficient of the metamaterial is adjusted between 0.02 and 0.3. Set and record the lengths of the first baffle 5, the second baffle 6 and the third baffle 7, calculate the sound absorption performance of the low-frequency sound absorption structure 100 from 200 Hz to 350 Hz, and record the sound absorption performance in steps of 5 Hz; record the sound absorption coefficients of 31 frequencies corresponding to each group of 3 geometric parameters to form a complete data set; the data set contains the geometric parameters of the input features and the sound absorption coefficient of the target output, which is used for the subsequent training and verification of the machine learning model. The neural network structure is as follows Figure 2 As shown; like Figure 3 The sound pressure level diagram shown in the figure shows that compared with the sound pressure of 90dB at the entrance of the sound source, the sound pressure is concentrated in the resonant cavity area and significantly increased to 106dB, an increase of 17%, indicating that the sound energy is effectively coupled and controlled in this area; the first baffle 5, the second baffle 6 and the third baffle 7 further optimize the propagation mode of the sound wave in the cavity; Step 3, performing machine learning optimization of the sound absorption performance of the low-frequency sound absorption structure 100 based on a multi-layer perceptron and a genetic algorithm, specifically, comprises the following sub-steps: 3.1. Construct a multi-layer perceptron neural network model to model the mapping relationship between geometric parameters and sound absorption coefficients, train the model using the data set collected in step 2, and use cross-validation to evaluate the generalization performance of the model, thereby optimizing the prediction ability of the model; The structure of the multi-layer perceptron neural network model is as follows Figure 2 As shown, the model structure includes: Input layer: The input data includes three features, which are the extension lengths of the first partition 5, the second partition 6 and the third partition 7 in the resonant cavity 4; Hidden layer: Two hidden layers are set, and ReLU activation function is used after each hidden layer. The first hidden layer contains 64 neurons and the second hidden layer contains 128 neurons. Dropout layer: A Dropout layer is set after each hidden layer with a Dropout probability of 0.5 to reduce overfitting; Output layer: finally outputs 31 values, representing the sound absorption performance in the range of 200Hz to 350Hz, with a step size of 5Hz; Model training and validation are performed based on the data set collected in step 2. The process includes: Use mean square error MSE as the loss function: ; in, n is the total number of samples in the dataset, n =9540; y i is the actual value, is the predicted value; is the L2 regularization term, which is used to prevent overfitting. l is the regularization coefficient, oh Represents the weight parameters in the neural network; The L2 regularization formula is as follows: ; in, R (ω) represents the regularization term, oh Represents the weight parameters in the neural network; l is the regularization coefficient, set l =10 -5 ; oh j For the j Weight parameters; p is the total number of parameters; The Adam optimizer is used to optimize the parameters of the neural network. The update formula includes: (1) Calculation of first-order and second-order momentum estimates of gradients: m t =β 1 m t-1 +(1 -β 1) g t v t =β 2 v t-1 +(1 -β 2) g t 2 in, t is the number of iterations; m t For the t The first-order momentum estimate of the gradient of the iteration, representing the moving average; v t For the t The second-order momentum estimate of the gradient of the iteration, which represents the moving average of the square; m t-1 , v t-1 The first t -1 iteration of gradient first-order momentum estimation and gradient second-order momentum estimation; β 1 and β 2 is the attenuation coefficient, which is β 1=0.9, β 2=0.999; g t For the t The gradient at iteration ; (2) Deviation correction: , ; in, is the first-order momentum after bias correction; is the bias-corrected second-order momentum; and They are β 1 and β 2 of t The second square represents β 1 and β 2 Pass t The attenuation effect of the iterations; (3) Parameter update rules: ; in, i t It is t Update the model parameters of the iteration, i t+1 The t +1 update iteration of model parameters; or is the learning rate, set to or =0.001; is a smoothing term, and its value is = 10 -8 , used to avoid the denominator being zero; The model validation uses the KFold cross-validation method, which divides the data set into 5 subsets and uses 5-fold cross-validation for training and validation. The cross-validation calculation formula is as follows: ; in, K Indicates the number of cross-validation folds, value K =5, score k For the k The verification score of the fold; 3.2. Use genetic algorithm to optimize geometric parameters and output optimized geometric parameters. The genetic algorithm sets the initial population size to 100 and the number of genetic iterations to 40 generations. The following steps are used to optimize geometric parameter data: (1) Constructing fitness function The extended lengths of the first baffle 5, the second baffle 6 and the third baffle 7 of the low-frequency sound absorbing structure 100 in the resonant cavity 4 are used as inputs, and the sound absorption coefficient of the low-frequency sound absorbing structure 100 at multiple frequencies is predicted using the trained multi-layer perceptron model; the fitness value is determined by calculating the total sound absorption coefficient and combining the sound absorption performance near the target low frequency of 200 Hz; the fitness value is expressed by the following formula: ; in, mis the number of frequency points, and the frequency points are selected in the range of 200Hz to 350Hz with a step size of 5Hz. m =31; a i It is i The sound absorption coefficient of each frequency; f peak is the frequency Hz corresponding to the maximum sound absorption coefficient; f target is the target frequency, i.e. 200Hz; d is the penalty factor, with a value of d =0.2, used to adjust the trade-off between the total sound absorption coefficient and the target frequency deviation; The sound absorption coefficient is calculated using the following formula: ; Among them, the reflection coefficient R Defined as ; Z H is the acoustic impedance of the sound absorbing structure; Z 0= r 0 c 0 is the characteristic impedance of air, where the density of air r 0=1.21 kg / m 3 , the speed of sound in air c 0=343 m / s ; (2) Based on the fitness function, simulate the natural selection process for optimization, including: Crossover operation: The two-point crossover operation cxTwoPoint is used to cross the individuals, with a crossover probability of 0.5; two crossover points are randomly selected c 1 and c 2 pairs of offspring O 1 and O The gene expression of 2 is updated as follows: O 1= P 1[: c 1]+ P 2[ c 1: c 2]+ P 1[ c 2:] O 2= P 2[: c 1]+ P 1[ c 1: c 2]+ P 2[ c 2:] in, P 1 andP 2 is the gene sequence of two parent individuals, [: c 1] is from the beginning of the sequence to the intersection point c 1 before the part; [ c 1: c 2] For the sequence from the intersection c 1 to the intersection c 2 part between; [ c 2:] is the sequence from the intersection c 2 to the end of the sequence; Mutation operation: The individual is mutated through the Gaussian mutation operation mutGaussian, with a mutation probability of 0.2; for individual I =[ x 1, x 2, x 3], each gene x i Gaussian mutation occurs with probability 0.2: x’ = x + N (0, s 2 ) in, N (0, s 2 ) has a mean of 0 and a variance of s 2 Gaussian distributed noise; Selection operation: Through the tournament selection operation selTournament, the tournament size is 3, and 3 individuals are randomly selected from the population { I 1, I 2, I 3}, calculate its fitness value F , and select the one with the highest fitness: I selected =arg max i∈{1,2,3} F ( I i ); in, I i Indicates the extracted i individual; F ( I i ) is the fitness function; I i The fitness value is determined by the fitness function F ( I i ) is calculated, arg max i∈{1,2,3} F ( I i ) means in the set { I 1, I 2, I 3} Select the function F ( I i ) The individual index with the maximum value i .

[0026] Step 4: Figure 4 As shown, the optimized geometric parameters are substituted into COMSOL Multiphysics for recalculation and verification, and the final sound absorption coefficient distribution curve is obtained. The sound absorption performance is compared with that of the initial geometric parameters to verify the optimization effect. like Figure 4 As shown in the figure, the sound absorption coefficient of the sound absorption structure before and after optimization is compared, and the effect is: the peak value increases from 0.8604 to 0.9649, an increase of 12.2%; the 3dB bandwidth is widened from 51.4Hz to 55.9Hz, an increase of 8.8%; the center frequency decreases from 292Hz to 267Hz, a decrease of 8.6%. It can be seen that the sound absorption coefficient of the optimized structure is improved, the effective sound absorption range is expanded and shifted to low frequencies, which meets the design goals.

[0027] The present invention relates to the field of acoustics, and in particular to the quantitative analysis of the interaction between sound waves and sound-absorbing structures and its application in the calculation of sound absorption coefficients. In order to place practical applications within the basic acoustic theory framework, the present invention discusses the interaction between sound waves and materials, which is quantitatively described by the key parameter of acoustic impedance. In acoustic theory, acoustic impedance Z H It is used to describe the response characteristics of a material to external acoustic excitation. For the calculation of the sound absorption coefficient α of the acoustic metamaterial under normal incidence conditions, the present invention adopts the following formula: ; Among them, the reflection coefficient R Defined as ; Z H is the acoustic impedance of the sound absorbing structure; Z 0= r 0 c 0 is the characteristic impedance of air, and its value is determined by the density of air. r 0 and the speed of sound in air c 0 jointly determine, specifically, the density of air r 0=1.21 kg / m 3 , the speed of sound in air c0=343 m / s ; When the impedance of the sound absorbing structure Z H Impedance to air Z 0, a perfect vibration absorption effect can be achieved. Accurately controlling the acoustic impedance of the sound absorbing structure plays a vital role in optimizing its sound absorption performance. The present invention is designed as follows Figure 1 A low-frequency sound absorbing structure is shown. In order to avoid parameter redundancy, the acoustic impedance of the sound absorbing structure is controlled by designing the lengths of the first baffle 5, the second baffle 6 and the third baffle 7 in the cavity.

[0028] In the entire optimization workflow, the machine learning model is combined with the genetic algorithm. Through model training, cross-validation, iterative optimization and finite element simulation, a small-size structure that can meet the low-frequency sound absorption performance requirements and has good scalability is finally obtained. Figure 4 As shown, the formula The calculated sound absorption coefficient can be expressed by a two-dimensional curve. The peak value of the sound absorption coefficient of the optimized structure is increased by 12.2%, and the sound absorption effect is optimized; the 3dB bandwidth is expanded by 8.8%, and the effective sound absorption range is expanded; the center frequency is reduced by 8.6%, shifting to low frequency, which meets the design goals.

[0029] The above are preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A machine learning optimization method for low-frequency sound absorption structure based on three-dimensional printing, characterized in that: Here are the steps: Step 1, constructing a low-frequency sound absorbing structure (100) for achieving low-frequency sound absorption: the low-frequency sound absorbing structure (100) is made of a photosensitive resin material through photocuring three-dimensional printing, and the low-frequency sound absorbing structure (100) is composed of a side seam (1), an extended cavity (2), a circular perforation (3), a resonant cavity (4), a first baffle (5), a second baffle (6) and a third baffle (7), wherein the side seam (1) is arranged 1 mm above the bottom of the right side surface of the low-frequency sound absorbing structure (100), and the extended cavity (2) extends along the side seam (1) into the low-frequency sound absorbing structure (100) to form an extended cavity (2); the resonant cavity (4) is formed by a first baffle (5), a second baffle (6) and a third baffle (7). The cavity (4) is arranged above the extended cavity (2); the bottom surface of the resonant cavity (4) and the top surface of the extended cavity (2) are connected via a circular perforation (3); the circular perforation (3) is arranged at an end of the extended cavity (2) away from the side seam (1); the first baffle (5), the second baffle (6) and the third baffle (7) are evenly staggered in the resonant cavity (4); the first baffle (5), the second baffle (6) and the third baffle (7) are relatively far away from the circular perforation (3) in sequence; the material density of the low-frequency sound absorbing structure (100) is between 1.0 g / cm³ and 1.2 g / cm³, and the Young's modulus is between 2000 MPa and 4000 MPa; Step 2: Dataset: Use the commercial finite element solver COMSOL Multiphysics to simulate and calculate the low-frequency sound absorption structure (100), set and record the lengths of the first baffle (5), the second baffle (6) and the third baffle (7), calculate the sound absorption performance of the low-frequency sound absorption structure (100) from 200 Hz to 350 Hz, and record the sound absorption performance in steps of 5 Hz; record the sound absorption coefficients of 31 frequencies corresponding to each group of 3 geometric parameters to form a complete data set; the data set contains the geometric parameters of the input features and the sound absorption coefficient of the target output, which is used for the subsequent training and verification of the machine learning model; Step 3, performing machine learning optimization of the sound absorption performance of the low-frequency sound absorption structure (100) based on a multi-layer perceptron and a genetic algorithm, specifically, comprising the following sub-steps: 3.

1. Construct a multi-layer perceptron neural network model to model the mapping relationship between geometric parameters and sound absorption coefficients, train the model using the data set collected in step 2, and use cross-validation to evaluate the generalization performance of the model, thereby optimizing the prediction ability of the model; 3.

2. Use genetic algorithm to optimize geometric parameters and output the optimized geometric parameters; Step 4: Substitute the optimized geometric parameters into COMSOL Multiphysics for recalculation and verification, obtain the final sound absorption coefficient distribution curve, and compare it with the sound absorption performance of the initial geometric parameters to verify the optimization effect.

2. The machine learning optimization method for low-frequency sound absorption structure based on three-dimensional printing according to claim 1, characterized in that: The length of the resonant cavity (4) in the low-frequency sound absorbing structure (100) is L =40-45mm, width W =23-25mm, height H = 23-25 ​​mm, height of the side seam (1) t = 1-2 mm, the wall thickness of the resonant cavity (4) b = 1mm, circular perforation (3) distance from side seam (1) D L = 30-40 mm, diameter of the circular perforation (3) D n =1-2mm.

3. The machine learning optimization method for low-frequency sound absorption structure based on three-dimensional printing according to claim 2, characterized in that: The length of the resonant cavity (4) in the low-frequency sound absorbing structure (100) is L =42mm, width W =24mm, height H = 24 mm, height of side seam (1) t = 2 mm, the wall thickness of the resonant cavity (4) b = 1mm, circular perforation (3) distance from side seam (1) D L = 35 mm, diameter of the circular perforation (3) D n =2mm.

4. The machine learning optimization method for low-frequency sound absorption structure based on three-dimensional printing according to claim 1, characterized in that: The top surface and bottom surface of the first partition plate (5), the second partition plate (6) and the third partition plate (7) are respectively fixedly connected to the top surface and bottom surface inside the resonance cavity (4).

5. The machine learning optimization method for low-frequency sound absorption structure based on three-dimensional printing according to claim 1, characterized in that: The right side surfaces of the first partition plate (5) and the third partition plate (7) are fixedly connected to the right side surface inside the resonance cavity (4), and the left side surface of the second partition plate (6) is fixedly connected to the left side surface inside the resonance cavity (4).

6. The machine learning optimization method for low-frequency sound absorption structure based on three-dimensional printing according to claim 1, characterized in that: The first partition plate (5), the second partition plate (6) and the third partition plate (7) have adjustable extension lengths in the resonance cavity (4).

7. The machine learning optimization method for low-frequency sound absorption structure based on three-dimensional printing according to any one of claims 1 to 6, characterized in that: In the calculation process of the commercial finite element solver COMSOL Multiphysics in step 2, the entire model uses hard boundaries to restrict the air domain. The side slits (1) and circular perforations (3) are selected as narrow areas. At the same time, the circular perforations (3) use the thermoviscous acoustic interface, and a plane wave with an amplitude of 1 Pa is used to simulate the incident harmonics. The Young's modulus attenuation coefficient of the metamaterial is adjusted between 0.02 and 0.

3.

8. The machine learning optimization method for low-frequency sound absorption structure based on three-dimensional printing according to any one of claims 1 to 6, characterized in that: The model structure of the multilayer perceptron neural network model in step 3.1 includes: Input layer: The input data includes three features, namely, the extension lengths of the first partition (5), the second partition (6), and the third partition (7) in the resonant cavity (4); Hidden layer: Two hidden layers are set, and ReLU activation function is used after each hidden layer. The first hidden layer contains 64 neurons and the second hidden layer contains 128 neurons. Dropout layer: A Dropout layer is set after each hidden layer with a Dropout probability of 0.5 to reduce overfitting; Output layer: The final output is 31 values, representing the sound absorption performance in the range of 200Hz to 350Hz, with a step size of 5Hz.

9. The machine learning optimization method for low-frequency sound absorption structure based on three-dimensional printing according to any one of claims 1 to 6, characterized in that: The model training and verification process of the multi-layer perceptron neural network model in step 3.1 includes: Use mean square error MSE as the loss function: ； in, n is the total number of samples in the data set, taking n =9540; y i is the actual value, is the predicted value; is the L2 regularization term, which is used to prevent overfitting. λ is the regularization coefficient, ω Represents the weight parameters in the neural network; The L2 regularization formula is as follows: ； in, R(ω) represents the regularization term, ω Represents the weight parameters in the neural network; λ is the regularization coefficient, and its value is λ =10 -5 ; ω j For the j weight parameters; p is the total number of parameters; The Adam optimizer is used to optimize the parameters of the neural network. The update formula includes: (1) Calculation of first-order and second-order momentum estimates of gradients: m t =β 1 m t-1 + （1 -β 1） g t v t =β 2 v t-1 + （1 -β 2） g t 2 in, t is the number of iterations; m t For the t The first-order momentum estimate of the gradient of the iteration, representing the moving average; v t For the t The second-order momentum estimate of the gradient of the iteration, which represents the moving average of the square; m t-1 , v t-1 The t -1 iteration of gradient first-order momentum estimation and gradient second-order momentum estimation; β 1 and β 2 is the attenuation coefficient, which is β 1=0.9, β 2=0.999; g t For the t The gradient at iteration ; (2) Deviation correction: ， ； in, is the first-order momentum after bias correction; is the bias-corrected second-order momentum; and They are β 1 and β 2 of t The second square represents β 1 and β 2 After t The attenuation effect of the iterations; (3) Parameter update rules: ； in, θ t It is t Update the model parameters of the iteration, θ t+1 The t +1 update iteration of model parameters; η is the learning rate, set to η =0.001; is the smoothing term, The value is = 10 -8 , used to avoid the denominator being zero; The model validation uses the KFold cross-validation method, which divides the data set into 5 subsets and uses 5-fold cross-validation for training and validation. The cross-validation calculation formula is as follows: ； in, K Indicates the number of cross-validation folds, value K =5, score k For the k The verification score of the fold.

10. The machine learning optimization method for low-frequency sound absorption structure based on three-dimensional printing according to any one of claims 1 to 6, characterized in that: In the genetic algorithm described in step 3.2, the initial population size is set to 100, the number of genetic iterations is set to 40, and the following steps are used to optimize the geometric parameter data: (1) Constructing fitness function The extended lengths of the first baffle (5), the second baffle (6) and the third baffle (7) of the low-frequency sound absorbing structure (100) in the resonant cavity (4) are used as inputs, and the sound absorption coefficient of the low-frequency sound absorbing structure (100) at multiple frequencies is predicted using a trained multi-layer perceptron model; the fitness value is determined by calculating the total sound absorption coefficient and combining the sound absorption performance near the target low frequency of 200 Hz; the fitness value is expressed by the following formula: ； in, m is the number of frequency points, and the frequency points are selected in the range of 200Hz to 350Hz with a step size of 5Hz. m =31; a i It is i The sound absorption coefficient of each frequency; f peak is the frequency Hz corresponding to the maximum sound absorption coefficient; f target is the target frequency, i.e. 200 Hz; δ is the penalty factor, with a value of δ =0.2, used to adjust the trade-off between the total sound absorption coefficient and the target frequency deviation; The sound absorption coefficient is calculated using the following formula: ； Among them, the reflection coefficient R Defined as ; Z H is the acoustic impedance of the sound absorbing structure; Z 0= ρ 0 c 0 is the characteristic impedance of air, where the density of air ρ 0=1.21 kg / m 3 , the speed of sound in air c 0=343 m / s ; (2) Based on the fitness function, simulate the natural selection process for optimization, including: Crossover operation: The two-point crossover operation cxTwoPoint is used to cross the individuals, with a crossover probability of 0.5; two crossover points are randomly selected c 1 and c 2 pairs of offspring O 1 and O The gene expression of 2 is updated as follows: O 1= P 1[: c 1]+ P 2[ c 1: c 2]+ P 1[ c 2:] O 2= P 2[: c 1]+ P 1[ c 1: c 2]+ P 2[ c 2:] in, P 1 and P 2 is the gene sequence of two parent individuals, [: c 1] is from the beginning of the sequence to the intersection point c 1 before the part; [ c 1: c 2] For the sequence from the intersection c 1 to the intersection c 2 part between; [ c 2:] is the sequence from the intersection c 2 to the end of the sequence; Mutation operation: The individual is mutated through the Gaussian mutation operation mutGaussian, with a mutation probability of 0.2; for individual I =[ x 1, x 2, x 3], each gene x i Gaussian mutation occurs with probability 0.2: x’ = x + N （0， σ 2 ） in, N (0, σ 2 ) has a mean of 0 and a variance of σ 2 Gaussian distributed noise; Selection operation: Through the tournament selection operation selTournament, the tournament size is 3, and 3 individuals are randomly selected from the population { I 1, I 2, I 3}, calculate its fitness value F , and select the one with the highest fitness: I selected =arg max i∈{1,2,3} F ( I i ) in, I i Indicates the extracted i individual; F ( I i ) is the fitness function; I i The fitness value is determined by the fitness function F ( I i ) is calculated, arg max i∈{1,2,3} F ( I i ) means in the set { I 1, I 2, I 3} Select the function F ( I i ) The individual index with the maximum value i .

Images